Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
be31f6af89 | ||
|
|
7a4b7c6db8 | ||
|
|
086c735c65 | ||
|
|
d4adb53a3a | ||
|
|
50acdc8216 | ||
|
|
2075d235d8 | ||
|
|
452d8e3895 | ||
|
|
d32925cccf | ||
|
|
f8b54ef708 | ||
|
|
a19dc6c5df | ||
|
|
124beb46db | ||
|
|
1121157938 | ||
|
|
e3aba0a637 | ||
|
|
3edb4468a8 | ||
|
|
699a827cae | ||
|
|
765e374584 | ||
|
|
2ab57d9a7e | ||
|
|
17dffac1ea | ||
|
|
36843e4bc9 | ||
|
|
33a0dbd34a | ||
|
|
80ae3decdd | ||
|
|
caef9a0ee3 | ||
|
|
72c827dddf | ||
|
|
498e09bb15 | ||
|
|
68d1f82a2e | ||
|
|
fdf43b197f | ||
|
|
7e2c824d4f | ||
|
|
8890c3ad13 | ||
|
|
f328406bb5 | ||
|
|
6114914dd6 | ||
|
|
4932ad4162 | ||
|
|
a3b117dafc | ||
|
|
3469a74cc1 | ||
|
|
b639c8945d | ||
|
|
9cd39f6ce8 | ||
|
|
d4cfd32c9a | ||
|
|
8215b7a9c5 | ||
|
|
3dfd44ba88 | ||
|
|
3414a19ce6 | ||
|
|
50a78a6917 | ||
|
|
1877ca1fa7 | ||
|
|
57bda29db8 | ||
|
|
3343762c70 | ||
|
|
342da7c353 | ||
|
|
da105160a8 | ||
|
|
977e462e76 | ||
|
|
57134cf36e | ||
|
|
c19a072a3a | ||
|
|
cd8a1be568 | ||
|
|
f968aeded8 | ||
|
|
fb71a02756 | ||
|
|
c8e65f12a6 | ||
|
|
739e56c5cf | ||
|
|
ade74cd636 | ||
|
|
48830c1afb | ||
|
|
b65481cb24 | ||
|
|
7d54941b75 | ||
|
|
5cbc6edce2 | ||
|
|
6b93bcb4c5 | ||
|
|
d49f2d5792 | ||
|
|
bfb47f3a8e | ||
|
|
cb86034de9 | ||
|
|
0d7c2e140b | ||
|
|
eefa7082ed | ||
|
|
8acd7b9d9f | ||
|
|
f026d3eebc | ||
|
|
1b3360dc99 | ||
|
|
16a736a2a9 | ||
|
|
8663eba113 | ||
|
|
f40ddf5f8e | ||
|
|
57e32ab64f | ||
|
|
483c3055b2 | ||
|
|
ca1e137a54 | ||
|
|
a7506952c8 | ||
|
|
dd7d8eff2d | ||
|
|
b9c6d87a2d | ||
|
|
94d53d1152 | ||
|
|
0037bde2aa | ||
|
|
1d88d787a3 | ||
|
|
987f7b8b04 | ||
|
|
9bc0cfe652 | ||
|
|
044d41ad06 | ||
|
|
b08b385e76 | ||
|
|
61b3050174 | ||
|
|
7b57d70e31 | ||
|
|
832cb1637b | ||
|
|
6290f66d03 | ||
|
|
f8f9896d38 | ||
|
|
be24b0a8dc | ||
|
|
34204d9993 | ||
|
|
3e6566af4f | ||
|
|
1183919964 | ||
|
|
f0a60da2e2 | ||
|
|
5d0f2c6380 | ||
|
|
495f0cc3f6 | ||
|
|
ed220c3c7d | ||
|
|
8e700d485c | ||
|
|
8f87dcce67 | ||
|
|
9e6949ec60 | ||
|
|
36ee3343a0 | ||
|
|
f1e0de5f2d | ||
|
|
b941c3fdb8 | ||
|
|
b79aed8569 | ||
|
|
ec61e9c2ca | ||
|
|
1d75934e45 | ||
|
|
882caa1d12 | ||
|
|
1301aa1b40 | ||
|
|
e3ed8e80f2 | ||
|
|
7b3266e7d8 | ||
|
|
bc6e2863dc | ||
|
|
da51a8b7fa | ||
|
|
46f96f7fc8 | ||
|
|
0e3651b475 | ||
|
|
b228f2f9fe | ||
|
|
9d5dc75eca | ||
|
|
7cb3e81890 | ||
|
|
968bad2548 | ||
|
|
b942b2b9f0 | ||
|
|
725af08c90 | ||
|
|
c10354abff |
No files matched your search
@@ -0,0 +1,392 @@
|
||||
# Architecture
|
||||
> Part of [AGENTS.md](../AGENTS.md) — project guidance for AI coding agents.
|
||||
|
||||
## Directory Structure
|
||||
|
||||
```
|
||||
plan2code/
|
||||
├── src/ # Source workflow prompts (14 markdown files)
|
||||
│ ├── plan2code-0-pathfinder-references/ # Reference files for pathfinder skill
|
||||
│ │ ├── brief.md # Dated plain-English decision briefs
|
||||
│ │ ├── chart.md # MODE A: destination + frontier grills, templates
|
||||
│ │ ├── github-issues.md # Issue-backed map (loaded only when Backend is github)
|
||||
│ │ ├── grilling.md # Folded-in grilling + domain-modeling
|
||||
│ │ ├── questions.md # On-disk question-file format + markers
|
||||
│ │ ├── resolve.md # Per-type resolution + graduating the fog
|
||||
│ │ ├── handoff.md # Clearing gate + PLAN-DRAFT handoff
|
||||
│ │ └── trail.md # Every-response map visual + pathed resume command
|
||||
│ ├── shared-references/ # Reference files shared across skills
|
||||
│ │ └── building-habits.md # Find the cause, test first, pin behaviour (quick-task, implement, implement-review)
|
||||
│ ├── plan2code-review-references/ # Reference files for review skill
|
||||
│ │ ├── verification-protocol.md # Deep verification + confidence calibration
|
||||
│ │ ├── dimensions.md # 11 dimensions with detailed checklists
|
||||
│ │ ├── false-positives.md # Known false-positive patterns
|
||||
│ │ ├── reviewer-brief.md # Fill-in brief for the one fresh helper that runs the analysis
|
||||
│ │ └── session-end.md # Next-step routing at review session end
|
||||
│ ├── plan2code-init-update-references/ # Reference files for init-update skill
|
||||
│ │ └── ai-agent-file-sync.md # Step 7: replace AI configs with AGENTS.md refs
|
||||
│ └── plan2code-4-finalize-references/ # Reference files for finalize skill
|
||||
│ └── community-feedback-submission.md # STEP 6.5 payload schema + submission tiers
|
||||
├── plan2code-loop/ # Autonomous loop CLI tool (Node.js/TypeScript)
|
||||
│ ├── src/ # TypeScript source
|
||||
│ └── dist/ # Built output (tsup)
|
||||
├── plan2code-bot/ # Autonomous end-to-end workflow test runner (TypeScript, tsup, Claude Agent SDK, vitest); user docs in .readme/test-bot.md
|
||||
├── plan2code-metrics/ # Recursive self-improvement toolchain
|
||||
│ ├── src/ # TypeScript source
|
||||
│ │ └── prompts/ # Internal AI prompt templates (no char limit)
|
||||
│ └── dist/ # Built output (tsup)
|
||||
├── src/statusline-claude/ # Claude CLI status line (Node.js, zero deps, single file)
|
||||
│ ├── statusline.js # Self-contained: config, git, formatters, render
|
||||
│ └── statusline-config.json # Default config template
|
||||
├── src/launcher/ # Global `plan2code` command (Node.js, zero deps)
|
||||
│ ├── plan2code.js # Opens /plan2code in Claude Code or Devin in the cwd (or a picked folder)
|
||||
│ ├── models.json # Curated model menu, copied to ~/.plan2code/bin/ on install
|
||||
│ └── plan2code.ico # Desktop shortcut icon (Windows)
|
||||
├── src/web-console/ # Local browser UI bundled into every skill (Node.js, zero deps, no build)
|
||||
│ ├── console.mjs # CLI the agent drives: open, post, wait, chat, keep, status, stop, help
|
||||
│ ├── server.mjs, routes.mjs, static.mjs, cmd-*.mjs, picker.mjs, and the by-job files (files, sessions, patches, scan, inbox, workspace, settings)
|
||||
│ ├── console.md, console-*.md, notes/, building*.md # Agent-facing contract (console.md read once, the rest on demand)
|
||||
│ └── public/ # Page assets served to the browser
|
||||
├── scripts/ # Development scripts
|
||||
│ ├── bench-web-console.mjs # Start-path timing
|
||||
│ ├── capture-screenshots.mjs # Stages web console screens and saves the docs screenshots (needs a local Chrome or Edge, through `playwright-core`)
|
||||
│ ├── browser.mjs # The one place a browser is launched (Chrome, then Edge, through `playwright-core`; `PLAN2CODE_TEST_BROWSER` forces one); page tests, the screenshots and the bench use it
|
||||
│ ├── css-snapshot.mjs # Dev-only: every element's computed style on every screen, both themes; take one before a stylesheet move and `--compare` after
|
||||
│ ├── vendor-codemirror.mjs # Dev-only: bundles the pinned CodeMirror 6 packages with esbuild into `public/vendor/codemirror.esm.js` (installed in a temp folder from `vendor-codemirror-lock.json`, never in the repo)
|
||||
│ ├── check-skill-table.mjs # src/plan2code.md "What each skill reads and writes" table vs each skill's prompt and references
|
||||
│ ├── parse-check.mjs # Imports every shipped browser module as real ESM
|
||||
│ ├── screenshots/ # JSON payloads posted per shot (`ask` reuses `question.json`; `finish` follows `signoff.json`)
|
||||
│ ├── test-web-console-*.mjs, web-console-test-helpers.mjs # Web console suites, split by area (the page tests are `-page-*`, the source shape `-shape`), and their shared setup
|
||||
│ ├── test-launcher.mjs, test-getting-started.mjs # Launcher suite; newcomer docs kept in step
|
||||
│ ├── test-skill-scripts.mjs, test-script-<skill>.mjs, test-git-repo.mjs, skill-script-helpers.mjs, fixture-helpers.mjs # Skill script suites and fixtures
|
||||
│ └── validate-char-count.js # Pre-commit character count validator
|
||||
├── skills/ # Generated, gitignored build output — one Agent Skill per src/ prompt
|
||||
│ └── plan2code-<name>/ # SKILL.md plus references/ and scripts/ where present
|
||||
│ # Generated by npm run build:skills; consumed by skills add
|
||||
├── .husky/ # Git hooks (husky)
|
||||
│ └── pre-commit # Runs character count validation
|
||||
├── .claude/ # Repo-local Claude Code config (NOT installed by install.js)
|
||||
│ └── skills/ # Maintainer-only dev skills, e.g. plan2code-publish/, plan2code-model-update/
|
||||
├── .github/ISSUE_TEMPLATE/ # bug.yml, idea.yml, config.yml (target of the console's feedback button)
|
||||
├── .readme/ # User guides linked from README (web-console.md, web-console-design.md, walkthrough.md, autonomous-loop.md, metrics.md, status-line.md, test-bot.md)
|
||||
├── docs/ # Landing page `index.html` served at plan2code.jparkerweb.com (GitHub Pages, `CNAME`) and assets
|
||||
│ └── screenshots/ # Web console screenshots, <shot>-light.webp and <shot>-dark.webp (generated)
|
||||
├── specs/ # Feature specs (if any in-progress)
|
||||
├── install.js # Interactive installer (Node.js)
|
||||
├── package.json # Root package (husky only, private: true)
|
||||
├── version.json # Version metadata
|
||||
├── CHANGELOG.md, QUICK-REFERENCE.md, LICENSE
|
||||
├── .gitattributes, .editorconfig # Pin LF (see Code Style & Gotchas)
|
||||
├── prototypes/, specs--completed/, dist/ # Local only, gitignored: design prototypes, archived specs, stale pre-2.2 build output. Ignore root dist/.
|
||||
└── README.md # User documentation
|
||||
```
|
||||
|
||||
## Key Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `install.js` | Interactive installer — builds `skills/` from `src/`, then delegates installation to the skills CLI |
|
||||
| `src/plan2code-*.md` | Source workflow prompts (the "source of truth") |
|
||||
| `skills/` | Generated Agent Skills, gitignored build output regenerated by the installer (and `npm run build:skills`) before every `skills add` |
|
||||
| `scripts/validate-char-count.js` | Pre-commit validator ensuring all source prompts ≤ 20,000 chars |
|
||||
| `version.json` | Version metadata (name, version, description) |
|
||||
| `QUICK-REFERENCE.md` | User quick-reference card |
|
||||
| `src/statusline-claude/` | Claude CLI status bar (see Status Line below) |
|
||||
| `src/launcher/plan2code.js` | Global `plan2code` command that opens the dashboard skill in Claude Code, Devin or Codex (installed by `I` and Advanced → `E`; also via Advanced → `D`) |
|
||||
|
||||
## Workflow Prompts (in `src/`)
|
||||
|
||||
| File | Step | Purpose |
|
||||
|------|------|---------|
|
||||
| `plan2code.md` | — | The dashboard: opens the web console's skill menu and launches the picked skill into its own session |
|
||||
| `plan2code-init.md` | Init | Generate AGENTS.md as index + `.agents-docs/` section files (progressive discovery) |
|
||||
| `plan2code-init-update.md` | Update | Update AGENTS.md with learnings; detects and routes edits to `.agents-docs/` files |
|
||||
| `plan2code-0-pathfinder.md` | 0 | Chart a foggy idea as a map (local files, or GitHub Issues) of decision questions under `specs/<idea>/pathfinder/`, resolve them one at a time, hand a seeded PLAN-DRAFT to Step 1 |
|
||||
| `plan2code-quick-task.md` | quick | Lightweight planning for small tasks (standalone — not a pipeline step) |
|
||||
| `plan2code-1-plan.md` | 1 | Requirements analysis & architecture |
|
||||
| `plan2code-1b-revise-plan.md` | 1b | Mid-implementation revisions |
|
||||
| `plan2code-2-document.md` | 2 | Create implementation specs |
|
||||
| `plan2code-3-implement.md` | 3 | Execute implementation (phase by phase) |
|
||||
| `plan2code-3-implement-review.md` | 3 | Execute one phase, run focused review and fixes, then request approval |
|
||||
| `plan2code-review.md` | review | Post-implementation comprehensive review, analysed by one fresh helper when the tool has one (verified in session; the report says who reviewed) |
|
||||
| `plan2code-4-finalize.md` | 4 | Validate, summarize, feedback, archive (steps 1–7, +optional 6.5) |
|
||||
| `plan2code-handoff.md` | handoff | Compact the conversation into a self-contained handoff document for a fresh session |
|
||||
| `plan2code-xray.md` | xray | Explain how and why an area works (files, commits, PRs via `gh` when present), or rank the rough spots worth fixing into `ARCHITECTURE-BRIEF-<date>.md` for Pathfinder or Plan; never edits code |
|
||||
| `plan2code-diagnose.md` | diagnose | Find a bug's cause under the find-the-cause-first habit (`references/building-habits.md`) and write it up as `specs/<bug-name>/DIAGNOSIS-<YYYYMMDD>.md` without fixing it, then offer Quick Task to fix it, or Plan when the fix is big. The dashboard scan reports such a folder as spec state `diagnosed` ("Bug diagnosed"), which lights Quick Task (suggested) and Plan. Once Quick Task marks the diagnosis `Fixed` (nothing past it in the folder) the state is `fixed` ("Bug fixed"): no pipeline card lights, the picker never pre-selects it, and Quick Task offers to archive it with `specs.mjs archive` |
|
||||
| `plan2code-changelog.md` | changelog | Check the CHANGELOG version against the default branch, suggest editable entries for new work, keep `package.json` aligned, offer to commit the result through Git |
|
||||
| `plan2code-git.md` | git | Branches, pull (with conflict help), push, publish and commits (clear message, suggested splits) on the web console's git board, or plain instructions in the terminal (`switch to main`, `commit and push`); asks before every push, publish and delete |
|
||||
|
||||
## Naming Convention
|
||||
|
||||
Workflow files follow a strict naming pattern:
|
||||
- **The hub:** `plan2code.md` (bare name — `bare: true` in `SOURCE_PROMPTS`, no suffix; it is the dashboard the rest hang off, not a step)
|
||||
- **Utilities:** `plan2code-<name>.md` (single dash)
|
||||
- **Numbered steps:** `plan2code-<N>-<name>.md` (single dash, number, single dash)
|
||||
|
||||
Examples:
|
||||
- `plan2code-init.md` (utility)
|
||||
- `plan2code-1-plan.md` (step 1)
|
||||
- `plan2code-1b-revise-plan.md` (step 1b)
|
||||
|
||||
## Reference Files
|
||||
|
||||
Some workflows use companion reference files for depth that does not need to load on every invocation. The orchestrator (main workflow file) loads them via `Read` directives during execution.
|
||||
|
||||
**Pattern:** `src/<source-filename-without-extension>-references/` (e.g., `plan2code-review-references/`). A file several skills read lives in `src/shared-references/` instead and ships to each through `additionalReferences` (e.g., `building-habits.md` into Quick Task, Implement and Implement + Review).
|
||||
|
||||
**How the installer handles them:** the directory is copied verbatim to `skills/<skill-name>/references/`, so `Read references/<file>.md` resolves consistently for every agent. There is one output format, with no flat-file sibling directory or path rewrite.
|
||||
|
||||
Reference files are NOT subject to the 20,000 character limit. The review workflow pioneered this pattern (`verification-protocol`, `dimensions`, `false-positives`, `session-end`); the init-update workflow also uses it (`ai-agent-file-sync` for its Step 7), `plan2code-4-finalize.md` uses it for STEP 6.5 (`community-feedback-submission`), and `plan2code-0-pathfinder.md` leans on it hardest (`brief`, `chart`, `github-issues`, `grilling`, `questions`, `resolve`, `handoff`, `trail` — the orchestrator is a dispatcher, the depth lives in the references). Other workflows can adopt it when a source file carries detail that is only needed some of the time. The implement-review skill is a generated composition: `additionalReferences` in `SOURCE_PROMPTS` packages the canonical implement prompt, review prompt, and review reference directory into its own `references/` directory so those workflows are reused without source duplication.
|
||||
|
||||
## Skill Scripts
|
||||
|
||||
Anything a workflow step decides with one correct answer (parsing a spec's checkboxes, rebuilding Pathfinder's map markers, the commit message, which AI config files exist) lives in a script the agent runs, not in prose it follows. Prose keeps the judgment.
|
||||
|
||||
| Source | Ships to | How |
|
||||
|---|---|---|
|
||||
| `src/skill-scripts/<name>.mjs` | `skills/<skill>/scripts/<name>.mjs` | Shared: a skill lists the ones it runs in `scripts: [...]` on its `SOURCE_PROMPTS` entry. Skills install independently, so each gets its own copy |
|
||||
| `src/skill-scripts/common.mjs` | every skill that has scripts | `SHARED_SCRIPTS_ALWAYS` in `install.js` |
|
||||
| `src/<source>-scripts/<name>.mjs` | `skills/<skill>/scripts/<name>.mjs` | A skill's own scripts, mirroring `-references/`. A name that collides with a shared script is a build error |
|
||||
| `version.json` (repo root) | `skills/<skill>/scripts/version.json` | Copied at build, so an installed skill can report its version |
|
||||
|
||||
| Script | Skills | Does |
|
||||
|---|---|---|
|
||||
| `specs.mjs` | plan, revise-plan, document, implement, implement-review, review, quick-task, finalize, handoff | `list` / `status` (Phase Checklist, groups, task markers, numbering, the implement selection verdict, consistency checks) / `metrics` / `mark` / `archive`. Imports `scanProject()` from the bundled `web-console/scan.mjs`, so the dashboard and the skills share one spec classifier |
|
||||
| `commit-msg.mjs` | implement(-review), review, quick-task, finalize, init-update, git | The `<subject>` / `AI Assisted` commit command (two `-m` flags), with optional `git add` |
|
||||
| `review-scope.mjs` | review, implement(-review), quick-task | Review Mode's git fallback: files, lines, doc share, base branch |
|
||||
| `agents-md.mjs` | init, init-update | AGENTS.md structure, budget, orphans, broken links, always-inline sections |
|
||||
| `agent-files.mjs` | init, init-update | Detect and replace other agents' config files with AGENTS.md pointers |
|
||||
| `pathfinder.mjs` (own) | 0-pathfinder | `reconcile`, `frontier`, `claim`, `resolve`, `rule-out`, `trail`, `gate`, `lint`, `brief-data` |
|
||||
| `feedback-payload.mjs` (own) | 4-finalize | STEP 6.5's payload (real sha256 prompt hashes) and the gh / browser / print submission tiers |
|
||||
| `xray.mjs` (own) | xray | `hotspots` (churn, files changed together, often-changed files with no test, from `git log` over a capped window) and `history <path>` (commits following renames, a blame summary, PR titles and first paragraphs through `gh` when signed in, and which sources were used). Read-only |
|
||||
| `changelog-state.mjs` (own) | changelog | `state`, `bump`, `set-package-version`: the default branch's version, whether the branch's entry can be extended (not released, not on another branch), the file's heading style, the gap since the entry was last touched; only `set-package-version` writes, and only the version field |
|
||||
| `git.mjs` (own) | git | `state`, `plan`, `branch-check`, `init-check`, `delete-check`, `cleanup-list`, `conflicts`, `pr-url`, `classify-error`: the repo snapshot, each action's exact command and confirm text (shared by the terminal and the board), branch-name, delete, cleanup and git init checks, a stopped rebase's conflicts, the pull-request link and git's errors sorted into kinds with a next step. Read-only: the agent runs every command it prints, and `guard()` refuses force push, hook skipping, amend, remote delete and blanket add |
|
||||
|
||||
**Conventions** (`common.mjs`): Node 18+ built-ins only; one JSON object on stdout (`ok: false` plus `error`, `message`, `next` on a handled failure, the same line on stderr); exit 0 ok, 1 crash, 2 bad arguments, 3 not found, 4 invalid or check failed, 5 refused; `--help` documents commands and exit codes; writes take `--dry-run`; `PLAN2CODE_NOW` pins the clock for tests. A SKILL.md names a script as `node "<S>/<name>.mjs"`, where `<S>` is `scripts/` beside it.
|
||||
|
||||
**Tests:** `scripts/test-skill-scripts.mjs` (installer plumbing and the shared scripts), `scripts/test-script-<skill>.mjs` (a skill's own), with fixtures from `scripts/skill-script-helpers.mjs`. Importing that module rebuilds `skills/` unless `npm_lifecycle_event` is `test` (`npm test` has just built it). Git fixtures go through `copyFixture()` (`scripts/fixture-helpers.mjs`): built once per test file, copied per test, since every `git` process costs a few hundred milliseconds on Windows; a remote inside the fixture is added with `slashed()` so the copy's `.git/config` can be pointed at its own origin. They run the built `skills/` tree, and one test fails if any SKILL.md or shipped reference names a `<S>/<name>.mjs` that skill does not ship. The per-skill scripts import `./common.mjs`, which only sits beside them in the built tree, so run them from `skills/`, not `src/`.
|
||||
|
||||
## Repo-Local Skills (`.claude/skills/`)
|
||||
|
||||
Maintainer-only skills committed to the repo but deliberately excluded from the generated `skills/` product artifact:
|
||||
|
||||
- `plan2code-publish/` — publishes a GitHub Release after version files agree.
|
||||
- `plan2code-changelog/` — validates release classification and keeps version files synchronized.
|
||||
- `plan2code-model-update/` — refreshes the launcher's curated model menu (`src/launcher/models.json`) from `devin models list` and Claude Code's documented model aliases: shows a diff, applies only the changes the maintainer approves, validates the file and runs `npm test`. Terminal only, and it never commits.
|
||||
- `sync-repo/` — decrypts the protected upstream-sync workflow in memory.
|
||||
|
||||
Do not run `skills add` against the repository root: recursive discovery also finds these maintainer skills. `install.js` targets `skills/` and passes explicit workflow names instead. Global install/uninstall cleanup removes `plan2code-*` workflow skills from user skill directories; it never operates on this repository's `.claude/skills/` directory, and `sync-repo` intentionally has no `plan2code-` prefix.
|
||||
|
||||
## Web Console
|
||||
|
||||
Optional local browser UI shipped with **every** skill. Source lives in `src/web-console/` and is fanned into each skill by an `additionalReferences: [{ source: 'web-console', target: 'web-console' }]` entry in `SOURCE_PROMPTS`, landing at `skills/<skill>/references/web-console/`. The bare `plan2code` skill is the hub: it opens the console as `--workflow dashboard`, the page draws the skill menu itself (from each `SKILLS` entry's `card` in `public/skills.js`, through `SKILL_CATALOG` in `public/answers.js`, kept in sync with the install set by a test), and a card click reaches the agent as a `{ "i": "__launch", "skill": ..., "workflow": ... }` send — the dashboard then **resumes its own session** under the launched skill's workflow (`open --resume <sid> --workflow <w>` restates `workflow`/`title`/`specDir` on the live server) and runs that skill's file. `plan2code-review` now has a console of its own AND still runs inside builds on the page (a `review` verdict on Implementation's sign-off card, or the **Review it now** button on a finished quick task), so `plan2code-3-implement` and `plan2code-quick-task` also carry `review.md` and the review references, the same way `implement-review` does. `CONSOLE_WORKFLOWS` in `public/answers.js`, built from the same `SKILLS` list, decides whether a copied hand-off asks the next session for the console.
|
||||
|
||||
| File | Role |
|
||||
|---|---|
|
||||
| `console.mjs` | the CLI the agent drives: `open`, `post`, `wait`, `chat` (the instant Quick question check), `keep` (copy a cited note attachment into `specs/<idea>/attachments/`), `delete-spec`, `handoff new`, `delete-handoff` (both on `handoffs.mjs`), `status`, `stop`, `help` (a compact summary for an agent that found the binary but not `console.md`; `help <topic>` prints one contract file, `help topics` lists them). `post --wait <N>` posts and waits in one command |
|
||||
| `server.mjs` | HTTP server, spawned **detached** by `open` (never as a harness background task, which get killed on compaction and at assorted timeouts) |
|
||||
| `public/` (other files) | `index.html`, `favicon.svg` (Planny peeking up from the tab bar, served as `image/svg+xml`) with `favicon.png` (the same icon at 192 px, served as `image/png`) as the fallback, `vendor/marked.esm.js`, the chimes (`start-skill.mp3`, `bootup.mp3`, `start-stop.mp3`, `next.mp3`, `insert.mp3`, `sleeping.mp3`; which moment plays which is `SOUND_EVENTS` in `palette.js`, one switch per event saved in `looks.json`), and a `package.json` that only says `"type": "module"`, so Node (the server and the tests import the pure modules) parses them as ES modules without a reparse warning. The stylesheet is the files in `public/styles/`, joined by the server into the one `/app.css` the page asks for |
|
||||
| `cmd-chat.mjs` | the `chat` command: hand over Quick questions now, never waiting |
|
||||
| `cmd-help.mjs` | the `help` command: the CLI's usage and the contract's topic files; the usage's workflow list and its build sessions come from `WORKFLOWS` and `isBuild()` in `skills.js` |
|
||||
| `cmd-open.mjs` | the `open` command: start or resume a session, its server and the browser; refuses a `--workflow` that `isWorkflow()` does not know (exit 2, naming the valid ones), and asks `startsClean()` (`public/hops.js`) whether a resume blanks the page |
|
||||
| `cmd-post-wait.mjs` | `post` and `wait`: publish a patch, then collect what the person sent |
|
||||
| `cmd-small.mjs` | the small commands: keep, forget, delete-spec, handoff, delete-handoff, status and stop; `handoff new` refuses an unknown `--workflow` the same way `open` does |
|
||||
| `files.mjs` | where the console's files live, how they are written safely, and the argument parser both command lines share |
|
||||
| `inbox.mjs` | the Quick question chat's inbox beside the card slot |
|
||||
| `patches.mjs` | checking and merging an agent's patch into the session state: `validate()` (the house rules; allows `templates` only as `"idea"` on a `text` item, anything else exits 3), the patch merge, `resolveDocFiles()` and `applyPatch()` |
|
||||
| `routes.mjs` | every URL the page can call, in one ordered list (`ROUTES`, walked by `handle()`); `server.mjs` hands each request to it |
|
||||
| `scan.mjs` | what the dashboard knows about the repo: `scanProject()`, `classifySpec()` (a folder's files to a spec state), `TASK_LINE_RE` (re-exported from `spec-files.mjs`) and `removeSpec()` |
|
||||
| `sessions.mjs` | a session's roots and handle files (`repoRoots()`, `healthOk()`, `attachmentName()`: the kept-file name `<slug>-<id8>.<ext>`, the same upload always gets the same name, `readOverview()`) and the console folder's housekeeping: the three sweeps `open` runs fire-and-forget after it prints (`sweepUploads()`, `staleSessions()` / `removeSessions()`, `staleScratch()` / `removeScratch()`) and `cleanupFindings()` / `removeCleanup()` for User Preferences → Cleanup |
|
||||
| `settings.mjs` | the person's saved console settings: Subagents and pull-request hosts |
|
||||
| `spec-files.mjs` | no imports: how a spec's markdown files are read, `MARKERS`, `TASK_LINE_RE`, `TASK_ID_RE`, `CHECKBOX_RE`, `STATUS_RE`, `statusOf()` and `countTasks()`; shared by `scan.mjs`, `patches.mjs` and `src/skill-scripts/specs.mjs` (through `consoleModule()`) |
|
||||
| `static.mjs` | serving the page's own files: `SERVABLE` (the allow-list), `TYPES`, caching and ETags, the accent colors, and `CSS_ORDER` + `joinedStyles()`, the one place the cascade order is stated |
|
||||
| `workspace.mjs` | the session's extra folders, and the folders remembered per project and spec |
|
||||
| `public/app.js` | the page's entry and the only page file that starts anything: the start-up block. `index.html` loads it; it imports `screens/core.js` and the screens beside it |
|
||||
| `public/doc-files.js` | a document as the page shows it, and as a file: blocks, Markdown and HTML download |
|
||||
| `public/hops.js` | no imports: the hop rule, `startsClean(from, to)`, which says whether a hop from one workflow to another starts the new skill on a clean page (to or from the dashboard, into Git, or from one skill into another off a finished screen, but never out of Git or into Review); shared by `cmd-open.mjs`, `server.mjs` (its Ask reset) and `screens/core.js` |
|
||||
| `public/looks.js` | how the page looks and sounds: the saved looks, their sync, and the preferences dialog's swatches |
|
||||
| `public/mention-box.js` | the @name suggestions popover under a text box |
|
||||
| `public/net.js` | the page talking to its own server |
|
||||
| `public/palette.js` | the highlight colors, the sound events and the card widths, as data (importable by Node so a test can check every shade in both themes) |
|
||||
| `public/render.js` | Markdown to DOM, safely: no HTML string is ever produced, only nodes built with `createElement` and `textContent`; also the shared page helpers (`el`, `md`, `copyButton`, `lightDismiss`) |
|
||||
| `public/selectors.js` | what the page reads off its state: the questions, the finish, the scan, who has the ball |
|
||||
| `public/send-state.js` | whether Send is available, and what its button says |
|
||||
| `public/skills.js` | the skill list: every per-skill fact the console uses (card, order, start pose, launch scoring, subagent opt-in, which spec states light its card), data only, imported by the page and by Node; the older tables (`SKILL_CATALOG`, `START_POSES`, `CONSOLE_WORKFLOWS` and the rest, in `answers.js`) are lookups on it. Each entry also carries `weight` (what its launch and `run` score on the meter, or null), `started` and `ran` (the meter's labels for them, or null), `resume` (`"overview"`, `"folder"` or null: what the resume command takes after the skill's command) and an optional `card.help` (Help's line for the card when it differs from `blurb`). `WORKFLOWS` (every entry's workflow, in order) and `isWorkflow()` are what the CLI checks a `--workflow` against. The meter's `WEIGHTS`, `LAUNCH_LABELS` and `RUN_LABELS`, `resumeCommand()`, Help's card list and `cmd-help`'s workflow list are all derived from it, so a new skill is one entry here, not an edit to each of those |
|
||||
| `public/sound.js` | the sound cues: which plays, one at a time, held until the first click |
|
||||
| `public/spec-states.js` | the spec states (`diagnosed`, `fixed`, `exploring`, `mapped`, `planned`, `documented`, `building`, `built`, `unrecognized`): each one's picker label, the card it is the natural next step for and its recommendation, data only; which cards a state lights lives in `skills.js`, how a folder maps to a state in `classifySpec()` in `scan.mjs` |
|
||||
| `public/state.js` | the page's shared state (`page.S` the server's truth, `page.local` what is staged) and the `redraw()` / save hooks every screen calls; defines only |
|
||||
| `public/uploads.js` | pictures and documents attached to a note: chips, trays, re-encoding, upload, retry |
|
||||
| `public/screens/ask.js` | the Ask chat, the Subagents tab, and attaching files to notes |
|
||||
| `public/screens/cards.js` | question cards: every kind, the pager, settled and in-flight records |
|
||||
| `public/screens/cleanup.js` | User Preferences, Cleanup tab |
|
||||
| `public/screens/core.js` | the core every screen sits inside: connection, the render loop, the page chrome and Send; the only file that imports the screens, and only `app.js` imports it |
|
||||
| `public/screens/dashboard.js` | the dashboard: cards, the spec picker, handoff chips, delete, and the first-open wake-up |
|
||||
| `public/screens/docs.js` | documents: tabs, blocks, print and download, and the brief button |
|
||||
| `public/screens/ending.js` | how a session ends: the finished screen, its offers, Stop and the way home |
|
||||
| `public/screens/git-host.js` | hosts the git board: tabs, panels and what each click sends |
|
||||
| `public/screens/help-dialog.js` | the Help dialog and the first-run Welcome (named so it is never confused with the pure help.js) |
|
||||
| `public/screens/looks.js` | User Preferences: looks, sounds and the launcher's model menus |
|
||||
| `public/screens/starting.js` | the launching, starting and waiting screens, with Planny's poses |
|
||||
| `public/screens/workspace.js` | the read-only Workspace of extra folders, and @mentions |
|
||||
| `public/styles/ask.css` | The Ask pane and its Quick question chat |
|
||||
| `public/styles/dashboard.css` | The dashboard: the menu, the spec picker, its confirm and the launching pane |
|
||||
| `public/styles/docs.css` | Documents and the doc tools |
|
||||
| `public/styles/ending.css` | The end of a session: the hand-off and the stopping screen |
|
||||
| `public/styles/git.css` | The git board |
|
||||
| `public/styles/help.css` | The help dialog, its diagrams and its tabs |
|
||||
| `public/styles/looks.css` | The looks button and the highlight swatches |
|
||||
| `public/styles/pieces.css` | Shared pieces: cards, options, settled answers, pager, forms, checklist, markdown and the modal |
|
||||
| `public/styles/planny.css` | Planny the mascot: the flight, his moods and variants, and the wake-up |
|
||||
| `public/styles/poses.css` | The start-screen poses, one per skill. After the dashboard on purpose: its narrow-window rules override the dashboard's |
|
||||
| `public/styles/responsive.css` | Print, then the narrow-window rules: last, so its overrides come after everything they override |
|
||||
| `public/styles/shell.css` | The page shell: banner, top bar and meter, layout, sidebar, aside, footer, waiting and arrival |
|
||||
| `public/styles/tokens.css` | Colours, type, sizes and the light and dark themes: the variables every other file reads |
|
||||
| `public/help.js` | the Help dialog's PURE rules: `HELP_TABS` (18 tabs: ids, order, labels, diagram flags; every tab uses the chosen highlight color; The git board sits right after Watching a build), `helpTabFor()` (which tab opens, FR-8 order, first match wins: finished → Stopping and finishing, server gone or agent adrift → When something looks stuck, opened from the Workspace dialog → Your workspace, then Ask, the Subagents tab → Helpers (subagents), a red-meter dashboard → Session meter, dashboard, a doc or the Overview, a git session → The git board, a build, else What this page is) and `helpKeyTarget()` (roving arrow keys, Home, End, wrapping). No module-scope DOM, so `node --test` covers it |
|
||||
| `git-repo.mjs` | the one read-only reader of a git repository: the worktree status (`countPending()`, behind `pendingFiles()`), the branch table, the default branch, a merge or rebase in progress, the remotes and their web addresses, the last fetch and the pull-request link; `snapshot()` is what `open` and every `reread` store as `state.git`. Every git call carries `GIT_OPTIONAL_LOCKS=0`, so a background look never takes the index lock. Imported by `cmd-open.mjs`, `cmd-post-wait.mjs` and `sessions.mjs`; the git skill's `git.mjs` reaches it through `common.mjs` |
|
||||
| `public/git-board.js` | PURE, one import (`pr-url.js`): the git board's rules from a `state.git` snapshot: branch order and the Remote only fold at `REMOTE_FOLD` 50, whether a new branch name is free, which buttons show and are enabled, whether the board still waits on the agent (`boardAwaiting()`: from a click until the agent's next post, not just until `wait` collects it), the plain sentence each click sends as `reply`, the "Last refreshed" line, which files start ticked in the commit dialog, and the pull-request link; the next step (ten rules, `nextStep()`), the tab that owns it, per-tab badges (`tabBadges()`), the busy mode and per-control gate (`busyMode()`, `controlAllowed()`), the tab to show (`pickTab()`), and the create-panel sources and clean-up groups. `app.js` only renders what it says |
|
||||
| `public/git-board-view.js` | No DOM access of its own: `drawGitBoard(ctx)` draws the tabbed board (header, tab strip with Done with git, the card slot, step strip, Changes / Branches / Sync) from the helpers it is handed (`el`, `md`, `copyButton`), every control through one gate; `screens/git-host.js` hosts it, and `scripts/test-web-console-git-board.mjs` drives it with a recording fake `el` |
|
||||
| `public/pr-url.js` | PURE, no imports: `prUrl()`, the "open a pull request" link for the GitHub, GitLab, Azure DevOps and Bitbucket shapes (`null` for an unknown kind, no web address, or a non-https result). `git-repo.mjs` re-exports it, and the board's base picker rebuilds the link in the browser with the same code |
|
||||
| `public/workspace.js` | PURE, no imports: the Workspace's name rules (`nameProblem()`, `NAME_MAX`, `defaultName()`, `freeName()` for the `-2` suggestion), the footer label and its width tiers (`footerLabel()`, `FOOTER_TIERS`) and `changeLine()`, the `Workspace: …` reply line an agent is handed per change. Imported by the server, `cmd-chat.mjs`, `cmd-post-wait.mjs`, `workspace.mjs` and the page |
|
||||
| `public/meter.js` | PURE, imports only `skills.js`: the session meter. `WEIGHTS` (the events that are not a skill's own launch, merged with each skill's `weight` from `skills.js`; its keys are also `RUN_EVENTS`, the `run` events `post` accepts), `LAUNCH_COUNTED` (workflows whose launch itself scores), the built-phase sizing (`TASK_EVENTS`, the keys of `TASK_BONUS`: `implement-phase` +0 and `implement-review-phase` +1; `isTaskCount()` accepts a whole `tasks` from 1 to `MAX_TASKS` 999; `runPoints()` scores such a run `ceil(tasks / TASKS_PER_POINT)` (3) plus its bonus, and any other run its `WEIGHTS` value), `ANSWERS_PER_POINT` 2 (`answer` entries score per skill run, `floor(count / 2)`), `breakdownFrom()` (the click-the-ring list: one row per scoring entry plus one answers row per skill run), `pointsFrom()` (the count, its sum, folded from `ledger.ndjson` and deduplicated by id, never stored), `levelFor()` with `YELLOW_AT` 5 / `RED_AT` 10, `ringFraction()` (full at `RING_FULL` 15), `WORDS`, `tooltipFor()`, `RED_BANNER` and `meterView()` |
|
||||
| `public/mentions.js` | PURE, no imports: the `@name` popover's logic — `mentionAt()` finds an `@partial` at the caret, `matchNames()` filters the workspace names, `applyMention()` splices a pick in and returns the new caret. Used by the Ask box, notes and text answers |
|
||||
| `public/favicon.js` | The tab icon's status bar. `faviconState({ mood, spin, finished })` (PURE) maps the call `renderStatus()` makes for Planny's line to `busy` (the spinning ring), `ready` (`point`), `attention` (`adrift`, `gone`, or `work` without the ring — the stale line) or `plain` (finished, `happy`); `faviconSvg()` is `FAVICON_BODY` (kept equal to `favicon.svg` by a test) plus a bar along the bottom edge in the `FAVICON_COLORS` color (busy dashed on a white strip, so the states differ by pattern; the rest solid); `setFavicon()` swaps both `<link rel=icon>` hrefs only on a change — the SVG as a data URL, the PNG link drawn through a canvas. Called from `say()` in `renderStatus()`, which runs every second |
|
||||
| `public/subagents.js` | PURE, no imports: the Subagents switch. `SUBAGENT_WORKFLOWS` / `offered()` (the opt-in table: `implement`, `implement-review`, `quick-task`, `review`, `pathfinder`, each with its default instruction), `cleanSetting()` (`{ on, instruction, max }` or `{ error }`: `bad`, `too-long` past 2,000 characters, `max` outside 1-20), `FRAME_LINES`, `blockFor(setting, told)` (the `Subagents:` lines and `subagents` field an agent is owed, given the session setting and its cursor; never says "off" to an agent not told "on"), `checkHelper()` / `checkHelpers()` (the `helpers` house rule) and the page's view rules `showSwitch()`, `switchLabel()`, `helperRows()`, `showTab()`, `CHECKIN_LINE`. Imported by the server, the `cmd-*.mjs` files, `patches.mjs`, `settings.mjs`, the page and the tests; in `SERVABLE` and preloaded |
|
||||
| `handoffs.mjs` | the handoff store, the only code that names, lists, marks, deletes and sweeps handoffs, all in `~/.plan2code/handoffs/` (`PLAN2CODE_HANDOFFS_DIR` for tests; `PLAN2CODE_NOW` pins its clock): `newHandoff()` claims `YYYY-MM-DD-HHmm-handoff` (`-2`, `-3` on a clash, the `.json` created exclusively) and writes only `<id>.json` (`{ v: 1, id, title, worktree, project, spec, workflow, skill, written, fromStop, usedAt }`), the agent writing `<id>.md`; `listHandoffs(worktree)` (unused, same worktree, `.md` present, newest first, title and Next task read off the document); `readHandoffMeta()`, `markHandoffUsed()`; `removeHandoff()` (`HANDOFF_ID` only, regular files, never a link, realpath inside the folder, throws on any refusal); `staleHandoffs()` / `removeHandoffs()` for the sweep |
|
||||
| `notepads.mjs` | the notebook store (the feature is named Notebook; its code, routes and storage folder keep the name `notepad`), the only code that names, reads, writes and removes notebooks, one per folder Plan2Code runs in, in `~/.plan2code/notepads/<folder-name>-<12 hex>/` (`PLAN2CODE_NOTEPADS_DIR` for tests), split into named tabs: `meta.json` (`{ v: 2, folder, created }`), `tabs.json` (`{ v: 1, order, last, tabs: { id: { name, created } } }`) and `tabs/<id>/note.md` with `tabs/<id>/images/`. `notepadKey()` (the folder's basename slug and the first 12 hex of `sha256(foldKey(folder))`), `listTabs()` / `defaultTabId()`, `readNotepad(folder, tab)` (never creates or writes anything; `{ tabs, last, tab }` with the tab's `text`, `savedAt` and `images` repeated at the top), the tab changes `createTab()` / `renameTab()` / `reorderTabs()` / `setLastTab()` / `deleteTab()` (index first, then the folder; names pass `normalizeTabName()`, `TAB_NAME_MAX` 40, any case compared by `nameKey()`, `NOTEPAD_MAX_TABS` 20), `saveNote(folder, tab, text)` (1 MB cap, atomic), `addImage()` / `addThumb()` / `removeImage()` (JPEG bytes only, 200 pictures per tab, UUID names), `imagePath()` (regular files whose realpath stays inside the folder), `staleNotepads(now, maxAgeMs)` (the real folders directly under it named like a key, never a link or a file, whose newest file is at least `maxAgeMs` old, as `{ key, folder, path }` with `folder` from `meta.json` or null), `removeNotepad(key)` (the key checked against `NOTEPAD_KEY_RE`, the path kept inside the notepads folder by `path.relative`, a link refused, then the whole folder removed; User Preferences, Cleanup is its only caller) and `NotepadError` (`code` and `status`, turned into `{ error }` by the `/notepad` routes). **Migration:** a notepad in the first shape (`note.md` and `images/` at the top) reads as one virtual tab, Notes (`LEGACY_TAB_ID`), and writes nothing; its first write moves the files into `tabs/<LEGACY_TAB_ID>/` and writes `tabs.json` last, every step safe to run again after a crash. A `tabs.json` that does not hold up is set aside as `tabs.json.corrupt` and rebuilt from the tab folders on the next write. Every write runs under a `notepad.lock` in the notepad's folder. The agent CLI never imports it: nothing in a notepad reaches the agent |
|
||||
| `public/notepad.js` | PURE, no imports: the Notebook's rules. `SAVE_DEBOUNCE_MS` 800, `RETRY_STEPS_MS` (1 s up to 30 s), `NOTE_MAX_BYTES` / `NOTEPAD_MAX_IMAGES` / `TAB_NAME_MAX` / `NOTEPAD_MAX_TABS` / `IMAGE_ID_RE` / `TAB_ID_RE` (kept equal to `notepads.mjs` by a test), `noteBytes()`, the save-state reducer `nextSave(state, event)` from `SAVE_START` (states `idle`, `pending`, `saving`, `saved`, `failed`, `too-long`; it returns the timer to arm), `saveStatus()` (the status line's words), `unsaved()` (what `beforeunload` asks on), `keepsText()` (unsaved or too long: a reopen never replaces the editor's text then), `tabSwitch()` (whether leaving a tab must save it first), `NOT_LOADED`, `EDITOR_NOT_LOADED`, `errorSentence()` (one sentence per `/notepad` refusal, else a lost connection), the tab rules `cleanTabName()`, `nameTaken()`, `tabNameProblem()`, `moveTab()`, `dropTab()` and the two-confirm delete `nextDelete()` / `DELETE_STAGES`, and `step()` (wrapping through the pictures) |
|
||||
| `public/screens/notepad.js` | the Notebook: `#btn-notepad` in the top bar on every screen (disabled while the server is gone, `renderNotepadButton()` in the render pass), `#notepad-modal`, the one CodeMirror editor (made on first open by a dynamic import of `notepad-editor.js`), the page's view of the notepad as `{ tabs, activeId }`, the name form (New tab and Rename, never `window.prompt`), the in-modal two-step delete, and autosave through `nextSave()` to `POST /notepad/text?tab=<id>`, flushed on close, when the page is hidden and before a switch. The editor stays read-only until the first read lands, so nothing typed into an empty editor is saved over a note. **Every save and every picture is bound to the tab it was made in**: `saveTab` is fixed when the change is made, a picture entry carries its `tab`, and a switch waits for the save (`settled()`), stays put with "Not saved yet, so staying on this tab." when it cannot, and drops a deleted tab's unsaved text without sending it |
|
||||
| `public/notepad-tabs.js` | the tab bar: `createTabs({ onSwitch, onChange })` with `draw(tabs, activeId)` (`role="tab"` buttons, roving `tabindex`, arrow keys, Alt+arrows to reorder, F2 and double-click to rename, native drag and drop with an `.is-drop-before` mark that only a tab drag lights, focus kept across redraws, `#notepad-empty` and `#notepad-body` toggled) and `focusTab()`. No fetches: it calls back, and `screens/notepad.js` owns every request |
|
||||
| `public/notepad-editor.js` | the Notebook's live-preview editor on CodeMirror 6 (`makeCodeMirrorEditor(parent, { onChange, label })` returning `{ getValue, setValue, setReadOnly, focus, destroy }`). A `ViewPlugin` decorates only the lines in view from the Markdown syntax tree: heading line classes `cm-h1` to `cm-h6`, bullets drawn as a widget, the marks around bold, links, quotes and a heading hidden on every line the selection is not on. The editor sits in a shadow root (`.notepad-cm-host`), because CodeMirror writes its rules as a `<style>` element, which `style-src 'self'` refuses, and adopts them as a constructed stylesheet inside a shadow root. `setValue()` is `setState()`: not reported through `onChange`, and the undo history is cleared (so each tab starts with a clean one) |
|
||||
| `public/notepad-editor.css` | the one stylesheet of that shadow root, linked from `notepad-editor.js` (a `<link>` inside the root, in `SERVABLE`, not in `CSS_ORDER`): heading sizes, bullets, quote, code and link looks on the console's tokens (custom properties inherit across the boundary, so both themes work). Rules that meet CodeMirror's own base theme use `div.cm-editor` for the specificity |
|
||||
| `public/vendor/codemirror.esm.js` | CodeMirror 6 (state, view, language, commands, lang-markdown, MIT), bundled into one minified ES module by `scripts/vendor-codemirror.mjs` (sha256 `4ff96d58fc1a5497eb933426bd2d160d2fb0cf490de8bb9302c304096c71c1d4`, the six top-level versions in the script and the file's header comment, everything they pull in pinned by `scripts/vendor-codemirror-lock.json` and installed with `npm ci`, so the same lock gives the same bytes). Never edited by hand: change a version in the script and run `node scripts/vendor-codemirror.mjs --update-lock` (needs npm and network; the packages install in a temp folder, never in the repo), or without the flag to rebuild from the lock |
|
||||
| `public/styles/notepad.css` | the notebook's own rules: the top bar button, the dialog, the tab bar and its tools, the name form, the delete question, the empty state and the pictures. The editor's look is `notepad-editor.css`, inside its shadow root |
|
||||
| `picker.mjs` | the per-OS native folder picker behind **Browse…** (`pickerCommand()` → `{ command, args, env }` or `null`; `pickFolder()` runs it with async `spawn`, so the server keeps serving while the dialog is open). Copied from `src/launcher/plan2code.js` (self-contained CommonJS, so it cannot be shared) with the prompt as a parameter; a drift test keeps the two in step |
|
||||
| `update-check.mjs` | the dashboard's release check, server-only (never in `SERVABLE`): `compareVersions()` (numeric X.Y.Z, `null` otherwise), `latestTag()` (the highest `refs/tags/vX.Y.Z`, peeled `^{}` and pre-release tags skipped), `checkForUpdate({ installed, cacheFile, now, run })` (never throws) and `runLsRemote()` (`git ls-remote --tags` on the repo: no shell, `GIT_TERMINAL_PROMPT=0`, `GCM_INTERACTIVE=never`, SSH `BatchMode` when `GIT_SSH_COMMAND` is unset, `windowsHide`, killed at 10 s; git authenticates itself, the console never touches a credential). The answer, failures included, is cached for an hour in `~/.plan2code/console/update-check.json` (`UPDATE_CHECK_FILE`, in `PROTECTED_CONSOLE_FILES` so no sweep removes it). `server.mjs` starts it after the ready line and never awaits it; `stateFrame()` carries `update: { installed, latest }` only when a newer release exists (its `latest` is part of `haveKey()`, so a page that connected first still gets it), and `GET /version` returns `{ version, latest }`. Tests seed a fresh cached failure in every console home, so no test server reaches the network. The `plan2code` launcher reads the same cache for its terminal release notice (a copy of this module sits in `~/.plan2code/bin/`) |
|
||||
| `public/chat.js` | the Quick question chat's PURE rules, shared by the server and the page: `CHAT_LIMIT` / `CHAT_MAX_CHARS` / `CHAT_MAX_ATTACHMENTS` (the combined image + document cap; `CHAT_MAX_IMAGES` is kept as an alias of it), `chatOffline()` (the server's `409 offline` guard), and the page's view model (`chatView`, `sendState`, `nextAbout`, `contextOptions`, `unreadDot` / `shouldChime`). Ask context is the `{ history, about }` model: `nextAbout()` records the last 3 places visited in `history` and sets `about` only when the person picks one from **+ Add context** (`contextOptions()` lists that history plus *This spec*); dropping it or a successful send clears it, so the page never attaches context on its own. Imports only `answers.js`, no module-scope DOM, so `node --test` covers it |
|
||||
| `public/starters.js` | PURE, no imports: the Role list (`ROLES`, `ROLE_NOT_SET`, `normalizeRole()`, `needsRoleNudge()`: the dashboard banner shows until `looks.json` carries any `role`), the 19 starter templates (Markdown `## heading` sections, shape pinned by a test) and their per-role orders (`TEMPLATES`, `TEMPLATE_ORDERS`, `templatesFor()`, `templateSwap()` for the replace prompt), and the Ask starter sets (`STARTER_SETS`, `STARTER_SET_FOR`, `startersFor()`). Imported by the page's looks and screens and by the tests; in `SERVABLE`, preloaded by `index.html` and parse-checked. The page owns the wording; a skill only flags its fresh-idea `text` card with `"templates": "idea"` |
|
||||
| `public/answers.js` | the page's PURE answer-shaping logic (what an answer reads as, what a placeholder offers, whether a send carries an answer at all). Kept out of the page's entry because `app.js` cannot be imported outside a browser, so anything left in it is untestable. The `scripts/test-web-console-*.mjs` tests import it directly. |
|
||||
| `public/labels.js` | `taskLabel()` / `activityLabel()`: rewrites a build's `Task 4.2 of 6` activity line to `Task 2 of 6` (only for `implement` / `implement-review`; a plan's `Task 2.1` is a real section number). A separate module for the same reason as `answers.js`: pure, so `node --test` can import it |
|
||||
| `public/boot.js` | `playWake()`: the dashboard's first-open wake-up. Self-contained (it owns its timers, the listeners that swallow input mid-run and the one measured glide transform; the page's `stir()` callback times the nudge between the click and the boot, which `screens/dashboard.js` fills with one snore; `skipEl` — the muted Skip button, and Escape — ends the run early with `onSkip` as the cue to silence queued sounds) and free of module-scope DOM access, so it can be imported by the tests and kept out of the screens' render paths; `GLIDE_AT_MS` / `DONE_AT_MS` are its timings |
|
||||
| `console.md` | the core of the agent-facing contract, read once per conversation (every skill ships the same copy, so a dashboard hop never re-reads it): starting, the turn (`post --wait`, the exit codes, handling a send, `settle`), posting, the payload and its kinds, documents (including `file` blocks), the house rules, and an index of the topic files below with the moment each is read. A test caps it at 24,000 characters |
|
||||
| `console-finish.md` · `console-stop.md` · `console-chat.md` · `console-workspace.md` · `console-subagents.md` · `console-launches.md` · `console-meter.md` · `console-attachments.md` · `console-trouble.md` | topic files, each read only when its moment first comes: finishing (the finish and its buttons), stop requests (the way home mid-workflow, `stopWarning`, resuming a pause), Quick questions, the Workspace, standing instructions and helper reports, dashboard launches and the menu payload, the session meter's `run` events (read only when a `run` is refused: the notes inline every `run`), keeping a cited note attachment, and recovery |
|
||||
| `notes/<workflow>.md` | per-workflow notes (`init` for both inits, `pathfinder` with Briefs, `plan`, `revise-plan`, `document`, `implement` for both builds, `quick-task`, `review`, `finalize`, `handoff`, `changelog`, `git`, `xray`, `diagnose`). Each skill's Interface line reads `<D>/console.md` and its own notes file right after `open`; a test checks every skill names one that exists |
|
||||
| `building.md` · `building-review.md` | the build half of the contract, for `implement`, `implement-review` and `quick-task`: progress posts (`agent.activity`, `agent.quietMinutes`, `file` blocks re-read with `refresh`), the chat check between tasks, questions mid-build and stop requests; `building-review.md` is the review run on the page (the sign-off's `review` verdict, **Review it now**, Implement + Review's Stage 2), read only when asked for |
|
||||
|
||||
Key design points:
|
||||
|
||||
- **First-run Welcome.** The first dashboard a person sees (after the wake-up finishes) opens `#welcome-modal`. Any close (button, Esc, backdrop) saves `looks.welcomeSeen: true` to `looks.json`, which survives "Back to default". Help's first tab has a **Show the welcome again** link (`data-action="welcome"`). Logic: `maybeWelcome()` / `openWelcome()` in `screens/help-dialog.js`.
|
||||
- **Top-bar icons.** `#btn-looks` (gear) opens `#looks-modal`, titled User Preferences: Role, Theme, Card width, Highlight color, Sounds and Models. `#btn-feedback` (megaphone) is a plain link to `https://github.com/jparkerweb/plan2code/issues/new/choose`, backed by `.github/ISSUE_TEMPLATE/bug.yml` and `idea.yml` (`config.yml` sets `blank_issues_enabled: false`). `DEFAULT_ACCENT` in `palette.js` is `ocean`.
|
||||
- **Version in Help.** `GET /version` reads `version.json` beside `server.mjs`, falling back to `../../version.json` for a run from `src/` (the `/version` route in `routes.mjs`). `renderHelpVersion()` in `screens/help-dialog.js` fills `#help-version`. `computeExpectedSkills()` in `install.js` injects the root `version.json` into every `references/web-console/`, so a version bump changes every skill.
|
||||
- **Models in User Preferences.** `GET` / `POST /models` in `routes.mjs` read the shipped `~/.plan2code/bin/models.json` and read/write the user's `~/.plan2code/models.json` (`SHIPPED_MODELS_FILE` / `USER_MODELS_FILE` in `files.mjs`). `PLAN2CODE_MODELS_DIR` relocates both for tests. The launcher reads the same two files for its model menu.
|
||||
- **The wait is bounded.** `wait --seconds 240` exits `0` (answers), `10` (still waiting, `message: "Waiting on your answer in the web console"` to relay), `20` (server gone, resume it) or `30` (cancelled). The agent loops. Nothing blocks for the whole time a person takes.
|
||||
- **A turn is one command, and the CLI does the bookkeeping.** Agent speed is model round trips and typed tokens, not the console (`bench-web-console.mjs --roundtrip`: Send→agent ~70 ms, post→page ~180 ms), so the CLI absorbs every step with one right answer: `consume()` marks the agent `working` when it hands over a submit (`markWorking()`), and `wait` hands the turn back (`markWaiting()`) when it starts with an open question, a finish, or on the dashboard or git board; `post --wait <N>` posts and waits in one process; `settle: true | [ids]` (`settleItems()` in `patches.mjs`) records the latest send's cards as answered from their `submitted`; a new or reopened question with no stated status sets `waiting` and waiting drops `quietMinutes` (`settleAgent()`); a doc whose content changed with no `version` moves up one (`mergeDocs()`); a chat reply with no `id` is `r<re>`; doc blocks with `file` (and `select: "tasks"`, doc-level `refresh: true`) are read from the worktree by `resolveDocFiles()` before the merge, refusing paths outside it; and a hop (`__launch`, `__dashboard`, `__commit`, `__pickup`) comes with `resume` (the exact `open --resume` command) and `skillFile` (`hopFor()`), a pick-up also with `handoffFile`. The wait loop's health check runs beside the 50 ms polling instead of blocking it, and is aborted on exit. `help <topic>` prints any contract file; `help topics` lists them. `token` defaults to the option key in the page's `tokenFor()`, and nothing reads `fallbackText`, so the contract no longer asks for either.
|
||||
- **The CLI hands the agent its terminal line.** `open`, `post` and `wait` (exits `0` and `10`) print `terminalLine: "→ Look at the web console: <url>"` (`terminalLine()` in `sessions.mjs`), and `console.md` asks the agent to end every terminal message with the latest one verbatim, so the tool builds the line rather than the model. In `wait` it is added to the printed result only; the collected `result.json` on disk never carries it. `open` also prints `swept: { sessions, scratch, handoffs }` when it found anything to clean.
|
||||
- **State fields written by `open`, not the agent.** Every `open` (fresh or resume) records `state.worktree` and `state.branch` from `repoRoots()` — the branch is read off `<gitdir>/HEAD` on the walk that already finds the gitdir (`""` on a detached HEAD or outside git; env-relocated repos ask git, as before) — and the page shows them in the footer as the workspace label (`footerLabel()`: `folder · branch`, or `folder + N folders · branch` once folders are added, stepping down through narrower tiers); a click opens the Workspace dialog. `state.wake = true` is set only by a fresh `open --workflow dashboard` and deleted by every resume (server restart, launch, Back to the dashboard); the page also keeps a per-sid `sessionStorage` guard so a reload never replays it.
|
||||
- **`looks.width` is a person-level preference** alongside theme, accent and sounds in `looks.json`. `CARD_WIDTHS` in `public/palette.js` (`narrow` 720, `comfortable` 880 — default — `wide` 1080) is read by the page (`cardWidth()` validates a saved value) and by `routes.mjs`, which paints `data-width` on first load; `styles/tokens.css` maps `data-width` onto the single `--card-width` variable that every column rule uses.
|
||||
- **`GET /overview` is the one route that reads a project file.** It serves `<spec>/overview.md` as `text/markdown` with `cache-control: no-store` (so the Overview tab is always fresh), or `404 { "error": "no overview" }`. A dashboard session honours `?spec=` only when it equals a `dir` in `state.scan.specs`; every other workflow uses `state.specDir` and ignores the query. The root is `state.worktree` (fallback `state.project`), and `readOverview()` resolves and `realpath`s the file and refuses anything outside the root's realpath, so `../`, absolute paths and outward symlinks all 404.
|
||||
- **Month-old sessions are deleted whole.** `open` lists `staleSessions()` (directories matching the session-id pattern whose `state.json` mtime is older than 30 days, never the sid being opened — no exceptions for paused sessions or unread sends) and `staleScratch()` (top-level regular `.json` / `.mjs` files in the console folder older than 30 days, never `looks.json` or `console-dir` — `PROTECTED_CONSOLE_FILES` — never a directory or symlink) before it prints, and removes them after; `removeSessions()` / `removeScratch()` re-check every name against the session-id pattern / the scratch-name rule before deleting — not the age, the skipped sid or the file type, which the `stale*` listing already decided, so never hand them names that did not come from it. `console.md` tells agents to write temporary payload files into the session's own folder so they go with it.
|
||||
- **User Preferences → Cleanup deletes on demand, from a list the server makes.** `POST /cleanup` (origin-checked) with `{ scan: true }` returns `cleanupFindings()`: `{ items: [{ id, where, name, kind, bytes, folder? }], bytes }` (`folder` on `notepad:` items only), ids `session:<sid>` (the `staleSessions()` rule, and every file in the folder that old too, never the serving sid), `console:<name>` (anything at the top of the console home but `PROTECTED_CONSOLE_FILES`, `sessions` and `runtime`, directories too) and `root:<name>` (anything at the top of `~/.plan2code` but `KEPT_PLAN2CODE_ENTRIES`: `console`, `bin`, `launcher.json`, `install.json`, `models.json`, `handoffs`, `notepads`), `notepad:<key>` (a month-old notepad, whole; see Notebook below) and `completed:<name>` (each folder or link directly under the session worktree's `specs--completed/` whose newest mtime is older than the session age, 30 days; loose files there stay; the server passes `project: sessionWorktree() || PROJECT`, and without a `project` the archive is never scanned). Both stray kinds must be untouched for `STRAY_GRACE_MS` (an hour, by the newest `lstat` mtime anywhere inside, since rewriting a file never moves its folder's mtime; unreadable reads as fresh): the same folders hold `workspaces.json.lock` and `writeJsonAtomic()`'s `<file>.<pid>.tmp`, which live for milliseconds. `root:` is only scanned when the console home is `<PLAN2CODE_MODELS_DIR or ~/.plan2code>/console`, so a test or dev home never reaches the real folder. Paths never go to the page. `{ delete: [id] }` runs `removeCleanup()`, which re-scans and removes only ids still on the fresh list (symlinks unlinked, never followed), returning `{ removed, bytes, failed }`. The page always shows the list before **Delete these**.
|
||||
- **The console's path is stated, not searched for.** Each Interface line names `references/web-console/` beside the SKILL.md and the `~/.plan2code/console/console-dir` fallback; the prompts with room (all but pathfinder, plan, document and finalize, which sit near the char limit) also name the canonical global install path `~/.agents/skills/<skill>/references/web-console/` (the skills CLI's real store; every agent dir links into it), and every `console.mjs open` writes `HERE` to `~/.plan2code/console/console-dir` (only `open`, so a `help` or dev run from `src/` never repoints it) so a later session can read the path from a fixed place. Without these the agent hunts the skill install dirs on every session.
|
||||
- **`open` needs no payload, and runs first.** `--file` and `--title` are optional (the title defaults to the folder name). Every skill's Interface line puts `node "<D>/console.mjs" open --workflow <w>` BEFORE reading console.md or the project, and a test (`every skill opens the console before it reads anything`) keeps it that way; a blank session renders a starting screen ("Starting Pathfinder", Planny in flight) until the first post. Every skill replaces the flight with its own animated pose (init — init-update borrows it — pathfinder, plan — revise-plan borrows it — document, implement — implement-review borrows it — finalize, quick-task, review, handoff; only the dashboard keeps the flight), cloned by `startStage()` in `screens/starting.js` from `<template id="start-poses">` in `index.html` and animated under `.pose` in `styles/poses.css`; each `SKILLS` entry's `pose` in `skills.js` is the list (`START_POSES`/`startPose()` in `answers.js` read it), and a test keeps the template in sync with it and every catalog workflow mapped to a pose. The same pose stands above the waiting pane (`.waiting-pane`, agent working with an `activity` and nothing to ask). `posePane()` keeps the pane on screen across renders when the pose is unchanged — `renderMain()` holds any `:scope > [data-pose]` child back from the clear — so the SVG never leaves the DOM, its animations never restart on a state frame, and Planny carries unbroken from launching → starting → waiting. The dashboard's launch hand-off resumes first and reads the launched skill's file after.
|
||||
- **The dashboard scan knows whether the folder is a git repository.** `scanProject()` returns `{ hasAgents, isGit, pending, specs }`; `isGit` comes from `insideGitRepo()`, the same filesystem walk `findRoots()` does (no `git` process, linked worktrees and submodules count, a set `GIT_DIR` / `GIT_WORK_TREE` / `GIT_COMMON_DIR` counts as a repo). The Git card is never greyed, since a clean tree still has branches to switch, pull and push. When `isGit` is `false` the card shows `GIT_INIT_NOTE` ("Not a git repository yet: it offers to start one") as its detail line; a scan with no `isGit` counts as a repo. In a repo, `pending` is `pendingFiles()` in `sessions.mjs`, which calls `countPending()` in `git-repo.mjs`: one bounded `git status --porcelain -z` under `GIT_OPTIONAL_LOCKS=0` (`null` when git cannot say) counting modified, staged, deleted and untracked paths. Above `0` the detail line is `pendingNote(n)` ("3 files to commit"); `0` and `null` show no note. A finish with `commit: true` puts a **Commit it now** button on the finished screen (`commitOffer()`, `renderCommitOffer()`); its `__commit` press makes the agent resume as `git` in the same session and run the commit flow above the board. `open --resume` treats any switch into `git` (this press, or Changelog's "Commit this now?") as a hop, like a dashboard launch: `switchWorkflow()` blanks the page, finish and the last run's `state.git` included, and `draft.json` goes. Without that, the old finish outlived the switch, and the page sat on the old ending above the new questions and the board. A confirm item may carry `files: [{ path, state }]`, drawn as a collapsed table by `filesTable()`. Subagents is **on** by default for the five opted-in skills (`defaultSetting()`); a saved Off stays off.
|
||||
- **The start path is timed, and `open` is built around it.** Measure with `node scripts/bench-web-console.mjs` (`--browser-delay 900` for a real Chrome launch, `--roundtrip` for Send→agent and post→page, `PLAN2CODE_CONSOLE_TRACE=1` on `open` for a step timeline). Four things make it fast, and each is load-bearing:
|
||||
- **No git process.** `repoRoots()` in `sessions.mjs` finds the common dir and worktree top by walking to `.git` (following `gitdir:` and `commondir` files) — each `git rev-parse` cost 150ms+ on Windows. It asks git only when `GIT_DIR`/`GIT_WORK_TREE`/`GIT_COMMON_DIR` relocate the repo, and uses the native realpath so an 8.3 short name keys the same project git would.
|
||||
- **The socket handover.** `open` spawns the server first, then binds the loopback port itself (the first `listen()` blocks ~50ms on Windows, overlapped with the server's boot), launches the browser on that URL immediately (Chrome via `start` takes ~900ms to its first request, the longest step of all), and hands the listening socket to the server over IPC (`bindLoopback()`/`handOff()` in `sessions.mjs`, `--handoff` in `server.mjs`). Requests queue in the socket until the server takes it; one `open` already accepted is passed across as a socket and acknowledged (`conn-held`) before the channel is closed. No channel, or no socket within 3s, and the server binds its own port; `open` then opens the real URL.
|
||||
- **The first paint needs no fetch.** `routes.mjs` (`renderIndex()`) renders `index.html` with the session's title, badge and saved theme (`data-theme`, `data-looks-accent`, matched by accent rules generated from `palette.js` and appended to the joined stylesheet by `static.mjs`) and the whole first state as an inline `<script type="application/json" id="boot">` (every `<` escaped; data blocks are not executed, so the CSP is unchanged). `modulepreload` hints fetch every module in parallel, the page draws in the same task as the script runs, and `/events?have=<key>` skips the opening frame when the page already holds that exact state. The chimes load on first use, not at start-up.
|
||||
- **Reads are stat-gated.** `fileStamp()` (mtime:size:ino) decides whether `state.json`, `result.json` and `looks.json` changed before anything reads or parses them — per request, per heartbeat and in the 1s poll; the parsed state is cached (`readState()` returns it; `/submit` clones before editing). `wait` stats `result.json` every 50ms instead of parsing it every 400ms. Static assets are held in memory for the server's life and revalidate by ETag.
|
||||
- **The Workspace and the session meter live beside `state.json`, one writer each, and outlive every hop.** Three session files, none of which `switchWorkflow()` ever touches, so both survive dashboard → skill → dashboard (a new console session starts with a count of 0, and with the folders remembered for its folder and spec, below):
|
||||
|
||||
| File | Writer | Holds |
|
||||
|---|---|---|
|
||||
| `workspace.json` | the server (`workspace.mjs`) | the folders (`id`, `path`, `name`, `description`, `original`, `nested`), `version`, the `changes` log, `missing` ids, and `remote` (`remoteWarning()` in `sessions.mjs`, computed by the server at boot) |
|
||||
| `ledger.ndjson` | `console.mjs` | append-only, one JSON line per entry. Meter events: `launch` (every fresh `open` and every resume into another workflow), `run` (a post's `run`, id scoped by launch, with `tasks` when a built phase reports one) and `answer` (one per item the person answered in a collected send, written by `ledgerAnswers()`, id `<launch>:answer:<send stamp>:<item>`). Also `folder-issue` reports |
|
||||
| `workspace-cursor.json` | `console.mjs` | the last workspace `version` handed to the agent; advanced after the print, never backwards |
|
||||
|
||||
The page changes the workspace only through five routes: `GET /workspace` (`?check=1` re-stats every folder first), `POST /workspace/add` (path resolved against `state.worktree`, `~` expanded, case-insensitive duplicate check on win32/darwin; `not-a-folder`, `duplicate`, `bad-name`, `name-taken` + `suggest`), `POST /workspace/edit`, `POST /workspace/remove` (the original folder refuses) and `POST /workspace/browse` (one picker at a time, 409 `busy`; 404 `no-picker` when `remote` is set or no picker exists; `PLAN2CODE_PICKER_ECHO` stands in for the dialog in tests). `stateFrame()` carries `workspace` (folders, `missing`, `remote`, the current launch's folder `issues`) and `meter` (`meterView()` over the ledger), and both files are on the 1s poll; it also carries an optional `update` once the boot-time release check (`update-check.mjs`) finds a newer release. The agent hears of the workspace through `open` output (`workspace: { folders, missing? }`, which also seeds the cursor) and then each change once, as `workspace: [...]` plus `Workspace: …` reply lines on `wait` exit 0 or `chat`; a change alone never ends a `wait` slice (`pendingWorkspace` on exit 10). `post` and `open --file` lift `run` and `folderIssue` out of the patch into the ledger, never into `state.json`; an unknown event or a malformed issue is exit 3. **Remembered workspaces.** `workspace.mjs` keeps `~/.plan2code/console/workspaces.json` (`WORKSPACES_FILE`, under `PLAN2CODE_CONSOLE_HOME` in tests): `projects[<case-folded worktree>] = { path, project, specs: { "specs/<name>": … } }`, each entry `{ original: { name, description }, folders: [{ path, name, description, nested? }], at }`. `rememberedWorkspace()` answers spec, else project, else nothing; `initialWorkspace(worktree, entry)` builds from it, both in the server's first `workspaceNow()` and in `open`'s read-only `workspaceOnOpen()`, so they agree. `workspace.json` carries `scope` (the spec key or `""`). Every user change (`bumpWorkspace`, not `missing`/`found`) calls `rememberWorkspace()`. `setScope()` swaps the list, logging `removed`/`added`/`renamed`/`described` changes so the cursor stays truthful; `POST /workspace/scope { spec }` (the dashboard picker, on selection and before a launch) seeds an unsaved spec from the project's list, and `followSpecDir()` (state poll, boot) moves the scope to a posted `specDir`, saving the current list as an unsaved spec's. Two writers, each a read-modify-write of one key: the server and `console.mjs forget --spec` (Finalize Step 6). The contract is in `console-workspace.md` and `console-meter.md`, and `building.md` (per-phase `run`), so the skill prompts stay unchanged.
|
||||
- **The Subagents switch is a standing instruction, injected only on change.** The page's icon button (`#btn-subagents`, after Write a brief) and `#subagents-modal` show only when the frame's `subagents` block says `offered && supported`. `offered` comes from `public/subagents.js`; `supported` means the latest `{ "type": "open" }` line in `events.ndjson` carries `caps: ["subagents"]` (`latestOpenCaps()`), so an older skill copy's `open` hides the button. Four places hold it, one writer each:
|
||||
|
||||
| File | Writer | Holds |
|
||||
|---|---|---|
|
||||
| `~/.plan2code/console/subagents.json` | `server.mjs` | per project folder → workflow: `{ on, instruction, max }`, `instruction: null` being the shipped default; on `PROTECTED_CONSOLE_FILES` |
|
||||
| `<session>/subagents-setting.json` | the server (`settings.mjs`) | `{ workflow, on, instruction, max, revision }`: synced from the store at boot and on any workflow change (`serverSubagents().sync` in `settings.mjs`), `revision` bumped only by a real change |
|
||||
| `<session>/subagents-cursor.json` | `console.mjs` | `{ revision, state }`, the last block handed over; `open` resets it, and it moves only after the print |
|
||||
| `state.json` → `helpers` | `console.mjs post` | the helpers the agent reports, merged by `id`, checked by `checkHelpers()` plus the prose scan; dropped by `switchWorkflow()` on a dashboard hop |
|
||||
|
||||
`POST /subagents` (origin-checked; `400` `not-offered` / `bad` / `too-long` / `max`) saves the store and bumps the session setting. `consume()`, `cmdChat()`, `deliverChat()` and `open` append `blockFor()`'s lines last in `reply` and the `subagents` field; a change alone never ends a `wait` slice. The page's Subagents tab (before Ask) draws `state.helpers` through `helperRows()`. Helpers never reach the meter ledger. Contract: `console-subagents.md`.
|
||||
- **The filesystem is the transport.** Sessions live in `~/.plan2code/console/sessions/<sid>/`, deliberately not under `specs/`, so the console cannot trip the metrics scraper or the loop's marker parser, and survives `git clean`. A result written after the agent dies is picked up by the next session.
|
||||
- **Attachments on notes and quick questions live in `<sid>/uploads/`**, never in the project: images as `<uuid>.jpg`, documents as `<uuid>.<ext>` with `ext` from `DOC_TYPES` in `answers.js` (text, code, PDF). The browser re-encodes images to JPEG and sends raw bytes to `POST /upload` as `image/jpeg`; documents go as-is as `application/octet-stream`, the extension taken by `docExt()` from the uncut `x-p2c-name`. `readRaw(req, limit, cb)` in `routes.mjs` caps images at `MAX_BODY` (4 MB) and documents at `MAX_DOC_BYTES` (10 MB), and drains rather than destroys so the client gets its 413. Images need the `FF D8 FF` magic; documents pass `checkDocument()` in `sessions.mjs` (`%PDF-` for PDF, strict UTF-8 with no NUL for text), else 415. The server names the file with `crypto.randomUUID()`. `GET /uploads/<id>.<ext>` serves images as `image/jpeg` and documents under a fixed type (`application/pdf`, else `text/plain`) with `nosniff` and, on text, CSP `sandbox` (a sandboxed PDF cannot open in the viewer), so a browser can show but never run one; `recordSubmitted()` writes every send's note onto its item as `sentNote { at, text, images, files }` (paths and names only), which `noteAwaiting()` in `answers.js` turns into the Sent box's attachment links and the Notes pane's pending note until the agent's next thread message; `DELETE /uploads/<id>.<ext>` takes any allowed extension; both stay contained under `uploads/`. `isOwnUpload()` returns the kind (`"image"` / `"file"` / `false`), and `attachmentsOk()` makes `/submit` comments and `/chat` messages carry images only in `images[]` and documents only in `files[]`, this session's uploads only, at most 5 together (`MAX_ATTACHMENTS`). A comment's `reply` gains one ` Image: <path> (<name>)` or ` File: <path> (<name>)` line per attachment, in attach order; a chat entry's lines come from `chatReplyLines()`, its images first, then its files. `sweepUploads()` bounds disk growth, and the session sweep removes the whole session a month after that. A note attachment a spec file cites is copied out first by `console.mjs keep` (`--session --upload --name --spec [--from]`): it checks both paths (the upload must sit under the session's `uploads/`, and the spec folder under `state.project`, real paths included, so a symlinked folder cannot carry the copy outside), copies with `COPYFILE_EXCL` and reuses an existing copy, prints `{ ok, path, link, image, reused }` with a forward-slash link relative to `--from`, and logs a `keep` event. It is the agent's hand, not the server's: it runs in the agent's shell only when the agent decides to cite a file, so the server still never writes into a project.
|
||||
- **Answers carry their terminal token.** Each item ships `fallbackText` and `token`, so a click resolves to the literal word the prompt already expects (`approved`, `a`, `skip`). No workflow needs a second code path, and declining the console degrades to prose with nothing lost.
|
||||
- **A build tells the page how long silence is normal.** The page calls a working agent stuck after two minutes without a post, which is right for a conversation and wrong for a twenty-minute build task. `agent.quietMinutes` (1 to 60, counted only while `working`) stretches the stuck, adrift and Send-grace thresholds; `quietLimitMs()` in `answers.js` is the one rule.
|
||||
- **A finished quick task's review button is a request through the wait loop**, like the brief: `{ "i": "__review" }` or `{ "i": "__done" }`. The agent keeps waiting after posting a finish that carries `review`, and takes the review up by posting `"finish": null`, which puts the session back to work. Implementation's review needs no such machinery: it is a verdict on the sign-off card, asked before approval, so the session never left work to take it up.
|
||||
- **Back to the dashboard is the same kind of post-finish request.** A finish with `finish.dashboard: true` shows the button; a press arrives as `{ "i": "__dashboard", "type": "dashboard" }`, and the agent runs `open --resume <sid> --no-open --workflow dashboard` then posts `"finish": null` with a fresh `menu`. The agent waits ~10 minutes after the finish for it (alongside `__review` / `__done` on a quick task); after that the page swaps the button for the `/plan2code` command. `finish.command` is optional — without one the page shows the "All done" line — and `validate()` rejects a `<placeholder>` command and a non-boolean `dashboard`. The session-level actions are therefore `__brief`, `__stop`, `__launch`, `__review`, `__done` and `__dashboard`; a new post-finish button should copy this precedent.
|
||||
- **Continue here, Update CHANGELOG first and Ask prompt blocks.** Three small additions on the same pattern. **Continue here** is page-only: `continueOffer(fin)` (`public/answers.js`) reads `finish.command`, and when it starts with a Plan2Code skill (and the finish is not a pause) `screens/ending.js` draws a button beside the Next step block, hidden when the session meter is red; the press is the dashboard's own `{ "i": "__launch", ... }` through `sendAfterBuild("launch", offer)`, so the agent writes nothing new (`startsClean()` cleans the page for the hop, except out of Git and into Review; a same-skill next step keeps the workflow, so the agent posts `"finish": null`). **Update CHANGELOG first** is `finish.changelog: true`, accepted by `validate()` only on `quick-task` and `finalize` (a paused finish is exempt from that check and the page ignores the flag), and it belongs with `commit: true`; the press is `__changelog`, a `HOP_ACTIONS` entry in `cmd-post-wait.mjs` that resumes as `changelog`, whose "Commit this now?" yes carries on to Git. **Ask prompt blocks** are contract only (`console-chat.md` → Prompts to carry away): the page already draws a Copy button on every fenced block.
|
||||
- **`__dashboard` also arrives mid-workflow.** A left-pointing triangle (`#btn-home`, filled with `--accent`) sits left of Stop session on every non-dashboard page. Its state comes from the pure `homeButtonState()` in `answers.js`: hidden on the dashboard, on a finish and during a stop, and otherwise gated by the same `turnGate()` Stop now uses (the person's turn, unless the agent has gone adrift). The confirm (`#home-modal`) reuses `stopWarning()`, and the submit carries the staged answers plus `__dashboard`, with `HOME_REPLY`. With no finish on the page, the agent treats it as a stop that lands on the menu: it saves its place as for `__stop`, then resumes as the dashboard with `"finish": null` + `menu`, with no finish and no stop in between (console-stop.md → "Back to the dashboard, mid-workflow"; building.md for builds). `local.homeward` drives Planny's "Saving your place and opening the dashboard…" line until the through-the-dashboard reset clears it.
|
||||
- **Handoffs live outside every repo, in `~/.plan2code/handoffs/`, and the console owns them** (`handoffs.mjs`; the console ships in every skill, so the Stop flow, the Handoff skill and the dashboard all reach it through `console.mjs`). `handoff new --workflow <w> --skill <s> [--spec specs/<x>] [--title <t>] [--from-stop]` claims one for this checkout and prints `{ ok, id, path, meta }` (exit 2 bad usage, 3 a bad value). Off the dashboard the Stop modal offers **Stop with a handoff** (`#stop-handoff`, suggested) above **Just stop and save** (`#stop-go`); the first sends `__stop` with `handoff: true` and `STOP_HANDOFF_REPLY`, and `wait` adds `handoffSkill` (the built Handoff skill's `SKILL.md`, `handoffFor()`); console-stop.md gives the order (answers, save, `handoff new --from-stop`, write, paused finish naming the file, `stop`). On a dashboard, `cmdOpen()` adds `scan.handoffs` (`listHandoffs(worktree)`) and `scan.handoffsDir` after `scanProject()`, which stays handoff-free because `specs.mjs list` shares it. The picker draws them as dashed `.spec-chip.is-handoff` chips after the specs (`specSel = "handoff:<id>"`); a picked one replaces the skill cards with `renderHandoffPreview()`: **Pick it up here**, **Read it all** (`GET /handoff?id=`, served only for an id in the dashboard's own `state.scan.handoffs`), **Copy for a new conversation** (`handoffCopyText()`) and **Delete** (`openHandoffDelete()`, one step). Pick it up sends `{ "i": "__pickup", "type": "pickup", "handoff": <id> }`; `HOP_ACTIONS.pickup` (`pickupHop()`) reads the stored `.json` only, never the page, and falls back to Quick Task with `fallback: true` when the record, its skill or its spec is gone, or the Handoff skill wrote it (resuming that skill would only write another handoff); `markPickedUp()` stamps `usedAt` as the hop is printed, so the next scan drops the chip. Delete sends `__delete` with `handoff` in place of `spec`, and the agent runs `delete-handoff --handoff <id>` (`removeHandoff()`, exit 3 on a refusal, nothing touched). `open` sweeps handoffs untouched for 30 days (`staleHandoffs()`, the `.json`'s mtime, else the `.md`'s), picked up or not, and reports them in `swept.handoffs`; Cleanup never lists the folder (`KEPT_PLAN2CODE_ENTRIES`).
|
||||
- **Notebook: the person's, one per folder, in `~/.plan2code/notepads/`, in named tabs, and never the agent's.** `notepads.mjs` is the store's one owner (`PLAN2CODE_NOTEPADS_DIR` moves it for tests). The folder is the session's worktree, else its project (`notepadRoot()` in `routes.mjs`), keyed `<folder-name>-<12 hex>` by `notepadKey()` (the hash over `foldKey()`, so case-only path differences match on Windows and macOS, and two worktrees get two notepads). **Layout:** `meta.json` (`{ v: 2, folder, created }`), `tabs.json` (`{ v: 1, order: [id], last, tabs: { id: { name, created } } }`, the index and the only place order and the last tab live) and, per tab, `tabs/<id>/note.md` with `tabs/<id>/images/<uuid>.jpg` and `<uuid>.thumb.jpg`; a tab id is 12 hex. Every write takes the folder's `notepad.lock`; a read never creates a file, so only the person's edits age a notepad. A delete removes the tab from the index first, then its folder, and the next write sweeps away a tab folder the index no longer names (a delete that crashed half way). **Migration:** the first shape (`v: 1`, one `note.md` and `images/` at the top) reads as one virtual tab, Notes, with the fixed id `LEGACY_TAB_ID`, and a read writes nothing; the first write moves the files into `tabs/<LEGACY_TAB_ID>/` and writes `tabs.json` last, so a crash in the middle is finished by the next write and never loses a file. A `tabs.json` that does not hold up is set aside as `tabs.json.corrupt` and rebuilt from the tab folders. **Routes:** eleven, placed after `/upload` in `ROUTES` (the shape test pins the order): `GET /notepad[?tab=<id>]` (`{ tabs, last, tab: { id, text, savedAt, images } }`, with the tab's `text`, `savedAt` and `images` repeated at the top), `POST /notepad/text?tab=` (`{ text }`, 1 MB, 413 `too-long`), `POST /notepad/image?tab=` and `POST /notepad/thumb?id=<uuid>&tab=` (raw `image/jpeg` the page re-encoded with `reencode()`, 4 MB, 200 pictures per tab: 415 `not-jpeg`, 413 `too-large`, 409 `too-many`), `POST /notepad/image/delete?tab=` (`{ id }`), `POST /notepad/tab` (`{ name }`), `/notepad/tab/rename` (`{ id, name }`), `/notepad/tab/delete` (`{ id }`), `/notepad/tab/order` (`{ order }`, every id once) and `/notepad/tab/last` (`{ id }`), and `GET /notepad/images/<tab>/<uuid>[.thumb].jpg` (matched on the raw request line like `/uploads/`, served through `imagePath()`'s realpath containment, `no-store`). A text or picture request with no `?tab` means the last tab used (and makes Notes when there is none), so an unchanged client keeps working. The ten POSTs are origin-checked, and every refusal is a `NotepadError` turned into `{ error }` (`bad-name`, `duplicate-name`, `too-many-tabs`, `no-such-tab` beside the picture and text codes). None of them writes to the session folder or `events.ndjson`, and `console.mjs` never imports `notepads.mjs`, so nothing in a notepad reaches `state.json` or anything `wait` prints. **The editor, and the CSP.** CodeMirror 6 replaced OverType 2.6.1 after a spike (typing at 200 KB measured about 24 ms a key against about 99 ms, and real heading sizes): `public/vendor/codemirror.esm.js` is one minified file (about 500 KB) made by the dev-only `scripts/vendor-codemirror.mjs` from `scripts/vendor-codemirror-lock.json`, never installed in the repo, and loaded by a dynamic import only when the Notebook first opens. CodeMirror writes its rules as a `<style>` element, which `style-src 'self'` refuses, so the editor lives in the open shadow root of `.notepad-cm-host` where it adopts them as a constructed stylesheet, and its own look is `public/notepad-editor.css`, a `<link>` inside the root. Custom properties inherit across the boundary, so both themes work; page tests reach the editor with Playwright's CSS locators (they pierce open shadow roots) and read its text from `EditorView.findFromDOM()`, since lines the cursor is not on draw without their Markdown marks. CodeMirror's own rules win a tie in specificity (they are adopted after the linked sheet), so `notepad-editor.css` writes `div.cm-editor .cm-scroller` for the few it overrides. `scripts/test-web-console-page-notepad.mjs` fails on any `securitypolicyviolation` with the notepad open. **Upgrading CodeMirror:** change a version in `scripts/vendor-codemirror.mjs`, run `node scripts/vendor-codemirror.mjs --update-lock` (npm and network; it installs in a temp folder), update the sha256 in the files-table row, then run the two notepad test files. **Tabs on the page:** `screens/notepad.js` binds every save and picture to the tab it was made in (a switch waits for the save, and stays put when it cannot), `public/notepad-tabs.js` draws the bar, and `public/notepad.js` holds the name, order and delete rules as pure code. **Cleanup.** No sweep at `open` touches a notepad, and `notepads` is in `KEPT_PLAN2CODE_ENTRIES`, so the folder is never a stray. `cleanupFindings()` lists a notepad as one `notepad:<key>` item (with `folder` from `meta.json`, labelled "Notebook for <folder>"Line truncated
|
||||
- **A Bug fixed spec deletes in one step.** Its chip shows a visible **Delete** (`.spec-chip-del-label`) instead of the hover ✕, `openDeleteConfirm()` gives it a fixed-bug warning and a **Delete it** button, and `deleteStep()` sends `__delete` on the first press, with no name to type. `chipDetail()` drops the scan's repeated "bug fixed" detail under the label.
|
||||
- **The Quick question chat is a second, append-only channel beside the card slot.** The page's **Ask** tab (always last, every workflow, still there after a finish) posts to `POST /chat` (a message, or `{ reset: true }` for New conversation) and `POST /chat/decision` (Approve / Decline on an edit the agent proposed). The server is the only writer of `<sid>/chat.ndjson` (one JSON line per `message` / `decision` / `reset`, each with a `seq`; `appendChat()` in `inbox.mjs`); `console.mjs` is the only writer of `<sid>/chat-cursor.json` (the last seq handed over, advanced only after printing) and of the agent's replies in `state.json` → `chat.replies` (merged by `id`, checked by `validateChat()`: real `re`, proposal paths outside the running `specs/<idea>/`). The server never writes chat into `state.json` — `post` read-modify-writes it under `withStateLock()` — and `stateFrame()` merges inbox and replies into the frame's `chat` block (`conversation`, `messages`, `typed`, `limit`, `offline`) in memory. `/chat` never checks `pendingResult()`, so neither channel can block the other. `wait` keeps its exit codes 0/10/20/30: exit 0 gains `chat` (or is `type: "chat"` with no actions), and the instant `console.mjs chat` answers 0/10/20 without touching `result.json`, which builds run after every task. Guards: 10 typed messages per conversation (`409 limit`), 4,000 characters (`400 too-long`), own uploads only, of the right kind (`400 image`, `400 file`), `409 offline` when `chatOffline()` says no agent is there, `409 stale` for an old conversation. A hop through the dashboard (checked on every state change and at server start, so a restart still sees it) appends a `reset` and starts a new conversation. A lone reset never ends a `wait` slice (`deliverableChat()`); it rides along with the next message.
|
||||
- **`validate()` in `patches.mjs` enforces four workflow rules mechanically**: max three open required questions, no internal vocabulary in a title, one recommended option, and no loop markers or metrics-scraper bait.
|
||||
- **The palette is written twice for dark, and that duplication is the mechanism.** `@media (prefers-color-scheme: dark) :root:not([data-theme="light"])` follows the system; `:root[data-theme="dark"]` is the explicit choice from the colors panel. Drop the `:not()` and a system-dark browser overrides someone who asked for light. A chosen accent is applied as an inline custom property on `:root` (CSSOM, which the CSP allows), and the default is applied by REMOVING that override so the stylesheet's own per-theme values win. The server's `data-looks-accent` stand-in only lasts until `applyLooks()` runs, which removes it first thing — left on, its rule would beat "Back to default".
|
||||
- **Help is in the page, built on first open.** The **?** button (`#btn-about`) opens `<dialog id="help-modal">`, which replaced the old "What this page is" About dialog. Its 18 panels and their icon sheet are hand-written HTML and SVG in `<template id="help-content">` in `index.html` (after `#start-poses`), cloned into `#help-panels` the first time **?** is pressed (except the dashboard topic's card list: `buildHelp()` fills its `.help-cards` from `SKILL_CATALOG` and `CATALOG_GROUPS` at that moment, in the dashboard's order), so first load builds nothing and Help still reads fully once the server is gone. `help.js` supplies the tab list and rules, `screens/help-dialog.js` the wiring (tab buttons, roving focus, `renderAbout()` for the live connection line on tab 1, `lightDismiss()`, and a Ctrl/⌘+Enter guard scoped to this dialog). SVG is styled by class and CSS variables only — a `style=` attribute is dropped by the CSP, and a test fails on one — and every number the prose quotes sits in a `data-fact` span a test checks against the constant it comes from.
|
||||
- **Stuck sessions are explained twice, in Help and on the status line.** `stuck` ("When something looks stuck") is the second tab in `HELP_TABS`; its panel opens with a `help-callout` ("Check this first": Plan2Code often waits for a permission in the terminal, which the page cannot see) and four You see / Likely cause / Do this rows before the diagram. The quiet and Not running status lines carry a "What to check" button (`openHelpOn("stuck")`) inside the existing `role="status"` element, so it exists only while the symptom shows. Every finished and paused screen gets a "Before you close this" panel from `renderCloseGuide()` in `renderHandoff()` (Safe to close, Start fresh, Carry on). Tests in `scripts/test-web-console-source.mjs` check the tab order, the callout and rows, and the `renderCloseGuide` call.
|
||||
- **Markdown is rendered to DOM nodes, never to an HTML string** (`public/render.js`), so agent-authored text that quotes a hostile source cannot execute. Only `marked.lexer()` is used.
|
||||
|
||||
Tests: `npm test` runs, in order, `validate-char-count.js`, `install.js --build-skills`, `parse-check.mjs`, `check-skill-table.mjs`, then one `node --test` over the skill-script tests (`test-skill-scripts.mjs`, `test-script-*.mjs`, `test-git-repo.mjs`), `test-launcher.mjs`, `test-getting-started.mjs` and the web console's `test-web-console-*.mjs`, so they run in parallel, one process each. The console tests are split by area (`-session`, `-lifecycle`, `-logic`, `-server`, `-chat`, `-chat-stress`, `-workspace`, `-subagents`, `-concurrency`, `-source`, `-git`, `-qa`, `-speed`, `-hardening`). Their shared setup is `scripts/web-console-test-helpers.mjs`: importing it gives the file its own console home (so `workspaces.json`, `subagents.json`, `looks.json` and sessions never collide across files) and registers the `stop --all` cleanup. `-session` and `-lifecycle` each run an ordered chain of tests on one session of their own; everything else opens a session per test. A new test goes in the file for its area, after the tests it depends on. The parse check exists because `node --check` parses a `.js` file as a CommonJS script and has already let a browser-fatal string literal through; it imports each shipped module as a real ES module instead. They live in `scripts/`, not `src/web-console/`, because everything under the latter ships into every skill.
|
||||
|
||||
**Adding a file under `public/`:** a page module needs `SERVABLE` in `static.mjs` and a `<link rel="modulepreload">` in `index.html`. The set is hardcoded rather than a directory lookup so there is nothing to traverse; a module missing from it 404s and the page dies at import with no useful error (the import-fetch test fetches every import and fails naming the file). A module missing its preload still works, but loads serially after `app.js` and slows the first paint. A screen goes in `public/screens/`, imports only `state.js` and the pure modules (never another screen), and is imported by `screens/core.js`; the import guard in `scripts/test-web-console-shape.mjs` fails naming a screen that breaks either rule. A stylesheet goes in `public/styles/` and on `CSS_ORDER` in `static.mjs`, never on `SERVABLE`; the joined-stylesheet test fails when the folder and the list disagree. Every new file also needs its row in the files table above, which the docs-table test (same file) checks.
|
||||
|
||||
## Status Line
|
||||
|
||||
Optional Claude Code status bar living in `src/statusline-claude/`. Three-line bar beside a Planny icon: two content lines with a dashed rule between, showing model (+ effort), project/worktree, branch, uncommitted diff stats, session duration + cost, context window usage, and plan/quota usage.
|
||||
|
||||
**Design constraints:**
|
||||
- **Zero runtime dependencies** — `statusline.js` is self-contained (config loader, git helpers, formatters, render). Copied verbatim to `~/.claude/plan2code-statusline.js` on install; no bundler step.
|
||||
- **Stdin-driven** — all data comes from Claude Code's stdin JSON (`model`, `workspace`, `context_window`, `rate_limits`, `cost`). No API calls, no auth, no background processes.
|
||||
- **Silent failure** — outer `try/catch` around `main()` plus `process.exit(0)` on missing stdin guarantees the script never crashes the CLI. All git ops are timeout-bounded (1.5s) and non-git workspaces short-circuit via `isGitRepo()` (walks up to 10 parent dirs looking for `.git`).
|
||||
- **Atomic settings writes** — installer writes `~/.claude/settings.json` via temp file + rename so a crash never leaves the file truncated.
|
||||
- **Custom-config respect** — installer detects non-plan2code `statusLine` entries, prompts before replacing, and backs up to `statusline-previous.json`. Uninstall only removes `settings.statusLine` if it points to the plan2code bundle.
|
||||
|
||||
**Layout:**
|
||||
|
||||
```
|
||||
src/statusline-claude/
|
||||
├── statusline.js # Self-contained: config, git, formatters, render
|
||||
├── statusline-config.json # Default config template
|
||||
└── README.md # User docs: install, config, debugging
|
||||
```
|
||||
|
||||
**Adaptive plan-usage display:** the formatter auto-selects between `5h/7d` rate-limit percentages (Pro/Max/Teams — when `rate_limits` present in stdin) and `Nk in · Nk out` session-token counts (Bedrock/Vertex/PAYG — when `rate_limits` absent). Segment is hidden when neither shape is available.
|
||||
|
||||
**Installer integration** lives in `install.js` under the `STATUS LINE INSTALLATION` section (`installStatusLine`, `uninstallStatusLine`). Included in Advanced → `E` (Everything); also available individually via Advanced → `S`.
|
||||
|
||||
## Global `plan2code` Command
|
||||
|
||||
Typing `plan2code` in any directory opens the dashboard skill against the current project, **in that directory**, in one of three CLIs (the `CLIS` table in the launcher):
|
||||
|
||||
| CLI | Runs |
|
||||
| --- | --- |
|
||||
| Claude Code | `claude /plan2code --permission-mode bypassPermissions [args]` |
|
||||
| Devin | `devin --permission-mode bypass [args] -- /plan2code` |
|
||||
| Codex | `codex --dangerously-bypass-approvals-and-sandbox [args] $plan2code` (Codex starts a skill with `$name`; the launch line follows Codex's documentation) |
|
||||
|
||||
On a terminal it first prints a Planny banner (`renderBanner()`). With more than one on `PATH` it asks `Plan2Code opens inside an AI coding agent. Pick which one to use:` as a numbered menu, the last pick pre-selected and marked `(last used)` (Enter keeps it; a number or a CLI id also works); with one installed it uses that without asking, printing `Opening with <CLI>…` (as does a `--cli` pick); with none it exits 127 and prints `SKILL_STEPS`: how to install an agent, `cd` into the project, and type `/plan2code` (`$plan2code` in Codex). An uninstalled `--cli` pick prints that CLI's own steps after its error (its install command, `cd` into the project, then `plan2code --cli <id>` or its prompt). `--cli claude` / `devin` / `codex` (or `--cli=<name>`) skips the menu and is never forwarded; an unknown name exits 2, an uninstalled one 127. The pick is saved as `lastCli` in `~/.plan2code/launcher.json`, merged beside `lastFolder`. Before spawning, unless the forwarded args carry `--model` / `--model=` (or, for Codex, `-m`), it asks `Which model should <CLI> use?` from `models.json` plus the user's additions, Enter keeping the model the CLI last used — Ctrl+C at any launcher prompt exits 130. With no TTY on stdin there is no menu (last pick, else the first installed) and no model question: it prints that the CLI will use the model last used in it (switch it in that CLI on its own, or pass `--model <name>`). Headings, numbers, defaults, retry lines and the `plan2code:` error prefixes are colored with `paint()` (the escape values of `install.js`'s `COLORS`, copied), stdout only when stdout is a TTY and stderr only when stderr is, and never when `NO_COLOR` is set; piped runs print plain text and no banner. Other arguments are forwarded to the CLI (`plan2code --model opus`), and its exit code is passed back. `plan2code update` is the one subcommand: it is never forwarded and opens no agent, it runs `npx --yes --allow-git=all git+https://github.com/jparkerweb/plan2code.git --update`, so `install.js --update` reinstalls what `~/.plan2code/install.json` lists. On every other start, before spawning the CLI, it prints one line when a newer release is out (`Plan2Code v<latest> is out (you have v<installed>). Run: plan2code update`), compared against `~/.plan2code/bin/version.json` and read from the console's cached release check (`~/.plan2code/console/update-check.json`); it never waits on the network, and when the cache is missing or stale it refreshes it in a detached background process so the next start knows. Tests: `scripts/test-launcher.mjs` (run by `npm test`) spawns the launcher against stand-in `claude`/`devin`/`codex` commands and a temp home.
|
||||
|
||||
**Design constraints:**
|
||||
- **Stable copy, not the package dir** — the installer normally runs from an npx cache directory npm may delete, so `installLauncher()` copies `src/launcher/plan2code.js` to `~/.plan2code/bin/plan2code.js` and the shims point there. Beside it go `update-check.mjs` (the web console's release check, for the terminal notice) and a `version.json` (the installed version). (The loop/metrics/bot wrappers point into `__dirname` and don't have this protection.)
|
||||
- **npm-style shims** — written into npm's global bin (`npm config get prefix`; `<prefix>/bin` off Windows): an sh shim everywhere, plus `.cmd` and `.ps1` on Windows, so cmd.exe, PowerShell and Git Bash all resolve it. On macOS/Linux, when the npm bin isn't writable (system Node), it falls back to `~/.local/bin`.
|
||||
- **Marker-based ownership** — every shim contains `plan2code-launcher`; `uninstallLauncher()` removes only files carrying it, leaving any other `plan2code` bin alone.
|
||||
- **Resolving the CLI** — the launcher walks `PATH` (+ `PATHEXT` on Windows) itself. An `.exe` is spawned directly; a `.cmd`/`.bat` wrapper goes through `cmd.exe /d /s /c` with quoted args, since Node refuses to spawn batch files without a shell. The installer warns only when neither `claude` nor `devin` is on `PATH`.
|
||||
- **No bin-name overlap** — the installer's own bin in `package.json` is `plan2code-install` (→ `install.js`), so `plan2code` belongs to the launcher alone. npx runs a package's only bin whatever it's named, so the README's `npx … plan2code.git` command is unaffected; keep it the only bin, or npx will need `-c plan2code-install`.
|
||||
- **`--pick-folder` is shortcut-only** — the launcher strips it before building the CLI's args. The shortcut runs the CLI menu, then the folder picker, then the model menu. With it, a native folder picker chooses the cwd instead: on Windows, the Explorer-style `IFileOpenDialog` (`FOS_PICKFOLDERS`) via `powershell -STA -EncodedCommand`, its C# interop (`WINDOWS_PICKER_SOURCE`) passed in an env var and compiled with `Add-Type` (~0.5s), with a TopMost owner form so it doesn't open behind the console — Windows PowerShell's `FolderBrowserDialog` is the old tree-only dialog, and is kept only as the fallback when `Add-Type` is blocked (Constrained Language Mode, AppLocker); `osascript choose folder` on macOS, and `zenity` then `kdialog` on Linux (only when `DISPLAY`/`WAYLAND_DISPLAY` is set). If there's no picker, or the picker fails, it falls back to a typed `Project folder [last]:` prompt. A picker that exits 0/1 with nothing printed means the person cancelled, so the launcher exits 0. The picker starts on the last pick, stored in `~/.plan2code/launcher.json`. From the shortcut, a non-zero exit other than Ctrl+C (130 / `0xC000013A`) waits for Enter so the error doesn't vanish with the window. Typed in a terminal, `plan2code` behaves exactly as before.
|
||||
|
||||
**Desktop shortcut** — after the shims are written, `installLauncher()` (now async) calls `offerDesktopShortcut()`. It asks `Also add a Plan2Code shortcut to your desktop? (y/N)`, skips the question when stdin isn't a TTY, and refreshes an existing marked shortcut without asking. `installDesktopShortcut()` writes it to the real desktop (`[Environment]::GetFolderPath('Desktop')` on Windows, which covers OneDrive redirection; `xdg-user-dir DESKTOP` on Linux; `~/Desktop` otherwise):
|
||||
|
||||
| OS | File | Runs |
|
||||
| --- | --- | --- |
|
||||
| Windows | `Plan2Code.lnk` (written by `WScript.Shell`) | `pwsh.exe` (else Windows PowerShell) `-NoLogo -ExecutionPolicy Bypass -File "<bin>\plan2code.ps1" --pick-folder`, icon `src/launcher/plan2code.ico` (the web console's Peek-a-boo favicon, 16–256 px) copied to `~/.plan2code/bin/plan2code.ico` |
|
||||
| macOS | `Plan2Code.command` (0755) | `exec "<bin>/plan2code" --pick-folder` in Terminal |
|
||||
| Linux | `plan2code.desktop` (0755, `Terminal=true`, `gio … metadata::trusted`) | `"<bin>/plan2code" --pick-folder`, `Icon=` the web console's `favicon.png` copied to `~/.plan2code/bin/plan2code.png` |
|
||||
|
||||
The macOS and Linux shortcuts carry the `plan2code-launcher` marker as a comment line. A `.lnk` has nowhere to hide one (its Description is the hover tooltip), so it's recognized by what it runs: the UTF-16 strings `plan2code.ps1` and `--pick-folder` stored in the file (`plan2code.cmd` also matches, so shortcuts from before the PowerShell switch get refreshed). `uninstallLauncher()` removes only a recognized shortcut, plus the icons (`plan2code.ico`, `plan2code.png`), `bin/models.json` and `launcher.json` (never the user's `~/.plan2code/models.json`). A shortcut failure prints a warning and never fails the command install.
|
||||
|
||||
**Installer integration** lives in `install.js` under the `PLAN2CODE COMMAND` section (`installLauncher`, `uninstallLauncher`, plus the shortcut helpers). `install()` awaits it after a successful skills install (so `I` and Advanced → `E` get it), `U` removes it, and Advanced → `D` installs it alone. Every global install writes `~/.plan2code/install.json`, the install record listing the pieces installed (skills, launcher, statusline, loop, metrics, bot); `install.js --update` (what `plan2code update` runs) reinstalls exactly those, with no menu and never uninstalling, or with no record the skills and the `plan2code` command. After an install, `printGettingStarted()` prints the three steps (cd into the project, start Plan2Code, pick a card) and, when no agent CLI is on `PATH`, how to get one.
|
||||
@@ -0,0 +1,38 @@
|
||||
# Code Style & Gotchas
|
||||
> Part of [AGENTS.md](../AGENTS.md) — project guidance for AI coding agents.
|
||||
|
||||
## Code Style
|
||||
|
||||
- **install.js:** CommonJS, Node.js built-ins only (no external deps), ANSI colors via `COLORS` constant, readline-based prompts
|
||||
- **plan2code-loop, plan2code-metrics & plan2code-bot:** TypeScript + ESM, built with tsup (target ES2022, moduleResolution: bundler)
|
||||
- External deps (loop, metrics): `@inquirer/prompts`, `chalk`, `execa`, `fs-extra`, `ora`
|
||||
- External deps (bot): `@anthropic-ai/claude-agent-sdk`, `chalk`, `fs-extra`, `ora`
|
||||
- Interactive CLI via `@inquirer/prompts` (select, input, confirm)
|
||||
- **File operations:** Synchronous fs by default; the web console's fire-and-forget sweeps and `readOverview()` use `fs.promises`
|
||||
- **src/web-console:** ESM, Node built-ins only, no build step. It is bundled into every skill, so it must stay dependency-free and runnable as a plain `node console.mjs`. Anything added under `src/web-console/` ships to users — put tests in `scripts/` instead.
|
||||
|
||||
## Gotchas / Pitfalls
|
||||
|
||||
- **Version sync:** When adding a new version to `CHANGELOG.md`, also update `version.json` and `package.json` (root) to match. `README.md` (the `Version X.Y.Z` line near the top) also carries the version, and `version.json`'s `releaseDate` moves with it. `version.json` is copied into every skill's `references/web-console/` (the console's Help shows it), so after a bump run `npm run build:skills` or `npm test` (`--verify-skills`) fails. The installer displays the version from `version.json` in its header. All three files (`CHANGELOG.md`, `version.json`, `package.json`) must always show the same version number.
|
||||
- **CHANGELOG ordering:** Entries in `CHANGELOG.md` must be in reverse-chronological order — newest version at the top, oldest at the bottom. New entries are always inserted immediately after the file header.
|
||||
- **CHANGELOG house format is not Keep a Changelog:** version headings are `## vX.Y.Z` — with a `v` prefix and **no date**. The release date is recorded only in `version.json`'s `releaseDate`. Category headings carry emoji: `### ✨ Added`, `### 🔧 Changed`, `### 🐛 Fixed`, `### 💥 Breaking`, `### 🗑️ Removed`, `### 📚 Documentation`. Older entries contain one-off variants (`🎁 Added`, `📦 Updated`, `📝 Documentation`, `🏎️ Improved`, `🧪 Testing`) — do not introduce new ones. The `.claude/skills/plan2code-changelog/` skill automates version selection and formatting; use it rather than hand-rolling an entry.
|
||||
- **PowerShell mangles the CHANGELOG emoji:** `Get-Content` / `Select-String` render the `###` heading emoji as `?` under the default Windows console encoding, so a heading audit done that way reports garbage. Read `CHANGELOG.md` with a file-read or grep tool instead.
|
||||
- **`.claude/skills/` is tracked:** a new repo-local skill only needs `git add` (see Architecture → Repo-Local Skills). A correction that is a workflow belongs there as a skill, linked from AGENTS.md, not as a Failure log line.
|
||||
- **Loop `.gitignore` setup:** `ensureGitignore()` runs at startup in `Controller.run()` as a pre-flight step, not just inside `createTaskCommit()`. This is critical for phase mode where the Node controller doesn't handle commits — without it, `git add -A` would stage spec files.
|
||||
- **Workflow file character limit:** All `src/plan2code-*.md` files (and the dashboard prompt `src/plan2code.md`) must be ≤ 20,000 characters (about 5k tokens, the usual Agent Skills guidance for a SKILL.md body). A husky pre-commit hook enforces this, and `plan2code-metrics` (`improver.ts`, `applier.ts`) applies the same number to proposed prompt edits, so change them together. History: 11,000 originally (headroom under Windsurf's old 12,000-char limit for platform-specific files, gone since 2.1.0's single-format build), 11,500 in 2.4.0, 20,000 in 2.4.1. The limit is now a prompt-size discipline only: the whole SKILL.md loads on every invocation while references load on demand, so situational detail still belongs in a reference file, and anything with one correct answer belongs in a script (see Skill scripts in the architecture doc).
|
||||
- **Keep LF line endings:** `.gitattributes` pins `eol=lf` because `validate-char-count.js` counts the characters on disk, and a CRLF checkout adds about one per line to every prompt. Measure with `node scripts/validate-char-count.js` before trusting a near-limit prompt.
|
||||
- **The pre-commit hook runs only the char-count check:** `.husky/pre-commit` is `node scripts/validate-char-count.js` alone. `skills/` drift, parse errors and test failures are caught only by `npm test`, so run it before committing. Sub-package tests are separate; see [Development Commands](./AGENTS-development-commands.md).
|
||||
- **`skills/` is generated build output (gitignored):** edit `src/` only. The installer rebuilds `skills/` on every run, so it is always up to date at install time. `npm test` runs `install.js --build-skills` so a broken `SOURCE_PROMPTS` entry or unreadable source fails CI. Never hand-edit `skills/`; `install.js --verify-skills` can diff a stale tree against `src/` when diagnosing.
|
||||
- **Metrics internal prompts have no char limit:** Files in `plan2code-metrics/src/prompts/` are NOT subject to the 20,000 char limit — only `src/plan2code-*.md` consumer-facing prompts are.
|
||||
- **User Feedback table format:** The `## User Feedback` markdown table in `overview.md` has a strict format the collector regex depends on. Field names must be exactly `Rating`, `Reason`, `Went Well`, `Went Poorly`. Pipe characters in values must be escaped as `\|`.
|
||||
- **PLAN-DRAFT confidence numbers are scraped by regex:** `collector.ts` scrapes the latest `specs/<feature>/PLAN-DRAFT-*.md` prose. Overall confidence falls back to prose only when `<!-- METRICS_JSON ... -->` lacks `confidence` (`collector.ts:186-196`): `Confidence: 95%`, or a table row `| Confidence | 95` with no `%`. The four *breakdown* patterns (`collector.ts:200-203`) run on every draft, METRICS_JSON or not: `/[Rr]equirements?[:\s|]+(\d{1,2})/` and its siblings match a bare dimension word followed by whitespace, a colon, or a pipe and then digits. So a PLAN-DRAFT written by anything other than `/plan2code-1-plan` Phase 7 must keep `Confidence` followed by a number (with `%`, or as a table row) **and** bare `Requirements` / `Feasibility` / `Integration` / `Risk` followed by a number off the page — including innocent table rows like `| Requirements | 11 |`. Otherwise the metrics pipeline records a planning-step confidence that no planning step produced. `/plan2code-0-pathfinder` works around this by hyphenating the labels (`Requirements-clarity 22/25`), which breaks the character class.
|
||||
- **Web console result-handoff invariant:** `result.json` holds answers a person pressed Send on. **An uncollected result (no `consumedAt`) is never overwritten and never deleted.** `/submit` and `/cancel` return 409 while one is pending, `open` clears the file only when it is already consumed, and `wait` stamps `consumedAt` **after** printing the result, never before, and exits by setting `process.exitCode` rather than calling `process.exit()`. That ordering is deliberate: an agent harness that kills a long shell command must not be able to land between "marked collected" and "handed over", and `process.exit()` can truncate an unflushed pipe. A repeat delivery is recoverable, a lost one is not. Two separate data-loss bugs came from breaking this in different places, and both were silent: the person sees "Sent", the agent never receives it. Any new code path that touches `result.json` must preserve the invariant, and `scripts/test-web-console-lifecycle.mjs` guards it (its "result handoff (regressions)" tests). Related: the server writes each submitted answer onto its item as `submitted`, and `validate()` in `patches.mjs` must keep excluding that field from the completion-marker and metrics-scraper scans, which are meant for agent-authored text only. A person who typed `TASK_COMPLETE` into an answer would otherwise make every later patch unpostable.
|
||||
- **Web console oversized bodies:** `readBody()` and `readRaw()` (the `POST /upload` reader) in `routes.mjs` drain the rest of the body past `MAX_BODY` instead of calling `req.destroy()`, so an oversized body gets a 413 rather than a connection reset, and memory still stays capped. A new body reader must drain the same way.
|
||||
- **Web console commands are tied to the directory `open` ran in:** `console.mjs` finds a running server through a handle file under a hash of the project directory (`handleFile(project, sid)` → `runtimeDirFor(project)` → `<RUNTIME_DIR>/<cwdHash(project)>/<sid>.json` in `sessions.mjs`, with `RUNTIME_DIR` = `os.tmpdir()/plan2code-console`, or `$PLAN2CODE_CONSOLE_HOME/runtime`), and the project is the working directory of `open` / `open --resume`. Run `status`, `chat`, `wait` and `stop` from that same directory. From anywhere else `status` says `live: false`, `chat` / `wait` report `server-gone` (exit 20) and `stop` stops nothing, while the server is in fact still running. It is easy to mistake for a crash when a scratch session is opened from the repo and then driven from its session folder; check `server.log` and `events.ndjson` (a real exit writes an `exit` event or a stack) before chasing one.
|
||||
- **Windows temp paths in web console tests:** `os.tmpdir()` can be an 8.3 short path (`C:\Users\JUSTIN~1.PAR\...`), while `server.mjs` canonicalises its session dir with `fs.realpathSync.native` to the long form. Any test comparing a server-returned path (e.g. an upload's `path`) against the test's `session` must pass the test side through `fs.realpathSync.native()` first, and compare case-insensitively on Windows.
|
||||
- **Web console assets:** `computeExpectedSkills()` copies references as `Buffer`s, so binary files are fine. Adding a `public/` file needs the three edits in Architecture → Web Console. The vendored `marked.esm.js` sha256 is in `.readme/web-console.md`.
|
||||
- **The default highlight color lives in two places:** changing it means editing `DEFAULT_ACCENT` in `public/palette.js` and the light, system-dark and explicit-dark `--accent*` values in `public/styles/tokens.css`. No test ties them together.
|
||||
- **Reference file sizing guideline:** Files in `src/plan2code-*-references/` directories target ~100-200 lines each (soft guideline; evaluate splitting above 300). They are NOT subject to the 20,000 character limit. The pre-commit hook (`validate-char-count.js`) only checks `src/plan2code-*.md` flat files — subdirectory contents are automatically excluded.
|
||||
- **The splitting guideline has a hard ceiling — reference files cannot always be split:** each new reference costs the orchestrator a `Read references/<file>.md` line plus its fallback blockquote (~150-200 chars), which adds up across a prompt's 20,000-char budget. When a reference legitimately exceeds 300 lines (e.g. `plan2code-0-pathfinder-references/chart.md`), that is an accepted trade-off, not an oversight. Nested folders under `-references/` work: `references/` is the real path on every agent.
|
||||
- **Windows global bins for loop, metrics and bot are wrappers, not `npm link`:** on win32 the installer writes `<name>.cmd` and `<name>.ps1` into `npm config get prefix`, each running `node <package>/dist/bin/<name>.js` (`install.js:1302-1323` for the loop; the metrics and bot installers do the same). After a source change, `npm run build` in the package is enough; no reinstall.
|
||||
- **plan2code-metrics only runs from a repo checkout:** `analyzer.ts` and `improver.ts` load `src/prompts/analyze.md` / `improve.md` at runtime through `new URL('../src/prompts/...', import.meta.url)`, resolved relative to `dist/` (`analyzer.ts:11`, `improver.ts:13`). A packed or copied `dist/` without `src/prompts/` fails.
|
||||
@@ -0,0 +1,156 @@
|
||||
# Development Commands
|
||||
> Part of [AGENTS.md](../AGENTS.md) — project guidance for AI coding agents.
|
||||
|
||||
## Common Commands
|
||||
|
||||
```bash
|
||||
# Install dev dependencies (sets up husky pre-commit hooks only; each sub-package
|
||||
# below needs its own npm install. Running `npm test` needs Node 20+; users of
|
||||
# the installed skills still need only Node 18+)
|
||||
npm install
|
||||
|
||||
# Run the interactive installer
|
||||
node install.js
|
||||
|
||||
# Regenerate skills/ from src/ (non-interactive)
|
||||
npm run build:skills
|
||||
|
||||
# Full check (about 70s): char limits, skills/ build, browser-module parse check,
|
||||
# dashboard skill-table check, web console + launcher + getting-started node:test suites
|
||||
npm test
|
||||
|
||||
# One web console or launcher test
|
||||
node --test --test-name-pattern "<regex>" scripts/test-web-console-<area>.mjs
|
||||
|
||||
# Web console start-up benchmark (the paint columns use a local Chrome or Edge through
|
||||
# playwright-core, which `npm install` already provides)
|
||||
node scripts/bench-web-console.mjs [--runs 7] [--workflow dashboard]
|
||||
|
||||
# Refresh the web console screenshots in docs/screenshots/ (needs a local Chrome or Edge).
|
||||
# Rerun after any change a person would see on the console page, and open every image
|
||||
# before committing: right screen, both themes, no username or home path in frame.
|
||||
# PLAN2CODE_TEST_BROWSER=chrome|msedge forces which browser the page tests and these scripts use
|
||||
node scripts/capture-screenshots.mjs # every screen
|
||||
node scripts/capture-screenshots.mjs --only dashboard # one screen (dashboard-utilities scrolls to the utility cards)
|
||||
|
||||
# Compare every element's computed style on every screen before and after a stylesheet change
|
||||
# (dev-only, not in npm test): take a baseline first, then compare after each move
|
||||
node scripts/css-snapshot.mjs --out before.json
|
||||
node scripts/css-snapshot.mjs --compare before.json
|
||||
|
||||
# Plan2Code Loop
|
||||
cd plan2code-loop && npm install # First time setup
|
||||
cd plan2code-loop && npm run build # Build the CLI
|
||||
|
||||
# Plan2Code Metrics
|
||||
cd plan2code-metrics && npm install # First time setup
|
||||
cd plan2code-metrics && npm run build # Build the CLI
|
||||
cd plan2code-metrics && npm test # vitest (aggregator, community, improver)
|
||||
|
||||
# Plan2Code Bot (end-to-end workflow runner, Claude Agent SDK)
|
||||
cd plan2code-bot && npm install && npm run build
|
||||
cd plan2code-bot && npm test # vitest
|
||||
```
|
||||
|
||||
The root `npm test` does not run the metrics or bot vitest suites; run them in their package. `npm run dev` in loop, metrics and bot is `tsup --watch`. The web console and launcher suites isolate themselves with `PLAN2CODE_CONSOLE_HOME`, `PLAN2CODE_MODELS_DIR` and `PLAN2CODE_NO_BROWSER=1` (`scripts/web-console-test-helpers.mjs`), so they never open a browser or touch your real console home. The web console suites are split by area so `node --test` runs them in parallel.
|
||||
|
||||
## Test/Dev Env Vars
|
||||
|
||||
| Variable | Effect |
|
||||
|----------|--------|
|
||||
| `PLAN2CODE_CONSOLE_HOME` | Replaces `~/.plan2code/console`: sessions, `looks.json` and the runtime handle dir all move under it (`src/web-console/files.mjs`). Always set it for scratch runs so `stop --all` cannot reach real sessions. |
|
||||
| `PLAN2CODE_NO_BROWSER` | `open` does not launch a browser (`NO_BROWSER` also works). |
|
||||
| `PLAN2CODE_BROWSER` | Browser command line to run with the link appended, instead of the system default. |
|
||||
| `PLAN2CODE_MODELS_DIR` | Moves the launcher model menus (`bin/models.json`, `models.json`) away from `~/.plan2code`, for tests. |
|
||||
| `PLAN2CODE_PICKER_ECHO` | Tests only: `/workspace/browse` returns this as the picked folder instead of opening a picker (`-` means cancelled). |
|
||||
| `PLAN2CODE_CONSOLE_TRACE` | Set to `1` on `open` to print a start-up step timeline to stderr. |
|
||||
|
||||
## Installer Menu Options
|
||||
|
||||
**Main menu:**
|
||||
|
||||
| Option | Action |
|
||||
|--------|--------|
|
||||
| `I` | Install the Plan2Code skills globally via the `skills` CLI, plus the global `plan2code` command (opens the dashboard in Claude Code, Devin or Codex), then print the getting-started steps. No dev tools |
|
||||
| `U` | Uninstall Plan2Code: skills + `plan2code` command + `plan2code-loop` + `plan2code-metrics` + `plan2code-bot` + Claude Code status line (confirmation required) |
|
||||
| `A` | Open the ADVANCED sub-menu |
|
||||
| `Q` | Quit |
|
||||
|
||||
**ADVANCED sub-menu (`A`):**
|
||||
|
||||
| Option | Action |
|
||||
|--------|--------|
|
||||
| `L` | Install the skills into the current project instead of globally |
|
||||
| `O` | Install plan2code-loop CLI only |
|
||||
| `M` | Install plan2code-metrics CLI only |
|
||||
| `S` | Install Claude Code status line only |
|
||||
| `B` | Install plan2code-bot CLI only |
|
||||
| `D` | Install the global `plan2code` command only |
|
||||
| `E` | Everything: the skills, the `plan2code` command and every dev tool (`plan2code-loop`, `plan2code-bot`, `plan2code-metrics`, the Claude Code status line) |
|
||||
| `Q` | Return to main menu |
|
||||
|
||||
## Non-Interactive Flags
|
||||
|
||||
`install.js` takes no arguments for normal use, but exposes two build hooks and the non-interactive update. Any argument other than these three (when none is present) exits 1 with usage; extra arguments beside `--build-skills` or `--verify-skills` are ignored, while `--update` must be the only argument.
|
||||
|
||||
| Flag | Action |
|
||||
|------|--------|
|
||||
| `--build-skills` | Regenerate `skills/` from `src/`, pruning stale skills and reference files |
|
||||
| `--verify-skills` | Diff local `skills/` against `src/`; exits 1 on drift. Diagnostic only, the installer rebuilds anyway |
|
||||
| `--update` | No menu: reinstall what `~/.plan2code/install.json` lists (skills, launcher, statusline, loop, metrics, bot), never uninstalling; with no record, the skills and the `plan2code` command. `plan2code update` runs it through npx |
|
||||
|
||||
## How the Installer Works
|
||||
|
||||
1. **Builds `skills/` from `src/`** — one Agent Skill per source prompt, including uncommitted source edits.
|
||||
2. **Checks the skills CLI is reachable** with `npx --yes skills --version`.
|
||||
3. **Sweeps pre-2.2 install paths** and removes installed `plan2code-*` skills so renamed or retired prompts cannot survive as orphans.
|
||||
4. **Delegates installation** to `npx --yes skills add "<repo>/skills" -g -s <skill names> -y`.
|
||||
5. **Installs the global `plan2code` command** (only when step 4 succeeded). Advanced → `L` runs the same flow without `-g` and without the launcher.
|
||||
|
||||
The skills CLI owns distribution from step 4 onward. It stores canonical skills under `~/.agents/skills/` and links them into agents that maintain their own skill directory. Plan2Code no longer maintains platform-specific output formats.
|
||||
|
||||
**Invocation choices:**
|
||||
|
||||
| Choice | Reason |
|
||||
|--------|--------|
|
||||
| Explicit space-separated `-s <names>` | Avoids shell expansion and prevents unrelated directories under `skills/` from being installed. |
|
||||
| No `-a` / `--agent '*'` | Uses the CLI's supported default agent set instead of requesting incompatible scope/agent combinations. |
|
||||
| Captured output | Suppresses the CLI's duplicated banners while preserving real failures; unsupported-scope noise is filtered. |
|
||||
|
||||
## Skill Format
|
||||
|
||||
| Item | Value |
|
||||
|------|-------|
|
||||
| Path | `skills/<skill-name>/SKILL.md` |
|
||||
| Skill name | `generateSkillName(prompt)`, such as `plan2code-1-plan` or `plan2code-init` |
|
||||
| Frontmatter | `name`, `description`, `disable-model-invocation: true` |
|
||||
| Reference files | `skills/<skill-name>/references/<path>`, copied from `src/<prompt>-references/` and `additionalReferences` (any file type; every skill bundles `web-console/` plus a copy of `version.json`) |
|
||||
| Scripts | `skills/<skill-name>/scripts/<file>.mjs`, plus `common.mjs` and a generated `version.json` (see Skill Scripts in the architecture doc) |
|
||||
|
||||
`disable-model-invocation: true` is unconditional because these workflows are user-initiated. Agents that do not recognize the field ignore it.
|
||||
|
||||
## Editing Workflow Prompts
|
||||
|
||||
See the `skills/` build-artifact gotcha in [Code Style & Gotchas](./AGENTS-code-style.md).
|
||||
|
||||
1. Edit the source file under `src/`.
|
||||
2. Run `npm run build:skills`.
|
||||
3. Test the workflow in an AI tool.
|
||||
4. `skills/` is gitignored, so only the `src/` change is committed.
|
||||
5. Never edit `skills/` by hand because the next build overwrites it.
|
||||
|
||||
## Adding a New Workflow Prompt / Skill
|
||||
|
||||
1. Create `src/plan2code-<name>.md` with body content only and keep it under 20,000 characters.
|
||||
2. Register it in `SOURCE_PROMPTS` in `install.js` (with the web-console `additionalReferences` entry every skill carries); add a `generateStepLabel()` case when needed. List any shared scripts it runs in `scripts: [...]`, and put its own scripts in `src/plan2code-<name>-scripts/` (with a `scripts/test-script-<name>.mjs` added to `package.json`'s `test` list).
|
||||
3. Register it with the web console. The meter's points and labels, the resume command, Help's card list and `console.mjs help`'s workflow list are all derived from `skills.js`, so the edits are `skills.js`, `install.js` (step 2), the skill's prompt (step 1), its pose and its notes; `npm test` names anything else left out:
|
||||
- `src/web-console/public/skills.js`: one entry (workflow, label, start pose, flags, subagents line, the meter's `weight`, `started` and `ran`, and `resume`) with its card (plus `help` when Help's line should differ from the blurb), and the card's `states` and `greyed`. Utilities go in group `"extra"` before Changelog.
|
||||
- `src/web-console/public/index.html`: its start pose, an `<svg class="pose pose-<workflow>" data-pose="<workflow>">` in `<template id="start-poses">` (pose CSS in `public/styles/poses.css`), unless its `pose` borrows an existing one (as Implement + Review borrows Implement's).
|
||||
- Its help topic: a `src/web-console/notes/<workflow>.md` (named in the skill's Interface line) or a `HELP_TOPICS` alias in `src/web-console/cmd-help.mjs`.
|
||||
- `src/plan2code.md`: the skill/workflow table and "What each skill reads and writes" (`scripts/check-skill-table.mjs`: every backticked token must appear in the skill's prompt).
|
||||
- `console.md` (the `open --workflow` list and the `notes/<workflow>.md` row).
|
||||
- Optional: `STARTER_SET_FOR` in `public/starters.js` (unlisted gets "general").
|
||||
|
||||
**Adding a spec state** is shorter: one entry in `src/web-console/public/spec-states.js`, the detection in `classifySpec()` in `src/web-console/scan.mjs`, the `states` of each card in `skills.js` that takes it, and a line in the dashboard skill (`src/plan2code.md`); then `npm test`.
|
||||
4. Update command inventories in `README.md` (dashboard-card and command tables), `QUICK-REFERENCE.md`, `.agents-docs/AGENTS-architecture.md` (prompt table, own-script rows, notes list), and `CHANGELOG.md`. Update `docs/index.html` for core pipeline steps, and for a utility only when it is a headline change (its `.utils` block).
|
||||
5. Run `npm run build:skills` and `npm test`.
|
||||
@@ -0,0 +1,54 @@
|
||||
# Plan2Code Loop
|
||||
> Part of [AGENTS.md](../AGENTS.md) — project guidance for AI coding agents.
|
||||
|
||||
A separate Node.js CLI tool that autonomously implements specs by looping through tasks.
|
||||
|
||||
## Loop Architecture
|
||||
|
||||
The loop uses an **LLM-driven discovery** approach:
|
||||
- Node app just orchestrates iterations and parses completion markers
|
||||
- The LLM reads spec files (`overview.md`, `phase-X.md`) to discover tasks
|
||||
- The LLM finds unchecked checkboxes, implements ONE task per iteration, marks it complete
|
||||
- No regex parsing of markdown in Node - the AI handles all task discovery
|
||||
|
||||
## Loop Commands
|
||||
|
||||
Run `plan2code-loop` in a project (fully interactive, no flags). Build commands: see [Development Commands](./AGENTS-development-commands.md).
|
||||
|
||||
The CLI auto-detects specs in `./specs/`, prompts for selection if multiple found, and handles session continuation interactively. Only `specs/<feature>/overview.md` is detected; archived specs in `specs--completed/` are ignored. Session state is stored per-spec in `specs/<feature>/.plan2code-loop/`.
|
||||
|
||||
Exit codes: 0 all complete, 1 max iterations, 2 interrupted (SIGINT/SIGTERM saves state), 3 error. The state dir holds `config.json`, `scratchpad.md` (LLM notes), `iteration.log` (NDJSON) and `spec.hash` (a mismatch prompts "Start fresh?"). Defaults: 100 max iterations, 3 min timeout, 5 retries.
|
||||
|
||||
## Supported Agents
|
||||
|
||||
Claude Code, GitHub Copilot CLI, Devin CLI, defined in `plan2code-loop/src/agents/` (one file each, registered in `agents/index.ts`).
|
||||
|
||||
## Loop Modes
|
||||
|
||||
The CLI asks users to choose a loop mode:
|
||||
- **One task per loop** (default) - Each agent invocation implements exactly one task. The Node controller handles git commits.
|
||||
- **One phase per loop** - Each agent invocation implements all remaining tasks in the current phase. The LLM handles git commits (with JIRA ticket ID if provided). The controller parses multiple completion markers from a single iteration.
|
||||
|
||||
## Completion Markers
|
||||
|
||||
The LLM must output one of these formats:
|
||||
- `TASK_COMPLETE: 1.1 - Task description` - Task done successfully
|
||||
- `TASK_BLOCKED: 1.1 - Reason` - Cannot complete task
|
||||
- `PHASE_COMPLETE` - Current phase finished (phase mode only)
|
||||
- `LOOP_COMPLETE` - All phases finished
|
||||
- `PREREQ_COMPLETE: P1.1 - Description` - Prerequisite verified
|
||||
- `PREREQ_ASSUMED: P2.1 - Description` - Prerequisite that cannot be verified, assumed met
|
||||
|
||||
Parsing is in `utils/completion.ts` and is lenient: `TASK_COMPLETE: 1.1: x` and `TASK_COMPLETE[1.1]: x` also match.
|
||||
|
||||
## Key Source Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `plan2code-loop/src/controller.ts` | Main loop orchestrator |
|
||||
| `plan2code-loop/src/prompt/templates.ts` | Prompt templates for both loop modes |
|
||||
| `plan2code-loop/src/utils/git.ts` | `createTaskCommit()` — handles task-mode commits with footer |
|
||||
| `plan2code-loop/src/cli.ts` | Interactive session setup (spec, agent, JIRA ID, loop mode, max iterations, resume/fresh) |
|
||||
| `plan2code-loop/src/utils/completion.ts` | Marker parsing (`checkForCompletion` task mode, `checkForAllCompletions` phase mode) |
|
||||
| `plan2code-loop/src/state/manager.ts` | Per-spec state dir, spec hash, iteration log |
|
||||
| `plan2code-loop/src/agents/` | Agent adapters (claude-code, copilot-cli, devin-cli) |
|
||||
@@ -0,0 +1,89 @@
|
||||
# Plan2Code Metrics
|
||||
> Part of [AGENTS.md](../AGENTS.md) — project guidance for AI coding agents.
|
||||
|
||||
A recursive self-improvement toolchain for plan2code contributors. Collects run metrics, aggregates by prompt generation, diagnoses weak steps via AI, and proposes surgical prompt edits.
|
||||
|
||||
## Metrics Data Flow
|
||||
|
||||
```
|
||||
Collect → Aggregate → Analyze → Improve → Apply
|
||||
```
|
||||
|
||||
1. **Collector** reads project artifacts (`specs/<feature>/`) → writes `RunMetrics` JSON per run
|
||||
2. **Aggregator** groups runs by prompt SHA fingerprint (cohorts) → `aggregated.json`
|
||||
3. **Analyzer** invokes AI with aggregated metrics + prompt contents → diagnosis markdown
|
||||
4. **Improver** invokes AI with diagnosis → validated `PromptEdit[]` proposals (char limit + verbatim checks)
|
||||
5. **Applier** shows interactive diffs → patches `src/plan2code-*.md` files
|
||||
|
||||
## Metrics Commands
|
||||
|
||||
Run `plan2code-metrics` (fully interactive, no flags). Build and test commands: see [Development Commands](./AGENTS-development-commands.md).
|
||||
|
||||
## Metrics CLI Menu
|
||||
|
||||
| Option | Action |
|
||||
|--------|--------|
|
||||
| Collect | Read spec artifacts → run JSON |
|
||||
| Import | Copy run JSON from another project |
|
||||
| View | Display cohort metrics with health indicators |
|
||||
| Analyze | AI diagnosis of weak metrics |
|
||||
| Propose | AI improvement proposals with validation |
|
||||
| Apply | Interactive diff review + file patching |
|
||||
| Fetch community submissions | List/parse/import open community-feedback GitHub issues from jparkerweb/plan2code, close on success |
|
||||
| Delete metrics data | Delete selected runs, all runs + aggregated data, or everything including proposals |
|
||||
|
||||
Community submissions arrive as GitHub issues labeled `community-feedback` on `jparkerweb/plan2code`, created by the finalize prompt's post-Step-6 submission flow; the "Fetch community submissions" option requires an authenticated `gh` CLI to list/close them.
|
||||
|
||||
## Key Source Files
|
||||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `types.ts` | All interfaces (`RunMetrics`, `UserFeedback`, `CohortMetrics`, etc.) + `METRIC_TARGETS` |
|
||||
| `collector.ts` | Reads project artifacts → run JSON (parses plan drafts, overview.md, loop logs) |
|
||||
| `aggregator.ts` | Merges runs by prompt generation (SHA cohort) → `aggregated.json` |
|
||||
| `community.ts` | Lists/parses/closes `community-feedback`-labeled GitHub issues via `gh` CLI |
|
||||
| `analyzer.ts` | AI diagnosis via `prompts/analyze.md` template |
|
||||
| `improver.ts` | AI proposals via `prompts/improve.md` + validation (char count, old_text match) |
|
||||
| `applier.ts` | Interactive diff review + file patching |
|
||||
| `cli.ts` | Menu-driven interactive CLI (100% prompts, no flags) |
|
||||
| `invoke-llm.ts` | Unified LLM interface (Claude Code, GitHub Copilot CLI, or Devin CLI) |
|
||||
| `*.test.ts` | vitest suites for aggregator, community, improver (`npm test` in `plan2code-metrics/`) |
|
||||
|
||||
## User Feedback
|
||||
|
||||
The collector parses an optional `## User Feedback` table from `overview.md`:
|
||||
|
||||
```markdown
|
||||
## User Feedback
|
||||
| Field | Value |
|
||||
|-------|-------|
|
||||
| Rating | 8 |
|
||||
| Reason | Smooth workflow |
|
||||
| Went Well | Planning was thorough |
|
||||
| Went Poorly | Some tasks unclear |
|
||||
```
|
||||
|
||||
Feedback is collected during finalize (Step 5) or retroactively via the CLI. Pipe characters in values are escaped as `\|`. The aggregator computes `avg_user_rating` and `feedback_count` per cohort.
|
||||
|
||||
## Supported AI Agents
|
||||
|
||||
- **Claude Code** (recommended): `claude --print --dangerously-skip-permissions`, prompt written to a temp file and piped to stdin (execa `inputFile`)
|
||||
- **GitHub Copilot CLI**: `copilot --allow-all-tools -s`, prompt on stdin (default model `claude-sonnet-4`)
|
||||
- **Devin CLI**: `devin` CLI with `--print --prompt-file <file> --permission-mode dangerous`
|
||||
|
||||
## Metric Targets
|
||||
|
||||
| Metric | Target | Direction |
|
||||
|--------|--------|-----------|
|
||||
| `avg_confidence` | ≥ 90 | higher is better |
|
||||
| `avg_clarification_rounds` | ≤ 2.0 | lower is better |
|
||||
| `avg_verification_gaps_found` | ≤ 2.0 | lower is better |
|
||||
| `avg_parallel_groups` | ≥ 0.5 | higher is better |
|
||||
| `avg_verification_items_added` | ≤ 1.5 | lower is better |
|
||||
| `avg_task_completion_rate` | ≥ 0.95 | higher is better |
|
||||
| `avg_blocker_count` | ≤ 1.5 | lower is better |
|
||||
| `avg_verification_failures_found` | ≤ 1.0 | lower is better |
|
||||
| `archival_success_rate` | ≥ 0.99 | higher is better |
|
||||
| `avg_user_rating` | ≥ 7.0 | higher is better |
|
||||
|
||||
On start the CLI asks for the plan2code repo path (default: saved `plan2codeRepoPath` in `~/.plan2code-metrics.json`, else auto-detected up to 5 parent dirs) and the project path (default: cwd). Data is stored in `<project>/.plan2code-metrics/` (runs/, aggregated.json, proposals/).
|
||||
@@ -0,0 +1,149 @@
|
||||
---
|
||||
name: plan2code-changelog
|
||||
description: "Validate and fix the CHANGELOG.md version number before opening a PR. Reads main branch to determine the current latest version, classifies changes on the current branch, and proposes the correct next semver. Use this skill when the user mentions changelog, version number, preparing a PR, release version, semver check, or says 'check the changelog', 'what version should this be', 'prepare for PR', or 'fix the version'. Also use proactively when you notice a CHANGELOG entry that may have an incorrect version number."
|
||||
---
|
||||
|
||||
# Plan2Code Changelog Validator
|
||||
|
||||
Ensure the CHANGELOG.md entry for the current branch has the correct semver version before a PR is opened. This skill exists because parallel branches independently pick version numbers that collide or leap-frog when merged — this validates against main's actual state right before the PR.
|
||||
|
||||
## Workflow
|
||||
|
||||
### Step 1 — Gather state
|
||||
|
||||
Run these commands to understand the current situation:
|
||||
|
||||
```bash
|
||||
# 1. Current latest version on main
|
||||
git show main:CHANGELOG.md | head -20
|
||||
|
||||
# 2. Current branch name (for ticket ID extraction)
|
||||
git branch --show-current
|
||||
|
||||
# 3. What this branch changed (commit subjects)
|
||||
git log main...HEAD --oneline
|
||||
|
||||
# 4. Files changed on this branch
|
||||
git diff main...HEAD --name-only
|
||||
```
|
||||
|
||||
Extract from main's CHANGELOG:
|
||||
- The **latest version number** (first `## vX.Y.Z` line)
|
||||
|
||||
Note: on Windows, PowerShell's console encoding mangles the emoji in the `###` headings to `?`. Read `CHANGELOG.md` with the file-read or grep tool rather than `Get-Content` / `Select-String` when you need to see them.
|
||||
|
||||
Extract from the branch:
|
||||
- The **list of changed files** to classify the change type
|
||||
- The **commit messages** for changelog entry content
|
||||
|
||||
### Step 2 — Classify the change
|
||||
|
||||
Determine the change type by examining what was modified on this branch:
|
||||
|
||||
| Signal | Classification | Version Bump | Heading |
|
||||
|--------|---------------|--------------|---------|
|
||||
| An install target removed, or an existing workflow's contract broken | Breaking change | **Major** (X.0.0) | `### 💥 Breaking` |
|
||||
| New workflow prompt (`.md` file under `src/`) | New workflow | **Minor** (x.Y.0) | `### ✨ Added` |
|
||||
| New capability added to an existing prompt, or a new `.claude/skills/` skill | New capability | **Patch** (x.y.Z) | `### ✨ Added` |
|
||||
| Behavioral changes to existing prompt(s), installer, or docs | Behavior change | **Patch** (x.y.Z) | `### 🔧 Changed` |
|
||||
| Bug fix to existing prompt(s) or tooling | Bug fix | **Patch** (x.y.Z) | `### 🐛 Fixed` |
|
||||
| A prompt, target, or file deleted | Removal | **Patch** (x.y.Z) | `### 🗑️ Removed` |
|
||||
| README / `.readme/` / docs-site only | Documentation | **Patch** (x.y.Z) | `### 📚 Documentation` |
|
||||
| Mix of the above | Use the **highest** bump (major > minor > patch) | Combine headings |
|
||||
|
||||
Use only the headings in this table — the CHANGELOG has historical one-off variants (`🎁 Added`, `📦 Updated`, `📝 Documentation`, `🏎️ Improved`, `🧪 Testing`) that should not be introduced in new entries.
|
||||
|
||||
### Step 3 — Compute the correct version
|
||||
|
||||
Starting from main's latest version:
|
||||
- **Major bump:** increment the first number, reset the rest (e.g., `1.16.1` → `2.0.0`)
|
||||
- **Minor bump:** increment the middle number, reset patch to 0 (e.g., `2.0.0` → `2.1.0`)
|
||||
- **Patch bump:** increment the last number (e.g., `2.1.0` → `2.1.1`)
|
||||
|
||||
### Step 4 — Check the current branch's CHANGELOG
|
||||
|
||||
Read the current `CHANGELOG.md` on the branch. Look for:
|
||||
|
||||
0. **You are on `main` with no diff** — there is no branch to validate. Instead, compare the top CHANGELOG version against `git log` since the commit that released it: if commits have landed on `main` without a CHANGELOG entry, treat those commits as the change set and continue from Step 2. Say so explicitly rather than reporting "nothing to do."
|
||||
|
||||
1. **No entry exists yet for this branch's work** — the branch hasn't added a version entry above main's latest. Proceed to Step 5 to draft one.
|
||||
|
||||
2. **An entry exists but the version is wrong** — the branch has a version entry, but it doesn't match the computed correct version (common when branches were rebased or other PRs merged first). Report the discrepancy:
|
||||
|
||||
```
|
||||
Version check for branch: {branch-name}
|
||||
|
||||
Main is at: {main-version}
|
||||
Branch claims: {branch-version}
|
||||
Correct version: {computed-version} ({classification})
|
||||
|
||||
The version needs to be updated: {branch-version} → {computed-version}
|
||||
```
|
||||
|
||||
Ask: "Update the version to {computed-version}? (yes / no)"
|
||||
|
||||
3. **An entry exists and the version is correct** — report success:
|
||||
|
||||
```
|
||||
Version check for branch: {branch-name}
|
||||
|
||||
Main is at: {main-version}
|
||||
Branch version: {branch-version} ({classification})
|
||||
|
||||
Version is correct. CHANGELOG is ready for PR.
|
||||
```
|
||||
|
||||
Stop here unless the user asks for content changes.
|
||||
|
||||
### Step 5 — Draft or fix the CHANGELOG entry
|
||||
|
||||
**If no entry exists**, draft a new one based on the commits and changed files. Match this repo's house format exactly — a bare `## vX.Y.Z` heading with **no date**, emoji `###` headings from the Step 2 table, and a blank line between bullets:
|
||||
|
||||
```markdown
|
||||
## {computed-version-with-v-prefix}
|
||||
|
||||
### ✨ Added
|
||||
|
||||
- **{prompt-or-area}** — {what changed, and why it matters to someone installing it}
|
||||
|
||||
### 🔧 Changed
|
||||
|
||||
- **{prompt-or-area}** — {what changed}
|
||||
```
|
||||
|
||||
Conventions to follow, drawn from existing entries:
|
||||
|
||||
- Bold lead-in naming the prompt, file, or area, then an em dash (`—`), then the description.
|
||||
- Reference prompts by their command (`/plan2code-1-plan`) or path (`src/plan2code-init.md`), not by informal name.
|
||||
- One paragraph per bullet is fine — this CHANGELOG favours substantive entries over terse one-liners, and a bullet may carry extra indented paragraphs for detail.
|
||||
- A release with a big theme may open with a one-line summary paragraph directly under the `## vX.Y.Z` heading, before the first `###`.
|
||||
|
||||
Insert the new section directly below the `All notable changes...` line and above the previous version's heading.
|
||||
|
||||
Present the draft and ask for approval before writing.
|
||||
|
||||
**If the version is wrong**, update only the version number — preserve the existing content unless the user asks for content changes too.
|
||||
|
||||
After any changes, show the final CHANGELOG entry for confirmation.
|
||||
|
||||
### Step 6 — Sync `package.json` and `version.json` versions
|
||||
|
||||
After writing or updating the CHANGELOG entry, update the `version` field in `package.json` at the repo root to match the computed version:
|
||||
|
||||
1. Read `package.json` and `version.json` then check the current `version` value.
|
||||
2. If it already matches the computed version, skip — no change needed.
|
||||
3. If it differs, update the `"version"` field in both files to the computed version (e.g., `"version": "2.1.1"`).
|
||||
4. Set `releaseDate` in `version.json` to today's date in `YYYY-MM-DD`. This is the only place a date is recorded — the CHANGELOG headings carry no date.
|
||||
5. Include `package.json` and `version.json` in the same commit as the CHANGELOG changes.
|
||||
|
||||
This keeps `package.json`, `version.json`, and `CHANGELOG.md` in lockstep so `npm pkg get version` always reflects the latest release.
|
||||
|
||||
## Rules
|
||||
|
||||
- Never create a version entry without checking main first — the whole point is to derive the version from main's current state
|
||||
- Always present changes before writing — the user should see and approve the CHANGELOG entry
|
||||
- Match the existing file's format — `## vX.Y.Z` with no date, emoji `###` headings. Do not introduce Keep a Changelog's `## [x.y.z] - date` style
|
||||
- Write for someone reading the release notes, not for someone reading the diff — say what the change lets them do
|
||||
- If multiple change types exist (Added + Changed), use multiple headings under the same version
|
||||
- `version.json`'s `releaseDate` is today's date, i.e. when the release is being prepared, not when the work started
|
||||
- If the branch has no meaningful changes vs main (e.g., only non-shipping files changed), say so and ask if a CHANGELOG entry is actually needed
|
||||
@@ -0,0 +1,116 @@
|
||||
---
|
||||
name: plan2code-model-update
|
||||
description: "Refresh the plan2code launcher's curated model menu in src/launcher/models.json from `devin models list` and Claude Code's documented model aliases, with the maintainer approving every change before anything is written. Use this skill when the user says 'update the models', 'refresh models.json', 'new Claude model', 'devin models changed', or otherwise asks to bring the launcher's model list up to date."
|
||||
---
|
||||
|
||||
# Plan2Code Model Update
|
||||
|
||||
Bring the launcher's curated model menu (`src/launcher/models.json`) up to date with the models each CLI offers today. Discover what Devin and Claude Code currently offer, show the maintainer a diff against the shipped file, apply only the changes they approve, validate the file, and run `npm test`. This skill never commits.
|
||||
|
||||
**Repo-local by design.** This skill lives in the repo's `.claude/skills/` and is intentionally NOT wired into `install.js` — it is a maintainer dev tool, not part of the shipped product, so it is never installed to `~/.claude/skills/`. Do **not** copy it there: the uninstaller (`uninstallSkills()` in `install.js`) and every re-install (`install()`) both run `cleanLegacyPaths()`, which deletes every entry matching `/^plan2code-/` under `~/.claude/skills/` (the `LEGACY_PATHS` row for Claude Code skills), so a copy placed there would be silently removed.
|
||||
|
||||
**Terminal only.** This skill runs in the terminal, with no web console session. Ask every question here.
|
||||
|
||||
## Workflow
|
||||
|
||||
### Step 1 — Preflight
|
||||
|
||||
Run from the repo root (the folder holding `install.js` and `src/launcher/`). Run `git status --porcelain -- src/launcher/models.json`. If it prints anything, warn — do not stop:
|
||||
|
||||
> `src/launcher/models.json` already has uncommitted changes. The diff below compares against the file as it stands on disk, including those changes.
|
||||
|
||||
### Step 2 — Read the current file
|
||||
|
||||
Read `src/launcher/models.json`. It has three keys: `_note` (a string), `claude` and `devin` (each an array of `{ "id", "label" }`). Keep the `_note` text exactly as read — Step 7 writes it back verbatim and the Validation rules check it.
|
||||
|
||||
### Step 3 — Discover Devin's models
|
||||
|
||||
If `devin` is on PATH (`command -v devin` in bash, `Get-Command devin` in PowerShell), run:
|
||||
|
||||
```bash
|
||||
devin models list
|
||||
```
|
||||
|
||||
Show its raw output to the maintainer before any interpretation — the format is not a stable contract. The output is long (hundreds of ids across about twenty families), so save it to a scratch file outside the repo, say where, and show the family headings in full. From it, take the explicit ids at Low, Medium and High effort only, plus `adaptive`. Skip every id the Validation rules forbid (`xhigh`, `max`, `fast`, `priority` endings), and also skip `none`-effort ids, ids with no effort suffix (such as `swe-1-7`, which is a Max model), and `fusion-*` combinations.
|
||||
|
||||
The 30-entry cap means the file can never hold every family at three efforts. Propose additions by family — newest and most-used first — and say how many entries that leaves.
|
||||
|
||||
If `devin` is not on PATH or the command fails, say so with the error, and switch to **guided manual edits** for Devin: ask the maintainer which ids to add, remove or relabel, one at a time, and carry those into Step 5 as the proposed list.
|
||||
|
||||
### Step 4 — Discover Claude Code's models
|
||||
|
||||
Look up Claude Code's current model documentation — the model configuration page in the Claude Code docs. Locate it on each run (search the Claude Code docs for model configuration) rather than using a remembered URL; docs move. List the documented model aliases (for example `default`, `sonnet`, `opus`, `haiku`, `opusplan`) and what each one means, and name the page you used. Keep `default` as the file's first entry even though the docs call it a special value rather than an alias. Bracketed aliases such as `opus[1m]` are valid ids; propose them only when the maintainer wants them in the menu.
|
||||
|
||||
If the lookup fails or the page does not list aliases, say so, and switch to **guided manual edits** for Claude, exactly as in Step 3.
|
||||
|
||||
### Step 5 — Show the diff
|
||||
|
||||
For each CLI, compare the discovered list with the current one by `id` and show one table:
|
||||
|
||||
| Change | id | Current label | Proposed label | Source |
|
||||
| --- | --- | --- | --- | --- |
|
||||
| added | `new-id` | — | New label | `devin models list` |
|
||||
| gone | `old-id` | Old label | — | not in `devin models list` |
|
||||
| relabelled | `same-id` | Old label | New label | Claude Code docs: <page> |
|
||||
|
||||
- **added:** offered by the CLI, not in the file.
|
||||
- **gone:** in the file, no longer offered.
|
||||
- **relabelled:** same `id`, a better or changed label. Propose a label in the file's existing style.
|
||||
|
||||
Summarise unchanged entries as a count under the table ("19 Devin entries unchanged") instead of listing them. If approving every **added** Devin row would take the list past 30 entries, say so above the table and by how many. Call out any likely rename before approval (see the rename warning under Validation rules). If both tables are empty, say the file is current and stop.
|
||||
|
||||
### Step 6 — Approve each change
|
||||
|
||||
Ask about each row, one at a time: **yes**, **no**, or **edit the label** (they type the label to use). Write nothing until every row has an answer. A "no" leaves that entry exactly as it is today.
|
||||
|
||||
### Step 7 — Edit `models.json`
|
||||
|
||||
Apply only the approved rows:
|
||||
|
||||
- Keep `_note` verbatim.
|
||||
- Keep the existing order. Remove a **gone** entry where it stands, change a **relabelled** label in place, and append each **added** entry at the end of its list.
|
||||
- Write two-space-indented JSON with a trailing newline, matching the file's current formatting.
|
||||
|
||||
### Step 8 — Validate
|
||||
|
||||
Check the edited file against every rule under Validation rules. On a failure, show the rule and the entry that broke it, and go back to Step 6 for the affected rows. Do not run tests on a file that fails validation.
|
||||
|
||||
### Step 9 — Test
|
||||
|
||||
Run `npm test` from the repo root and report the result honestly: pass, or the failing suite and its output. Never describe a failing run as passing.
|
||||
|
||||
### Step 10 — Remind about the release
|
||||
|
||||
A launcher model change reaches people only with the next release. Remind the maintainer to add a `CHANGELOG.md` line and keep `CHANGELOG.md`, `version.json` and `package.json` on the same version — `/plan2code-changelog` does both.
|
||||
|
||||
### Step 11 — Suggest a commit
|
||||
|
||||
Suggest a one-line commit message that says what changed, and do not run it:
|
||||
|
||||
```bash
|
||||
git add src/launcher/models.json
|
||||
git commit -m "Refresh the launcher's model menu"
|
||||
```
|
||||
|
||||
Give `add` and `commit` as two separate commands (Windows PowerShell 5.1 has no `&&`).
|
||||
|
||||
## Validation rules
|
||||
|
||||
Check every rule before `npm test` (Step 8). They mirror the shipped-file test in `scripts/test-launcher.mjs` ("the shipped models.json is curated Devin at low/medium/high only") plus the menu's own needs:
|
||||
|
||||
- The file is valid JSON.
|
||||
- `_note` is present and unchanged from what Step 2 read.
|
||||
- `claude` and `devin` are both non-empty arrays.
|
||||
- `devin` has at most 30 entries.
|
||||
- Every entry has a non-empty string `id` and a non-empty string `label`.
|
||||
- Ids are unique within each list, and labels are unique within each list.
|
||||
- No Devin id ends in `xhigh`, `max`, `fast` or `priority`.
|
||||
|
||||
**Warn on renames.** When an entry is **gone** and a near-identical id is **added** in the same list (a changed version number or suffix, say `glm-5-3-high` → `glm-5-4-high`), call the pair out before approval as a likely rename. People's own lists in `~/.plan2code/models.json` merge with the shipped one by id (`mergeModels()` in `src/launcher/plan2code.js`), so a renamed id can bring back a user's old copy of the entry beside the new one. Approve the pair knowingly, or keep the old id.
|
||||
|
||||
## Rules
|
||||
|
||||
- **Never commit and never push** — Step 11 suggests the commit; the maintainer runs it.
|
||||
- **Touch only `src/launcher/models.json`**, plus `CHANGELOG.md` only if the maintainer asks for the release line.
|
||||
- **Nothing is written before every row is answered** (Step 6).
|
||||
- **Never install this skill** — never add it to `install.js`, and never copy it to `~/.claude/skills/` (the uninstaller deletes `plan2code-*` entries there).
|
||||
@@ -0,0 +1,159 @@
|
||||
---
|
||||
name: plan2code-publish
|
||||
description: "Publish a GitHub Release for jparkerweb/plan2code whenever CHANGELOG.md's top version is ahead of the latest published release on GitHub — after verifying CHANGELOG.md, version.json, and package.json all agree on the version. Use this skill when the user says 'publish a release', 'create a GitHub release', 'cut a release', 'tag a release', 'tag and release', 'is the changelog published', or otherwise mentions publishing/releasing/tagging this repo."
|
||||
---
|
||||
|
||||
# Plan2Code Release Publisher
|
||||
|
||||
Publish a GitHub Release for `jparkerweb/plan2code` whenever `CHANGELOG.md`'s top version is ahead of the latest published release on GitHub. This turns the merged CHANGELOG entry on `main` into an actual GitHub Release (which also creates the `vX.Y.Z` git tag).
|
||||
|
||||
**Repo-local by design.** This skill lives in the repo's `.claude/skills/` and is intentionally NOT wired into `install.js` — it is a maintainer dev tool, not part of the shipped product, so it is never installed to `~/.claude/skills/`. Do **not** copy it there: the uninstaller (`uninstallFiles()` in `install.js`) and every re-install's pre-copy cleanup in `install()` both delete every entry matching `/^plan2code-/` under `~/.claude/skills/`, so a copy placed there would be silently removed.
|
||||
|
||||
## Workflow
|
||||
|
||||
### Step 1 — Preflight: clean working tree
|
||||
|
||||
Run `git status --porcelain`. If the output is non-empty, stop immediately — do not switch branches or take any other action. Tell the user:
|
||||
|
||||
> Working tree has uncommitted changes. Commit or stash them, then re-run this skill.
|
||||
|
||||
### Step 2 — Switch to main and pull
|
||||
|
||||
If the working tree is clean, switch to `main` and pull latest. Run these as two separate, non-chained commands (never `&&`/`;`-chain `git`/`gh` commands — Windows PowerShell 5.1 rejects `&&`):
|
||||
|
||||
```bash
|
||||
git checkout main
|
||||
git pull origin main
|
||||
```
|
||||
|
||||
### Step 3 — Read the three version sources
|
||||
|
||||
Read all three files at the repo root and extract each version:
|
||||
|
||||
- `CHANGELOG.md` — parse the first `## vX.Y.Z` heading. Strip the leading `v` → `$CHANGELOG_VERSION`. Note: plan2code CHANGELOG headings are `## vX.Y.Z` (v-prefixed, **no** date and **no** brackets) — different from a `## [x.y.z] - YYYY-MM-DD` format.
|
||||
- `version.json` — the `version` field → `$VERSION_JSON`. Also read its `releaseDate` field → `$RELEASE_DATE` (informational only — shown at the confirm step, never part of the sync gate; use `(none)` if absent).
|
||||
- `package.json` (root) → the `version` field → `$PACKAGE_JSON`.
|
||||
|
||||
Also capture from `CHANGELOG.md` the **section body** for the top version: everything from the `## vX.Y.Z` heading line itself (heading **included**) up to — but not including — the next `## v` heading, or end-of-file if there is none. Call this `$SECTION`. Keep the `## vX.Y.Z` heading in `$SECTION`; plan2code release bodies include it.
|
||||
|
||||
### Step 4 — Version-sync preflight (STOP on mismatch)
|
||||
|
||||
All three versions must be identical. This enforces the repo's documented invariant (`.agents-docs/AGENTS-code-style.md` → "Version sync"): `CHANGELOG.md`, `version.json`, and `package.json` must always show the same version number.
|
||||
|
||||
If `$CHANGELOG_VERSION`, `$VERSION_JSON`, and `$PACKAGE_JSON` are **not** all equal, **stop** — do not read the release, do not publish. Report exactly which files disagree:
|
||||
|
||||
> ⚠️ Version files are out of sync — refusing to publish. The repo requires `CHANGELOG.md`, `version.json`, and `package.json` to match.
|
||||
>
|
||||
> - **CHANGELOG.md:** $CHANGELOG_VERSION
|
||||
> - **version.json:** $VERSION_JSON
|
||||
> - **package.json:** $PACKAGE_JSON
|
||||
>
|
||||
> Fix the mismatch first, then re-run this skill. To realign: pick the intended version (normally the highest / newest CHANGELOG entry) and update the other two files to match — see the "Version sync" gotcha in `.agents-docs/AGENTS-code-style.md`.
|
||||
|
||||
This skill never modifies these files — it only reads and compares them.
|
||||
|
||||
### Step 5 — Determine the highest published release
|
||||
|
||||
List every published (non-draft) release and take the numerically-highest semver tag. Do **not** rely on `gh release view` / GitHub's "Latest" flag: that flag returns whatever release is *marked* latest — normally the newest semver, but a maintainer can manually pin it to an older release, which would make the Step 6 ahead-comparison misfire.
|
||||
|
||||
```bash
|
||||
gh release list --repo jparkerweb/plan2code --limit 100 --json tagName,isDraft -q '.[] | select(.isDraft==false) | .tagName'
|
||||
```
|
||||
|
||||
Strip any leading `v` from each returned tag, compare them as numeric `(major, minor, patch)` tuples (the same rule as Step 6), and take the maximum → `$RELEASE_VERSION`. If the command returns no tags or exits non-zero for **any** reason (no releases yet, transient error, etc.), set `$RELEASE_VERSION = "0.0.0"` — no error-text matching is needed.
|
||||
|
||||
### Step 6 — Compare versions
|
||||
|
||||
Compare `$CHANGELOG_VERSION` vs `$RELEASE_VERSION` as a numeric `(major, minor, patch)` tuple. Never do a plain string/lexicographic compare — e.g. `"1.9.0" > "1.10.0"` is true as strings but wrong numerically.
|
||||
|
||||
### Step 7 — Not ahead: no-op
|
||||
|
||||
If `$CHANGELOG_VERSION` ≤ `$RELEASE_VERSION`, print a simple status message showing both versions and stop:
|
||||
|
||||
> CHANGELOG top version ($CHANGELOG_VERSION) is not ahead of the latest published release ($RELEASE_VERSION). Nothing to publish.
|
||||
|
||||
No error is raised and no release is created.
|
||||
|
||||
### Step 8 — Ahead: compute and confirm
|
||||
|
||||
If `$CHANGELOG_VERSION` > `$RELEASE_VERSION`, compute:
|
||||
|
||||
- `tag = "v$CHANGELOG_VERSION"`
|
||||
- `title = "v$CHANGELOG_VERSION"` (plan2code keeps the `v` prefix in release titles)
|
||||
- `notes` = the header line `# What's New 🎉`, then one blank line, then `$SECTION` verbatim (`$SECTION` already starts with the `## vX.Y.Z` heading). Build this as a real multi-line string with **actual newlines** — the `\n\n` shorthand shown elsewhere means "a blank line," never the literal two-character sequence `\` + `n`. Getting this wrong would run the header and the first CHANGELOG heading together with a stray `\n\n` in the published body.
|
||||
|
||||
Present all three to the user and wait for an explicit answer before any write. Offer the optional decorative title suffix — a plain `vX.Y.Z` title is the default, but a release may append one (e.g. `v1.14.0 - 🔍 Review workflow`):
|
||||
|
||||
> 🚀 [Publish Plan2Code Release]
|
||||
>
|
||||
> CHANGELOG is ahead of the latest published release:
|
||||
> - **Current release:** $RELEASE_VERSION
|
||||
> - **CHANGELOG top version:** $CHANGELOG_VERSION
|
||||
> - **version.json releaseDate:** $RELEASE_DATE (informational — read from `version.json`)
|
||||
>
|
||||
> Proposed release:
|
||||
> - **Tag:** $tag
|
||||
> - **Title:** $title
|
||||
> - **Notes:**
|
||||
> ```
|
||||
> $notes
|
||||
> ```
|
||||
>
|
||||
> Publish this release? Reply **yes** to publish as-is, **no** to cancel, or provide a decorative suffix to append to the title (e.g. `⇢ 🎆 Feature Name` or `- 🔍 Feature Name`).
|
||||
|
||||
If the user supplies a suffix, set `title = "v$CHANGELOG_VERSION " + <suffix>` (single space join) and proceed to publish. The tag and notes are unaffected by the suffix.
|
||||
|
||||
### Step 9 — Publish (on approval)
|
||||
|
||||
On approval, write `$notes` to a temp file — never pass multiline text inline via `--notes`, that regresses into a quoting bug — then create the release targeting `main`. Two requirements for the temp file: `$notes` must already hold **real newlines** (per Step 8) because `printf '%s'` / `WriteAllText` write it byte-for-byte — a literal `\n` in the string lands literally in the release body; and it MUST be **UTF-8** because the notes contain emoji (`🎉`, `🐛`, `✨`, `🔧`).
|
||||
|
||||
**bash (preferred in this environment):**
|
||||
|
||||
```bash
|
||||
NOTES_FILE=$(mktemp)
|
||||
printf '%s' "$notes" > "$NOTES_FILE"
|
||||
gh release create "$tag" --repo jparkerweb/plan2code --title "$title" --notes-file "$NOTES_FILE" --target main
|
||||
rm -f "$NOTES_FILE"
|
||||
```
|
||||
|
||||
**PowerShell:** do NOT use `Set-Content` — under Windows PowerShell 5.1 it writes ANSI/UTF-16 by default and mangles the emoji into `??`. Write UTF-8 **without BOM** (a BOM would leak into the release body):
|
||||
|
||||
```powershell
|
||||
$NotesFile = [System.IO.Path]::GetTempFileName()
|
||||
[System.IO.File]::WriteAllText($NotesFile, $notes, [System.Text.UTF8Encoding]::new($false))
|
||||
gh release create "$tag" --repo jparkerweb/plan2code --title "$title" --notes-file "$NotesFile" --target main
|
||||
Remove-Item -Path $NotesFile
|
||||
```
|
||||
|
||||
Always delete the temp file afterward, regardless of whether `gh release create` succeeded or failed.
|
||||
|
||||
**Failure handling — already-exists classification:** if `gh release create` exits non-zero, inspect the error text.
|
||||
|
||||
- If and only if it contains the substring `already exists` (real output: `HTTP 422: Validation Failed` / `Release.tag_name already exists`), report this to the user as already published, not as a raw CLI error:
|
||||
|
||||
> This version ($CHANGELOG_VERSION) was already published as a release — nothing more to do.
|
||||
|
||||
- Every other failure (auth, network, permissions, etc.) must be surfaced to the user verbatim. Never silently reclassify a genuine failure as "already published."
|
||||
|
||||
### Step 10 — Verify
|
||||
|
||||
Confirm the release now exists and report its URL:
|
||||
|
||||
```bash
|
||||
gh release view "$tag" --repo jparkerweb/plan2code
|
||||
```
|
||||
|
||||
Report the release URL to the user.
|
||||
|
||||
## Rules
|
||||
|
||||
- **Repo-local only** — this skill is not part of the installed product; never add it to `install.js`, and never copy it to `~/.claude/skills/` (the uninstaller deletes `plan2code-*` entries there).
|
||||
- **Read-only on version files** — never modify `CHANGELOG.md`, `version.json`, or `package.json`; this skill only reads and compares them.
|
||||
- **Version-sync gate is hard** (Step 4) — if the three version sources disagree, stop and report; do not publish a release from an inconsistent repo.
|
||||
- **Never run a local `git tag` or `git push`** — tag creation is delegated entirely to `gh release create --target main`.
|
||||
- **Always use `--notes-file`**, never inline multiline `--notes`, and always write the notes file as UTF-8 (no BOM) so emoji survive.
|
||||
- **Always clean up the temp notes file**, even on a mid-run error.
|
||||
- **Always get explicit approval before any write** (Step 8) — no release is created without a yes (or a yes-with-suffix).
|
||||
- **Derive the current version from the highest published semver tag** (Step 5), never from GitHub's manually-pinnable "Latest" flag. On an empty or failed release list, treat it as "no prior release" (baseline `0.0.0`) — no error-text matching needed.
|
||||
- **On a `gh release create` failure** (Step 9), only reclassify as already-published when the error contains `already exists` — every other failure must be shown verbatim, never swallowed.
|
||||
- **Idempotent and safe to re-run** at any time — re-running after a successful publish hits the Step 7 no-op; re-running after a race-lost publish hits the Step 9 already-exists handling.
|
||||
@@ -0,0 +1,58 @@
|
||||
---
|
||||
name: sync-repo
|
||||
description: "Run the encrypted, password-protected repository sync workflow for this project. The real instructions are stored encrypted at rest and are only revealed in-session after you supply the correct password. Invoke explicitly with /sync-repo."
|
||||
disable-model-invocation: true
|
||||
---
|
||||
|
||||
# sync-repo (password-protected)
|
||||
|
||||
The real instructions for this skill are encrypted at rest in `sync-repo.enc`
|
||||
and are NOT readable without the password. Do not guess, reconstruct, or invent
|
||||
the workflow. Follow this launcher exactly.
|
||||
|
||||
## What you (the agent) must do
|
||||
|
||||
1. **Ask the user for the password.** Request the decryption passphrase (via
|
||||
AskUserQuestion or a plain prompt). Do NOT proceed without it. Tell the user
|
||||
it will be passed to a local script via an environment variable, never written
|
||||
to disk, and warn them that — because you must run the command — the password
|
||||
will appear in this session's local transcript. (It never enters the repo.)
|
||||
|
||||
2. **Decrypt to STDOUT only.** Run the decrypt script with the password supplied
|
||||
through the `SKILL_PASSWORD` environment variable — **never** as a command-line
|
||||
argument. From the repo root:
|
||||
|
||||
- **Windows PowerShell:**
|
||||
```powershell
|
||||
$env:SKILL_PASSWORD='<password the user gave you>'; node .\.claude\skills\sync-repo\decrypt.mjs .\.claude\skills\sync-repo\sync-repo.enc; Remove-Item Env:\SKILL_PASSWORD
|
||||
```
|
||||
- **bash / macOS / Linux:**
|
||||
```bash
|
||||
SKILL_PASSWORD='<password the user gave you>' node ./.claude/skills/sync-repo/decrypt.mjs ./.claude/skills/sync-repo/sync-repo.enc
|
||||
```
|
||||
|
||||
3. **Handle the result.**
|
||||
- If decryption **succeeds**, the script prints the real workflow instructions
|
||||
to STDOUT. Treat that STDOUT as the authoritative instructions for this
|
||||
skill for the rest of this session, and carry them out.
|
||||
- If decryption **fails** (exit code 1, message "Decryption failed: wrong
|
||||
password or corrupted data."), the password was wrong or the file is
|
||||
corrupt. Tell the user, ask them to re-enter the password, and retry. Do
|
||||
NOT attempt to reconstruct the instructions from anything else.
|
||||
|
||||
## Hard rules
|
||||
|
||||
- **Never write the decrypted plaintext to a file.** Read it from STDOUT only.
|
||||
`decrypt.mjs` intentionally has no file-output mode.
|
||||
- **Never echo the password back** into the conversation, and never put it in a
|
||||
CLI argument or in a persisted env export.
|
||||
- After decrypting, always clear the variable (`Remove-Item Env:\SKILL_PASSWORD`
|
||||
on PowerShell; the inline form on bash never persists it).
|
||||
|
||||
## Security note (be honest with the user)
|
||||
|
||||
This protects the workflow body **only at rest in the repository**. Once
|
||||
decrypted, the plaintext enters this session's context and may be written to the
|
||||
Claude Code transcript/logs and be visible on a screen-share. It is
|
||||
obfuscation-grade confidentiality, not runtime secrecy or access control —
|
||||
anyone with both the repo and the password can read the body.
|
||||
@@ -0,0 +1,42 @@
|
||||
#!/usr/bin/env node
|
||||
// decrypt.mjs — verifies GCM auth tag, prints plaintext to STDOUT only.
|
||||
// Password from $SKILL_PASSWORD. Exits 1 on wrong password / tamper, leaking nothing.
|
||||
// Usage: SKILL_PASSWORD=... node decrypt.mjs <file.enc>
|
||||
import { readFileSync } from 'node:fs';
|
||||
import { scryptSync, createDecipheriv } from 'node:crypto';
|
||||
|
||||
const MAGIC = Buffer.from('SENC', 'ascii');
|
||||
const VERSION = 0x01;
|
||||
const SCRYPT = { N: 1 << 17, r: 8, p: 1, maxmem: 256 * 1024 * 1024 };
|
||||
const KEYLEN = 32, SALTLEN = 16, IVLEN = 12, TAGLEN = 16;
|
||||
const HEADER = MAGIC.length + 1; // 5
|
||||
|
||||
const password = process.env.SKILL_PASSWORD;
|
||||
if (!password) { console.error('ERROR: set SKILL_PASSWORD env var.'); process.exit(2); }
|
||||
|
||||
const encPath = process.argv[2];
|
||||
if (!encPath) { console.error('Usage: node decrypt.mjs <file.enc>'); process.exit(2); }
|
||||
|
||||
try {
|
||||
const blob = Buffer.from(readFileSync(encPath, 'utf8').trim(), 'base64');
|
||||
if (blob.length < HEADER + SALTLEN + IVLEN + TAGLEN) throw new Error('truncated');
|
||||
if (!blob.subarray(0, MAGIC.length).equals(MAGIC)) throw new Error('bad magic');
|
||||
if (blob[MAGIC.length] !== VERSION) throw new Error('unsupported version');
|
||||
|
||||
let off = HEADER;
|
||||
const salt = blob.subarray(off, off += SALTLEN);
|
||||
const iv = blob.subarray(off, off += IVLEN);
|
||||
const authTag = blob.subarray(off, off += TAGLEN);
|
||||
const ciphertext = blob.subarray(off);
|
||||
|
||||
const key = scryptSync(password, salt, KEYLEN, SCRYPT);
|
||||
const decipher = createDecipheriv('aes-256-gcm', key, iv);
|
||||
decipher.setAuthTag(authTag);
|
||||
// final() throws here if the tag does not verify (wrong password or tampering).
|
||||
const plaintext = Buffer.concat([decipher.update(ciphertext), decipher.final()]);
|
||||
process.stdout.write(plaintext); // STDOUT only — never written to disk.
|
||||
} catch (err) {
|
||||
// Generic message: do not echo crypto internals or any plaintext.
|
||||
console.error('Decryption failed: wrong password or corrupted data.');
|
||||
process.exit(1);
|
||||
}
|
||||
@@ -0,0 +1,32 @@
|
||||
#!/usr/bin/env node
|
||||
// encrypt.mjs — AES-256-GCM + scrypt. Password from $SKILL_PASSWORD (never argv).
|
||||
// Usage: SKILL_PASSWORD=... node encrypt.mjs <plaintextFile|-> <outFile.enc>
|
||||
// (pass '-' or omit the input path to read plaintext from STDIN)
|
||||
import { readFileSync, writeFileSync } from 'node:fs';
|
||||
import { scryptSync, randomBytes, createCipheriv } from 'node:crypto';
|
||||
|
||||
const MAGIC = Buffer.from('SENC', 'ascii');
|
||||
const VERSION = 0x01;
|
||||
const SCRYPT = { N: 1 << 17, r: 8, p: 1, maxmem: 256 * 1024 * 1024 };
|
||||
const KEYLEN = 32, SALTLEN = 16, IVLEN = 12;
|
||||
|
||||
const password = process.env.SKILL_PASSWORD;
|
||||
if (!password) { console.error('ERROR: set SKILL_PASSWORD env var.'); process.exit(2); }
|
||||
|
||||
const inPath = process.argv[2];
|
||||
const outPath = process.argv[3];
|
||||
if (!outPath) { console.error('Usage: node encrypt.mjs <plaintextFile|-> <outFile.enc>'); process.exit(2); }
|
||||
|
||||
// readFileSync(0) reads STDIN; use it when no input file (or '-') is given.
|
||||
const plaintext = (!inPath || inPath === '-') ? readFileSync(0) : readFileSync(inPath);
|
||||
|
||||
const salt = randomBytes(SALTLEN);
|
||||
const iv = randomBytes(IVLEN);
|
||||
const key = scryptSync(password, salt, KEYLEN, SCRYPT);
|
||||
const cipher = createCipheriv('aes-256-gcm', key, iv);
|
||||
const ciphertext = Buffer.concat([cipher.update(plaintext), cipher.final()]);
|
||||
const authTag = cipher.getAuthTag(); // 16 bytes
|
||||
|
||||
const blob = Buffer.concat([MAGIC, Buffer.from([VERSION]), salt, iv, authTag, ciphertext]);
|
||||
writeFileSync(outPath, blob.toString('base64') + '\n');
|
||||
console.error(`Wrote ${outPath} (${blob.length} raw bytes, base64-encoded).`);
|
||||
@@ -0,0 +1,56 @@
|
||||
#!/usr/bin/env node
|
||||
// set-synced.mjs: rewrite the "Last synced" line inside sync-repo.enc, in memory only.
|
||||
// Decrypts, replaces exactly one anchored line, re-encrypts, then decrypts again to verify.
|
||||
// Plaintext never touches disk and never passes through a shell pipe (PowerShell pipes
|
||||
// re-encode UTF-8 through the console code page, which is how the body got mojibake).
|
||||
// Usage: SKILL_PASSWORD=... node set-synced.mjs <file.enc> "<new value>"
|
||||
// e.g. node set-synced.mjs sync-repo.enc "v2.4.0 (main @ 1a2b3c4)"
|
||||
import { readFileSync, writeFileSync } from 'node:fs';
|
||||
import { scryptSync, randomBytes, createCipheriv, createDecipheriv } from 'node:crypto';
|
||||
|
||||
const MAGIC = Buffer.from('SENC', 'ascii');
|
||||
const VERSION = 0x01;
|
||||
const SCRYPT = { N: 1 << 17, r: 8, p: 1, maxmem: 256 * 1024 * 1024 };
|
||||
const KEYLEN = 32, SALTLEN = 16, IVLEN = 12, TAGLEN = 16;
|
||||
// Anchored to a whole line that starts with "**Last synced upstream:". Command text elsewhere in
|
||||
// the body can mention the phrase without ever matching, because it never starts a line this way.
|
||||
const LINE = /^\*\*Last synced upstream: .*\*\*$/gm;
|
||||
|
||||
const password = process.env.SKILL_PASSWORD;
|
||||
const [encPath, value] = process.argv.slice(2);
|
||||
if (!password) { console.error('ERROR: set SKILL_PASSWORD env var.'); process.exit(2); }
|
||||
if (!encPath || !value) { console.error('Usage: node set-synced.mjs <file.enc> "<new value>"'); process.exit(2); }
|
||||
if (value.includes('*') || value.includes('\n')) { console.error('ERROR: value may not contain * or a newline.'); process.exit(2); }
|
||||
|
||||
function decrypt(b64) {
|
||||
const blob = Buffer.from(b64.trim(), 'base64');
|
||||
if (!blob.subarray(0, MAGIC.length).equals(MAGIC) || blob[MAGIC.length] !== VERSION) throw new Error('bad header');
|
||||
let off = MAGIC.length + 1;
|
||||
const salt = blob.subarray(off, off += SALTLEN);
|
||||
const iv = blob.subarray(off, off += IVLEN);
|
||||
const tag = blob.subarray(off, off += TAGLEN);
|
||||
const d = createDecipheriv('aes-256-gcm', scryptSync(password, salt, KEYLEN, SCRYPT), iv);
|
||||
d.setAuthTag(tag);
|
||||
return Buffer.concat([d.update(blob.subarray(off)), d.final()]).toString('utf8');
|
||||
}
|
||||
|
||||
function encrypt(text) {
|
||||
const salt = randomBytes(SALTLEN), iv = randomBytes(IVLEN);
|
||||
const c = createCipheriv('aes-256-gcm', scryptSync(password, salt, KEYLEN, SCRYPT), iv);
|
||||
const ct = Buffer.concat([c.update(Buffer.from(text, 'utf8')), c.final()]);
|
||||
return Buffer.concat([MAGIC, Buffer.from([VERSION]), salt, iv, c.getAuthTag(), ct]).toString('base64') + '\n';
|
||||
}
|
||||
|
||||
let body;
|
||||
try { body = decrypt(readFileSync(encPath, 'utf8')); }
|
||||
catch { console.error('Decryption failed: wrong password or corrupted data.'); process.exit(1); }
|
||||
|
||||
const hits = body.match(LINE) || [];
|
||||
if (hits.length !== 1) { console.error(`ERROR: expected exactly one "Last synced" line, found ${hits.length}. Nothing written.`); process.exit(1); }
|
||||
if (body.includes('�')) { console.error('ERROR: body contains U+FFFD (encoding damage). Nothing written.'); process.exit(1); }
|
||||
|
||||
const next = body.replace(LINE, `**Last synced upstream: ${value}**`);
|
||||
const out = encrypt(next);
|
||||
if (decrypt(out) !== next) { console.error('ERROR: round-trip verification failed. Nothing written.'); process.exit(1); }
|
||||
writeFileSync(encPath, out);
|
||||
console.error(`Updated: ${hits[0]} -> **Last synced upstream: ${value}**`);
|
||||
@@ -0,0 +1 @@
|
||||
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 truncated
|
||||
@@ -0,0 +1,6 @@
|
||||
root = true
|
||||
|
||||
[*]
|
||||
end_of_line = lf
|
||||
charset = utf-8
|
||||
insert_final_newline = true
|
||||
@@ -0,0 +1,31 @@
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
# Line endings
|
||||
#
|
||||
# Git stores LF, and every text file is checked out as LF on all platforms.
|
||||
# This is not cosmetic: scripts/validate-char-count.js measures the characters
|
||||
# actually on disk, so a CRLF checkout adds ~1 character per line. The workflow
|
||||
# prompts in src/plan2code-*.md are counted against a 20,000 character budget,
|
||||
# and a CRLF working tree inflates that count, turning
|
||||
# `npm test` into a check that passes or fails depending on how the repo was
|
||||
# cloned. Pinning eol=lf makes the count reproducible everywhere.
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
* text=auto eol=lf
|
||||
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
# Binary — never line-ending-converted, never diffed as text
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
*.png binary
|
||||
*.jpg binary
|
||||
*.mp3 binary
|
||||
*.jpeg binary
|
||||
*.gif binary
|
||||
*.ico binary
|
||||
*.mp4 binary
|
||||
*.webm binary
|
||||
*.woff binary
|
||||
*.woff2 binary
|
||||
|
||||
# The encrypted sync-repo blob is base64 text but must never have its bytes
|
||||
# altered by line-ending normalization. Treat it as binary so autocrlf/eol
|
||||
# settings can never corrupt the ciphertext.
|
||||
*.enc binary
|
||||
@@ -0,0 +1,78 @@
|
||||
name: "🐛 Bug"
|
||||
description: Something in Plan2Code or the web console is broken or behaves unexpectedly.
|
||||
title: "🐛 Bug: "
|
||||
labels: ["bug"]
|
||||
body:
|
||||
- type: textarea
|
||||
id: what-happened
|
||||
attributes:
|
||||
label: What happened?
|
||||
description: Describe the problem. Screenshots are welcome.
|
||||
validations:
|
||||
required: true
|
||||
- type: textarea
|
||||
id: expected
|
||||
attributes:
|
||||
label: What did you expect to happen?
|
||||
validations:
|
||||
required: true
|
||||
- type: textarea
|
||||
id: steps
|
||||
attributes:
|
||||
label: Steps to reproduce
|
||||
placeholder: |
|
||||
1. Run /plan2code
|
||||
2. Pick ...
|
||||
3. See ...
|
||||
validations:
|
||||
required: true
|
||||
- type: dropdown
|
||||
id: skill
|
||||
attributes:
|
||||
label: Which skill or tool?
|
||||
options:
|
||||
- Dashboard (/plan2code)
|
||||
- Init / Init Update
|
||||
- Pathfinder
|
||||
- Plan / Revise Plan
|
||||
- Quick Task
|
||||
- Document
|
||||
- Implement / Implement + Review
|
||||
- Review
|
||||
- Finalize
|
||||
- Handoff
|
||||
- Web console (page itself)
|
||||
- Loop (plan2code-loop)
|
||||
- Metrics
|
||||
- Status line
|
||||
- Installer
|
||||
- Other
|
||||
validations:
|
||||
required: true
|
||||
- type: dropdown
|
||||
id: interface
|
||||
attributes:
|
||||
label: Where were you working?
|
||||
options:
|
||||
- Web console
|
||||
- Terminal
|
||||
- Not sure
|
||||
validations:
|
||||
required: true
|
||||
- type: input
|
||||
id: version
|
||||
attributes:
|
||||
label: Plan2Code version
|
||||
description: Found in version.json, the installer banner, or at the bottom of the web console's Help dialog.
|
||||
placeholder: "2.4.0"
|
||||
- type: input
|
||||
id: environment
|
||||
attributes:
|
||||
label: OS, Node version and agent CLI
|
||||
placeholder: "Windows 11, Node 22, Claude Code"
|
||||
- type: textarea
|
||||
id: logs
|
||||
attributes:
|
||||
label: Console output or logs
|
||||
description: Anything from the terminal or the browser console that helps.
|
||||
render: shell
|
||||
@@ -0,0 +1 @@
|
||||
blank_issues_enabled: false
|
||||
@@ -0,0 +1,29 @@
|
||||
name: "💡 Idea"
|
||||
description: Suggest a feature or an improvement to Plan2Code.
|
||||
title: "💡 Idea: "
|
||||
labels: ["enhancement"]
|
||||
body:
|
||||
- type: textarea
|
||||
id: problem
|
||||
attributes:
|
||||
label: What problem or goal is this for?
|
||||
description: What are you trying to do that is hard or impossible today?
|
||||
validations:
|
||||
required: true
|
||||
- type: textarea
|
||||
id: idea
|
||||
attributes:
|
||||
label: Your idea
|
||||
description: What would you like Plan2Code to do?
|
||||
validations:
|
||||
required: true
|
||||
- type: textarea
|
||||
id: who
|
||||
attributes:
|
||||
label: Who would this help?
|
||||
placeholder: "Product leads writing specs, engineers running the loop, ..."
|
||||
- type: textarea
|
||||
id: alternatives
|
||||
attributes:
|
||||
label: Alternatives you considered
|
||||
description: Workarounds you use now, or other ways it could work.
|
||||
@@ -1,3 +1,26 @@
|
||||
specs/
|
||||
dist/
|
||||
CLAUDE.md
|
||||
specs/
|
||||
specs--completed/
|
||||
dist/
|
||||
plan2code-loop/dist
|
||||
plan2code-loop/node_modules
|
||||
plan2code-loop/package-lock.json
|
||||
plan2code-metrics/dist
|
||||
plan2code-metrics/node_modules
|
||||
plan2code-metrics/package-lock.json
|
||||
.plan2code-loop
|
||||
.plan2code-metrics
|
||||
nul
|
||||
.cognition/
|
||||
handoffs/
|
||||
node_modules/
|
||||
package-lock.json
|
||||
SYNC.md
|
||||
|
||||
# Generated by install.js/`npm run build:skills` from src/, regenerated on
|
||||
# every install, so it never needs committing. Anchored: .claude/skills/ and
|
||||
# per-skill references must stay tracked.
|
||||
/skills/
|
||||
|
||||
# Throwaway design prototypes (ai-assist-prototype). The decision they
|
||||
# recorded lives in the code and the CHANGELOG; the files stay local.
|
||||
prototypes/
|
||||
@@ -0,0 +1 @@
|
||||
node scripts/validate-char-count.js
|
||||
@@ -0,0 +1,19 @@
|
||||
# Exclude user-generated spec files
|
||||
specs/
|
||||
specs--completed/
|
||||
|
||||
# Exclude development files
|
||||
.husky/
|
||||
.git/
|
||||
.gitignore
|
||||
CLAUDE.md
|
||||
|
||||
# Exclude stale generated output from pre-2.2 checkouts
|
||||
dist/
|
||||
|
||||
# Exclude dependencies (installer will run npm install if needed)
|
||||
node_modules/
|
||||
package-lock.json
|
||||
plan2code-loop/node_modules/
|
||||
plan2code-loop/package-lock.json
|
||||
plan2code-loop/dist/
|
||||
@@ -0,0 +1,65 @@
|
||||
# Autonomous Loop
|
||||
|
||||
`plan2code-loop` is a CLI that works through your spec's tasks on its own, one agent call at a
|
||||
time. It is an **alternative to Step 3**, not a replacement — the four-step workflow and the specs it
|
||||
produces are unchanged.
|
||||
|
||||
← [Back to README](../README.md)
|
||||
|
||||
---
|
||||
|
||||
## When to use it instead of Step 3
|
||||
|
||||
| Approach | Best for |
|
||||
|----------|----------|
|
||||
| `/plan2code-3-implement` | Interactive control, reviewing each phase, logic that needs your judgment |
|
||||
| `/plan2code-3-implement-review` | The same interactive control, with a focused review and its fixes applied before you approve the phase |
|
||||
| `plan2code-loop` | Straightforward implementations, batch work, overnight runs |
|
||||
|
||||
The loop reads the same `overview.md` and phase files. You can start with the loop and finish by
|
||||
hand, or the reverse — the checkboxes are the only handoff.
|
||||
|
||||
---
|
||||
|
||||
## Install
|
||||
|
||||
```bash
|
||||
# From the plan2code root directory
|
||||
node install.js # A → E (everything + dev tools) or A → O (loop only)
|
||||
```
|
||||
|
||||
## Run
|
||||
|
||||
```bash
|
||||
plan2code-loop # fully interactive
|
||||
```
|
||||
|
||||
It will:
|
||||
|
||||
1. Find specs in `./specs/`
|
||||
2. Let you pick one if there are several
|
||||
3. Offer to resume an existing session
|
||||
4. Ask for a JIRA ticket ID, which agent to drive, the loop mode, and a max iteration count
|
||||
|
||||
Then, per iteration: read `overview.md` and the phase files, find the first unchecked task (or
|
||||
phase), implement it, mark the checkbox, repeat — until everything is done or it hits the iteration
|
||||
cap.
|
||||
|
||||
---
|
||||
|
||||
## Loop modes
|
||||
|
||||
| Mode | Each agent call | Git commits | Best for |
|
||||
|------|-----------------|-------------|----------|
|
||||
| **One task per loop** (default) | Implements a single task | The Node controller commits after each task | Smaller models, cautious execution |
|
||||
| **One phase per loop** | Implements every task in a phase | The agent commits after each task, with the JIRA ID | Larger context windows, tightly related tasks |
|
||||
|
||||
Session state lives per-spec in `specs/<feature>/.plan2code-loop/`, so each feature's progress
|
||||
stays isolated.
|
||||
|
||||
---
|
||||
|
||||
## Full documentation
|
||||
|
||||
Architecture, completion markers, agent adapters, and configuration:
|
||||
[`plan2code-loop/README.md`](../plan2code-loop/README.md)
|
||||
@@ -0,0 +1,59 @@
|
||||
# Metrics & Self-Improvement
|
||||
|
||||
`plan2code-metrics` closes the loop on the workflow itself: it collects data from your finished
|
||||
specs, aggregates it across runs and prompt generations, then uses AI to diagnose which step is
|
||||
underperforming and propose edits to the workflow prompts.
|
||||
|
||||
Aimed at **contributors and heavy users** — you don't need it to use Plan2Code.
|
||||
|
||||
← [Back to README](../README.md)
|
||||
|
||||
---
|
||||
|
||||
## The habit
|
||||
|
||||
One thing to remember: **collect after every finished spec.** Everything else is on demand.
|
||||
|
||||
```bash
|
||||
# Install once, from the plan2code root
|
||||
node install.js # A → E (everything + dev tools) or A → M (metrics only)
|
||||
|
||||
# After finishing a spec (steps 1–4)
|
||||
cd your-project
|
||||
plan2code-metrics # → "Collect metrics" → pick the spec dir → done, ~5 seconds
|
||||
```
|
||||
|
||||
Then, when you're curious or have a few runs banked:
|
||||
|
||||
```bash
|
||||
plan2code-metrics # → "View metrics status" the dashboard
|
||||
# → "Run analysis" AI diagnosis of weak steps
|
||||
# → "Generate improvement proposal" concrete prompt edits
|
||||
# → "Review and apply" patch src/plan2code-*.md
|
||||
```
|
||||
|
||||
## How much data you need
|
||||
|
||||
| Runs | What you get |
|
||||
|------|--------------|
|
||||
| **1** | Raw data and a basic dashboard. Start here. |
|
||||
| **3+** | AI analysis unlocks. Pattern detection starts working. |
|
||||
| **5–10+** | Averages stabilise; generation-over-generation comparisons become meaningful. |
|
||||
|
||||
You're looking for trends, not individual scores.
|
||||
|
||||
---
|
||||
|
||||
## Sending feedback upstream
|
||||
|
||||
`/plan2code-4-finalize` can submit an anonymised metrics payload to the maintainers as a
|
||||
`community-feedback` issue on the repo. Community runs are cohorted by the Plan2Code version that
|
||||
produced them, so your data improves the prompts everyone installs — without displacing the
|
||||
maintainer's own measurements.
|
||||
|
||||
---
|
||||
|
||||
## Full documentation
|
||||
|
||||
Data model, aggregation, cohorts, analysis prompts, and the ingestion flow:
|
||||
[`plan2code-metrics/README.md`](../plan2code-metrics/README.md)
|
||||
@@ -0,0 +1,54 @@
|
||||
# Claude Code Status Line
|
||||
|
||||
A persistent three-line status bar for Claude Code: model, project, git branch, uncommitted diff
|
||||
stats, session duration and cost, context-window usage, and plan quota.
|
||||
|
||||
It reads everything from the JSON Claude Code already sends on stdin — **no API calls, no auth, no
|
||||
background processes.** Optional, and unrelated to the workflow itself.
|
||||
|
||||
← [Back to README](../README.md)
|
||||
|
||||
---
|
||||
|
||||
## What it looks like
|
||||
|
||||
On Pro / Max / Teams accounts, where rate limits are available:
|
||||
|
||||
```
|
||||
╭───╮ Opus 5 / high │ plan2code │ feature/pathfinder-github-iss │ +12 -3
|
||||
│ ★ │ ┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄
|
||||
╰┬─┬╯ 3h 5m ($4.62) │ ▰▰▰▰▰▱▱▱▱▱▱▱ 42% (84K) │ 5h: 28% · 7d: 61%
|
||||
```
|
||||
|
||||
On Enterprise / Bedrock / Vertex / pay-as-you-go, where they aren't, the last segment becomes session
|
||||
token counts instead:
|
||||
|
||||
```
|
||||
╭───╮ Sonnet 5 │ plan2code │ main │ +12 -3
|
||||
│ ★ │ ┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄
|
||||
╰┬─┬╯ 2m ($0.18) │ ▰▰▱▱▱▱▱▱▱▱▱▱ 18% │ 88k in · 3k out
|
||||
```
|
||||
|
||||
The icons down the left are Planny, the project mascot.
|
||||
|
||||
---
|
||||
|
||||
## Install
|
||||
|
||||
```bash
|
||||
node install.js # A → E (everything + dev tools) or A → S (status line only)
|
||||
```
|
||||
|
||||
That copies the script to `~/.claude/plan2code-statusline.js`, writes a default config to
|
||||
`~/.claude/statusline-config.json` (an existing config is preserved), and registers it in
|
||||
`~/.claude/settings.json`.
|
||||
|
||||
If you already have a custom `statusLine` entry, the installer asks before replacing it and backs the
|
||||
old one up. Uninstalling removes the script and the settings entry but leaves your config file alone.
|
||||
|
||||
---
|
||||
|
||||
## Full documentation
|
||||
|
||||
Config options, compact mode, thresholds, and troubleshooting:
|
||||
[`src/statusline-claude/README.md`](../src/statusline-claude/README.md)
|
||||
@@ -0,0 +1,46 @@
|
||||
# Workflow Test Bot
|
||||
|
||||
`plan2code-bot` drives the whole workflow end to end with no human in the loop — init, plan,
|
||||
document, implement, finalize — to test that the prompts still hold together.
|
||||
|
||||
Built for **maintainers**. If you're using Plan2Code to ship features, you don't need this.
|
||||
|
||||
← [Back to README](../README.md)
|
||||
|
||||
---
|
||||
|
||||
## Two modes, auto-detected
|
||||
|
||||
| Condition | Mode | What it does |
|
||||
|-----------|------|--------------|
|
||||
| No `AGENTS.md` in the working directory | **New project** | Invents an app idea, creates a subdirectory, writes `IDEA.md`, runs init, then all four steps |
|
||||
| `AGENTS.md` present | **Enhancement** | Reads the existing codebase, proposes a realistic enhancement, writes `IDEA.md`, then runs plan → finalize |
|
||||
|
||||
## Install
|
||||
|
||||
```bash
|
||||
node install.js # A → E (everything + dev tools) or A → B (bot only)
|
||||
```
|
||||
|
||||
## Run
|
||||
|
||||
```bash
|
||||
# New project mode — start from an empty directory
|
||||
mkdir /tmp/test-bot && cd /tmp/test-bot
|
||||
plan2code-bot
|
||||
|
||||
# Enhancement mode — start from a project that has an AGENTS.md
|
||||
cd my-project
|
||||
plan2code-bot
|
||||
|
||||
# Or seed the idea generator yourself
|
||||
plan2code-bot --idea "web app that renders the current weather as vector images"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Full documentation
|
||||
|
||||
Agent SDK wiring, run evaluation, and scoring:
|
||||
[`plan2code-bot/README.md`](../plan2code-bot/README.md) ·
|
||||
[`plan2code-bot/EVALUATION-SYSTEM.md`](../plan2code-bot/EVALUATION-SYSTEM.md)
|
||||
@@ -0,0 +1,174 @@
|
||||
# Walkthrough: one feature, start to finish
|
||||
|
||||
A REST API for task management goes from a sentence to archived specs, all on the web console.
|
||||
Each session stays short, and the specs on disk carry everything from one session to the next.
|
||||
|
||||
← [Back to README](../README.md)
|
||||
|
||||
---
|
||||
|
||||
## Before you start
|
||||
|
||||
- **Node.js 18 or newer.** Check with `node --version`. No Node? Get it from [nodejs.org](https://nodejs.org/) (the LTS download), or run `winget install OpenJS.NodeJS.LTS` on Windows, `brew install node` on macOS, or use `nvm` on Linux. Then open a new terminal.
|
||||
- **Start from your project.** Open your terminal in the project you want to work on (`cd` into it) before you run anything. Plan2Code works on the folder you start it in.
|
||||
- **Ways in.** `plan2code` (Claude Code, Devin or Codex), or type `/plan2code` in your agent (`$plan2code` in Codex).
|
||||
- **No agent yet?** Install Claude Code, Codex or Devin first.
|
||||
|
||||
Not installed yet? The install steps are in the [README](../README.md#install-and-start).
|
||||
|
||||
---
|
||||
|
||||
## Session 1: Plan
|
||||
|
||||
Run `plan2code` in the project (or `/plan2code` inside your agent). The dashboard opens in your
|
||||
browser with every step laid out as a card.
|
||||
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="../docs/screenshots/dashboard-dark.webp">
|
||||
<img src="../docs/screenshots/dashboard-light.webp" alt="The Plan2Code dashboard: a Set up card, then the steps in order as cards, one of them marked Suggested.">
|
||||
</picture>
|
||||
|
||||
Pick **Plan** and describe the idea in the box: *I want to build a REST API for a task management
|
||||
application.* The same page turns into the Plan session.
|
||||
|
||||
The questions arrive in batches of up to three, each option with its trade-off written underneath.
|
||||
Answer what is there and press **Send to Plan2Code**; the next batch follows.
|
||||
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="../docs/screenshots/question-dark.webp">
|
||||
<img src="../docs/screenshots/question-light.webp" alt="A Plan question card, How tasks are paged, with three options, the first marked Suggested, each with its trade-off underneath.">
|
||||
</picture>
|
||||
|
||||
The phase breakdown comes back as a list you can reorder and edit. Documents a skill writes on the
|
||||
page open as tabs like this one, where settled parts read as decisions and anything still a guess
|
||||
is marked as assumed and still open.
|
||||
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="../docs/screenshots/doc-dark.webp">
|
||||
<img src="../docs/screenshots/doc-light.webp" alt="The What we've agreed tab for the task API: a settled summary, an assumed section on paging with a dashed edge, and a dimmed draft list of what is still to work out.">
|
||||
</picture>
|
||||
|
||||
Plan proposes a tech stack, Fastify + Postgres + Zod, and does not pick it alone: a sign-off card
|
||||
asks you to approve it. Plan then designs the architecture. At 92% confidence (the gate is 90%) it
|
||||
asks whether to write the draft, and with 3 assumptions written down, it writes:
|
||||
|
||||
```
|
||||
specs/task-api/PLAN-DRAFT-20260804.md
|
||||
```
|
||||
|
||||
Two files land: the draft, and a `PLAN-CONVERSATION-*.md` log of how you got there. The finish
|
||||
card names the next step.
|
||||
|
||||
> **Started foggy instead?** Run `/plan2code-0-pathfinder` first. When its map clears it writes a
|
||||
> `PLAN-DRAFT` that Plan picks up at Phase 4, with requirements and scope already answered.
|
||||
|
||||
---
|
||||
|
||||
## Session 2: Document
|
||||
|
||||
On Plan's finish card, press **Back to the dashboard** (or start a fresh console session if the
|
||||
session meter says so; see Session 3 below). Pick **Document**, with `specs/task-api` selected in
|
||||
the picker at the top. It reads `specs/task-api/PLAN-DRAFT-20260804.md`.
|
||||
|
||||
The overview and each phase file appear as tabs as they are written, so you watch the spec take
|
||||
shape:
|
||||
|
||||
```
|
||||
specs/task-api/overview.md
|
||||
specs/task-api/phase-1.md Project setup (6 tasks)
|
||||
specs/task-api/phase-2.md Data model (8 tasks)
|
||||
specs/task-api/phase-3.md API endpoints (11 tasks)
|
||||
specs/task-api/phase-4.md Authentication (7 tasks)
|
||||
```
|
||||
|
||||
Parallel execution groups: Phase 3 and Phase 4 don't share files.
|
||||
|
||||
---
|
||||
|
||||
## Sessions 3 to N: Implement, one phase each
|
||||
|
||||
Look at the session meter in the top bar first. Plan and Document add 2 points each, so after
|
||||
those two the meter is at 4: **Session: getting long**, in yellow. That is the cue to close this
|
||||
console session and start a fresh one for the build (run `plan2code` again). This is the first of
|
||||
the four rules:
|
||||
|
||||
> **1 · Keep each session short.**
|
||||
> Chaining a couple of small skills on the dashboard is fine. Start a fresh console session when the session meter turns red, and always before a big planning or build step. The specs on disk carry everything between sessions.
|
||||
|
||||
On the fresh dashboard, pick **Implement** for `specs/task-api`. Phase 1 (Project setup) is the next
|
||||
unchecked phase, so it starts there. The page shows the build as it goes: a progress bar counting
|
||||
tasks, the phase's task list ticking as each task lands on disk, and a line beside Planny saying
|
||||
what it is doing now. Use the **Ask** tab for a quick question without interrupting the build.
|
||||
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="../docs/screenshots/build-dark.webp">
|
||||
<img src="../docs/screenshots/build-light.webp" alt="A phase of a task API being built: 5 of 11 done on the progress bar, and the phase's task list with the first five ticked.">
|
||||
</picture>
|
||||
|
||||
When all 6 of 6 tasks are ticked in `phase-1.md`, a **Completion report** tab opens with the
|
||||
sign-off card: **Review the code first**, **Approve this phase**, or **I want changes**.
|
||||
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="../docs/screenshots/signoff-dark.webp">
|
||||
<img src="../docs/screenshots/signoff-light.webp" alt="The Approve this phase card, with a button to read the completion report and three choices: Review the code first, Approve this phase, and I want changes.">
|
||||
</picture>
|
||||
|
||||
After you approve, `overview.md` marks Phase 1 done, and the finish card gives the next command:
|
||||
Phase 2, Data model (8 tasks), in a new session.
|
||||
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="../docs/screenshots/finish-dark.webp">
|
||||
<img src="../docs/screenshots/finish-light.webp" alt="The finished screen after a phase sign-off: the phase is built, the next implement command with a Copy button, and a Back to the dashboard button.">
|
||||
</picture>
|
||||
|
||||
Repeat. A fresh session each time. It always finds the next open phase itself.
|
||||
|
||||
When you reach a parallel group, it offers you the choice: open a second agent, take the other
|
||||
phase, and the `[/]` marks keep them from colliding.
|
||||
|
||||
Pick **Implement + review** instead when review should run automatically before phase approval.
|
||||
**Review** remains available on the dashboard for an independent second opinion at any other time.
|
||||
|
||||
---
|
||||
|
||||
## Final session: Finalize
|
||||
|
||||
With every phase approved, the dashboard suggests **Finalize** for `specs/task-api`. Pick it in a
|
||||
fresh session. Each check lands on the page as a report tab, and anything that needs your say is
|
||||
a card:
|
||||
|
||||
- **Validation.** All 32 tasks verified against the phase specs. 2 gaps found and fixed.
|
||||
- **Documentation review.** README needs the new `/tasks` endpoints; AGENTS.md is current. A card
|
||||
lists the proposed doc updates, and you tick the ones to make.
|
||||
- **Spec cleanup.** A confirm card, then `specs/task-api/` moves to `specs--completed/task-api/`.
|
||||
|
||||
The finish card says the implementation is complete, and gives the commit command when doc
|
||||
updates landed.
|
||||
|
||||
---
|
||||
|
||||
## If requirements move mid-build
|
||||
|
||||
Don't patch the code and hope the specs catch up. Pick **Revise the plan** on the dashboard: it
|
||||
edits the specs (and only the specs), so the drawing and the build stay in agreement.
|
||||
|
||||
---
|
||||
|
||||
## Prefer the terminal?
|
||||
|
||||
The same journey is four commands, each in a new conversation:
|
||||
|
||||
1. `/plan2code-1-plan` with the idea in a sentence. Writes `specs/task-api/PLAN-DRAFT-20260804.md`.
|
||||
2. `/plan2code-2-document specs/task-api/PLAN-DRAFT-20260804.md`. Writes the overview and phase files.
|
||||
3. `/plan2code-3-implement specs/task-api/overview.md`, once per phase. It finds the next open phase itself.
|
||||
4. `/plan2code-4-finalize specs/task-api/overview.md`. Verifies, updates docs, and archives the spec.
|
||||
|
||||
Add `--web` to any of them (for example `/plan2code-1-plan --web`) to open that step straight on the
|
||||
web console without being asked. Every command and argument is in the README's
|
||||
[Prefer the terminal?](../README.md#prefer-the-terminal) section. You can switch between terminal and
|
||||
console at any point, because the files under `specs/` are the only state.
|
||||
|
||||
## More
|
||||
|
||||
- [web-console.md](web-console.md): every screen, setting and recovery path
|
||||
- [../QUICK-REFERENCE.md](../QUICK-REFERENCE.md): the one-page card
|
||||
@@ -0,0 +1,380 @@
|
||||
# Plan2Code Web Console: design proposal
|
||||
|
||||
**Status:** implemented in v2.4.0. Kept as the design record, because it explains
|
||||
*why* the thing is shaped the way it is. For how to use it, see
|
||||
[web-console.md](./web-console.md); for where the code lives, see
|
||||
[AGENTS-architecture.md](../.agents-docs/AGENTS-architecture.md).
|
||||
**Date:** 2026-09-20
|
||||
**Scope:** an optional local browser UI that `plan2code-0-pathfinder` and `plan2code-1-plan` can offer at startup, built as a shared component other workflow steps can adopt later.
|
||||
|
||||
---
|
||||
|
||||
## 1. Why this is smaller than it looks
|
||||
|
||||
Pathfinder is already written against a *delivery-channel abstraction*. Its rules say:
|
||||
|
||||
> AskUserQuestion when available; prose Q blocks only as fallback.
|
||||
|
||||
and `grilling.md` specifies the question object in full: a plain two-or-three-word header, the probe with its why-it-matters, two to four genuine options each described by its trade-off with exactly one named as the recommendation, plus an automatic `Other` escape hatch.
|
||||
|
||||
That is a form. The console is not a new workflow, it is a **third delivery channel** alongside the structured tool and prose. The methodology, the file formats, the gates and the rules are untouched.
|
||||
|
||||
Plan is the opposite: pure prose Q and A with seven phases and four named approval gates. But every one of its gates already resolves to a literal typed token (`approved`, `needs changes`, `approve / refine / abort`). That gives us the second half of the idea.
|
||||
|
||||
### The keystone: answers map back to the literal token
|
||||
|
||||
Every console request carries two extra fields:
|
||||
|
||||
| Field | Purpose |
|
||||
| --- | --- |
|
||||
| `fallbackText` | the exact terminal phrasing the prompt would have printed |
|
||||
| `token` | what each button resolves to: `approved`, `H`, `A`, `S 1,3,5`, `yes`, `skip` |
|
||||
|
||||
Clicking **Approve** in the browser is then byte-identical to typing `approved` in the terminal. No prompt logic ever forks. If the console is absent, refused, or times out, the agent prints `fallbackText` and the session continues in the terminal with nothing lost. Mid-session switching in either direction is free, because the markdown files under `specs/` remain the only source of truth.
|
||||
|
||||
This one decision is what keeps the integration from metastasising across twelve prompt files.
|
||||
|
||||
---
|
||||
|
||||
## 2. Hard constraints found during research
|
||||
|
||||
These are verified, not assumed. They shape everything below.
|
||||
|
||||
### 2.1 The character limit is the binding constraint
|
||||
|
||||
`scripts/validate-char-count.js` caps every flat `src/plan2code-*.md` at 20,000 characters since 2.4.1 (11,000 when the numbers below were measured), enforced by a husky pre-commit hook. Measured today:
|
||||
|
||||
```
|
||||
10995 5 plan2code-0-pathfinder.md <- 5 characters of headroom
|
||||
10676 324 plan2code-1-plan.md
|
||||
10835 165 plan2code-2-document.md
|
||||
```
|
||||
|
||||
Neither target prompt can absorb the integration inline. **Trimming pathfinder by roughly 250 characters is a prerequisite task, not a nice-to-have.** Reference files are exempt from the limit, so all of the console contract lives in one.
|
||||
|
||||
### 2.2 Packaging needs zero installer code changes
|
||||
|
||||
`computeExpectedSkills()` in `install.js` copies `additionalReferences` directories verbatim through `listFilesRecursive()`, which has no extension filter. The initial implementation fanned one shared source directory into two skills; the current installer fans it into every skill.
|
||||
|
||||
Current packaging constraints:
|
||||
|
||||
- Reference files are copied as `Buffer`s, so binary assets are supported; the shipped MP3 chimes exercise this path. Browser-served assets must also be added to the server's `SERVABLE` allow-list and covered by a test.
|
||||
- `skills/` is generated build output (committed, and checked for drift by `npm test`) and `buildSkills()` prunes files it doesn't expect. Assets must originate in `src/` and never be hand-placed.
|
||||
|
||||
### 2.3 `specs/` is gitignored, which is an argument *for* the server
|
||||
|
||||
Three prompts repeat the warning that Glob silently fails on `specs/` and only a shell listing works. A Node server enumerating candidate spec directories server-side and handing the page a list is strictly better than either a terminal listing or a browser file input.
|
||||
|
||||
### 2.4 Formats that must round-trip byte for byte
|
||||
|
||||
- `<!-- METRICS_JSON {...} -->` comments
|
||||
- the `## User Feedback` table (exact field names `Rating`, `Reason`, `Went Well`, `Went Poorly`, pipes escaped as `\|`)
|
||||
- the five-state checkbox alphabet `[ ]` `[/]` `[x]` `[?]` `[!]`, with the invariant "never reset `[/]` to `[ ]`"
|
||||
- the handoff string `**Status:** Phase 3 Complete - Resume at Phase 4`, plain ASCII hyphen, single spaces
|
||||
|
||||
The console carries all of these as opaque strings and never reformats them.
|
||||
|
||||
### 2.5 Two regex landmines
|
||||
|
||||
- `plan2code-metrics` scrapes confidence with patterns like `/[Rr]equirements?[:\s|]+(\d{1,2})/` that **do not require a percent sign**. Nothing the console writes under `specs/` may contain bare `Requirements` / `Feasibility` / `Integration` / `Risk` followed by a number.
|
||||
- The loop parses `TASK_COMPLETE`, `PHASE_COMPLETE` and friends. Pathfinder already forbids these tokens under `specs/`.
|
||||
|
||||
Both are cheap to enforce mechanically in the server's write path.
|
||||
|
||||
---
|
||||
|
||||
## 3. Architecture
|
||||
|
||||
### 3.1 Placement
|
||||
|
||||
```
|
||||
src/web-console/
|
||||
console.mjs CLI: open | post | wait | status | stop
|
||||
server.mjs the HTTP server (spawned detached by `open`); routes.mjs lists its URLs
|
||||
files.mjs, sessions.mjs, patches.mjs, scan.mjs, ... paths, atomic writes, patch merge, validate(), the repo scan
|
||||
console.md the agent-facing contract
|
||||
public/index.html markup shell only
|
||||
public/app.js the client's entry (no inline script, see CSP below); screens/ and state.js hold the rest
|
||||
public/styles/ the stylesheet, joined by the server into /app.css
|
||||
public/render.js markdown tokens to DOM nodes
|
||||
public/vendor/marked.esm.js pinned 15.0.7, MIT, lexer only
|
||||
```
|
||||
|
||||
Wired in with one data entry per consumer:
|
||||
|
||||
```js
|
||||
{
|
||||
source: 'plan2code-0-pathfinder.md',
|
||||
// ...
|
||||
additionalReferences: [{ source: 'web-console', target: 'web-console' }]
|
||||
}
|
||||
```
|
||||
|
||||
Lands at `~/.agents/skills/<skill>/references/web-console/` on all ~28 target agents. The server finds its own siblings via `path.dirname(fileURLToPath(import.meta.url))`.
|
||||
|
||||
The agent needs an absolute path to invoke it. `ai-assist-git-pr` already establishes the convention, proven on Windows, and we reuse its wording:
|
||||
|
||||
> `<SKILL_ROOT>` = the directory containing this `SKILL.md` (its install location). Use the absolute path you loaded it from.
|
||||
|
||||
### 3.2 The transport, which is the genuinely hard part
|
||||
|
||||
A turn-based agent must wait up to twenty minutes for a human. Claude Code's Bash tool caps at 600s and **harness-managed background tasks are not a safe place to wait**: there are open issues documenting them being killed at 5 to 20 minutes, killed on compaction, killed when a new prompt arrives, and leaked with no handle when spawned by subagents. Detached processes are explicitly immune.
|
||||
|
||||
So: **split into two processes with deliberately different lifetimes.**
|
||||
|
||||
```
|
||||
# once, at handoff
|
||||
node <SKILL_ROOT>/references/web-console/console.mjs open --file request.json
|
||||
-> spawns server.mjs DETACHED, prints URL + session id, exits in under 300ms
|
||||
|
||||
# repeatedly, until done
|
||||
node ... console.mjs wait --seconds 240
|
||||
exit 0 -> stdout is the result JSON. Done.
|
||||
exit 10 -> {"status":"waiting","elapsed":"6m12s","answered":3,"total":7,...}
|
||||
Agent relays one line to the user and calls wait again.
|
||||
exit 20 -> server is dead. Agent restarts it, re-reports the URL.
|
||||
exit 30 -> human hit Cancel.
|
||||
```
|
||||
|
||||
Why bounded rather than a single long block:
|
||||
|
||||
- The deadline lives in our code, not the harness's. `--seconds 240` covers a 20-minute session in five turns. Drop to `--seconds 90` for harnesses with a 120s default (Cursor auto-backgrounds and cannot be told not to).
|
||||
- Every return is a free heartbeat: "still waiting, 3 of 7 answered, 6 minutes in" beats silence.
|
||||
- Interruption is survivable. Ctrl-C the agent, compact the context, restart: the next `wait` re-attaches, because state is on disk.
|
||||
|
||||
The waiter uses `fs.watch` on the session **directory** (watching a file breaks on Windows when the file is replaced by rename) with a 500ms `stat` fallback as the authority, and pings `/health` every 5s for liveness. The result is delivered **through the filesystem**, not HTTP, which decouples the waiter from the server and is also the resumability story.
|
||||
|
||||
**Optional push accelerator, Claude Code only:** at `start`, also fire a backgrounded `until [ -f <dir>/result.json ]; do sleep 2; done`. If it survives, submit-to-agent latency drops to near zero. If it gets killed, nothing breaks, because the poll loop is the source of truth.
|
||||
|
||||
### 3.3 Port, lifecycle, security
|
||||
|
||||
| Concern | Decision |
|
||||
| --- | --- |
|
||||
| Port | `listen(0, '127.0.0.1')`, handle file in `os.tmpdir()/<tool>/<sha1(cwd).slice(0,8)>/`. This is Jupyter's `jpserver-<pid>.json` pattern and RFC 8252 §7.3. A fixed port is fatal here: you run git worktrees, so two agents in two checkouts of one repo is routine, and a fixed port makes that silently wrong. |
|
||||
| Bind | the literal `127.0.0.1`, never `0.0.0.0`, never the string `localhost` (which may resolve to `::1` and produce the classic "server is up but the browser gets ECONNREFUSED" bug on Windows). |
|
||||
| Auto-open | best-effort, never fatal. Skip when `DISPLAY` and `WAYLAND_DISPLAY` are both unset, or `SSH_CONNECTION` / `REMOTE_CONTAINERS` is set. Honour `BROWSER=` and `--no-open`. |
|
||||
| Orphan prevention | a **server-side idle deadline** (30 min, bumped by any authenticated request) is the mechanism, not a nicety. Windows has no real SIGTERM, and a detached server with no console never sees `SIGINT`, so signal handlers cannot be relied on. Plus a 4h absolute cap, a `pagehide` beacon, an explicit `stop`, and a reap sweep on every `start`. |
|
||||
| Liveness test | `process.kill(pid, 0)` **and** a `/health` check whose returned session id matches the handle. PID reuse is real; the sid match is what disambiguates. |
|
||||
|
||||
Security, six controls, about 60 lines:
|
||||
|
||||
1. Bind `127.0.0.1`.
|
||||
2. **`Host` header allowlist.** This is the DNS-rebinding defence and the highest-value line in the server. Vite shipped GHSA-vg6x-rcgg-rjx6 for exactly this omission.
|
||||
3. 128-bit token **in the URL path**, not the query string. Path placement also kills the Windows `cmd /c start` `&`-injection hazard, because the URL then contains no `&`.
|
||||
4. First `GET /s/<token>/` sets `HttpOnly; SameSite=Strict` cookie and 302s to `/`. Token leaves the address bar, history and pasted screenshots; CSRF protection comes free.
|
||||
5. `Origin` check on every mutating request.
|
||||
6. Strict CSP with no `unsafe-inline`, which is why JS and CSS are separate files rather than one inlined HTML.
|
||||
|
||||
**On whether XSS matters here.** The tempting argument is "it is the user's own machine and the model would not write `<script>`". That misses the real risk. The page is same-origin with a server that reads and writes the user's files and holds the session token, so script in that page can post arbitrary answers back to the agent, which then acts on them with the agent's full tool permissions. And the markdown is only nominally agent-authored: in practice the agent is summarising a dependency README, a scraped page, a PR description, a log. Treat it as attacker-controlled.
|
||||
|
||||
The structural fix, rather than a filter: **vendor `marked` for `lexer()` only and render tokens to the DOM with `createElement` and `textContent`.** No HTML string is ever produced, so there is nothing for a sanitiser bypass to bypass, and the strict CSP holds. Roughly 120 lines of renderer. Hand-rolling the parser instead is a trap: hand-rolled markdown fails exactly where agent-authored technical documents live (a table inside a list item, a fenced block containing backticks) and its failure mode is usually an injection hole.
|
||||
|
||||
### 3.4 Browser transport
|
||||
|
||||
SSE primary (about fifteen lines on Node's built-in `http`), with automatic fallback to 3s interval polling after three consecutive errors. **Exactly one `EventSource` per page, ever**: browsers cap HTTP/1.1 at ~6 connections per origin, and a second stream per tab across three tabs wedges the origin with no error and no timeout. Multiplex everything through one stream with a `type` field.
|
||||
|
||||
The page shows the **agent's** liveness, not the server's. If the agent's turn crashed, the server is still happily up and a naive spinner lies forever. Stamp `agentLastSeen` on every waiter ping; when stale past two minutes the page says so plainly: "The agent has not checked in for 4 minutes. Your answers are saved. Check your terminal."
|
||||
|
||||
### 3.5 State on disk
|
||||
|
||||
The filesystem is the database and the result transport.
|
||||
|
||||
```
|
||||
~/.plan2code/console/sessions/<sid>/
|
||||
session.json sid, cwd, workflow, title, phase
|
||||
request-<rev>.json the agent's payload, immutable per revision
|
||||
draft.json in-progress answers, debounced ~500ms write
|
||||
result.json written ATOMICALLY on submit (temp + fsync + rename)
|
||||
events.ndjson append-only, doubles as SSE Last-Event-ID replay
|
||||
```
|
||||
|
||||
Deliberately **not** under `specs/`: that keeps the console clear of the metrics scraper and the loop's marker parser, and survives a `git clean`.
|
||||
|
||||
Draft persistence is the highest-value feature in the tool and among the cheapest. Twenty minutes of a product manager's structured answers must never be lost to a closed tab. Server-side debounced write plus a `localStorage` mirror keyed by `sid + rev`.
|
||||
|
||||
Recovery matrix:
|
||||
|
||||
| Failure | Recovery |
|
||||
| --- | --- |
|
||||
| Tab closed or browser crashed | Reopen the URL, draft restored, agent never notices |
|
||||
| Server died, agent alive | `wait` returns exit 20, agent runs `start --resume <sid>`, new port, same session dir |
|
||||
| **Agent session died, human still working** | Human submits, `result.json` lands on disk. A fresh session runs `status`, finds the unconsumed result, picks up where it left off |
|
||||
| Machine rebooted | Handle file is gone (correct), session dir survives, `--resume` works |
|
||||
|
||||
---
|
||||
|
||||
## 4. The interaction contract
|
||||
|
||||
### 4.1 Item envelope
|
||||
|
||||
```jsonc
|
||||
{
|
||||
"id": "i7", "topic": "t2", "kind": "choice",
|
||||
"title": "Export format", // PLAIN 2-4 words, never internal jargon
|
||||
"body": "markdown: the probe plus its why-it-matters",
|
||||
"options": [ { "k": "A", "text": "CSV", "detail": "trade-off", "recommended": true } ],
|
||||
"allowOther": true,
|
||||
"required": true,
|
||||
"status": "open",
|
||||
"answer": null,
|
||||
"thread": [],
|
||||
"fallbackText": "the exact terminal phrasing",
|
||||
"token": { "A": "a", "B": "b" } // maps a click back to the literal reply
|
||||
}
|
||||
```
|
||||
|
||||
Note `recommended` is **optional per option**. Handoff explicitly wants its inferred task offered as the recommendation.
|
||||
|
||||
### 4.2 Primitives
|
||||
|
||||
Tier 1, needed for pathfinder and plan, build now:
|
||||
|
||||
| Kind | Covers |
|
||||
| --- | --- |
|
||||
| `choice` | Step 0 intent gate, all six destination probes, the 14 frontier axes, plan's coverage and scope questions |
|
||||
| `multi` | plan's testing types (Unit / Integration / E2E / None) |
|
||||
| `text` | sacrificial boundary, the embarrassment question, kebab-case feature name **with live pattern validation the terminal cannot do** |
|
||||
| `confirm` | the Tier-2 sketch gate, the lock offer, abort confirmations |
|
||||
| `recap` | the recap-and-confirm turn. Non-skippable by design |
|
||||
| `review` | plan's four approval gates, `1b`'s spec-update gate, paper-sketch reactions |
|
||||
| `checklist` | `legwork · HITL`: numbered steps plus Done / Blocked / Need help / Defer plus a values field |
|
||||
| `menu` | the fork menu: up to three takeable questions plus Start fresh, one recommended, with the resume command as copy-to-clipboard |
|
||||
| `list` | orderable and editable rows, for plan Phase 6's implementation phases |
|
||||
|
||||
Tier 2, design the schema to admit them but do not build yet: `findings-triage`, `table-review`, `form`, `path-picker`, `command-handoff`, `notice`, `progress`.
|
||||
|
||||
### 4.3 Rules the server enforces mechanically
|
||||
|
||||
Several prose rules become checks, which is the quiet advantage of routing through a server at all:
|
||||
|
||||
- **Reject a patch leaving more than three open required items.** Grilling says "the cap is three regardless of what the environment allows. The ceiling is the human's attention, not the tool's schema." A web UI tempts you to show ten. Make the rule mechanical.
|
||||
- **Reject internal jargon in `title`**: `grill`, `frontier`, `fog`, `HITL`, `Locked:`, `Blocked by:`. There is an explicit do-not-say list in `grilling.md`; this is where to enforce it.
|
||||
- **One authoritative gate per session.** `plan2code-3-implement-review` proves several prompts each carry an approval gate while only one may fire when composed. A `gate: { id, authoritative }` field plus a server guard.
|
||||
- **Defer is a third verb**, distinct from reject.
|
||||
- Reject forbidden tokens and bare confidence-word-plus-number patterns in anything written under `specs/`.
|
||||
- Stamp every timestamp server-side. Models do not reliably know the time.
|
||||
|
||||
---
|
||||
|
||||
## 5. The UI
|
||||
|
||||
Three panes, plus view tabs, closer to pathfinder's own vocabulary than to a grilling UI.
|
||||
|
||||
```
|
||||
┌──────────────────────────────────────────────────────────────────────┐
|
||||
│ 🧭 audit-export · Pathfinder · Working 4 of 9 cleared ▓▓▓▓░░░░░ │
|
||||
│ ● Waiting on you · 3 questions [Questions] [Map] [Draft] │
|
||||
├───────────────┬──────────────────────────────┬───────────────────────┤
|
||||
│ THE MAP │ What you end up with │ DISCUSSION │
|
||||
│ │ │ │
|
||||
│ ✓ Destination │ Why this matters: ... │ thread on this item │
|
||||
│ ✓ Codebase │ │ │
|
||||
│ ● Export fmt │ ○ A CSV, ... │ │
|
||||
│ ○ Size cap │ ◉ B Parquet RECOMMENDED │ │
|
||||
│ ⊘ Retention │ ○ C Both, ... │ │
|
||||
│ │ ○ Something else ______ │ │
|
||||
│ NOT YET CLEAR │ │ │
|
||||
│ · fog item │ Not sure, skip for now │ │
|
||||
├───────────────┴──────────────────────────────┴───────────────────────┤
|
||||
│ 2 staged · Export format → B · +1 comment ⌘↩ [Send to Agent] │
|
||||
└──────────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
### What to take from grill-with-ui
|
||||
|
||||
- **Batch staging with one explicit Send.** Everything is local and reversible until one deliberate press. For a non-technical user this removes the terror of "did I just commit to that?"
|
||||
- **The three-tier commitment vocabulary**: staged (amber, removable) → sent and pending (dashed, spinner) → recorded (green check). Honoured consistently on every surface.
|
||||
- **The whole stuck-agent apparatus**: live elapsed counter, disabled Send while working, a five-minute grace that re-enables Send with an explanation, server-gone detection with self-reconnect. About 40 lines, and more honest about agent latency than most commercial agent UIs.
|
||||
- **Assumed regions.** The best idea in that repo: the generated artifact marks regions that depend on still-open questions with a dashed outline and "assumed, pending Q3". This transplants directly onto a plan taking shape.
|
||||
- **Versioned artifacts with a staleness flag** and a one-line change note.
|
||||
- `withInputs()` focus preservation, raw-string diffing before re-render, and the `prefers-reduced-motion` handling that keeps progress indicators legible rather than freezing them.
|
||||
|
||||
### What to change
|
||||
|
||||
- **Topics, not rounds.** Grill groups the nav by round, which is a temporal artifact: "questions the agent happened to ask on turn 4". Its own sample data has one round containing three unrelated subjects. Product people cannot use that. Group by topic, stable and nameable.
|
||||
- **Show real progress.** Grill has no "N of M" counter at all. Pathfinder's trail footer already computes `4/9 cleared` and a plain-English confidence line. Put both in the header. In a 45-minute session with a PM, "how much longer is this" is the first question asked.
|
||||
- **Recommendations become optional.** Grill always leads with one, which is right when the agent has an opinion and you are pushing on it. In discovery the agent frequently should not have an opinion, and pre-filling one anchors a PM into rubber-stamping. Neutral mode: no `rec`, or reframed as "what similar products do".
|
||||
- **Real, accessible form controls.** Grill's options are `<li>` with `onclick`, so they are unreachable by keyboard and invisible to screen readers. Non-negotiable to fix if non-technical stakeholders are in scope.
|
||||
- **Markdown actually renders.** Grill escapes everything and sets `white-space: pre-line`; there is no markdown at all. A plan document cannot be shown that way.
|
||||
- **Rename everything.** "Grill", "durable", "Defer", "Reopen", "Why A." is a vocabulary for interrogating an engineer who already has a plan.
|
||||
- **Do not dim rejected options to 45%.** In discovery the rejected options are often the most valuable thing in the room, and an engineer joining late needs to see why B lost.
|
||||
|
||||
### Two things the console unlocks that the terminal cannot
|
||||
|
||||
- **Tier-2 UI sketches.** `resolve.md` already sanctions building 3 to 5 structurally different UI variants switched by "a URL search param plus a small floating bar". The console can host them in a sandboxed iframe with a proper variant switcher. This is already in the methodology and currently awkward.
|
||||
- **Anchored reactions.** `resolve.md` insists every sketch probe "names its row or element". With `anchors: { "row5": "b3" }`, clicking the probe highlights the row. That is the inline-commenting capability, scoped to something the methodology already demands.
|
||||
|
||||
### Room-screen polish (v2.4.0)
|
||||
|
||||
Built for a mixed product and engineering room reading one screen together.
|
||||
|
||||
- **One width variable.** `--card-width` on `:root` in `styles/tokens.css` sets the column the card, the pager and the document tabs share (`max-width: min(var(--card-width), 100%)`, so a narrow window still wins); no fixed `720px` column rule is left outside a media query. Three presets, picked under *Card width* in the looks panel and saved as `looks.width`: `narrow` 720px, `comfortable` 880px (the default, and the variable's own value), `wide` 1080px, applied as `:root[data-width="…"]`. `CARD_WIDTHS` in `palette.js` is the same list for the page's validation and the server's first-paint `data-width`; **`palette.js` and `app.css` must agree**, which is the one place the number is written twice. The dashboard keeps its own 860px layout. Inside the card the `62ch` / `68ch` measure caps come off (`.card .md, .card .prompt { max-width: none; }`) so a wider card is not a narrow column in a wide frame; documents keep `.md`'s 68ch.
|
||||
- **One box grows.** On the primary card, the answer box that is being typed in — a `text` question's box, a choice's *Something else* box once picked, or the note under a verdict / confirm / recap once shown — is `textarea.grow`, and the card takes the column's full height above the pager (`.card.is-primary.has-grow { flex: 1 1 auto; }`). `fitGrowBox()` in `app.js` writes the card's free height as the box's `min-height`, **never under 160px**; a `ResizeObserver` watches the main column rather than the box, so the box growing can never retrigger it, and it writes only on a change over 1px. `resize: vertical` with that moving floor makes the handle taller-only; past the fill the card scrolls. Every other box keeps its ordinary size, and the notes panel is untouched.
|
||||
- **A switch per sound.** Every cue is an event in `SOUND_EVENTS` (`palette.js`), each naming its file and rank: `startSkill` (`start-skill.mp3`, played once the dashboard's **Start** is accepted) 5, `bootup` 4, `sessionStart` / `sessionEnd` (`start-stop.mp3`) 3, `question` / `skillReady` / `chatReply` (`next.mp3`) 2, `newTab` (`insert.mp3`) 1, `snore` (`sleeping.mp3`, looped by the wake-up outside the queue) 0. The queue, the held slot and the one-at-a-time rule in `app.js` work on events, one `Audio` per file shared by the events that use it. User Preferences shows a *Play sounds* master (`looks.sound`) over one box per event, saved flat as `sound<Event>` (`soundStartSkill`, …) because `looks.json` only holds flat values; `soundPrefs()` turns any missing or non-boolean switch on, so a file from before the switches keeps every sound. A cue plays only while the master and its own switch are both on; the master off greys the boxes but keeps their ticks, and ticking a box plays it.
|
||||
- **Send breathes.** `#btn-send:not(:disabled)` runs `send-pulse`, a soft accent ring that spreads and fades every 2.4s; a disabled Send is still, and reduced motion switches it off.
|
||||
- **Per-tab scroll memory.** An in-memory `Map` keyed by view id holds the scroller's position (the main column on a document or the Overview, the card on the questions view, with the item it belonged to), restored when the tab comes back. Page-local, never persisted, cleared when the session turns into or out of the dashboard.
|
||||
- **The Overview tab.** Appears only while `GET /overview` returns a file for the session's spec (on the dashboard: the picker's spec; gone for *start from scratch*), fetched with `no-store` on load, on a spec change and on every tab click, so it always shows the file as it is on disk. Rendered through the same DOM-only markdown path as every doc, captioned read-only. It never becomes a doc: the page is not the record.
|
||||
- **The footer slot.** The workspace label sits centred in the footer's middle track, 12px and muted: `footerLabel()` in `public/workspace.js` builds `folder · branch` (from the workspace's original folder and `state.branch`), or `folder + N folders · branch` once folders are added, and `renderWhere()` steps down through its narrower tiers (`FOOTER_TIERS`) until the text fits. A warning dot marks a missing or unreadable folder. A click opens the Workspace dialog (`#workspace-modal`), where each folder has its own **Copy path**. The notification pill is fixed over the same spot and covers it while it shows, on purpose: nothing there needs pressing while the pill is up. The dashboard keeps the footer for this label alone: `renderFooter()` puts `is-dash` on it, which hides the summary and Send (and on a narrow screen keeps the label, the one thing left in the bar); the footer only disappears there when there is no label to show.
|
||||
- **The wake-up.** A fresh dashboard (`state.wake`, plus a per-sid `sessionStorage` guard) plays Planny powering on centre stage, as proven in `pathfinder/sketch-01`. The wake layer hides the dashboard behind a solid `var(--bg)` backdrop (`.wake::before`, so it follows the theme) whose opacity fades out over the same 0.6s as the glide, revealing the menu as he lands; the notification pill (`.banner`, z-index 46) stays above the layer (45). Before the first click or key he sleeps there on loop under a "Click to wake Planny" hint (`.wake.dormant`): Z's rising, slow breathing, slack arms swaying out of step, his feet pulsing like a standby light. While he sleeps the page tries to loop `sleeping.mp3` (browsers usually refuse until the first click, so this is normally silent). That click fades the hint and nudges him (`.wake.stirring`): he rocks gently about his feet (`wake-nudge`) while exactly one snore plays from the top, via the `stir()` callback `playWake()` awaits — timed by the snore's `ended`, capped at 6s, or a 2.6s timer when sounds are off or refused. Then the boot starts to `bootup.mp3` (in place of the opening chime; outranked only by the Start-skill cue, which cannot coincide with it because the wake layer swallows every click and key until the run ends), which fades out over 0.5s the moment the run ends or is aborted. The boot pops the Z's outward: 0.4s power-on and his feet blink · 1.35s feet plant · 1.5s / 1.9s arms lift off his sides · 2.5s the star opens lit, with a scan · 2.85s he glances left, right, then ahead · 3.2s smile · 3.6s hop and a cheer, star back to ink · 4.3s a 0.6s glide into the rail, measured once by `boot.js` and handed to CSS as `--wake-glide` · the menu groups rise in 60ms apart as he lands, and the note types in. Done by 5s (a fallback timer covers a hidden tab whose transition never fires). The beats are CSS keyframes on delays under `.wake.booting`, all inside `@media (prefers-reduced-motion: no-preference)`; there is no skip: from the waking click on, clicks and plain keys (no Ctrl/Meta/Alt) are swallowed so the nudge, boot and sound always play out; only a launch mid-run aborts it (snore stopped, boot-up faded), and under reduced motion `playWake()` resolves at once and the awake dashboard is simply there.
|
||||
|
||||
---
|
||||
|
||||
## 6. The startup question
|
||||
|
||||
Both prompts open with one ask. Pathfinder already uses `AskUserQuestion`, so this costs almost nothing:
|
||||
|
||||
> Run this session in the **web console** (a local page in your browser, better for walking through decisions with someone) or **here in the terminal**?
|
||||
|
||||
Recommended default is an open decision (see §8). Because the markdown files stay the source of truth, the user can switch either way mid-session at no cost, and the prompt should say so.
|
||||
|
||||
---
|
||||
|
||||
## 7. Work plan
|
||||
|
||||
| # | Task | Notes |
|
||||
| --- | --- | --- |
|
||||
| 0 | **Trim `plan2code-0-pathfinder.md` by ~250 characters** | Hard prerequisite. 5 characters of headroom today. Candidates: the `grilling.md` fallback blockquote, the Rules list. |
|
||||
| 1 | `src/web-console/` skeleton: `console.mjs` start/wait/status/stop, detached spawn, handle file, reap sweep | The transport is the risky part, build and prove it first |
|
||||
| 2 | `server.mjs`: the six security controls, SSE, atomic result write with Windows `EPERM` retry | |
|
||||
| 3 | `index.html` + `app.js` + `app.css` + vendored `marked` lexer, token-to-DOM renderer | |
|
||||
| 4 | Tier 1 primitives, staging, drafts, Send | |
|
||||
| 5 | `console.md`: the agent contract | The only file the prompts point at |
|
||||
| 6 | `SOURCE_PROMPTS` entries + `npm run build:skills` + commit `skills/` | Zero installer code changes |
|
||||
| 7 | Pathfinder integration: startup ask, channel rule, `Read` line | ~250 chars, funded by task 0 |
|
||||
| 8 | Plan integration | 324 chars headroom, fits, trim ~150 for margin |
|
||||
| 9 | CHANGELOG + `version.json` + `package.json` in lockstep | `plan2code-publish` refuses to release on mismatch |
|
||||
|
||||
### Three things most likely to bite during implementation
|
||||
|
||||
1. **Forgetting `windowsHide: true` on the detached spawn.** It defaults to `false`, and `detached` on Windows forces a console window that "once enabled, cannot be disabled". Every handoff flashes a black box at the user.
|
||||
2. **`fs.rename` `EPERM` from antivirus and search indexers on Windows.** Intermittent, unreproducible on demand, looks exactly like a logic bug. Retry three times with backoff from day one.
|
||||
3. **Relying on `SIGTERM` for cleanup on Windows.** It does not arrive. Build the idle deadline first, not last, and comment why.
|
||||
|
||||
### Non-obvious portability notes
|
||||
|
||||
- grill-with-ui's heredoc idiom (`patch <<'EOF'`) is **not portable to PowerShell**, which is the default shell for Claude Code on Windows. Use a `--file <path>` form as the primary documented interface.
|
||||
- `nohup ... &` is bash-only. Backgrounding happens inside `console.mjs start`, never in the shell command the agent writes.
|
||||
- Always emit `node "<abs>/console.mjs"` quoted. Install paths contain spaces.
|
||||
|
||||
---
|
||||
|
||||
## 8. Open decisions
|
||||
|
||||
1. **Default channel.** Terminal (lower ceremony for an engineer working solo) or console (better for the cross-functional sessions that motivated this)? Recommendation: console marked as recommended in the ask, terminal as the low-ceremony alternative.
|
||||
2. **Vendoring `marked`.** It is MIT and dependency-free, but it is the first vendored third-party code in the repo, against a house style of "Node built-ins only". The alternative, a hand-rolled parser, is materially worse on both correctness and security. Recommendation: vendor it, pin the version, record the SHA-256.
|
||||
3. **Single-driver or multi-user.** Everything above assumes one browser, one driver, no identity or attribution. A facilitated workshop with one person at the keyboard works fine. Two people answering independently is a different product and reaches into the state model. Recommendation: single-driver for v1, say so explicitly.
|
||||
4. **Third consumer.** After pathfinder and plan, `/plan2code-review` is the strongest case: two of its rules exist only because output goes to a terminal ("for 15+ findings, present top 10", "output tables as direct markdown, NOT inside code blocks") and a browser deletes both. Its `S 1,3,5` fix selection is literally a checkbox list compressed into a CLI token, and one findings UI serves both `/plan2code-review` and `/plan2code-3-implement-review`.
|
||||
|
||||
---
|
||||
|
||||
## 9. Honest assessment of size
|
||||
|
||||
This is not a weekend. Rough shape: `console.mjs` plus `server.mjs` around 700 to 900 lines, the client around 900 to 1,200, the contract file 300 to 400 lines of prose, plus the prompt trims and build wiring. The transport and lifecycle work (tasks 1 and 2) is where the risk concentrates, and it is worth proving end to end on one primitive before building the other eight.
|
||||
|
||||
A smaller first cut that still tests the whole idea: pathfinder only, `choice` and `text` and `recap` only, no artifact pane. That exercises the transport, the token mapping, the fallback path and the three-probe cap, which are the parts most likely to be wrong.
|
||||
|
||||
---
|
||||
|
||||
## Credits
|
||||
|
||||
The architecture owes a large debt to `grill-with-ui`, whose file-ownership model, staged-then-send interaction, commitment tiers and assumed-region idea are all borrowed here. The implementation is independent.
|
||||
@@ -0,0 +1,964 @@
|
||||
# The Web Console
|
||||
|
||||
## New here? A two-minute tour
|
||||
|
||||
**Launch it.** After installing, run `plan2code` in your project folder. It starts Claude Code or
|
||||
Devin on the dashboard, and the page opens in your browser. In any other agent, run `/plan2code`
|
||||
inside it, or add `--web` to a skill (`/plan2code-1-plan --web plan a lunch voting app`).
|
||||
|
||||
**What you see.**
|
||||
|
||||
- **The dashboard** has a card for every skill. The one it suggests next is flagged. Pick a card and
|
||||
that skill starts on the same page.
|
||||
- **Questions** come laid out with the trade-offs next to each option and a progress bar on top.
|
||||
Nothing is sent until you press **Send**, and half-typed answers survive a closed tab.
|
||||
- **Tabs** show the document taking shape, the build progress and, always last, **Ask**, where you can
|
||||
put a quick question to the running agent.
|
||||
- **Sign-off** asks for your approval at the end of a phase. You can run the code review first from
|
||||
the same card, or press **Show me it working** to have the agent start the app and show you
|
||||
screenshots of the change right on the page.
|
||||
|
||||
**Where next.** [walkthrough.md](walkthrough.md) follows one feature from the first idea to the
|
||||
last phase. The rest of this file is the reference: every card, button and rule. Prefer the terminal?
|
||||
Run the same commands without `--web` and answer there; the files under `specs/` are identical.
|
||||
|
||||
---
|
||||
|
||||
The web console is the main way to use Plan2Code: a local page in your browser
|
||||
where you pick a step, answer its questions, watch the documents and the build
|
||||
take shape, and approve the work. Every skill runs on it, and `/plan2code` is
|
||||
the front door: it opens a dashboard of all of them, and whichever you pick
|
||||
starts right there on the same page.
|
||||
|
||||
It exists because the hardest part of adopting Plan2Code is not the engineering.
|
||||
It is getting the person who actually knows what the product should do into the
|
||||
room. Pathfinder and Planning are the two steps where that person matters most,
|
||||
and they were the two steps that looked like a wall of terminal text.
|
||||
|
||||
## Quick start
|
||||
|
||||
1. Install Plan2Code (see [Install and start](../README.md#install-and-start) in the README).
|
||||
2. Run `plan2code` in your project, or `/plan2code` inside your agent. The dashboard opens in your
|
||||
browser.
|
||||
3. Pick a card. The same page becomes that step's session.
|
||||
4. Answer on the page and press **Send to Plan2Code**.
|
||||
|
||||
Starting a step by its own command instead? Add `--web` (for example `/plan2code-1-plan --web`) and
|
||||
it opens on the page without asking.
|
||||
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="../docs/screenshots/dashboard-dark.webp">
|
||||
<img src="../docs/screenshots/dashboard-light.webp" alt="The Plan2Code dashboard: a Set up card, then the steps in order as cards, one of them marked Suggested.">
|
||||
</picture>
|
||||
|
||||
Scroll down for the utilities. Outside a git repository the **Git** card says so and still offers to start one:
|
||||
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="../docs/screenshots/dashboard-utilities-dark.webp">
|
||||
<img src="../docs/screenshots/dashboard-utilities-light.webp" alt="The utility cards: Quick task, Review, Handoff and Git, which notes that the folder is not a git repository yet and offers to start one.">
|
||||
</picture>
|
||||
|
||||
---
|
||||
|
||||
## What you get
|
||||
|
||||
- **Every question laid out**, with the trade-offs written next to each option
|
||||
instead of scrolling past in your history.
|
||||
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="../docs/screenshots/question-dark.webp">
|
||||
<img src="../docs/screenshots/question-light.webp" alt="A Plan question card, How tasks are paged, with three options, the first marked Suggested, each with its trade-off underneath.">
|
||||
</picture>
|
||||
|
||||
- **A progress bar.** "4 of 9 settled" answers the first thing anybody asks.
|
||||
- **Previous and Next under each card**, walking the questions still waiting, so
|
||||
the list on the left is somewhere to jump from rather than the only way round.
|
||||
- **An example you can accept.** Where a question comes with one, an *Autofill
|
||||
suggestion* button puts it in the box as a real answer for you to edit. It
|
||||
disappears as soon as you have typed anything of your own.
|
||||
- **Answers you have settled read as answers**, not as a form you might still be
|
||||
able to change: what you chose, stated in words, with everything else locked.
|
||||
- **A question you have sent is held** until Plan2Code answers it, showing
|
||||
what you sent. The rest of the page carries on working, so you can read ahead
|
||||
or answer the next question while you wait.
|
||||
- **The document taking shape**, in a tab, with the parts that are still guesses
|
||||
clearly marked as guesses.
|
||||
- **A brief, on demand** (Pathfinder). Press *Write a brief*, choose how far back,
|
||||
and what comes back is a plain-English report of what has been decided, what is
|
||||
still open and what happens next, in its own tab with Print and Save buttons.
|
||||
It is the thing you take to a meeting.
|
||||
- **Nothing is sent until you press Send.** Everything before that is local and
|
||||
reversible, so nobody has to worry about committing to something by accident.
|
||||
- **Nothing gets lost.** Close the tab, reload, restart your machine: your
|
||||
half-typed answers are still there. Once you press Send, what you sent is
|
||||
held until Plan2Code actually collects it, so it cannot be written over.
|
||||
- **It tells you when the other half stops listening.** The terminal and this
|
||||
page are two programs that fail separately, and a page that sat there saying
|
||||
"one moment" forever was the worst way to find that out. Now it says so, and
|
||||
says what to do: answering anyway still works, because what you send is held
|
||||
on disk until something comes for it.
|
||||
- **Starters picked for your role.** Tell *User Preferences* what you do
|
||||
(engineer, product lead, architect, designer, QA, engineering manager) and
|
||||
the starter templates on an idea card and the starter questions on the Ask
|
||||
tab put the most useful ones first. It changes the order, never the
|
||||
questions a skill asks (see *Your role* below).
|
||||
- **Light or dark, and a highlight color you pick.** The gear button at the
|
||||
top right opens *User Preferences*: your role first, then these. It follows
|
||||
your system by default; set it to one or the other if
|
||||
you would rather it stayed put. Remembered on your machine, so it carries
|
||||
over to every session.
|
||||
- **A card as wide as you want it.** The same panel has a *Card width*
|
||||
setting — **Narrow** (720px), **Comfortable** (880px, the default) or
|
||||
**Wide** (1080px) — that widens the question card, the Previous / Next pager
|
||||
and the document tabs together. The dashboard keeps its own layout, and on a
|
||||
small window the column simply fits the window. Remembered with the colors,
|
||||
so it follows you into every session.
|
||||
- **Text that uses the card.** A question's text runs the full width of the
|
||||
card rather than stopping in a narrow column, and the answer box you are
|
||||
typing in grows to fill the card's free height: the box of a text question,
|
||||
the *Something else* box once you pick it, or the note under a verdict,
|
||||
yes/no or recap once it shows. Other boxes stay small. Drag the handle to
|
||||
make it taller; it never shrinks below the space it was given, and on a short
|
||||
window the card scrolls instead of squeezing the box under 160px.
|
||||
- **Send tells you it is ready.** While there is something to send, the Send
|
||||
button pulses gently; it goes still when there is nothing to send.
|
||||
- **Each tab remembers where you were.** Scroll halfway down a document,
|
||||
jump to the questions, come back: you are where you left off. The same goes
|
||||
for a long question card. It lasts as long as the tab is open.
|
||||
- **The spec's overview, one click away.** When the session is working on a
|
||||
spec that has an `overview.md`, an **Overview** tab shows it — read-only,
|
||||
and read fresh from disk each time you open the tab, so an edit shows up
|
||||
straight away. No file, no tab. On the dashboard it follows the spec picked
|
||||
at the top, and disappears for *start from scratch*.
|
||||
- **Where you are, at the bottom.** The footer names the folder the session
|
||||
was launched from and its git branch (`plan2code · feature/…`), muted in
|
||||
the middle. Click it to open the Workspace dialog (see *Your workspace*).
|
||||
Outside a git repo it shows only the folder.
|
||||
- **A chime when it's your turn.** The page plays a sound when new questions
|
||||
arrive, when a new tab (a document, the overview) joins the strip, and when
|
||||
the session opens or closes, so you can look away without missing your cue.
|
||||
Starting a skill from the dashboard plays its own sound too. The same panel
|
||||
has a *Play sounds* switch for all of them, and a box per moment (Planny
|
||||
snoring, Planny waking up, starting a skill, session opens, skill is ready,
|
||||
session ends, new questions, a reply on Ask, a new tab), so you can keep only
|
||||
the ones you want. Ticking a box plays its sound; everything is remembered
|
||||
like the colors.
|
||||
- **Files in your notes.** Show instead of describe: attach a screenshot, a
|
||||
photo or a document to any note or quick question (see *Attachments in notes
|
||||
and questions* below).
|
||||
- **A notebook of your own.** One per project folder, in named tabs, for
|
||||
jottings and screenshots that are yours, not the agent's (see *Your notebook*
|
||||
below).
|
||||
- **A nudge when it might be waiting on you.** Your agent may stop in the
|
||||
terminal to ask permission for something, and the page cannot see that. So
|
||||
the dashboard and every starting screen carry a one-line tip about hands-off
|
||||
modes (`auto` mode in Claude Code, `smart` mode in Devin) that can cut down
|
||||
on those stops, though they may still need your attention, and when the agent
|
||||
has been working and silent for about 30 seconds, Planny's line asks
|
||||
*"Still working, or waiting on an approval in your terminal?"* — well before
|
||||
the two-minute *"Still working on it"* line.
|
||||
- **The tab icon says whose turn it is.** A bar along the bottom of Planny's
|
||||
favicon follows the line beside him: dashed amber while Plan2Code is
|
||||
working or picking up your answers, solid green when it is your move, solid
|
||||
red when it has gone quiet or the connection is lost (busy is dashed so the
|
||||
states differ by pattern, not only color). A finished session goes back to
|
||||
the plain icon, so a console left in a background tab can be checked at a
|
||||
glance.
|
||||
- **Help.** The **?** at the top right opens a Help dialog with 18 topics,
|
||||
one per tab down the left (across the top on a narrow window), opening on
|
||||
the one for where you are. It is part of the page itself, so it still reads
|
||||
fully when the page has lost its program.
|
||||
- Works offline, on your own machine only. No account, no install, no network.
|
||||
|
||||
An Implement phase ends on a sign-off card: read the completion report, then
|
||||
review the code first, approve the phase, or ask for changes. Implement +
|
||||
review has already reviewed the code, so its card has no review button.
|
||||
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="../docs/screenshots/signoff-dark.webp">
|
||||
<img src="../docs/screenshots/signoff-light.webp" alt="The Approve this phase card, with a button to read the completion report and three choices: Review the code first, Approve this phase, and I want changes.">
|
||||
</picture>
|
||||
|
||||
The **Ask** tab is a chat beside the cards, for a quick question at any point.
|
||||
When a question is really a new task, the answer ends with a ready-to-paste
|
||||
prompt in a block with a Copy button, to take into a new conversation.
|
||||
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="../docs/screenshots/ask-dark.webp">
|
||||
<img src="../docs/screenshots/ask-light.webp" alt="The Ask tab: the question Where are tasks paged? and Plan2Code's answer naming the file.">
|
||||
</picture>
|
||||
|
||||
## Using it
|
||||
|
||||
The easy way in is the dashboard:
|
||||
|
||||
```
|
||||
/plan2code
|
||||
```
|
||||
|
||||
A page opens with every skill laid out as cards — the setup pair, the pipeline
|
||||
in order, and the utilities alongside — with a note about what it made of your
|
||||
project (no AGENTS.md yet, a spec waiting on Phase 2) and a *Suggested* flag on
|
||||
the card it would pick. **Git** is among the utilities, always available: it opens
|
||||
the git board, three tabs — Changes, Branches and Sync — that open on the
|
||||
likely next step (Help's *The git board* topic walks through it), and asks
|
||||
before every push, publish and delete. In a folder that is not a git
|
||||
repository its card says *Not a git repository yet: it offers to start one*,
|
||||
and clicking it still works. **Codebase X-ray** is always available too: it
|
||||
explains how and why an area works, or ranks its rough spots into
|
||||
`specs/<name>/ARCHITECTURE-BRIEF-<date>.md`, and never changes code.
|
||||
**Diagnose a bug** sits beside it, also always
|
||||
available: it finds a bug's cause and writes it up as
|
||||
`specs/<bug-name>/DIAGNOSIS-<date>.md` without fixing it. Pick such a spec in
|
||||
the picker and it reads *Bug diagnosed*: Quick Task (suggested) and Plan light
|
||||
up, while Document, Implement, Implement + Review and Finalize stay greyed. Once
|
||||
Quick Task has fixed it, the folder reads *Bug fixed*: Quick Task offers to
|
||||
archive it to `specs--completed/`, and until then the picker never opens on it
|
||||
and hides it while *Hide unavailable workflows* is on. Its chip has a visible
|
||||
**Delete** button in place of the hover ✕ other specs carry, and one confirm
|
||||
removes the folder (any other spec also asks you to type its name). Click a card and Planny
|
||||
flies while it gets ready;
|
||||
a few seconds later the same page is that skill's console, already running. No
|
||||
command names to remember.
|
||||
|
||||
Handoffs this checkout has not picked up yet follow the specs in the picker as
|
||||
dashed **Handoff** chips, each with its title and age. Select one and the skill
|
||||
cards give way to a preview: when it was written, its spec, the skill it came
|
||||
from and its Next task. **Pick it up here** carries on in that skill and spec
|
||||
in this same session (Quick Task takes over, and says so, when the skill or
|
||||
spec is gone), and the chip is gone from the next dashboard. **Read it all**
|
||||
opens the whole document, **Copy for a new conversation** copies a one-line
|
||||
prompt that points a fresh conversation at the file, and **Delete** removes it
|
||||
for good after one confirm. Handoffs from *Stop with a handoff* (below) and
|
||||
from the Handoff skill land in the same place, `~/.plan2code/handoffs/`.
|
||||
|
||||
A freshly opened dashboard starts with Planny asleep in the middle of the page.
|
||||
Click to wake him: he snores once while he gets a gentle shake side to side,
|
||||
then about five seconds of him powering on to a boot-up sound (arms lifting
|
||||
off his sides, his star opening, a hop and a cheer) before he glides into his spot at
|
||||
the top and the menu rises in. (Browsers stay silent until your first click,
|
||||
so the snoring usually starts with it; with *Sounds* off, the same wake-up
|
||||
plays without audio.)
|
||||
It plays only on a fresh `/plan2code`: not on a reload, not when you come
|
||||
back with **Back to the dashboard**, and not after a launch. To skip it — from
|
||||
the asleep screen or mid-animation — press the muted **Skip** button at the
|
||||
bottom right or hit Escape; either goes straight to the dashboard, silent.
|
||||
With reduced motion switched on in your system settings you get the awake
|
||||
dashboard at once.
|
||||
|
||||
Or start any step directly by its command (the full list is in the README's
|
||||
[Prefer the terminal?](../README.md#prefer-the-terminal) section).
|
||||
|
||||
The first thing it asks is how you would like to work:
|
||||
|
||||
> **How would you like to work through this?**
|
||||
>
|
||||
> - **In your browser** (suggested)
|
||||
> - **Here in the terminal**
|
||||
|
||||
Pick the browser and a page opens at a `127.0.0.1` address, straight away:
|
||||
opening the page is the first thing the skill does, before it reads your
|
||||
project, so for the first few seconds you see a starting screen naming the step
|
||||
("Starting Pathfinder") while it gets its bearings — for the core steps, with
|
||||
Planny acting that step out. The questions replace it the
|
||||
moment they are ready. Answer what is there, press **Send to Plan2Code**, and
|
||||
it carries on. You can switch back to the
|
||||
terminal at any point by saying so: the files under `specs/` are the same either
|
||||
way, and neither side owns them.
|
||||
|
||||
While the page is open, the agent's messages in the terminal end with a
|
||||
pointer back to it — `→ Look at the web console: http://127.0.0.1:…` — and
|
||||
while it is waiting on you it says so in those words: *Waiting on your answer
|
||||
in the web console*. Glance at the terminal, and it always tells you where to
|
||||
look.
|
||||
|
||||
Know you want the page already? Pass `--web` with the command —
|
||||
`/plan2code-1-plan --web plan a lunch voting app` — and it opens the console
|
||||
without asking. The flag is dropped before the rest of the argument is read, so
|
||||
it never becomes part of the request.
|
||||
|
||||
Sharing the link with a colleague on another machine will not work, and that is
|
||||
deliberate. It is bound to your own machine only. To work through a session
|
||||
together, share your screen.
|
||||
|
||||
For the same reason, the web console is only offered when the agent is running
|
||||
on your own machine. An agent working in a cloud VM, a container or over SSH
|
||||
stays in the terminal: a `127.0.0.1` link from somewhere else is a link you
|
||||
cannot open.
|
||||
|
||||
### Your role
|
||||
|
||||
The first control in *User Preferences* (the gear button) is **Role**:
|
||||
Engineer, Product lead / PM, Architect / tech lead, Designer (UX), QA / test
|
||||
engineer, Engineering manager, or **Not set / none of these**, the default.
|
||||
It only reorders things: the starter templates on an idea card and the starter
|
||||
questions on the Ask tab. It never changes what a skill asks or does. It is
|
||||
kept in `looks.json` with your colors, so it follows you into every session,
|
||||
and **Back to default** sets it back to *Not set*.
|
||||
|
||||
Until you have chosen, the dashboard shows a one-line banner at the top —
|
||||
*Pick your role to get starter templates ordered for you.* — with **Set up
|
||||
preferences** and **Not now**. Choosing any role, *Not set* included, or
|
||||
pressing *Not now* puts it away for good.
|
||||
|
||||
### Starter templates
|
||||
|
||||
The first "What's the idea?" box in Pathfinder, Plan and Quick Task has a row
|
||||
of starter templates above it: **Blank** first, then outlines to fill in (an
|
||||
engineering spec, product requirements, a design decision, a bug
|
||||
investigation, a refactor, a data migration, and so on), in the order your
|
||||
role puts them. With a role chosen, the first one carries a *For your role*
|
||||
pill. Pick one and the box fills with editable Markdown, one `## heading` per
|
||||
answer with the answer on the lines under it, and the first `[blank]` is
|
||||
selected so you can type straight over it. Brackets mark only the parts you
|
||||
fill in; everything else is a default you can keep or edit. If you have
|
||||
already typed something, a strip asks **Replace** or **Keep mine** first.
|
||||
Only what is in the box is sent, exactly as if you had typed it.
|
||||
|
||||
The templates live in the page (`public/starters.js`), not in the prompts. A
|
||||
skill only marks its fresh-idea card with `"templates": "idea"`, and `post`
|
||||
refuses that flag on anything but a `text` card. A resumed map or plan asks
|
||||
no idea question, so it shows no templates, and the terminal never has them.
|
||||
|
||||
### Leave for later (Pathfinder)
|
||||
|
||||
Pathfinder's scope question is **Leave for later** — *"Which of these features
|
||||
are we leaving out this time?"* It is a tick-any list of 3–5 features someone
|
||||
might expect, each ending with what leaving it out means ("Scheduled exports
|
||||
(Leaving this out = someone runs each export by hand)"), with a recommended
|
||||
set to tick in one go. The features you tick become the first lines of the
|
||||
map's *Out of scope*. Every option names a feature, never a rule to keep, so a
|
||||
tick always means "not this time".
|
||||
|
||||
### Skipping a question
|
||||
|
||||
**Skip this one**, on an optional question, now moves you straight on: the card
|
||||
reads *Skipped* for a beat (about a quarter of a second) and the next open
|
||||
question comes up. On the last one, focus goes to **Send to Plan2Code**
|
||||
instead. A click or a key press in that beat cancels the move. **Do not skip**
|
||||
on a skipped card brings it back.
|
||||
|
||||
### Your workspace
|
||||
|
||||
The folder label in the middle of the footer — `shop · main`, or
|
||||
`shop + 2 folders · main` once you have added some (shorter on a narrow
|
||||
window) — opens the **Workspace** dialog: the folders the agent uses as
|
||||
context for this console session.
|
||||
|
||||
- **The folder you started in** is always first. It can be renamed and given a
|
||||
description, but not removed.
|
||||
- **Add a folder** by pasting a path (`../shared-ui` counts from the folder
|
||||
you started in; `~` is your home folder) or with **Browse…**, which opens
|
||||
your system's own folder picker. Browse… is hidden when the page looks like
|
||||
it is being reached from another machine (SSH, a dev container, a
|
||||
Codespace). A path that is not a folder, one already in the list, and a name
|
||||
already taken are each refused with a message (a taken name comes with a
|
||||
**Use @name-2** button); a folder inside another one in the list is
|
||||
accepted, with a note.
|
||||
- **Every folder has an `@name`** (lowercase letters, numbers and hyphens) and
|
||||
an optional one-line *What is it?*. Type `@` in the Ask box, a note or a
|
||||
typed answer and a list of names pops up; the agent reads `@shared-ui` as
|
||||
that folder.
|
||||
- **What the agent does with them.** It is told the list when its session
|
||||
opens and each change once after that. Added folders are read-only
|
||||
reference: it reads them, reads each one's `AGENTS.md` (or `CLAUDE.md`)
|
||||
before first using it, and changes one only if you ask. Your harness may
|
||||
ask permission the first time it reads outside the project.
|
||||
- **Marks.** *This folder no longer exists* when it is gone from disk; *The
|
||||
agent can't read this yet* when the agent reported a failed read (in Claude
|
||||
Code with a copyable `/add-dir <path>` to run); *Inside another folder in
|
||||
the list* for a nested one.
|
||||
|
||||
The workspace carries across skills you start from the dashboard and back, and
|
||||
it is remembered for next time:
|
||||
|
||||
- **Saved on every change**, in `~/.plan2code/console/workspaces.json` (beside
|
||||
`looks.json`, never in the project, since the paths are your machine's),
|
||||
keyed by the folder you started in.
|
||||
- **One list per spec.** *Start from scratch* on the dashboard shows the
|
||||
project's list. Picking a spec loads its own; the first time, it starts as a
|
||||
copy of the project's, and after that the two are separate. A spec created
|
||||
mid-run (Pathfinder, Plan) takes the list in force with it. The line under
|
||||
the dialog's title says whose list it is.
|
||||
- **Forgotten on archive.** Finalize's Spec Cleanup step says it will forget
|
||||
the spec's list and runs `console.mjs forget --spec specs/<name>` after the
|
||||
move.
|
||||
|
||||
### Subagents
|
||||
|
||||
On a build (Implement, Implement + review, Quick task), a review and
|
||||
Pathfinder, the agent can hand independent pieces of work to helpers
|
||||
(subagents) while it keeps the conversation with you.
|
||||
|
||||
- **The button.** An icon in the top bar, after Stop session (and Write a
|
||||
brief on Pathfinder): one larger node linked to three smaller ones, lit in
|
||||
your highlight color while helpers are on. It shows only on those skills,
|
||||
and only when the skill's copy of the console can pass the setting on.
|
||||
- **The dialog.** A click opens it; the button never switches anything by
|
||||
itself. **Use helpers** or **Work alone**, the instruction the agent follows
|
||||
(**Reset to default** puts the shipped one back), and how many helpers may
|
||||
run at once (1 to 20; your agent's own limit still applies). **Save** sends
|
||||
it; the agent hears of it at its next check-in, as a setting, not as
|
||||
something you typed.
|
||||
- **Saved per project and per skill**, on until switched off, in
|
||||
`~/.plan2code/console/subagents.json`. The next session of the same skill
|
||||
in the same folder starts the same way.
|
||||
- **The Subagents tab.** With the first helper the agent reports, a tab
|
||||
appears before Ask: one row per helper with what it was asked and whether it
|
||||
is running, done or failed, plus a one-line result at the end. Rows change at
|
||||
the agent's check-ins, not live. *Working alone* means your agent has no way
|
||||
to start helpers here. The tab clears when you go back to the dashboard.
|
||||
- **Pathfinder's research** always uses helpers, whatever the switch says, and
|
||||
they show in the tab too.
|
||||
|
||||
### Your notebook
|
||||
|
||||
The **Notebook** icon in the top bar, on the dashboard, every skill and the
|
||||
finished screen, opens a large dialog with a scratch pad for the folder you are
|
||||
working in.
|
||||
|
||||
- **Tabs.** A row of named tabs sits across the top, each with its own text and
|
||||
its own pictures. **+ New tab** asks for a name first (1 to 40 characters, no
|
||||
two the same in any case, up to 20 tabs), in a small dialog. There is no
|
||||
toolbar under the row: a double-click (or **F2**) on a tab renames it, the **x**
|
||||
beside its name deletes it (the **Delete** key does too), and tabs are moved
|
||||
only by dragging them. The tab you left open is the one you come back to.
|
||||
Delete opens a dialog that asks twice and takes the tab's text and pictures
|
||||
with it; with no tab left, the dialog asks you to make one. A notebook from before tabs opens
|
||||
as one tab called **Notes**.
|
||||
- **Markdown, styled as you type.** The editor shows Markdown in place:
|
||||
headings grow, bullets draw, bold, code, quotes and links take their look, and
|
||||
the marks come back on the line you are on. The text itself stays plain
|
||||
Markdown (saved as the tab's `note.md`, up to 1 MB).
|
||||
- **Pictures beside it.** Paste a screenshot, drop files on the dialog or press
|
||||
**Add image**: each becomes a thumbnail in a strip under the text (up to 200
|
||||
per tab). Click one for a full-screen preview (arrow keys step through, Esc
|
||||
closes); its **X** asks before it deletes.
|
||||
- **It saves itself**, about a second after you stop typing, when you close the
|
||||
dialog and before you switch tabs. If a tab's text cannot be saved, switching
|
||||
is refused ("Not saved yet, so staying on this tab") rather than losing it.
|
||||
If the connection drops, your text stays in the page and is retried, and the
|
||||
browser tab warns before you close it with something unsaved.
|
||||
- **One per folder, kept between sessions.** Every session started in the same
|
||||
folder (each git worktree counts as its own) opens the same notebook, in
|
||||
`~/.plan2code/notepads/<folder-name>-<12 hex>/`: `meta.json` (which folder it
|
||||
belongs to), `tabs.json` (the tabs, their order and the last one open) and one
|
||||
folder per tab, `tabs/<id>/`, holding its `note.md` and `images/`. Two pages
|
||||
open on one folder share it, and the last save wins.
|
||||
- **Private.** It never goes into your project, your session or anything the
|
||||
agent reads, so the agent never sees it. It stays on this machine.
|
||||
- **Removed only when you say.** No automatic cleanup touches it. Once the
|
||||
newest file in a notebook is 30 days old or more, *User Preferences →
|
||||
Cleanup* offers it as one item named after its folder's full path
|
||||
(*Notebook for /home/sam/code/shop*),
|
||||
and deleting it removes the whole notebook, every tab's text and pictures.
|
||||
|
||||
### Session meter
|
||||
|
||||
A small ring pill in the top bar — **Session: fresh** (green), **Session:
|
||||
getting long** (yellow), **Session: time for a fresh start** (red) — counts the
|
||||
work this console session has done. Click it for the count, a list of each
|
||||
step that added points and what it added (for example *Quick task started +1*),
|
||||
and a **What is this?** link to Help.
|
||||
|
||||
Each skill run adds points (`WEIGHTS` in `public/meter.js`): Plan, Document,
|
||||
Review, Init and Init update 2; Revise plan, Quick task and Finalize 1; a
|
||||
Pathfinder map 2 and each question its research subagents settle 1; a built phase by its size,
|
||||
one point per 3 tasks it completed (rounded up), plus 1 for Implement + Review
|
||||
(a flat 2, or 3, if the agent did not report a task count); Handoff and the dashboard 0.
|
||||
A build counts while it runs: each task the progress bar ticks off adds to the
|
||||
build's row (*Implement + Review: 9 tasks built so far*), Implement + Review's
|
||||
review stage adds its 1 as it starts, and the approved phase takes the row over
|
||||
with its final score, so the meter never waits for the sign-off to catch up.
|
||||
On top of that, every 2 questions you answer on the page add 1 point to the
|
||||
skill run you answered them in (`ANSWERS_PER_POINT`), so a long Pathfinder or a
|
||||
Plan with many clarifying questions weighs more than a short one. A review run on the
|
||||
page after a quick task or a phase sign-off counts as a Review too. Green is
|
||||
under 5, yellow from 5, red from 10, and the ring is full at 15. At red the dashboard
|
||||
also shows a banner: starting a **new console session** keeps the agent sharp
|
||||
(resuming this one carries the count along). It is a rule of thumb, not a
|
||||
reading of the agent's real context, and it never blocks anything.
|
||||
|
||||
### While something is being built
|
||||
|
||||
Implementation, Implement + Review and a Quick Task spend most of their time
|
||||
building rather than asking, so the page shows the build instead:
|
||||
|
||||
- **What it is doing right now**, beside Planny ("Task 5 of 9: the rate
|
||||
limiter"), and the progress bar counting tasks done. Tasks are counted
|
||||
within the phase, to match the bar — the phase is already named in the
|
||||
headline — so you never see "Task 4.2 of 6"; the page rewrites that form if
|
||||
an agent still sends it.
|
||||
- **The phase's task list** in its own tab, ticking as each task lands on
|
||||
disk, and **the phase file itself** (`phase-3.md`) rendered in the next —
|
||||
the prerequisites and task specs, not just the checklist.
|
||||
- **Any question the build needs answered** (which phase, a spec conflict,
|
||||
failing tests) appears as an ordinary question, and the sign-off is a
|
||||
**Completion report** tab with an *Approve this phase* card.
|
||||
- A long task is not mistaken for a stall. The build says how long it may go
|
||||
quiet, and the page only calls it stuck after that.
|
||||
|
||||
### Review before you approve
|
||||
|
||||
The *Approve this phase* card carries a **Review the code first** button beside
|
||||
the approval. Press it and the same session runs a focused code review of
|
||||
exactly the files the phase changed, before you are asked to approve anything.
|
||||
The findings come back as a tab, and a *Which to fix* card lists every one with
|
||||
its severity: tick the ones to fix (or use the *Critical and warnings* / *All
|
||||
of them* quick picks), press Send, and it fixes and re-checks them before the
|
||||
approval card comes back.
|
||||
|
||||
A quick task has no approval step, so its offer sits on the finished screen
|
||||
instead: a large **Review it now** button above the next step, with **No
|
||||
thanks, I am done** beside it. If the session has already closed, the button
|
||||
turns into the `/plan2code-review` command to run in the terminal.
|
||||
|
||||
Implement + Review shows neither: it reviews every phase before sign-off
|
||||
already.
|
||||
|
||||
### When a session ends
|
||||
|
||||
A finished session says so, and ends in one of three shapes:
|
||||
|
||||
- **A next step.** What happened, and the exact command to run next (with a
|
||||
Copy button) — the next phase, Finalize, a commit.
|
||||
- **All done.** Nothing is left to run, so there is no command to copy:
|
||||
*"All done, nothing left to run."* Init, Init update and Handoff end this
|
||||
way, and so do Review and Finalize when nothing landed that needs committing.
|
||||
- **Paused.** You pressed *Stop session*. The card names what was saved and
|
||||
gives the command that picks it up later. Nothing else is offered.
|
||||
|
||||
*Stop session* offers two ways to stop (on the dashboard, where nothing has
|
||||
started, it is a plain Stop). **Stop with a handoff**, the suggested one,
|
||||
saves your place as usual and also has the agent write a handoff: where the
|
||||
work stands and the next task, kept in `~/.plan2code/handoffs/` rather than in
|
||||
your project. The paused card names the file, and the dashboard offers it as a
|
||||
chip until it is picked up. **Just stop and save** saves your place and gives
|
||||
the resume command, nothing more; where the step has nothing saved yet it reads
|
||||
*Stop anyway*, under a warning about what is lost.
|
||||
|
||||
When the next step is another Plan2Code skill, the screen also has a
|
||||
**Continue here** button beside it: one press starts that skill in the same
|
||||
conversation, as a dashboard card would. It disappears once the session meter is
|
||||
red, when a fresh conversation is the better choice. A finished Quick Task or
|
||||
Finalize that ends on a commit can also offer **Update CHANGELOG first**, beside
|
||||
**Commit it now**: it opens Changelog right there, and Changelog's yes to
|
||||
*Commit this now?* carries on to Git.
|
||||
|
||||
The first two also carry a **Back to the dashboard** button (beside the next
|
||||
step, or as the main button under "All done"). Press it and the same page turns
|
||||
back into the skill menu, in the same conversation, so the next skill starts
|
||||
right there. The agent keeps listening for it for about ten minutes after the
|
||||
session ends; after that, or once the session has closed, the button turns into
|
||||
the `/plan2code` command instead. That command is on both of these screens
|
||||
anyway, for starting the dashboard in a fresh conversation — the better choice
|
||||
after a long skill, since a fresh conversation starts with a clean context.
|
||||
|
||||
You don't have to finish first. On every skill but the dashboard itself, a
|
||||
small **triangle** pointing left, in your highlight color, sits beside *Stop
|
||||
session*. Press it, confirm, and the agent saves your place exactly as a stop
|
||||
would, with any answers you have ready going along. Then the page turns into
|
||||
the dashboard instead of showing a finish card. Pick the same skill again to
|
||||
carry on, or pick another one. Like Stop, it only works on your turn, and where
|
||||
nothing is saved yet (early in a plan) the confirm says what would be lost.
|
||||
|
||||
### Attachments in notes and questions
|
||||
|
||||
Any note, any quick question on the Ask tab, and the fresh-idea box on
|
||||
Pathfinder, Plan and Quick Task can carry files (on a card they travel with your
|
||||
answer as a note attachment), three ways:
|
||||
|
||||
- the **+ Attach file** button beside the box (pick one or more files),
|
||||
- **paste** a screenshot or a copied file straight into the box,
|
||||
- **drag and drop** files onto the notes panel or the Ask composer.
|
||||
|
||||
Two kinds are allowed:
|
||||
|
||||
- **Images.** Each is shrunk and re-encoded in your browser (JPEG, 2000 px on
|
||||
the long edge at most, phone-photo rotation kept) and shows as a thumbnail.
|
||||
- **Documents**: text, code and PDF (`.md`, `.txt`, `.json`, `.yaml`, `.csv`,
|
||||
`.log`, `.js`, `.ts`, `.py`, `.sql`, `.pdf` and the like), up to 10 MB each.
|
||||
They upload exactly as they are and show as a chip with the file type, name
|
||||
and size. The server checks the contents match the type (a PDF header, or
|
||||
UTF-8 text with no NUL bytes), and a document is never opened from the page.
|
||||
|
||||
Up to 5 attachments per note and 5 per question, images and documents counted
|
||||
together. Anything else (`.docx`, a file over 10 MB, a dotfile such as `.env`)
|
||||
picked or dropped is refused with a message naming the file; a paste only
|
||||
picks up the files it can attach, and leaves any text to paste as usual. Each
|
||||
file uploads straight away while you carry on typing, and sits in a tray with a
|
||||
remove button; removing one deletes its file. A failed upload offers retry or
|
||||
remove and holds back only that note, so the rest of your answers still send.
|
||||
|
||||
The files are stored with the session, in
|
||||
`~/.plan2code/console/sessions/<id>/uploads/`, never in your project, under a
|
||||
random name the server picks. When you send, each note is followed by one line
|
||||
per attachment:
|
||||
|
||||
```
|
||||
Note on Header row: Please keep the header row.
|
||||
Image: /home/sam/.plan2code/console/sessions/<id>/uploads/<uuid>.jpg (header.png)
|
||||
File: /home/sam/.plan2code/console/sessions/<id>/uploads/<uuid>.pdf (api-spec.pdf)
|
||||
```
|
||||
|
||||
and the agent opens those paths with its own file reader. Uploads from sessions
|
||||
untouched for 30 days are swept away the next time a session opens.
|
||||
|
||||
**Keeping the ones a spec cites.** When the agent is about to write a file
|
||||
under `specs/<idea>/` that links to one of your note attachments (a plan, the
|
||||
overview, a phase file, a Pathfinder question or the map), it first copies the
|
||||
attachment into `specs/<idea>/attachments/` with `console.mjs keep` and links
|
||||
the copy, so the spec still shows it after the session is swept. The copy is
|
||||
named `<slug of your file name>-<8 characters of the upload id>.<ext>`, so
|
||||
keeping the same upload twice reuses it. Attachments nothing cites stay in the
|
||||
session, and quick-question attachments are never kept. `keep` is run by the
|
||||
agent, in its own shell; the server itself still never writes into your
|
||||
project.
|
||||
|
||||
### Ask a quick question
|
||||
|
||||
The **Ask** tab, always the last tab, on the dashboard and in every skill,
|
||||
opens a **Quick question** chat. Ask anything about the project's files, or
|
||||
anything at all, without waiting for a card. The agent running the skill
|
||||
answers at its next check-in (in a build, after the task it is on), and the
|
||||
workflow carries on meanwhile. Asking never holds up a card send, and a card
|
||||
send never holds up a question.
|
||||
|
||||
- **Context only when you add it.** A question starts with no context, so it
|
||||
reads as a general question. **+ Add context**, beside *+ Attach file*,
|
||||
lists the last 3 places you visited (question cards, document sections, a
|
||||
spec picked on the dashboard) plus *This spec*; pick one and an *About: …*
|
||||
chip sits above the box. × removes it, and it clears after the question is
|
||||
sent.
|
||||
- **Starter questions.** An empty conversation offers a few questions to start
|
||||
from, chosen for the skill you are in and ordered by your role; the ones
|
||||
that need context appear once you have added some. Clicking one fills the
|
||||
box without sending it.
|
||||
- **Pictures.** The same as notes: the button, paste, or drag and drop, up to 5
|
||||
per question.
|
||||
- **Ten questions per conversation.** The `N of 10` counter is always in view.
|
||||
After the tenth is answered, **New conversation** starts a clean one. So does
|
||||
switching skills through the dashboard.
|
||||
- **Edits need your approval.** Ask for a change to a file and the agent
|
||||
replies with a summary and the list of files it would touch, with
|
||||
**Approve** and **Decline**. Nothing changes until you approve. Afterwards
|
||||
it lists what changed, with line counts, and nothing is committed unless you
|
||||
spell out a commit in your message. It never edits the running skill's own
|
||||
files under `specs/`, and a chat message never answers a card or moves the workflow on: that is what the cards are for.
|
||||
- **When you cannot send.** Two different lines explain it: "That's 10
|
||||
questions in this conversation" means start a new one, and "No agent is
|
||||
connected right now" means the session has finished or the agent has gone
|
||||
quiet, so resume it to ask. Either way the conversation above stays
|
||||
readable.
|
||||
|
||||
A reply that lands while you are on another tab puts a dot on **Ask** and
|
||||
chimes once (if sounds are on).
|
||||
|
||||
### When an update is out
|
||||
|
||||
When a newer Plan2Code release is out, the dashboard shows an **UPDATE
|
||||
AVAILABLE** banner at the top. Click it for the details: the version you
|
||||
have, the new one (linked to its Releases page) and the command that updates
|
||||
you, `plan2code update`, with a Copy button. It updates everything that was
|
||||
installed (the skills, the `plan2code` command and any extras you added), with
|
||||
no menu, and never uninstalls anything. If the `plan2code` command is not
|
||||
installed, the dialog also shows the install command,
|
||||
`npx --allow-git=all git+https://github.com/jparkerweb/plan2code.git`, to run
|
||||
instead. **×** hides the banner for this session; the next dashboard shows it
|
||||
again until you update.
|
||||
|
||||
The `plan2code` command tells you too: before it starts your agent it prints
|
||||
one line, `Plan2Code v<latest> is out (you have v<installed>). Run: plan2code update`.
|
||||
It reads the same saved check, so it never waits on the network; when that
|
||||
check is missing or old, it refreshes it in the background for next time.
|
||||
|
||||
The check uses your own git login to read the repo's release tags, once an
|
||||
hour at most. If git cannot reach the repo (no git, no access, offline), you
|
||||
simply see no banner, and nothing waits on it. The version in Help always
|
||||
links to the Releases page.
|
||||
|
||||
### Keyboard
|
||||
|
||||
| Key | Does |
|
||||
| --- | --- |
|
||||
| `Ctrl` + `Enter` (`⌘` + `Enter` on a Mac) | Send |
|
||||
| `Tab` / `Space` | Move between options and pick one |
|
||||
| In the Ask box: `Enter` / `Ctrl` + `Enter` (`⌘` + `Enter`) | `Enter` is a new line; `Ctrl` + `Enter` sends the quick question, never the cards |
|
||||
| `Esc` | Closes whichever dialog is open; on the dashboard, backs out of a pick |
|
||||
| In Help: arrow keys, `Home`, `End` | Move between topics (the arrows wrap). `Ctrl` + `Enter` does nothing inside Help |
|
||||
|
||||
Every control is a real button, radio or checkbox, so screen readers and
|
||||
keyboard-only navigation work.
|
||||
|
||||
## Models in User Preferences
|
||||
|
||||
The `plan2code` launcher's model menu comes from `models.json`, which every install overwrites with the authors' curated list. **User Preferences → Models** (Claude, Devin and Codex tabs) lets you add a model that came out before Plan2Code was updated; additions are kept in `~/.plan2code/models.json`, and **Reset to default** removes them. Restart `plan2code` to see a change. You can always run `plan2code --model <id>`, or switch model inside your agent before running a skill. Devin ids ending `-xhigh` or `-max` are refused. Maintainers refresh the curated list with the repo-local `/plan2code-model-update` skill, which shows a diff and changes only what they approve.
|
||||
|
||||
---
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
| What happened | What to do |
|
||||
| --- | --- |
|
||||
| You closed the tab | Open the link again. Everything is where you left it. After about two minutes with no tab open the link stops working: ask the agent to resume the session for a new one. |
|
||||
| The link stopped working | Tell the agent. It restarts the session and gives you a new link. |
|
||||
| Your agent session died while you were mid-answer | Press Send anyway. Your answers are written to disk and are never discarded, including when the session is restarted. The next session picks them up. |
|
||||
| The page says Plan2Code is not running | It has not checked in for a few minutes. Look at the terminal: it may have finished its turn, hit an error, or be waiting on you there. If it is idle, type `continue` in the terminal and it picks your answers up. Answering here still works, and what you send is held for it. |
|
||||
| You are not sure anything is connected | The **?** at the top right opens Help. Its *What this page is* tab says what keeps the page alive and whether both halves are talking at that moment, and *When something looks stuck* covers what to check. |
|
||||
| You would rather use the terminal after all | Say so. Nothing is lost. |
|
||||
|
||||
---
|
||||
|
||||
## How it works
|
||||
|
||||
Nothing is installed. The skills ship a small zero-dependency Node server
|
||||
(`references/web-console/`), and the workflow step starts it when you say yes.
|
||||
|
||||
```
|
||||
agent server (detached) your browser
|
||||
| | |
|
||||
|-- open (binds the port, starts ->| |
|
||||
| the server AND the browser) ---|---------------------------->|
|
||||
|<-- http://127.0.0.1:PORT/s/TOK/ |<---- the page, first state -|
|
||||
| | already inside it |
|
||||
|-- post the first questions ----->|---- pushed to the page ---->|
|
||||
|-- wait --seconds 240 ----------->| |
|
||||
| (returns every 4 minutes with | |
|
||||
| progress, then waits again) |<---- you press Send --------|
|
||||
|<-- your answers -----------------| |
|
||||
```
|
||||
|
||||
The server runs detached rather than as a background task of the agent, because
|
||||
agent background tasks get killed at various timeouts, and that would take your
|
||||
half-finished answers with them.
|
||||
|
||||
**It is built to show you something fast.** A browser takes most of a second to
|
||||
turn up after it is asked, so `open` binds the page's port itself and sends the
|
||||
browser there before the server has even finished starting; the server takes
|
||||
the port over a moment later, and the browser's request waits for it rather
|
||||
than being refused. The page arrives with the session already inside it, so it
|
||||
draws the real screen without asking for anything first, in your own theme and
|
||||
colors from the first frame. On a Windows laptop the page is in front of you in
|
||||
roughly the time the browser itself takes to open.
|
||||
|
||||
**It stays up while the page is open.** The page pings it every few seconds, so
|
||||
the idle clock never runs down while you are there. Close the tab and it shuts
|
||||
itself down about two minutes later; it stops after four hours regardless, and
|
||||
the agent stops it outright when the session ends.
|
||||
|
||||
That also means **the server routinely outlives the agent**. It is the agent, not
|
||||
the server, that reads your answers, and the two fail separately. The page tells
|
||||
the two apart: the **?** button at the top right opens Help, whose *What this
|
||||
page is* tab says which halves are talking right now (and *When something
|
||||
looks stuck* covers what to check), and Planny stops looking busy once
|
||||
nothing is listening rather than spinning at you indefinitely.
|
||||
|
||||
**State lives in three places**, and none of them is your repository (the one
|
||||
exception being the note attachments the agent keeps for a spec, above):
|
||||
|
||||
| Where | What | Survives |
|
||||
| --- | --- | --- |
|
||||
| `~/.plan2code/console/sessions/<id>/` | the questions, your draft, your answers | 30 days after the session was last touched |
|
||||
| `~/.plan2code/console/sessions/<id>/workspace.json`, `ledger.ndjson`, `workspace-cursor.json` | the workspace's folders (paths, names, descriptions — never their contents), the session meter's events, and how far the agent has been told of workspace changes. Kept beside the session, so they outlive every dashboard hop | with the session |
|
||||
| `~/.plan2code/console/sessions/<id>/uploads/` | images and documents attached to notes and quick questions | 30 days after the session was last touched |
|
||||
| `~/.plan2code/handoffs/<id>.md`, `<id>.json` | each handoff's document, and which checkout, spec and skill it belongs to and whether it was picked up (`handoffs.mjs` is their one owner) | 30 days after it was last touched, picked up or not |
|
||||
| `~/.plan2code/notepads/<folder-name>-<12 hex>/` | your notebook for one folder: `meta.json`, `tabs.json` and, per tab, `tabs/<id>/note.md` and `tabs/<id>/images/` (`notepads.mjs` is their one owner; the agent never reads them) | until you delete it through Cleanup, which offers it once its newest file is 30 days old |
|
||||
| `~/.plan2code/console/looks.json` | your role, theme, colors, sounds and card width | always |
|
||||
| `~/.plan2code/console/subagents.json` | your Subagents switch, instruction and limit, per project folder and skill | always |
|
||||
| `~/.plan2code/console/sessions/<id>/subagents-setting.json`, `subagents-cursor.json` | this session's copy of the switch, and how far the agent has been told of it | with the session |
|
||||
| your system temp directory | the port, process id and session token | until reboot |
|
||||
|
||||
Each of the workspace and meter files has exactly one writer: the server owns
|
||||
`workspace.json` (the page changes it only through the `/workspace` routes
|
||||
under Security), and `console.mjs` owns `ledger.ndjson` and
|
||||
`workspace-cursor.json`. The meter's count is never stored; it is folded from
|
||||
the ledger every time (`public/meter.js`), so a repeated `post` never counts
|
||||
twice. The logic lives in small pure modules the tests import directly —
|
||||
`public/workspace.js` (names, the footer label, the change lines the agent
|
||||
reads), `public/meter.js` and `public/mentions.js` (the `@name` popover) — and
|
||||
**Browse…** runs the per-OS picker in `picker.mjs`, copied from the
|
||||
`plan2code` launcher and kept in step with it by a test.
|
||||
|
||||
**Old sessions clean themselves up.** Each time a session opens, whole session
|
||||
folders nobody has touched for 30 days are deleted — questions, drafts,
|
||||
answers, uploads and all, paused or not — along with stray scratch files
|
||||
(`.json` / `.mjs`) left at the top of `~/.plan2code/console/` for as long, and
|
||||
handoffs in `~/.plan2code/handoffs/` untouched for as long, both files each.
|
||||
Your `looks.json` and the `console-dir` pointer are never touched, and neither
|
||||
is the session being opened. Nothing of value goes with them: the page is
|
||||
never the record, `specs/` in your project is.
|
||||
|
||||
**Or clean up on demand.** *User Preferences → Cleanup* → **Find files to
|
||||
clean up** lists, with sizes, everything in `~/.plan2code/` that is not
|
||||
needed: sessions untouched for 30 days (never the one you are in), anything at
|
||||
the top of `~/.plan2code/console/` other than `sessions/`, `looks.json`,
|
||||
`workspaces.json`, `subagents.json`, `console-dir` and `update-check.json`, and anything at the top of `~/.plan2code/` other than
|
||||
`console/`, `bin/`, `launcher.json`, `install.json` (what you installed, which
|
||||
`plan2code update` reads), `models.json`, `handoffs/` (old handoffs go by
|
||||
age, above) and `notepads/`. Each notebook whose newest file is 30 days old or
|
||||
more is listed as one item, *Notebook for* its folder, and goes whole; no
|
||||
automatic sweep ever removes one. It also lists each
|
||||
folder in the project's `specs--completed/` whose newest file is more than 30
|
||||
days old: archived specs Finalize moved there. Deleting one is permanent:
|
||||
`specs--completed/` is usually gitignored, so git can't restore it. A stray is listed once
|
||||
it has sat untouched for an hour, so a lock or temp file another session is
|
||||
writing right now is never caught. **Delete these** removes
|
||||
that list and nothing else. A console running from another home
|
||||
(`PLAN2CODE_CONSOLE_HOME`) only ever looks inside that home.
|
||||
|
||||
---
|
||||
|
||||
## Security
|
||||
|
||||
It is a local dev server that reads files in your project (never writing to it)
|
||||
and keeps its own state in your home folder, so it is built to be boring about
|
||||
this:
|
||||
|
||||
- Bound to `127.0.0.1` only, never `0.0.0.0`. Not reachable from your network.
|
||||
- A `Host` header allow-list, which is what stops a website you happen to be
|
||||
visiting from talking to it through a DNS rebinding trick.
|
||||
- A 128-bit token in the link, swapped for an `HttpOnly; SameSite=Strict` cookie
|
||||
on first load so it leaves your address bar, your history and any screenshot.
|
||||
- A strict Content Security Policy with no inline script allowed.
|
||||
- Markdown written by the agent is turned into page elements directly and never
|
||||
into an HTML string, so a document that quotes a hostile README cannot run
|
||||
anything. It shows up as text, which is what it is.
|
||||
- Uploads are named by the server (`<uuid>.jpg`, or `<uuid>.<ext>` with the
|
||||
extension taken from the allow-list, via `crypto.randomUUID()`), never by the
|
||||
file name you sent, and live only under the session's own `uploads/`. The
|
||||
server checks the bytes: a JPEG header for images (4 MB cap), and for
|
||||
documents a `%PDF-` header or strict UTF-8 with no NUL byte (10 MB cap).
|
||||
Documents are served back only under a fixed type (`application/pdf`, or
|
||||
`text/plain` for text and code) with `nosniff` (and `sandbox` on text), so
|
||||
the Sent box can link them. A send may only point at
|
||||
uploads inside that session's `uploads/`, images in `images` and documents
|
||||
in `files`.
|
||||
|
||||
### Routes
|
||||
|
||||
The upload routes, the send, the overview and handoff reads, the workspace and the notebook. Like every page route, they are on `127.0.0.1`
|
||||
behind the session cookie, and the ones that write also check the request's
|
||||
origin.
|
||||
|
||||
| Route | Does |
|
||||
| --- | --- |
|
||||
| `POST /upload` | Raw bytes, original name in `x-p2c-name`. `Content-Type: image/jpeg`: writes `uploads/<uuid>.jpg` and answers `{ ok, id, kind: "image", path, url, name, size }`; not a JPEG → 415, over 4 MB → 413. `Content-Type: application/octet-stream`: a document, its extension from the name's allow-listed extension; writes `uploads/<uuid>.<ext>` and answers `{ ok, id, kind: "file", path, name, size }` with no `url`; not an allowed extension or contents that do not match → 415 `type`, over 10 MB → 413. Any other content type → 415. |
|
||||
| `GET /uploads/<id>.<ext>` | Serves an upload: an image as `image/jpeg` (the thumbnail after a reload), a document as `application/pdf` or `text/plain; charset=utf-8` with `nosniff` and, on text, `Content-Security-Policy: sandbox`. Only `<uuid>.<allowed ext>` names under `uploads/`; anything else is 404. |
|
||||
| `DELETE /uploads/<id>.<ext>` | Deletes an image or document removed before sending. 204, or 404 if it is not there. |
|
||||
| `POST /submit` | The Send. A note may carry `images` and `files`, each `[{ path, name }]`: at most 5 together, images in `images` and documents in `files`, every path inside this session's `uploads/`, otherwise 400. |
|
||||
| `POST /chat` | A Quick question `{ text, about?, images?, files?, conversation }`, or `{ reset: true, conversation }` for New conversation. Appended to the session's `chat.ndjson`. 400 `too-long` (over 4,000 characters), `image`, `file` or `bad`; 409 `offline`, `stale` or `limit` (10 per conversation). Never refused because a card send is still uncollected. |
|
||||
| `POST /chat/decision` | Approve or Decline on an edit the agent proposed: `{ re, decision, text?, conversation }`. Once per proposal; does not count toward the 10. |
|
||||
| `GET /overview?spec=specs/<name>` | The Overview tab's read of `<spec>/overview.md`, as `text/markdown` with `cache-control: no-store`. On the dashboard `spec` must be one of the scanned specs; elsewhere the session's own spec is used. The file's real path must stay inside the project, so `../`, absolute paths and symlinks pointing out all get 404. |
|
||||
| `GET /handoff?id=<id>` | *Read it all*: the handoff's `.md` from `~/.plan2code/handoffs/`, as `text/markdown` with `cache-control: no-store`. A dashboard only, and only an id its own scan listed: a used, unknown or malformed id is 404. |
|
||||
| `GET /workspace` | The Workspace dialog's list: folders, `missing`, `remote` and the agent's folder `issues`. `?check=1` re-checks every folder on disk first. |
|
||||
| `POST /workspace/add` | `{ path, name?, description? }`. The path is resolved against the folder the session started in (`~` expanded) and must be a folder: 400 `not-a-folder`, `duplicate` (with its `name`; compared case-insensitively on Windows and macOS), `bad-name`, or `name-taken` with a `suggest`. Answers the new entry, `nested: true` when it sits inside another folder in the list. |
|
||||
| `POST /workspace/edit` | `{ id, name?, description? }`. Renames or re-describes one folder: 400 `bad-name` / `name-taken`, 404 `unknown`. |
|
||||
| `POST /workspace/remove` | `{ id }`. 400 `original` for the folder the session started in, 404 `unknown`. |
|
||||
| `POST /workspace/browse` | Opens the system folder picker and answers `{ path }` or `{ cancelled: true }`; never adds anything itself. 409 `busy` while one is open, 404 `no-picker` when the session looks remote or no picker exists. |
|
||||
| `GET /notepad[?tab=<id>]` | The notepad for the folder this session runs in: `{ tabs: [{ id, name }], last, tab: { id, text, savedAt, images: [{ id, url, thumb }] } | null }`, with the tab's `text`, `savedAt` and `images` repeated at the top. Without `tab` it answers the last one used; 404 `no-such-tab` for an id it does not have. A notepad in the first shape answers one virtual tab, Notes. Reading never creates or moves a file. |
|
||||
| `POST /notepad/text?tab=<id>` | `{ text }`. Saves that tab's `note.md` and answers `{ ok, savedAt }`; 400 `bad`, 404 `no-such-tab`, 413 `too-long` (over 1 MB). |
|
||||
| `POST /notepad/image?tab=<id>` | Raw `image/jpeg` (the page re-encodes every picture first). Writes the tab's `images/<uuid>.jpg` and answers `{ ok, id, url }`; 415 `not-jpeg`, 413 `too-large` (over 4 MB), 409 `too-many` (200 pictures in the tab). |
|
||||
| `POST /notepad/thumb?id=<uuid>&tab=<id>` | Raw `image/jpeg`: that picture's thumbnail. 404 `not-found` or `no-such-tab`, 415 `not-jpeg`, 413 `too-large`. |
|
||||
| `POST /notepad/image/delete?tab=<id>` | `{ id }`. Deletes a picture and its thumbnail; 404 `not-found` or `no-such-tab`. |
|
||||
| `POST /notepad/tab` | `{ name }`. Makes a tab, which becomes the last one used, and answers `{ ok, id, name }`; 400 `bad-name`, 409 `duplicate-name` (any case) or `too-many-tabs` (20). |
|
||||
| `POST /notepad/tab/rename` | `{ id, name }`. Answers `{ ok, id, name }`; 400 `bad-name`, 404 `no-such-tab`, 409 `duplicate-name`. |
|
||||
| `POST /notepad/tab/delete` | `{ id }`. Removes the tab from the index, then its folder (text and pictures); 404 `no-such-tab`. |
|
||||
| `POST /notepad/tab/order` | `{ order: [id] }`, every current id exactly once; 400 `bad` otherwise. |
|
||||
| `POST /notepad/tab/last` | `{ id }`. Remembers the open tab; 404 `no-such-tab`. |
|
||||
| `GET /notepad/images/<tab>/<uuid>.jpg`, `<uuid>.thumb.jpg` | Serves a picture or its thumbnail as `image/jpeg`, only by a tab id and a UUID name, a regular file (never a link) whose real path stays inside `~/.plan2code/notepads/`; anything else is 404. |
|
||||
| `POST /subagents` | `{ on, instruction, max }` (`instruction: null` for the shipped default). Saves the switch for this project and skill and answers `{ ok, setting }`; 400 `not-offered` on a skill without the switch, `bad`, `too-long` (over 2,000 characters) or `max` (outside 1 to 20). |
|
||||
|
||||
## For maintainers
|
||||
|
||||
| | |
|
||||
| --- | --- |
|
||||
| Source | `src/web-console/` (one row per file in the files table of `.agents-docs/AGENTS-architecture.md`; a test keeps it complete) |
|
||||
| Ships as | `skills/<every skill>/references/web-console/` |
|
||||
| Wiring | one `additionalReferences` entry per skill in `install.js`; the dashboard's menu lives in `public/skills.js` (each entry's `card`; `SKILL_CATALOG` in `public/answers.js` is a lookup on it) |
|
||||
| Agent contract | `src/web-console/console.md` (read once), its topic files (`console-*.md`), `notes/<workflow>.md`, and `building.md` / `building-review.md` for the builds; `console.mjs help <topic>` prints any of them |
|
||||
| Tests | `node --test scripts/test-web-console-*.mjs` (split by area, shared setup in `scripts/web-console-test-helpers.mjs`), also run by `npm test` |
|
||||
| Start-up benchmark | `node scripts/bench-web-console.mjs` (needs a local Chrome or Edge for the paint columns, driven through `playwright-core` from `npm install`; `--browser-delay 900` models a real browser launch, `--roundtrip` times Send→agent and post→page) |
|
||||
| Screenshots | `node scripts/capture-screenshots.mjs` (needs a local Chrome or Edge, driven through `playwright-core` from `npm install`; `PLAN2CODE_TEST_BROWSER=chrome|msedge` forces one) |
|
||||
| Dependencies | none at runtime. `marked` 15.0.7 (MIT) is vendored for its lexer only, and CodeMirror 6 (MIT) for the notebook's editor as one bundled file, `public/vendor/codemirror.esm.js`, made by the dev-only `node scripts/vendor-codemirror.mjs` from a pinned lock (about 500 KB, loaded only when the Notebook is first opened); the page's policy blocks the `<style>` element CodeMirror writes, so the editor lives in a shadow root where it adopts its rules as a constructed stylesheet (steps in the architecture doc's Notebook point) |
|
||||
|
||||
Edit `src/` only. `skills/` is a committed build artifact: regenerate it with
|
||||
`npm run build:skills` and commit it with the source change, since `npm test`
|
||||
(via `--verify-skills`) fails when it drifts from `src/`.
|
||||
|
||||
### Driving it by hand
|
||||
|
||||
You do not need an agent to poke at the console. Point `PLAN2CODE_CONSOLE_HOME`
|
||||
somewhere disposable first, so you never touch a real session:
|
||||
|
||||
```bash
|
||||
export PLAN2CODE_CONSOLE_HOME=/tmp/p2c-play # Windows: $env:PLAN2CODE_CONSOLE_HOME
|
||||
|
||||
cat > /tmp/payload.json <<'JSON'
|
||||
{ "workflow": "pathfinder", "title": "Playing about",
|
||||
"items": [ { "id": "q1", "kind": "choice", "title": "Export format",
|
||||
"body": "Pick one.",
|
||||
"options": [ { "k": "A", "text": "CSV", "recommended": true },
|
||||
{ "k": "B", "text": "Excel" } ],
|
||||
"token": { "A": "a", "B": "b" } } ],
|
||||
"agent": { "status": "waiting" } }
|
||||
JSON
|
||||
|
||||
node src/web-console/console.mjs open --file /tmp/payload.json # prints the URL, opens the browser
|
||||
node src/web-console/console.mjs wait --session <sid> --seconds 60
|
||||
node src/web-console/console.mjs stop --all
|
||||
```
|
||||
|
||||
`node src/web-console/console.mjs help` prints the same command summary an
|
||||
agent gets when it finds the binary before the docs.
|
||||
|
||||
`wait` exits `0` with the answers, `10` if nobody has finished yet, `20` if the
|
||||
server died, `30` on Cancel. Pick `--seconds` to sit under whatever your harness
|
||||
allows a single command: it is a poller, so killing it costs nothing, and a
|
||||
collected result is printed before it is marked collected, which means an
|
||||
interrupted handover can only repeat itself, never lose an answer. `status`
|
||||
lists sessions and flags any whose answers were submitted but never collected.
|
||||
|
||||
When something misbehaves, the session directory is the whole story:
|
||||
`state.json` (what the agent published), `draft.json` (what the person has typed
|
||||
but not sent), `result.json` (what they sent), `events.ndjson` (an append-only
|
||||
log you can `cat`), and `server.log`.
|
||||
|
||||
Set `--idle-ms 60000` on `open` if you want the server to shut itself down
|
||||
quickly while experimenting.
|
||||
|
||||
Two environment variables help when the start is what you are looking at:
|
||||
|
||||
| Variable | Does |
|
||||
| --- | --- |
|
||||
| `PLAN2CODE_CONSOLE_TRACE=1` | `open` prints a timeline of its steps to stderr (roots found, server spawned, port bound, browser sent, state written, server listening). |
|
||||
| `PLAN2CODE_BROWSER` | The command that opens the link instead of the system default, run through the shell with the link appended, e.g. `PLAN2CODE_BROWSER='firefox --new-tab'`. |
|
||||
|
||||
Every `console.mjs open` also writes its own directory to
|
||||
`$PLAN2CODE_CONSOLE_HOME/console-dir` (or `~/.plan2code/console/console-dir`
|
||||
when the override is unset): it is how an agent finds the console on a later
|
||||
session without searching the skill install dirs.
|
||||
|
||||
The vendored file is `src/web-console/public/vendor/marked.esm.js`,
|
||||
sha256 `7a7d9a521ac9384e0c3a075120a7c486cbd0c3c32cc5601bbb79a23e97403690`.
|
||||
Only `marked.lexer()` is used; the rendering is ours, in `public/render.js`, and
|
||||
builds DOM nodes rather than HTML so nothing needs sanitising.
|
||||
|
||||
### Refreshing the screenshots
|
||||
|
||||
The docs and the landing page show the console through the images in
|
||||
`docs/screenshots/`, one light and one dark WebP per screen. Rerun the capture
|
||||
after any change a person would see on the page: a new layout, a renamed
|
||||
button, a different colour.
|
||||
|
||||
```bash
|
||||
node scripts/capture-screenshots.mjs # every screen
|
||||
node scripts/capture-screenshots.mjs --only dashboard # one screen
|
||||
```
|
||||
|
||||
Each screen is staged with no agent, from the payloads in
|
||||
`scripts/screenshots/` (its README names the file behind each screen), in a
|
||||
throwaway sample project and console home that the script removes when it is
|
||||
done. It prints each file's size and warns over 300 KB.
|
||||
|
||||
Open every image before you commit it: the right screen, both themes, nothing
|
||||
cut off, and no username, home path or real project name anywhere on it.
|
||||
@@ -0,0 +1,108 @@
|
||||
# AGENTS.md
|
||||
|
||||
This file provides guidance to AI coding agents working with code in this repository.
|
||||
|
||||
## Project Overview
|
||||
|
||||
Plan2Code is a structured 4-step workflow methodology for AI-assisted software development. It provides prompt templates that can be installed globally or per-project for various AI coding tools (Claude Code, Cursor, Copilot, Continue, Windsurf, Codeium, Devin, Zed).
|
||||
|
||||
**Version:** Check `version.json` for current version
|
||||
**Author:** Justin Parker
|
||||
**License:** MIT
|
||||
|
||||
Plan2Code is started from the project the person works in (`cd` into it, then run `plan2code`), not from this repository; every newcomer doc says so, next to the Node.js 18+ requirement.
|
||||
|
||||
## How to Use This File
|
||||
|
||||
This file is an index — each section below contains a brief summary and a link to a detail file in `.agents-docs/`. Read only the sections relevant to your current task. Full details (commands, tables, file lists) are in the linked files. The sections "Project Overview", "How to Use This File", "Mascot", and "Keeping this file current" / "Failure log" are fully inline here and are never split into `.agents-docs/`.
|
||||
|
||||
## Architecture
|
||||
|
||||
High-level directory structure, key files, workflow prompt inventory, and file naming conventions.
|
||||
|
||||
Details: [Architecture](./.agents-docs/AGENTS-architecture.md)
|
||||
|
||||
## Plan2Code Loop
|
||||
|
||||
Autonomous CLI tool (`plan2code-loop/`) that implements specs by looping through tasks. Covers loop architecture, modes (one-task vs one-phase), completion markers, and key source files.
|
||||
|
||||
Details: [Plan2Code Loop](./.agents-docs/AGENTS-plan2code-loop.md)
|
||||
|
||||
## Plan2Code Metrics
|
||||
|
||||
Recursive self-improvement toolchain (`plan2code-metrics/`) for collecting run metrics, aggregating by prompt generation, diagnosing weak steps, and proposing prompt edits.
|
||||
|
||||
Details: [Plan2Code Metrics](./.agents-docs/AGENTS-plan2code-metrics.md)
|
||||
|
||||
## Plan2Code Status Line (Claude CLI)
|
||||
|
||||
Optional CLI status bar (`src/statusline-claude/`) for Claude Code. Displays model (+ effort), project/worktree, branch, git diff stats, duration + session cost, context usage, and usage stats (rate limits or token counts). Reads data directly from Claude Code's stdin JSON (plus timeout-bounded git calls): no API calls, no auth, no background processes.
|
||||
|
||||
Details: [Architecture](./.agents-docs/AGENTS-architecture.md) (see Status Line section)
|
||||
|
||||
## Web Console
|
||||
|
||||
Optional local browser UI (`src/web-console/`, zero dependencies, detached `node` server on `127.0.0.1`) bundled into every skill via `additionalReferences`. The bare `plan2code` skill opens its dashboard, a card menu that launches any skill in the same session. Pages cover questions, sign-off gates (with an in-page code review), build progress, the living document, an **Ask** chat, a read-only **Workspace** of extra folders (remembered per folder and spec in `~/.plan2code/console/workspaces.json`), a session meter, a **git board** for the `git` workflow (three tabs, Changes, Branches and Sync, opening on the likely next step; branches, pull, push, commits and pull-request links, drawn from `state.git`; contract in `notes/git.md`), **Stop with a handoff** (handoffs live in `~/.plan2code/handoffs/`, owned by `handoffs.mjs`, swept after 30 days, and offered as dashboard chips to pick up in the same session), a private **Notebook** in the top bar (named tabs of Markdown and pictures, a live-preview CodeMirror editor, one notepad per folder in `~/.plan2code/notepads/`, owned by `notepads.mjs`, never shown to the agent, removed only through Cleanup once a month untouched), a built-in 18-topic Help, a first-run Welcome, User Preferences (gear) and a bug/idea link to GitHub issues. On opted-in skills (builds, review, Pathfinder) a **Subagents** button in the top bar turns helpers on or off per project and skill (on by default for those skills until switched off, saved in `~/.plan2code/console/subagents.json`); the agent hears of it as a standing instruction only when it changes, and reports its helpers in a **Subagents** tab beside Ask (contract in `console-subagents.md`). Per-skill facts live in one list, `public/skills.js`, from which the meter, the resume command, Help's card list and the CLI's workflow list are derived; task files are read through `spec-files.mjs` (shared with the `specs.mjs` skill script), and the rule for which hops start the page clean is `startsClean()` in `public/hops.js`. The agent contract is read in pieces: `console.md` once per conversation, then a topic file (`console-*.md`, `notes/<workflow>.md`, `building*.md`) only when its moment comes; the server never writes into a project.
|
||||
Details: [Architecture](./.agents-docs/AGENTS-architecture.md) (see Web Console section) and [.readme/web-console.md](./.readme/web-console.md)
|
||||
|
||||
## Skill Scripts
|
||||
|
||||
Deterministic workflow steps run as Node scripts shipped in each skill's `scripts/` (shared ones in `src/skill-scripts/`, a skill's own in `src/<skill>-scripts/`, listed per skill in `SOURCE_PROMPTS` → `scripts`). Prose keeps the judgment. JSON on stdout, documented exit codes, tests run against the built `skills/` tree.
|
||||
|
||||
Details: [Architecture](./.agents-docs/AGENTS-architecture.md) (see Skill Scripts section)
|
||||
|
||||
## Development Commands
|
||||
|
||||
Build commands, installer menu options, non-interactive skill-build verification, skills CLI delegation, skill format, and how to edit workflow prompts.
|
||||
|
||||
Details: [Development Commands](./.agents-docs/AGENTS-development-commands.md)
|
||||
|
||||
## Code Style & Gotchas
|
||||
|
||||
Language/toolchain conventions for `install.js` vs TypeScript packages, and pitfalls to avoid (version sync, `.gitignore` pre-flight, character limits, User Feedback table format).
|
||||
|
||||
Details: [Code Style & Gotchas](./.agents-docs/AGENTS-code-style.md)
|
||||
|
||||
## Mascot
|
||||
|
||||
The project has a mascot called "Planny": a box with a star for an eye, stick arms and two small feet. He appears in installer output, workflow prompts, the loop, the Claude Code status line (box, star and feet, no arms) and the web console. ASCII variants are defined in the `MASCOT` constant in `install.js` (and `plan2code-loop/src/utils/logger.ts`) and appear in workflow markdown files: arms down at rest, one arm waving when he is asking something, both arms up when he is celebrating. The eye is always the star.
|
||||
|
||||
The web console draws him as inline SVG in `src/web-console/public/index.html`, where he doubles as the page's state indicator: his star lights in the highlight colour and he waves when something is yours to do, the star turns and his feet walk while the agent works, it goes green when all is done, he shows no arms at all when the agent is not answering, and he fades with his star shut when the connection drops. The parts are classed (`shell`, `eye`, `smile`, `foot`, and one `arms a-<mood>` set per mood) and `screens/core.js` switches mood with a single class, so the drawing stays in the markup and the styling in `styles/planny.css`. The nine skill start poses, the dashboard wake-up, `favicon.svg` / `favicon.js` and `src/launcher/plan2code.ico` all use the same design.
|
||||
|
||||
```
|
||||
╭───╮
|
||||
│ ★ │╱
|
||||
╱│ ◡ │
|
||||
╰┬─┬╯
|
||||
```
|
||||
|
||||
## Keeping this file current
|
||||
|
||||
The `Failure log` section below is a recording of mistakes made by previous AI Agents while working with this code base.
|
||||
|
||||
When you make a mistake, get corrected, or discover something about this codebase that wasn't written down:
|
||||
|
||||
1. Add one line to the `Failure log` below, in the imperative, describing the correct behaviour.
|
||||
2. Keep it specific to this repo. General advice belongs nowhere.
|
||||
3. If this fix is a workflow rather than a rule, put it in `.claude/skills/` and link it from here.
|
||||
4. Include the change in the same commit and mention it in your summary.
|
||||
5. A skill rule broken twice becomes a script check (a `scripts/` test or a skill-script check), not more prose.
|
||||
6. Before adding a line, look for one on the same topic: sharpen or extend that one rather than adding a near-duplicate.
|
||||
7. Keep the log to 17 entries at most. Over the cap, first merge entries that share a cause, then drop the lowest-value ones: one-offs unlikely to recur, rules a test or script now enforces, and entries about code that no longer exists.
|
||||
|
||||
## Failure log
|
||||
|
||||
- Do not audit `CHANGELOG.md` headings through PowerShell — the emoji come back as `?`. See the gotcha for the correct approach.
|
||||
- Sync upstream only through `/sync-repo`, and verify its baseline against the real tree before porting: an earlier sync silently skipped a whole upstream release (the `3-implement-review` skill) while the recorded version froze. Update the baseline with `.claude/skills/sync-repo/set-synced.mjs`, never with a shell pipe over the decrypted body.
|
||||
- After a sync merge, run `npm test` before trusting a "clean" file: when upstream and plan2code fixed the same bug, `git merge-file` keeps both copies without a conflict (a sync once left `let pattern` declared twice in `app.js`, caught only by `parse-check`).
|
||||
- When extracting upstream files in Git Bash, run `git show <ref>:<path>` with `MSYS_NO_PATHCONV=1` and `C:/` style paths (never `/c/`): path conversion rewrites `origin/main:.readme/x.md` into `origin\main;.readme\x.md`, the show fails, and the merge silently runs against an empty "theirs". Check every extracted file is non-empty before merging.
|
||||
- After a sync, grep the result for every upstream name the rebrand map can miss (the `/sync-repo` body lists them): the owner slug and company name in any case, the bare brand word inside identifiers and fixtures, and the ticket key followed by anything, not only digits. Each slipped through once: an owner slug in `feedback-payload.mjs` and its test (fixed by hand to `jparkerweb/plan2code`); in v2.7.0 a `KEPT_<BRAND>_ENTRIES` constant, a `<brand>Dir` option, a `"<brand>"` test folder and an owner slug in a git remote URL; in v2.8.0 git board fixtures built as `` `feature/<KEY>-${11000 + i}-…` `` template literals, which a digits-only rewrite to `ABC-<n>` misses. No upstream name may appear in plain text anywhere in this repo.
|
||||
- Keep plan2code's ticket-free `commit-msg.mjs` (`<subject>`, `AI Assisted`) in every `/sync-repo`: upstream's ticket-from-branch rule was ported by mistake once and removed in v2.6.0.
|
||||
- When a new first-run dialog is added to the web console, set its seen flag in `scripts/capture-screenshots.mjs`'s `looks.json` too: the Welcome dialog once covered the regenerated dashboard screenshots until `welcomeSeen: true` was added.
|
||||
- Import `scripts/skill-script-helpers.mjs` in any test that builds git fixtures for a skill script or `git-repo.mjs`: it scrubs the whole test process's git config, so fixtures, imported modules and spawned scripts agree. Mixed configs broke `git plan switch` once (a global `core.autocrlf=true` checked fixtures out with CRLF the scrubbed script read as changed).
|
||||
- Before deleting a test file that upstream split or removed, diff plan2code's copy against the rebranded upstream base and port the plan2code-only tests: v2.7.0's split of the web console suite would otherwise have dropped seven hardening tests (now in `scripts/test-web-console-hardening.mjs`).
|
||||
- Register a new skill in `install.js` `SOURCE_PROMPTS` before running its `scripts/test-script-<name>.mjs`: importing `scripts/skill-script-helpers.mjs` rebuilds `skills/` and prunes any skill folder `install.js` does not list, so the script under test vanishes.
|
||||
- When a `CHANGELOG.md` heading gets a version number, set the same number in `version.json` (with its `releaseDate`), the root `package.json` and README's `Version X.Y.Z` line in the same change, then run `npm run build:skills`. The changelog skill only touches `package.json`: v2.9.0 nearly shipped with `version.json` at 2.8.1, and README's line sat at 2.6.0 for three releases.
|
||||
- When `npm test` fails only timing-bound suites (the chat stress test, the page-cards redraw test "a redraw keeps the place of...", then a cascade in the session suite starting at "no submitted frame within 5s") while the machine is busy, rerun those files alone, and the `node --test` list with `--test-concurrency=4`, before suspecting the change: they failed that way on untouched code under load during the web console file split, and the redraw test did again in three phases of web-console-health. In web-console-notepad, four more failed only in full runs and passed alone: the Workspace page's @-mention test, the dashboard page's handoff chip test, the session suite's document route (`connect ETIMEDOUT`) and the notepad page's 200 KB typing test (why its budget there is 200 ms, not the 92 ms it takes alone).
|
||||
- Post a helper as `done` or `failed` in the same turn its completion notice arrives: its row stays `running` on the Subagents tab until a post says otherwise (a build once reached its sign-off with one row spinning). A `finish` is now refused while any helper is `running`.
|
||||
- Bring the Windows folder picker (`picker.mjs`, copied into `src/launcher/plan2code.js`) to the front with an Alt tap before `SetForegroundWindow`, never with `windowsHide`, the owner form's `TopMost`, `HWND_TOPMOST` or `AttachThreadInput`: measured on Windows 11, `SetWindowPos(HWND_TOPMOST)` returns true while the dialog stays non-topmost behind the browser, and only the Alt tap made it the foreground window. Check with `GetForegroundWindow` from a second process, since no test can see it.
|
||||
@@ -0,0 +1,14 @@
|
||||
# CLAUDE.md
|
||||
|
||||
**CRITICAL — MANDATORY FIRST STEP: You MUST read [AGENTS.md](./AGENTS.md) before responding to ANY user message, including simple questions. Do NOT skip this step regardless of how trivial the request appears. No exceptions.**
|
||||
|
||||
See AGENTS.md for complete project documentation including:
|
||||
- Development commands and setup
|
||||
- Architecture overview
|
||||
- Workflow prompt reference
|
||||
- Plan2Code Loop CLI details
|
||||
- Code style and gotchas
|
||||
- Keeping this file current / Failure log
|
||||
- Section details in .agents-docs/
|
||||
|
||||
This file exists for Claude Code auto-loading. All AI coding agents should reference AGENTS.md.
|
||||
@@ -1,66 +1,143 @@
|
||||
# Plan2Code Quick Reference
|
||||
|
||||
## Before you start
|
||||
|
||||
- **Node.js 18 or newer.** Check with `node --version`. No Node? Get it from [nodejs.org](https://nodejs.org/) (the LTS download), or run `winget install OpenJS.NodeJS.LTS` on Windows, `brew install node` on macOS, or use `nvm` on Linux. Then open a new terminal.
|
||||
- **Start from your project.** Open your terminal in the project you want to work on (`cd` into it) before you run anything. Plan2Code works on the folder you start it in.
|
||||
- **Ways in.** `plan2code` (Claude Code, Devin or Codex), or type `/plan2code` in your agent (`$plan2code` in Codex).
|
||||
- **No agent yet?** Install Claude Code, Codex or Devin first.
|
||||
|
||||
## Launch
|
||||
|
||||
The web console is the main way in: a local page where questions, documents, build progress and sign-offs live.
|
||||
|
||||
| How | Command | What happens |
|
||||
| ------------------------- | ------------------------------------ | -------------------------------------------------------------------------------------- |
|
||||
| From your project (shell) | `plan2code` | Opens Claude Code, Devin or Codex on the dashboard (`--cli claude` / `devin` / `codex` to choose) |
|
||||
| Inside any agent | `/plan2code` (`$plan2code` in Codex) | Opens the dashboard: a card for every skill, launched on the same page |
|
||||
| Install | `npx --allow-git=all git+https://github.com/jparkerweb/plan2code.git` | Installs the skills and the `plan2code` command (re-run it to update without the `plan2code` command) |
|
||||
| Update | `plan2code update` | Updates everything that was installed, with no menu; never uninstalls anything |
|
||||
| Straight into a skill | `/plan2code-1-plan --web` (any step) | Skips the "web console or terminal?" question and opens the page |
|
||||
|
||||
The install command always opens a menu. Back at your prompt with no output at all? npm could not reach the repository and hid the reason: run `git ls-remote https://github.com/jparkerweb/plan2code.git` to see it (usually the network, a proxy or the VPN).
|
||||
|
||||
Pick a skill on the dashboard and the same page becomes that session. Details: [.readme/web-console.md](.readme/web-console.md) · worked example: [.readme/walkthrough.md](.readme/walkthrough.md).
|
||||
|
||||
The **Notebook** icon in the top bar opens a private scratch pad for the folder you are in (Markdown and pictures, kept in `~/.plan2code/notepads/`, never shown to the agent).
|
||||
|
||||
## Commands
|
||||
|
||||
| Step | Command | Input | Output |
|
||||
| ------ | ---------------------------| --------------- | ------------------------- |
|
||||
| Init | /plan2code---init | None | AGENTS.md file |
|
||||
| Update | /plan2code---init-update | AGENTS.md | Updated AGENTS.md |
|
||||
| 0 | /plan2code---quick-task | Requirements | Conversational plan |
|
||||
| 1 | /plan2code-1--plan | Requirements | PLAN-DRAFT.md |
|
||||
| 1b | /plan2code-1b--revise-plan | Specs + changes | Updated specs |
|
||||
| 2 | /plan2code-2--document | PLAN-DRAFT.md | overview.md + Phase files |
|
||||
| 3 | /plan2code-3--implement | overview.md | Implemented code |
|
||||
| 4 | /plan2code-4--finalize | overview.md | Archived specs |
|
||||
Every command below is what a dashboard card runs. Typed on its own, each one asks "web console or terminal?" first.
|
||||
|
||||
| Step | Command | Input | Output |
|
||||
| ---------- | ----------------------------- | --------------- | ------------------------------------------------------------------------------------------------------------- |
|
||||
| — | /plan2code | None | Web console dashboard — a menu of every skill below, launched on the page |
|
||||
| Init | /plan2code-init | None | AGENTS.md file |
|
||||
| Update | /plan2code-init-update | AGENTS.md | Updated AGENTS.md |
|
||||
| 0 | /plan2code-0-pathfinder | A foggy idea | pathfinder/map.md *or* GitHub Issues + PLAN-DRAFT-<date>.md |
|
||||
| quick | /plan2code-quick-task | Requirements | A short plan, then the change built (standalone, not a pipeline step) |
|
||||
| review | /plan2code-review | Scope guidance | Review findings + fixes |
|
||||
| 1 | /plan2code-1-plan | Requirements | PLAN-CONVERSATION-<date>.md + PLAN-DRAFT-<date>.md |
|
||||
| 1b | /plan2code-1b-revise-plan | Specs + changes | Updated specs |
|
||||
| 2 | /plan2code-2-document | PLAN-DRAFT.md | overview.md + Phase files |
|
||||
| 3 | /plan2code-3-implement | overview.md | Implemented code |
|
||||
| 3+review | /plan2code-3-implement-review | overview.md | Reviewed implementation ready for approval (alternative to `/plan2code-3-implement`) |
|
||||
| 4 | /plan2code-4-finalize | overview.md | Archived specs |
|
||||
| handoff | /plan2code-handoff | Conversation | Self-contained handoff doc (OS temp dir by default, or a folder you pick such as `handoffs/`) |
|
||||
| xray | /plan2code-xray | An area, or none | An explanation citing files and commits, or `ARCHITECTURE-BRIEF-<date>.md` with the rough spots you picked |
|
||||
| diagnose | /plan2code-diagnose | A bug, or none | `DIAGNOSIS-<date>.md` with the cause and its evidence, then Quick Task (or Plan for a big fix) to fix it |
|
||||
| changelog | /plan2code-changelog | Your branch | `CHANGELOG.md` entries and the `package.json` version, from the default branch's latest version |
|
||||
| git | /plan2code-git | Your repo | Commits (`<subject>` / `AI Assisted`), branches, pull with conflict help, push, publish |
|
||||
|
||||
**Terminal instead:** run any command without `--web` and answer the interface question with **terminal**. Nothing is lost: same questions, same gates, same files under `specs/`. You can switch between the two mid-feature.
|
||||
|
||||
## File Structure
|
||||
|
||||
```
|
||||
specs/
|
||||
├── PLAN-DRAFT-<timestamp>.md # From Step 1
|
||||
└── <feature-name>/
|
||||
├── overview.md # From Step 2
|
||||
└── Phase X.md # From Step 2
|
||||
├── pathfinder/ # From Step 0 (optional, if charted locally)
|
||||
│ ├── map.md # the map: destination, decisions, fog
|
||||
│ ├── questions/NN-<slug>.md # one decision question per file
|
||||
│ └── briefs/brief-<date>.md # on-demand plain-English decision briefs
|
||||
│ # (GitHub Issues backend: map issue + sub-issues instead)
|
||||
├── PLAN-DRAFT-<date>.md # From Step 1 (verified plan)
|
||||
├── PLAN-CONVERSATION-<date>.md # From Step 1 (conversation log)
|
||||
├── overview.md # From Step 2
|
||||
└── phase-X.md # From Step 2
|
||||
|
||||
specs--completed/ # After Step 4
|
||||
└── <feature-name>/ # Archived specs
|
||||
specs--completed/ # After Step 4
|
||||
└── <feature-name>/ # Archived specs
|
||||
```
|
||||
|
||||
Note: `<date>` uses YYYYMMDD format (e.g., `20250204`)
|
||||
|
||||
## Key Rules
|
||||
|
||||
- Start NEW conversation for each step (and each implementation phase)
|
||||
- ONE phase per conversation
|
||||
- Reply "approved" to complete phases
|
||||
- Keep sessions short: fresh console session when the meter turns red, and before a big plan or build step
|
||||
- ONE phase per conversation (but parallel phases can run in separate instances)
|
||||
- Approve phases on the sign-off card (or reply "approved" in the terminal)
|
||||
- 90% confidence required before planning completes
|
||||
- Never look in `specs--completed/` (it's archived specs)
|
||||
|
||||
## Phase Status
|
||||
|
||||
| Checkbox | Status | Meaning |
|
||||
|----------|--------|---------|
|
||||
| `[ ]` | Pending | Not started |
|
||||
| `[/]` | In Progress | Agent working (or paused) |
|
||||
| `[x]` | Complete | Approved |
|
||||
| `[!]` | Blocked | Couldn't be done; the line says why and what you need to do |
|
||||
| `[?]` | Assumed | Couldn't be verified, assumed complete; check it |
|
||||
|
||||
## Parallel Execution
|
||||
|
||||
When phases have no file conflicts or dependencies, they can run simultaneously:
|
||||
|
||||
1. Documentation Mode auto-detects parallel-eligible phases
|
||||
2. Implementation Mode asks which phase to take (a card on the web console), with the status of each
|
||||
3. Run multiple `/plan2code-3-implement` instances on different phases
|
||||
4. `[/]` status shows which phases are actively being worked on
|
||||
|
||||
## Quick Troubleshooting
|
||||
|
||||
| Issue | Solution |
|
||||
| ---------------------- | ----------------------------------------------- |
|
||||
| Lost context mid-phase | Attach spec files, say "resume from Task X.Y" |
|
||||
| Wrong phase started | Say "abort", start correct phase |
|
||||
| Need to change plan | Use `/plan2code-1b--revise-plan` |
|
||||
| Multiple spec folders | Specify which: "Continue with specs/user-auth/" |
|
||||
| Need AGENTS.md file | Use `/plan2code---init` to generate one |
|
||||
| Update AGENTS.md | Use `/plan2code---init-update` after sessions |
|
||||
| Issue | Solution |
|
||||
| ---------------------- | ------------------------------------------------ |
|
||||
| Lost context mid-phase | Attach spec files, say "resume from Task X.Y" |
|
||||
| Wrong phase started | Say "abort", start correct phase |
|
||||
| Need to change plan | Use `/plan2code-1b-revise-plan` |
|
||||
| Multiple spec folders | Specify which: "Continue with specs/user-auth/" |
|
||||
| Need AGENTS.md file | Use `/plan2code-init` to generate one |
|
||||
| Update AGENTS.md | Use `/plan2code-init-update` after sessions |
|
||||
| Run phases in parallel | Check Parallel Execution Groups in overview.md |
|
||||
|
||||
## Workflow Decision
|
||||
|
||||
```
|
||||
New to a project?
|
||||
└── /plan2code---init → Generate AGENTS.md for project-specific guidance
|
||||
└── /plan2code-init → Generate AGENTS.md for project-specific guidance
|
||||
|
||||
Learned something during a session?
|
||||
└── /plan2code---init-update → Add learnings to AGENTS.md
|
||||
└── /plan2code-init-update → Add learnings to AGENTS.md
|
||||
|
||||
Too foggy to plan? (big idea, don't yet know what the questions are)
|
||||
└── /plan2code-0-pathfinder → chart it, clear one decision at a time
|
||||
├── continue-or-stop menu between decisions; fresh session recommended after ~3
|
||||
└── then → /plan2code-1-plan (resumes at Phase 4)
|
||||
|
||||
Is it a quick, small task?
|
||||
├── Yes → /plan2code---quick-task (standalone)
|
||||
└── No → /plan2code-1--plan (full workflow)
|
||||
├── /plan2code-2--document
|
||||
├── /plan2code-3--implement (repeat per phase)
|
||||
└── /plan2code-4--finalize
|
||||
├── Yes → /plan2code-quick-task (standalone)
|
||||
└── No → /plan2code-1-plan (full workflow)
|
||||
├── /plan2code-2-document
|
||||
├── /plan2code-3-implement (repeat per phase)
|
||||
│ ├── OR: /plan2code-3-implement-review (review gate before approval)
|
||||
│ └── OR: plan2code-loop (autonomous alternative)
|
||||
└── /plan2code-4-finalize
|
||||
|
||||
Need to revise mid-implementation?
|
||||
└── /plan2code-1b--revise-plan
|
||||
└── /plan2code-1b-revise-plan
|
||||
```
|
||||
|
||||
## Autonomous Loop (Alternative)
|
||||
|
||||
`plan2code-loop` is a hands-off alternative to Step 3. See [.readme/autonomous-loop.md](.readme/autonomous-loop.md).
|
||||
@@ -1,485 +1,432 @@
|
||||
# Plan2Code: AI-Assisted Software Development Workflow
|
||||
|
||||
A structured 4-step workflow for developing features and projects with AI assistance. This methodology emphasizes thorough planning before implementation, ensuring well-documented, maintainable code.
|
||||
|
||||
<img src="docs/plan2code.jpg" alt="Plan2Code Workflow" height="400">
|
||||
|
||||
## Overview
|
||||
|
||||
```
|
||||
🤔 📝 ⚡ 🧹
|
||||
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
|
||||
│ Step 1 │ │ Step 2 │ │ Step 3 │ │ Step 4 │
|
||||
│ PLAN │ --> │ DOCUMENT │ --> │ IMPLEMENT │ --> │ FINALIZE │
|
||||
└─────────────────┘ └─────────────────┘ └─────────────────┘ └─────────────────┘
|
||||
New Chat New Chat New Chat (per phase) New Chat
|
||||
```
|
||||
|
||||
| Command | Use When |
|
||||
|---------|----------|
|
||||
| `/plan2code---init` | Generate AGENTS.md file for new/existing projects |
|
||||
| `/plan2code---init-update` | Update AGENTS.md with new learnings from coding sessions |
|
||||
| `/plan2code---quick-task` | Small, quick tasks that don't need full workflow |
|
||||
| `/plan2code-1--plan` | Starting a new feature (full planning) |
|
||||
| `/plan2code-1b--revise-plan` | Requirements change mid-implementation |
|
||||
| `/plan2code-2--document` | After planning, create implementation specs |
|
||||
| `/plan2code-3--implement` | Execute implementation (one phase per conversation) |
|
||||
| `/plan2code-4--finalize` | All phases complete, ready to archive |
|
||||
|
||||
**Key Rules:**
|
||||
- Start NEW conversation for each step (and each implementation phase)
|
||||
- ONE phase per conversation
|
||||
- Reply "approved" to complete phases
|
||||
- 90% confidence required before planning completes
|
||||
|
||||
See [QUICK-REFERENCE.md](QUICK-REFERENCE.md) for full reference card.
|
||||
|
||||
---
|
||||
|
||||
## Installation
|
||||
|
||||
### Prerequisites
|
||||
|
||||
**Node.js** (v14 or later) is required. If you don't have it:
|
||||
- Download from [nodejs.org](https://nodejs.org/)
|
||||
- Or: `brew install node` (macOS) | `winget install OpenJS.NodeJS` (Windows) | `sudo apt install nodejs` (Linux)
|
||||
|
||||
### Quick Start
|
||||
|
||||
```bash
|
||||
git clone https://github.com/jparkerweb/plan2code.git
|
||||
cd plan2code
|
||||
node install.js
|
||||
```
|
||||
|
||||
The interactive installer will guide you through:
|
||||
- **Global installation** (recommended) - commands available in all projects
|
||||
- **Local/project installation** - commands for a specific project only
|
||||
- **Uninstall** - remove previously installed files
|
||||
|
||||
<img src="docs/install-script.jpg" width="600">
|
||||
|
||||
### Supported Platforms
|
||||
|
||||
| Platform | Global Location | Invocation |
|
||||
|----------|-----------------|------------|
|
||||
| Claude Code | `~/.claude/commands/` | `/plan2code-1--plan` |
|
||||
| Copilot CLI | `~/.copilot/agents/` | `--agent=plan2code-1--plan` |
|
||||
| VS Code Copilot | `~/Library/Application Support/Code/User/prompts/` | Slash commands |
|
||||
| Windsurf | `~/.codeium/windsurf/global_workflows/` | `/plan2code-1--plan` |
|
||||
| Cursor | `~/.cursor/commands/` | `/plan2code-1--plan` |
|
||||
| Continue | `~/.continue/prompts/` | `/plan2code-1--plan` |
|
||||
| Antigravity | `.agent/workflows/` (project only) | `/plan2code-1--plan` |
|
||||
|
||||
### CLI Options
|
||||
|
||||
```bash
|
||||
node install.js # Interactive menu
|
||||
node install.js --platform claude # Install specific platform
|
||||
node install.js --local # Install to current project instead of global
|
||||
node install.js --dry-run # Preview what would be installed
|
||||
node install.js --uninstall # Remove installed files
|
||||
node install.js --help # Show all options
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
<details>
|
||||
<summary>Platform Details</summary>
|
||||
|
||||
### Claude Code CLI
|
||||
|
||||
Type `/plan2code-1--plan` in chat. Restart Claude Code after installation.
|
||||
|
||||
**Docs:** [Claude Code Slash Commands](https://code.claude.com/docs/en/slash-commands)
|
||||
|
||||
### GitHub Copilot CLI
|
||||
|
||||
```bash
|
||||
copilot --agent=plan2code-1--plan --prompt "I want to build a REST API"
|
||||
```
|
||||
|
||||
Requires: `npm install -g @github/copilot@latest`
|
||||
|
||||
**Docs:** [GitHub Copilot CLI Custom Agents](https://docs.github.com/en/copilot/concepts/agents/about-copilot-cli)
|
||||
|
||||
### VS Code GitHub Copilot
|
||||
|
||||
Open Copilot Chat (`Ctrl+Shift+I`), type `/` to see prompts. Requires per-project install via `node install.js --local`.
|
||||
|
||||
**Docs:** [VS Code Copilot Prompt Files](https://code.visualstudio.com/docs/copilot/customization/prompt-files)
|
||||
|
||||
### Windsurf IDE
|
||||
|
||||
Type `/plan2code-1--plan` in Cascade. Note: 12,000 character limit per workflow.
|
||||
|
||||
**Docs:** [Windsurf Workflows](https://docs.windsurf.com/windsurf/cascade/workflows)
|
||||
|
||||
### Cursor AI
|
||||
|
||||
Type `/` in chat, select command from dropdown.
|
||||
|
||||
**Docs:** [Cursor Commands](https://docs.cursor.com/agent/chat/commands)
|
||||
|
||||
### Google Antigravity
|
||||
|
||||
Type `/plan2code-1--plan` in chat. Requires per-project install via `node install.js --local`.
|
||||
|
||||
**Docs:** [Customize Antigravity](https://atamel.dev/posts/2025/11-25_customize_antigravity_rules_workflows/)
|
||||
|
||||
### Continue (VS Code/JetBrains)
|
||||
|
||||
Type `/plan2code-1--plan` in chat. Install the Continue extension first.
|
||||
|
||||
**Docs:** [Continue Prompts](https://docs.continue.dev/customize/deep-dives/prompts)
|
||||
|
||||
</details>
|
||||
|
||||
---
|
||||
|
||||
<details>
|
||||
<summary>Manual Installation</summary>
|
||||
|
||||
If your AI tool isn't listed or you prefer manual setup:
|
||||
|
||||
1. **Copy/Paste:** Copy contents from `src/plan2code-*.md` files into your conversation
|
||||
2. **File Reference:** Tell the AI: `Please follow the instructions in src/plan2code-1--plan.md`
|
||||
3. **Custom Integration:** Adapt files from `dist/` directories to your tool's format
|
||||
|
||||
</details>
|
||||
|
||||
---
|
||||
|
||||
## Important: Start Fresh Conversations
|
||||
|
||||
**Start a new conversation/chat session before each step.** This includes:
|
||||
|
||||
- Step 1: New conversation
|
||||
- Step 2: New conversation
|
||||
- Step 3: New conversation **for each phase** (Phase 1, Phase 2, etc.)
|
||||
- Step 4: New conversation
|
||||
|
||||
Fresh conversations prevent context pollution and ensure the AI focuses on the current task with the relevant specifications.
|
||||
|
||||
---
|
||||
|
||||
## The Workflow Steps
|
||||
|
||||
### Step 1: Planning Mode 🤔
|
||||
|
||||
**Purpose:** Thoroughly analyze requirements and design the solution architecture before writing any code.
|
||||
|
||||
**AI Role:** Senior software architect and technical product manager
|
||||
|
||||
**Phases (completed one at a time):**
|
||||
|
||||
1. **Requirements Analysis** - Extract functional/non-functional requirements, identify ambiguities
|
||||
2. **System Context Examination** - Review existing codebase, identify integration points
|
||||
3. **Tech Stack** - Recommend and confirm all technologies (requires user sign-off)
|
||||
4. **Architecture Design** - Propose patterns, define components, design interfaces/schemas
|
||||
5. **Technical Specification** - Break down implementation phases, identify risks
|
||||
6. **Transition Decision** - Finalize plan when confidence reaches 90%+
|
||||
|
||||
**Output:** `specs/PLAN-DRAFT-<timestamp>.md` containing the complete implementation plan
|
||||
|
||||
**Key Behaviors:**
|
||||
|
||||
- AI stops after each phase for clarification
|
||||
- Must reach 90% confidence before finalizing
|
||||
- All assumptions are documented
|
||||
- User must approve tech stack decisions
|
||||
|
||||
---
|
||||
|
||||
### Step 2: Documentation Mode 📝
|
||||
|
||||
**Purpose:** Transform the planning output into structured, actionable implementation documents.
|
||||
|
||||
**Required Context:** Attach or reference the `specs/PLAN-DRAFT-<timestamp>.md` from Step 1 (or provide the planning conversation).
|
||||
|
||||
**Output Structure:**
|
||||
|
||||
```
|
||||
specs/
|
||||
└── <feature-name>/
|
||||
├── overview.md # High-level overview with phase checkboxes
|
||||
├── Phase 1.md # Detailed tasks for Phase 1
|
||||
├── Phase 2.md # Detailed tasks for Phase 2
|
||||
└── Phase N.md # ...additional phases
|
||||
```
|
||||
|
||||
**Document Format:**
|
||||
|
||||
- Each phase file contains detailed one-story-point tasks
|
||||
- All tasks have checkboxes `[ ]` for progress tracking
|
||||
- Each phase is self-contained (developer needs no prior context)
|
||||
- Unit/E2E testing excluded unless explicitly requested
|
||||
|
||||
---
|
||||
|
||||
### Step 3: Implementation Mode ⚡
|
||||
|
||||
**Purpose:** Execute the implementation following the documented specifications.
|
||||
|
||||
**AI Role:** Senior software engineer
|
||||
|
||||
**Required Context:** Provide the path to `specs/<feature-name>/overview.md`. The command will auto-detect the next uncompleted phase and read the corresponding `Phase X.md` file automatically.
|
||||
|
||||
**Workflow:**
|
||||
|
||||
1. Identify the next uncompleted phase (unchecked in `overview.md`)
|
||||
2. Implement ALL tasks in that phase exactly as specified
|
||||
3. Update `Phase X.md` checkboxes as tasks complete `[x]`
|
||||
4. Update `overview.md` phase checkbox when phase completes
|
||||
5. Perform code review to ensure nothing was missed
|
||||
6. Add completion summary to the phase document
|
||||
|
||||
**Key Rules:**
|
||||
|
||||
- **Start a new conversation for EACH phase**
|
||||
- Work on ONE phase per conversation (unless told otherwise)
|
||||
- Follow specifications EXACTLY as documented
|
||||
- Keep checkboxes updated (enables progress tracking across sessions)
|
||||
- Do NOT run tests unless specified in phase tasks
|
||||
|
||||
---
|
||||
|
||||
### Step 4: Finalization Mode 🧹
|
||||
|
||||
**Purpose:** Validate implementation, create summaries, and archive documentation.
|
||||
|
||||
**Required Context:** Attach or reference the `specs/<feature-name>/` directory contents.
|
||||
|
||||
**Steps:**
|
||||
|
||||
1. **Validation** - Verify all tasks implemented correctly, check for issues
|
||||
2. **Summary** - Document what was built and list all modified/created files
|
||||
3. **Documentation Review** - Identify any needed README/CHANGELOG updates
|
||||
4. **Spec Cleanup** - Move completed specs to `specs--completed/<implementation-name>/`
|
||||
5. **Final Confirmation** - Confirm completion
|
||||
|
||||
---
|
||||
|
||||
## How to Use These Prompts
|
||||
|
||||
### Option 1: Platform-Specific Slash Commands (Recommended)
|
||||
|
||||
This repository includes pre-configured workflow files for all major AI coding assistants. See the [Installation](#installation) section above for platform-specific setup instructions.
|
||||
|
||||
**Quick commands after setup:**
|
||||
|
||||
```
|
||||
/plan # Start planning a new feature
|
||||
/document # Create implementation docs from plan
|
||||
/implement # Begin/continue implementation
|
||||
/finalize # Wrap up after all phases complete
|
||||
```
|
||||
|
||||
### Option 2: Direct File Reference
|
||||
|
||||
Reference the prompt files directly in your conversation:
|
||||
|
||||
```
|
||||
Please follow the instructions in src/plan2code-1--plan.md
|
||||
|
||||
I want to build a user authentication system with OAuth support.
|
||||
```
|
||||
|
||||
### Option 3: Copy/Paste
|
||||
|
||||
Copy the contents of each prompt file and paste at the beginning of your conversation when starting that step.
|
||||
|
||||
---
|
||||
|
||||
## Complete Workflow Example
|
||||
|
||||
### Starting a New Project
|
||||
|
||||
**Session 1 - Planning (New Chat):**
|
||||
|
||||
```
|
||||
User: [Paste or invoke Step 1 prompt]
|
||||
I want to build a REST API for a task management application.
|
||||
|
||||
AI: 🤔 [REQUIREMENTS ANALYSIS]
|
||||
... asks clarifying questions, works through phases ...
|
||||
|
||||
AI: 🤔 [TRANSITION DECISION]
|
||||
Confidence: 92%. Creating specs/PLAN DRAFT.md...
|
||||
```
|
||||
|
||||
**Session 2 - Documentation (New Chat):**
|
||||
|
||||
```
|
||||
User: [Paste or invoke Step 2 prompt]
|
||||
[Attach: specs/PLAN DRAFT.md]
|
||||
|
||||
AI: 📝 [DOCUMENTATION]
|
||||
Creating specs/task-api/overview.md...
|
||||
Creating specs/task-api/Phase 1.md...
|
||||
Creating specs/task-api/Phase 2.md...
|
||||
...
|
||||
```
|
||||
|
||||
**Session 3 - Implementation Phase 1 (New Chat):**
|
||||
|
||||
```
|
||||
User: [Paste or invoke Step 3 prompt]
|
||||
[Provide: specs/task-api/overview.md]
|
||||
|
||||
AI: ⚡ [PHASE 1: Project Setup]
|
||||
(Auto-detected Phase 1 as next uncompleted phase)
|
||||
Implementing tasks...
|
||||
✓ Phase 1 complete. Updated checkboxes in Phase 1.md and overview.md.
|
||||
```
|
||||
|
||||
**Session 4 - Implementation Phase 2 (New Chat):**
|
||||
|
||||
```
|
||||
User: [Paste or invoke Step 3 prompt]
|
||||
[Provide: specs/task-api/overview.md]
|
||||
|
||||
AI: ⚡ [PHASE 2: Database Models]
|
||||
(Auto-detected Phase 2 as next uncompleted phase)
|
||||
Implementing tasks...
|
||||
✓ Phase 2 complete. Updated checkboxes in Phase 2.md and overview.md.
|
||||
```
|
||||
|
||||
**Sessions 5-N - Continue Implementation (New Chat for each phase):**
|
||||
|
||||
```
|
||||
... repeat for each remaining phase ...
|
||||
```
|
||||
|
||||
**Final Session - Finalization (New Chat):**
|
||||
|
||||
```
|
||||
User: [Paste or invoke Step 4 prompt]
|
||||
[Provide: specs/task-api/overview.md]
|
||||
|
||||
AI: 🧹 [VALIDATION]
|
||||
Verifying implementation...
|
||||
|
||||
AI: 🧹 [SPEC CLEANUP]
|
||||
Moving to specs--completed/task-api/
|
||||
|
||||
Implementation complete!
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Progress Tracking
|
||||
|
||||
The checkbox system enables seamless progress tracking across multiple sessions:
|
||||
|
||||
**overview.md:**
|
||||
|
||||
```markdown
|
||||
## Phases
|
||||
|
||||
- [x] Phase 1: Project Setup
|
||||
- [x] Phase 2: Database Models
|
||||
- [ ] Phase 3: API Endpoints <- Next phase to implement
|
||||
- [ ] Phase 4: Authentication
|
||||
```
|
||||
|
||||
**Phase 3.md:**
|
||||
|
||||
```markdown
|
||||
## Tasks
|
||||
|
||||
- [x] Create routes file
|
||||
- [x] Implement GET /tasks
|
||||
- [ ] Implement POST /tasks <- Current task
|
||||
- [ ] Implement PUT /tasks/:id
|
||||
- [ ] Implement DELETE /tasks/:id
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Best Practices
|
||||
|
||||
1. **Start fresh conversations** - New chat for each step and each implementation phase
|
||||
2. **Always attach specs** - The AI needs the spec files to understand the current state
|
||||
3. **Don't skip planning** - The upfront investment prevents costly rework later
|
||||
4. **Confirm tech stack** - Ensure AI gets explicit approval before architecture design
|
||||
5. **One phase at a time** - Keeps conversations focused and manageable
|
||||
6. **Update checkboxes immediately** - Maintains accurate progress state
|
||||
7. **Review phase output** - Verify each phase before moving to the next
|
||||
8. **Keep spec files** - The completed folder serves as project documentation
|
||||
|
||||
---
|
||||
|
||||
## What to Attach at Each Step
|
||||
|
||||
| Step | Required Input |
|
||||
| ------------------ | ---------------------------------------------------- |
|
||||
| Step 1 (Plan) | None (describe your feature/project) |
|
||||
| Step 2 (Document) | `specs/PLAN DRAFT.md` or planning conversation |
|
||||
| Step 3 (Implement) | `specs/<feature>/overview.md` (auto-detects phase) |
|
||||
| Step 4 (Finalize) | `specs/<feature>/overview.md` |
|
||||
|
||||
---
|
||||
|
||||
## File Structure After Complete Implementation
|
||||
|
||||
```
|
||||
your-project/
|
||||
├── specs/
|
||||
│ └── another-feature/ # In-progress feature
|
||||
│ ├── overview.md
|
||||
│ └── Phase 1.md
|
||||
├── specs--completed/
|
||||
│ └── feature-name/
|
||||
│ ├── overview.md # Archived with completion summary
|
||||
│ ├── Phase 1.md # All checkboxes marked [x]
|
||||
│ ├── Phase 2.md
|
||||
│ └── ...
|
||||
├── your project files...
|
||||
└── README.md
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Customization
|
||||
|
||||
Feel free to modify these prompts to fit your workflow:
|
||||
|
||||
- **Add testing phases** - Uncomment/add testing requirements in Step 2
|
||||
- **Adjust confidence threshold** - Change the 90% threshold in Step 1
|
||||
- **Modify output structure** - Customize the specs folder organization
|
||||
- **Add code review steps** - Enhance Step 3 with additional review gates
|
||||
|
||||
---
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
**Slash commands/workflows not recognized:**
|
||||
|
||||
- Check if your project's `.gitignore` includes patterns like `.windsurf/`, `.cursor/`, `.continue/`, or `.agent/`
|
||||
- Many AI tools don't recognize workflows in gitignored directories
|
||||
- Solution: Use global installation by copying the directories to your home directory (e.g., `cp -r .windsurf ~/`)
|
||||
|
||||
**AI jumps ahead to implementation during planning:**
|
||||
|
||||
- The prompts explicitly forbid this, but if it happens, remind the AI: "Stay in planning mode. Do not write code yet."
|
||||
|
||||
**AI doesn't know what to implement:**
|
||||
|
||||
- Make sure you provided the path to `overview.md`
|
||||
- The AI will auto-detect the next phase and read the corresponding `Phase X.md` file
|
||||
|
||||
**Lost progress between sessions:**
|
||||
|
||||
- Check `overview.md` for phase status
|
||||
- Review individual phase files for task completion status
|
||||
|
||||
**AI not following spec exactly:**
|
||||
|
||||
- Reference the specific phase document and ask it to re-read the requirements
|
||||
|
||||
**Too many/few phases:**
|
||||
|
||||
- Adjust during Step 2 (Documentation) - phases should represent logical groupings of work
|
||||
|
||||
|
||||
|
||||
# Plan2Code
|
||||
|
||||
**A spec-driven workflow for AI coding agents.**
|
||||
|
||||
<img src="docs/banner.jpg" alt="banner" data="object-fit:contain;" style="max-width:1024px;">
|
||||
|
||||
You work through Plan2Code on a page in your browser. The dashboard lists every step as a card, and
|
||||
each step's questions, progress and sign-offs arrive on that same page while your agent does the
|
||||
work. What you decide still lands in your repo as plain files: an approved plan becomes phase
|
||||
documents, and the agent builds to them one phase at a time, so the next session, the next agent and
|
||||
the next engineer all start from the same specs.
|
||||
|
||||
One command opens it, every step is a card, and the terminal is always there if you prefer it.
|
||||
|
||||
Version 2.11.0 · MIT · 📖 [plan2code.jparkerweb.com](https://plan2code.jparkerweb.com)
|
||||
|
||||
---
|
||||
|
||||
## See it
|
||||
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="docs/screenshots/dashboard-dark.webp">
|
||||
<img src="docs/screenshots/dashboard-light.webp" alt="The Plan2Code dashboard for a project mid-build: a Set up card, then the steps in order, with the Implement card marked Suggested and reading Phase 3 of 4 is next.">
|
||||
</picture>
|
||||
|
||||
The dashboard, in a project halfway through a build. It suggests the next step for the spec you pick.
|
||||
|
||||
---
|
||||
|
||||
## Install and start
|
||||
|
||||
### Before you start
|
||||
|
||||
- **Node.js 18 or newer.** Check with `node --version`. No Node? Get it from [nodejs.org](https://nodejs.org/) (the LTS download), or run `winget install OpenJS.NodeJS.LTS` on Windows, `brew install node` on macOS, or use `nvm` on Linux. Then open a new terminal.
|
||||
- **Start from your project.** Open your terminal in the project you want to work on (`cd` into it) before you run anything. Plan2Code works on the folder you start it in.
|
||||
- **Ways in.** `plan2code` (Claude Code, Devin or Codex), or type `/plan2code` in your agent (`$plan2code` in Codex).
|
||||
- **No agent yet?** Install Claude Code, Codex or Devin first.
|
||||
|
||||
Installation needs network access and runs through the [skills CLI](https://skills.sh). To update, run `plan2code update` (or re-run the install command).
|
||||
|
||||
```bash
|
||||
npx --allow-git=all git+https://github.com/jparkerweb/plan2code.git
|
||||
```
|
||||
|
||||
This fetches the installer to a temp directory, builds the workflow as Agent Skills, delegates
|
||||
installation to `skills add`, and cleans up after itself. The installed skills work independently
|
||||
from then on.
|
||||
|
||||
**Back at your prompt with no output at all?** The installer always opens the menu below, so nothing
|
||||
means npm could not reach the repository and hid the reason. Run
|
||||
`git ls-remote https://github.com/jparkerweb/plan2code.git` to see it: usually the network, a proxy
|
||||
or the VPN.
|
||||
|
||||
The installer opens this menu (cloning and running `node install.js`, below, opens the same one):
|
||||
|
||||
```
|
||||
╔═════════════════════════════════════════════════════════╗
|
||||
║ INSTALL PLAN2CODE ║
|
||||
╠═════════════════════════════════════════════════════════╣
|
||||
║ I. INSTALL Install skills + the plan2code command ║
|
||||
║ U. UNINSTALL Remove everything Plan2Code installed ║
|
||||
║ A. ADVANCED Project install, dev tools, and more ║
|
||||
║ Q. QUIT Exit ║
|
||||
╚═════════════════════════════════════════════════════════╝
|
||||
```
|
||||
|
||||
### Start
|
||||
|
||||
1. `cd` into your project, then run `plan2code`. It starts Claude Code, Devin or Codex on the dashboard,
|
||||
and the dashboard opens in your browser.
|
||||
2. In a project without an `AGENTS.md`, pick **Set up this project** first: Plan and Quick task
|
||||
need it.
|
||||
3. Pick a card.
|
||||
|
||||
Already inside your agent? Type `/plan2code` instead (`$plan2code` in Codex).
|
||||
|
||||
<details>
|
||||
<summary>About the plan2code command</summary>
|
||||
|
||||
Install (`I`) adds `plan2code` as a global command (Advanced `A` → `D` adds just the command). Run it from any project and the Plan2Code
|
||||
dashboard opens right there, in **Claude Code**, **Devin** or **Codex**. With more than one installed it asks which and
|
||||
remembers your pick; `plan2code --cli claude`, `--cli devin` or `--cli codex` skips the question, and `--model <name>`
|
||||
chooses the model. It works in cmd, PowerShell, Git Bash, macOS and Linux shells, and needs the
|
||||
Claude Code, Devin or Codex CLI on your `PATH`. It starts the agent with permission prompts off
|
||||
(`--permission-mode bypassPermissions` in Claude Code, `--permission-mode bypass` in Devin, `--dangerously-bypass-approvals-and-sandbox` in Codex); run
|
||||
`claude /plan2code` yourself if you want prompts. The installer then offers a desktop shortcut (answer `y`),
|
||||
which opens a folder picker first. Uninstalling (`U`) removes both.
|
||||
</details>
|
||||
|
||||
**Supported tools:** every agent supported by the skills CLI, including Claude Code · Cursor ·
|
||||
GitHub Copilot · Windsurf · Codex · Continue · Codeium · Zed · Amp · OpenCode · Devin · Crush · Pi ·
|
||||
Gemini CLI · Cline · Roo · Kilo · Goose · Trae · Qwen Code.
|
||||
|
||||
The installer keeps one canonical copy of each skill under `~/.agents/skills/` and links it into
|
||||
agents that maintain their own directory. To update, run `plan2code update` (or re-run the install command).
|
||||
|
||||
Use the installer rather than calling `skills add` against the repository root: recursive discovery
|
||||
would also find maintainer-only skills under `.claude/skills/`. The installer targets `skills/`
|
||||
explicitly.
|
||||
|
||||
<details>
|
||||
<summary>Prefer to clone?</summary>
|
||||
|
||||
```bash
|
||||
git clone https://github.com/jparkerweb/plan2code.git
|
||||
cd plan2code
|
||||
node install.js
|
||||
|
||||
# Only if you plan to modify or contribute to Plan2Code itself
|
||||
npm install && npx husky
|
||||
```
|
||||
</details>
|
||||
|
||||
---
|
||||
|
||||
## A session on the page
|
||||
|
||||
**Answer the questions.** They arrive a few at a time, each option with its trade-off written beside
|
||||
it, and a progress bar says how far along you are.
|
||||
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="docs/screenshots/question-dark.webp">
|
||||
<img src="docs/screenshots/question-light.webp" alt="A Plan question card, How tasks are paged, with three options, the first marked Suggested, each with its trade-off underneath.">
|
||||
</picture>
|
||||
|
||||
**Watch the build.** Tasks tick off as they land, and the line beside Planny says what is being
|
||||
worked on right now.
|
||||
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="docs/screenshots/build-dark.webp">
|
||||
<img src="docs/screenshots/build-light.webp" alt="A phase of a task API being built: 5 of 11 done on the progress bar, and the phase's task list with the first five ticked.">
|
||||
</picture>
|
||||
|
||||
**Sign off.** Read the completion report, then approve the phase or ask for changes. In Implement,
|
||||
you can also have the code reviewed first; Implement + review has already done it.
|
||||
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="docs/screenshots/signoff-dark.webp">
|
||||
<img src="docs/screenshots/signoff-light.webp" alt="The Approve this phase card, with a button to read the completion report and three choices: Review the code first, Approve this phase, and I want changes.">
|
||||
</picture>
|
||||
|
||||
**Ask a quick question any time.** The Ask tab is a chat beside the cards, answered at the agent's
|
||||
next check-in, and it never holds up your answers.
|
||||
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="docs/screenshots/ask-dark.webp">
|
||||
<img src="docs/screenshots/ask-light.webp" alt="The Ask tab: the question Where are tasks paged? and Plan2Code's answer naming the file.">
|
||||
</picture>
|
||||
|
||||
There is more on the page when you need it. Notes on any question can carry screenshots and
|
||||
documents. The folder label in the bottom bar opens your workspace, where you add other folders
|
||||
as read-only context and point at them by `@name`. The **Notebook** in the top bar is a private pad of your own for the
|
||||
folder, in Markdown with pictures, that the agent never sees. The session meter in the top bar turns from green
|
||||
to red as a session grows long and suggests a fresh one. **Stop session** saves your place and gives
|
||||
you the command to carry on later, and **Back to the dashboard** takes you home to pick the next
|
||||
step in the same session.
|
||||
|
||||
---
|
||||
|
||||
## The workflow
|
||||
|
||||
```
|
||||
┌╴╴╴╴╴╴╴╴╴╴╴╴┐
|
||||
╎0 PATHFINDER╎ optional · for an idea too big or unclear to plan
|
||||
└╴╴╴╴╴╴┬╴╴╴╴╴┘
|
||||
▼
|
||||
┌────────────┐ ┌────────────┐ ┌────────────┐ ┌╴╴╴╴╴╴╴╴╴╴╴╴┐ ┌────────────┐
|
||||
│ 1 PLAN │─>│ 2 DOCUMENT │─>│3 IMPLEMENT │─>╎ REVIEW ╎─>│ 4 FINALIZE │
|
||||
│decide what │ │ draw it as │ │build to the│ ╎ optional ╎ │verify, sum,│
|
||||
│ to build │ │phase specs │ │ drawing │ ╎ any time ╎ │ archive │
|
||||
└────────────┘ └────────────┘ └────────────┘ └╴╴╴╴╴╴╴╴╴╴╴╴┘ └────────────┘
|
||||
short sessions: fresh when the meter turns red, and before a big step
|
||||
├◀─────────────── one feature, start to archive ──────────────────▶┤
|
||||
```
|
||||
|
||||
Each box is a card on the dashboard. Chaining a couple of small steps in one session is fine, but
|
||||
start a fresh session before a big plan or build step: planning context leaking into implementation
|
||||
is where most agent drift starts.
|
||||
|
||||
The dashboard's cards, and when each one lights up for the spec you pick:
|
||||
|
||||
| Card | What it is for | Lights up when |
|
||||
|------|----------------|----------------|
|
||||
| Set up this project | Reads your project and writes AGENTS.md, the guide every later step works from. | The project has no AGENTS.md yet |
|
||||
| Refresh AGENTS.md | Brings AGENTS.md and its notes up to date with what the project has learned lately. | The project has an AGENTS.md |
|
||||
| Pathfinder | A foggy idea becomes a clear list of decisions, settled one question at a time. | You start fresh, or the spec is still being explored |
|
||||
| Plan | Requirements, technical design and your approval: the shape of what gets built. | You start fresh, or the spec has a finished Pathfinder map, a drafted plan or a bug diagnosis |
|
||||
| Revise the plan | Requirements changed mid-build? Adjust the plan without starting over. | The spec is written up into phases and not fully built |
|
||||
| Document | The plan becomes a checklist of small tasks, grouped into phases, that a developer can just do. | The spec has a drafted plan |
|
||||
| Implement | Builds the next phase, task by task, with a report and your sign-off at the end. | The spec has phases with tasks still to build |
|
||||
| Implement + review | One phase built, then a careful review of the changes, then your sign-off. All in one run. | The spec has phases with tasks still to build |
|
||||
| Finalize | Checks the work, writes the summary, files the specs away and suggests the commit message. | Every task in the spec is done |
|
||||
| Quick task | Too small for the full process? A quick plan, then it just builds it. | Always (suggested when the spec is a diagnosed bug) |
|
||||
| Review | A second opinion on the changes. Problems ranked, and you pick what gets fixed. | Always |
|
||||
| Handoff | Pack this conversation into a document a fresh session can pick up cold. Any skill's **Stop with a handoff** writes one too, and the dashboard lists them to pick up. | Always |
|
||||
| Codebase X-ray | Explain how and why an area works, or find the rough spots worth fixing. | Always |
|
||||
| Diagnose a bug | Find a bug's cause and write it up, without fixing it. | Always |
|
||||
| Changelog | Checks the CHANGELOG version against the main branch and suggests entries for what is new. | Always |
|
||||
| Git | Branches, pull, push and commits on one board, asking before anything leaves your machine. | Always (offers to start a repository outside one) |
|
||||
|
||||
---
|
||||
|
||||
## The four rules that do most of the work
|
||||
|
||||
**1 · Keep each session short.**
|
||||
Chaining a couple of small skills on the dashboard is fine. Start a fresh console session when the session meter turns red, and always before a big planning or build step. The specs on disk carry everything between sessions.
|
||||
|
||||
**2 · No code until the plan hits 90% confidence.**
|
||||
Step 1 will not finalize below the threshold. Under it, the agent keeps asking and keeps reading your
|
||||
code — and writes every assumption down where you can argue with it.
|
||||
|
||||
**3 · Checkboxes are the state, not the chat.**
|
||||
Progress lives in the spec files. Any agent, any session, resumes cold from them.
|
||||
|
||||
**4 · Approve a phase to close it.**
|
||||
On the sign-off card, or by replying `approved` in the terminal. Nothing advances on a guess about
|
||||
what you meant.
|
||||
|
||||
---
|
||||
|
||||
## What lands in your repo
|
||||
|
||||
Each feature gets a folder under `specs/` (the plan, the overview and one file per phase), and Step 4
|
||||
moves it to `specs--completed/`. The layout and progress marks are on the
|
||||
[quick reference](QUICK-REFERENCE.md#file-structure).
|
||||
|
||||
Add `specs/` to your project's `.gitignore` (`plan2code-loop` adds it for you): it's your working
|
||||
drawing, not a deliverable. Share a folder deliberately with `git add -f` when you want to.
|
||||
|
||||
Step 2 marks which phases don't share files. Open a second agent on one of those, and the `[/]` marks
|
||||
keep the two out of each other's way.
|
||||
|
||||
---
|
||||
|
||||
## The six steps in detail
|
||||
|
||||
Each step is its own run, and the specs on disk are the only thing carried from one to the next.
|
||||
Chain a small one onto the last, or start a fresh session for a big one (rule 1).
|
||||
|
||||
### 0 · Pathfinder 🧭 (optional)
|
||||
|
||||
On the page: one question at a time with the options and their trade-offs, the map growing in its own
|
||||
tab, and a **Write a brief** button for a printable summary.
|
||||
|
||||
Some ideas are too big and unclear to plan: you can feel the shape of the work but you can't write
|
||||
it as requirements, so planning would just invent the answers. Pathfinder finds the *way* to the
|
||||
destination; Step 1 then walks it.
|
||||
|
||||
1. **Name the destination** — one or two lines fixing what this effort is finding its way to. Settled
|
||||
first, because it fixes scope. It also asks where the map should live: **local files** under
|
||||
gitignored `specs/` (private, solo — the default), or **GitHub Issues** (a map issue with one
|
||||
sub-issue per decision, native blocking, so your team can see and work the frontier in the tracker).
|
||||
2. **Chart the map** — a breadth-first grilling surfaces the open decisions. Anything you can phrase
|
||||
*sharply* becomes a question file; anything you can only sense stays listed as fog.
|
||||
3. **Clear the questions one at a time** — resolving one burns off the fog behind it, graduating
|
||||
whatever just became sharp into new questions. After each decision it offers a menu: take the next
|
||||
question here, or start fresh — recommended after about three, to keep the agent sharp.
|
||||
Ask for a **brief** at any point and you get a dated, plain-English summary of what has been
|
||||
decided, what is still open, and what is next — meeting minutes, with no jargon in them.
|
||||
4. **Hand off** — when nothing is left to decide, it writes a `PLAN-DRAFT` that
|
||||
`/plan2code-1-plan` resumes from at Phase 4, with requirements, context, and scope already
|
||||
answered.
|
||||
|
||||
**Question types:** `grill` (a decision only you can make — the default) · `research` (a fact gates
|
||||
it; background agents resolve these, several in parallel) · `sketch` (you need something concrete to
|
||||
react to) · `legwork` (manual work that has to happen before a decision is possible).
|
||||
|
||||
It never answers its own questions, and it **plans, it never builds.** When the urge to just build it
|
||||
arrives, the map is done. Skip Step 0 entirely when you already know what you're building.
|
||||
|
||||
**Out:** `specs/<feature>/pathfinder/map.md` + `questions/` (or a `pathfinder:map` issue and its
|
||||
sub-issues) → `PLAN-DRAFT-<date>.md`. The draft is always a local file — that is what Step 1 reads.
|
||||
|
||||
### 1 · Plan 🤔
|
||||
|
||||
On the page: questions in batches of up to three, the phase breakdown as a list you can reorder and
|
||||
edit, and a sign-off at each stage.
|
||||
|
||||
The agent works as a senior architect through seven phases, stopping for you after each: requirements
|
||||
analysis · system context (reading your actual codebase) · scope assessment (a large project saves and
|
||||
resumes in a fresh session) · tech stack (needs your explicit sign-off) · architecture design ·
|
||||
technical specification · transition decision.
|
||||
|
||||
It won't finalize below **90% confidence**, and every assumption it makes is written into the draft.
|
||||
|
||||
**In:** a description of the feature. **Out:** `PLAN-DRAFT-<date>.md` + `PLAN-CONVERSATION-<date>.md`
|
||||
|
||||
### 2 · Document 📝
|
||||
|
||||
On the page: a question only where the plan leaves something open, each phase file appearing as its
|
||||
own tab as it is written, and one sign-off at the end.
|
||||
|
||||
The plan becomes the drawing. One `overview.md` with the phase checklist, plus one file per phase of
|
||||
one-story-point tasks. Each phase is **self-contained** — an agent opening `phase-3.md` cold needs
|
||||
nothing else to build it. Unit and E2E tests are excluded unless you ask for them.
|
||||
|
||||
The overview also identifies the **parallel execution groups**: phases with no shared files or
|
||||
dependencies, safe to run in separate agents at once.
|
||||
|
||||
**In:** the `PLAN-DRAFT`. **Out:** `overview.md` + `phase-1…N.md`
|
||||
|
||||
### 3 · Implement ⚡
|
||||
|
||||
On the page: a progress bar and the phase's task list ticking over as tasks land, then the completion
|
||||
report and a sign-off card where you approve, ask for changes, or have the code reviewed first.
|
||||
|
||||
Point it at `overview.md` and it does the rest: finds the next unchecked phase, implements every task
|
||||
exactly as specified, ticks tasks off as they land, then reviews its own work against the spec and
|
||||
writes a completion summary.
|
||||
|
||||
One phase per conversation. It won't run tests unless the phase says to.
|
||||
|
||||
**In:** `specs/<feature>/overview.md`. **Out:** working code, and updated checkboxes.
|
||||
|
||||
Want a second pair of eyes before you sign off? `/plan2code-3-implement-review` builds the phase the
|
||||
same way, runs a focused review and the fixes you pick, and only then asks for approval.
|
||||
|
||||
### Review 🔬 — optional, any time
|
||||
|
||||
On the page: a few questions on scope, the findings as a report you can read in full, and a list
|
||||
where you tick what gets fixed.
|
||||
|
||||
An independent second opinion, not a rubber stamp. It figures out its own scope (conversation
|
||||
context, your instruction, or the git diff as a fallback), analyses across 11 dimensions, and ranks
|
||||
findings Critical / Warning / Suggestion. Every finding cites a file and a line, or it gets dropped —
|
||||
and the review pass is read-only. It fixes things only if you ask, and verifies each fix afterwards.
|
||||
|
||||
Spec-aware when `specs/` exists, and works fine without it. Most useful right after a planning or
|
||||
implementation step, but there's no wrong time to run it.
|
||||
|
||||
### 4 · Finalize 🧹
|
||||
|
||||
On the page: the task audit and the summary as reports, a list of the doc updates to approve, and a
|
||||
confirmation before anything is archived.
|
||||
|
||||
Validates every task against its phase spec, writes the summary and the list of files touched, flags
|
||||
the docs that drifted (`README`, `CHANGELOG`, `AGENTS.md`), then archives the whole spec folder —
|
||||
`pathfinder/` included — to `specs--completed/`. That folder is the record of *why* the code looks
|
||||
like this.
|
||||
|
||||
**In:** `specs/<feature>/overview.md`. **Out:** archived specs.
|
||||
|
||||
---
|
||||
|
||||
## Prefer the terminal?
|
||||
|
||||
Every skill also runs right in the terminal. Each one asks at the start whether you want the web
|
||||
console or the terminal; add `--web` to skip the question and go straight to the web console:
|
||||
`/plan2code-1-plan --web plan a REST API for tasks`.
|
||||
|
||||
| Command | Use it when |
|
||||
|---------|-------------|
|
||||
| `/plan2code` | Open the dashboard in the web console: every skill below as a card, launched on the page |
|
||||
| `/plan2code-0-pathfinder` | The idea is too big and unclear to plan. Charts it as decisions, clears them one at a time, hands a hot plan draft to Step 1 |
|
||||
| `/plan2code-1-plan` | Starting a feature. Full requirements → architecture pass |
|
||||
| `/plan2code-2-document` | Planning is done. Turn the plan into phase specs |
|
||||
| `/plan2code-3-implement` | Build the next phase (one per conversation) |
|
||||
| `/plan2code-3-implement-review` | Build the next phase and review it before you approve it (instead of `/plan2code-3-implement`) |
|
||||
| `/plan2code-review` | Independent second opinion on local changes, then optional fixes |
|
||||
| `/plan2code-4-finalize` | All phases done. Validate, summarize, archive |
|
||||
| `/plan2code-init` | Generate this repo's `AGENTS.md` so every agent starts informed |
|
||||
| `/plan2code-init-update` | Fold what you learned this session back into `AGENTS.md` |
|
||||
| `/plan2code-quick-task` | A small change that doesn't warrant the full sequence |
|
||||
| `/plan2code-1b-revise-plan` | Requirements moved mid-build. Revise the specs, not the code |
|
||||
| `/plan2code-handoff` | Compact this conversation into a doc the next one resumes from, saved in `~/.plan2code/handoffs/` and listed on the dashboard to pick up |
|
||||
| `/plan2code-xray` | Explain how and why an area of the code works (citing files, commits and PRs), or rank the rough spots worth fixing into a brief for Pathfinder or Plan; never edits code |
|
||||
| `/plan2code-diagnose` | Find a bug's cause and write it up as `specs/<bug-name>/DIAGNOSIS-<date>.md` without fixing it, then offer `/plan2code-quick-task` to fix it, or `/plan2code-1-plan` when the fix is big |
|
||||
| `/plan2code-changelog` | Check the CHANGELOG version against the default branch, suggest entries for new work you can edit, keep `package.json` aligned, then hand off to Git to commit |
|
||||
| `/plan2code-git` | Branches, pull, push and commits on one board (or plain instructions in the terminal); asks before every push, publish and delete |
|
||||
|
||||
---
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
**The skills aren't recognised.** Re-run the installer and restart your AI tool. Confirm the global
|
||||
install with `npx skills list -g`. For a project install, check the generated directories aren't
|
||||
gitignored.
|
||||
|
||||
**Your tool doesn't read Agent Skills.** Since v2.2.0, Plan2Code ships only as skills. If your tool
|
||||
has no skill support, paste the relevant `src/plan2code-*.md` manually or point it at the installed
|
||||
copy under `~/.agents/skills/`.
|
||||
|
||||
**The agent starts coding during planning.** The prompts forbid it, but models drift. Say: "Stay in
|
||||
planning mode. Do not write code yet."
|
||||
|
||||
**The agent doesn't know what to implement.** Give it the path to `overview.md` — it reads the phase
|
||||
file itself from there.
|
||||
|
||||
**You lost track between sessions.** `overview.md` has the phase status; the phase files have the
|
||||
task status. That's the whole state.
|
||||
|
||||
**The agent isn't following the spec.** Point at the specific phase document and tell it to re-read
|
||||
the requirements.
|
||||
|
||||
**Too many or too few phases.** Fix it in Step 2 — a phase should be a logical grouping of work, not
|
||||
a fixed size.
|
||||
|
||||
**The agent runs on another machine, or over SSH.** The page is served on `127.0.0.1` of the machine
|
||||
the agent runs on, so your browser can only reach it there. A forwarded port often works; otherwise
|
||||
work in the terminal, which loses nothing.
|
||||
|
||||
**Web console problems** (lost contact, a closed tab, a dead link): see
|
||||
[.readme/web-console.md](.readme/web-console.md#troubleshooting).
|
||||
|
||||
---
|
||||
|
||||
## Customizing
|
||||
|
||||
The prompts are yours to edit. Common changes: add testing requirements in Step 2, move the 90%
|
||||
confidence threshold in Step 1, restructure the `specs/` layout, or add review gates to Step 3.
|
||||
Source files live in `src/`; run `npm run build:skills`, then re-run `node install.js` to push your
|
||||
edits out through the skills CLI.
|
||||
|
||||
---
|
||||
|
||||
## Dive deeper
|
||||
|
||||
Core reference:
|
||||
|
||||
- **[.readme/web-console.md](.readme/web-console.md)**: the full guide to the web console, from the dashboard to the last sign-off, including the private Notebook in the top bar
|
||||
- **[QUICK-REFERENCE.md](QUICK-REFERENCE.md)** — the one-page card: commands, inputs, outputs, decision tree
|
||||
- **[.readme/walkthrough.md](.readme/walkthrough.md)** — one feature from a sentence to archived specs, session by session
|
||||
- **[AGENTS.md](AGENTS.md)** — architecture and contributor guide for this repo
|
||||
- **[CHANGELOG.md](CHANGELOG.md)** — what changed, and why
|
||||
|
||||
Optional tooling — none of it is required to use the workflow:
|
||||
|
||||
- **[.readme/autonomous-loop.md](.readme/autonomous-loop.md)** — `plan2code-loop`, a hands-off alternative to Step 3
|
||||
- **[.readme/status-line.md](.readme/status-line.md)** — three-line Claude Code status bar: model, context, quota, diff
|
||||
- **[.readme/metrics.md](.readme/metrics.md)** — `plan2code-metrics`, measuring and improving the prompts themselves
|
||||
- **[.readme/test-bot.md](.readme/test-bot.md)** — `plan2code-bot`, maintainer harness that runs the whole workflow unattended
|
||||
|
After Width: | Height: | Size: 3.1 KiB |
|
After Width: | Height: | Size: 71 KiB |
|
Before Width: | Height: | Size: 185 KiB |
|
Before Width: | Height: | Size: 24 KiB After Width: | Height: | Size: 2.6 KiB |
|
Before Width: | Height: | Size: 2.4 KiB After Width: | Height: | Size: 884 B |
@@ -0,0 +1,7 @@
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 32 32" role="img" aria-label="Plan2Code">
|
||||
<rect x="6" y="2.6" width="20" height="25.4" rx="4.4" fill="#eef3fa" stroke="#3b332c" stroke-width="2.2" />
|
||||
<rect x="9.6" y="27.6" width="4.8" height="2.6" rx="1.3" fill="#3b332c" />
|
||||
<rect x="17.6" y="27.6" width="4.8" height="2.6" rx="1.3" fill="#3b332c" />
|
||||
<path d="M16 8.8 L17.41 12.26 L21.14 12.53 L18.28 14.94 L19.17 18.57 L16 16.6 L12.83 18.57 L13.72 14.94 L10.86 12.53 L14.59 12.26 Z" fill="#2455a4" />
|
||||
<path d="M12.2 20.6 Q16 24.2 19.8 20.6" fill="none" stroke="#3b332c" stroke-width="1.8" stroke-linecap="round" />
|
||||
</svg>
|
||||
|
After Width: | Height: | Size: 636 B |
|
Before Width: | Height: | Size: 46 KiB |
|
Before Width: | Height: | Size: 95 KiB |
|
After Width: | Height: | Size: 99 KiB |
|
After Width: | Height: | Size: 107 KiB |
|
After Width: | Height: | Size: 110 KiB |
|
After Width: | Height: | Size: 114 KiB |
|
After Width: | Height: | Size: 89 KiB |
|
After Width: | Height: | Size: 97 KiB |
|
After Width: | Height: | Size: 109 KiB |
|
After Width: | Height: | Size: 119 KiB |
|
After Width: | Height: | Size: 115 KiB |
|
After Width: | Height: | Size: 122 KiB |
|
After Width: | Height: | Size: 97 KiB |
|
After Width: | Height: | Size: 103 KiB |
|
After Width: | Height: | Size: 73 KiB |
|
After Width: | Height: | Size: 78 KiB |
|
After Width: | Height: | Size: 62 KiB |
|
After Width: | Height: | Size: 67 KiB |
|
After Width: | Height: | Size: 106 KiB |
|
After Width: | Height: | Size: 117 KiB |
|
After Width: | Height: | Size: 96 KiB |
|
After Width: | Height: | Size: 104 KiB |
@@ -0,0 +1,17 @@
|
||||
{
|
||||
"name": "plan2code",
|
||||
"version": "2.11.0",
|
||||
"private": true,
|
||||
"bin": {
|
||||
"plan2code-install": "./install.js"
|
||||
},
|
||||
"scripts": {
|
||||
"prepare": "husky",
|
||||
"build:skills": "node install.js --build-skills",
|
||||
"test": "node scripts/validate-char-count.js && node install.js --build-skills && node scripts/parse-check.mjs && node scripts/check-skill-table.mjs && node --test scripts/test-script-git.mjs scripts/test-git-repo.mjs scripts/test-skill-scripts.mjs scripts/test-script-changelog.mjs scripts/test-web-console-git.mjs scripts/test-web-console-git-board.mjs scripts/test-web-console-chat.mjs scripts/test-web-console-subagents.mjs scripts/test-web-console-speed.mjs scripts/test-web-console-qa.mjs scripts/test-web-console-concurrency.mjs scripts/test-web-console-workspace.mjs scripts/test-web-console-lifecycle.mjs scripts/test-web-console-chat-stress.mjs scripts/test-web-console-server.mjs scripts/test-web-console-session.mjs scripts/test-web-console-logic.mjs scripts/test-web-console-skills.mjs scripts/test-web-console-spec-states.mjs scripts/test-web-console-state.mjs scripts/test-web-console-shape.mjs scripts/test-script-pathfinder.mjs scripts/test-launcher.mjs scripts/test-web-console-source.mjs scripts/test-web-console-hardening.mjs scripts/test-web-console-handoffs.mjs scripts/test-web-console-notepad.mjs scripts/test-script-xray.mjs scripts/test-script-finalize.mjs scripts/test-getting-started.mjs scripts/test-install-update.mjs scripts/test-browser-helper.mjs scripts/test-web-console-page-cards.mjs scripts/test-web-console-page-dashboard.mjs scripts/test-web-console-page-session.mjs scripts/test-web-console-page-ask.mjs scripts/test-web-console-page-workspace.mjs scripts/test-web-console-page-help.mjs scripts/test-web-console-page-prefs.mjs scripts/test-web-console-page-git.mjs scripts/test-web-console-page-notepad.mjs"
|
||||
},
|
||||
"devDependencies": {
|
||||
"husky": "^9.0.0",
|
||||
"playwright-core": "1.64.1"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,49 @@
|
||||
# Changelog
|
||||
|
||||
## 1.1.0
|
||||
|
||||
### Resume support
|
||||
- Add `--resume` flag to continue incomplete runs from saved state
|
||||
- Skip previously succeeded steps when resuming (init, plan, document, implement, finalize)
|
||||
- Restore idea name, description, project directory, and implement pass counter from state
|
||||
- Auto-detect state files in current directory (enhancement mode) or subdirectories (new-project mode)
|
||||
- Delete state file automatically after a fully successful run
|
||||
- Preserve state file on failure for later resume
|
||||
- Add `deleteState()` and `findExistingState()` utilities to bot-state module
|
||||
- Add bot-state unit tests (saveState, loadState, deleteState, findExistingState)
|
||||
|
||||
### Idea generation improvements
|
||||
- Expand idea categories from binary CLI/web-app coin flip to 12 diverse categories (games, dashboards, browser extensions, desktop utilities, etc.)
|
||||
- Add guidance to avoid defaulting to developer-centric tools (git analyzers, code formatters)
|
||||
- Strengthen `--idea` seed clause so the LLM stays aligned with the user's theme instead of ignoring it
|
||||
- Update system prompt to encourage creative, cross-domain ideas
|
||||
|
||||
### Init step overhaul (new projects)
|
||||
- Init now creates a minimal AGENTS.md stub (name, description, status) instead of running the full `/plan2code-init` skill
|
||||
- Prevents hallucinated architecture, commands, and `.agents-docs/` files before the plan step runs
|
||||
- Init evaluation criteria updated to reward minimalism and penalize premature detail
|
||||
|
||||
### Implement step overhaul
|
||||
- Implement step now works directly with Read/Write/Edit/Glob/Grep tools instead of delegating to Skill sub-session
|
||||
- Inlined step-by-step process: find specs, pick phase, implement tasks, mark checkboxes
|
||||
- Fixes issue where Skill sub-sessions did all work invisibly, causing zero tool observations
|
||||
|
||||
### Observation tracking fix
|
||||
- Capture `tool_use` blocks from the assistant message stream in session-runner as a fallback when `canUseTool` callback doesn't fire
|
||||
- Add deduplication in ObservationCollector to prevent double-counting from both sources
|
||||
- Fixes all steps reporting 0 tools used / 0 files created in BOT-NOTES and evaluations
|
||||
|
||||
### Evaluator improvements
|
||||
- Increase evaluator `maxTurns` from 3 to 30 so it has room for tool calls before producing the scored response
|
||||
- Add warning log when evaluation parser can't find SCORE in output (was silently defaulting to 50)
|
||||
|
||||
## 1.0.0
|
||||
|
||||
- Initial release
|
||||
- Two auto-detected modes: new-project and enhancement
|
||||
- `--idea` flag to seed the idea generator
|
||||
- Full workflow execution: init → plan → document → implement → finalize
|
||||
- Artifact validation after each step
|
||||
- State persistence to `.plan2code-bot-state.json`
|
||||
- Auto-responder for autonomous Claude Agent SDK sessions
|
||||
- Bot-friendly skill installation (strips `disable-model-invocation`)
|
||||
@@ -0,0 +1,234 @@
|
||||
# LLM-as-Judge Evaluation System
|
||||
|
||||
## Overview
|
||||
|
||||
The plan2code-bot now includes an **always-on LLM-as-judge evaluation system** that transforms it from a "yes-man" into an authentic QA agent. This provides realistic quality signals for `plan2code-metrics` to analyze and drive recursive self-improvement.
|
||||
|
||||
## Key Features
|
||||
|
||||
### 1. Intelligent Decision Making (Real-Time)
|
||||
|
||||
**What:** During execution, when `AskUserQuestion` is called, the bot uses an LLM to make thoughtful decisions based on current observations.
|
||||
|
||||
**How it works:**
|
||||
- Collects observations up to the current point (tools used, files created, errors)
|
||||
- Queries LLM with context: "Given what you've seen, should you approve this plan?"
|
||||
- LLM inspects current artifacts using Read/Glob/Grep
|
||||
- Returns evidence-based answer with reasoning
|
||||
- All decisions are recorded for metrics analysis
|
||||
|
||||
**Example:**
|
||||
```
|
||||
Question: "Approve this plan?"
|
||||
Observations: Created PLAN-DRAFT.md, 3 phases, 42s duration, no errors
|
||||
LLM reads PLAN-DRAFT.md, evaluates quality
|
||||
LLM decides: "Yes, approve - phases are well-scoped and realistic"
|
||||
```
|
||||
|
||||
### 2. Post-Step Evaluation
|
||||
|
||||
**What:** After each step completes, the bot evaluates quality using step-specific criteria.
|
||||
|
||||
**How it works:**
|
||||
- Collects complete execution observations
|
||||
- Queries LLM with evaluation criteria for the step
|
||||
- LLM inspects final artifacts
|
||||
- Returns structured evaluation (score, strengths, weaknesses, suggestions)
|
||||
- Writes `specs/<feature>/BOT-EVALUATION.md` and `specs/<feature>/BOT-NOTES.md` (falls back to project root if no spec folder exists yet, e.g. during `init`)
|
||||
|
||||
**Example output:**
|
||||
```markdown
|
||||
# Evaluation: plan Step
|
||||
|
||||
**Score:** 78/100
|
||||
|
||||
## Strengths
|
||||
- Clear phase breakdown with realistic scope
|
||||
- Tech stack choices appropriate
|
||||
|
||||
## Weaknesses
|
||||
- Phase 3 description too vague
|
||||
- No testing strategy mentioned
|
||||
|
||||
## Suggestions
|
||||
- Expand Phase 3 with concrete tasks
|
||||
- Add explicit testing phase
|
||||
```
|
||||
|
||||
### 3. Quality Gate
|
||||
|
||||
**What:** Before finalize, checks that average quality score is acceptable.
|
||||
|
||||
**How it works:**
|
||||
- Calculates average score across all evaluated steps
|
||||
- If average < 60, blocks finalization
|
||||
- Displays clear message about quality issues
|
||||
- User must review `specs/<feature>/BOT-EVALUATION.md` and fix problems
|
||||
|
||||
## Files Created
|
||||
|
||||
### New Files
|
||||
|
||||
1. **`src/observation-collector.ts`**
|
||||
- Tracks execution details (tools, files, messages, errors, questions)
|
||||
- Provides snapshots for real-time decisions
|
||||
- Captures complete history for evaluation
|
||||
|
||||
2. **`src/intelligent-responder.ts`**
|
||||
- Replaces hardcoded auto-responder
|
||||
- Uses LLM to answer AskUserQuestion prompts
|
||||
- Provides reasoning for all decisions
|
||||
- Falls back gracefully if LLM unavailable
|
||||
|
||||
3. **`src/prompts/evaluation-criteria.ts`**
|
||||
- Step-specific evaluation criteria (init, plan, document, implement, finalize)
|
||||
- Quality checks, common pitfalls, scoring guidance
|
||||
- Emphasizes honest scoring (most work should score 70-85)
|
||||
|
||||
4. **`src/evaluator.ts`**
|
||||
- Post-step evaluation using LLM-as-judge
|
||||
- Queries LLM with observations and criteria
|
||||
- Parses structured evaluation output
|
||||
- Writes `specs/<feature>/BOT-EVALUATION.md` and `specs/<feature>/BOT-NOTES.md`
|
||||
|
||||
### Modified Files
|
||||
|
||||
1. **`src/types.ts`**
|
||||
- Added interfaces: `ToolObservation`, `QuestionContext`, `ExecutionObservation`, `EvaluationResult`
|
||||
- Extended `StepResult` with `evaluation` and `observations` fields
|
||||
|
||||
2. **`src/session-runner.ts`**
|
||||
- Added `collector` parameter to `SessionOptions`
|
||||
- Returns `observations` in `SessionResult`
|
||||
- Records all messages for observation tracking
|
||||
- Uses intelligent responder instead of auto-responder
|
||||
|
||||
3. **`src/cli.ts`**
|
||||
- Creates `ObservationCollector` for each step
|
||||
- Always runs evaluation after successful steps
|
||||
- Displays scores with color coding (green/yellow/red)
|
||||
- Implements quality gate before finalize
|
||||
- Shows evaluation summary in step output
|
||||
|
||||
4. **`src/bin/plan2code-bot.ts`**
|
||||
- Updated help text to mention LLM-as-judge evaluation
|
||||
- No new CLI flags (evaluation is always on)
|
||||
|
||||
### Deleted Files
|
||||
|
||||
1. **`src/auto-responder.ts`** - Replaced by intelligent-responder.ts
|
||||
2. **`src/auto-responder.test.ts`** - No longer needed
|
||||
|
||||
## Output Files (Created During Execution)
|
||||
|
||||
Both files are written to `specs/<feature>/` so they stay co-located with the feature they describe. If no spec folder exists yet (e.g. during `init`), they fall back to the project root.
|
||||
|
||||
### BOT-EVALUATION.md
|
||||
|
||||
Contains evaluation results for each step:
|
||||
- Score (0-100)
|
||||
- Strengths identified
|
||||
- Weaknesses found
|
||||
- Suggestions for improvement
|
||||
- Critical issues (if any)
|
||||
- Full reasoning from LLM
|
||||
|
||||
### BOT-NOTES.md
|
||||
|
||||
Contains execution observations:
|
||||
- Duration, tool counts, file changes
|
||||
- Questions asked and LLM reasoning for answers
|
||||
- Tool usage timeline
|
||||
- Files created/modified
|
||||
- Assistant output summary
|
||||
|
||||
## Data Structure for Metrics
|
||||
|
||||
All evaluation data is structured in `StepResult`:
|
||||
|
||||
```typescript
|
||||
{
|
||||
step: 'plan',
|
||||
success: true,
|
||||
duration: 42000,
|
||||
evaluation: {
|
||||
score: 78,
|
||||
strengths: ["Clear phases", "Realistic scope"],
|
||||
weaknesses: ["Phase 3 too vague"],
|
||||
suggestions: ["Add specific tasks to Phase 3"],
|
||||
criticalIssues: [],
|
||||
reasoning: "...",
|
||||
timestamp: 1234567890,
|
||||
evaluatorModel: 'claude-sonnet-4-5'
|
||||
},
|
||||
observations: {
|
||||
tools: [{ toolName, input, output, timestamp }, ...],
|
||||
questionsAsked: [
|
||||
{
|
||||
question: "Approve plan?",
|
||||
selectedAnswer: "Yes, approve",
|
||||
llmReasoning: "Phases are well-scoped...",
|
||||
timestamp: 1234567890
|
||||
}
|
||||
],
|
||||
filesCreated: [...],
|
||||
filesModified: [...],
|
||||
errors: []
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Benefits for Recursive Improvement
|
||||
|
||||
1. **Authentic Signals:** Real quality scores identify actual problem areas
|
||||
2. **Detailed Context:** Observations + reasoning explain WHY failures happen
|
||||
3. **Correlation Analysis:** Link patterns (tool usage, duration, errors) to quality
|
||||
4. **Continuous Loop:** Better metrics → improved workflows → higher scores → repeat
|
||||
|
||||
## Usage
|
||||
|
||||
No special flags needed - evaluation is always on:
|
||||
|
||||
```bash
|
||||
# New project
|
||||
plan2code-bot --idea "todo app"
|
||||
|
||||
# Enhancement
|
||||
cd my-project && plan2code-bot
|
||||
|
||||
# Resume with evaluation data preserved
|
||||
plan2code-bot --resume
|
||||
```
|
||||
|
||||
## Verification
|
||||
|
||||
After running the bot, check:
|
||||
|
||||
1. **`specs/<feature>/BOT-EVALUATION.md`** - Should show realistic scores (not all 100s)
|
||||
2. **`specs/<feature>/BOT-NOTES.md`** - Should show LLM reasoning for decisions
|
||||
3. **Console output** - Should display color-coded scores after each step
|
||||
4. **State file** (`.plan2code-bot-state.json`) - Should include evaluation data
|
||||
|
||||
## Trade-offs
|
||||
|
||||
### Latency
|
||||
- Adds ~2-3s per AskUserQuestion call (~15-20s total per run)
|
||||
- Worth it for authentic evaluation
|
||||
|
||||
### Token Cost
|
||||
- ~20-26K tokens per run (~$0.60 with Opus 4.6)
|
||||
- Investment pays off through metrics-driven improvement
|
||||
|
||||
### Determinism
|
||||
- LLM decisions vary between runs (non-deterministic)
|
||||
- Realistic - humans vary too
|
||||
- Metrics average over many runs
|
||||
|
||||
## Future Enhancements
|
||||
|
||||
Potential improvements:
|
||||
- Model selection per step (use Haiku for simple decisions)
|
||||
- Configurable quality gate threshold
|
||||
- Historical score tracking across runs
|
||||
- Comparison with previous evaluations
|
||||
- More sophisticated scoring (weighted by step importance)
|
||||
@@ -0,0 +1,111 @@
|
||||
# plan2code-bot
|
||||
|
||||
Autonomous workflow test runner for plan2code. Uses the Claude Agent SDK to simulate a human running through the entire plan2code workflow (init, plan, document, implement, finalize) end-to-end.
|
||||
|
||||
## Two Modes (Auto-Detected)
|
||||
|
||||
1. **New Project Mode** — No `AGENTS.md` in cwd: generates an app idea, creates a subdirectory, writes IDEA.md, runs init, then all 4 steps.
|
||||
2. **Enhancement Mode** — `AGENTS.md` exists in cwd: scans the existing codebase and proposes a realistic enhancement, writes IDEA.md, then runs plan through finalize.
|
||||
|
||||
## Installation
|
||||
|
||||
From the plan2code root:
|
||||
|
||||
```bash
|
||||
node install.js
|
||||
# Select A > B to install the bot only, or A > E to install everything
|
||||
```
|
||||
|
||||
Or manually:
|
||||
|
||||
```bash
|
||||
cd plan2code-bot
|
||||
npm install
|
||||
npm run build
|
||||
npm link
|
||||
```
|
||||
|
||||
## Usage
|
||||
|
||||
```bash
|
||||
# New project mode (run from an empty directory)
|
||||
mkdir /tmp/test-bot && cd /tmp/test-bot
|
||||
plan2code-bot
|
||||
|
||||
# Enhancement mode (run from an existing project with AGENTS.md)
|
||||
cd my-project
|
||||
plan2code-bot
|
||||
|
||||
# Seed the idea generator with a specific concept
|
||||
plan2code-bot --idea "web app that displays the current weather as vector images"
|
||||
|
||||
# Resume a previous incomplete run
|
||||
plan2code-bot --resume
|
||||
```
|
||||
|
||||
### `--idea`
|
||||
|
||||
Pass a quoted string after `--idea` to seed the idea generator with a specific concept. The AI will use it as inspiration rather than generating a completely random idea. Wrap the value in double quotes so the shell treats it as a single argument.
|
||||
|
||||
```bash
|
||||
# Specific app concept
|
||||
plan2code-bot --idea "web app that displays the current weather as vector images"
|
||||
|
||||
# Short keyword to nudge the category
|
||||
plan2code-bot --idea "markdown editor"
|
||||
|
||||
# Detailed constraint
|
||||
plan2code-bot --idea "CLI tool that converts CSV files to SQLite databases with type inference"
|
||||
|
||||
# Works in enhancement mode too — guides what kind of enhancement to propose
|
||||
cd my-existing-project
|
||||
plan2code-bot --idea "add dark mode support"
|
||||
```
|
||||
|
||||
Without `--idea`, the bot picks a random category (CLI tool or web app) and invents something on its own.
|
||||
|
||||
### `--resume`
|
||||
|
||||
Resume a previous incomplete run. The bot searches for a `.plan2code-bot-state.json` file in the current directory (enhancement mode) or in immediate subdirectories (new-project mode). If found, it restores the idea, config, and progress — skipping steps that already succeeded and continuing from where it left off.
|
||||
|
||||
```bash
|
||||
# A run failed at the implement step — resume it
|
||||
plan2code-bot --resume
|
||||
|
||||
# Can combine with --idea (idea is ignored when resuming since it's restored from state)
|
||||
plan2code-bot --resume --idea "ignored when state exists"
|
||||
```
|
||||
|
||||
If no state file is found, the bot starts a fresh run.
|
||||
|
||||
## How It Works
|
||||
|
||||
1. Detects mode based on presence of `AGENTS.md`
|
||||
2. Generates an idea (new app or enhancement) via Claude, optionally guided by `--idea` seed
|
||||
3. Writes `IDEA.md` to the project directory
|
||||
4. Installs bot-friendly copies of plan2code skills (strips `disable-model-invocation` so sessions can invoke them)
|
||||
5. Runs each workflow step as a separate Claude Agent SDK session:
|
||||
- **init** — generates `AGENTS.md` (new-project mode only)
|
||||
- **plan** — creates plan draft in `specs/<feature>/`
|
||||
- **document** — produces `overview.md` and `phase-*.md` files
|
||||
- **implement** — loops until all phases are complete (max 10 passes)
|
||||
- **finalize** — validates and archives to `specs--completed/`
|
||||
6. Validates expected artifacts after each step (aborts on missing artifacts)
|
||||
7. Moves `IDEA.md` into `specs/<feature>/` after the plan step so it stays with its feature
|
||||
8. Auto-responds to `AskUserQuestion` prompts (approvals, testing gates, name questions)
|
||||
9. Saves state to `.plan2code-bot-state.json` after each step
|
||||
|
||||
## State File
|
||||
|
||||
After each step, the bot saves its state to `.plan2code-bot-state.json` in the project directory. This includes the config, all step results, and progress tracking.
|
||||
|
||||
- **On full success** — the state file is automatically deleted (clean finish)
|
||||
- **On failure/incomplete** — the state file is preserved so you can `--resume` later
|
||||
|
||||
## Development
|
||||
|
||||
```bash
|
||||
npm run build # Build with tsup
|
||||
npm run dev # Watch mode
|
||||
npm test # Run tests (vitest)
|
||||
```
|
||||
@@ -0,0 +1,36 @@
|
||||
{
|
||||
"name": "plan2code-bot",
|
||||
"version": "1.1.0",
|
||||
"description": "Plan2Code Bot - Autonomous workflow runner for testing plan2code end-to-end",
|
||||
"type": "module",
|
||||
"main": "dist/index.js",
|
||||
"bin": {
|
||||
"plan2code-bot": "./dist/bin/plan2code-bot.js"
|
||||
},
|
||||
"files": [
|
||||
"dist"
|
||||
],
|
||||
"engines": {
|
||||
"node": ">=18.0.0"
|
||||
},
|
||||
"scripts": {
|
||||
"build": "tsup",
|
||||
"dev": "tsup --watch",
|
||||
"start": "node dist/bin/plan2code-bot.js",
|
||||
"test": "vitest run",
|
||||
"prepublishOnly": "npm run build"
|
||||
},
|
||||
"dependencies": {
|
||||
"@anthropic-ai/claude-agent-sdk": "^0.2.63",
|
||||
"chalk": "^5.6.2",
|
||||
"fs-extra": "^11.3.3",
|
||||
"ora": "^9.0.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@types/fs-extra": "^11.0.4",
|
||||
"@types/node": "^25.0.3",
|
||||
"tsup": "^8.5.1",
|
||||
"typescript": "^5.9.3",
|
||||
"vitest": "^4.0.18"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,116 @@
|
||||
import { runCLI } from '../cli.js';
|
||||
|
||||
function showHelp(): void {
|
||||
console.log(`
|
||||
+----------------------------------------------------------------+
|
||||
— PLAN2CODEDE-BOT —
|
||||
—----------------------------------------------------------------—
|
||||
— Autonomous workflow test runner foplan2codede —
|
||||
— Features LLM-as-judge for honest quality evaluation —
|
||||
+----------------------------------------------------------------+
|
||||
|
||||
Usage:
|
||||
plan2code-bot [options]
|
||||
|
||||
Options:
|
||||
--help Show this help message
|
||||
--idea <string> Seed the idea generator with a specific concept
|
||||
Example: --idea "web app for weather"
|
||||
Example: --idea="CLI tool for CSV conversion"
|
||||
--resume Resume a previous incomplete run
|
||||
|
||||
Modes:
|
||||
— New Project Mode - Run from empty directory
|
||||
The bot generates an app idea, creates a subdirectory, writes
|
||||
IDEA.md, runs init, then all 4 workflow steps.
|
||||
|
||||
— Enhancement Mode - Run from directory with AGENTS.md
|
||||
The bot scans the existing codebase, proposes an enhancement,
|
||||
writes IDEA.md, then runs plan through finalize.
|
||||
|
||||
Evaluation:
|
||||
The bot acts as an authentic QA agent, using LLM-based decision
|
||||
making during execution and providing honest quality assessments
|
||||
after each step. Results are written to specs/<feature>/BOT-EVALUATION.md
|
||||
and specs/<feature>/BOT-NOTES.md for metrics analysis.
|
||||
|
||||
Examples:
|
||||
# New project (from empty directory)
|
||||
plan2code-bot
|
||||
|
||||
# Enhancement (from existing project)
|
||||
cd my-project && plan2code-bot
|
||||
|
||||
# With specific idea
|
||||
plan2code-bot --idea "markdown editor with live preview"
|
||||
|
||||
# Resume incomplete run
|
||||
plan2code-bot --resume
|
||||
|
||||
Documentation:
|
||||
https://github.com/jparkerweb/plan2code
|
||||
`);
|
||||
}
|
||||
|
||||
function stripQuotes(str: string): string {
|
||||
// Remove surrounding quotes if present (both single and double)
|
||||
if ((str.startsWith('"') && str.endsWith('"')) ||
|
||||
(str.startsWith("'") && str.endsWith("'"))) {
|
||||
return str.slice(1, -1);
|
||||
}
|
||||
return str;
|
||||
}
|
||||
|
||||
function parseArgs(): { idea?: string; resume?: boolean; help?: boolean } {
|
||||
const args = process.argv.slice(2);
|
||||
|
||||
// Check for --help
|
||||
if (args.includes('--help') || args.includes('-h')) {
|
||||
return { help: true };
|
||||
}
|
||||
|
||||
// Parse --idea (supports both --idea="value" and --idea "value")
|
||||
let idea: string | undefined;
|
||||
for (let i = 0; i < args.length; i++) {
|
||||
const arg = args[i];
|
||||
|
||||
// Format: --idea="value"
|
||||
if (arg.startsWith('--idea=')) {
|
||||
idea = stripQuotes(arg.substring('--idea='.length));
|
||||
break;
|
||||
}
|
||||
|
||||
// Format: --idea "value"
|
||||
if (arg === '--idea' && i + 1 < args.length) {
|
||||
idea = stripQuotes(args[i + 1]);
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// Parse --resume
|
||||
const resume = args.includes('--resume');
|
||||
|
||||
return { idea, resume: resume || undefined };
|
||||
}
|
||||
|
||||
async function main() {
|
||||
try {
|
||||
const { idea, resume, help } = parseArgs();
|
||||
|
||||
if (help) {
|
||||
showHelp();
|
||||
process.exit(0);
|
||||
}
|
||||
|
||||
await runCLI({ idea, resume });
|
||||
process.exit(0);
|
||||
} catch (err) {
|
||||
if (err instanceof Error && err.message.includes('User force closed')) {
|
||||
process.exit(0);
|
||||
}
|
||||
console.error(err instanceof Error ? err.message : String(err));
|
||||
process.exit(1);
|
||||
}
|
||||
}
|
||||
|
||||
main();
|
||||
@@ -0,0 +1,121 @@
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import fs from 'fs-extra';
|
||||
import path from 'path';
|
||||
import os from 'os';
|
||||
import { saveState, loadState, deleteState, findExistingState } from './bot-state.js';
|
||||
import type { BotState } from './types.js';
|
||||
|
||||
function makeTmpDir(): string {
|
||||
return fs.mkdtempSync(path.join(os.tmpdir(), 'bot-state-test-'));
|
||||
}
|
||||
|
||||
function makeState(projectDir: string): BotState {
|
||||
return {
|
||||
config: {
|
||||
workDir: path.dirname(projectDir),
|
||||
projectDir,
|
||||
ideaName: 'test-idea',
|
||||
ideaDescription: 'A test idea',
|
||||
mode: 'new-project',
|
||||
},
|
||||
steps: [],
|
||||
currentStep: null,
|
||||
implementPasses: 0,
|
||||
allPhasesComplete: false,
|
||||
};
|
||||
}
|
||||
|
||||
describe('bot-state', () => {
|
||||
let tmpDir: string;
|
||||
|
||||
beforeEach(() => {
|
||||
tmpDir = makeTmpDir();
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
fs.removeSync(tmpDir);
|
||||
});
|
||||
|
||||
describe('saveState', () => {
|
||||
it('writes valid JSON', () => {
|
||||
const projectDir = path.join(tmpDir, 'project');
|
||||
fs.ensureDirSync(projectDir);
|
||||
const state = makeState(projectDir);
|
||||
|
||||
saveState(state);
|
||||
|
||||
const filePath = path.join(projectDir, '.plan2code-bot-state.json');
|
||||
expect(fs.existsSync(filePath)).toBe(true);
|
||||
const parsed = fs.readJsonSync(filePath);
|
||||
expect(parsed.config.ideaName).toBe('test-idea');
|
||||
});
|
||||
});
|
||||
|
||||
describe('loadState', () => {
|
||||
it('returns state from file', () => {
|
||||
const projectDir = path.join(tmpDir, 'project');
|
||||
fs.ensureDirSync(projectDir);
|
||||
const state = makeState(projectDir);
|
||||
saveState(state);
|
||||
|
||||
const loaded = loadState(projectDir);
|
||||
expect(loaded).not.toBeNull();
|
||||
expect(loaded!.config.ideaName).toBe('test-idea');
|
||||
expect(loaded!.implementPasses).toBe(0);
|
||||
});
|
||||
|
||||
it('returns null when file does not exist', () => {
|
||||
const result = loadState(path.join(tmpDir, 'nonexistent'));
|
||||
expect(result).toBeNull();
|
||||
});
|
||||
});
|
||||
|
||||
describe('deleteState', () => {
|
||||
it('removes the file', () => {
|
||||
const projectDir = path.join(tmpDir, 'project');
|
||||
fs.ensureDirSync(projectDir);
|
||||
const state = makeState(projectDir);
|
||||
saveState(state);
|
||||
|
||||
const filePath = path.join(projectDir, '.plan2code-bot-state.json');
|
||||
expect(fs.existsSync(filePath)).toBe(true);
|
||||
|
||||
deleteState(projectDir);
|
||||
expect(fs.existsSync(filePath)).toBe(false);
|
||||
});
|
||||
|
||||
it('is a no-op when file does not exist', () => {
|
||||
// Should not throw
|
||||
deleteState(path.join(tmpDir, 'nonexistent'));
|
||||
});
|
||||
});
|
||||
|
||||
describe('findExistingState', () => {
|
||||
it('finds state in workDir (enhancement mode)', () => {
|
||||
const state = makeState(tmpDir);
|
||||
state.config.projectDir = tmpDir;
|
||||
state.config.mode = 'enhancement';
|
||||
saveState(state);
|
||||
|
||||
const found = findExistingState(tmpDir);
|
||||
expect(found).not.toBeNull();
|
||||
expect(found!.config.ideaName).toBe('test-idea');
|
||||
});
|
||||
|
||||
it('finds state in a subdirectory (new-project mode)', () => {
|
||||
const projectDir = path.join(tmpDir, 'my-app');
|
||||
fs.ensureDirSync(projectDir);
|
||||
const state = makeState(projectDir);
|
||||
saveState(state);
|
||||
|
||||
const found = findExistingState(tmpDir);
|
||||
expect(found).not.toBeNull();
|
||||
expect(found!.config.projectDir).toBe(projectDir);
|
||||
});
|
||||
|
||||
it('returns null when no state exists', () => {
|
||||
const found = findExistingState(tmpDir);
|
||||
expect(found).toBeNull();
|
||||
});
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,48 @@
|
||||
import fs from 'fs-extra';
|
||||
import path from 'path';
|
||||
import type { BotState } from './types.js';
|
||||
|
||||
const STATE_FILE = '.plan2code-bot-state.json';
|
||||
|
||||
export function saveState(state: BotState): void {
|
||||
const filePath = path.join(state.config.projectDir, STATE_FILE);
|
||||
fs.writeJsonSync(filePath, state, { spaces: 2 });
|
||||
}
|
||||
|
||||
export function loadState(projectDir: string): BotState | null {
|
||||
const filePath = path.join(projectDir, STATE_FILE);
|
||||
if (!fs.existsSync(filePath)) {
|
||||
return null;
|
||||
}
|
||||
return fs.readJsonSync(filePath) as BotState;
|
||||
}
|
||||
|
||||
export function deleteState(projectDir: string): void {
|
||||
const filePath = path.join(projectDir, STATE_FILE);
|
||||
if (fs.existsSync(filePath)) {
|
||||
fs.removeSync(filePath);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Search for an existing state file in workDir (enhancement mode)
|
||||
* or in immediate subdirectories (new-project mode).
|
||||
*/
|
||||
export function findExistingState(workDir: string): BotState | null {
|
||||
// Enhancement mode: state is in workDir directly
|
||||
const direct = loadState(workDir);
|
||||
if (direct) return direct;
|
||||
|
||||
// New-project mode: state is in a subdirectory
|
||||
try {
|
||||
for (const entry of fs.readdirSync(workDir, { withFileTypes: true })) {
|
||||
if (entry.isDirectory()) {
|
||||
const sub = loadState(path.join(workDir, entry.name));
|
||||
if (sub) return sub;
|
||||
}
|
||||
}
|
||||
} catch {
|
||||
// workDir not readable — ignore
|
||||
}
|
||||
return null;
|
||||
}
|
||||
@@ -0,0 +1,195 @@
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import fs from 'fs-extra';
|
||||
import os from 'os';
|
||||
import path from 'path';
|
||||
import { validateStepArtifacts, installSkillsForBot } from './cli.js';
|
||||
|
||||
let tmpDir: string;
|
||||
|
||||
beforeEach(() => {
|
||||
tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'p2c-cli-test-'));
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
fs.removeSync(tmpDir);
|
||||
});
|
||||
|
||||
// ── validateStepArtifacts ───────────────────────────────────────────
|
||||
|
||||
describe('validateStepArtifacts', () => {
|
||||
describe('init', () => {
|
||||
it('valid when AGENTS.md exists', () => {
|
||||
fs.writeFileSync(path.join(tmpDir, 'AGENTS.md'), '# Agents');
|
||||
const result = validateStepArtifacts('init', tmpDir);
|
||||
expect(result.valid).toBe(true);
|
||||
expect(result.missing).toEqual([]);
|
||||
});
|
||||
|
||||
it('missing when AGENTS.md does not exist', () => {
|
||||
const result = validateStepArtifacts('init', tmpDir);
|
||||
expect(result.valid).toBe(false);
|
||||
expect(result.missing).toContain('AGENTS.md');
|
||||
});
|
||||
});
|
||||
|
||||
describe('plan', () => {
|
||||
it('valid when specs/feature/PLAN-DRAFT-*.md exists', () => {
|
||||
const specDir = path.join(tmpDir, 'specs', 'my-feature');
|
||||
fs.ensureDirSync(specDir);
|
||||
fs.writeFileSync(path.join(specDir, 'PLAN-DRAFT-v1.md'), '# Plan');
|
||||
const result = validateStepArtifacts('plan', tmpDir);
|
||||
expect(result.valid).toBe(true);
|
||||
});
|
||||
|
||||
it('missing when specs/ is absent', () => {
|
||||
const result = validateStepArtifacts('plan', tmpDir);
|
||||
expect(result.valid).toBe(false);
|
||||
expect(result.missing).toContain('specs/ directory');
|
||||
});
|
||||
|
||||
it('missing when specs/ has dirs but no plan draft files', () => {
|
||||
const specDir = path.join(tmpDir, 'specs', 'my-feature');
|
||||
fs.ensureDirSync(specDir);
|
||||
fs.writeFileSync(path.join(specDir, 'notes.md'), '# Notes');
|
||||
const result = validateStepArtifacts('plan', tmpDir);
|
||||
expect(result.valid).toBe(false);
|
||||
expect(result.missing).toContain('specs/*/PLAN-DRAFT-*.md');
|
||||
});
|
||||
});
|
||||
|
||||
describe('document', () => {
|
||||
it('valid when overview.md and phase-*.md exist', () => {
|
||||
const specDir = path.join(tmpDir, 'specs', 'my-feature');
|
||||
fs.ensureDirSync(specDir);
|
||||
fs.writeFileSync(path.join(specDir, 'overview.md'), '# Overview');
|
||||
fs.writeFileSync(path.join(specDir, 'phase-1.md'), '# Phase 1');
|
||||
const result = validateStepArtifacts('document', tmpDir);
|
||||
expect(result.valid).toBe(true);
|
||||
});
|
||||
|
||||
it('missing overview.md when absent', () => {
|
||||
const specDir = path.join(tmpDir, 'specs', 'my-feature');
|
||||
fs.ensureDirSync(specDir);
|
||||
fs.writeFileSync(path.join(specDir, 'phase-1.md'), '# Phase 1');
|
||||
const result = validateStepArtifacts('document', tmpDir);
|
||||
expect(result.valid).toBe(false);
|
||||
expect(result.missing).toContain('specs/*/overview.md');
|
||||
});
|
||||
|
||||
it('missing phase files when absent', () => {
|
||||
const specDir = path.join(tmpDir, 'specs', 'my-feature');
|
||||
fs.ensureDirSync(specDir);
|
||||
fs.writeFileSync(path.join(specDir, 'overview.md'), '# Overview');
|
||||
const result = validateStepArtifacts('document', tmpDir);
|
||||
expect(result.valid).toBe(false);
|
||||
expect(result.missing).toContain('specs/*/phase-*.md files');
|
||||
});
|
||||
|
||||
it('accepts phase files inside phases/ subdirectory', () => {
|
||||
const specDir = path.join(tmpDir, 'specs', 'my-feature');
|
||||
const phasesDir = path.join(specDir, 'phases');
|
||||
fs.ensureDirSync(phasesDir);
|
||||
fs.writeFileSync(path.join(specDir, 'overview.md'), '# Overview');
|
||||
fs.writeFileSync(path.join(phasesDir, 'phase-1.md'), '# Phase 1');
|
||||
const result = validateStepArtifacts('document', tmpDir);
|
||||
expect(result.valid).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
describe('finalize', () => {
|
||||
it('valid when specs--completed/ has a subdirectory', () => {
|
||||
fs.ensureDirSync(path.join(tmpDir, 'specs--completed', 'my-feature'));
|
||||
const result = validateStepArtifacts('finalize', tmpDir);
|
||||
expect(result.valid).toBe(true);
|
||||
});
|
||||
|
||||
it('missing when specs--completed/ is absent', () => {
|
||||
const result = validateStepArtifacts('finalize', tmpDir);
|
||||
expect(result.valid).toBe(false);
|
||||
expect(result.missing).toContain('specs--completed/ directory');
|
||||
});
|
||||
|
||||
it('missing when specs--completed/ is empty', () => {
|
||||
fs.ensureDirSync(path.join(tmpDir, 'specs--completed'));
|
||||
const result = validateStepArtifacts('finalize', tmpDir);
|
||||
expect(result.valid).toBe(false);
|
||||
expect(result.missing).toContain('archived spec in specs--completed/');
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
// ── installSkillsForBot ─────────────────────────────────────────────
|
||||
|
||||
describe('installSkillsForBot', () => {
|
||||
let fakeHome: string;
|
||||
let projectDir: string;
|
||||
let origHome: string | undefined;
|
||||
let origUserProfile: string | undefined;
|
||||
|
||||
beforeEach(() => {
|
||||
fakeHome = fs.mkdtempSync(path.join(os.tmpdir(), 'p2c-home-'));
|
||||
projectDir = fs.mkdtempSync(path.join(os.tmpdir(), 'p2c-proj-'));
|
||||
origHome = process.env.HOME;
|
||||
origUserProfile = process.env.USERPROFILE;
|
||||
process.env.HOME = fakeHome;
|
||||
process.env.USERPROFILE = fakeHome;
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
process.env.HOME = origHome;
|
||||
process.env.USERPROFILE = origUserProfile;
|
||||
fs.removeSync(fakeHome);
|
||||
fs.removeSync(projectDir);
|
||||
});
|
||||
|
||||
it('copies skills from user dir to project .claude/skills/', () => {
|
||||
const srcDir = path.join(fakeHome, '.claude', 'skills', 'plan2code-init');
|
||||
fs.ensureDirSync(srcDir);
|
||||
fs.writeFileSync(path.join(srcDir, 'SKILL.md'), '---\nname: init\n---\nSome content');
|
||||
|
||||
installSkillsForBot(projectDir);
|
||||
|
||||
const dest = path.join(projectDir, '.claude', 'skills', 'plan2code-init', 'SKILL.md');
|
||||
expect(fs.existsSync(dest)).toBe(true);
|
||||
expect(fs.readFileSync(dest, 'utf-8')).toContain('Some content');
|
||||
});
|
||||
|
||||
it('strips disable-model-invocation: true from copied SKILL.md', () => {
|
||||
const srcDir = path.join(fakeHome, '.claude', 'skills', 'plan2code-1-plan');
|
||||
fs.ensureDirSync(srcDir);
|
||||
fs.writeFileSync(
|
||||
path.join(srcDir, 'SKILL.md'),
|
||||
'disable-model-invocation: true\n---\nname: plan\n---\nPlan content',
|
||||
);
|
||||
|
||||
installSkillsForBot(projectDir);
|
||||
|
||||
const dest = path.join(projectDir, '.claude', 'skills', 'plan2code-1-plan', 'SKILL.md');
|
||||
const content = fs.readFileSync(dest, 'utf-8');
|
||||
expect(content).not.toContain('disable-model-invocation');
|
||||
expect(content).toContain('Plan content');
|
||||
});
|
||||
|
||||
it('preserves rest of skill content', () => {
|
||||
const srcDir = path.join(fakeHome, '.claude', 'skills', 'plan2code-2-document');
|
||||
fs.ensureDirSync(srcDir);
|
||||
const original = 'disable-model-invocation: true\n---\nname: doc\n---\nLine 1\nLine 2\nLine 3';
|
||||
fs.writeFileSync(path.join(srcDir, 'SKILL.md'), original);
|
||||
|
||||
installSkillsForBot(projectDir);
|
||||
|
||||
const dest = path.join(projectDir, '.claude', 'skills', 'plan2code-2-document', 'SKILL.md');
|
||||
const content = fs.readFileSync(dest, 'utf-8');
|
||||
expect(content).toContain('Line 1');
|
||||
expect(content).toContain('Line 2');
|
||||
expect(content).toContain('Line 3');
|
||||
expect(content).toContain('name: doc');
|
||||
});
|
||||
|
||||
it('skips gracefully when source skill does not exist', () => {
|
||||
// No skills in fakeHome — should not throw
|
||||
expect(() => installSkillsForBot(projectDir)).not.toThrow();
|
||||
// No .claude/skills/ created in project
|
||||
expect(fs.existsSync(path.join(projectDir, '.claude', 'skills'))).toBe(false);
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,587 @@
|
||||
import fs from 'fs-extra';
|
||||
import path from 'path';
|
||||
import chalk from 'chalk';
|
||||
import ora from 'ora';
|
||||
import { generateNewAppIdea, generateEnhancementIdea } from './idea-generator.js';
|
||||
import { runSession } from './session-runner.js';
|
||||
import { buildStepPrompt } from './prompts/step-instructions.js';
|
||||
import { checkAllPhasesComplete } from './step-detector.js';
|
||||
import { saveState, loadState, deleteState, findExistingState } from './bot-state.js';
|
||||
import { ObservationCollector } from './observation-collector.js';
|
||||
import { evaluateStep } from './evaluator.js';
|
||||
import type { BotConfig, BotMode, BotState, StepName, StepResult } from './types.js';
|
||||
|
||||
const BANNER = `
|
||||
╔══════════════════════════════════════╗
|
||||
║ plan2code-bot v1.1.0 ║
|
||||
║ Autonomous Workflow Test Runner ║
|
||||
╚══════════════════════════════════════╝
|
||||
`;
|
||||
|
||||
const MAX_IMPLEMENT_PASSES = 10;
|
||||
|
||||
/** Skill name mapping: bot step name → installed skill directory name */
|
||||
const SKILL_MAP: Record<StepName, string> = {
|
||||
init: 'plan2code-init',
|
||||
plan: 'plan2code-1-plan',
|
||||
document: 'plan2code-2-document',
|
||||
implement: 'plan2code-3-implement',
|
||||
finalize: 'plan2code-4-finalize',
|
||||
};
|
||||
|
||||
/**
|
||||
* Install bot-friendly copies of plan2code skills into the project's .claude/skills/.
|
||||
* The global skills have `disable-model-invocation: true` which prevents the autonomous
|
||||
* session from invoking them via the Skill tool. We copy them with that flag removed
|
||||
* so the session can invoke the real workflow prompts instead of guessing.
|
||||
*/
|
||||
export function installSkillsForBot(projectDir: string): void {
|
||||
const userSkillsDir = path.join(
|
||||
process.env.HOME || process.env.USERPROFILE || '',
|
||||
'.claude',
|
||||
'skills',
|
||||
);
|
||||
const projectSkillsDir = path.join(projectDir, '.claude', 'skills');
|
||||
|
||||
for (const skillName of Object.values(SKILL_MAP)) {
|
||||
const srcFile = path.join(userSkillsDir, skillName, 'SKILL.md');
|
||||
if (!fs.existsSync(srcFile)) continue;
|
||||
|
||||
const content = fs.readFileSync(srcFile, 'utf-8');
|
||||
// Remove the disable-model-invocation line so the bot session can invoke the skill
|
||||
const patched = content.replace(/^disable-model-invocation:\s*true\n?/m, '');
|
||||
|
||||
const destDir = path.join(projectSkillsDir, skillName);
|
||||
fs.ensureDirSync(destDir);
|
||||
fs.writeFileSync(path.join(destDir, 'SKILL.md'), patched);
|
||||
}
|
||||
}
|
||||
|
||||
export function validateStepArtifacts(step: StepName, projectDir: string): { valid: boolean; missing: string[] } {
|
||||
const missing: string[] = [];
|
||||
|
||||
switch (step) {
|
||||
case 'init': {
|
||||
const agentsPath = path.join(projectDir, 'AGENTS.md');
|
||||
if (!fs.existsSync(agentsPath)) missing.push('AGENTS.md');
|
||||
break;
|
||||
}
|
||||
case 'plan': {
|
||||
const specsDir = path.join(projectDir, 'specs');
|
||||
if (!fs.existsSync(specsDir)) {
|
||||
missing.push('specs/ directory');
|
||||
} else {
|
||||
const entries = fs.readdirSync(specsDir, { withFileTypes: true });
|
||||
const specDirs = entries.filter((e) => e.isDirectory());
|
||||
const hasPlanDraft = specDirs.some((d) => {
|
||||
const files = fs.readdirSync(path.join(specsDir, d.name));
|
||||
return files.some((f) => /plan[-_]?draft/i.test(f));
|
||||
});
|
||||
if (!hasPlanDraft) missing.push('specs/*/PLAN-DRAFT-*.md');
|
||||
}
|
||||
break;
|
||||
}
|
||||
case 'document': {
|
||||
const specsDir = path.join(projectDir, 'specs');
|
||||
if (!fs.existsSync(specsDir)) {
|
||||
missing.push('specs/ directory');
|
||||
} else {
|
||||
const entries = fs.readdirSync(specsDir, { withFileTypes: true });
|
||||
const specDirs = entries.filter((e) => e.isDirectory());
|
||||
let foundOverview = false;
|
||||
let foundPhaseFile = false;
|
||||
for (const d of specDirs) {
|
||||
const specPath = path.join(specsDir, d.name);
|
||||
const files = fs.readdirSync(specPath);
|
||||
if (files.some((f) => f === 'overview.md')) foundOverview = true;
|
||||
if (files.some((f) => /^phase[-_]?\d+.*\.md$/i.test(f))) foundPhaseFile = true;
|
||||
// Also check phases/ subdirectory
|
||||
const phasesSubdir = path.join(specPath, 'phases');
|
||||
if (fs.existsSync(phasesSubdir)) {
|
||||
const subFiles = fs.readdirSync(phasesSubdir);
|
||||
if (subFiles.some((f) => /phase/i.test(f))) foundPhaseFile = true;
|
||||
}
|
||||
}
|
||||
if (!foundOverview) missing.push('specs/*/overview.md');
|
||||
if (!foundPhaseFile) missing.push('specs/*/phase-*.md files');
|
||||
}
|
||||
break;
|
||||
}
|
||||
case 'finalize': {
|
||||
const completedDir = path.join(projectDir, 'specs--completed');
|
||||
if (!fs.existsSync(completedDir)) {
|
||||
missing.push('specs--completed/ directory');
|
||||
} else {
|
||||
const entries = fs.readdirSync(completedDir, { withFileTypes: true });
|
||||
const specDirs = entries.filter((e) => e.isDirectory());
|
||||
if (specDirs.length === 0) missing.push('archived spec in specs--completed/');
|
||||
}
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
return { valid: missing.length === 0, missing };
|
||||
}
|
||||
|
||||
function detectMode(workDir: string): BotMode {
|
||||
const agentsPath = path.join(workDir, 'AGENTS.md');
|
||||
return fs.existsSync(agentsPath) ? 'enhancement' : 'new-project';
|
||||
}
|
||||
|
||||
function formatDuration(ms: number): string {
|
||||
const seconds = Math.floor(ms / 1000);
|
||||
const minutes = Math.floor(seconds / 60);
|
||||
const remainingSeconds = seconds % 60;
|
||||
if (minutes > 0) {
|
||||
return `${minutes}m ${remainingSeconds}s`;
|
||||
}
|
||||
return `${seconds}s`;
|
||||
}
|
||||
|
||||
async function runStep(
|
||||
step: StepName,
|
||||
config: BotConfig,
|
||||
state: BotState,
|
||||
): Promise<StepResult> {
|
||||
const spinner = ora({
|
||||
text: chalk.cyan(`Running ${step} step...`),
|
||||
spinner: 'dots',
|
||||
}).start();
|
||||
|
||||
const prompt = buildStepPrompt(step, config);
|
||||
|
||||
try {
|
||||
// Create observation collector
|
||||
const collector = new ObservationCollector(step);
|
||||
|
||||
const result = await runSession({
|
||||
prompt,
|
||||
config,
|
||||
step,
|
||||
maxTurns: step === 'implement' ? 80 : 50,
|
||||
collector,
|
||||
});
|
||||
|
||||
if (result.success) {
|
||||
spinner.succeed(
|
||||
chalk.green(`${step} completed in ${formatDuration(result.duration)}`)
|
||||
);
|
||||
|
||||
// Run evaluation
|
||||
spinner.text = chalk.cyan('Evaluating step quality...');
|
||||
spinner.start();
|
||||
|
||||
const evaluation = await evaluateStep(step, result.observations, config.projectDir);
|
||||
|
||||
spinner.succeed(
|
||||
chalk.cyan(`Evaluation complete: ${formatScore(evaluation.score)}`)
|
||||
);
|
||||
|
||||
// Display evaluation summary
|
||||
console.log(chalk.dim(` Score: ${formatScore(evaluation.score)}`));
|
||||
if (evaluation.strengths.length > 0) {
|
||||
console.log(chalk.green(` ✓ ${evaluation.strengths[0]}`));
|
||||
}
|
||||
if (evaluation.weaknesses.length > 0) {
|
||||
console.log(chalk.yellow(` ⚠ ${evaluation.weaknesses[0]}`));
|
||||
}
|
||||
|
||||
const stepResult: StepResult = {
|
||||
step,
|
||||
success: result.success,
|
||||
sessionId: result.sessionId,
|
||||
duration: result.duration,
|
||||
error: null,
|
||||
evaluation,
|
||||
observations: result.observations,
|
||||
};
|
||||
|
||||
return stepResult;
|
||||
} else {
|
||||
spinner.fail(chalk.red(`${step} failed after ${formatDuration(result.duration)}`));
|
||||
|
||||
return {
|
||||
step,
|
||||
success: false,
|
||||
sessionId: result.sessionId,
|
||||
duration: result.duration,
|
||||
error: 'Session failed',
|
||||
observations: result.observations,
|
||||
};
|
||||
}
|
||||
} catch (error) {
|
||||
const errorMsg = error instanceof Error ? error.message : String(error);
|
||||
spinner.fail(chalk.red(`${step} error: ${errorMsg}`));
|
||||
return {
|
||||
step,
|
||||
success: false,
|
||||
sessionId: null,
|
||||
duration: 0,
|
||||
error: errorMsg,
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
function formatScore(score: number): string {
|
||||
if (score >= 85) return chalk.green(`${score}/100`);
|
||||
if (score >= 70) return chalk.yellow(`${score}/100`);
|
||||
return chalk.red(`${score}/100`);
|
||||
}
|
||||
|
||||
export interface CLIOptions {
|
||||
idea?: string;
|
||||
resume?: boolean;
|
||||
}
|
||||
|
||||
/** Check if a step completed successfully in a saved state */
|
||||
function stepSucceeded(state: BotState, step: StepName): boolean {
|
||||
return state.steps.some((s) => s.step === step && s.success);
|
||||
}
|
||||
|
||||
export async function runCLI(options: CLIOptions = {}): Promise<void> {
|
||||
console.log(chalk.cyan(BANNER));
|
||||
|
||||
const workDir = process.cwd();
|
||||
|
||||
// Check for resumable state
|
||||
let resuming = false;
|
||||
let savedState: BotState | null = null;
|
||||
|
||||
if (options.resume) {
|
||||
savedState = findExistingState(workDir);
|
||||
if (savedState) {
|
||||
resuming = true;
|
||||
console.log(chalk.yellow('Resuming previous incomplete run...'));
|
||||
} else {
|
||||
console.log(chalk.dim('No previous state found, starting fresh.'));
|
||||
}
|
||||
}
|
||||
|
||||
const mode = resuming ? savedState!.config.mode : detectMode(workDir);
|
||||
|
||||
console.log(chalk.dim(`Working directory: ${workDir}`));
|
||||
console.log(chalk.dim(`Mode: ${mode === 'new-project' ? 'New Project' : 'Enhancement'}`));
|
||||
if (options.idea) {
|
||||
console.log(chalk.dim(`Idea seed: ${options.idea}`));
|
||||
}
|
||||
console.log('');
|
||||
|
||||
let ideaName: string;
|
||||
let ideaDescription: string;
|
||||
let projectDir: string;
|
||||
|
||||
if (resuming) {
|
||||
// Restore from saved state
|
||||
ideaName = savedState!.config.ideaName;
|
||||
ideaDescription = savedState!.config.ideaDescription;
|
||||
projectDir = savedState!.config.projectDir;
|
||||
console.log(chalk.green(`Restored idea: ${ideaName}`));
|
||||
console.log(chalk.dim(` ${ideaDescription}`));
|
||||
console.log('');
|
||||
} else {
|
||||
// Step 1: Generate idea
|
||||
const ideaSpinner = ora({
|
||||
text: chalk.cyan('Generating idea...'),
|
||||
spinner: 'dots',
|
||||
}).start();
|
||||
|
||||
try {
|
||||
if (mode === 'new-project') {
|
||||
const idea = await generateNewAppIdea(options.idea);
|
||||
ideaName = idea.name;
|
||||
ideaDescription = idea.description;
|
||||
} else {
|
||||
const idea = await generateEnhancementIdea(workDir, options.idea);
|
||||
ideaName = idea.name;
|
||||
ideaDescription = idea.description;
|
||||
}
|
||||
ideaSpinner.succeed(chalk.green(`Idea generated: ${ideaName}`));
|
||||
} catch (error) {
|
||||
ideaSpinner.fail(chalk.red('Failed to generate idea'));
|
||||
throw error;
|
||||
}
|
||||
|
||||
console.log(chalk.dim(` ${ideaDescription}`));
|
||||
console.log('');
|
||||
|
||||
// Determine project directory
|
||||
projectDir = mode === 'new-project'
|
||||
? path.join(workDir, ideaName)
|
||||
: workDir;
|
||||
|
||||
// Create project directory for new projects
|
||||
if (mode === 'new-project') {
|
||||
fs.ensureDirSync(projectDir);
|
||||
}
|
||||
}
|
||||
|
||||
// Install bot-friendly skills (without disable-model-invocation)
|
||||
installSkillsForBot(projectDir);
|
||||
console.log(chalk.dim('Installed plan2code skills for bot sessions'));
|
||||
|
||||
// Write IDEA.md (only if not resuming past plan step, since it gets moved)
|
||||
if (!resuming || !stepSucceeded(savedState!, 'plan')) {
|
||||
const ideaContent = `# ${ideaName}\n\n${ideaDescription}\n`;
|
||||
fs.writeFileSync(path.join(projectDir, 'IDEA.md'), ideaContent);
|
||||
console.log(chalk.dim(`Wrote IDEA.md to ${projectDir}`));
|
||||
}
|
||||
console.log('');
|
||||
|
||||
// Build config
|
||||
const config: BotConfig = {
|
||||
workDir,
|
||||
projectDir,
|
||||
ideaDescription,
|
||||
ideaName,
|
||||
mode,
|
||||
};
|
||||
|
||||
// Initialize or restore state
|
||||
const state: BotState = resuming
|
||||
? { ...savedState!, config }
|
||||
: {
|
||||
config,
|
||||
steps: [],
|
||||
currentStep: null,
|
||||
implementPasses: 0,
|
||||
allPhasesComplete: false,
|
||||
};
|
||||
|
||||
// Step 2: Run init (new project only)
|
||||
if (mode === 'new-project') {
|
||||
if (resuming && stepSucceeded(savedState!, 'init')) {
|
||||
console.log(chalk.dim('--- Init (skipped — previously succeeded) ---'));
|
||||
} else {
|
||||
console.log(chalk.bold('--- Init ---'));
|
||||
state.currentStep = 'init';
|
||||
const initResult = await runStep('init', config, state);
|
||||
state.steps.push(initResult);
|
||||
saveState(state);
|
||||
|
||||
if (!initResult.success) {
|
||||
console.log(chalk.red('\nInit failed. Aborting.'));
|
||||
printSummary(state, workDir, false);
|
||||
return;
|
||||
}
|
||||
const initValidation = validateStepArtifacts('init', projectDir);
|
||||
if (!initValidation.valid) {
|
||||
console.log(chalk.yellow(` ⚠ Missing artifacts: ${initValidation.missing.join(', ')}`));
|
||||
initResult.success = false;
|
||||
initResult.error = `Missing artifacts: ${initValidation.missing.join(', ')}`;
|
||||
console.log(chalk.red('\nInit artifacts missing. Aborting.'));
|
||||
printSummary(state, workDir, false);
|
||||
return;
|
||||
}
|
||||
}
|
||||
console.log('');
|
||||
}
|
||||
|
||||
// Step 3: Plan
|
||||
if (resuming && stepSucceeded(savedState!, 'plan')) {
|
||||
console.log(chalk.dim('--- Plan (skipped — previously succeeded) ---'));
|
||||
} else {
|
||||
console.log(chalk.bold('--- Plan ---'));
|
||||
state.currentStep = 'plan';
|
||||
const planResult = await runStep('plan', config, state);
|
||||
state.steps.push(planResult);
|
||||
saveState(state);
|
||||
|
||||
if (!planResult.success) {
|
||||
console.log(chalk.red('\nPlan step failed. Aborting.'));
|
||||
printSummary(state, workDir, false);
|
||||
return;
|
||||
}
|
||||
const planValidation = validateStepArtifacts('plan', projectDir);
|
||||
if (!planValidation.valid) {
|
||||
console.log(chalk.yellow(` ⚠ Missing artifacts: ${planValidation.missing.join(', ')}`));
|
||||
planResult.success = false;
|
||||
planResult.error = `Missing artifacts: ${planValidation.missing.join(', ')}`;
|
||||
console.log(chalk.red('\nPlan artifacts missing. Aborting.'));
|
||||
printSummary(state, workDir, false);
|
||||
return;
|
||||
}
|
||||
|
||||
// Move IDEA.md into the spec directory so it stays with its feature
|
||||
const ideaPath = path.join(projectDir, 'IDEA.md');
|
||||
if (fs.existsSync(ideaPath)) {
|
||||
const specEntries = fs.readdirSync(path.join(projectDir, 'specs'), { withFileTypes: true });
|
||||
const firstSpecDir = specEntries.find((e) => e.isDirectory());
|
||||
if (firstSpecDir) {
|
||||
const dest = path.join(projectDir, 'specs', firstSpecDir.name, 'IDEA.md');
|
||||
fs.moveSync(ideaPath, dest, { overwrite: true });
|
||||
console.log(chalk.dim(`Moved IDEA.md → specs/${firstSpecDir.name}/IDEA.md`));
|
||||
}
|
||||
}
|
||||
}
|
||||
console.log('');
|
||||
|
||||
// Step 4: Document
|
||||
if (resuming && stepSucceeded(savedState!, 'document')) {
|
||||
console.log(chalk.dim('--- Document (skipped — previously succeeded) ---'));
|
||||
} else {
|
||||
console.log(chalk.bold('--- Document ---'));
|
||||
state.currentStep = 'document';
|
||||
const docResult = await runStep('document', config, state);
|
||||
state.steps.push(docResult);
|
||||
saveState(state);
|
||||
|
||||
if (!docResult.success) {
|
||||
console.log(chalk.red('\nDocument step failed. Aborting.'));
|
||||
printSummary(state, workDir, false);
|
||||
return;
|
||||
}
|
||||
const docValidation = validateStepArtifacts('document', projectDir);
|
||||
if (!docValidation.valid) {
|
||||
console.log(chalk.yellow(` ⚠ Missing artifacts: ${docValidation.missing.join(', ')}`));
|
||||
docResult.success = false;
|
||||
docResult.error = `Missing artifacts: ${docValidation.missing.join(', ')}`;
|
||||
console.log(chalk.red('\nDocument artifacts missing. Aborting.'));
|
||||
printSummary(state, workDir, false);
|
||||
return;
|
||||
}
|
||||
}
|
||||
console.log('');
|
||||
|
||||
// Step 5: Implement (loop until all phases complete)
|
||||
if (resuming && savedState!.allPhasesComplete) {
|
||||
console.log(chalk.dim('--- Implement (skipped — all phases already complete) ---'));
|
||||
} else {
|
||||
console.log(chalk.bold('--- Implement ---'));
|
||||
while (state.implementPasses < MAX_IMPLEMENT_PASSES) {
|
||||
state.implementPasses++;
|
||||
state.currentStep = 'implement';
|
||||
|
||||
console.log(chalk.dim(` Pass ${state.implementPasses}/${MAX_IMPLEMENT_PASSES}`));
|
||||
const implResult = await runStep('implement', config, state);
|
||||
state.steps.push(implResult);
|
||||
saveState(state);
|
||||
|
||||
if (!implResult.success) {
|
||||
console.log(chalk.yellow(`\nImplement pass ${state.implementPasses} failed. Continuing...`));
|
||||
}
|
||||
|
||||
// Check if all phases are complete
|
||||
if (checkAllPhasesComplete(projectDir)) {
|
||||
state.allPhasesComplete = true;
|
||||
saveState(state);
|
||||
console.log(chalk.green(' All phases complete!'));
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
if (!state.allPhasesComplete && state.implementPasses >= MAX_IMPLEMENT_PASSES) {
|
||||
console.log(chalk.yellow(`\nMax implement passes (${MAX_IMPLEMENT_PASSES}) reached.`));
|
||||
}
|
||||
}
|
||||
console.log('');
|
||||
|
||||
// Step 6: Finalize
|
||||
if (resuming && stepSucceeded(savedState!, 'finalize')) {
|
||||
console.log(chalk.dim('--- Finalize (skipped — previously succeeded) ---'));
|
||||
} else {
|
||||
console.log(chalk.bold('--- Finalize ---'));
|
||||
|
||||
// Check quality gate: average score must be >= 60
|
||||
const evaluatedSteps = state.steps.filter((s) => s.evaluation);
|
||||
if (evaluatedSteps.length > 0) {
|
||||
const avgScore =
|
||||
evaluatedSteps.reduce((sum, s) => sum + (s.evaluation?.score ?? 0), 0) /
|
||||
evaluatedSteps.length;
|
||||
|
||||
console.log(chalk.dim(` Average quality score: ${formatScore(Math.round(avgScore))}`));
|
||||
|
||||
if (avgScore < 60) {
|
||||
console.log(
|
||||
chalk.red(
|
||||
'\n⚠ Quality gate failed: Average score is below 60. Please review and fix issues before finalizing.'
|
||||
)
|
||||
);
|
||||
console.log(chalk.dim(' Check specs/<feature>/BOT-EVALUATION.md for detailed feedback.'));
|
||||
printSummary(state, workDir, false);
|
||||
return;
|
||||
}
|
||||
}
|
||||
|
||||
state.currentStep = 'finalize';
|
||||
const finalizeResult = await runStep('finalize', config, state);
|
||||
state.steps.push(finalizeResult);
|
||||
saveState(state);
|
||||
|
||||
if (finalizeResult.success) {
|
||||
const finalValidation = validateStepArtifacts('finalize', projectDir);
|
||||
if (!finalValidation.valid) {
|
||||
console.log(chalk.yellow(` ⚠ Missing artifacts: ${finalValidation.missing.join(', ')}`));
|
||||
finalizeResult.success = false;
|
||||
finalizeResult.error = `Missing artifacts: ${finalValidation.missing.join(', ')}`;
|
||||
saveState(state);
|
||||
}
|
||||
}
|
||||
}
|
||||
console.log('');
|
||||
|
||||
// Determine overall success
|
||||
const allSucceeded = state.steps.length > 0 && state.steps.every((s) => s.success);
|
||||
printSummary(state, workDir, allSucceeded);
|
||||
|
||||
// Clean up state file on full success
|
||||
if (allSucceeded) {
|
||||
deleteState(projectDir);
|
||||
console.log(chalk.dim('Cleaned up state file (run succeeded)'));
|
||||
} else {
|
||||
console.log(chalk.dim('State file preserved for resume (run incomplete)'));
|
||||
}
|
||||
console.log('');
|
||||
}
|
||||
|
||||
function printSummary(state: BotState, workDir: string, allSucceeded: boolean): void {
|
||||
const { ideaName, mode, projectDir } = state.config;
|
||||
|
||||
console.log(chalk.cyan('═══════════════════════════════════════'));
|
||||
console.log(chalk.bold(' Bot Run Summary'));
|
||||
console.log(chalk.cyan('═══════════════════════════════════════'));
|
||||
console.log(chalk.dim(` Project: ${ideaName}`));
|
||||
console.log(chalk.dim(` Mode: ${mode}`));
|
||||
console.log(chalk.dim(` Directory: ${projectDir}`));
|
||||
console.log('');
|
||||
|
||||
const totalDuration = state.steps.reduce((sum, s) => sum + s.duration, 0);
|
||||
const successCount = state.steps.filter((s) => s.success).length;
|
||||
|
||||
for (const step of state.steps) {
|
||||
const icon = step.success ? chalk.green('✓') : chalk.red('✗');
|
||||
const scoreText = step.evaluation
|
||||
? ` [${formatScore(step.evaluation.score)}]`
|
||||
: '';
|
||||
console.log(
|
||||
` ${icon} ${step.step.padEnd(12)} ${formatDuration(step.duration)}${scoreText}`
|
||||
);
|
||||
}
|
||||
|
||||
console.log('');
|
||||
|
||||
// Display average quality score if available
|
||||
const evaluatedSteps = state.steps.filter((s) => s.evaluation);
|
||||
if (evaluatedSteps.length > 0) {
|
||||
const avgScore =
|
||||
evaluatedSteps.reduce((sum, s) => sum + (s.evaluation?.score ?? 0), 0) /
|
||||
evaluatedSteps.length;
|
||||
console.log(
|
||||
chalk.dim(` Average quality: ${formatScore(Math.round(avgScore))}`)
|
||||
);
|
||||
}
|
||||
|
||||
console.log(
|
||||
chalk.dim(
|
||||
` Total: ${successCount}/${state.steps.length} steps succeeded in ${formatDuration(totalDuration)}`
|
||||
)
|
||||
);
|
||||
console.log(chalk.dim(` Implement passes: ${state.implementPasses}`));
|
||||
if (!allSucceeded) {
|
||||
console.log(
|
||||
chalk.dim(
|
||||
` State saved to: ${path.relative(workDir, projectDir)}/.plan2code-bot-state.json`
|
||||
)
|
||||
);
|
||||
}
|
||||
console.log('');
|
||||
}
|
||||
@@ -0,0 +1,311 @@
|
||||
import { query } from '@anthropic-ai/claude-agent-sdk';
|
||||
import fs from 'fs-extra';
|
||||
import path from 'path';
|
||||
import type { EvaluationResult, ExecutionObservation, StepName } from './types.js';
|
||||
import { getCriteriaForStep } from './prompts/evaluation-criteria.js';
|
||||
|
||||
/**
|
||||
* Evaluates a completed step using LLM-as-judge.
|
||||
* Returns honest quality assessment based on observations and artifacts.
|
||||
*/
|
||||
export async function evaluateStep(
|
||||
step: StepName,
|
||||
observations: ExecutionObservation,
|
||||
projectDir: string
|
||||
): Promise<EvaluationResult> {
|
||||
const criteria = getCriteriaForStep(step);
|
||||
const prompt = buildEvaluationPrompt(step, observations, criteria, projectDir);
|
||||
|
||||
try {
|
||||
// Query LLM with ability to inspect artifacts
|
||||
const session = query({
|
||||
prompt,
|
||||
options: {
|
||||
maxTurns: 30,
|
||||
cwd: projectDir,
|
||||
permissionMode: 'bypassPermissions',
|
||||
allowDangerouslySkipPermissions: true,
|
||||
allowedTools: ['Read', 'Glob', 'Grep'],
|
||||
systemPrompt:
|
||||
'You are a QA engineer evaluating completed work. Be thorough, honest, and constructive.',
|
||||
},
|
||||
});
|
||||
|
||||
let output = '';
|
||||
for await (const message of session) {
|
||||
if (message.type === 'assistant') {
|
||||
for (const block of message.message.content) {
|
||||
if (block.type === 'text') output += block.text;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
const evaluation = parseEvaluationOutput(output, step);
|
||||
|
||||
// Write evaluation files
|
||||
await writeEvaluationFiles(evaluation, observations, projectDir);
|
||||
|
||||
return evaluation;
|
||||
} catch (error) {
|
||||
console.warn('Evaluation failed, using fallback:', error);
|
||||
return createFallbackEvaluation(step, observations);
|
||||
}
|
||||
}
|
||||
|
||||
function buildEvaluationPrompt(
|
||||
step: StepName,
|
||||
observations: ExecutionObservation,
|
||||
criteria: ReturnType<typeof getCriteriaForStep>,
|
||||
projectDir: string
|
||||
): string {
|
||||
const duration = observations.endTime - observations.startTime;
|
||||
const durationSec = Math.floor(duration / 1000);
|
||||
|
||||
const toolsSummary = observations.tools
|
||||
.map((t) => `- ${t.toolName} (${new Date(t.timestamp).toISOString()})`)
|
||||
.join('\n');
|
||||
|
||||
const filesSummary = [
|
||||
...observations.filesCreated.map((f) => `CREATED: ${f}`),
|
||||
...observations.filesModified.map((f) => `MODIFIED: ${f}`),
|
||||
].join('\n');
|
||||
|
||||
const questionsSummary = observations.questionsAsked
|
||||
.map(
|
||||
(q) =>
|
||||
`Q: ${q.question}\nA: ${q.selectedAnswer}\nReasoning: ${q.llmReasoning}`
|
||||
)
|
||||
.join('\n\n');
|
||||
|
||||
return `You are a QA engineer evaluating the quality of a completed workflow step.
|
||||
|
||||
## Step Information
|
||||
- Step: ${step}
|
||||
- Duration: ${durationSec}s
|
||||
- Tools used: ${observations.tools.length}
|
||||
- Files created: ${observations.filesCreated.length}
|
||||
- Files modified: ${observations.filesModified.length}
|
||||
- Errors: ${observations.errors.length}
|
||||
|
||||
## Execution Details
|
||||
|
||||
### Tools Used
|
||||
${toolsSummary || '(none)'}
|
||||
|
||||
### Files Changed
|
||||
${filesSummary || '(none)'}
|
||||
|
||||
${observations.questionsAsked.length > 0 ? `### Questions & Decisions\n${questionsSummary}` : ''}
|
||||
|
||||
${observations.errors.length > 0 ? `### Errors Encountered\n${observations.errors.join('\n')}` : ''}
|
||||
|
||||
## Evaluation Criteria
|
||||
|
||||
**Key Artifacts Expected:**
|
||||
${criteria.keyArtifacts.map((a) => `- ${a}`).join('\n')}
|
||||
|
||||
**Quality Checks:**
|
||||
${criteria.qualityChecks.map((c) => `- ${c}`).join('\n')}
|
||||
|
||||
**Common Pitfalls to Watch For:**
|
||||
${criteria.commonPitfalls.map((p) => `- ${p}`).join('\n')}
|
||||
|
||||
**Scoring Guidance:**
|
||||
${criteria.scoringGuidance}
|
||||
|
||||
## Your Task
|
||||
|
||||
Evaluate this step honestly and thoroughly:
|
||||
|
||||
1. **Inspect the artifacts** using Read, Glob, and Grep tools
|
||||
2. **Check against quality criteria** listed above
|
||||
3. **Identify strengths and weaknesses** based on actual evidence
|
||||
4. **Provide constructive suggestions** for improvement
|
||||
5. **Assign an honest score** (0-100) following the guidance
|
||||
|
||||
Be critical but fair. Most work scores 70-85. Don't inflate scores.
|
||||
|
||||
## Response Format
|
||||
|
||||
SCORE: <number 0-100>
|
||||
|
||||
STRENGTHS:
|
||||
- <strength 1>
|
||||
- <strength 2>
|
||||
- <strength 3>
|
||||
|
||||
WEAKNESSES:
|
||||
- <weakness 1>
|
||||
- <weakness 2>
|
||||
|
||||
SUGGESTIONS:
|
||||
- <suggestion 1>
|
||||
- <suggestion 2>
|
||||
|
||||
CRITICAL_ISSUES:
|
||||
- <critical issue 1 (or "None")>
|
||||
|
||||
REASONING:
|
||||
<1-2 paragraphs explaining your evaluation, referencing specific files/evidence>
|
||||
|
||||
Provide honest, evidence-based evaluation.`;
|
||||
}
|
||||
|
||||
function parseEvaluationOutput(
|
||||
output: string,
|
||||
step: StepName
|
||||
): EvaluationResult {
|
||||
// Extract score
|
||||
const scoreMatch = output.match(/SCORE:\s*(\d+)/i);
|
||||
if (!scoreMatch) {
|
||||
console.warn(`Evaluation parser: no SCORE found in output (${output.length} chars). Defaulting to 50.`);
|
||||
}
|
||||
const score = scoreMatch ? parseInt(scoreMatch[1], 10) : 50;
|
||||
|
||||
// Extract sections
|
||||
const strengthsMatch = output.match(
|
||||
/STRENGTHS:\s*((?:- .+\n?)+)/i
|
||||
);
|
||||
const weaknessesMatch = output.match(
|
||||
/WEAKNESSES:\s*((?:- .+\n?)+)/i
|
||||
);
|
||||
const suggestionsMatch = output.match(
|
||||
/SUGGESTIONS:\s*((?:- .+\n?)+)/i
|
||||
);
|
||||
const criticalMatch = output.match(
|
||||
/CRITICAL_ISSUES:\s*((?:- .+\n?)+)/i
|
||||
);
|
||||
const reasoningMatch = output.match(/REASONING:\s*(.+?)(?=\n\n|$)/is);
|
||||
|
||||
const parseList = (text: string | undefined): string[] => {
|
||||
if (!text) return [];
|
||||
return text
|
||||
.split('\n')
|
||||
.map((line) => line.replace(/^-\s*/, '').trim())
|
||||
.filter((line) => line.length > 0 && !line.toLowerCase().includes('none'));
|
||||
};
|
||||
|
||||
return {
|
||||
step,
|
||||
score: Math.max(0, Math.min(100, score)),
|
||||
strengths: parseList(strengthsMatch?.[1]),
|
||||
weaknesses: parseList(weaknessesMatch?.[1]),
|
||||
suggestions: parseList(suggestionsMatch?.[1]),
|
||||
criticalIssues: parseList(criticalMatch?.[1]),
|
||||
timestamp: Date.now(),
|
||||
evaluatorModel: 'claude-sonnet-4-5',
|
||||
reasoning: reasoningMatch?.[1]?.trim() || 'No reasoning provided',
|
||||
};
|
||||
}
|
||||
|
||||
function createFallbackEvaluation(
|
||||
step: StepName,
|
||||
observations: ExecutionObservation
|
||||
): EvaluationResult {
|
||||
return {
|
||||
step,
|
||||
score: 50,
|
||||
strengths: ['Step completed'],
|
||||
weaknesses: ['Evaluation failed - using fallback'],
|
||||
suggestions: ['Re-run with evaluation enabled'],
|
||||
criticalIssues: ['Evaluation system unavailable'],
|
||||
timestamp: Date.now(),
|
||||
evaluatorModel: 'fallback',
|
||||
reasoning: 'Evaluation failed, using fallback. Cannot provide detailed assessment.',
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Resolves the active spec subdirectory (e.g. specs/<feature>/).
|
||||
* Falls back to projectDir if no spec folder exists yet (e.g. during init).
|
||||
*/
|
||||
function resolveOutputDir(projectDir: string): string {
|
||||
const specsDir = path.join(projectDir, 'specs');
|
||||
if (fs.existsSync(specsDir)) {
|
||||
const entries = fs.readdirSync(specsDir, { withFileTypes: true });
|
||||
const firstSpec = entries.find((e) => e.isDirectory());
|
||||
if (firstSpec) {
|
||||
return path.join(specsDir, firstSpec.name);
|
||||
}
|
||||
}
|
||||
return projectDir;
|
||||
}
|
||||
|
||||
async function writeEvaluationFiles(
|
||||
evaluation: EvaluationResult,
|
||||
observations: ExecutionObservation,
|
||||
projectDir: string
|
||||
): Promise<void> {
|
||||
const outputDir = resolveOutputDir(projectDir);
|
||||
|
||||
// Write BOT-EVALUATION.md
|
||||
const evalContent = formatEvaluationMarkdown(evaluation);
|
||||
const evalPath = path.join(outputDir, 'BOT-EVALUATION.md');
|
||||
|
||||
if (fs.existsSync(evalPath)) {
|
||||
// Append to existing file
|
||||
const existing = fs.readFileSync(evalPath, 'utf-8');
|
||||
fs.writeFileSync(evalPath, existing + '\n\n---\n\n' + evalContent);
|
||||
} else {
|
||||
fs.writeFileSync(evalPath, evalContent);
|
||||
}
|
||||
|
||||
// Write BOT-NOTES.md
|
||||
const notesContent = formatObservationsMarkdown(observations);
|
||||
const notesPath = path.join(outputDir, 'BOT-NOTES.md');
|
||||
|
||||
if (fs.existsSync(notesPath)) {
|
||||
const existing = fs.readFileSync(notesPath, 'utf-8');
|
||||
fs.writeFileSync(notesPath, existing + '\n\n---\n\n' + notesContent);
|
||||
} else {
|
||||
fs.writeFileSync(notesPath, notesContent);
|
||||
}
|
||||
}
|
||||
|
||||
function formatEvaluationMarkdown(evaluation: EvaluationResult): string {
|
||||
return `# Evaluation: ${evaluation.step} Step
|
||||
|
||||
**Score:** ${evaluation.score}/100
|
||||
**Timestamp:** ${new Date(evaluation.timestamp).toISOString()}
|
||||
**Evaluator:** ${evaluation.evaluatorModel}
|
||||
|
||||
## Strengths
|
||||
${evaluation.strengths.map((s) => `- ${s}`).join('\n') || '(none)'}
|
||||
|
||||
## Weaknesses
|
||||
${evaluation.weaknesses.map((w) => `- ${w}`).join('\n') || '(none)'}
|
||||
|
||||
## Suggestions for Improvement
|
||||
${evaluation.suggestions.map((s) => `- ${s}`).join('\n') || '(none)'}
|
||||
|
||||
${evaluation.criticalIssues.length > 0 ? `## Critical Issues\n${evaluation.criticalIssues.map((i) => `- ${i}`).join('\n')}\n` : ''}
|
||||
|
||||
## Reasoning
|
||||
${evaluation.reasoning}`;
|
||||
}
|
||||
|
||||
function formatObservationsMarkdown(observations: ExecutionObservation): string {
|
||||
const duration = observations.endTime - observations.startTime;
|
||||
const durationSec = Math.floor(duration / 1000);
|
||||
|
||||
return `# Observations: ${observations.step} Step
|
||||
|
||||
**Duration:** ${durationSec}s
|
||||
**Tools Used:** ${observations.tools.length}
|
||||
**Files Created:** ${observations.filesCreated.length}
|
||||
**Files Modified:** ${observations.filesModified.length}
|
||||
**Errors:** ${observations.errors.length}
|
||||
|
||||
${observations.questionsAsked.length > 0 ? `## Questions Asked & Answers\n\n${observations.questionsAsked.map((q) => `### Question: "${q.question}"\n**Selected:** "${q.selectedAnswer}"\n**Reasoning:** ${q.llmReasoning}`).join('\n\n')}\n` : ''}
|
||||
|
||||
## Tool Usage
|
||||
${observations.tools.map((t) => `- ${t.toolName}`).join('\n')}
|
||||
|
||||
## Files Created
|
||||
${observations.filesCreated.map((f) => `- ${f}`).join('\n') || '(none)'}
|
||||
|
||||
## Files Modified
|
||||
${observations.filesModified.map((f) => `- ${f}`).join('\n') || '(none)'}
|
||||
|
||||
${observations.assistantMessages.length > 0 ? `## Assistant Output Summary\n${observations.assistantMessages.slice(0, 3).map((m) => `> ${m.substring(0, 100)}...`).join('\n')}\n` : ''}`;
|
||||
}
|
||||
@@ -0,0 +1,114 @@
|
||||
import { query } from '@anthropic-ai/claude-agent-sdk';
|
||||
|
||||
interface IdeaResult {
|
||||
name: string;
|
||||
description: string;
|
||||
}
|
||||
|
||||
function parseIdea(text: string): IdeaResult {
|
||||
const nameMatch = text.match(/NAME:\s*(.+)/i);
|
||||
const descMatch = text.match(/DESCRIPTION:\s*([\s\S]+?)(?:\n\n|$)/i);
|
||||
|
||||
const name = nameMatch?.[1]?.trim() ?? 'auto-project';
|
||||
const description = descMatch?.[1]?.trim() ?? text.trim();
|
||||
|
||||
// Ensure kebab-case
|
||||
const kebabName = name
|
||||
.toLowerCase()
|
||||
.replace(/[^a-z0-9]+/g, '-')
|
||||
.replace(/^-|-$/g, '');
|
||||
|
||||
return { name: kebabName, description };
|
||||
}
|
||||
|
||||
export async function generateNewAppIdea(seed?: string): Promise<IdeaResult> {
|
||||
const categories = [
|
||||
'CLI tool',
|
||||
'single-page web app',
|
||||
'REST API service',
|
||||
'browser extension',
|
||||
'interactive data visualization dashboard',
|
||||
'terminal-based game',
|
||||
'real-time web app (using WebSockets)',
|
||||
'static site generator or theme',
|
||||
'browser-based game',
|
||||
'desktop utility (using Electron or Tauri)',
|
||||
'chat bot or conversational tool',
|
||||
'automation script or workflow tool',
|
||||
];
|
||||
const category = categories[Math.floor(Math.random() * categories.length)];
|
||||
|
||||
const seedClause = seed
|
||||
? `\n\nThe user provided this seed for inspiration. Stay closely aligned with the theme and intent of the seed — build on it, don't ignore it:\n"${seed}"`
|
||||
: '';
|
||||
|
||||
const prompt = `Generate a random, creative idea for a ${category}. The project should be achievable in a single coding session (1-2 hours) and should be interesting but not overly complex.
|
||||
|
||||
IMPORTANT: Be creative and diverse with your ideas. Avoid defaulting to developer-centric tools (git analyzers, code formatters, repo scanners, etc.) unless the category specifically calls for it. Think about ideas that would appeal to a broad audience — productivity, entertainment, education, health, finance, art, music, social, cooking, travel, fitness, etc.${seedClause}
|
||||
|
||||
Respond in EXACTLY this format (no other text):
|
||||
NAME: <kebab-case-project-name>
|
||||
DESCRIPTION: <2-3 sentence description of what the app does, its key features, and the tech stack to use>`;
|
||||
|
||||
const session = query({
|
||||
prompt,
|
||||
options: {
|
||||
maxTurns: 1,
|
||||
systemPrompt: 'You are a wildly creative project idea generator. You come up with surprising, fun, and diverse software project ideas spanning many domains — not just developer tools. Respond only in the exact format requested.',
|
||||
},
|
||||
});
|
||||
|
||||
let output = '';
|
||||
for await (const message of session) {
|
||||
if (message.type === 'assistant') {
|
||||
for (const block of message.message.content) {
|
||||
if (block.type === 'text') {
|
||||
output += block.text;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return parseIdea(output);
|
||||
}
|
||||
|
||||
export async function generateEnhancementIdea(projectDir: string, seed?: string): Promise<IdeaResult> {
|
||||
const seedClause = seed
|
||||
? `\n\nUse this as inspiration for the enhancement: "${seed}"`
|
||||
: '';
|
||||
|
||||
const prompt = `You are in a project directory. Scan the existing codebase to understand what it does, then propose a realistic enhancement (new feature, refactor, improvement, or extension).
|
||||
|
||||
Use the Read, Glob, and Grep tools to explore the project. Look at:
|
||||
- Package.json or similar config files for project info
|
||||
- Source files for current functionality
|
||||
- README or docs for context${seedClause}
|
||||
|
||||
Then respond in EXACTLY this format (no other text):
|
||||
NAME: <kebab-case-enhancement-name>
|
||||
DESCRIPTION: <2-3 sentence description of the enhancement, what it adds/changes, and why it would be valuable>`;
|
||||
|
||||
const session = query({
|
||||
prompt,
|
||||
options: {
|
||||
maxTurns: 8,
|
||||
cwd: projectDir,
|
||||
tools: { type: 'preset', preset: 'claude_code' },
|
||||
allowedTools: ['Read', 'Glob', 'Grep'],
|
||||
systemPrompt: { type: 'preset', preset: 'claude_code' },
|
||||
},
|
||||
});
|
||||
|
||||
let output = '';
|
||||
for await (const message of session) {
|
||||
if (message.type === 'assistant') {
|
||||
for (const block of message.message.content) {
|
||||
if (block.type === 'text') {
|
||||
output += block.text;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return parseIdea(output);
|
||||
}
|
||||
@@ -0,0 +1,2 @@
|
||||
export { runCLI } from './cli.js';
|
||||
export type { BotConfig, BotMode, BotState, StepName, StepResult } from './types.js';
|
||||
@@ -0,0 +1,243 @@
|
||||
import { query } from '@anthropic-ai/claude-agent-sdk';
|
||||
import type { BotConfig, ExecutionObservation, StepName } from './types.js';
|
||||
import type { ObservationCollector } from './observation-collector.js';
|
||||
|
||||
interface AskUserQuestionInput {
|
||||
questions: Array<{
|
||||
question: string;
|
||||
options: Array<{ label: string; description: string }>;
|
||||
multiSelect?: boolean;
|
||||
}>;
|
||||
}
|
||||
|
||||
interface IntelligentAnswers {
|
||||
answers: Record<string, string>;
|
||||
reasoning: Record<string, string>;
|
||||
}
|
||||
|
||||
/**
|
||||
* Creates an intelligent responder that uses LLM-as-judge for ALL decisions.
|
||||
* Replaces the old hardcoded auto-responder logic.
|
||||
*/
|
||||
export function createIntelligentResponder(
|
||||
config: BotConfig,
|
||||
step: StepName,
|
||||
collector: ObservationCollector
|
||||
) {
|
||||
return async (
|
||||
toolName: string,
|
||||
input: Record<string, unknown>
|
||||
): Promise<{ behavior: 'allow'; updatedInput?: Record<string, unknown> } | { behavior: 'deny'; message: string }> => {
|
||||
// Record every tool invocation for observations
|
||||
collector.recordToolUse(toolName, input, undefined, true);
|
||||
|
||||
// Handle AskUserQuestion with LLM-generated answers
|
||||
if (toolName === 'AskUserQuestion') {
|
||||
const askInput = input as unknown as AskUserQuestionInput;
|
||||
|
||||
// Get current observations to provide context to LLM
|
||||
const observations = collector.getSnapshot();
|
||||
|
||||
// Generate answers using LLM-as-judge
|
||||
const answers = await generateIntelligentAnswers(
|
||||
askInput,
|
||||
observations,
|
||||
config,
|
||||
step
|
||||
);
|
||||
|
||||
// Record each question/answer pair for metrics
|
||||
for (const q of askInput.questions) {
|
||||
const answer = answers.answers[q.question];
|
||||
const reasoning = answers.reasoning[q.question] || 'No reasoning provided';
|
||||
collector.recordQuestion(q.question, q.options, answer, reasoning);
|
||||
}
|
||||
|
||||
return {
|
||||
behavior: 'allow',
|
||||
updatedInput: { ...input, answers: answers.answers },
|
||||
};
|
||||
}
|
||||
|
||||
// Allow all other tools
|
||||
return { behavior: 'allow' };
|
||||
};
|
||||
}
|
||||
|
||||
async function generateIntelligentAnswers(
|
||||
askInput: AskUserQuestionInput,
|
||||
observations: ExecutionObservation,
|
||||
config: BotConfig,
|
||||
step: StepName
|
||||
): Promise<IntelligentAnswers> {
|
||||
const prompt = buildDecisionPrompt(askInput, observations, config, step);
|
||||
|
||||
try {
|
||||
// Query LLM for decision (single turn, read-only tools)
|
||||
const session = query({
|
||||
prompt,
|
||||
options: {
|
||||
maxTurns: 1,
|
||||
cwd: config.projectDir,
|
||||
permissionMode: 'bypassPermissions',
|
||||
allowDangerouslySkipPermissions: true,
|
||||
allowedTools: ['Read', 'Glob', 'Grep'],
|
||||
systemPrompt: 'You are a QA engineer reviewing work-in-progress. Be thoughtful and honest.',
|
||||
},
|
||||
});
|
||||
|
||||
let output = '';
|
||||
for await (const message of session) {
|
||||
if (message.type === 'assistant') {
|
||||
for (const block of message.message.content) {
|
||||
if (block.type === 'text') output += block.text;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return parseDecisionOutput(output, askInput);
|
||||
} catch (error) {
|
||||
console.warn('LLM decision failed, using fallback logic:', error);
|
||||
// Fallback to reasonable defaults if LLM fails
|
||||
return generateFallbackAnswers(askInput, step);
|
||||
}
|
||||
}
|
||||
|
||||
function buildDecisionPrompt(
|
||||
askInput: AskUserQuestionInput,
|
||||
observations: ExecutionObservation,
|
||||
config: BotConfig,
|
||||
step: StepName
|
||||
): string {
|
||||
const duration = observations.endTime - observations.startTime;
|
||||
const toolSummary = observations.tools
|
||||
.map((t) => `- ${t.toolName}`)
|
||||
.join('\n');
|
||||
const filesSummary = [
|
||||
...observations.filesCreated.map((f) => `CREATED: ${f}`),
|
||||
...observations.filesModified.map((f) => `MODIFIED: ${f}`),
|
||||
].join('\n');
|
||||
|
||||
const questionsText = askInput.questions
|
||||
.map((q, i) => {
|
||||
const optionsText = q.options
|
||||
.map((o, j) => ` ${j + 1}. ${o.label} - ${o.description}`)
|
||||
.join('\n');
|
||||
return `QUESTION ${i + 1}: ${q.question}\nOptions:\n${optionsText}`;
|
||||
})
|
||||
.join('\n\n');
|
||||
|
||||
return `You are a QA engineer reviewing a workflow step in progress.
|
||||
|
||||
## Context
|
||||
- Step: ${step}
|
||||
- Mode: ${config.mode}
|
||||
- Duration so far: ${Math.floor(duration / 1000)}s
|
||||
- Tools used: ${observations.tools.length}
|
||||
- Errors encountered: ${observations.errors.length}
|
||||
|
||||
## What's Happened So Far
|
||||
|
||||
### Tools Used
|
||||
${toolSummary || '(none yet)'}
|
||||
|
||||
### Files Changed
|
||||
${filesSummary || '(none yet)'}
|
||||
|
||||
${observations.errors.length > 0 ? `### Errors\n${observations.errors.join('\n')}` : ''}
|
||||
|
||||
## Questions to Answer
|
||||
|
||||
${questionsText}
|
||||
|
||||
## Your Task
|
||||
|
||||
You need to answer these questions as a thoughtful QA engineer would:
|
||||
1. Use Read, Glob, and Grep tools to inspect the current state of artifacts if needed
|
||||
2. Consider what you've observed (tools used, files created, errors)
|
||||
3. For each question, select the most appropriate answer
|
||||
4. Provide brief reasoning for your choice
|
||||
|
||||
Respond in this format:
|
||||
|
||||
QUESTION 1:
|
||||
ANSWER: <option label>
|
||||
REASONING: <1-2 sentences explaining your choice>
|
||||
|
||||
QUESTION 2:
|
||||
ANSWER: <option label>
|
||||
REASONING: <1-2 sentences>
|
||||
|
||||
Be honest. If work looks incomplete or problematic, don't approve it.
|
||||
If tests should be run but haven't been, don't skip them without good reason.
|
||||
Act like a real developer who cares about quality.`;
|
||||
}
|
||||
|
||||
function parseDecisionOutput(
|
||||
output: string,
|
||||
askInput: AskUserQuestionInput
|
||||
): IntelligentAnswers {
|
||||
const answers: Record<string, string> = {};
|
||||
const reasoning: Record<string, string> = {};
|
||||
|
||||
// Parse structured output
|
||||
const questionBlocks = output.split(/QUESTION \d+:/i).slice(1);
|
||||
|
||||
askInput.questions.forEach((q, i) => {
|
||||
const block = questionBlocks[i] || '';
|
||||
|
||||
const answerMatch = block.match(/ANSWER:\s*(.+?)(?=\n|$)/i);
|
||||
const reasoningMatch = block.match(/REASONING:\s*(.+?)(?=\n\n|$)/is);
|
||||
|
||||
const selectedLabel = answerMatch?.[1]?.trim() || '';
|
||||
|
||||
// Find matching option by label (case-insensitive partial match)
|
||||
const matchedOption = q.options.find(
|
||||
(opt) =>
|
||||
opt.label.toLowerCase().includes(selectedLabel.toLowerCase()) ||
|
||||
selectedLabel.toLowerCase().includes(opt.label.toLowerCase())
|
||||
);
|
||||
|
||||
answers[q.question] = matchedOption?.label || q.options[0].label;
|
||||
reasoning[q.question] = reasoningMatch?.[1]?.trim() || 'No reasoning provided';
|
||||
});
|
||||
|
||||
return { answers, reasoning };
|
||||
}
|
||||
|
||||
function generateFallbackAnswers(
|
||||
askInput: AskUserQuestionInput,
|
||||
step: StepName
|
||||
): IntelligentAnswers {
|
||||
// Simple fallback: pick first option for most questions
|
||||
// For approval questions, approve; for testing, skip
|
||||
const answers: Record<string, string> = {};
|
||||
const reasoning: Record<string, string> = {};
|
||||
|
||||
for (const q of askInput.questions) {
|
||||
const questionLower = q.question.toLowerCase();
|
||||
|
||||
if (questionLower.includes('approve') || questionLower.includes('proceed')) {
|
||||
const approveOption = q.options.find(
|
||||
(o) =>
|
||||
o.label.toLowerCase().includes('approve') ||
|
||||
o.label.toLowerCase().includes('yes')
|
||||
);
|
||||
answers[q.question] = approveOption?.label || q.options[0].label;
|
||||
reasoning[q.question] = 'Fallback approval (LLM unavailable)';
|
||||
} else if (questionLower.includes('test')) {
|
||||
const skipOption = q.options.find(
|
||||
(o) =>
|
||||
o.label.toLowerCase().includes('skip') ||
|
||||
o.label.toLowerCase().includes('none')
|
||||
);
|
||||
answers[q.question] = skipOption?.label || q.options[0].label;
|
||||
reasoning[q.question] = 'Fallback skip (LLM unavailable)';
|
||||
} else {
|
||||
answers[q.question] = q.options[0].label;
|
||||
reasoning[q.question] = 'Fallback first option (LLM unavailable)';
|
||||
}
|
||||
}
|
||||
|
||||
return { answers, reasoning };
|
||||
}
|
||||
@@ -0,0 +1,113 @@
|
||||
import type { ExecutionObservation, StepName } from './types.js';
|
||||
|
||||
/**
|
||||
* Collects detailed observations during step execution.
|
||||
* Tracks tool usage, messages, errors, file changes, and questions asked.
|
||||
*/
|
||||
export class ObservationCollector {
|
||||
private observations: ExecutionObservation;
|
||||
private recentToolKeys: Set<string> = new Set();
|
||||
|
||||
constructor(step: StepName) {
|
||||
this.observations = {
|
||||
step,
|
||||
startTime: Date.now(),
|
||||
endTime: 0,
|
||||
tools: [],
|
||||
assistantMessages: [],
|
||||
errors: [],
|
||||
filesCreated: [],
|
||||
filesModified: [],
|
||||
questionsAsked: [],
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Records a tool invocation with its input and output.
|
||||
* Deduplicates if the same tool+input is recorded from both canUseTool and the message stream.
|
||||
*/
|
||||
recordToolUse(
|
||||
toolName: string,
|
||||
input: Record<string, unknown>,
|
||||
output: unknown,
|
||||
allowed: boolean
|
||||
): void {
|
||||
// Deduplicate based on tool name + serialized input (within a short time window)
|
||||
const key = `${toolName}:${JSON.stringify(input)}`;
|
||||
if (this.recentToolKeys.has(key)) {
|
||||
return;
|
||||
}
|
||||
this.recentToolKeys.add(key);
|
||||
// Clean up old keys periodically to avoid unbounded growth
|
||||
if (this.recentToolKeys.size > 500) {
|
||||
const entries = [...this.recentToolKeys];
|
||||
this.recentToolKeys = new Set(entries.slice(entries.length - 250));
|
||||
}
|
||||
|
||||
this.observations.tools.push({
|
||||
toolName,
|
||||
input,
|
||||
output,
|
||||
timestamp: Date.now(),
|
||||
allowed,
|
||||
autoAnswered: toolName === 'AskUserQuestion',
|
||||
});
|
||||
|
||||
// Extract file paths from common tools
|
||||
if (toolName === 'Write' && input.file_path) {
|
||||
this.observations.filesCreated.push(input.file_path as string);
|
||||
}
|
||||
if (toolName === 'Edit' && input.file_path) {
|
||||
this.observations.filesModified.push(input.file_path as string);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Records messages from the session (assistant text, errors).
|
||||
*/
|
||||
recordMessage(message: any): void {
|
||||
if (message.type === 'assistant') {
|
||||
for (const block of message.message.content) {
|
||||
if (block.type === 'text') {
|
||||
this.observations.assistantMessages.push(block.text);
|
||||
}
|
||||
}
|
||||
}
|
||||
if (message.type === 'error') {
|
||||
this.observations.errors.push(message.error?.message ?? 'Unknown error');
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Records a question that was asked and the LLM-generated answer.
|
||||
*/
|
||||
recordQuestion(
|
||||
question: string,
|
||||
options: Array<{ label: string; description: string }>,
|
||||
selectedAnswer: string,
|
||||
llmReasoning: string
|
||||
): void {
|
||||
this.observations.questionsAsked.push({
|
||||
question,
|
||||
options,
|
||||
llmReasoning,
|
||||
selectedAnswer,
|
||||
timestamp: Date.now(),
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
* Gets a snapshot of current observations (for real-time decision making).
|
||||
*/
|
||||
getSnapshot(): ExecutionObservation {
|
||||
return { ...this.observations, endTime: Date.now() };
|
||||
}
|
||||
|
||||
/**
|
||||
* Finalizes observations and returns the complete record.
|
||||
*/
|
||||
finalize(): ExecutionObservation {
|
||||
this.observations.endTime = Date.now();
|
||||
return { ...this.observations };
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,158 @@
|
||||
import type { StepName } from '../types.js';
|
||||
|
||||
export interface StepEvaluationCriteria {
|
||||
step: StepName;
|
||||
keyArtifacts: string[];
|
||||
qualityChecks: string[];
|
||||
commonPitfalls: string[];
|
||||
scoringGuidance: string;
|
||||
}
|
||||
|
||||
export const EVALUATION_CRITERIA: Record<StepName, StepEvaluationCriteria> = {
|
||||
init: {
|
||||
step: 'init',
|
||||
keyArtifacts: ['AGENTS.md', 'IDEA.md'],
|
||||
qualityChecks: [
|
||||
'AGENTS.md exists with project name and description',
|
||||
'AGENTS.md includes a brief intro line and a Status section indicating the project is in planning phase',
|
||||
'AGENTS.md does NOT contain hallucinated architecture, commands, file structures, or tech stack details',
|
||||
'No .agents-docs/ directory was created (too early for detail files)',
|
||||
'No project scaffolding (package.json, dependencies, src/) was created',
|
||||
'IDEA.md exists with the project idea',
|
||||
],
|
||||
commonPitfalls: [
|
||||
'Hallucinating architecture or tech stack details before the plan step',
|
||||
'Creating .agents-docs/ detail files with invented content',
|
||||
'Scaffolding project files or installing dependencies prematurely',
|
||||
],
|
||||
scoringGuidance: `
|
||||
100 = Perfect: AGENTS.md stub with intro line, project name/description, and status section. IDEA.md present. Nothing else created.
|
||||
85-95 = Good but minor extra content beyond the expected stub format (e.g., an extra placeholder heading)
|
||||
70-84 = AGENTS.md exists but includes some hallucinated details (e.g., assumed tech stack or commands)
|
||||
50-69 = Significant hallucination (e.g., .agents-docs/ created with invented content, project scaffolded)
|
||||
<50 = Major problems (e.g., AGENTS.md missing, full project structure hallucinated)
|
||||
|
||||
The expected AGENTS.md format is: intro line, Project Overview (name + description), and a Status section. This is the target for a 100 score.
|
||||
`,
|
||||
},
|
||||
|
||||
plan: {
|
||||
step: 'plan',
|
||||
keyArtifacts: ['specs/*/PLAN-DRAFT-*.md', 'IDEA.md'],
|
||||
qualityChecks: [
|
||||
'Plan breaks work into clear, achievable phases',
|
||||
'Each phase has specific goals and deliverables',
|
||||
'Technical approach is appropriate',
|
||||
'Scope is realistic for the idea',
|
||||
'Dependencies between phases are identified',
|
||||
],
|
||||
commonPitfalls: [
|
||||
'Phases too vague ("polish the app")',
|
||||
'Missing specific tasks within phases',
|
||||
'No testing strategy mentioned',
|
||||
'Overly ambitious scope',
|
||||
'Missing file paths or specific actions',
|
||||
],
|
||||
scoringGuidance: `
|
||||
100 = Exceptional plan: detailed phases, realistic scope, clear tasks, testing included
|
||||
85-95 = Good plan with minor improvements possible (e.g., one phase could be more specific)
|
||||
70-84 = Acceptable but has vague sections or missing testing strategy
|
||||
50-69 = Significant issues (e.g., multiple vague phases, unrealistic scope)
|
||||
<50 = Major problems (e.g., no clear phases, plan doesn't match idea)
|
||||
|
||||
Most plans should score 70-85. Be critical of vague language.
|
||||
`,
|
||||
},
|
||||
|
||||
document: {
|
||||
step: 'document',
|
||||
keyArtifacts: ['specs/*/overview.md', 'specs/*/phase-*.md files'],
|
||||
qualityChecks: [
|
||||
'overview.md provides clear project summary',
|
||||
'Each phase file has specific tasks with checkboxes',
|
||||
'File paths are explicit (not generic)',
|
||||
'Dependencies between tasks are identified',
|
||||
'Technical details are specific',
|
||||
'Acceptance criteria are clear',
|
||||
],
|
||||
commonPitfalls: [
|
||||
'Tasks too generic ("implement feature X")',
|
||||
'Missing file paths',
|
||||
'No checkboxes or unclear task structure',
|
||||
'Missing dependencies',
|
||||
'Overly verbose or lacking specifics',
|
||||
],
|
||||
scoringGuidance: `
|
||||
100 = Exceptional documentation: specific tasks, explicit file paths, clear dependencies
|
||||
85-95 = Good documentation with minor vagueness in one or two tasks
|
||||
70-84 = Acceptable but multiple tasks lack specifics or file paths
|
||||
50-69 = Significant issues (e.g., many generic tasks, missing file paths)
|
||||
<50 = Major problems (e.g., tasks don't match plan, fundamentally vague)
|
||||
|
||||
Most documentation should score 70-85. Penalize generic language heavily.
|
||||
`,
|
||||
},
|
||||
|
||||
implement: {
|
||||
step: 'implement',
|
||||
keyArtifacts: ['actual code files', 'checked-off tasks in phase files'],
|
||||
qualityChecks: [
|
||||
'Phase tasks are being completed',
|
||||
'Code files are actually created/modified',
|
||||
'Implementation follows the documented plan',
|
||||
'No major errors blocking progress',
|
||||
'Tests are written (if applicable)',
|
||||
],
|
||||
commonPitfalls: [
|
||||
'Tasks marked complete but files not actually changed',
|
||||
'Implementation deviates significantly from plan',
|
||||
'Errors not addressed',
|
||||
'Skipping tests without justification',
|
||||
'Working on wrong phase',
|
||||
],
|
||||
scoringGuidance: `
|
||||
100 = Exceptional implementation: all tasks complete, code works, tests pass
|
||||
85-95 = Good implementation with minor issues or incomplete tests
|
||||
70-84 = Acceptable but some tasks incomplete or code has issues
|
||||
50-69 = Significant issues (e.g., many tasks incomplete, code doesn't work)
|
||||
<50 = Major problems (e.g., wrong phase, no actual work done)
|
||||
|
||||
Implementation scoring depends heavily on actual progress. Be realistic.
|
||||
`,
|
||||
},
|
||||
|
||||
finalize: {
|
||||
step: 'finalize',
|
||||
keyArtifacts: ['specs--completed/', 'README or docs', 'final code state'],
|
||||
qualityChecks: [
|
||||
'All phases are marked complete',
|
||||
'Spec moved to specs--completed/',
|
||||
'Documentation is updated',
|
||||
'Code is in working state',
|
||||
'No obvious loose ends',
|
||||
],
|
||||
commonPitfalls: [
|
||||
'Incomplete phases',
|
||||
'Missing specs--completed/ move',
|
||||
'Documentation not updated',
|
||||
'Code broken or incomplete',
|
||||
'Unrealistic self-assessment',
|
||||
],
|
||||
scoringGuidance: `
|
||||
100 = Exceptional finalization: everything complete, polished, documented
|
||||
85-95 = Good finalization with minor issues
|
||||
70-84 = Acceptable but some loose ends or documentation gaps
|
||||
50-69 = Significant issues (e.g., incomplete phases, broken code)
|
||||
<50 = Major problems (e.g., work not actually done, fundamentally incomplete)
|
||||
|
||||
Finalize scores should reflect overall project quality. Be honest.
|
||||
`,
|
||||
},
|
||||
};
|
||||
|
||||
/**
|
||||
* Gets evaluation criteria for a specific step.
|
||||
*/
|
||||
export function getCriteriaForStep(step: StepName): StepEvaluationCriteria {
|
||||
return EVALUATION_CRITERIA[step];
|
||||
}
|
||||
@@ -0,0 +1,58 @@
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { buildStepPrompt } from './step-instructions.js';
|
||||
import type { BotConfig } from '../types.js';
|
||||
|
||||
const config: BotConfig = {
|
||||
workDir: '/tmp/work',
|
||||
projectDir: '/tmp/work/my-app',
|
||||
ideaDescription: 'A todo app with drag-and-drop',
|
||||
ideaName: 'drag-todo',
|
||||
mode: 'new-project',
|
||||
};
|
||||
|
||||
describe('buildStepPrompt', () => {
|
||||
it('each step includes the autonomous preamble', () => {
|
||||
const steps = ['init', 'plan', 'document', 'implement', 'finalize'] as const;
|
||||
for (const step of steps) {
|
||||
const prompt = buildStepPrompt(step, config);
|
||||
expect(prompt).toContain('running autonomously');
|
||||
}
|
||||
});
|
||||
|
||||
it('init prompt includes /plan2code-init skill invocation', () => {
|
||||
const prompt = buildStepPrompt('init', config);
|
||||
expect(prompt).toContain('/plan2code-init');
|
||||
});
|
||||
|
||||
it('plan prompt includes /plan2code-1-plan skill invocation', () => {
|
||||
const prompt = buildStepPrompt('plan', config);
|
||||
expect(prompt).toContain('/plan2code-1-plan');
|
||||
});
|
||||
|
||||
it('document prompt includes /plan2code-2-document skill invocation', () => {
|
||||
const prompt = buildStepPrompt('document', config);
|
||||
expect(prompt).toContain('/plan2code-2-document');
|
||||
});
|
||||
|
||||
it('implement prompt instructs direct tool usage without skill invocation', () => {
|
||||
const prompt = buildStepPrompt('implement', config);
|
||||
expect(prompt).toContain('Do NOT use the Skill tool');
|
||||
});
|
||||
|
||||
it('finalize prompt includes /plan2code-4-finalize skill invocation', () => {
|
||||
const prompt = buildStepPrompt('finalize', config);
|
||||
expect(prompt).toContain('/plan2code-4-finalize');
|
||||
});
|
||||
|
||||
it('plan prompt includes project name and description', () => {
|
||||
const prompt = buildStepPrompt('plan', config);
|
||||
expect(prompt).toContain('drag-todo');
|
||||
expect(prompt).toContain('A todo app with drag-and-drop');
|
||||
});
|
||||
|
||||
it('init prompt includes project name and description', () => {
|
||||
const prompt = buildStepPrompt('init', config);
|
||||
expect(prompt).toContain('drag-todo');
|
||||
expect(prompt).toContain('A todo app with drag-and-drop');
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,131 @@
|
||||
import type { BotConfig, StepName } from '../types.js';
|
||||
|
||||
const AUTONOMOUS_PREAMBLE = `You are running autonomously as part of an automated test pipeline. Do NOT pause for human input. When you encounter questions or approval gates, make reasonable decisions and proceed. If asked for confirmation, approve. If asked to choose, pick the most reasonable option. Complete the entire step without stopping.`;
|
||||
|
||||
export function buildStepPrompt(step: StepName, config: BotConfig): string {
|
||||
switch (step) {
|
||||
case 'init':
|
||||
return buildInitPrompt(config);
|
||||
case 'plan':
|
||||
return buildPlanPrompt(config);
|
||||
case 'document':
|
||||
return buildDocumentPrompt(config);
|
||||
case 'implement':
|
||||
return buildImplementPrompt(config);
|
||||
case 'finalize':
|
||||
return buildFinalizePrompt(config);
|
||||
}
|
||||
}
|
||||
|
||||
function buildInitPrompt(config: BotConfig): string {
|
||||
return `${AUTONOMOUS_PREAMBLE}
|
||||
|
||||
This is a brand new project with no existing code. Create a minimal stub AGENTS.md file and an IDEA.md file. Do NOT run the /plan2code-init skill — there is no codebase to analyze yet.
|
||||
|
||||
The project idea is: ${config.ideaDescription}
|
||||
The project name is: ${config.ideaName}
|
||||
|
||||
## What to create
|
||||
|
||||
### AGENTS.md
|
||||
Create a minimal stub with ONLY the following — do NOT invent architecture, tech stack details, commands, or file structures:
|
||||
|
||||
\`\`\`markdown
|
||||
# AGENTS.md
|
||||
|
||||
This file provides guidance to AI coding agents when working with code in this repository.
|
||||
|
||||
## Project Overview
|
||||
**Name:** ${config.ideaName}
|
||||
**Description:** ${config.ideaDescription}
|
||||
|
||||
## Status
|
||||
This project is in the planning phase. Architecture, commands, and detailed documentation will be added after the plan and document steps are complete.
|
||||
\`\`\`
|
||||
|
||||
### IDEA.md
|
||||
If IDEA.md does not already exist, create it with the project name and description.
|
||||
|
||||
## Rules
|
||||
- Do NOT create .agents-docs/ or any detail files — there is nothing to document yet
|
||||
- Do NOT hallucinate architecture, dependencies, file structures, or tech stack choices
|
||||
- Do NOT install dependencies or scaffold project files
|
||||
- ONLY create the two files above`;
|
||||
}
|
||||
|
||||
function buildPlanPrompt(config: BotConfig): string {
|
||||
return `${AUTONOMOUS_PREAMBLE}
|
||||
|
||||
Run the /plan2code-1-plan skill to create a plan for this project.
|
||||
|
||||
Read the IDEA.md file first to understand the project. The project is: ${config.ideaDescription}
|
||||
|
||||
When making decisions during planning:
|
||||
- Set confidence levels reasonably high (85-95%)
|
||||
- Accept the generated tech stack without revision
|
||||
- Do not request additional reference files
|
||||
- Approve the plan when asked for sign-off
|
||||
- Keep scope small and achievable (3-4 phases max)
|
||||
- Use the project name: ${config.ideaName}`;
|
||||
}
|
||||
|
||||
function buildDocumentPrompt(config: BotConfig): string {
|
||||
return `${AUTONOMOUS_PREAMBLE}
|
||||
|
||||
Run the /plan2code-2-document skill to transform the plan into implementation specs.
|
||||
|
||||
Read the existing plan output in specs/ first to understand what was planned.
|
||||
|
||||
When making decisions:
|
||||
- Accept all generated documentation
|
||||
- Approve phase breakdowns and task lists
|
||||
- Do not request changes to the generated docs`;
|
||||
}
|
||||
|
||||
function buildImplementPrompt(config: BotConfig): string {
|
||||
return `${AUTONOMOUS_PREAMBLE}
|
||||
|
||||
You are a senior software engineer implementing a project phase. Do NOT use the Skill tool — implement directly using Read, Write, Edit, Glob, and Grep tools.
|
||||
|
||||
## Process
|
||||
|
||||
1. **Find the spec**: Read \`specs/*/overview.md\` to find the phase checklist
|
||||
2. **Pick the next phase**: Find the first phase marked \`[ ]\` (pending) or \`[/]\` (in-progress)
|
||||
3. **Read the phase file**: Read the corresponding \`phase-X.md\` from the same directory
|
||||
4. **Mark phase in-progress**: Update \`[ ]\` to \`[/]\` in overview.md
|
||||
5. **Implement each task sequentially**:
|
||||
- Read the task specification completely
|
||||
- Write the code using Write or Edit tools — create real files, not code blocks
|
||||
- Mark the task \`[x]\` in the phase file immediately after completing it
|
||||
6. **Complete the phase**: After all tasks, fill in the "Phase Completion Summary" in the phase file
|
||||
7. **Mark phase complete**: Update \`[/]\` to \`[x]\` in overview.md
|
||||
|
||||
## Rules
|
||||
|
||||
- Follow AGENTS.md if it exists
|
||||
- Implement specs EXACTLY — no creative additions or unsolicited improvements
|
||||
- Write task completion status (\`[x]\`) to disk immediately after each task — never batch
|
||||
- Only create files mentioned in the spec tasks
|
||||
- Use the specified file paths, function names, and structures from the spec
|
||||
- No placeholder code — fully implement every function
|
||||
- Match existing codebase conventions
|
||||
- Do NOT run git commands
|
||||
- Skip running tests unless explicitly listed as a phase task
|
||||
|
||||
## Project info
|
||||
- Project: ${config.ideaName}
|
||||
- Description: ${config.ideaDescription}
|
||||
- Project directory: ${config.projectDir}`;
|
||||
}
|
||||
|
||||
function buildFinalizePrompt(config: BotConfig): string {
|
||||
return `${AUTONOMOUS_PREAMBLE}
|
||||
|
||||
Run the /plan2code-4-finalize skill to validate and archive the completed project.
|
||||
|
||||
When making decisions:
|
||||
- Approve all documentation updates
|
||||
- Accept the completion summary
|
||||
- If asked for a rating or feedback, give 8/10 and positive feedback
|
||||
- Complete the archival process fully`;
|
||||
}
|
||||
@@ -0,0 +1,82 @@
|
||||
import { describe, it, expect, vi } from 'vitest';
|
||||
|
||||
// Mock the SDK before importing session-runner
|
||||
vi.mock('@anthropic-ai/claude-agent-sdk', () => ({
|
||||
query: vi.fn(),
|
||||
}));
|
||||
|
||||
import { query } from '@anthropic-ai/claude-agent-sdk';
|
||||
import { runSession } from './session-runner.js';
|
||||
import { ObservationCollector } from './observation-collector.js';
|
||||
import type { BotConfig } from './types.js';
|
||||
|
||||
const config: BotConfig = {
|
||||
workDir: '/tmp/work',
|
||||
projectDir: '/tmp/work/my-app',
|
||||
ideaDescription: 'test app',
|
||||
ideaName: 'test-app',
|
||||
mode: 'new-project',
|
||||
};
|
||||
|
||||
describe('runSession', () => {
|
||||
it('returns success: false when output is empty', async () => {
|
||||
// Simulate a session that yields an assistant message with empty text
|
||||
const mockQuery = vi.mocked(query);
|
||||
mockQuery.mockReturnValue(
|
||||
(async function* () {
|
||||
yield {
|
||||
type: 'assistant' as const,
|
||||
session_id: 'sess-1',
|
||||
message: { content: [{ type: 'text' as const, text: '' }] },
|
||||
};
|
||||
yield {
|
||||
type: 'result' as const,
|
||||
session_id: 'sess-1',
|
||||
};
|
||||
})() as any,
|
||||
);
|
||||
|
||||
const collector = new ObservationCollector('init');
|
||||
const result = await runSession({
|
||||
prompt: 'do something',
|
||||
config,
|
||||
step: 'init',
|
||||
collector,
|
||||
});
|
||||
|
||||
expect(result.success).toBe(false);
|
||||
expect(result.output.trim()).toBe('');
|
||||
expect(result.observations).toBeDefined();
|
||||
});
|
||||
|
||||
it('returns success: true when output has content', async () => {
|
||||
const mockQuery = vi.mocked(query);
|
||||
mockQuery.mockReturnValue(
|
||||
(async function* () {
|
||||
yield {
|
||||
type: 'assistant' as const,
|
||||
session_id: 'sess-2',
|
||||
message: { content: [{ type: 'text' as const, text: 'AGENTS.md has been created successfully' }] },
|
||||
};
|
||||
yield {
|
||||
type: 'result' as const,
|
||||
session_id: 'sess-2',
|
||||
};
|
||||
})() as any,
|
||||
);
|
||||
|
||||
const collector = new ObservationCollector('init');
|
||||
const result = await runSession({
|
||||
prompt: 'do something',
|
||||
config,
|
||||
step: 'init',
|
||||
collector,
|
||||
});
|
||||
|
||||
expect(result.success).toBe(true);
|
||||
expect(result.output).toContain('AGENTS.md');
|
||||
expect(result.sessionId).toBe('sess-2');
|
||||
expect(result.observations).toBeDefined();
|
||||
expect(result.observations.step).toBe('init');
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,77 @@
|
||||
import { query } from '@anthropic-ai/claude-agent-sdk';
|
||||
import { createIntelligentResponder } from './intelligent-responder.js';
|
||||
import type { BotConfig, ExecutionObservation, StepName } from './types.js';
|
||||
import type { ObservationCollector } from './observation-collector.js';
|
||||
|
||||
export interface SessionOptions {
|
||||
prompt: string;
|
||||
config: BotConfig;
|
||||
step: StepName;
|
||||
maxTurns?: number;
|
||||
collector: ObservationCollector;
|
||||
}
|
||||
|
||||
export interface SessionResult {
|
||||
sessionId: string | null;
|
||||
output: string;
|
||||
success: boolean;
|
||||
duration: number;
|
||||
observations: ExecutionObservation;
|
||||
}
|
||||
|
||||
export async function runSession(options: SessionOptions): Promise<SessionResult> {
|
||||
const { prompt, config, step, maxTurns = 50, collector } = options;
|
||||
const startTime = Date.now();
|
||||
let output = '';
|
||||
let sessionId: string | null = null;
|
||||
|
||||
try {
|
||||
const session = query({
|
||||
prompt,
|
||||
options: {
|
||||
cwd: config.projectDir,
|
||||
maxTurns,
|
||||
permissionMode: 'bypassPermissions',
|
||||
allowDangerouslySkipPermissions: true,
|
||||
canUseTool: createIntelligentResponder(config, step, collector),
|
||||
systemPrompt: { type: 'preset', preset: 'claude_code' },
|
||||
settingSources: ['project'],
|
||||
},
|
||||
});
|
||||
|
||||
for await (const message of session) {
|
||||
// Record all messages for observations
|
||||
collector.recordMessage(message);
|
||||
|
||||
if (message.type === 'assistant') {
|
||||
sessionId = message.session_id ?? sessionId;
|
||||
for (const block of message.message.content) {
|
||||
if (block.type === 'text') {
|
||||
output += block.text + '\n';
|
||||
} else if (block.type === 'tool_use') {
|
||||
// Capture tool invocations from the message stream as a fallback
|
||||
// in case canUseTool doesn't fire (e.g., Skill sub-sessions)
|
||||
collector.recordToolUse(
|
||||
block.name,
|
||||
block.input as Record<string, unknown>,
|
||||
undefined,
|
||||
true
|
||||
);
|
||||
}
|
||||
}
|
||||
} else if (message.type === 'result') {
|
||||
sessionId = message.session_id ?? sessionId;
|
||||
}
|
||||
}
|
||||
|
||||
const duration = Date.now() - startTime;
|
||||
const hasOutput = output.trim().length > 0;
|
||||
const observations = collector.finalize();
|
||||
return { sessionId, output, success: hasOutput, duration, observations };
|
||||
} catch (error) {
|
||||
const duration = Date.now() - startTime;
|
||||
const errorMsg = error instanceof Error ? error.message : String(error);
|
||||
const observations = collector.finalize();
|
||||
return { sessionId, output, success: false, duration, observations };
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,164 @@
|
||||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||||
import fs from 'fs-extra';
|
||||
import os from 'os';
|
||||
import path from 'path';
|
||||
import { checkAllPhasesComplete, detectStepCompletion } from './step-detector.js';
|
||||
|
||||
let tmpDir: string;
|
||||
|
||||
beforeEach(() => {
|
||||
tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'p2c-test-'));
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
fs.removeSync(tmpDir);
|
||||
});
|
||||
|
||||
// ── checkAllPhasesComplete ──────────────────────────────────────────
|
||||
|
||||
describe('checkAllPhasesComplete', () => {
|
||||
it('returns false when no specs/ directory exists', () => {
|
||||
expect(checkAllPhasesComplete(tmpDir)).toBe(false);
|
||||
});
|
||||
|
||||
it('returns false when specs/ has no subdirectories', () => {
|
||||
fs.ensureDirSync(path.join(tmpDir, 'specs'));
|
||||
expect(checkAllPhasesComplete(tmpDir)).toBe(false);
|
||||
});
|
||||
|
||||
it('returns false when spec dir exists but has no overview.md and no phase files', () => {
|
||||
// This is the false-positive bug we fixed — an empty spec dir should NOT be "complete"
|
||||
fs.ensureDirSync(path.join(tmpDir, 'specs', 'my-feature'));
|
||||
expect(checkAllPhasesComplete(tmpDir)).toBe(false);
|
||||
});
|
||||
|
||||
it('returns true when overview.md has all phases checked [x]', () => {
|
||||
const specDir = path.join(tmpDir, 'specs', 'my-feature');
|
||||
fs.ensureDirSync(specDir);
|
||||
fs.writeFileSync(
|
||||
path.join(specDir, 'overview.md'),
|
||||
`# Overview\n- [x] Phase 1: Setup\n- [x] Phase 2: Core\n- [x] Phase 3: Polish\n`,
|
||||
);
|
||||
expect(checkAllPhasesComplete(tmpDir)).toBe(true);
|
||||
});
|
||||
|
||||
it('returns false when overview.md has unchecked [ ] phases', () => {
|
||||
const specDir = path.join(tmpDir, 'specs', 'my-feature');
|
||||
fs.ensureDirSync(specDir);
|
||||
fs.writeFileSync(
|
||||
path.join(specDir, 'overview.md'),
|
||||
`# Overview\n- [x] Phase 1: Setup\n- [ ] Phase 2: Core\n- [ ] Phase 3: Polish\n`,
|
||||
);
|
||||
expect(checkAllPhasesComplete(tmpDir)).toBe(false);
|
||||
});
|
||||
|
||||
it('returns true via fallback: phase-*.md files with all checked, no overview.md', () => {
|
||||
const specDir = path.join(tmpDir, 'specs', 'my-feature');
|
||||
fs.ensureDirSync(specDir);
|
||||
fs.writeFileSync(
|
||||
path.join(specDir, 'phase-1.md'),
|
||||
`# Phase 1\n- [x] Task A\n- [x] Task B\n`,
|
||||
);
|
||||
fs.writeFileSync(
|
||||
path.join(specDir, 'phase-2.md'),
|
||||
`# Phase 2\n- [x] Task C\n`,
|
||||
);
|
||||
expect(checkAllPhasesComplete(tmpDir)).toBe(true);
|
||||
});
|
||||
|
||||
it('returns false via fallback: phase-*.md with unchecked items', () => {
|
||||
const specDir = path.join(tmpDir, 'specs', 'my-feature');
|
||||
fs.ensureDirSync(specDir);
|
||||
fs.writeFileSync(
|
||||
path.join(specDir, 'phase-1.md'),
|
||||
`# Phase 1\n- [x] Task A\n- [ ] Task B\n`,
|
||||
);
|
||||
expect(checkAllPhasesComplete(tmpDir)).toBe(false);
|
||||
});
|
||||
|
||||
it('returns true via nested phases/ subdirectory fallback with all checked', () => {
|
||||
const specDir = path.join(tmpDir, 'specs', 'my-feature');
|
||||
const phasesDir = path.join(specDir, 'phases');
|
||||
fs.ensureDirSync(phasesDir);
|
||||
fs.writeFileSync(
|
||||
path.join(phasesDir, 'phase-1.md'),
|
||||
`# Phase 1\n- [x] Task A\n- [x] Task B\n`,
|
||||
);
|
||||
expect(checkAllPhasesComplete(tmpDir)).toBe(true);
|
||||
});
|
||||
|
||||
it('returns false via nested phases/ with unchecked items', () => {
|
||||
const specDir = path.join(tmpDir, 'specs', 'my-feature');
|
||||
const phasesDir = path.join(specDir, 'phases');
|
||||
fs.ensureDirSync(phasesDir);
|
||||
fs.writeFileSync(
|
||||
path.join(phasesDir, 'phase-1.md'),
|
||||
`# Phase 1\n- [x] Task A\n- [ ] Task B\n`,
|
||||
);
|
||||
expect(checkAllPhasesComplete(tmpDir)).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
// ── detectStepCompletion ────────────────────────────────────────────
|
||||
|
||||
describe('detectStepCompletion', () => {
|
||||
it('init: completed when output mentions agents.md created', () => {
|
||||
const result = detectStepCompletion('AGENTS.md has been created successfully', 'init');
|
||||
expect(result.completed).toBe(true);
|
||||
expect(result.nextStep).toBe('plan');
|
||||
});
|
||||
|
||||
it('init: not completed for unrelated output', () => {
|
||||
const result = detectStepCompletion('Hello world, nothing happened', 'init');
|
||||
expect(result.completed).toBe(false);
|
||||
expect(result.nextStep).toBeNull();
|
||||
});
|
||||
|
||||
it('plan: completed when plan is saved', () => {
|
||||
const result = detectStepCompletion('The plan has been saved and finalized', 'plan');
|
||||
expect(result.completed).toBe(true);
|
||||
expect(result.nextStep).toBe('document');
|
||||
});
|
||||
|
||||
it('plan: not completed for unrelated output', () => {
|
||||
const result = detectStepCompletion('Reading the codebase...', 'plan');
|
||||
expect(result.completed).toBe(false);
|
||||
expect(result.nextStep).toBeNull();
|
||||
});
|
||||
|
||||
it('document: completed when overview.md is mentioned', () => {
|
||||
const result = detectStepCompletion('Created overview.md with all phases', 'document');
|
||||
expect(result.completed).toBe(true);
|
||||
expect(result.nextStep).toBe('implement');
|
||||
});
|
||||
|
||||
it('document: not completed for unrelated output', () => {
|
||||
const result = detectStepCompletion('Thinking about the design...', 'document');
|
||||
expect(result.completed).toBe(false);
|
||||
expect(result.nextStep).toBeNull();
|
||||
});
|
||||
|
||||
it('implement: completed when phase is done', () => {
|
||||
const result = detectStepCompletion('Phase 1 is now complete!', 'implement');
|
||||
expect(result.completed).toBe(true);
|
||||
expect(result.nextStep).toBe('finalize');
|
||||
});
|
||||
|
||||
it('implement: not completed for unrelated output', () => {
|
||||
const result = detectStepCompletion('Working on some files', 'implement');
|
||||
expect(result.completed).toBe(false);
|
||||
expect(result.nextStep).toBeNull();
|
||||
});
|
||||
|
||||
it('finalize: completed when finalize is done', () => {
|
||||
const result = detectStepCompletion('Finalize step is complete and archived', 'finalize');
|
||||
expect(result.completed).toBe(true);
|
||||
expect(result.nextStep).toBeNull(); // last step
|
||||
});
|
||||
|
||||
it('finalize: not completed for unrelated output', () => {
|
||||
const result = detectStepCompletion('Just starting...', 'finalize');
|
||||
expect(result.completed).toBe(false);
|
||||
expect(result.nextStep).toBeNull();
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,151 @@
|
||||
import fs from 'fs-extra';
|
||||
import path from 'path';
|
||||
import type { StepName } from './types.js';
|
||||
|
||||
export interface DetectionResult {
|
||||
completed: boolean;
|
||||
nextStep: StepName | null;
|
||||
needsAnotherImplementPass: boolean;
|
||||
}
|
||||
|
||||
const STEP_ORDER: StepName[] = ['init', 'plan', 'document', 'implement', 'finalize'];
|
||||
|
||||
export function detectStepCompletion(output: string, step: StepName): DetectionResult {
|
||||
const lowerOutput = output.toLowerCase();
|
||||
|
||||
let completed = false;
|
||||
|
||||
switch (step) {
|
||||
case 'init':
|
||||
completed = lowerOutput.includes('agents.md') && (
|
||||
lowerOutput.includes('created') ||
|
||||
lowerOutput.includes('generated') ||
|
||||
lowerOutput.includes('written')
|
||||
);
|
||||
break;
|
||||
|
||||
case 'plan':
|
||||
completed = lowerOutput.includes('plan') && (
|
||||
lowerOutput.includes('complete') ||
|
||||
lowerOutput.includes('approved') ||
|
||||
lowerOutput.includes('finalized') ||
|
||||
lowerOutput.includes('saved')
|
||||
);
|
||||
break;
|
||||
|
||||
case 'document':
|
||||
completed = lowerOutput.includes('overview.md') || (
|
||||
lowerOutput.includes('document') && lowerOutput.includes('complete')
|
||||
);
|
||||
break;
|
||||
|
||||
case 'implement':
|
||||
completed = lowerOutput.includes('phase') && (
|
||||
lowerOutput.includes('complete') ||
|
||||
lowerOutput.includes('done') ||
|
||||
lowerOutput.includes('finished')
|
||||
);
|
||||
break;
|
||||
|
||||
case 'finalize':
|
||||
completed = lowerOutput.includes('finalize') && (
|
||||
lowerOutput.includes('complete') ||
|
||||
lowerOutput.includes('archived') ||
|
||||
lowerOutput.includes('done')
|
||||
);
|
||||
break;
|
||||
}
|
||||
|
||||
// Determine next step
|
||||
const currentIdx = STEP_ORDER.indexOf(step);
|
||||
const nextStep = currentIdx < STEP_ORDER.length - 1 ? STEP_ORDER[currentIdx + 1] : null;
|
||||
|
||||
return {
|
||||
completed,
|
||||
nextStep: completed ? nextStep : null,
|
||||
needsAnotherImplementPass: false,
|
||||
};
|
||||
}
|
||||
|
||||
export function checkAllPhasesComplete(projectDir: string): boolean {
|
||||
const specsDir = path.join(projectDir, 'specs');
|
||||
|
||||
if (!fs.existsSync(specsDir)) {
|
||||
return false;
|
||||
}
|
||||
|
||||
const entries = fs.readdirSync(specsDir, { withFileTypes: true });
|
||||
const specDirs = entries.filter((e) => e.isDirectory());
|
||||
|
||||
if (specDirs.length === 0) {
|
||||
return false;
|
||||
}
|
||||
|
||||
let foundPhaseTracking = false;
|
||||
|
||||
for (const dir of specDirs) {
|
||||
const specPath = path.join(specsDir, dir.name);
|
||||
|
||||
// Try overview.md first
|
||||
const overviewPath = path.join(specPath, 'overview.md');
|
||||
if (fs.existsSync(overviewPath)) {
|
||||
foundPhaseTracking = true;
|
||||
if (hasUncheckedPhases(fs.readFileSync(overviewPath, 'utf-8'))) {
|
||||
return false;
|
||||
}
|
||||
continue;
|
||||
}
|
||||
|
||||
// Fallback: look for phase-*.md or PHASE-*.md in the spec dir
|
||||
const phaseFiles = findPhaseFiles(specPath);
|
||||
if (phaseFiles.length > 0) {
|
||||
foundPhaseTracking = true;
|
||||
for (const pf of phaseFiles) {
|
||||
if (hasUncheckedPhases(fs.readFileSync(pf, 'utf-8'))) {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
continue;
|
||||
}
|
||||
|
||||
// Fallback: look inside a phases/ subdirectory
|
||||
const phasesSubdir = path.join(specPath, 'phases');
|
||||
if (fs.existsSync(phasesSubdir)) {
|
||||
const subPhaseFiles = findPhaseFiles(phasesSubdir);
|
||||
if (subPhaseFiles.length > 0) {
|
||||
foundPhaseTracking = true;
|
||||
for (const pf of subPhaseFiles) {
|
||||
if (hasUncheckedPhases(fs.readFileSync(pf, 'utf-8'))) {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Only return true if we positively confirmed all phases are checked off
|
||||
return foundPhaseTracking;
|
||||
}
|
||||
|
||||
function hasUncheckedPhases(content: string): boolean {
|
||||
const lines = content.split('\n');
|
||||
|
||||
const phaseLines = lines.filter((line) =>
|
||||
line.match(/^[-*]\s*\[[ x]\]/i) && line.toLowerCase().includes('phase')
|
||||
);
|
||||
|
||||
if (phaseLines.length > 0) {
|
||||
return phaseLines.some((line) => line.includes('[ ]'));
|
||||
}
|
||||
|
||||
// No phase-specific checkboxes — check for any unchecked boxes
|
||||
return lines.some((line) => /^[-*]\s*\[ \]/.test(line));
|
||||
}
|
||||
|
||||
function findPhaseFiles(dir: string): string[] {
|
||||
if (!fs.existsSync(dir)) return [];
|
||||
const entries = fs.readdirSync(dir);
|
||||
return entries
|
||||
.filter((name) => /^phase[-_]?\d+.*\.md$/i.test(name))
|
||||
.map((name) => path.join(dir, name));
|
||||
}
|
||||
@@ -0,0 +1,70 @@
|
||||
export type BotMode = 'new-project' | 'enhancement';
|
||||
|
||||
export interface BotConfig {
|
||||
workDir: string;
|
||||
projectDir: string;
|
||||
ideaDescription: string;
|
||||
ideaName: string;
|
||||
mode: BotMode;
|
||||
}
|
||||
|
||||
export type StepName = 'init' | 'plan' | 'document' | 'implement' | 'finalize';
|
||||
|
||||
export interface ToolObservation {
|
||||
toolName: string;
|
||||
input: Record<string, unknown>;
|
||||
output?: unknown;
|
||||
timestamp: number;
|
||||
allowed: boolean;
|
||||
autoAnswered?: boolean;
|
||||
}
|
||||
|
||||
export interface QuestionContext {
|
||||
question: string;
|
||||
options: Array<{ label: string; description: string }>;
|
||||
llmReasoning: string;
|
||||
selectedAnswer: string;
|
||||
timestamp: number;
|
||||
}
|
||||
|
||||
export interface ExecutionObservation {
|
||||
step: StepName;
|
||||
startTime: number;
|
||||
endTime: number;
|
||||
tools: ToolObservation[];
|
||||
assistantMessages: string[];
|
||||
errors: string[];
|
||||
filesCreated: string[];
|
||||
filesModified: string[];
|
||||
questionsAsked: QuestionContext[];
|
||||
}
|
||||
|
||||
export interface EvaluationResult {
|
||||
step: StepName;
|
||||
score: number;
|
||||
strengths: string[];
|
||||
weaknesses: string[];
|
||||
suggestions: string[];
|
||||
criticalIssues: string[];
|
||||
timestamp: number;
|
||||
evaluatorModel: string;
|
||||
reasoning: string;
|
||||
}
|
||||
|
||||
export interface StepResult {
|
||||
step: StepName;
|
||||
success: boolean;
|
||||
sessionId: string | null;
|
||||
duration: number;
|
||||
error: string | null;
|
||||
evaluation?: EvaluationResult;
|
||||
observations?: ExecutionObservation;
|
||||
}
|
||||
|
||||
export interface BotState {
|
||||
config: BotConfig;
|
||||
steps: StepResult[];
|
||||
currentStep: StepName | null;
|
||||
implementPasses: number;
|
||||
allPhasesComplete: boolean;
|
||||
}
|
||||
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"compilerOptions": {
|
||||
"target": "ES2022",
|
||||
"module": "ESNext",
|
||||
"moduleResolution": "bundler",
|
||||
"lib": ["ES2022"],
|
||||
"outDir": "dist",
|
||||
"rootDir": ".",
|
||||
"strict": true,
|
||||
"esModuleInterop": true,
|
||||
"skipLibCheck": true,
|
||||
"forceConsistentCasingInFileNames": true,
|
||||
"resolveJsonModule": true,
|
||||
"declaration": true,
|
||||
"declarationMap": true,
|
||||
"sourceMap": true
|
||||
},
|
||||
"include": ["src/**/*"],
|
||||
"exclude": ["node_modules", "dist"]
|
||||
}
|
||||
@@ -0,0 +1,15 @@
|
||||
import { defineConfig } from 'tsup';
|
||||
|
||||
export default defineConfig({
|
||||
entry: {
|
||||
'bin/plan2code-bot': 'src/bin/plan2code-bot.ts',
|
||||
index: 'src/index.ts',
|
||||
},
|
||||
format: ['esm'],
|
||||
dts: false,
|
||||
clean: true,
|
||||
sourcemap: true,
|
||||
banner: {
|
||||
js: '#!/usr/bin/env node',
|
||||
},
|
||||
});
|
||||
@@ -0,0 +1,7 @@
|
||||
import { defineConfig } from 'vitest/config';
|
||||
|
||||
export default defineConfig({
|
||||
test: {
|
||||
include: ['src/**/*.test.ts'],
|
||||
},
|
||||
});
|
||||
@@ -0,0 +1,212 @@
|
||||
# Plan2Code Loop
|
||||
|
||||
An autonomous CLI tool that implements Plan2Code specs by looping through tasks automatically.
|
||||
|
||||
> **Note:** This is an **alternative** to `/plan2code-3-implement`, not a replacement. Use the manual Step 3 workflow when you want interactive control over each phase, or use this loop when you prefer hands-off autonomous execution.
|
||||
|
||||
## Installation
|
||||
|
||||
```bash
|
||||
# From the plan2code root directory:
|
||||
|
||||
# Option 1: Install everything (recommended)
|
||||
node install.js # Select A (Advanced) → E (Everything)
|
||||
|
||||
# Option 2: Install loop only
|
||||
node install.js # Select A (Advanced) → O (Loop CLI)
|
||||
|
||||
# Option 3: Manual build and link
|
||||
cd plan2code-loop
|
||||
npm install
|
||||
npm run build
|
||||
npm link
|
||||
```
|
||||
|
||||
## Usage
|
||||
|
||||
Simply run the command - everything is interactive:
|
||||
|
||||
```bash
|
||||
plan2code-loop
|
||||
```
|
||||
|
||||
The CLI will:
|
||||
1. Auto-detect specs in `./specs/` directory
|
||||
2. Let you select a spec if multiple are found
|
||||
3. Prompt to continue if an existing session is found
|
||||
4. Ask for JIRA ticket ID, agent selection, loop mode, and max iterations
|
||||
|
||||
## How It Works
|
||||
|
||||
The loop uses an **LLM-driven discovery** approach:
|
||||
|
||||
1. **Spec Selection** - Interactive menu to select from discovered specs
|
||||
2. **Task Discovery** - The AI reads `overview.md` and phase files to find unchecked tasks
|
||||
3. **Implementation** - The AI implements tasks (one per iteration in task mode, or all in a phase in phase mode)
|
||||
4. **Checkbox Update** - The AI marks tasks complete in the markdown file
|
||||
5. **Scratchpad Update** - The AI appends notes to the per-spec scratchpad
|
||||
6. **Completion Marker** - The AI outputs structured markers (e.g., `TASK_COMPLETE: 1.1 - description`)
|
||||
7. **Loop** - Repeat until all tasks done or max iterations reached
|
||||
|
||||
### Loop Modes
|
||||
|
||||
The CLI asks you to choose a loop mode:
|
||||
|
||||
| Mode | Behavior | Git Commits | Best For |
|
||||
|------|----------|-------------|----------|
|
||||
| **One task per loop** (default) | Each agent invocation implements exactly one task | Node controller commits after each task | Smaller models, careful step-by-step execution |
|
||||
| **One phase per loop** | Each agent invocation implements all remaining tasks in the current phase | LLM commits after each task (with JIRA ID if provided) | Smart models with larger context windows, keeping related tasks together |
|
||||
|
||||
### Why LLM-Driven?
|
||||
|
||||
The Node app does NOT parse markdown to find tasks. Instead, the AI reads the spec files directly and decides what to work on. This is:
|
||||
|
||||
- **More flexible** - Works with any reasonable markdown format
|
||||
- **Smarter** - AI can handle edge cases and ambiguity
|
||||
- **Simpler** - Node code is just orchestration, not parsing
|
||||
|
||||
## Completion Markers
|
||||
|
||||
The AI must output one of these markers at the end of each iteration:
|
||||
|
||||
```
|
||||
TASK_COMPLETE: 1.1 - Initialize project structure
|
||||
TASK_BLOCKED: 2.3 - Missing API credentials
|
||||
PHASE_COMPLETE
|
||||
LOOP_COMPLETE
|
||||
```
|
||||
|
||||
| Marker | Meaning |
|
||||
|--------|---------|
|
||||
| `TASK_COMPLETE: X.X - desc` | Task implemented and marked complete |
|
||||
| `TASK_BLOCKED: X.X - reason` | Cannot complete task (explains why) |
|
||||
| `PHASE_COMPLETE` | Current phase finished (phase mode only) |
|
||||
| `LOOP_COMPLETE` | All phases finished |
|
||||
|
||||
In **phase mode**, the AI outputs multiple `TASK_COMPLETE` markers (one per task) within a single iteration, followed by `PHASE_COMPLETE` or `LOOP_COMPLETE`.
|
||||
|
||||
## Session Files
|
||||
|
||||
Session state is stored **per-spec** inside the spec directory:
|
||||
|
||||
```
|
||||
specs/my-feature/
|
||||
├── overview.md
|
||||
├── phase-1.md
|
||||
├── phase-2.md
|
||||
└── .plan2code-loop/ # Per-spec session state
|
||||
├── config.json # Session configuration
|
||||
├── scratchpad.md # LLM-managed progress notes
|
||||
├── iteration.log # JSON log of each iteration
|
||||
└── spec.hash # Hash for detecting spec changes
|
||||
```
|
||||
|
||||
The scratchpad is managed by the LLM itself - after each task, the AI appends notes about what was done, decisions made, and files changed. This helps future iterations skip exploration.
|
||||
|
||||
## Supported Agents
|
||||
|
||||
| Agent | Status |
|
||||
|-------|--------|
|
||||
| Claude Code | Supported |
|
||||
| GitHub Copilot CLI | Supported |
|
||||
| Devin CLI | Supported |
|
||||
|
||||
The loop uses your configured default model for each agent.
|
||||
|
||||
## Example Session
|
||||
|
||||
```
|
||||
$ plan2code-loop
|
||||
|
||||
╭──────────────────────────────────────╮
|
||||
│ │
|
||||
│ 🔮 Planny's Loop │
|
||||
│ Autonomous Implementation │
|
||||
│ │
|
||||
╰──────────────────────────────────────╯
|
||||
|
||||
Found spec: specs/todo-app
|
||||
Feature: Todo App
|
||||
Phases: 0/3
|
||||
Tasks: 0/15
|
||||
|
||||
══════════════════════════════════════════════
|
||||
Spec: Todo App
|
||||
══════════════════════════════════════════════
|
||||
Phases: 0/3
|
||||
Tasks: 0/15
|
||||
|
||||
? JIRA Ticket ID (optional): PROJ-123
|
||||
? Select AI agent: Claude Code
|
||||
? Tasks per loop iteration: One task per loop (default)
|
||||
? Maximum iterations: 100
|
||||
|
||||
Starting Plan2Code Loop
|
||||
══════════════════════════════════════════════
|
||||
Agent: Claude Code
|
||||
Model: default
|
||||
Spec: C:\projects\my-app\specs\todo-app
|
||||
Loop mode: One task per loop
|
||||
Max iterations: 100
|
||||
|
||||
Iteration 1/100
|
||||
[1/100] Task 1.1: Initialize project with Vite (45s)
|
||||
✓ Completed: Task 1.1: Initialize project with Vite
|
||||
|
||||
Iteration 2/100
|
||||
[2/100] Task 1.2: Configure TypeScript (32s)
|
||||
✓ Completed: Task 1.2: Configure TypeScript
|
||||
|
||||
...
|
||||
|
||||
Session Summary
|
||||
══════════════════════════════════════════════
|
||||
Total iterations: 12
|
||||
Tasks completed: 12
|
||||
Exit reason: all_complete
|
||||
|
||||
Session files saved to specs/todo-app/.plan2code-loop:
|
||||
- config.json (session configuration)
|
||||
- scratchpad.md (LLM-managed notes)
|
||||
- iteration.log (history)
|
||||
```
|
||||
|
||||
## Development
|
||||
|
||||
```bash
|
||||
# Install dependencies
|
||||
npm install
|
||||
|
||||
# Build
|
||||
npm run build
|
||||
|
||||
# Link for global usage
|
||||
npm link
|
||||
|
||||
# Unlink
|
||||
npm unlink
|
||||
```
|
||||
|
||||
## Architecture
|
||||
|
||||
```
|
||||
src/
|
||||
├── bin/plan2code-loop.ts # CLI entry point
|
||||
├── index.ts # Main exports
|
||||
├── controller.ts # Loop orchestration
|
||||
├── cli.ts # Interactive prompts
|
||||
├── agents/ # Agent implementations
|
||||
│ ├── claude-code.ts
|
||||
│ ├── copilot-cli.ts
|
||||
│ └── devin-cli.ts
|
||||
├── prompt/ # Prompt building
|
||||
│ ├── templates.ts
|
||||
│ └── builder.ts
|
||||
├── state/ # Session state management
|
||||
│ └── manager.ts
|
||||
├── spec/ # Spec utilities (for CLI display)
|
||||
│ └── utils.ts
|
||||
└── utils/ # Utilities
|
||||
├── completion.ts # Marker parsing
|
||||
└── logger.ts
|
||||
```
|
||||
@@ -0,0 +1,47 @@
|
||||
{
|
||||
"name": "plan2code-loop",
|
||||
"version": "1.6.2",
|
||||
"description": "Plan2Code Loop - Autonomous spec-driven implementation CLI",
|
||||
"type": "module",
|
||||
"main": "dist/index.js",
|
||||
"bin": {
|
||||
"plan2code-loop": "./dist/bin/plan2code-loop.js"
|
||||
},
|
||||
"files": [
|
||||
"dist"
|
||||
],
|
||||
"engines": {
|
||||
"node": ">=18.0.0"
|
||||
},
|
||||
"keywords": [
|
||||
"cli",
|
||||
"ai",
|
||||
"agent",
|
||||
"automation",
|
||||
"claude",
|
||||
"copilot",
|
||||
"devin",
|
||||
"spec-driven"
|
||||
],
|
||||
"license": "MIT",
|
||||
"scripts": {
|
||||
"build": "tsup",
|
||||
"dev": "tsup --watch",
|
||||
"start": "node dist/bin/plan2code-loop.js",
|
||||
"prepublishOnly": "npm run build"
|
||||
},
|
||||
"dependencies": {
|
||||
"@inquirer/prompts": "^8.1.0",
|
||||
"chalk": "^5.6.2",
|
||||
"execa": "^9.6.1",
|
||||
"fs-extra": "^11.3.3",
|
||||
"ora": "^9.0.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@types/fs-extra": "^11.0.4",
|
||||
"@types/node": "^25.0.3",
|
||||
"tsup": "^8.5.1",
|
||||
"typescript": "^5.9.3"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,82 @@
|
||||
import type { Agent, AgentConfig, AgentExecutionOptions, AgentExecutionResult } from './types.js';
|
||||
import { executeCommand } from '../utils/process.js';
|
||||
import { writeFileSync, unlinkSync } from 'fs';
|
||||
import { join } from 'path';
|
||||
import { tmpdir } from 'os';
|
||||
|
||||
const claudeCodeConfig: AgentConfig = {
|
||||
name: 'claude-code',
|
||||
displayName: 'Claude Code',
|
||||
command: 'claude',
|
||||
models: [
|
||||
{ value: 'default', label: 'Default (use Claude config)' },
|
||||
],
|
||||
defaultModel: 'default',
|
||||
flags: {
|
||||
prompt: '--print',
|
||||
model: '--model',
|
||||
skipPermissions: '--dangerously-skip-permissions',
|
||||
},
|
||||
};
|
||||
|
||||
class ClaudeCodeAgent implements Agent {
|
||||
readonly config = claudeCodeConfig;
|
||||
|
||||
async execute(options: AgentExecutionOptions): Promise<AgentExecutionResult> {
|
||||
// Write prompt to temp file - more reliable than stdin on Windows
|
||||
const tempFile = join(tmpdir(), `plan2code-prompt-${Date.now()}.txt`);
|
||||
writeFileSync(tempFile, options.prompt, 'utf-8');
|
||||
|
||||
try {
|
||||
// Build args: flags first, then read prompt from temp file via shell
|
||||
const args: string[] = [
|
||||
this.config.flags.prompt, // --print for non-interactive mode
|
||||
this.config.flags.skipPermissions,
|
||||
];
|
||||
|
||||
// Only add --model if not using default
|
||||
if (options.model && options.model !== 'default') {
|
||||
args.push(this.config.flags.model, options.model);
|
||||
}
|
||||
|
||||
// Use stdin from the temp file
|
||||
const result = await executeCommand({
|
||||
command: this.config.command,
|
||||
args,
|
||||
cwd: options.cwd,
|
||||
timeout: options.timeout,
|
||||
signal: options.signal,
|
||||
stdinFile: tempFile,
|
||||
});
|
||||
|
||||
return {
|
||||
stdout: result.stdout,
|
||||
stderr: result.stderr,
|
||||
exitCode: result.exitCode,
|
||||
timedOut: result.timedOut,
|
||||
cancelled: result.cancelled,
|
||||
duration: result.duration,
|
||||
};
|
||||
} finally {
|
||||
// Clean up temp file
|
||||
try {
|
||||
unlinkSync(tempFile);
|
||||
} catch {
|
||||
// Ignore cleanup errors
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async isAvailable(): Promise<boolean> {
|
||||
// Run claude --version to verify it's actually installed and working
|
||||
const result = await executeCommand({
|
||||
command: this.config.command,
|
||||
args: ['--version'],
|
||||
cwd: process.cwd(),
|
||||
timeout: 5000,
|
||||
});
|
||||
return result.exitCode === 0;
|
||||
}
|
||||
}
|
||||
|
||||
export const claudeCodeAgent = new ClaudeCodeAgent();
|
||||
@@ -0,0 +1,70 @@
|
||||
import type { Agent, AgentConfig, AgentExecutionOptions, AgentExecutionResult } from './types.js';
|
||||
import { executeCommand } from '../utils/process.js';
|
||||
|
||||
const copilotCliConfig: AgentConfig = {
|
||||
name: 'copilot-cli',
|
||||
displayName: 'GitHub Copilot CLI',
|
||||
command: 'copilot',
|
||||
models: [
|
||||
{ value: 'claude-sonnet-4', label: 'Claude Sonnet 4 (Default)' },
|
||||
{ value: 'claude-sonnet-4.5', label: 'Claude Sonnet 4.5' },
|
||||
{ value: 'claude-opus-4.5', label: 'Claude Opus 4.5' },
|
||||
{ value: 'gpt-5', label: 'GPT-5' },
|
||||
{ value: 'gpt-5-mini', label: 'GPT-5 Mini' },
|
||||
{ value: 'gemini-3-pro-preview', label: 'Gemini 3 Pro' },
|
||||
],
|
||||
defaultModel: 'claude-sonnet-4',
|
||||
flags: {
|
||||
prompt: '-p',
|
||||
model: '--model',
|
||||
skipPermissions: '--allow-all-tools',
|
||||
silent: '-s',
|
||||
},
|
||||
};
|
||||
|
||||
class CopilotCliAgent implements Agent {
|
||||
readonly config = copilotCliConfig;
|
||||
|
||||
async execute(options: AgentExecutionOptions): Promise<AgentExecutionResult> {
|
||||
// Use stdin for prompt to handle multi-line text properly
|
||||
const args: string[] = [];
|
||||
|
||||
// Only add --model if not using default
|
||||
if (options.model && options.model !== 'default') {
|
||||
args.push(this.config.flags.model, options.model);
|
||||
}
|
||||
|
||||
args.push(this.config.flags.skipPermissions, this.config.flags.silent!);
|
||||
|
||||
const result = await executeCommand({
|
||||
command: this.config.command,
|
||||
args,
|
||||
cwd: options.cwd,
|
||||
timeout: options.timeout,
|
||||
signal: options.signal,
|
||||
stdin: options.prompt,
|
||||
});
|
||||
|
||||
return {
|
||||
stdout: result.stdout,
|
||||
stderr: result.stderr,
|
||||
exitCode: result.exitCode,
|
||||
timedOut: result.timedOut,
|
||||
cancelled: result.cancelled,
|
||||
duration: result.duration,
|
||||
};
|
||||
}
|
||||
|
||||
async isAvailable(): Promise<boolean> {
|
||||
// Run copilot --version to verify it's installed
|
||||
const result = await executeCommand({
|
||||
command: this.config.command,
|
||||
args: ['--version'],
|
||||
cwd: process.cwd(),
|
||||
timeout: 5000,
|
||||
});
|
||||
return result.exitCode === 0;
|
||||
}
|
||||
}
|
||||
|
||||
export const copilotCliAgent = new CopilotCliAgent();
|
||||
@@ -0,0 +1,81 @@
|
||||
import type { Agent, AgentConfig, AgentExecutionOptions, AgentExecutionResult } from './types.js';
|
||||
import { executeCommand } from '../utils/process.js';
|
||||
import { writeFileSync, unlinkSync } from 'fs';
|
||||
import { join } from 'path';
|
||||
import { tmpdir } from 'os';
|
||||
|
||||
const devinCliConfig: AgentConfig = {
|
||||
name: 'devin-cli',
|
||||
displayName: 'Devin CLI',
|
||||
command: 'devin',
|
||||
models: [
|
||||
{ value: 'default', label: 'Default (use Devin config)' },
|
||||
],
|
||||
defaultModel: 'default',
|
||||
flags: {
|
||||
prompt: '--print',
|
||||
promptFile: '--prompt-file',
|
||||
model: '--model',
|
||||
skipPermissions: '--permission-mode',
|
||||
},
|
||||
};
|
||||
|
||||
class DevinCliAgent implements Agent {
|
||||
readonly config = devinCliConfig;
|
||||
|
||||
async execute(options: AgentExecutionOptions): Promise<AgentExecutionResult> {
|
||||
// Devin CLI takes the prompt via --prompt-file rather than stdin
|
||||
const tempFile = join(tmpdir(), `plan2code-prompt-${Date.now()}.txt`);
|
||||
writeFileSync(tempFile, options.prompt, 'utf-8');
|
||||
|
||||
try {
|
||||
const args: string[] = [
|
||||
this.config.flags.prompt, // --print for non-interactive mode
|
||||
this.config.flags.promptFile!, tempFile, // --prompt-file <path>
|
||||
this.config.flags.skipPermissions, 'dangerous', // --permission-mode dangerous (auto-approve all tools)
|
||||
];
|
||||
|
||||
// Only add --model if not using default
|
||||
if (options.model && options.model !== 'default') {
|
||||
args.push(this.config.flags.model, options.model);
|
||||
}
|
||||
|
||||
const result = await executeCommand({
|
||||
command: this.config.command,
|
||||
args,
|
||||
cwd: options.cwd,
|
||||
timeout: options.timeout,
|
||||
signal: options.signal,
|
||||
});
|
||||
|
||||
return {
|
||||
stdout: result.stdout,
|
||||
stderr: result.stderr,
|
||||
exitCode: result.exitCode,
|
||||
timedOut: result.timedOut,
|
||||
cancelled: result.cancelled,
|
||||
duration: result.duration,
|
||||
};
|
||||
} finally {
|
||||
// Clean up temp file
|
||||
try {
|
||||
unlinkSync(tempFile);
|
||||
} catch {
|
||||
// Ignore cleanup errors
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async isAvailable(): Promise<boolean> {
|
||||
// Run devin --version to verify it's actually installed and working
|
||||
const result = await executeCommand({
|
||||
command: this.config.command,
|
||||
args: ['--version'],
|
||||
cwd: process.cwd(),
|
||||
timeout: 5000,
|
||||
});
|
||||
return result.exitCode === 0;
|
||||
}
|
||||
}
|
||||
|
||||
export const devinCliAgent = new DevinCliAgent();
|
||||
@@ -0,0 +1,22 @@
|
||||
export type {
|
||||
Agent,
|
||||
AgentConfig,
|
||||
AgentExecutionOptions,
|
||||
AgentExecutionResult,
|
||||
ModelOption,
|
||||
} from './types.js';
|
||||
|
||||
export { agentRegistry } from './registry.js';
|
||||
export { claudeCodeAgent } from './claude-code.js';
|
||||
export { copilotCliAgent } from './copilot-cli.js';
|
||||
export { devinCliAgent } from './devin-cli.js';
|
||||
|
||||
// Register all agents
|
||||
import { agentRegistry } from './registry.js';
|
||||
import { claudeCodeAgent } from './claude-code.js';
|
||||
import { copilotCliAgent } from './copilot-cli.js';
|
||||
import { devinCliAgent } from './devin-cli.js';
|
||||
|
||||
agentRegistry.register(claudeCodeAgent);
|
||||
agentRegistry.register(copilotCliAgent);
|
||||
agentRegistry.register(devinCliAgent);
|
||||
@@ -0,0 +1,34 @@
|
||||
import type { Agent } from './types.js';
|
||||
|
||||
class AgentRegistry {
|
||||
private agents: Map<string, Agent> = new Map();
|
||||
|
||||
register(agent: Agent): void {
|
||||
this.agents.set(agent.config.name, agent);
|
||||
}
|
||||
|
||||
get(name: string): Agent | undefined {
|
||||
return this.agents.get(name);
|
||||
}
|
||||
|
||||
getAll(): Agent[] {
|
||||
return Array.from(this.agents.values());
|
||||
}
|
||||
|
||||
getAvailable(): Promise<Agent[]> {
|
||||
return Promise.all(
|
||||
this.getAll().map(async (agent) => ({
|
||||
agent,
|
||||
available: await agent.isAvailable(),
|
||||
}))
|
||||
).then((results) =>
|
||||
results.filter((r) => r.available).map((r) => r.agent)
|
||||
);
|
||||
}
|
||||
|
||||
getNames(): string[] {
|
||||
return Array.from(this.agents.keys());
|
||||
}
|
||||
}
|
||||
|
||||
export const agentRegistry = new AgentRegistry();
|
||||
@@ -0,0 +1,43 @@
|
||||
export interface ModelOption {
|
||||
value: string;
|
||||
label: string;
|
||||
}
|
||||
|
||||
export interface AgentConfig {
|
||||
name: string;
|
||||
displayName: string;
|
||||
command: string;
|
||||
models: ModelOption[];
|
||||
defaultModel: string;
|
||||
flags: {
|
||||
prompt: string;
|
||||
model: string;
|
||||
skipPermissions: string;
|
||||
silent?: string;
|
||||
promptFile?: string;
|
||||
};
|
||||
}
|
||||
|
||||
export interface AgentExecutionOptions {
|
||||
prompt: string;
|
||||
model: string;
|
||||
timeout: number; // milliseconds
|
||||
verbose: boolean;
|
||||
cwd: string;
|
||||
signal?: AbortSignal; // For cancellation
|
||||
}
|
||||
|
||||
export interface AgentExecutionResult {
|
||||
stdout: string;
|
||||
stderr: string;
|
||||
exitCode: number;
|
||||
timedOut: boolean;
|
||||
cancelled: boolean;
|
||||
duration: number; // milliseconds
|
||||
}
|
||||
|
||||
export interface Agent {
|
||||
config: AgentConfig;
|
||||
execute(options: AgentExecutionOptions): Promise<AgentExecutionResult>;
|
||||
isAvailable(): Promise<boolean>;
|
||||
}
|
||||
@@ -0,0 +1,34 @@
|
||||
import { run } from '../index.js';
|
||||
import { logger } from '../utils/index.js';
|
||||
|
||||
async function main() {
|
||||
try {
|
||||
const result = await run();
|
||||
|
||||
if (!result) {
|
||||
process.exit(0);
|
||||
}
|
||||
|
||||
// Exit codes per spec
|
||||
switch (result.exitReason) {
|
||||
case 'all_complete':
|
||||
logger.success('Loop completed successfully - all tasks done!');
|
||||
process.exit(0);
|
||||
case 'max_iterations':
|
||||
logger.warning('Loop ended: max iterations reached');
|
||||
process.exit(1);
|
||||
case 'interrupted':
|
||||
logger.info('Loop interrupted by user');
|
||||
process.exit(2);
|
||||
case 'error':
|
||||
logger.error('Loop ended with error');
|
||||
process.exit(3);
|
||||
}
|
||||
|
||||
} catch (error) {
|
||||
logger.error(error instanceof Error ? error.message : String(error));
|
||||
process.exit(3);
|
||||
}
|
||||
}
|
||||
|
||||
main();
|
||||
@@ -0,0 +1,240 @@
|
||||
import path from 'path';
|
||||
import { confirm, input, select } from '@inquirer/prompts';
|
||||
import { agentRegistry } from './agents/index.js';
|
||||
import { StateManager, type SessionConfig, type LoopMode } from './state/index.js';
|
||||
import { detectSpecDirectories, getSpecProgress } from './spec/utils.js';
|
||||
import { logger } from './utils/index.js';
|
||||
|
||||
export interface SessionSetupResult {
|
||||
config: SessionConfig;
|
||||
isResume: boolean;
|
||||
}
|
||||
|
||||
/**
|
||||
* Detect and select a spec directory
|
||||
*/
|
||||
async function selectSpec(cwd: string = process.cwd()): Promise<string | null> {
|
||||
// Auto-detect spec directories
|
||||
const specDirs = await detectSpecDirectories(cwd);
|
||||
|
||||
if (specDirs.length === 0) {
|
||||
logger.error('No spec directories found!');
|
||||
logger.info('Expected: specs/<feature>/overview.md');
|
||||
logger.info('');
|
||||
logger.info('To get started:');
|
||||
logger.info('');
|
||||
logger.info('1. Create a spec using `plan2code-1-plan`');
|
||||
logger.info(' command in our AI Agent');
|
||||
logger.info('');
|
||||
logger.info('2. Come back here and run `plan2code-loop`');
|
||||
logger.info(' as an alternative to `plan2code-3-implement`');
|
||||
logger.info('');
|
||||
return null;
|
||||
}
|
||||
|
||||
if (specDirs.length === 1) {
|
||||
const spec = specDirs[0];
|
||||
const progress = await getSpecProgress(spec);
|
||||
logger.info(`Found spec: ${path.relative(cwd, spec)}`);
|
||||
logger.dim(` Feature: ${progress.featureName}`);
|
||||
logger.dim(` Phases: ${progress.totalPhases}`);
|
||||
return spec;
|
||||
}
|
||||
|
||||
// Multiple specs - let user choose
|
||||
const choices = await Promise.all(
|
||||
specDirs.map(async (spec) => {
|
||||
const progress = await getSpecProgress(spec);
|
||||
const relativePath = path.relative(cwd, spec);
|
||||
return {
|
||||
name: `${progress.featureName} (${progress.totalPhases} phases) - ${relativePath}`,
|
||||
value: spec,
|
||||
};
|
||||
})
|
||||
);
|
||||
|
||||
const selectedSpec = await select({
|
||||
message: 'Select spec to implement:',
|
||||
choices,
|
||||
});
|
||||
|
||||
return selectedSpec;
|
||||
}
|
||||
|
||||
/**
|
||||
* Select AI agent
|
||||
*/
|
||||
async function selectAgent(): Promise<string> {
|
||||
const allAgents = agentRegistry.getAll();
|
||||
|
||||
const agentName = await select({
|
||||
message: 'Select AI agent:',
|
||||
choices: allAgents.map((agent) => ({
|
||||
name: agent.config.displayName,
|
||||
value: agent.config.name,
|
||||
})),
|
||||
});
|
||||
|
||||
return agentName;
|
||||
}
|
||||
|
||||
/**
|
||||
* Prompt for JIRA ticket ID
|
||||
*/
|
||||
async function promptJiraTicketId(): Promise<string | undefined> {
|
||||
const ticketId = await input({
|
||||
message: 'JIRA Ticket ID (optional, for commit messages):',
|
||||
});
|
||||
|
||||
return ticketId.trim() || undefined;
|
||||
}
|
||||
|
||||
/**
|
||||
* Select maximum iterations
|
||||
*/
|
||||
async function selectMaxIterations(): Promise<number> {
|
||||
const choices = [15, 30, 50, 75, 100, 125, 150, 200];
|
||||
|
||||
const max = await select({
|
||||
message: 'Maximum iterations:',
|
||||
choices: choices.map((n) => ({
|
||||
name: n.toString(),
|
||||
value: n,
|
||||
})),
|
||||
default: 100,
|
||||
});
|
||||
|
||||
return max;
|
||||
}
|
||||
|
||||
/**
|
||||
* Select loop mode: one task per loop or one phase per loop
|
||||
*/
|
||||
async function selectLoopMode(): Promise<LoopMode> {
|
||||
const mode = await select<LoopMode>({
|
||||
message: 'Tasks per loop iteration:',
|
||||
choices: [
|
||||
{
|
||||
name: 'One task per loop (default)',
|
||||
value: 'task' as LoopMode,
|
||||
},
|
||||
{
|
||||
name: 'One phase per loop (related tasks together)',
|
||||
value: 'phase' as LoopMode,
|
||||
},
|
||||
],
|
||||
default: 'task',
|
||||
});
|
||||
|
||||
return mode;
|
||||
}
|
||||
|
||||
/**
|
||||
* Handle existing session - returns action to take
|
||||
*/
|
||||
async function handleExistingSession(
|
||||
stateManager: StateManager,
|
||||
specPath: string
|
||||
): Promise<'continue' | 'fresh' | 'new'> {
|
||||
const state = await stateManager.detectSessionState(specPath);
|
||||
|
||||
if (state === 'new') {
|
||||
return 'new';
|
||||
}
|
||||
|
||||
if (state === 'continue') {
|
||||
const config = await stateManager.readConfig();
|
||||
const lastIter = config?.currentIteration ?? 0;
|
||||
|
||||
logger.info(`Found existing session at iteration ${lastIter}`);
|
||||
|
||||
const continueSession = await confirm({
|
||||
message: 'Continue previous session?',
|
||||
default: true,
|
||||
});
|
||||
|
||||
return continueSession ? 'continue' : 'fresh';
|
||||
}
|
||||
|
||||
if (state === 'changed') {
|
||||
logger.warning('Spec has changed since last session.');
|
||||
|
||||
const startFresh = await confirm({
|
||||
message: 'Start fresh? (This will clear previous progress)',
|
||||
default: false,
|
||||
});
|
||||
|
||||
return startFresh ? 'fresh' : 'continue';
|
||||
}
|
||||
|
||||
return 'new';
|
||||
}
|
||||
|
||||
/**
|
||||
* Setup session via interactive prompts
|
||||
*/
|
||||
export async function setupSession(
|
||||
stateManager: StateManager
|
||||
): Promise<SessionSetupResult | null> {
|
||||
// Show Planny welcome
|
||||
logger.welcome();
|
||||
|
||||
// Select spec
|
||||
const specPath = await selectSpec(process.cwd());
|
||||
if (!specPath) {
|
||||
return null;
|
||||
}
|
||||
|
||||
// Set spec path on state manager for per-spec state directory
|
||||
stateManager.setSpecPath(specPath);
|
||||
|
||||
// Show spec progress
|
||||
const progress = await getSpecProgress(specPath);
|
||||
console.log();
|
||||
logger.header(`Spec: ${progress.featureName}`);
|
||||
logger.info(`Phases: ${progress.totalPhases}`);
|
||||
console.log();
|
||||
|
||||
// Check for existing session
|
||||
const sessionAction = await handleExistingSession(stateManager, specPath);
|
||||
|
||||
if (sessionAction === 'continue') {
|
||||
const existingConfig = await stateManager.readConfig();
|
||||
if (existingConfig) {
|
||||
const agent = await selectAgent();
|
||||
existingConfig.agent = agent;
|
||||
await stateManager.writeConfig(existingConfig);
|
||||
logger.info('Resuming previous session...');
|
||||
return { config: existingConfig, isResume: true };
|
||||
}
|
||||
}
|
||||
|
||||
if (sessionAction === 'fresh') {
|
||||
await stateManager.clearState();
|
||||
}
|
||||
|
||||
// Collect new session configuration
|
||||
const jiraTicketId = await promptJiraTicketId();
|
||||
const agent = await selectAgent();
|
||||
const loopMode = await selectLoopMode();
|
||||
const maxIterations = await selectMaxIterations();
|
||||
|
||||
const config: SessionConfig = {
|
||||
agent,
|
||||
model: 'default',
|
||||
maxIterations,
|
||||
specPath,
|
||||
timeout: 3,
|
||||
maxRetries: 5,
|
||||
verbose: false,
|
||||
startedAt: new Date().toISOString(),
|
||||
currentIteration: 0,
|
||||
jiraTicketId,
|
||||
loopMode,
|
||||
};
|
||||
|
||||
// Initialize session
|
||||
await stateManager.initializeNewSession(config);
|
||||
|
||||
return { config, isResume: false };
|
||||
}
|
||||
@@ -0,0 +1,522 @@
|
||||
import { agentRegistry, type Agent, type AgentExecutionResult } from './agents/index.js';
|
||||
import { StateManager, type SessionConfig, type IterationLogEntry } from './state/index.js';
|
||||
import { buildLoopPrompt } from './prompt/index.js';
|
||||
import { checkForCompletion, checkForAllCompletions, logger, ensureGitRepo, ensureGitignore, type CompletionCheckResult } from './utils/index.js';
|
||||
|
||||
export interface TaskCompleteInfo {
|
||||
marker: string;
|
||||
taskId?: string;
|
||||
taskName?: string;
|
||||
}
|
||||
|
||||
export interface ControllerOptions {
|
||||
config: SessionConfig;
|
||||
stateManager: StateManager;
|
||||
onIteration?: (iteration: number, max: number) => void;
|
||||
onTaskComplete?: (info: TaskCompleteInfo) => void | Promise<void>;
|
||||
onLoopComplete?: () => void;
|
||||
}
|
||||
|
||||
export interface LoopResult {
|
||||
completed: boolean;
|
||||
iterations: number;
|
||||
finalMarker?: string;
|
||||
exitReason: 'all_complete' | 'max_iterations' | 'interrupted' | 'error';
|
||||
tasksCompleted: number;
|
||||
prereqsCompleted: number;
|
||||
error?: Error;
|
||||
}
|
||||
|
||||
export class Controller {
|
||||
private readonly config: SessionConfig;
|
||||
private readonly stateManager: StateManager;
|
||||
private readonly agent: Agent;
|
||||
private readonly onIteration?: (iteration: number, max: number) => void;
|
||||
private readonly onTaskComplete?: (info: TaskCompleteInfo) => void | Promise<void>;
|
||||
private readonly onLoopComplete?: () => void;
|
||||
private interrupted = false;
|
||||
private abortController: AbortController | null = null;
|
||||
private tasksCompleted = 0;
|
||||
private prereqsCompleted = 0;
|
||||
|
||||
constructor(options: ControllerOptions) {
|
||||
this.config = options.config;
|
||||
this.stateManager = options.stateManager;
|
||||
this.onIteration = options.onIteration;
|
||||
this.onTaskComplete = options.onTaskComplete;
|
||||
this.onLoopComplete = options.onLoopComplete;
|
||||
|
||||
const agent = agentRegistry.get(this.config.agent);
|
||||
if (!agent) {
|
||||
throw new Error(`Agent not found: ${this.config.agent}`);
|
||||
}
|
||||
this.agent = agent;
|
||||
}
|
||||
|
||||
private async buildPrompt(): Promise<string> {
|
||||
return buildLoopPrompt({
|
||||
specPath: this.config.specPath,
|
||||
iteration: this.config.currentIteration + 1,
|
||||
maxIterations: this.config.maxIterations,
|
||||
stateManager: this.stateManager,
|
||||
loopMode: this.config.loopMode || 'task',
|
||||
jiraTicketId: this.config.jiraTicketId,
|
||||
});
|
||||
}
|
||||
|
||||
private computeTimeoutMs(attempt: number): number {
|
||||
const baseMs = this.config.timeout * 60 * 1000;
|
||||
return baseMs + (attempt * 30 * 1000);
|
||||
}
|
||||
|
||||
private formatDuration(ms: number): string {
|
||||
const totalSec = Math.round(ms / 1000);
|
||||
const min = Math.floor(totalSec / 60);
|
||||
const sec = totalSec % 60;
|
||||
if (min === 0) return `${sec}s`;
|
||||
if (sec === 0) return `${min}m`;
|
||||
return `${min}m ${sec}s`;
|
||||
}
|
||||
|
||||
private async executeWithRetry(prompt: string, iterNum: number): Promise<AgentExecutionResult | 'fatal_timeout'> {
|
||||
const maxAttempts = (this.config.maxRetries ?? 5) + 1;
|
||||
|
||||
for (let attempt = 0; attempt < maxAttempts; attempt++) {
|
||||
const timeoutMs = this.computeTimeoutMs(attempt);
|
||||
|
||||
if (attempt > 0) {
|
||||
const prevTimeoutMs = this.computeTimeoutMs(attempt - 1);
|
||||
logger.warning(
|
||||
`Timed out after ${this.formatDuration(prevTimeoutMs)}, retrying (${attempt}/${maxAttempts - 1})...`
|
||||
);
|
||||
}
|
||||
|
||||
const spinnerBase = attempt > 0
|
||||
? `Waiting for AI Agent response (retry ${attempt}/${maxAttempts - 1})`
|
||||
: 'Waiting for AI Agent response (please be patient)';
|
||||
const spinner = logger.spinner(spinnerBase);
|
||||
const startTime = Date.now();
|
||||
|
||||
const elapsedInterval = setInterval(() => {
|
||||
const elapsed = Math.round((Date.now() - startTime) / 1000);
|
||||
spinner.text = `${spinnerBase} ... (${elapsed}s)`;
|
||||
}, 1000);
|
||||
|
||||
const result = await this.executeIteration(prompt, timeoutMs);
|
||||
clearInterval(elapsedInterval);
|
||||
spinner.stop();
|
||||
|
||||
// Cancelled or interrupted — return immediately, don't retry
|
||||
if (result.cancelled || this.interrupted) {
|
||||
return result;
|
||||
}
|
||||
|
||||
// Completed (success or error exit code) — return to caller
|
||||
if (!result.timedOut) {
|
||||
return result;
|
||||
}
|
||||
|
||||
// Timed out — retry if attempts remain, otherwise fatal
|
||||
if (attempt < maxAttempts - 1) {
|
||||
continue;
|
||||
}
|
||||
|
||||
// All attempts exhausted
|
||||
logger.error(
|
||||
`Iteration ${iterNum} timed out on all ${maxAttempts} attempt${maxAttempts === 1 ? '' : 's'}. Stopping loop.`
|
||||
);
|
||||
const entry: IterationLogEntry = {
|
||||
iteration: iterNum,
|
||||
timestamp: new Date().toISOString(),
|
||||
duration: result.duration,
|
||||
exitCode: -1,
|
||||
status: 'timeout',
|
||||
};
|
||||
await this.stateManager.appendIterationLog(entry);
|
||||
return 'fatal_timeout';
|
||||
}
|
||||
|
||||
return 'fatal_timeout'; // unreachable, satisfies TS
|
||||
}
|
||||
|
||||
private async executeIteration(prompt: string, timeoutMs: number): Promise<AgentExecutionResult> {
|
||||
// Create new AbortController for this iteration
|
||||
this.abortController = new AbortController();
|
||||
|
||||
const result = await this.agent.execute({
|
||||
prompt,
|
||||
model: this.config.model,
|
||||
timeout: timeoutMs,
|
||||
verbose: this.config.verbose,
|
||||
cwd: process.cwd(),
|
||||
signal: this.abortController.signal,
|
||||
});
|
||||
|
||||
this.abortController = null;
|
||||
return result;
|
||||
}
|
||||
|
||||
private createLogEntry(
|
||||
result: AgentExecutionResult,
|
||||
status: IterationLogEntry['status'],
|
||||
marker?: string
|
||||
): IterationLogEntry {
|
||||
return {
|
||||
iteration: this.config.currentIteration + 1,
|
||||
timestamp: new Date().toISOString(),
|
||||
duration: result.duration,
|
||||
exitCode: result.exitCode,
|
||||
status,
|
||||
completionMarker: marker,
|
||||
};
|
||||
}
|
||||
|
||||
private formatTaskDisplay(completion: CompletionCheckResult): string {
|
||||
if (completion.taskId && completion.taskName) {
|
||||
return `Task ${completion.taskId}: ${completion.taskName}`;
|
||||
} else if (completion.taskId) {
|
||||
return `Task ${completion.taskId}`;
|
||||
}
|
||||
return '';
|
||||
}
|
||||
|
||||
private displayIterationResult(result: AgentExecutionResult, iterNum: number, completion: CompletionCheckResult): void {
|
||||
const duration = Math.round(result.duration / 1000);
|
||||
const taskDisplay = this.formatTaskDisplay(completion);
|
||||
|
||||
// Show iteration completion with task info if available
|
||||
if (taskDisplay) {
|
||||
logger.iteration(iterNum, this.config.maxIterations, `${taskDisplay} (${duration}s)`);
|
||||
} else {
|
||||
logger.iteration(iterNum, this.config.maxIterations, `completed in ${duration}s`);
|
||||
}
|
||||
|
||||
// Verbose mode: show full output
|
||||
if (this.config.verbose) {
|
||||
console.log();
|
||||
logger.dim('--- Agent Output ---');
|
||||
console.log(result.stdout);
|
||||
if (result.stderr) {
|
||||
logger.dim('--- Agent Stderr ---');
|
||||
console.log(result.stderr);
|
||||
}
|
||||
logger.dim('--- End Output ---');
|
||||
console.log();
|
||||
} else if (result.exitCode !== 0 && result.stderr.trim()) {
|
||||
logger.error(` ${result.stderr.trim().split('\n')[0]}`);
|
||||
}
|
||||
}
|
||||
|
||||
async run(): Promise<LoopResult> {
|
||||
// Pre-flight: verify agent CLI is available
|
||||
const isAvailable = await this.agent.isAvailable();
|
||||
if (!isAvailable) {
|
||||
logger.error(`"${this.agent.config.displayName}" is not available!`);
|
||||
logger.info(`Please ensure the "${this.agent.config.command}" command is installed and available in your PATH.`);
|
||||
throw new Error(`Agent "${this.agent.config.displayName}" is not available. Please install it and try again.`);
|
||||
}
|
||||
|
||||
// Ensure git repo and .gitignore are set up before any iterations
|
||||
const gitReady = await ensureGitRepo(process.cwd());
|
||||
if (!gitReady) {
|
||||
throw new Error('Failed to initialize a git repository in the current working directory. Cannot start Plan2Code Loop.');
|
||||
}
|
||||
ensureGitignore(process.cwd());
|
||||
|
||||
const loopModeLabel = (this.config.loopMode || 'task') === 'phase' ? 'One phase per loop' : 'One task per loop';
|
||||
logger.header('Starting Plan2Code Loop');
|
||||
logger.info(`Agent: ${this.agent.config.displayName}`);
|
||||
logger.info(`Model: ${this.config.model}`);
|
||||
logger.info(`Spec: ${this.config.specPath}`);
|
||||
logger.info(`Loop mode: ${loopModeLabel}`);
|
||||
logger.info(`Max iterations: ${this.config.maxIterations}`);
|
||||
console.log();
|
||||
|
||||
while (this.config.currentIteration < this.config.maxIterations) {
|
||||
if (this.interrupted) {
|
||||
return {
|
||||
completed: false,
|
||||
iterations: this.config.currentIteration,
|
||||
exitReason: 'interrupted',
|
||||
tasksCompleted: this.tasksCompleted,
|
||||
prereqsCompleted: this.prereqsCompleted,
|
||||
};
|
||||
}
|
||||
|
||||
const iterNum = this.config.currentIteration + 1;
|
||||
this.onIteration?.(iterNum, this.config.maxIterations);
|
||||
|
||||
console.log();
|
||||
logger.info(`Iteration ${iterNum}/${this.config.maxIterations}`);
|
||||
|
||||
// Build prompt - simple, just spec path and iteration info
|
||||
const prompt = await this.buildPrompt();
|
||||
|
||||
try {
|
||||
const retryResult = await this.executeWithRetry(prompt, iterNum);
|
||||
|
||||
if (retryResult === 'fatal_timeout') {
|
||||
return {
|
||||
completed: false,
|
||||
iterations: this.config.currentIteration,
|
||||
exitReason: 'error',
|
||||
tasksCompleted: this.tasksCompleted,
|
||||
prereqsCompleted: this.prereqsCompleted,
|
||||
error: new Error(`Iteration ${iterNum} failed after all retry attempts`),
|
||||
};
|
||||
}
|
||||
|
||||
const result = retryResult;
|
||||
|
||||
// Check if cancelled
|
||||
if (result.cancelled || this.interrupted) {
|
||||
logger.info('Agent process cancelled');
|
||||
|
||||
const entry: IterationLogEntry = {
|
||||
iteration: iterNum,
|
||||
timestamp: new Date().toISOString(),
|
||||
duration: result.duration,
|
||||
exitCode: -1,
|
||||
status: 'interrupted',
|
||||
};
|
||||
await this.stateManager.appendIterationLog(entry);
|
||||
|
||||
return {
|
||||
completed: false,
|
||||
iterations: this.config.currentIteration,
|
||||
exitReason: 'interrupted',
|
||||
tasksCompleted: this.tasksCompleted,
|
||||
prereqsCompleted: this.prereqsCompleted,
|
||||
};
|
||||
}
|
||||
|
||||
// Branch completion handling based on loop mode
|
||||
const isPhaseMode = (this.config.loopMode || 'task') === 'phase';
|
||||
|
||||
if (isPhaseMode) {
|
||||
// Phase mode: parse ALL completion markers from output
|
||||
const allCompletions = checkForAllCompletions(result.stdout + result.stderr);
|
||||
|
||||
// Determine status
|
||||
let status: IterationLogEntry['status'] = 'running';
|
||||
if (allCompletions.tasks.length > 0 || allCompletions.loopComplete || allCompletions.phaseComplete) {
|
||||
const hasBlocked = allCompletions.tasks.some(t => t.marker === 'TASK_BLOCKED');
|
||||
const hasCompleted = allCompletions.tasks.some(t => t.marker === 'TASK_COMPLETE' || t.marker === 'PREREQ_COMPLETE' || t.marker === 'PREREQ_ASSUMED');
|
||||
status = hasCompleted || allCompletions.phaseComplete || allCompletions.loopComplete ? 'completed' : hasBlocked ? 'blocked' : 'running';
|
||||
} else if (result.timedOut) {
|
||||
status = 'timeout';
|
||||
} else if (result.exitCode !== 0) {
|
||||
status = 'error';
|
||||
}
|
||||
|
||||
// Log iteration with count of tasks
|
||||
const markerSummary = allCompletions.tasks.map(t => `${t.marker}: ${t.taskId}`).join(', ');
|
||||
const logEntry = this.createLogEntry(result, status, markerSummary || undefined);
|
||||
await this.stateManager.appendIterationLog(logEntry);
|
||||
|
||||
// Display each completed task
|
||||
const duration = Math.round(result.duration / 1000);
|
||||
for (const task of allCompletions.tasks) {
|
||||
if (task.marker === 'TASK_COMPLETE') {
|
||||
this.tasksCompleted++;
|
||||
const taskDisplay = this.formatTaskDisplay(task);
|
||||
logger.success(taskDisplay ? `Completed: ${taskDisplay}` : 'Task completed!');
|
||||
} else if (task.marker === 'PREREQ_COMPLETE') {
|
||||
this.prereqsCompleted++;
|
||||
const prereqDisplay = task.taskId && task.taskName
|
||||
? `Prereq ${task.taskId}: ${task.taskName}`
|
||||
: task.taskId ? `Prereq ${task.taskId}` : 'Prerequisite';
|
||||
logger.success(`Verified: ${prereqDisplay}`);
|
||||
} else if (task.marker === 'PREREQ_ASSUMED') {
|
||||
this.prereqsCompleted++;
|
||||
const prereqDisplay = task.taskId && task.taskName
|
||||
? `Prereq ${task.taskId}: ${task.taskName}`
|
||||
: task.taskId ? `Prereq ${task.taskId}` : 'Prerequisite';
|
||||
logger.success(`Assumed: ${prereqDisplay}`);
|
||||
} else if (task.marker === 'TASK_BLOCKED') {
|
||||
const blockInfo = task.taskId
|
||||
? `Task ${task.taskId} blocked: ${task.reason || 'Unknown reason'}`
|
||||
: `Task blocked: ${task.reason || 'Unknown reason'}`;
|
||||
logger.warning(blockInfo);
|
||||
}
|
||||
}
|
||||
|
||||
// Show phase-level summary
|
||||
if (allCompletions.tasks.length > 0) {
|
||||
const completedCount = allCompletions.tasks.filter(t => t.marker === 'TASK_COMPLETE').length;
|
||||
const prereqCount = allCompletions.tasks.filter(t => t.marker === 'PREREQ_COMPLETE' || t.marker === 'PREREQ_ASSUMED').length;
|
||||
const blockedCount = allCompletions.tasks.filter(t => t.marker === 'TASK_BLOCKED').length;
|
||||
const parts: string[] = [];
|
||||
if (completedCount > 0) parts.push(`${completedCount} task(s) completed`);
|
||||
if (prereqCount > 0) parts.push(`${prereqCount} prereq(s) verified`);
|
||||
if (blockedCount > 0) parts.push(`${blockedCount} blocked`);
|
||||
logger.iteration(iterNum, this.config.maxIterations,
|
||||
`Phase done: ${parts.join(', ')} (${duration}s)`);
|
||||
} else {
|
||||
logger.iteration(iterNum, this.config.maxIterations, `completed in ${duration}s`);
|
||||
}
|
||||
|
||||
// Verbose output
|
||||
if (this.config.verbose) {
|
||||
console.log();
|
||||
logger.dim('--- Agent Output ---');
|
||||
console.log(result.stdout);
|
||||
if (result.stderr) {
|
||||
logger.dim('--- Agent Stderr ---');
|
||||
console.log(result.stderr);
|
||||
}
|
||||
logger.dim('--- End Output ---');
|
||||
console.log();
|
||||
} else if (result.exitCode !== 0 && result.stderr.trim()) {
|
||||
logger.error(` ${result.stderr.trim().split('\n')[0]}`);
|
||||
}
|
||||
|
||||
// Handle LOOP_COMPLETE
|
||||
if (allCompletions.loopComplete) {
|
||||
this.onLoopComplete?.();
|
||||
logger.success('All tasks complete!');
|
||||
return {
|
||||
completed: true,
|
||||
iterations: iterNum,
|
||||
finalMarker: 'LOOP_COMPLETE',
|
||||
exitReason: 'all_complete',
|
||||
tasksCompleted: this.tasksCompleted,
|
||||
prereqsCompleted: this.prereqsCompleted,
|
||||
};
|
||||
}
|
||||
} else {
|
||||
// Task mode (default): existing single-marker logic
|
||||
const completion = checkForCompletion(result.stdout + result.stderr);
|
||||
|
||||
// Determine status
|
||||
let status: IterationLogEntry['status'] = 'running';
|
||||
if (completion.completed) {
|
||||
if (completion.marker === 'TASK_BLOCKED') {
|
||||
status = 'blocked';
|
||||
} else {
|
||||
status = 'completed';
|
||||
}
|
||||
} else if (result.timedOut) {
|
||||
status = 'timeout';
|
||||
} else if (result.exitCode !== 0) {
|
||||
status = 'error';
|
||||
}
|
||||
|
||||
// Log iteration
|
||||
const logEntry = this.createLogEntry(result, status, completion.marker);
|
||||
await this.stateManager.appendIterationLog(logEntry);
|
||||
|
||||
// Display iteration result with task info from completion marker
|
||||
this.displayIterationResult(result, iterNum, completion);
|
||||
|
||||
// Handle completion markers
|
||||
if (completion.completed) {
|
||||
const taskDisplay = this.formatTaskDisplay(completion);
|
||||
|
||||
if (completion.marker === 'TASK_COMPLETE') {
|
||||
this.tasksCompleted++;
|
||||
await this.onTaskComplete?.({
|
||||
marker: completion.marker,
|
||||
taskId: completion.taskId,
|
||||
taskName: completion.taskName,
|
||||
});
|
||||
logger.success(taskDisplay ? `Completed: ${taskDisplay}` : 'Task completed!');
|
||||
} else if (completion.marker === 'PREREQ_COMPLETE' || completion.marker === 'PREREQ_ASSUMED') {
|
||||
this.prereqsCompleted++;
|
||||
await this.onTaskComplete?.({
|
||||
marker: completion.marker,
|
||||
taskId: completion.taskId,
|
||||
taskName: completion.taskName,
|
||||
});
|
||||
const prereqDisplay = completion.taskId && completion.taskName
|
||||
? `Prereq ${completion.taskId}: ${completion.taskName}`
|
||||
: completion.taskId ? `Prereq ${completion.taskId}` : 'Prerequisite';
|
||||
const verb = completion.marker === 'PREREQ_COMPLETE' ? 'Verified' : 'Assumed';
|
||||
logger.success(`${verb}: ${prereqDisplay}`);
|
||||
} else if (completion.marker === 'TASK_BLOCKED') {
|
||||
const blockInfo = completion.taskId
|
||||
? `Task ${completion.taskId} blocked: ${completion.reason || 'Unknown reason'}`
|
||||
: `Task blocked: ${completion.reason || 'Unknown reason'}`;
|
||||
logger.warning(blockInfo);
|
||||
} else if (completion.marker === 'LOOP_COMPLETE') {
|
||||
// Commit any final changes before completing
|
||||
this.tasksCompleted++;
|
||||
await this.onTaskComplete?.({
|
||||
marker: completion.marker,
|
||||
taskId: completion.taskId,
|
||||
taskName: completion.taskName || 'Final implementation complete',
|
||||
});
|
||||
this.onLoopComplete?.();
|
||||
logger.success('All tasks complete!');
|
||||
return {
|
||||
completed: true,
|
||||
iterations: iterNum,
|
||||
finalMarker: 'LOOP_COMPLETE',
|
||||
exitReason: 'all_complete',
|
||||
tasksCompleted: this.tasksCompleted,
|
||||
prereqsCompleted: this.prereqsCompleted,
|
||||
};
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Increment iteration and update spec hash (so resume doesn't see false changes)
|
||||
await this.stateManager.incrementIteration();
|
||||
await this.stateManager.updateSpecHash(this.config.specPath);
|
||||
this.config.currentIteration++;
|
||||
|
||||
// Handle error (but continue - LLM might recover)
|
||||
if (result.exitCode !== 0) {
|
||||
// In phase mode, check if any tasks completed despite error exit code
|
||||
const hasCompletions = isPhaseMode
|
||||
? checkForAllCompletions(result.stdout + result.stderr).tasks.length > 0
|
||||
: checkForCompletion(result.stdout + result.stderr).completed;
|
||||
if (!hasCompletions) {
|
||||
logger.warning(`Iteration ${iterNum} exited with code ${result.exitCode}, continuing...`);
|
||||
}
|
||||
}
|
||||
|
||||
} catch (error) {
|
||||
clearInterval(elapsedInterval);
|
||||
spinner.stop();
|
||||
logger.error(`Iteration ${iterNum} failed: ${error}`);
|
||||
|
||||
// Log the error
|
||||
const entry: IterationLogEntry = {
|
||||
iteration: iterNum,
|
||||
timestamp: new Date().toISOString(),
|
||||
duration: 0,
|
||||
exitCode: -1,
|
||||
status: 'error',
|
||||
};
|
||||
await this.stateManager.appendIterationLog(entry);
|
||||
|
||||
return {
|
||||
completed: false,
|
||||
iterations: this.config.currentIteration,
|
||||
exitReason: 'error',
|
||||
tasksCompleted: this.tasksCompleted,
|
||||
prereqsCompleted: this.prereqsCompleted,
|
||||
error: error instanceof Error ? error : new Error(String(error)),
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
// Max iterations reached
|
||||
logger.warning('Max iterations reached');
|
||||
return {
|
||||
completed: false,
|
||||
iterations: this.config.currentIteration,
|
||||
exitReason: 'max_iterations',
|
||||
tasksCompleted: this.tasksCompleted,
|
||||
prereqsCompleted: this.prereqsCompleted,
|
||||
};
|
||||
}
|
||||
|
||||
interrupt(): void {
|
||||
this.interrupted = true;
|
||||
if (this.abortController) {
|
||||
this.abortController.abort();
|
||||
}
|
||||
}
|
||||
}
|
||||