Refresh the agent docs: a Test map section, merged sync log lines and current newcomer notes

AI Assisted
This commit is contained in:
jparkerweb committed 2026-11-11 08:08:08 -08:00
1 parent 15d66aa19c
commit d599d87669
11 files changed
+52 -24

No files matched your search

+4 -4
View File
@@ -14,18 +14,18 @@
## Gotchas / Pitfalls
- **Version sync:** When adding a new version to `CHANGELOG.md`, run `npm run set-version -- <x.y.z>` (`node scripts/set-version.mjs`; with no version on a terminal it shows the current one and asks, Enter taking the next patch; the one writer of every carrier; it never edits the changelog), which updates `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. The desktop app carries it too (under `plan2code-app/`: `package.json`, `package-lock.json` with two lines, `src-tauri/tauri.conf.json`, `src-tauri/Cargo.toml`, `fake-agent/Cargo.toml`, and `Cargo.lock`'s `plan2code-app` and `fake-agent` entries): `node scripts/check-versions.mjs [--tag vX.Y.Z]` compares those, `version.json`, `package.json`, `CHANGELOG.md` and README's line (twelve places in all), `npm test` runs it first on this tree, and the release workflow runs it before building.
- **Version sync:** When adding a new version to `CHANGELOG.md`, run `npm run set-version -- <x.y.z>` (`node scripts/set-version.mjs`; with no version on a terminal it shows the current one and asks, Enter taking the next patch; the one writer of every carrier; it never edits the changelog), which updates `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 that ships scripts (`skills/<skill>/scripts/version.json`) and into the shared console (`~/.plan2code/console/<version>/`, whose 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. The desktop app carries it too (under `plan2code-app/`: `package.json`, `package-lock.json` with two lines, `src-tauri/tauri.conf.json`, `src-tauri/Cargo.toml`, `fake-agent/Cargo.toml`, and `Cargo.lock`'s `plan2code-app` and `fake-agent` entries): `node scripts/check-versions.mjs [--tag vX.Y.Z]` compares those, `version.json`, `package.json`, `CHANGELOG.md` and README's line (twelve places in all), `npm test` runs it first on this tree, and the release workflow runs it before building.
- **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.
- **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. Git never writes CRLF here, but tools do (Python writing in text mode on Windows, some editors and generators), so `scripts/fix-line-endings.mjs` puts every text file git sees back to LF: `npm run fix:eol` by hand, `--check` to only list, and it runs by itself as npm's `pretest`, in the husky pre-commit before the char count, and after every Write or Edit through the PostToolUse hook in `.claude/settings.json`. In a Python script that writes repo files, open them with `newline="\n"` (or write bytes) anyway.
- **The pre-commit hook runs the LF fix, then the char-count check:** `.husky/pre-commit` is `node scripts/fix-line-endings.mjs` followed by `node scripts/validate-char-count.js`. `skills/` drift, parse errors and test failures are caught only by the tests, so run them before committing: the targeted suites for a change that stays in one area, the full `npm test` for shared code or before a PR (see "Targeted tests first" in [Development Commands](./AGENTS-development-commands.md)). Sub-package tests are separate; see [Development Commands](./AGENTS-development-commands.md).
- **The pre-commit hook runs the `nul` check, the LF fix, then the char-count check:** `.husky/pre-commit` is `node scripts/check-staged-nul.mjs` (refuses a staged file named `nul`, which a stray `> nul` in Git Bash writes on Windows), then `node scripts/fix-line-endings.mjs`, then `node scripts/validate-char-count.js`. `skills/` drift, parse errors and test failures are caught only by the tests, so run them before committing: the targeted suites for a change that stays in one area, the full `npm test` for shared code or before a PR (see "Targeted tests first" in [Development Commands](./AGENTS-development-commands.md)). 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 are matched case-insensitively; the house form is `Rating`, `Reason`, `Went Well`, `Went Poorly`, and `Rating` must parse to an integer from 1 to 10. 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.
- **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` (the `confidence` patterns in `metrics-pattern.json`): `Confidence: 95%`, or a table row `| Confidence | 95` with no `%`. The four *breakdown* patterns (`breakdown` in `metrics-pattern.json`, one source shared with the console's bait scanner and the skill scripts' `SCRAPE`, kept in step by `test-web-console-hardening.mjs`) run on every draft, METRICS_JSON or not: each matches a bare dimension word followed by whitespace or a colon and then digits, or a table row whose number ends the row. 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` (`-<uid>` on Linux and macOS, a 0700 folder with 0600 handles), 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.
@@ -35,4 +35,4 @@
- **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 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` (the metrics and bot installers both do this). 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.
- **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/` (`ANALYZE_PROMPT_PATH` in `analyzer.ts`, `IMPROVE_PROMPT_PATH` in `improver.ts`). A packed or copied `dist/` without `src/prompts/` fails.