Planny hit the gym and lost some weight

Trimmed the mascot ASCII art across all prompts and installer. Planny is now more aerodynamic and 40% less chunky.
docs: update AGENTS.md with plan2code-metrics section and corrections
2026-07-21 18:33:22 -07:00 · 2026-02-22 21:48:13 -08:00 · 2026-02-22 21:47:45 -08:00 · 2026-02-22 21:41:16 -08:00 · 2026-02-22 21:38:58 -08:00 · 2026-02-22 19:57:40 -08:00
38 changed files with 4205 additions and 501 deletions
@@ -5,6 +5,11 @@ 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
 node_modules/
 package-lock.json
@@ -18,6 +18,10 @@ plan2code/
 ├── plan2code-loop/         # Autonomous loop CLI tool (Node.js/TypeScript)
 │   ├── src/                # TypeScript source
 │   └── dist/               # Built output (tsup)
 ├── plan2code-metrics/      # Recursive self-improvement toolchain
 │   ├── src/                # TypeScript source
 │   │   └── prompts/        # Internal AI prompt templates (no char limit)
 │   └── dist/               # Built output (tsup)
 ├── scripts/                # Development scripts
 │   └── validate-char-count.js  # Pre-commit character count validator
 ├── dist/                   # Generated distribution files (auto-generated)
@@ -54,7 +58,7 @@ plan2code/
 | `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-4--finalize.md` | 4 | Validate, summarize, archive |
+| `plan2code-4--finalize.md` | 4 | Validate, summarize, feedback, archive (7 steps) |
 ## Plan2Code Loop (`plan2code-loop/`)
@@ -94,47 +98,125 @@ The LLM must output one of these formats:
 - `PHASE_COMPLETE` - Current phase finished (phase mode only)
 - `LOOP_COMPLETE` - All phases finished
 ## Plan2Code Metrics (`plan2code-metrics/`)
 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
 ```bash
 cd plan2code-metrics && npm run build  # Build the CLI
 plan2code-metrics                      # Run (fully interactive, no flags)
 ```
 ### 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 |
 ### Key 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` |
 | `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 or Copilot CLI) |
 ### 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` CLI with `--inputFile` for prompt delivery
 - **GitHub Copilot CLI**: `copilot` CLI with stdin prompt delivery
 ### Metric Targets
 | Metric | Target | Direction |
 |--------|--------|-----------|
 | `avg_confidence` | ≥ 90 | higher is better |
 | `avg_task_completion_rate` | ≥ 0.95 | higher is better |
 | `avg_blocker_count` | ≤ 1.5 | lower is better |
 | `avg_completion_marker_success_rate` | ≥ 0.95 | higher 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 |
 Data stored in `.plan2code-metrics/` (runs/, aggregated.json, proposals/).
 ## Development Commands
 ```bash
 # Install dev dependencies (sets up husky pre-commit hooks)
 npm install
-# Run the interactive installer
+# Run the interactive installer (always interactive — any CLI args are silently ignored)
 node install.js
 # Install to specific platform only
 node install.js --platform claude
 node install.js --platform cursor
 node install.js --platform copilot
 node install.js --platform continue
 node install.js --platform windsurf
 node install.js --platform codeium
 node install.js --platform vscode-copilot
 # Preview changes without installing
 node install.js --dry-run
 # Show local (per-project) installation instructions
 node install.js --local
 # Uninstall all Plan2Code files
 node install.js --uninstall
 # 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
 ```
 ### Installer Menu Options
 **Main menu:**
 | Option | Action |
 |--------|--------|
 | `I` | Install Plan2Code for all platforms + loop CLI |
 | `U` | Uninstall Plan2Code files + loop CLI (confirmation required) |
 | `C` | Open CUSTOM sub-menu |
 | `Q` | Quit |
 **CUSTOM sub-menu (`C`):**
 | Option | Action |
 |--------|--------|
 | `A` | Install to ALL platforms + build & link loop CLI |
 | `O` | Build & link plan2code-loop CLI only |
 | `U` | Uninstall prompts from all platforms + unlink loop CLI |
 | `L` | Show local (per-project) install instructions |
-| `1-7` | Install to specific platform |
+| `O` | Install plan2code-loop CLI only |
 | `M` | Install plan2code-metrics CLI only |
 | `Q` | Return to main menu |
 ## How the Installer Works
@@ -145,15 +227,19 @@ cd plan2code-loop && npm run build # Build the CLI
 ### Platform-Specific File Formats
-| Platform | Extension | Header |
+| Platform | Extension / File | Local Dir | Global Dir | Header |
-|----------|-----------|--------|
+|----------|-----------------|-----------|------------|--------|
-| Claude Code | `.md` | None |
+| Claude Code | `.md` | — | — | None |
-| Cursor | `.md` | None |
+| Cursor | `.md` | — | — | None |
-| Copilot CLI | `.md` | YAML frontmatter |
+| Copilot CLI | `.md` | — | — | YAML frontmatter |
-| Continue | `.prompt.md` | YAML frontmatter |
+| Continue | `.prompt.md` | — | — | YAML frontmatter |
-| Windsurf | `.md` | YAML frontmatter |
+| Windsurf | `.md` | — | — | YAML frontmatter |
-| VS Code Copilot | `.prompt.md` | YAML frontmatter |
+| VS Code Copilot | `.prompt.md` | — | — | YAML frontmatter |
-| Codeium | `.md` | YAML frontmatter |
+| Codeium | `.md` | — | — | YAML frontmatter |
 | Claude Code (Skills) | `SKILL.md` in subdir | `.claude/skills/<skill-name>/` | `~/.claude/skills/<skill-name>/` | YAML frontmatter + `disable-model-invocation: true` |
 | Agent Skills (Amp · Gemini CLI · OpenCode) | `SKILL.md` in subdir | `.agents/skills/<skill-name>/` | `~/.agents/skills/<skill-name>/` | YAML frontmatter (no disable flag) |
 | Crush | `SKILL.md` in subdir | — (global only) | `~/.config/crush/skills/<skill-name>/` (Unix) / `%LOCALAPPDATA%\crush\skills\<skill-name>\` (Windows) | YAML frontmatter |
 | Gemini CLI (TOML) | `.toml` | `.gemini/commands/` | `~/.gemini/commands/` | None (TOML fields: `description`, `prompt`) |
 ## Naming Convention
@@ -177,16 +263,19 @@ When modifying workflow prompts in `src/`:
 ## Code Style
- **JavaScript:** CommonJS modules (Node.js built-ins only - no external dependencies)
+- **install.js:** CommonJS, Node.js built-ins only (no external deps), ANSI colors via `COLORS` constant, readline-based prompts
- **Console output:** Uses ANSI color codes via the `COLORS` constant
+- **plan2code-loop & plan2code-metrics:** TypeScript + ESM, built with tsup (target ES2022, moduleResolution: bundler)
- **User interaction:** Readline-based interactive prompts
+  - External deps: `@inquirer/prompts`, `chalk`, `execa`, `ora`
- **File operations:** Synchronous fs operations for simplicity
+  - Interactive CLI via `@inquirer/prompts` (select, input, confirm)
 - **File operations:** Synchronous fs in all packages
 ## Gotchas/Pitfalls
- **Version sync:** When adding a new version to `CHANGELOG.md`, also update `version.json` to match. The installer displays the version from `version.json` in its header.
+- **Version sync:** When adding a new version to `CHANGELOG.md`, also update `version.json` and `package.json` to match. The installer displays the version from `version.json` in its header.
 - **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 must be ≤ 11,000 characters. A husky pre-commit hook enforces this. The 11,000 limit leaves buffer for platform-specific YAML headers (106-142 chars) to stay under Windsurf's 12,000 char limit.
 - **Metrics internal prompts have no char limit:** Files in `plan2code-metrics/src/prompts/` are NOT subject to the 11,000 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 `\|`.
 ## Git Commit Messages
@@ -199,7 +288,7 @@ When modifying workflow prompts in `src/`:
 ## Mascot
-The project has a mascot - an ASCII art robot that appears in installer output and workflow prompts. Mascot variants are defined in `MASCOT` constant in `install.js` and appear in workflow markdown files.
+The project has a mascot called "Planny" - an ASCII art robot that appears in installer output and workflow prompts. Mascot variants are defined in `MASCOT` constant in `install.js` and appear in workflow markdown files.
 ```
   ╭───╮
@@ -2,6 +2,81 @@
 All notable changes to Plan2Code will be documented in this file.
 ## v1.8.1
 ### ✨ Added
 - **User feedback collection** — Optional 1-10 rating with reason, what went well, and what went poorly
  - Finalize prompt (Step 5) asks for optional feedback before archival, writes structured table to `overview.md`
  - Collector parses `## User Feedback` table from `overview.md` into `RunMetrics.user_feedback`
  - Aggregator computes `avg_user_rating` and `feedback_count` per cohort
  - CLI offers interactive feedback collection if none found during metrics collection
  - Analysis and improvement prompts reference `avg_user_rating` metric target (≥ 7.0)
  - `UserFeedback` type exported from public API
 - **Pipe-safe feedback parsing** — User text containing `|` characters is escaped on write and correctly unescaped on parse using negative lookbehind regex
 ### 🐛 Fixed
 - **Duplicate run files** — Interactive feedback no longer creates a second run JSON; the original is deleted before re-collecting
 - **Finalize step ordering** — Feedback collection moved to Step 5 (before archival at Step 6), ensuring `overview.md` is written while still in the active spec directory
 ## v1.8.0
 ### ✨ Added
 - **plan2code-metrics** — New recursive self-improvement toolchain for plan2code contributors (`plan2code-metrics/`)
  - Fully interactive menu-driven CLI — no flags, all inputs collected via prompts
  - **Collect** metrics from completed project specs (plan, document, implement, finalize steps)
  - **Import** run data from other projects for cross-project aggregation
  - **View** metrics status with health indicators and generation-over-generation deltas
  - **Analyze** weak steps via AI-powered diagnosis (Claude Code or GitHub Copilot CLI)
  - **Generate** surgical improvement proposals with automatic validation (char count limits, edit verification)
  - **Review and apply** proposals with interactive diff review
  - Cohort-based aggregation groups runs by prompt generation (SHA fingerprint of prompt files)
  - Supports both Claude Code and GitHub Copilot CLI as AI backends
  - Standalone TypeScript package with tsup build (ESM), installed via `npm link`
 ### 🔧 Changed
 - **plan2code-4--finalize.md** — Added "Metrics Capture (Contributors)" note in Step 6 directing contributors to run `plan2code-metrics` after finalization
 - **plan2code-loop index.ts** — Added dim hint "run plan2code-metrics" after session summary
 ## v1.7.0
 ### ✨ Added
 - **4 new platform targets** — Gemini CLI, Crush, Amp, and OpenCode now supported
  - Gemini CLI installs as TOML commands (`.gemini/commands/plan2code-*.toml`)
  - Crush installs as skill subdirs (`~/.config/crush/skills/` on Unix, `%LOCALAPPDATA%\crush\skills\` on Windows)
  - Amp and OpenCode covered via shared Agent Skills target (`.agents/skills/`)
 - **Claude Code Skills format** — Migrated from flat `.claude/commands/*.md` to `.claude/skills/<skill-name>/SKILL.md` with `disable-model-invocation: true` frontmatter
 - **Agent Skills cross-tool target** — Single `.agents/skills/` install covers Amp, Gemini CLI, and OpenCode simultaneously
 - **Legacy cleanup** — Old `.claude/commands/plan2code-*.md` files automatically removed on install and uninstall
 - **TOML generation** — New `generateTomlContent()` produces Gemini CLI command files using TOML literal multi-line strings
 ### 🔧 Changed
 - `AGENTS.md` Platform-Specific File Formats table expanded to 5 columns with 4 new platform rows
 - `docs/index.html` hero section updated with 4 new platform pills
 - `README.md` Supported Platforms list updated with 4 new platforms
 ## v1.6.2
 ### 🔧 Changed
 - **Installer menu simplified** — Replaced the 7-platform picker with a clean 4-option menu (I/U/C/Q)
  - `I` — Install Plan2Code for all platforms + loop CLI
  - `U` — Uninstall (with confirmation prompt)
  - `C` — CUSTOM sub-menu: `L` (local install instructions), `O` (loop CLI only), `Q` (back)
  - `Q` — Quit
  - Any CLI arguments (e.g. `--dry-run`, `--platform`) are now silently ignored; installer always runs interactively
 - **README installation section** — npx install method promoted to primary recommended install path; updated menu example
 ### 🗑️ Removed
 - CLI flags `--dry-run`, `--platform`, `--local`, `--uninstall`, `--help`, `--loop`, `--uninstall-loop` (all removed; installer is always interactive)
 - `displayHelp()` function removed from `install.js`
 ## v1.6.1
 ### ✨ Added
@@ -3,7 +3,7 @@
 ## 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                 |
@@ -2,7 +2,7 @@
 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">
+<img src="docs/desk.jpg" alt="Plan2Code Workflow" height="275">
 ## Overview
@@ -15,8 +15,8 @@ A structured 4-step workflow for developing features and projects with AI assist
      New Chat               New Chat           New Chat (per phase)        New Chat
 ```
-| Command | Use When |
+| Command                          | When to Use                                              |
-|---------|----------|
+|----------------------------------|----------------------------------------------------------|
 | `/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         |
@@ -40,13 +40,13 @@ See [QUICK-REFERENCE.md](QUICK-REFERENCE.md) for full reference card.
 Plan2Code includes an interactive installer that generates and installs workflow files for all major AI coding assistants.
-<img src="docs/install-script.jpg" width="582">
+<img src="docs/install-script.jpg" width="600">
 ### Prerequisites
 The install script requires **Node.js** (v14 or later). If you don't have Node.js installed:
-1. Download from [nodejs.org](https://nodejs.org/)
+1. Download from [nodejs.org](https://nodejs.org/) (recommended)
 2. Or use a package manager:
   - **macOS:** `brew install node`
   - **Windows:** `winget install OpenJS.NodeJS` or `choco install nodejs`
@@ -61,8 +61,28 @@ The install script requires **Node.js** (v14 or later). If you don't have Node.j
 - Codeium (IntelliJ)
 - GitHub Copilot CLI
 - VS Code GitHub Copilot
 - Gemini CLI
 - Crush
 - Amp
 - OpenCode
-### Quick Start
+### Install via npx (Recommended — No Clone Required)
 Run the interactive installer directly using `npx` with your preferred GitHub authentication method:
 **If you use SSH keys:**
 ```bash
 npx git+ssh://git@github.com/jparkerweb/plan2code.git
 ```
 **If you use HTTPS authentication:**
 ```bash
 npx git+https://github.com/jparkerweb/plan2code.git
 ```
 This downloads the installer to a temporary location, runs it, installs the workflow files to your machine, and cleans up automatically. The installed workflows remain on your system and work independently. To update or reinstall, simply run the command again.
 ### Standard Installation (Clone Method)
 #### No Clone Required
@@ -84,7 +104,7 @@ This downloads the installer to a temporary location, runs it, installs the work
 ```bash
 # Clone the repository
-git clone https://github.com/plan/plan2code.git
+git clone https://github.com/jparkerweb/plan2code.git
 cd plan2code
 # Run the interactive installer
@@ -94,30 +114,21 @@ node install.js
 npm install
 ```
-The installer will display an interactive menu:
+The installer displays an interactive menu:
 ```
-Available platforms:
+╔════════════════════════════════════════════════════════════════╗
 ║ INSTALL PLAN2CODE                                            ║
 ╠════════════════════════════════════════════════════════════════╣
 ║  I.  INSTALL    Install Plan2Code for all platforms          ║
 ║  U.  UNINSTALL  Remove Plan2Code files                       ║
 ║  C.  CUSTOM     Advanced options                               ║
 ║  Q.  QUIT       Exit                                           ║
 ╚════════════════════════════════════════════════════════════════╝
-  1. Claude Code      (~/.claude/commands/)
+SELECT OPTION (I, U, C, Q) [I]:
  2. Copilot CLI      (~/.copilot/agents/)
  3. Cursor           (~/.cursor/commands/)
  4. Continue         (~/.continue/prompts/)
  5. Windsurf         (~/.codeium/windsurf/global_workflows/)
  6. Codeium (IJ)     (~/.codeium/global_workflows/)
  7. VS Code Copilot  (%APPDATA%\Code\User\prompts\)
  A. Install ALL platforms + loop CLI
  O. Build/link plan2code-loop CLI only
  L. Show local (project) install instructions
  U. Uninstall Plan2Code files + unlink loop CLI
  Q. Quit
 Enter choice (1-7, A, O, L, U, Q, or comma-separated like 1,3,5):
 ```
 For per-project installation or additional options, run `node install.js --help`.
 ---
 ## Important: Start Fresh Conversations
@@ -405,10 +416,10 @@ For hands-off implementation, Plan2Code includes an optional autonomous loop CLI
 # From the plan2code root directory:
 # Option 1: Install everything (recommended)
-node install.js  # Select option A
+node install.js  # Select I at the menu
 # Option 2: Install loop only
-node install.js  # Select option O
+node install.js  # Select C, then O at the menu
 ```
 ### Using the Loop
@@ -1,6 +1,6 @@
 {
  "name": "plan2code",
-  "version": "1.6.1",
+  "version": "1.8.1",
  "private": true,
  "bin": {
    "plan2code": "./install.js"
@@ -1,6 +1,6 @@
 {
  "name": "plan2code-loop",
-  "version": "1.6.1",
+  "version": "1.6.2",
  "description": "Plan2Code Loop - Autonomous spec-driven implementation CLI",
  "type": "module",
  "main": "dist/index.js",
@@ -176,7 +176,7 @@ async function handleExistingSession(
 export async function setupSession(
  stateManager: StateManager
 ): Promise<SessionSetupResult | null> {
-  // Show welcome
+  // Show Planny welcome
  logger.welcome();
  // Select spec
@@ -80,6 +80,7 @@ export async function run(): Promise<LoopResult | null> {
    logger.dim('  - config.json (session configuration)');
    logger.dim('  - scratchpad.md (LLM-managed notes)');
    logger.dim('  - iteration.log (history)');
    logger.dim('Tip: run `plan2code-metrics` to capture run data for prompt improvement.');
    return loopResult;
  } finally {
@@ -40,7 +40,7 @@ export async function ensureGitRepo(cwd: string): Promise<boolean> {
 /**
 * Required entries for the .gitignore file
 */
-const REQUIRED_GITIGNORE_ENTRIES = ['specs/', 'specs--completed/', 'nul', 'node_modules/'];
+const REQUIRED_GITIGNORE_ENTRIES = ['specs/', 'specs--completed/', '.plan2code-loop', '.plan2code-metrics', 'nul', 'node_modules/'];
 /**
 * Ensure .gitignore exists with required entries
@@ -109,7 +109,9 @@ export async function createTaskCommit(options: GitCommitOptions): Promise<boole
    // Build commit message
    let commitMessage = taskName;
    if (jiraTicketId) {
-      commitMessage = `${taskName}\n\n${jiraTicketId}`;
+      commitMessage = `${taskName}\n\n${jiraTicketId}\n\nAI Assisted`;
    } else {
      commitMessage = `${taskName}\n\nAI Assisted`;
    }
    // Create the commit
@@ -0,0 +1,289 @@
 # plan2code-metrics
 Recursive self-improvement toolchain for plan2code contributors. Collects metrics from completed project specs, aggregates them across runs and prompt generations, then uses AI to diagnose weak steps and propose targeted edits to the workflow prompts.
 ## Quick Reference
 ```bash
 # Install (one-time, from the plan2code root)
 node install.js            # → "I" (Install All) includes metrics
                           # → or "M" (Metrics only) under the CUSTOM sub-menu
 # After finishing any project spec (steps 1-4):
 cd your-project
 plan2code-metrics          # → "Collect metrics" → pick your spec dir → done (5 sec)
 # When you're curious or have 3+ runs:
 plan2code-metrics          # → "View metrics status" to see the dashboard
                           # → "Run analysis" for AI diagnosis of weak spots
                           # → "Generate improvement proposal" for prompt edits
                           # → "Review and apply" to patch src/plan2code-*.md
 ```
 **One habit:** collect after every finished spec. Everything else is on-demand.
 ### How Many Runs Do I Need?
 | Runs | What You Get |
 |------|-------------|
 | **1** | Raw data and basic dashboard. Start here. |
 | **3+** | AI analysis unlocks (warns below 3 that results may be unreliable). Pattern detection starts working. |
 | **5-10+** | Averages stabilize. Generation-over-generation comparisons become meaningful. |
 More is always better — each run adds a data point. You're looking for trends, not individual scores.
 ### The Feedback Loop
 ```
 Use plan2code on a project (steps 1-4)
     |
     v
 Collect metrics from the finished spec       <-- do this every time
     |
     v
 Aggregate across runs (automatic)
     |
     v
 Analyze weak spots (AI-powered, 3+ runs)
     |
     v
 Generate prompt improvements
     |
     v
 Apply edits to src/plan2code-*.md
     |
     v
 Prompts have new SHA hashes = new "generation"
     |
     v
 Use improved prompts on next project
     |
     v
 Collect again, compare generations            <-- the loop closes
 ```
 After applying edits, the prompt file SHA hashes change. The next collected run falls into a **new cohort** (generation). The dashboard then shows generation-over-generation deltas — "Did confidence go up? Did blockers decrease?" — so you can measure whether your edits actually helped.
 ---
 ## Installation
 Requires Node.js >= 18.
 ### Via the plan2code installer (recommended)
 From the plan2code repo root:
 ```bash
 node install.js
 ```
 Choose **I** (Install All) to install prompts, loop CLI, and metrics together. Or choose **C** (Custom) then **M** (Metrics) to install just the metrics CLI.
 The installer handles `npm install`, `npm run build`, and global linking automatically. After install, `plan2code-metrics` is available from any directory.
 ### Manual install
 If you prefer to install manually or are developing on the metrics package:
 ```bash
 cd plan2code-metrics
 npm install
 npm run build
 npm link
 ```
 To run without linking:
 ```bash
 npm start
 # or
 node dist/bin/plan2code-metrics.js
 ```
 ## Usage
 Run `plan2code-metrics` from inside (or near) a plan2code repository. The CLI is fully interactive — no flags, all inputs collected via prompts.
 ```
 plan2code-metrics
 ```
 ### Main Menu
 | Option | Description |
 |--------|-------------|
 | **Collect metrics** | Parse a completed project spec and extract step-by-step metrics into a run JSON |
 | **Import run data** | Copy a run JSON from another project into the local metrics store |
 | **View metrics status** | Show aggregated metrics with health indicators and generation deltas |
 | **Run analysis** | AI-powered diagnosis of weak steps (requires Claude Code or Copilot CLI) |
 | **Generate improvement proposal** | AI generates surgical prompt edits based on a diagnosis |
 | **Review and apply** | Interactive diff review to accept/reject individual edits |
 ### Each Time You Finish a Spec
 After completing Step 4 (finalize) on any project:
 ```bash
 cd your-project
 plan2code-metrics
 ```
 Pick **"Collect metrics"** and point it at your spec directory (`specs/<feature>/` or `specs--completed/<feature>/`). It reads your artifacts, extracts ~30 metrics, and writes a run JSON. Takes about 5 seconds.
 The data stays local to that project in `.plan2code-metrics/runs/`. To aggregate across multiple projects, use **"Import"** to copy run files into one central location.
 ### Cross-Project Aggregation
 If you use plan2code across several repos, you can consolidate all run data in one place:
 ```bash
 # From your central repo (e.g., the plan2code repo itself):
 plan2code-metrics
 # → "Import run data"
 # → Paste path to: /path/to/other-project/.plan2code-metrics/runs/run-xxx.json
 ```
 Imported runs are copied locally and included in all future aggregations, analyses, and comparisons.
 ## What It Measures
 Each collection scrapes your spec files and extracts:
 ### Step 1 (Plan) — from `PLAN-DRAFT-*.md` and `PLAN-CONVERSATION-*.md`
 - **Confidence score** — overall planning confidence percentage
 - **Confidence breakdown** — requirements, feasibility, integration, risk sub-scores
 - **Clarification rounds** — how many rounds of Q&A occurred
 - **Verification gaps found** — missing requirements caught during verification
 - **Functional/non-functional requirement counts** — FR- and NFR- headings
 - **Risk count** — risk table entries
 - **Phase count** — number of implementation phases planned
 ### Step 2 (Document) — from `overview.md` and `phase-*.md`
 - **Total tasks** — checkbox count across all phases
 - **Tasks per phase** — distribution of work
 - **Phase count** — number of phase files
 - **Parallel groups** — parallel execution groups identified
 - **Requirement coverage** — coverage percentage if present
 - **Verification items** — verification checklist items added
 ### Step 3 (Implement) — from `.plan2code-loop/` data (loop mode only)
 - **Task completion rate** — completed / total tasks
 - **Blocker count** — tasks marked TASK_BLOCKED
 - **Blocker categories** — normalized reasons for blocks
 - **Total iterations** — loop iteration count
 - **Avg iteration duration** — mean time per iteration
 - **Exit code distribution** — process exit codes
 - **Completion marker success rate** — valid markers / total iterations
 ### Step 4 (Finalize) — from `overview.md` and directory structure
 - **Completion rate at audit** — tasks done at finalization time
 - **Verification failures** — tasks marked with `[!]`
 - **Documentation updates needed** — TODO/FIXME/update markers
 - **Archival success** — whether spec was moved to `specs--completed/`
 ### Health Targets
 The dashboard compares key metrics against targets:
 | Metric | Target | Direction |
 |--------|--------|-----------|
 | avg_confidence | 90 | >= |
 | avg_clarification_rounds | 2.0 | <= |
 | avg_verification_gaps_found | 2.0 | <= |
 | avg_parallel_groups | 0.5 | >= |
 | avg_task_completion_rate | 0.95 | >= |
 | avg_blocker_count | 1.5 | <= |
 | avg_completion_marker_success_rate | 0.95 | >= |
 | avg_verification_failures_found | 1.0 | <= |
 | archival_success_rate | 0.99 | >= |
 Green checkmark = meeting target. Red X = below target (with the target shown).
 ## How It Works
 ### 1. Collect
 Reads completed project artifacts from `specs/` or `specs--completed/` and extracts metrics for each workflow step. Output: `.plan2code-metrics/runs/run-<timestamp>.json`
 ### 2. Aggregate
 Merges all run files into `aggregated.json`, grouped by **prompt generation** — a SHA fingerprint of the 8 workflow prompt files. Two runs that used identical prompt files belong to the same cohort.
 ### 3. Analyze
 Sends aggregated metrics to an AI model with an analyst prompt. The AI produces a diagnosis identifying the weakest workflow steps and root causes. No edits are proposed at this stage.
 Output: `.plan2code-metrics/proposals/<timestamp>-diagnosis.md`
 ### 4. Improve
 Sends the diagnosis plus current prompt file contents to an AI model. The AI proposes surgical `old_text -> new_text` edits, each validated against:
 - The `old_text` actually exists in the target file
 - The edited file stays under the 11,000 character limit
 Output: `.plan2code-metrics/proposals/prop-<timestamp>.json`
 ### 5. Apply
 Interactive diff review for each proposed edit. Accept, reject, or skip individual changes. Applied edits are patched directly into `src/plan2code-*.md`.
 ## Data Directory
 All metrics data lives in `.plan2code-metrics/` (add to `.gitignore` if desired):
 ```
 .plan2code-metrics/
 ├── runs/                  # Individual run JSONs
 │   ├── run-20260215-120000-a1b2.json
 │   └── run-20260220-090000-c3d4.json
 ├── aggregated.json        # Merged cohort data
 └── proposals/             # Diagnoses and improvement proposals
    ├── 20260220-diagnosis.md
    └── prop-20260220.json
 ```
 ## AI Backends
 The analysis and improvement steps require an AI agent. Two backends are supported:
 | Backend | Command | Notes |
 |---------|---------|-------|
 | **Claude Code** | `claude` | Uses `--print` mode. Recommended. |
 | **GitHub Copilot CLI** | `copilot` | Uses stdin piping with `--allow-all-tools -s`. |
 Model selection is interactive — choose from available models when prompted.
 ## Architecture
 ```
 src/
 ├── bin/plan2code-metrics.ts   # Entry point
 ├── cli.ts                     # Interactive menu (main loop)
 ├── types.ts                   # RunMetrics, PromptProposal, CohortMetrics, etc.
 ├── collector.ts               # Reads project artifacts → run JSON
 ├── aggregator.ts              # Merges runs → aggregated.json (cohort grouping)
 ├── analyzer.ts                # AI diagnosis via LLM invocation
 ├── improver.ts                # AI improvement proposal + validation
 ├── applier.ts                 # Interactive diff review + file patching
 ├── invoke-llm.ts              # Unified LLM invocation (Claude Code / Copilot CLI)
 ├── index.ts                   # Public API exports
 └── prompts/
    ├── analyze.md             # AI prompt template for diagnosis
    └── improve.md             # AI prompt template for improvement proposals
 ```
 ## Development
 ```bash
 npm run dev      # Watch mode (rebuilds on change)
 npm run build    # Production build
 npm test         # Run unit tests
 npm run test:watch  # Watch mode tests
 npm start        # Run the CLI
 ```
@@ -0,0 +1,46 @@
 {
  "name": "plan2code-metrics",
  "version": "1.0.0",
  "description": "Plan2Code Metrics - Recursive self-improvement toolchain for plan2code contributors",
  "type": "module",
  "main": "dist/index.js",
  "bin": {
    "plan2code-metrics": "./dist/bin/plan2code-metrics.js"
  },
  "files": [
    "dist"
  ],
  "engines": {
    "node": ">=18.0.0"
  },
  "keywords": [
    "cli",
    "ai",
    "metrics",
    "plan2code",
    "contributor-tooling"
  ],
  "license": "MIT",
  "scripts": {
    "build": "tsup",
    "dev": "tsup --watch",
    "start": "node dist/bin/plan2code-metrics.js",
    "test": "vitest run",
    "test:watch": "vitest",
    "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",
    "vitest": "^3.1.1"
  }
 }
@@ -0,0 +1,154 @@
 import { describe, it, expect } from 'vitest';
 import { avg, rate, buildCohortKey, backfillPromptVersions } from './aggregator.js';
 import type { PromptVersions } from './types.js';
 // ── avg() ─────────────────────────────────────────────────────────────────────
 describe('avg', () => {
  it('returns null for empty array', () => {
    expect(avg([])).toBeNull();
  });
  it('returns null for all-null/undefined values', () => {
    expect(avg([null, undefined, null])).toBeNull();
  });
  it('computes correct average for valid numbers', () => {
    expect(avg([10, 20, 30])).toBe(20);
  });
  it('filters out null/undefined/NaN from mixed arrays', () => {
    expect(avg([10, null, 20, undefined, NaN, 30])).toBe(20);
  });
 });
 // ── rate() ────────────────────────────────────────────────────────────────────
 describe('rate', () => {
  it('returns null for empty array', () => {
    expect(rate([])).toBeNull();
  });
  it('returns null for all-null values', () => {
    expect(rate([null, null])).toBeNull();
  });
  it('returns 1.0 for all-true', () => {
    expect(rate([true, true, true])).toBe(1.0);
  });
  it('returns 0.0 for all-false', () => {
    expect(rate([false, false, false])).toBe(0.0);
  });
  it('computes correct rate for mixed true/false', () => {
    expect(rate([true, false, true, false])).toBe(0.5);
  });
  it('filters out null/undefined from mixed arrays', () => {
    expect(rate([true, null, false, undefined])).toBe(0.5);
  });
 });
 // ── backfillPromptVersions() ──────────────────────────────────────────────────
 const FULL_VERSIONS: PromptVersions = {
  plan: 'sha256:aaa',
  revise_plan: 'sha256:bbb',
  document: 'sha256:ccc',
  implement: 'sha256:ddd',
  finalize: 'sha256:eee',
  init: 'sha256:fff',
  init_update: 'sha256:ggg',
  quick_task: 'sha256:hhh',
 };
 describe('backfillPromptVersions', () => {
  it('returns all 8 fields with sentinels when given empty-ish object', () => {
    const result = backfillPromptVersions({} as PromptVersions);
    expect(Object.keys(result)).toHaveLength(8);
    for (const val of Object.values(result)) {
      expect(val).toBe('sha256:missing');
    }
  });
  it('preserves existing values, fills missing with sha256:missing', () => {
    const partial = { plan: 'sha256:aaa', implement: 'sha256:ddd' } as PromptVersions;
    const result = backfillPromptVersions(partial);
    expect(result.plan).toBe('sha256:aaa');
    expect(result.implement).toBe('sha256:ddd');
    expect(result.revise_plan).toBe('sha256:missing');
    expect(result.document).toBe('sha256:missing');
    expect(result.finalize).toBe('sha256:missing');
    expect(result.init).toBe('sha256:missing');
    expect(result.init_update).toBe('sha256:missing');
    expect(result.quick_task).toBe('sha256:missing');
  });
  it('returns unchanged object when all 8 fields present', () => {
    const result = backfillPromptVersions(FULL_VERSIONS);
    expect(result).toEqual(FULL_VERSIONS);
  });
 });
 // ── buildCohortKey() ──────────────────────────────────────────────────────────
 describe('buildCohortKey', () => {
  it('returns 12-char hex string', () => {
    const key = buildCohortKey(FULL_VERSIONS);
    expect(key).toMatch(/^[0-9a-f]{12}$/);
  });
  it('is deterministic (same input → same output)', () => {
    const key1 = buildCohortKey(FULL_VERSIONS);
    const key2 = buildCohortKey(FULL_VERSIONS);
    expect(key1).toBe(key2);
  });
  it('old 4-field run with backfill sentinels produces same key as raw 4-field object', () => {
    // Simulate an old run that only had 4 fields
    const oldRun = {
      plan: 'sha256:aaa',
      implement: 'sha256:ddd',
      document: 'sha256:ccc',
      finalize: 'sha256:eee',
    } as PromptVersions;
    // After backfill, the missing fields get 'sha256:missing'
    const backfilled = backfillPromptVersions(oldRun);
    // buildCohortKey filters out 'sha256:missing', so both should match
    const keyDirect = buildCohortKey(oldRun);
    const keyBackfilled = buildCohortKey(backfilled);
    expect(keyDirect).toBe(keyBackfilled);
  });
  it('different prompt versions → different keys', () => {
    const altered = { ...FULL_VERSIONS, plan: 'sha256:zzz' };
    expect(buildCohortKey(FULL_VERSIONS)).not.toBe(buildCohortKey(altered));
  });
  it('key is independent of field insertion order', () => {
    const ordered: PromptVersions = {
      plan: 'sha256:aaa',
      revise_plan: 'sha256:bbb',
      document: 'sha256:ccc',
      implement: 'sha256:ddd',
      finalize: 'sha256:eee',
      init: 'sha256:fff',
      init_update: 'sha256:ggg',
      quick_task: 'sha256:hhh',
    };
    const reversed: PromptVersions = {
      quick_task: 'sha256:hhh',
      init_update: 'sha256:ggg',
      init: 'sha256:fff',
      finalize: 'sha256:eee',
      implement: 'sha256:ddd',
      document: 'sha256:ccc',
      revise_plan: 'sha256:bbb',
      plan: 'sha256:aaa',
    };
    expect(buildCohortKey(ordered)).toBe(buildCohortKey(reversed));
  });
 });
@@ -0,0 +1,227 @@
 /**
 * aggregator.ts
 * Merges all run JSON files into aggregated.json, grouped by prompt generation (SHA fingerprint).
 */
 import fs from 'fs';
 import path from 'path';
 import crypto from 'crypto';
 import type { RunMetrics, AggregatedMetrics, CohortMetrics, PromptVersions } from './types.js';
 // ── Helpers ───────────────────────────────────────────────────────────────────
 export function avg(values: (number | null | undefined)[]): number | null {
  const valid = values.filter((v): v is number => v != null && !isNaN(v));
  if (valid.length === 0) return null;
  return valid.reduce((a, b) => a + b, 0) / valid.length;
 }
 export function rate(values: (boolean | null | undefined)[]): number | null {
  const valid = values.filter((v): v is boolean => v != null);
  if (valid.length === 0) return null;
  return valid.filter(v => v).length / valid.length;
 }
 /**
 * Build a stable cohort key from the sorted prompt_versions object.
 * Two runs with identical prompt files get the same cohort key.
 */
 export function buildCohortKey(promptVersions: PromptVersions): string {
  // Filter out missing sentinels so old runs (4 fields) keep their original key
  const entries = Object.entries(promptVersions)
    .filter(([, v]) => v !== 'sha256:missing')
    .sort(([a], [b]) => a.localeCompare(b));
  const str = JSON.stringify(Object.fromEntries(entries));
  return crypto.createHash('sha256').update(str).digest('hex').slice(0, 12);
 }
 /**
 * Backfill missing PromptVersions fields for old run files (pre-v1.1).
 */
 export function backfillPromptVersions(pv: PromptVersions): PromptVersions {
  return {
    plan:        pv.plan        ?? 'sha256:missing',
    revise_plan: pv.revise_plan ?? 'sha256:missing',
    document:    pv.document    ?? 'sha256:missing',
    implement:   pv.implement   ?? 'sha256:missing',
    finalize:    pv.finalize    ?? 'sha256:missing',
    init:        pv.init        ?? 'sha256:missing',
    init_update: pv.init_update ?? 'sha256:missing',
    quick_task:  pv.quick_task  ?? 'sha256:missing',
  };
 }
 // ── Load run files ────────────────────────────────────────────────────────────
 export function loadRunFiles(runsDir: string): RunMetrics[] {
  if (!fs.existsSync(runsDir)) return [];
  const files = fs.readdirSync(runsDir)
    .filter(f => f.endsWith('.json') && f.startsWith('run-'))
    .sort();
  const runs: RunMetrics[] = [];
  for (const file of files) {
    try {
      const content = fs.readFileSync(path.join(runsDir, file), 'utf8');
      const data = JSON.parse(content) as RunMetrics;
      data.prompt_versions = backfillPromptVersions(data.prompt_versions);
      runs.push(data);
    } catch (err) {
      console.warn(`Warning: could not parse ${file}: ${err}`);
    }
  }
  return runs;
 }
 // ── Build cohort metrics ──────────────────────────────────────────────────────
 function buildCohort(runs: RunMetrics[], cohortKey: string): CohortMetrics {
  const runIds = runs.map(r => r.run_id);
  const timestamps = runs
    .flatMap(r => [r.project.started_at, r.project.completed_at])
    .filter((t): t is string => t != null)
    .sort();
  // Step 1 averages
  const avgConfidence = avg(runs.map(r => r.step1_plan.final_confidence));
  const avgClarification = avg(runs.map(r => r.step1_plan.clarification_rounds));
  const avgVerifGaps = avg(runs.map(r => r.step1_plan.verification_gaps_found));
  const avgFRCount = avg(runs.map(r => r.step1_plan.functional_requirements_count));
  const avgNFRCount = avg(runs.map(r => r.step1_plan.non_functional_requirements_count));
  const avgRiskCount = avg(runs.map(r => r.step1_plan.risk_count));
  const avgPhaseStep1 = avg(runs.map(r => r.step1_plan.phase_count));
  // Step 2 averages
  const avgTotalTasks = avg(runs.map(r => r.step2_document.total_tasks));
  const avgPhaseStep2 = avg(runs.map(r => r.step2_document.phase_count));
  const avgParallelGroups = avg(runs.map(r => r.step2_document.parallel_groups_identified));
  const avgReqCoverage = avg(runs.map(r => r.step2_document.requirement_coverage_percent));
  const avgVerifItems = avg(runs.map(r => r.step2_document.verification_items_added));
  // Step 3 (loop only)
  const loopRuns = runs.filter(r => r.step3_implement.used_loop_mode);
  const avgCompletionRate = avg(loopRuns.map(r => r.step3_implement.task_completion_rate));
  const avgBlockerCount = avg(loopRuns.map(r => r.step3_implement.blocker_count));
  const avgTotalIter = avg(loopRuns.map(r => r.step3_implement.total_iterations));
  const avgIterDuration = avg(loopRuns.map(r => r.step3_implement.avg_iteration_duration_ms));
  const avgMarkerSuccess = avg(loopRuns.map(r => r.step3_implement.completion_marker_success_rate));
  // Step 4 averages
  const avgCompletionAtAudit = avg(runs.map(r => r.step4_finalize.completion_rate_at_audit));
  const avgVerifFailures = avg(runs.map(r => r.step4_finalize.verification_failures_found));
  const avgDocUpdates = avg(runs.map(r => r.step4_finalize.documentation_updates_needed));
  const archivalRate = rate(runs.map(r => r.step4_finalize.archival_succeeded));
  // User feedback
  const feedbackRuns = runs.filter(r => r.user_feedback != null);
  const avgUserRating = avg(feedbackRuns.map(r => r.user_feedback!.overall_rating));
  const feedbackCount = feedbackRuns.length;
  return {
    cohort_key: cohortKey,
    prompt_versions: runs[0].prompt_versions,
    run_count: runs.length,
    run_ids: runIds,
    first_seen: timestamps[0] ?? runs[0].run_id,
    last_seen: timestamps[timestamps.length - 1] ?? runs[runs.length - 1].run_id,
    avg_confidence: avgConfidence,
    avg_clarification_rounds: avgClarification,
    avg_verification_gaps_found: avgVerifGaps,
    avg_functional_requirements_count: avgFRCount,
    avg_non_functional_requirements_count: avgNFRCount,
    avg_risk_count: avgRiskCount,
    avg_phase_count_step1: avgPhaseStep1,
    avg_total_tasks: avgTotalTasks,
    avg_phase_count_step2: avgPhaseStep2,
    avg_parallel_groups: avgParallelGroups,
    avg_requirement_coverage_percent: avgReqCoverage,
    avg_verification_items_added: avgVerifItems,
    loop_run_count: loopRuns.length,
    avg_task_completion_rate: avgCompletionRate,
    avg_blocker_count: avgBlockerCount,
    avg_total_iterations: avgTotalIter,
    avg_iteration_duration_ms: avgIterDuration,
    avg_completion_marker_success_rate: avgMarkerSuccess,
    avg_completion_rate_at_audit: avgCompletionAtAudit,
    avg_verification_failures_found: avgVerifFailures,
    avg_documentation_updates_needed: avgDocUpdates,
    archival_success_rate: archivalRate,
    avg_user_rating: avgUserRating,
    feedback_count: feedbackCount,
  };
 }
 // ── Main aggregator ───────────────────────────────────────────────────────────
 export function aggregate(runsDir: string, outputPath: string): AggregatedMetrics {
  const runs = loadRunFiles(runsDir);
  // Group by cohort key
  const cohortMap = new Map<string, RunMetrics[]>();
  for (const run of runs) {
    const key = buildCohortKey(run.prompt_versions);
    if (!cohortMap.has(key)) cohortMap.set(key, []);
    cohortMap.get(key)!.push(run);
  }
  // Sort cohorts by first seen
  const cohorts: CohortMetrics[] = [];
  for (const [key, cohortRuns] of cohortMap) {
    cohorts.push(buildCohort(cohortRuns, key));
  }
  cohorts.sort((a, b) => a.first_seen.localeCompare(b.first_seen));
  // Determine current cohort (most recent)
  const currentCohortKey = cohorts.length > 0
    ? cohorts[cohorts.length - 1].cohort_key
    : null;
  const aggregated: AggregatedMetrics = {
    schema_version: '1.0',
    last_updated: new Date().toISOString(),
    total_runs: runs.length,
    cohorts,
    current_cohort_key: currentCohortKey,
  };
  // Write to output path
  const dir = path.dirname(outputPath);
  fs.mkdirSync(dir, { recursive: true });
  fs.writeFileSync(outputPath, JSON.stringify(aggregated, null, 2), 'utf8');
  return aggregated;
 }
 export function loadAggregated(outputPath: string): AggregatedMetrics | null {
  try {
    const content = fs.readFileSync(outputPath, 'utf8');
    return JSON.parse(content) as AggregatedMetrics;
  } catch {
    return null;
  }
 }
 /**
 * Import a single run JSON from another project into the local runs dir.
 * Returns true if imported, false if already present.
 */
 export function importRun(runJsonPath: string, runsDir: string): boolean {
  const content = fs.readFileSync(runJsonPath, 'utf8');
  const run = JSON.parse(content) as RunMetrics;
  run.prompt_versions = backfillPromptVersions(run.prompt_versions);
  const destPath = path.join(runsDir, `${run.run_id}.json`);
  if (fs.existsSync(destPath)) {
    return false; // Already imported
  }
  fs.mkdirSync(runsDir, { recursive: true });
  fs.writeFileSync(destPath, JSON.stringify(run, null, 2), 'utf8');
  return true;
 }
@@ -0,0 +1,128 @@
 /**
 * analyzer.ts
 * Reads aggregated.json + prompt file contents, builds analysis prompt, invokes AI.
 */
 import fs from 'fs';
 import path from 'path';
 import type { AggregatedMetrics } from './types.js';
 import { invokeLLM, type AgentType } from './invoke-llm.js';
 const ANALYZE_PROMPT_PATH = new URL('../src/prompts/analyze.md', import.meta.url).pathname
  .replace(/^\/([A-Za-z]:)/, '$1'); // Fix Windows path
 // ── Helpers ───────────────────────────────────────────────────────────────────
 function readPromptFiles(plan2codeRoot: string): Record<string, string> {
  const srcDir = path.join(plan2codeRoot, 'src');
  const promptFiles = [
    'plan2code-1--plan.md',
    'plan2code-1b--revise-plan.md',
    'plan2code-2--document.md',
    'plan2code-3--implement.md',
    'plan2code-4--finalize.md',
    'plan2code---init.md',
    'plan2code---init-update.md',
    'plan2code---quick-task.md',
  ];
  const contents: Record<string, string> = {};
  for (const file of promptFiles) {
    try {
      contents[file] = fs.readFileSync(path.join(srcDir, file), 'utf8');
    } catch {
      contents[file] = '(file not found)';
    }
  }
  return contents;
 }
 function interpolate(template: string, vars: Record<string, string>): string {
  let result = template;
  for (const [key, value] of Object.entries(vars)) {
    result = result.replaceAll(`{{${key}}}`, value);
  }
  return result;
 }
 function generateDiagnosisId(): string {
  const now = new Date();
  const ts = now.toISOString().replace(/[-:T.Z]/g, '').slice(0, 14);
  return `diag-${ts}`;
 }
 // ── Main analyzer ─────────────────────────────────────────────────────────────
 export interface AnalyzerOptions {
  aggregatedPath: string;    // Path to aggregated.json
  plan2codeRoot: string;     // Path to plan2code repo root
  proposalsDir: string;      // Where to save diagnosis output
  model?: string;            // AI model to use (default: claude-opus-4-6)
  agent?: AgentType;         // Agent to use (default: claude-code)
 }
 export async function runAnalysis(opts: AnalyzerOptions): Promise<string> {
  const { aggregatedPath, plan2codeRoot, proposalsDir, model = 'claude-opus-4-6', agent = 'claude-code' } = opts;
  // Load aggregated metrics
  let aggregated: AggregatedMetrics | null = null;
  try {
    aggregated = JSON.parse(fs.readFileSync(aggregatedPath, 'utf8')) as AggregatedMetrics;
  } catch {
    throw new Error(`Could not read aggregated metrics at ${aggregatedPath}. Run "Collect metrics" and "Import run data" first.`);
  }
  if (aggregated.total_runs === 0) {
    throw new Error('No runs in aggregated metrics. Collect and import some runs first.');
  }
  // Read prompt files
  const promptContents = readPromptFiles(plan2codeRoot);
  // Format for interpolation
  const promptContentsStr = Object.entries(promptContents)
    .map(([file, content]) => `## ${file}\n\n${content}`)
    .join('\n\n---\n\n');
  const aggregatedStr = JSON.stringify(aggregated, null, 2);
  // Load analyze prompt template
  let analyzeTemplate: string;
  try {
    analyzeTemplate = fs.readFileSync(ANALYZE_PROMPT_PATH, 'utf8');
  } catch {
    // Fallback: look relative to cwd
    const altPath = path.join(process.cwd(), 'src', 'prompts', 'analyze.md');
    analyzeTemplate = fs.readFileSync(altPath, 'utf8');
  }
  const fullPrompt = interpolate(analyzeTemplate, {
    aggregatedMetrics: aggregatedStr,
    promptContents: promptContentsStr,
  });
  // Invoke Claude
  console.log(`\nInvoking AI analysis (model: ${model})...`);
  console.log('This may take a minute...\n');
  let diagnosisContent: string;
  try {
    diagnosisContent = await invokeLLM({
      prompt: fullPrompt,
      model,
      agent,
      timeout: 300_000,
    });
  } catch (err) {
    throw new Error(`AI invocation failed: ${err instanceof Error ? err.message : String(err)}\n\nMake sure the ${agent} CLI is installed and authenticated.`);
  }
  // Save diagnosis
  const diagId = generateDiagnosisId();
  fs.mkdirSync(proposalsDir, { recursive: true });
  const diagPath = path.join(proposalsDir, `${diagId}-diagnosis.md`);
  fs.writeFileSync(diagPath, diagnosisContent, 'utf8');
  console.log(`Diagnosis saved to: ${diagPath}`);
  return diagPath;
 }
@@ -0,0 +1,201 @@
 /**
 * applier.ts
 * Interactive review of a PromptProposal: display colored diff per edit,
 * user approves/rejects each edit, apply approved edits to src files.
 */
 import fs from 'fs';
 import path from 'path';
 import { confirm } from '@inquirer/prompts';
 import chalk from 'chalk';
 import type { PromptEdit, PromptProposal } from './types.js';
 import { validateEdit } from './improver.js';
 const CHAR_LIMIT = 11_000;
 // ── Diff display ──────────────────────────────────────────────────────────────
 function displayEditDiff(edit: PromptEdit, index: number, total: number): void {
  console.log();
  console.log(chalk.bold(`─── Edit ${index + 1} of ${total} ───────────────────────────────────`));
  console.log(chalk.cyan(`File:     ${edit.file}`));
  console.log(chalk.gray(`Rationale: ${edit.rationale}`));
  console.log(chalk.gray(`Expected impact: ${edit.expected_metric_impact}`));
  console.log(chalk.gray(`Char impact: ${edit.char_count_before} → ${edit.char_count_after} (${edit.char_count_delta >= 0 ? '+' : ''}${edit.char_count_delta})`));
  // Show char count status
  if (edit.char_count_after > CHAR_LIMIT) {
    console.log(chalk.red(`⚠ WARNING: Would exceed ${CHAR_LIMIT} char limit!`));
  } else {
    const headroom = CHAR_LIMIT - edit.char_count_after;
    console.log(chalk.green(`✓ Char count OK (${headroom} chars headroom after edit)`));
  }
  console.log();
  console.log(chalk.bold('── REMOVED (old_text) ──'));
  // Show old text with line-level context
  const oldLines = edit.old_text.split('\n');
  for (const line of oldLines) {
    console.log(chalk.red('- ') + chalk.red(line));
  }
  console.log();
  console.log(chalk.bold('── ADDED (new_text) ──'));
  const newLines = edit.new_text.split('\n');
  for (const line of newLines) {
    console.log(chalk.green('+ ') + chalk.green(line));
  }
  console.log();
 }
 // ── Apply edit to file ────────────────────────────────────────────────────────
 function applyEdit(edit: PromptEdit, plan2codeRoot: string): boolean {
  // Reject path traversal attempts
  if (edit.file.includes('..') || path.isAbsolute(edit.file)) {
    console.error(chalk.red(`✗ Rejected: "${edit.file}" contains path traversal or absolute path`));
    return false;
  }
  const filePath = path.join(plan2codeRoot, 'src', edit.file);
  try {
    let content = fs.readFileSync(filePath, 'utf8');
    if (!content.includes(edit.old_text)) {
      console.error(chalk.red(`✗ Cannot apply: old_text not found in ${edit.file} (may have been modified by a previous edit)`));
      return false;
    }
    content = content.replace(edit.old_text, edit.new_text);
    // Post-apply char count check
    if (content.length > CHAR_LIMIT) {
      console.error(chalk.red(`✗ Cannot apply: would exceed ${CHAR_LIMIT} char limit (${content.length} chars)`));
      return false;
    }
    fs.writeFileSync(filePath, content, 'utf8');
    console.log(chalk.green(`✓ Applied edit to ${edit.file} (now ${content.length} chars)`));
    return true;
  } catch (err) {
    console.error(chalk.red(`✗ Failed to apply edit: ${err instanceof Error ? err.message : String(err)}`));
    return false;
  }
 }
 // ── Main applier ──────────────────────────────────────────────────────────────
 export interface ApplierOptions {
  proposalPath: string;
  plan2codeRoot: string;
  proposalsDir: string;
 }
 export interface ApplierResult {
  approved: number;
  rejected: number;
  applied: number;
  failed: number;
 }
 export async function reviewAndApply(opts: ApplierOptions): Promise<ApplierResult> {
  const { proposalPath, plan2codeRoot, proposalsDir } = opts;
  // Load proposal
  let proposal: PromptProposal;
  try {
    proposal = JSON.parse(fs.readFileSync(proposalPath, 'utf8')) as PromptProposal;
  } catch {
    throw new Error(`Could not read proposal at ${proposalPath}`);
  }
  if (proposal.proposals.length === 0) {
    console.log(chalk.yellow('No edits in this proposal.'));
    return { approved: 0, rejected: 0, applied: 0, failed: 0 };
  }
  console.log();
  console.log(chalk.bold.cyan('=== Plan2Code Prompt Improvement Review ==='));
  console.log(chalk.gray(`Proposal: ${proposal.proposal_id}`));
  console.log(chalk.gray(`Created:  ${proposal.created_at}`));
  console.log(chalk.gray(`Based on: ${proposal.based_on_runs.length} run(s)`));
  console.log(chalk.gray(`Edits:    ${proposal.proposals.length}`));
  // Re-validate all edits against current file state
  const promptContents: Record<string, string> = {};
  const srcDir = path.join(plan2codeRoot, 'src');
  for (const edit of proposal.proposals) {
    if (!promptContents[edit.file]) {
      try {
        promptContents[edit.file] = fs.readFileSync(path.join(srcDir, edit.file), 'utf8');
      } catch {
        promptContents[edit.file] = '';
      }
    }
  }
  let approved = 0;
  let rejected = 0;
  let applied = 0;
  let failed = 0;
  for (let i = 0; i < proposal.proposals.length; i++) {
    const edit = proposal.proposals[i];
    // Re-validate
    const validation = validateEdit(edit, promptContents);
    if (!validation.valid) {
      console.log();
      console.log(chalk.red(`✗ Edit ${i + 1} is no longer valid (files may have changed):`));
      for (const err of validation.errors) {
        console.log(chalk.red(`  - ${err}`));
      }
      rejected++;
      continue;
    }
    displayEditDiff(edit, i, proposal.proposals.length);
    const approve = await confirm({
      message: `Apply this edit to ${edit.file}?`,
      default: true,
    });
    if (!approve) {
      console.log(chalk.gray('Skipped.'));
      rejected++;
      continue;
    }
    approved++;
    const success = applyEdit(edit, plan2codeRoot);
    if (success) {
      applied++;
      // Update in-memory content to reflect the edit
      promptContents[edit.file] = promptContents[edit.file].replace(edit.old_text, edit.new_text);
    } else {
      failed++;
    }
  }
  // Update proposal status
  proposal.status = applied > 0 ? 'applied' : 'rejected';
  fs.writeFileSync(proposalPath, JSON.stringify(proposal, null, 2), 'utf8');
  // Summary
  console.log();
  console.log(chalk.bold('─── Review Complete ──────────────────────────────────'));
  console.log(`Approved: ${chalk.green(String(approved))}  Rejected: ${chalk.red(String(rejected))}  Applied: ${chalk.green(String(applied))}  Failed: ${chalk.red(String(failed))}`);
  if (applied > 0) {
    console.log();
    console.log(chalk.bold.cyan('Next steps — create a PR with your changes:'));
    console.log(chalk.gray('  git add src/'));
    console.log(chalk.gray(`  git commit -m "metrics: apply prompt improvements (${proposal.proposal_id})"`));
    console.log(chalk.gray('  git push -u origin HEAD'));
    console.log(chalk.gray('  gh pr create --title "metrics: apply gen N improvements"'));
  }
  return { approved, rejected, applied, failed };
 }
@@ -0,0 +1,17 @@
 import { runCLI } from '../cli.js';
 async function main() {
  try {
    await runCLI();
    process.exit(0);
  } catch (err) {
    if (err instanceof Error && err.message.includes('User force closed')) {
      // Ctrl+C — exit cleanly
      process.exit(0);
    }
    console.error(err instanceof Error ? err.message : String(err));
    process.exit(1);
  }
 }
 main();
@@ -0,0 +1,645 @@
 /**
 * cli.ts
 * 100% interactive menu-driven CLI for plan2code-metrics.
 * No flags — all inputs collected via @inquirer/prompts.
 */
 import fs from 'fs';
 import path from 'path';
 import { select, input, confirm } from '@inquirer/prompts';
 import chalk from 'chalk';
 import ora from 'ora';
 import { collectRun } from './collector.js';
 import { aggregate, loadAggregated, importRun, loadRunFiles } from './aggregator.js';
 import { runAnalysis } from './analyzer.js';
 import { generateImprovement } from './improver.js';
 import { reviewAndApply } from './applier.js';
 import type { AggregatedMetrics, CohortMetrics } from './types.js';
 import { METRIC_TARGETS } from './types.js';
 import { AGENTS, type AgentType } from './invoke-llm.js';
 // ── Defaults ──────────────────────────────────────────────────────────────────
 const DEFAULT_METRICS_DIR = '.plan2code-metrics';
 const DEFAULT_RUNS_SUBDIR = 'runs';
 const DEFAULT_AGGREGATED_FILE = 'aggregated.json';
 const DEFAULT_PROPOSALS_SUBDIR = 'proposals';
 function getMetricsDirs(baseDir = process.cwd()) {
  const metricsDir = path.join(baseDir, DEFAULT_METRICS_DIR);
  return {
    metricsDir,
    runsDir: path.join(metricsDir, DEFAULT_RUNS_SUBDIR),
    aggregatedPath: path.join(metricsDir, DEFAULT_AGGREGATED_FILE),
    proposalsDir: path.join(metricsDir, DEFAULT_PROPOSALS_SUBDIR),
  };
 }
 // Detect plan2code root (either this directory or parent directories)
 function detectPlan2CodeRoot(): string | null {
  let dir = process.cwd();
  for (let i = 0; i < 5; i++) {
    const srcDir = path.join(dir, 'src');
    if (
      fs.existsSync(path.join(srcDir, 'plan2code-1--plan.md')) &&
      fs.existsSync(path.join(srcDir, 'plan2code-2--document.md'))
    ) {
      return dir;
    }
    const parent = path.dirname(dir);
    if (parent === dir) break;
    dir = parent;
  }
  return null;
 }
 // Detect plan2code version
 function detectPlan2CodeVersion(plan2codeRoot: string): string {
  try {
    const versionPath = path.join(plan2codeRoot, 'version.json');
    const content = JSON.parse(fs.readFileSync(versionPath, 'utf8'));
    return content.version ?? '0.0.0';
  } catch {
    try {
      const pkg = JSON.parse(fs.readFileSync(path.join(plan2codeRoot, 'package.json'), 'utf8'));
      return pkg.version ?? '0.0.0';
    } catch {
      return '0.0.0';
    }
  }
 }
 // ── Metric health helpers ─────────────────────────────────────────────────────
 function metricStatus(key: string, value: number | null): string {
  if (value == null) return chalk.gray('N/A');
  const target = METRIC_TARGETS[key as keyof typeof METRIC_TARGETS];
  if (!target) return chalk.white(String(Math.round(value * 100) / 100));
  const ok = target.direction === 'gte' ? value >= target.target : value <= target.target;
  const formatted = Number.isInteger(value) ? String(value) : value.toFixed(2);
  return ok ? chalk.green(`✓ ${formatted}`) : chalk.red(`✗ ${formatted} (target: ${target.direction === 'gte' ? '≥' : '≤'}${target.target})`);
 }
 // ── Agent + model selection ───────────────────────────────────────────────────
 async function selectAgentAndModel(): Promise<{ agent: AgentType; model: string }> {
  const agentChoice = await select({
    message: 'Which AI agent?',
    choices: Object.values(AGENTS).map(a => ({ name: a.displayName, value: a.name })),
  });
  const agentDef = AGENTS[agentChoice];
  const model = await select({
    message: 'AI model:',
    choices: agentDef.models.map(m => ({ name: m.label, value: m.value })),
  });
  return { agent: agentChoice, model };
 }
 // ── Flow: Collect metrics ─────────────────────────────────────────────────────
 async function flowCollect(): Promise<void> {
  console.log();
  console.log(chalk.bold.cyan('── Collect Metrics ──'));
  const sourceChoice = await select({
    message: 'Where is the completed project spec?',
    choices: [
      { name: 'Active spec directory (specs/<feature-name>/)', value: 'active' },
      { name: 'Archived spec (specs--completed/<feature-name>/)', value: 'archived' },
      { name: 'Custom path', value: 'custom' },
    ],
  });
  let specDir: string;
  let projectName: string;
  if (sourceChoice === 'active' || sourceChoice === 'archived') {
    const baseSubdir = sourceChoice === 'active' ? 'specs' : 'specs--completed';
    const baseDir = path.join(process.cwd(), baseSubdir);
    if (!fs.existsSync(baseDir)) {
      console.log(chalk.red(`No ${baseSubdir}/ directory found in ${process.cwd()}`));
      return;
    }
    const entries = fs.readdirSync(baseDir)
      .filter(f => fs.statSync(path.join(baseDir, f)).isDirectory());
    if (entries.length === 0) {
      console.log(chalk.red(`No spec directories found in ${baseSubdir}/`));
      return;
    }
    const chosen = await select({
      message: 'Select spec directory:',
      choices: entries.map(e => ({ name: e, value: e })),
    });
    specDir = path.join(baseDir, chosen);
    projectName = chosen;
  } else {
    specDir = await input({
      message: 'Enter full path to spec directory:',
      validate: (v) => fs.existsSync(v) ? true : 'Directory not found',
    });
    projectName = await input({
      message: 'Project name (for metrics label):',
      default: path.basename(specDir),
    });
  }
  // Detect plan2code root
  const plan2codeRoot = detectPlan2CodeRoot() ?? process.cwd();
  const plan2codeVersion = detectPlan2CodeVersion(plan2codeRoot);
  const { runsDir, aggregatedPath } = getMetricsDirs();
  const spinner = ora('Collecting metrics from project artifacts...').start();
  try {
    const metrics = await collectRun({
      specDir,
      projectName,
      plan2codeRoot,
      plan2codeVersion,
      outputDir: runsDir,
    });
    spinner.succeed(`Metrics collected: ${metrics.run_id}`);
    console.log(chalk.gray(`  Saved to: ${runsDir}/${metrics.run_id}.json`));
    // Re-aggregate
    aggregate(runsDir, aggregatedPath);
    console.log(chalk.gray('  Aggregated metrics updated.'));
    // Show summary
    console.log();
    console.log(chalk.bold('Collected:'));
    console.log(`  Step 1 (Plan):       ${metrics.step1_plan.present ? chalk.green('✓') : chalk.gray('—')}`);
    console.log(`  Step 2 (Document):   ${metrics.step2_document.present ? chalk.green('✓') : chalk.gray('—')}`);
    console.log(`  Step 3 (Implement):  ${metrics.step3_implement.present ? (metrics.step3_implement.used_loop_mode ? chalk.green('✓ (loop)') : chalk.yellow('✓ (manual)')) : chalk.gray('—')}`);
    console.log(`  Step 4 (Finalize):   ${metrics.step4_finalize.present ? chalk.green('✓') : chalk.gray('—')}`);
    console.log(`  User Feedback:       ${metrics.user_feedback ? chalk.green(`✓ (${metrics.user_feedback.overall_rating}/10)`) : chalk.gray('—')}`);
    // Offer to collect feedback interactively if not present
    if (!metrics.user_feedback) {
      console.log();
      const wantFeedback = await confirm({
        message: 'No user feedback found in overview.md. Would you like to provide feedback now?',
        default: false,
      });
      if (wantFeedback) {
        const rating = await input({
          message: 'Overall rating (1-10):',
          validate: (v) => {
            const n = parseInt(v, 10);
            return (n >= 1 && n <= 10) ? true : 'Must be a number between 1 and 10';
          },
        });
        const reason = await input({ message: 'Rating reason:' });
        const wentWell = await input({ message: 'What went well?' });
        const wentPoorly = await input({ message: 'What went poorly?' });
        // Write the feedback table into overview.md
        const overviewPath = path.join(specDir, 'overview.md');
        let overviewContent = '';
        try {
          overviewContent = fs.readFileSync(overviewPath, 'utf8');
        } catch { /* empty */ }
        // Escape pipe characters in user text to prevent table parsing issues
        const esc = (s: string) => s.replace(/\|/g, '\\|');
        const feedbackTable = [
          '',
          '## User Feedback',
          '| Field | Value |',
          '|-------|-------|',
          `| Rating | ${rating} |`,
          `| Reason | ${esc(reason)} |`,
          `| Went Well | ${esc(wentWell)} |`,
          `| Went Poorly | ${esc(wentPoorly)} |`,
          '',
        ].join('\n');
        fs.writeFileSync(overviewPath, overviewContent + feedbackTable, 'utf8');
        console.log(chalk.green('✓ Feedback written to overview.md'));
        // Delete the original run (without feedback) before re-collecting
        const originalRunPath = path.join(runsDir, `${metrics.run_id}.json`);
        try { fs.unlinkSync(originalRunPath); } catch { /* ignore */ }
        // Re-collect and re-aggregate
        const reSpinner = ora('Re-collecting metrics with feedback...').start();
        const updatedMetrics = await collectRun({
          specDir,
          projectName,
          plan2codeRoot,
          plan2codeVersion,
          outputDir: runsDir,
        });
        aggregate(runsDir, aggregatedPath);
        reSpinner.succeed(`Updated: ${updatedMetrics.run_id} (rating: ${updatedMetrics.user_feedback?.overall_rating}/10)`);
      }
    }
  } catch (err) {
    spinner.fail(`Collection failed: ${err instanceof Error ? err.message : String(err)}`);
  }
 }
 // ── Flow: Import run data ─────────────────────────────────────────────────────
 async function flowImport(): Promise<void> {
  console.log();
  console.log(chalk.bold.cyan('── Import Run Data ──'));
  console.log(chalk.gray('Copy a run JSON from another project into this repo for aggregation.'));
  console.log();
  const sourcePath = await input({
    message: 'Path to run JSON file (e.g., /path/to/project/.plan2code-metrics/runs/run-xxx.json):',
    validate: (v) => {
      if (!fs.existsSync(v)) return 'File not found';
      if (!v.endsWith('.json')) return 'Must be a .json file';
      return true;
    },
  });
  const { runsDir, aggregatedPath } = getMetricsDirs();
  try {
    const imported = importRun(sourcePath, runsDir);
    if (!imported) {
      console.log(chalk.yellow('Run already imported (same run_id exists).'));
    } else {
      console.log(chalk.green(`✓ Imported ${path.basename(sourcePath)}`));
    }
    const spinner = ora('Re-aggregating...').start();
    const aggregated = aggregate(runsDir, aggregatedPath);
    spinner.succeed(`Aggregated metrics updated (${aggregated.total_runs} total runs)`);
  } catch (err) {
    console.error(chalk.red(`Import failed: ${err instanceof Error ? err.message : String(err)}`));
  }
 }
 // ── Flow: View metrics status ─────────────────────────────────────────────────
 async function flowViewStatus(): Promise<void> {
  console.log();
  console.log(chalk.bold.cyan('── Metrics Status & History ──'));
  const { runsDir, aggregatedPath } = getMetricsDirs();
  const aggregated = loadAggregated(aggregatedPath);
  if (!aggregated || aggregated.total_runs === 0) {
    console.log(chalk.yellow('No metrics collected yet. Use "Collect metrics" to get started.'));
    return;
  }
  console.log();
  console.log(chalk.bold(`Total runs: ${aggregated.total_runs}  |  Generations: ${aggregated.cohorts.length}`));
  console.log(chalk.gray(`Last updated: ${aggregated.last_updated}`));
  for (let i = 0; i < aggregated.cohorts.length; i++) {
    const cohort = aggregated.cohorts[i];
    const isCurrent = cohort.cohort_key === aggregated.current_cohort_key;
    const label = isCurrent ? chalk.bold.green('[CURRENT]') : '';
    console.log();
    console.log(chalk.bold(`Generation ${i + 1} (sha:${cohort.cohort_key}) — ${cohort.run_count} run(s) ${label}`));
    console.log(chalk.gray(`  Period: ${cohort.first_seen?.slice(0, 10)} → ${cohort.last_seen?.slice(0, 10)}`));
    // Step 1 metrics
    if (cohort.avg_confidence != null || cohort.avg_clarification_rounds != null) {
      console.log(chalk.bold('  Step 1 (Plan):'));
      if (cohort.avg_confidence != null)
        console.log(`    avg_confidence:           ${metricStatus('avg_confidence', cohort.avg_confidence)}`);
      if (cohort.avg_clarification_rounds != null)
        console.log(`    avg_clarification_rounds: ${metricStatus('avg_clarification_rounds', cohort.avg_clarification_rounds)}`);
      if (cohort.avg_verification_gaps_found != null)
        console.log(`    avg_verification_gaps:    ${metricStatus('avg_verification_gaps_found', cohort.avg_verification_gaps_found)}`);
    }
    // Step 2 metrics
    if (cohort.avg_total_tasks != null || cohort.avg_parallel_groups != null) {
      console.log(chalk.bold('  Step 2 (Document):'));
      if (cohort.avg_total_tasks != null)
        console.log(`    avg_total_tasks:          ${chalk.white(cohort.avg_total_tasks.toFixed(1))}`);
      if (cohort.avg_parallel_groups != null)
        console.log(`    avg_parallel_groups:      ${metricStatus('avg_parallel_groups', cohort.avg_parallel_groups)}`);
      if (cohort.avg_verification_items_added != null)
        console.log(`    avg_verification_items:   ${metricStatus('avg_verification_items_added', cohort.avg_verification_items_added)}`);
    }
    // Step 3 metrics (loop only)
    if (cohort.loop_run_count > 0) {
      console.log(chalk.bold(`  Step 3 (Implement) — ${cohort.loop_run_count} loop run(s):`));
      if (cohort.avg_task_completion_rate != null)
        console.log(`    avg_task_completion_rate: ${metricStatus('avg_task_completion_rate', cohort.avg_task_completion_rate)}`);
      if (cohort.avg_blocker_count != null)
        console.log(`    avg_blocker_count:        ${metricStatus('avg_blocker_count', cohort.avg_blocker_count)}`);
      if (cohort.avg_completion_marker_success_rate != null)
        console.log(`    avg_marker_success_rate:  ${metricStatus('avg_completion_marker_success_rate', cohort.avg_completion_marker_success_rate)}`);
    }
    // Step 4 metrics
    if (cohort.avg_completion_rate_at_audit != null || cohort.archival_success_rate != null) {
      console.log(chalk.bold('  Step 4 (Finalize):'));
      if (cohort.avg_completion_rate_at_audit != null)
        console.log(`    avg_completion_at_audit:  ${chalk.white(cohort.avg_completion_rate_at_audit.toFixed(2))}`);
      if (cohort.avg_verification_failures_found != null)
        console.log(`    avg_verif_failures:       ${metricStatus('avg_verification_failures_found', cohort.avg_verification_failures_found)}`);
      if (cohort.archival_success_rate != null)
        console.log(`    archival_success_rate:    ${metricStatus('archival_success_rate', cohort.archival_success_rate)}`);
    }
    // User feedback
    if (cohort.feedback_count > 0) {
      console.log(chalk.bold('  User Feedback:'));
      console.log(`    avg_user_rating:          ${metricStatus('avg_user_rating', cohort.avg_user_rating)}`);
      console.log(`    feedback_count:           ${chalk.white(String(cohort.feedback_count))}`);
    }
    // Compare with previous generation
    if (i > 0) {
      const prev = aggregated.cohorts[i - 1];
      const deltas: string[] = [];
      if (cohort.avg_confidence != null && prev.avg_confidence != null) {
        const d = cohort.avg_confidence - prev.avg_confidence;
        deltas.push(`confidence ${d >= 0 ? chalk.green(`▲${d.toFixed(1)}`) : chalk.red(`▼${Math.abs(d).toFixed(1)}`)}`);
      }
      if (cohort.avg_task_completion_rate != null && prev.avg_task_completion_rate != null) {
        const d = cohort.avg_task_completion_rate - prev.avg_task_completion_rate;
        deltas.push(`completion ${d >= 0 ? chalk.green(`▲${(d * 100).toFixed(1)}%`) : chalk.red(`▼${(Math.abs(d) * 100).toFixed(1)}%`)}`);
      }
      if (deltas.length > 0) {
        console.log(chalk.gray(`  vs Gen ${i}: ${deltas.join('  ')}`));
      }
    }
  }
  // Run list
  const runs = loadRunFiles(runsDir);
  if (runs.length > 0) {
    console.log();
    console.log(chalk.bold(`Run files (${runs.length}):`));
    for (const run of runs.slice(-10)) {
      console.log(chalk.gray(`  ${run.run_id}  ${run.project.name}  v${run.plan2code_version}`));
    }
    if (runs.length > 10) {
      console.log(chalk.gray(`  ... and ${runs.length - 10} more`));
    }
  }
 }
 // ── Flow: Run analysis ────────────────────────────────────────────────────────
 async function flowRunAnalysis(): Promise<string | null> {
  console.log();
  console.log(chalk.bold.cyan('── Run Analysis (Diagnose Weak Steps) ──'));
  const { aggregatedPath, proposalsDir } = getMetricsDirs();
  const plan2codeRoot = detectPlan2CodeRoot() ?? process.cwd();
  const aggregated = loadAggregated(aggregatedPath);
  if (!aggregated || aggregated.total_runs === 0) {
    console.log(chalk.yellow('No aggregated metrics found. Collect and import runs first.'));
    return null;
  }
  if (aggregated.total_runs < 3) {
    const proceed = await confirm({
      message: `Only ${aggregated.total_runs} run(s) available (≥3 recommended for reliable analysis). Proceed anyway?`,
      default: false,
    });
    if (!proceed) return null;
  }
  const { agent, model } = await selectAgentAndModel();
  try {
    const diagPath = await runAnalysis({
      aggregatedPath,
      plan2codeRoot,
      proposalsDir,
      model,
      agent,
    });
    console.log();
    console.log(chalk.green('✓ Analysis complete'));
    console.log(chalk.gray(`Diagnosis: ${diagPath}`));
    const viewNow = await confirm({
      message: 'Open diagnosis in console?',
      default: true,
    });
    if (viewNow) {
      const content = fs.readFileSync(diagPath, 'utf8');
      console.log();
      console.log(chalk.dim('─'.repeat(60)));
      console.log(content);
      console.log(chalk.dim('─'.repeat(60)));
    }
    return diagPath;
  } catch (err) {
    console.error(chalk.red(`Analysis failed: ${err instanceof Error ? err.message : String(err)}`));
    return null;
  }
 }
 // ── Flow: Generate improvement proposal ──────────────────────────────────────
 async function flowGenerateProposal(): Promise<void> {
  console.log();
  console.log(chalk.bold.cyan('── Generate Improvement Proposal ──'));
  const { aggregatedPath, proposalsDir, runsDir } = getMetricsDirs();
  const plan2codeRoot = detectPlan2CodeRoot() ?? process.cwd();
  // Find diagnosis files
  let diagFiles: string[] = [];
  if (fs.existsSync(proposalsDir)) {
    diagFiles = fs.readdirSync(proposalsDir)
      .filter(f => f.endsWith('-diagnosis.md'))
      .sort()
      .reverse(); // most recent first
  }
  let diagnosisPath: string;
  if (diagFiles.length === 0) {
    console.log(chalk.yellow('No diagnosis files found. Running analysis first...'));
    const diagPath = await flowRunAnalysis();
    if (!diagPath) return;
    diagnosisPath = diagPath;
  } else {
    const choice = await select({
      message: 'Select diagnosis to base proposal on:',
      choices: [
        ...diagFiles.map(f => ({ name: f, value: path.join(proposalsDir, f) })),
        { name: '(run new analysis first)', value: '__new__' },
      ],
    });
    if (choice === '__new__') {
      const diagPath = await flowRunAnalysis();
      if (!diagPath) return;
      diagnosisPath = diagPath;
    } else {
      diagnosisPath = choice;
    }
  }
  const { agent, model } = await selectAgentAndModel();
  try {
    const result = await generateImprovement({
      diagnosisPath,
      plan2codeRoot,
      proposalsDir,
      runsDir,
      model,
      agent,
    });
    console.log();
    console.log(chalk.green(`✓ Proposal generated: ${result.proposal.proposal_id}`));
    console.log(chalk.gray(`  Valid edits:   ${result.validEditCount}`));
    console.log(chalk.gray(`  Invalid edits: ${result.invalidEditCount} (rejected)`));
    console.log(chalk.gray(`  Saved to: ${result.proposalPath}`));
    if (result.validEditCount > 0) {
      const reviewNow = await confirm({
        message: 'Review and apply edits now?',
        default: true,
      });
      if (reviewNow) {
        await reviewAndApply({
          proposalPath: result.proposalPath,
          plan2codeRoot,
          proposalsDir,
        });
      }
    }
  } catch (err) {
    console.error(chalk.red(`Proposal generation failed: ${err instanceof Error ? err.message : String(err)}`));
  }
 }
 // ── Flow: Review and apply proposal ──────────────────────────────────────────
 async function flowReviewAndApply(): Promise<void> {
  console.log();
  console.log(chalk.bold.cyan('── Review and Apply a Proposal ──'));
  const { proposalsDir } = getMetricsDirs();
  const plan2codeRoot = detectPlan2CodeRoot() ?? process.cwd();
  if (!fs.existsSync(proposalsDir)) {
    console.log(chalk.yellow('No proposals directory found. Generate a proposal first.'));
    return;
  }
  const proposalFiles = fs.readdirSync(proposalsDir)
    .filter(f => /^prop-\d+\.json$/.test(f))
    .sort()
    .reverse(); // most recent first
  if (proposalFiles.length === 0) {
    console.log(chalk.yellow('No proposal files found. Generate a proposal first.'));
    return;
  }
  const chosen = await select({
    message: 'Select proposal to review:',
    choices: proposalFiles.map(f => {
      try {
        const p = JSON.parse(fs.readFileSync(path.join(proposalsDir, f), 'utf8'));
        const label = `${f}  [${p.status}]  ${p.proposals?.length ?? 0} edits`;
        return { name: label, value: path.join(proposalsDir, f) };
      } catch {
        return { name: f, value: path.join(proposalsDir, f) };
      }
    }),
  });
  await reviewAndApply({
    proposalPath: chosen,
    plan2codeRoot,
    proposalsDir,
  });
 }
 // ── Main menu ─────────────────────────────────────────────────────────────────
 export async function runCLI(): Promise<void> {
  console.log();
  console.log(chalk.bold.white('plan2code-metrics'));
  console.log(chalk.gray('Recursive self-improvement toolchain for plan2code contributors'));
  console.log();
  // Check if we're in (or near) a plan2code repo
  const plan2codeRoot = detectPlan2CodeRoot();
  if (!plan2codeRoot) {
    console.log(chalk.yellow('⚠ Could not detect plan2code repository (src/plan2code-*.md not found nearby).'));
    console.log(chalk.gray('  Prompt version hashing and analysis will be limited.'));
    console.log();
  } else {
    const version = detectPlan2CodeVersion(plan2codeRoot);
    console.log(chalk.gray(`plan2code root: ${plan2codeRoot}  (v${version})`));
    console.log();
  }
  let continueLoop = true;
  while (continueLoop) {
    const action = await select({
      message: 'What would you like to do?',
      choices: [
        { name: 'Collect metrics for a completed project', value: 'collect' },
        { name: 'Import run data from another project', value: 'import' },
        { name: 'View metrics status and history', value: 'view' },
        { name: 'Run analysis (diagnose weak steps)', value: 'analyze' },
        { name: 'Generate improvement proposal', value: 'propose' },
        { name: 'Review and apply a proposal', value: 'apply' },
        { name: 'Exit', value: 'exit' },
      ],
    });
    switch (action) {
      case 'collect':
        await flowCollect();
        break;
      case 'import':
        await flowImport();
        break;
      case 'view':
        await flowViewStatus();
        break;
      case 'analyze':
        await flowRunAnalysis();
        break;
      case 'propose':
        await flowGenerateProposal();
        break;
      case 'apply':
        await flowReviewAndApply();
        break;
      case 'exit':
        continueLoop = false;
        break;
    }
    if (continueLoop && action !== 'exit') {
      console.log();
    }
  }
  console.log(chalk.gray('Goodbye.'));
 }
@@ -0,0 +1,520 @@
 /**
 * collector.ts
 * Reads finished project artifacts and writes a RunMetrics JSON file.
 * Zero dependency on plan2code-loop internals — reads files directly.
 */
 import fs from 'fs';
 import path from 'path';
 import crypto from 'crypto';
 import type {
  RunMetrics,
  PromptVersions,
  Step1PlanMetrics,
  Step2DocumentMetrics,
  Step3ImplementMetrics,
  Step4FinalizeMetrics,
  UserFeedback,
 } from './types.js';
 // ── Helpers ──────────────────────────────────────────────────────────────────
 function sha256File(filePath: string): string {
  try {
    const content = fs.readFileSync(filePath, 'utf8');
    return 'sha256:' + crypto.createHash('sha256').update(content).digest('hex');
  } catch {
    return 'sha256:missing';
  }
 }
 function readFileSafe(filePath: string): string | null {
  try {
    return fs.readFileSync(filePath, 'utf8');
  } catch {
    return null;
  }
 }
 function generateRunId(): string {
  const now = new Date();
  const ts = now.toISOString().replace(/[-:T]/g, '').slice(0, 14);
  const rand = crypto.randomBytes(2).toString('hex');
  return `run-${ts.slice(0, 8)}-${ts.slice(8, 14)}-${rand}`;
 }
 // ── Prompt version hashing ────────────────────────────────────────────────────
 export function collectPromptVersions(plan2codeRoot: string): PromptVersions {
  const srcDir = path.join(plan2codeRoot, 'src');
  return {
    plan:        sha256File(path.join(srcDir, 'plan2code-1--plan.md')),
    revise_plan: sha256File(path.join(srcDir, 'plan2code-1b--revise-plan.md')),
    document:    sha256File(path.join(srcDir, 'plan2code-2--document.md')),
    implement:   sha256File(path.join(srcDir, 'plan2code-3--implement.md')),
    finalize:    sha256File(path.join(srcDir, 'plan2code-4--finalize.md')),
    init:        sha256File(path.join(srcDir, 'plan2code---init.md')),
    init_update: sha256File(path.join(srcDir, 'plan2code---init-update.md')),
    quick_task:  sha256File(path.join(srcDir, 'plan2code---quick-task.md')),
  };
 }
 // ── Step 1: Plan ──────────────────────────────────────────────────────────────
 export function collectStep1(specDir: string): Step1PlanMetrics {
  // Find PLAN-DRAFT-*.md files
  let draftFiles: string[] = [];
  let convFiles: string[] = [];
  try {
    const files = fs.readdirSync(specDir);
    draftFiles = files
      .filter(f => f.startsWith('PLAN-DRAFT-') && f.endsWith('.md'))
      .map(f => path.join(specDir, f));
    convFiles = files
      .filter(f => f.startsWith('PLAN-CONVERSATION-') && f.endsWith('.md'))
      .map(f => path.join(specDir, f));
  } catch {
    return { present: false, final_confidence: null, confidence_breakdown: null,
      clarification_rounds: null, tech_stack_revision_rounds: null,
      verification_gaps_found: null, functional_requirements_count: null,
      non_functional_requirements_count: null, risk_count: null, phase_count: null };
  }
  if (draftFiles.length === 0) {
    return { present: false, final_confidence: null, confidence_breakdown: null,
      clarification_rounds: null, tech_stack_revision_rounds: null,
      verification_gaps_found: null, functional_requirements_count: null,
      non_functional_requirements_count: null, risk_count: null, phase_count: null };
  }
  // Use the latest draft file
  draftFiles.sort();
  const latestDraft = readFileSafe(draftFiles[draftFiles.length - 1]) ?? '';
  // Parse "Confidence: XX%" — look for overall or total confidence
  let finalConfidence: number | null = null;
  const confMatch = latestDraft.match(/(?:Overall|Final|Total)?\s*[Cc]onfidence[:\s]+(\d{1,3})%/);
  if (confMatch) {
    finalConfidence = parseInt(confMatch[1], 10);
  } else {
    // Try table format: | Confidence | 92 |
    const tableMatch = latestDraft.match(/[|]\s*[Cc]onfidence\s*[|]\s*(\d{1,3})/);
    if (tableMatch) finalConfidence = parseInt(tableMatch[1], 10);
  }
  // Confidence breakdown (requirements, feasibility, integration, risk)
  let confidenceBreakdown: Step1PlanMetrics['confidence_breakdown'] = null;
  const reqMatch = latestDraft.match(/[Rr]equirements?[:\s|]+(\d{1,2})/);
  const feasMatch = latestDraft.match(/[Ff]easibility[:\s|]+(\d{1,2})/);
  const intMatch = latestDraft.match(/[Ii]ntegration[:\s|]+(\d{1,2})/);
  const riskMatch = latestDraft.match(/[Rr]isk[:\s|]+(\d{1,2})/);
  if (reqMatch || feasMatch || intMatch || riskMatch) {
    confidenceBreakdown = {
      requirements: reqMatch ? parseInt(reqMatch[1], 10) : null,
      feasibility:  feasMatch ? parseInt(feasMatch[1], 10) : null,
      integration:  intMatch ? parseInt(intMatch[1], 10) : null,
      risk:         riskMatch ? parseInt(riskMatch[1], 10) : null,
    };
  }
  // Count ### FR- / ### NFR- headings
  const frCount = (latestDraft.match(/###\s+FR-/g) ?? []).length;
  const nfrCount = (latestDraft.match(/###\s+NFR-/g) ?? []).length;
  // Count risk table rows (lines starting with | that contain risk-level keywords)
  const riskRows = latestDraft.match(/^\s*[|][^|]*(?:High|Medium|Low|Critical)[^|]*[|]/gm) ?? [];
  const riskCount = riskRows.length || null;
  // Count ## Phase headings
  const phaseCount = (latestDraft.match(/^##\s+Phase\s+\d/gm) ?? []).length || null;
  // Clarification rounds from conversation file
  let clarificationRounds: number | null = null;
  let techStackRevisions: number | null = null;
  let verificationGaps: number | null = null;
  if (convFiles.length > 0) {
    convFiles.sort();
    const latestConv = readFileSafe(convFiles[convFiles.length - 1]) ?? '';
    // Count heading repetitions as clarification rounds (## Clarification or ## Round)
    const clarRounds = (latestConv.match(/^##\s+(?:Clarification|Round)\s+\d/gm) ?? []).length;
    clarificationRounds = clarRounds || null;
    // Tech stack revision rounds
    const techRounds = (latestConv.match(/^##\s+(?:Tech\s+Stack|Technology)\s+Revision/gmi) ?? []).length;
    techStackRevisions = techRounds || null;
    // Verification gaps found
    const gapMatches = latestConv.match(/(?:verification\s+gap|gap\s+found|missing\s+requirement)/gi) ?? [];
    verificationGaps = gapMatches.length || null;
  }
  return {
    present: true,
    final_confidence: finalConfidence,
    confidence_breakdown: confidenceBreakdown,
    clarification_rounds: clarificationRounds,
    tech_stack_revision_rounds: techStackRevisions,
    verification_gaps_found: verificationGaps,
    functional_requirements_count: frCount || null,
    non_functional_requirements_count: nfrCount || null,
    risk_count: riskCount,
    phase_count: phaseCount,
  };
 }
 // ── Step 2: Document ──────────────────────────────────────────────────────────
 export function collectStep2(specDir: string): Step2DocumentMetrics {
  const overviewPath = path.join(specDir, 'overview.md');
  const overview = readFileSafe(overviewPath);
  if (!overview) {
    return { present: false, total_tasks: null, tasks_per_phase: null,
      phase_count: null, parallel_groups_identified: null,
      requirement_coverage_percent: null, verification_items_added: null };
  }
  // Count all checkbox tasks: - [ ], - [x], - [!], - [/]
  const allTasks = (overview.match(/^\s*-\s+\[[ x!/?]\]/gm) ?? []).length;
  // Detect Parallel Execution Groups table
  const parallelGroups = (overview.match(/Parallel\s+Execution\s+Group/gi) ?? []).length;
  // Count phase files
  let phaseCount = 0;
  let tasksPerPhase: number[] = [];
  try {
    const files = fs.readdirSync(specDir);
    const phaseFiles = files
      .filter(f => /^phase-\d+\.md$/i.test(f))
      .sort();
    phaseCount = phaseFiles.length;
    for (const pf of phaseFiles) {
      const content = readFileSafe(path.join(specDir, pf)) ?? '';
      const count = (content.match(/^\s*-\s+\[[ x!/?]\]/gm) ?? []).length;
      tasksPerPhase.push(count);
    }
  } catch {
    // leave empty
  }
  // Requirement coverage: look for coverage percentage in overview
  let reqCoverage: number | null = null;
  const covMatch = overview.match(/[Cc]overage[:\s]+(\d{1,3})%/);
  if (covMatch) reqCoverage = parseInt(covMatch[1], 10);
  // Verification items added (look for verification checklist items)
  const verifItems = (overview.match(/(?:verify|verification|test|check):\s*\[[ x]\]/gi) ?? []).length;
  return {
    present: true,
    total_tasks: allTasks || null,
    tasks_per_phase: tasksPerPhase.length > 0 ? tasksPerPhase : null,
    phase_count: phaseCount || null,
    parallel_groups_identified: parallelGroups || 0,
    requirement_coverage_percent: reqCoverage,
    verification_items_added: verifItems || null,
  };
 }
 // ── Step 3: Implement (loop data) ─────────────────────────────────────────────
 export function collectStep3(specDir: string): Step3ImplementMetrics {
  const loopDir = path.join(specDir, '.plan2code-loop');
  const iterLogPath = path.join(loopDir, 'iteration.log');
  const configPath = path.join(loopDir, 'config.json');
  if (!fs.existsSync(loopDir)) {
    return { present: true, used_loop_mode: false, loop_mode: null,
      task_completion_rate: null, tasks_completed: null, tasks_total: null,
      blocker_count: null, blocker_categories: null, total_iterations: null,
      avg_iteration_duration_ms: null, exit_code_distribution: null,
      completion_marker_success_rate: null };
  }
  // Parse config.json for loop mode
  let loopMode: 'task' | 'phase' | null = null;
  const configContent = readFileSafe(configPath);
  if (configContent) {
    try {
      const config = JSON.parse(configContent);
      loopMode = config.loopMode ?? null;
    } catch {
      // ignore
    }
  }
  // Parse NDJSON iteration.log
  const iterLogContent = readFileSafe(iterLogPath);
  if (!iterLogContent) {
    return { present: true, used_loop_mode: true, loop_mode: loopMode,
      task_completion_rate: null, tasks_completed: null, tasks_total: null,
      blocker_count: null, blocker_categories: null, total_iterations: null,
      avg_iteration_duration_ms: null, exit_code_distribution: null,
      completion_marker_success_rate: null };
  }
  interface IterEntry {
    iteration: number;
    timestamp: string;
    duration: number;
    exitCode: number;
    status: string;
    completionMarker?: string;
  }
  const entries: IterEntry[] = [];
  for (const line of iterLogContent.split('\n')) {
    const trimmed = line.trim();
    if (!trimmed) continue;
    try {
      entries.push(JSON.parse(trimmed));
    } catch {
      // skip malformed lines
    }
  }
  const totalIterations = entries.length;
  if (totalIterations === 0) {
    return { present: true, used_loop_mode: true, loop_mode: loopMode,
      task_completion_rate: null, tasks_completed: null, tasks_total: null,
      blocker_count: null, blocker_categories: null, total_iterations: 0,
      avg_iteration_duration_ms: null, exit_code_distribution: null,
      completion_marker_success_rate: null };
  }
  // Exit code distribution
  const exitCodes: Record<string, number> = {};
  for (const e of entries) {
    const key = String(e.exitCode ?? 'other');
    exitCodes[key] = (exitCodes[key] ?? 0) + 1;
  }
  // Average duration
  const durations = entries.map(e => e.duration).filter(d => d != null && d > 0);
  const avgDuration = durations.length > 0
    ? Math.round(durations.reduce((a, b) => a + b, 0) / durations.length)
    : null;
  // Completion markers
  const markerEntries = entries.filter(e => e.completionMarker && e.completionMarker.trim() !== '');
  const taskCompleteEntries = markerEntries.filter(e =>
    e.completionMarker?.startsWith('TASK_COMPLETE')
  );
  const blockedEntries = markerEntries.filter(e =>
    e.completionMarker?.startsWith('TASK_BLOCKED')
  );
  // Completion marker success rate: entries where a valid marker was detected vs total
  const validMarkerCount = markerEntries.length;
  const markerSuccessRate = totalIterations > 0
    ? validMarkerCount / totalIterations
    : null;
  // Task counts from markers (used for completion_marker_success_rate)
  const blockerCount = blockedEntries.length;
  // Blocker categories (parse from "TASK_BLOCKED: X.Y - reason")
  const blockerCategories: string[] = [];
  for (const e of blockedEntries) {
    const match = e.completionMarker?.match(/TASK_BLOCKED:\s*[\d.]+\s*-\s*(.+)/);
    if (match) {
      // Normalize to snake_case category
      const reason = match[1].toLowerCase().replace(/\s+/g, '_').replace(/[^a-z0-9_]/g, '');
      if (!blockerCategories.includes(reason)) {
        blockerCategories.push(reason);
      }
    }
  }
  // Count tasks from overview.md checkboxes (consistent numerator and denominator)
  const overviewPath = path.join(specDir, 'overview.md');
  const overview = readFileSafe(overviewPath);
  let tasksTotal: number | null = null;
  let tasksCompleted: number | null = null;
  if (overview) {
    tasksTotal = (overview.match(/^\s*-\s+\[[ x!/?]\]/gm) ?? []).length || null;
    tasksCompleted = (overview.match(/^\s*-\s+\[x\]/gm) ?? []).length || null;
  }
  const taskCompletionRate = tasksTotal && tasksTotal > 0 && tasksCompleted != null
    ? tasksCompleted / tasksTotal
    : null;
  return {
    present: true,
    used_loop_mode: true,
    loop_mode: loopMode,
    task_completion_rate: taskCompletionRate,
    tasks_completed: tasksCompleted || null,
    tasks_total: tasksTotal,
    blocker_count: blockerCount,
    blocker_categories: blockerCategories.length > 0 ? blockerCategories : null,
    total_iterations: totalIterations,
    avg_iteration_duration_ms: avgDuration,
    exit_code_distribution: exitCodes,
    completion_marker_success_rate: markerSuccessRate,
  };
 }
 // ── Step 4: Finalize ──────────────────────────────────────────────────────────
 export function collectStep4(specDir: string): Step4FinalizeMetrics {
  // Check if spec was archived (specs--completed exists at parent level)
  const specDirName = path.basename(specDir);
  const parentDir = path.dirname(specDir);
  const completedPath = path.join(parentDir, '..', 'specs--completed', specDirName);
  const archivalSucceeded = fs.existsSync(completedPath);
  // Read overview for completion metrics
  const overviewPath = path.join(specDir, 'overview.md');
  // If archived, try from archived location
  const effectiveOverviewPath = archivalSucceeded
    ? path.join(completedPath, 'overview.md')
    : overviewPath;
  const overview = readFileSafe(effectiveOverviewPath) ?? readFileSafe(overviewPath);
  if (!overview) {
    return { present: false, completion_rate_at_audit: null,
      verification_failures_found: null, documentation_updates_needed: null,
      archival_succeeded: archivalSucceeded };
  }
  // Completion rate: completed tasks / total tasks
  const totalTasks = (overview.match(/^\s*-\s+\[[ x!/?]\]/gm) ?? []).length;
  const completedTasks = (overview.match(/^\s*-\s+\[x\]/gm) ?? []).length;
  const completionRate = totalTasks > 0 ? completedTasks / totalTasks : null;
  // Verification failures: look for [!] tasks or "verification failed" text
  const blockedTasks = (overview.match(/^\s*-\s+\[!\]/gm) ?? []).length;
  // Documentation updates needed (look for TODO or "update" markers)
  const docUpdates = (overview.match(/(?:TODO|FIXME|update\s+(?:README|CHANGELOG|docs))/gi) ?? []).length;
  return {
    present: true,
    completion_rate_at_audit: completionRate,
    verification_failures_found: blockedTasks || 0,
    documentation_updates_needed: docUpdates || null,
    archival_succeeded: archivalSucceeded,
  };
 }
 // ── User Feedback ─────────────────────────────────────────────────────────
 export function collectUserFeedback(specDir: string): UserFeedback | null {
  // Try both active and archived locations for overview.md
  const overviewPath = path.join(specDir, 'overview.md');
  const specDirName = path.basename(specDir);
  const parentDir = path.dirname(specDir);
  const completedPath = path.join(parentDir, '..', 'specs--completed', specDirName, 'overview.md');
  const overview = readFileSafe(overviewPath) ?? readFileSafe(completedPath);
  if (!overview) return null;
  // Look for ## User Feedback section with a markdown table
  const feedbackMatch = overview.match(
    /## User Feedback\s*\n\s*\|[^\n]*\|\s*\n\s*\|[-| ]+\|\s*\n([\s\S]*?)(?=\n##\s|\n*$)/
  );
  if (!feedbackMatch) return null;
  const tableBody = feedbackMatch[1];
  // Parse table rows: | Field | Value |
  // Use regex to split only on unescaped pipes, preserving whitespace in values
  const rows = tableBody.split('\n').filter(l => l.trim().startsWith('|'));
  const fields: Record<string, string> = {};
  for (const row of rows) {
    // Split on unescaped pipes (not preceded by backslash)
    const cells = row.split(/(?<!\\)\|/).map(c => c.trim()).filter(c => c.length > 0);
    if (cells.length >= 2) {
      const value = cells.slice(1).join('|').replace(/\\\|/g, '|');
      fields[cells[0].toLowerCase()] = value;
    }
  }
  const rating = parseInt(fields['rating'] ?? '', 10);
  if (isNaN(rating) || rating < 1 || rating > 10) return null;
  return {
    overall_rating: rating,
    rating_reason: fields['reason'] ?? '',
    what_went_well: fields['went well'] ?? '',
    what_went_poorly: fields['went poorly'] ?? '',
  };
 }
 // ── Main collector ────────────────────────────────────────────────────────────
 export interface CollectorOptions {
  specDir: string;           // Path to the spec directory (specs/<feature-name>)
  projectName: string;       // Human-readable project name
  plan2codeRoot: string;     // Path to the plan2code repo (for prompt hashing)
  plan2codeVersion: string;  // e.g. "1.7.0"
  outputDir: string;         // Where to write <run-id>.json
 }
 export async function collectRun(opts: CollectorOptions): Promise<RunMetrics> {
  const {
    specDir,
    projectName,
    plan2codeRoot,
    plan2codeVersion,
    outputDir,
  } = opts;
  const runId = generateRunId();
  // Get started_at / completed_at from spec directory mtime / iteration.log
  let startedAt: string | null = null;
  let completedAt: string | null = null;
  try {
    const stat = fs.statSync(specDir);
    startedAt = stat.birthtime.toISOString();
    completedAt = stat.mtime.toISOString();
  } catch {
    // leave null
  }
  // Try to get started_at from earliest iteration log entry
  const loopDir = path.join(specDir, '.plan2code-loop');
  const iterLogPath = path.join(loopDir, 'iteration.log');
  const iterLogContent = readFileSafe(iterLogPath);
  if (iterLogContent) {
    const lines = iterLogContent.split('\n').filter(l => l.trim());
    if (lines.length > 0) {
      try {
        const first = JSON.parse(lines[0]);
        if (first.timestamp) startedAt = first.timestamp;
      } catch { /* ignore */ }
      try {
        const last = JSON.parse(lines[lines.length - 1]);
        if (last.timestamp) completedAt = last.timestamp;
      } catch { /* ignore */ }
    }
  }
  const metrics: RunMetrics = {
    schema_version: '1.0',
    run_id: runId,
    plan2code_version: plan2codeVersion,
    prompt_versions: collectPromptVersions(plan2codeRoot),
    project: {
      name: projectName,
      started_at: startedAt,
      completed_at: completedAt,
    },
    step1_plan: collectStep1(specDir),
    step2_document: collectStep2(specDir),
    step3_implement: collectStep3(specDir),
    step4_finalize: collectStep4(specDir),
    user_feedback: collectUserFeedback(specDir),
  };
  // Write to output dir
  fs.mkdirSync(outputDir, { recursive: true });
  const outPath = path.join(outputDir, `${runId}.json`);
  fs.writeFileSync(outPath, JSON.stringify(metrics, null, 2), 'utf8');
  return metrics;
 }
@@ -0,0 +1,139 @@
 import { describe, it, expect } from 'vitest';
 import { validateEdit, parseProposalFromResponse } from './improver.js';
 import type { PromptEdit } from './types.js';
 // ── Shared fixtures ───────────────────────────────────────────────────────────
 const PROMPT_CONTENTS: Record<string, string> = {
  'plan2code-1--plan.md': 'This is the plan prompt content. It has some text here.',
  'plan2code-2--document.md': 'Document prompt with repeated text. repeated text. Done.',
  'plan2code-3--implement.md': 'Implement prompt content.',
 };
 function makeEdit(overrides: Partial<PromptEdit> = {}): PromptEdit {
  return {
    file: 'plan2code-1--plan.md',
    rationale: 'test rationale',
    expected_metric_impact: 'test impact',
    char_count_before: PROMPT_CONTENTS['plan2code-1--plan.md'].length,
    char_count_after: PROMPT_CONTENTS['plan2code-1--plan.md'].length,
    char_count_delta: 0,
    old_text: 'some text',
    new_text: 'better text',
    ...overrides,
  };
 }
 // ── validateEdit() ────────────────────────────────────────────────────────────
 describe('validateEdit', () => {
  it('valid edit passes with no errors', () => {
    const result = validateEdit(makeEdit(), PROMPT_CONTENTS);
    expect(result.valid).toBe(true);
    expect(result.errors).toHaveLength(0);
  });
  it('rejects path traversal (../ in file path)', () => {
    const result = validateEdit(makeEdit({ file: '../etc/passwd' }), PROMPT_CONTENTS);
    expect(result.valid).toBe(false);
    expect(result.errors[0]).toMatch(/path traversal/i);
  });
  it('rejects absolute paths', () => {
    const result = validateEdit(makeEdit({ file: '/etc/passwd' }), PROMPT_CONTENTS);
    expect(result.valid).toBe(false);
    expect(result.errors[0]).toMatch(/path traversal|absolute/i);
  });
  it('errors when file not found in promptContents', () => {
    const result = validateEdit(makeEdit({ file: 'nonexistent.md' }), PROMPT_CONTENTS);
    expect(result.valid).toBe(false);
    expect(result.errors[0]).toMatch(/not found/i);
  });
  it('errors when old_text not found in file content', () => {
    const result = validateEdit(makeEdit({ old_text: 'hallucinated text' }), PROMPT_CONTENTS);
    expect(result.valid).toBe(false);
    expect(result.errors[0]).toMatch(/not found verbatim/i);
  });
  it('warns when old_text appears multiple times', () => {
    const edit = makeEdit({
      file: 'plan2code-2--document.md',
      old_text: 'repeated text',
      char_count_before: PROMPT_CONTENTS['plan2code-2--document.md'].length,
      char_count_after: PROMPT_CONTENTS['plan2code-2--document.md'].length,
    });
    const result = validateEdit(edit, PROMPT_CONTENTS);
    expect(result.valid).toBe(true);
    expect(result.warnings.some(w => /appears.*times/i.test(w))).toBe(true);
  });
  it('errors when edit would exceed 11,000 char limit', () => {
    const bigText = 'x'.repeat(12_000);
    const edit = makeEdit({ new_text: bigText });
    const result = validateEdit(edit, PROMPT_CONTENTS);
    expect(result.valid).toBe(false);
    expect(result.errors.some(e => /exceed.*11.?000/i.test(e))).toBe(true);
  });
  it('warns when reported char counts diverge from actual (>10 chars off)', () => {
    const edit = makeEdit({
      char_count_before: 999,
      char_count_after: 999,
    });
    const result = validateEdit(edit, PROMPT_CONTENTS);
    expect(result.valid).toBe(true);
    expect(result.warnings.some(w => /char_count_before.*differs/i.test(w))).toBe(true);
  });
 });
 // ── parseProposalFromResponse() ───────────────────────────────────────────────
 describe('parseProposalFromResponse', () => {
  const sampleEdit = {
    file: 'test.md',
    rationale: 'r',
    expected_metric_impact: 'e',
    char_count_before: 100,
    char_count_after: 110,
    char_count_delta: 10,
    old_text: 'old',
    new_text: 'new',
  };
  it('parses JSON from markdown code block (```json ... ```)', () => {
    const response = `Here is my proposal:\n\n\`\`\`json\n${JSON.stringify([sampleEdit])}\n\`\`\`\n\nDone.`;
    const result = parseProposalFromResponse(response);
    expect(result).toHaveLength(1);
    expect(result![0].file).toBe('test.md');
  });
  it('parses JSON from bare code block (``` ... ```)', () => {
    const response = `Proposal:\n\n\`\`\`\n${JSON.stringify([sampleEdit])}\n\`\`\``;
    const result = parseProposalFromResponse(response);
    expect(result).toHaveLength(1);
    expect(result![0].old_text).toBe('old');
  });
  it('parses bare JSON array with old_text field', () => {
    const response = `Some preamble\n${JSON.stringify([sampleEdit])}\nSome postamble`;
    const result = parseProposalFromResponse(response);
    expect(result).toHaveLength(1);
  });
  it('returns null for non-JSON response', () => {
    const result = parseProposalFromResponse('No changes needed at this time.');
    expect(result).toBeNull();
  });
  it('returns null for malformed JSON', () => {
    const result = parseProposalFromResponse('```json\n{broken json]\n```');
    expect(result).toBeNull();
  });
  it('returns null for empty response', () => {
    const result = parseProposalFromResponse('');
    expect(result).toBeNull();
  });
 });
@@ -0,0 +1,288 @@
 /**
 * improver.ts
 * Reads diagnosis + prompt files, invokes AI, parses PromptEdit[] from response.
 * Validates: old_text verbatim match, char count limits.
 */
 import fs from 'fs';
 import path from 'path';
 import type { PromptEdit, PromptProposal } from './types.js';
 import { invokeLLM, type AgentType } from './invoke-llm.js';
 const CHAR_LIMIT = 11_000;
 const IMPROVE_PROMPT_PATH = new URL('../src/prompts/improve.md', import.meta.url).pathname
  .replace(/^\/([A-Za-z]:)/, '$1'); // Fix Windows path
 // ── Helpers ───────────────────────────────────────────────────────────────────
 function interpolate(template: string, vars: Record<string, string>): string {
  let result = template;
  for (const [key, value] of Object.entries(vars)) {
    result = result.replaceAll(`{{${key}}}`, value);
  }
  return result;
 }
 function generateProposalId(): string {
  const now = new Date();
  const ts = now.toISOString().replace(/[-:T.Z]/g, '').slice(0, 14);
  return `prop-${ts}`;
 }
 function readPromptFiles(plan2codeRoot: string): Record<string, string> {
  const srcDir = path.join(plan2codeRoot, 'src');
  const promptFiles = [
    'plan2code-1--plan.md',
    'plan2code-1b--revise-plan.md',
    'plan2code-2--document.md',
    'plan2code-3--implement.md',
    'plan2code-4--finalize.md',
    'plan2code---init.md',
    'plan2code---init-update.md',
    'plan2code---quick-task.md',
  ];
  const contents: Record<string, string> = {};
  for (const file of promptFiles) {
    try {
      contents[file] = fs.readFileSync(path.join(srcDir, file), 'utf8');
    } catch {
      contents[file] = '';
    }
  }
  return contents;
 }
 // ── Edit validation ───────────────────────────────────────────────────────────
 export interface ValidationResult {
  valid: boolean;
  errors: string[];
  warnings: string[];
 }
 export function validateEdit(
  edit: PromptEdit,
  promptContents: Record<string, string>,
 ): ValidationResult {
  const errors: string[] = [];
  const warnings: string[] = [];
  // Reject path traversal attempts
  if (edit.file.includes('..') || path.isAbsolute(edit.file)) {
    errors.push(`Rejected: "${edit.file}" contains path traversal or absolute path.`);
    return { valid: false, errors, warnings };
  }
  // Check target file exists
  const fileContent = promptContents[edit.file];
  if (fileContent === undefined) {
    errors.push(`Target file "${edit.file}" not found. Valid files: ${Object.keys(promptContents).join(', ')}`);
    return { valid: false, errors, warnings };
  }
  // Check old_text exists verbatim in the file
  if (!fileContent.includes(edit.old_text)) {
    errors.push(`old_text not found verbatim in "${edit.file}". The AI may have hallucinated text.`);
  } else {
    // Warn if old_text appears more than once (ambiguous match)
    const occurrences = fileContent.split(edit.old_text).length - 1;
    if (occurrences > 1) {
      warnings.push(`old_text appears ${occurrences} times in "${edit.file}". Only the first occurrence will be replaced.`);
    }
  }
  // Check char count after edit
  const afterContent = fileContent.replace(edit.old_text, edit.new_text);
  if (afterContent.length > CHAR_LIMIT) {
    errors.push(`Edit would cause "${edit.file}" to exceed ${CHAR_LIMIT} char limit (would be ${afterContent.length} chars).`);
  }
  // Verify reported char counts match reality
  const actualBefore = fileContent.length;
  const actualAfter = afterContent.length;
  if (Math.abs(edit.char_count_before - actualBefore) > 10) {
    warnings.push(`Reported char_count_before (${edit.char_count_before}) differs from actual (${actualBefore}).`);
  }
  if (Math.abs(edit.char_count_after - actualAfter) > 10) {
    warnings.push(`Reported char_count_after (${edit.char_count_after}) differs from actual (${actualAfter}).`);
  }
  return { valid: errors.length === 0, errors, warnings };
 }
 // ── AI response parsing ───────────────────────────────────────────────────────
 export function parseProposalFromResponse(response: string): PromptEdit[] | null {
  // Look for JSON code block containing PromptEdit[]
  const jsonBlockMatch = response.match(/```(?:json)?\s*(\[[\s\S]*?\])\s*```/);
  if (!jsonBlockMatch) {
    // Try bare JSON array
    const bareMatch = response.match(/(\[[\s\S]*"old_text"[\s\S]*\])/);
    if (!bareMatch) return null;
    try {
      return JSON.parse(bareMatch[1]) as PromptEdit[];
    } catch {
      return null;
    }
  }
  try {
    return JSON.parse(jsonBlockMatch[1]) as PromptEdit[];
  } catch {
    return null;
  }
 }
 // ── Main improver ─────────────────────────────────────────────────────────────
 export interface ImproverOptions {
  diagnosisPath: string;     // Path to diagnosis markdown file
  plan2codeRoot: string;     // Path to plan2code repo root
  proposalsDir: string;      // Where to save proposal JSON
  runsDir: string;           // For tracking which runs this is based on
  model?: string;
  agent?: AgentType;         // Agent to use (default: claude-code)
 }
 export interface ImproverResult {
  proposalPath: string;
  proposal: PromptProposal;
  validationResults: Array<{ edit: PromptEdit; result: ValidationResult }>;
  validEditCount: number;
  invalidEditCount: number;
 }
 export async function generateImprovement(opts: ImproverOptions): Promise<ImproverResult> {
  const { diagnosisPath, plan2codeRoot, proposalsDir, runsDir, model = 'claude-opus-4-6', agent = 'claude-code' } = opts;
  // Load diagnosis
  let diagnosisContent: string;
  try {
    diagnosisContent = fs.readFileSync(diagnosisPath, 'utf8');
  } catch {
    throw new Error(`Could not read diagnosis file at ${diagnosisPath}`);
  }
  // Read prompt files
  const promptContents = readPromptFiles(plan2codeRoot);
  const srcDir = path.join(plan2codeRoot, 'src');
  // Build char counts for each file
  const charCounts = Object.entries(promptContents)
    .map(([file, content]) => `| ${file} | ${content.length} | ${CHAR_LIMIT} | ${CHAR_LIMIT - content.length} headroom |`)
    .join('\n');
  const promptContentsStr = Object.entries(promptContents)
    .map(([file, content]) => `## ${file} (${content.length} chars)\n\n${content}`)
    .join('\n\n---\n\n');
  // Load improve prompt template
  let improveTemplate: string;
  try {
    improveTemplate = fs.readFileSync(IMPROVE_PROMPT_PATH, 'utf8');
  } catch {
    const altPath = path.join(process.cwd(), 'src', 'prompts', 'improve.md');
    improveTemplate = fs.readFileSync(altPath, 'utf8');
  }
  const fullPrompt = interpolate(improveTemplate, {
    diagnosisContent,
    promptContents: promptContentsStr,
    charCounts: `| File | Current Chars | Limit | Headroom |\n|------|--------------|-------|----------|\n${charCounts}`,
  });
  // Invoke Claude
  console.log(`\nInvoking AI improvement proposal (model: ${model})...`);
  console.log('This may take a minute...\n');
  let aiResponse: string;
  try {
    aiResponse = await invokeLLM({
      prompt: fullPrompt,
      model,
      agent,
      timeout: 300_000,
    });
  } catch (err) {
    throw new Error(`AI invocation failed: ${err instanceof Error ? err.message : String(err)}`);
  }
  // Parse edits
  const rawEdits = parseProposalFromResponse(aiResponse);
  if (!rawEdits || rawEdits.length === 0) {
    throw new Error('Could not parse PromptEdit[] from AI response. The AI may not have produced a valid JSON block.');
  }
  // Enforce max edits per cycle
  const MAX_EDITS = 5;
  if (rawEdits.length > MAX_EDITS) {
    console.warn(`\n⚠ AI generated ${rawEdits.length} edits (max is ${MAX_EDITS}). Truncating to first ${MAX_EDITS}.`);
    rawEdits.length = MAX_EDITS;
  }
  // Validate each edit
  const validationResults: ImproverResult['validationResults'] = [];
  const validEdits: PromptEdit[] = [];
  for (const edit of rawEdits) {
    const result = validateEdit(edit, promptContents);
    validationResults.push({ edit, result });
    if (result.valid) {
      // Compute accurate char counts
      const fileContent = promptContents[edit.file] ?? '';
      const afterContent = fileContent.replace(edit.old_text, edit.new_text);
      edit.char_count_before = fileContent.length;
      edit.char_count_after = afterContent.length;
      edit.char_count_delta = afterContent.length - fileContent.length;
      validEdits.push(edit);
    } else {
      console.warn(`\n⚠ Edit rejected for "${edit.file}":`);
      for (const err of result.errors) {
        console.warn(`  - ${err}`);
      }
    }
    for (const warn of result.warnings) {
      console.warn(`  Warning: ${warn}`);
    }
  }
  // Get run IDs that contributed to this analysis
  const runIds: string[] = [];
  try {
    const files = fs.readdirSync(runsDir)
      .filter(f => f.startsWith('run-') && f.endsWith('.json'));
    runIds.push(...files.map(f => f.replace('.json', '')));
  } catch { /* no runs dir */ }
  // Build proposal
  const proposalId = generateProposalId();
  const proposal: PromptProposal = {
    proposal_id: proposalId,
    created_at: new Date().toISOString(),
    based_on_runs: runIds,
    analyst_model: model,
    proposals: validEdits,
    status: 'pending',
    diagnosis_file: path.basename(diagnosisPath),
  };
  // Save proposal JSON
  fs.mkdirSync(proposalsDir, { recursive: true });
  const proposalPath = path.join(proposalsDir, `${proposalId}.json`);
  fs.writeFileSync(proposalPath, JSON.stringify(proposal, null, 2), 'utf8');
  // Also save raw AI response alongside
  const rawPath = path.join(proposalsDir, `${proposalId}-raw.md`);
  fs.writeFileSync(rawPath, aiResponse, 'utf8');
  return {
    proposalPath,
    proposal,
    validationResults,
    validEditCount: validEdits.length,
    invalidEditCount: rawEdits.length - validEdits.length,
  };
 }
@@ -0,0 +1,19 @@
 // Public API for plan2code-metrics
 export { collectRun, collectPromptVersions } from './collector.js';
 export { aggregate, loadAggregated, loadRunFiles, importRun } from './aggregator.js';
 export { runAnalysis } from './analyzer.js';
 export { generateImprovement, validateEdit, parseProposalFromResponse } from './improver.js';
 export { reviewAndApply } from './applier.js';
 export { invokeLLM, AGENTS } from './invoke-llm.js';
 export type { AgentType, InvokeLLMOptions } from './invoke-llm.js';
 export { runCLI } from './cli.js';
 export { METRIC_TARGETS } from './types.js';
 export type {
  RunMetrics,
  UserFeedback,
  PromptVersions,
  PromptEdit,
  PromptProposal,
  AggregatedMetrics,
  CohortMetrics,
 } from './types.js';
@@ -0,0 +1,98 @@
 /**
 * invoke-llm.ts
 * Unified LLM invocation for plan2code-metrics.
 * Supports Claude Code (temp file → stdin) and Copilot CLI (stdin string).
 * Mirrors the agent pattern from plan2code-loop.
 */
 import { execa } from 'execa';
 import { writeFileSync, unlinkSync } from 'fs';
 import { join } from 'path';
 import { tmpdir } from 'os';
 // ── Agent definitions ────────────────────────────────────────────────────────
 export type AgentType = 'claude-code' | 'copilot-cli';
 export interface AgentDef {
  name: AgentType;
  displayName: string;
  command: string;
  models: Array<{ value: string; label: string }>;
 }
 export const AGENTS: Record<AgentType, AgentDef> = {
  'claude-code': {
    name: 'claude-code',
    displayName: 'Claude Code',
    command: 'claude',
    models: [
      { value: 'claude-opus-4-6', label: 'Claude Opus 4.6 (Recommended)' },
      { value: 'claude-sonnet-4-6', label: 'Claude Sonnet 4.6 (faster)' },
    ],
  },
  'copilot-cli': {
    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' },
    ],
  },
 };
 // ── Invocation ───────────────────────────────────────────────────────────────
 export interface InvokeLLMOptions {
  prompt: string;
  model: string;
  agent: AgentType;
  timeout?: number;
 }
 export async function invokeLLM(opts: InvokeLLMOptions): Promise<string> {
  const { prompt, model, agent, timeout = 300_000 } = opts;
  const def = AGENTS[agent];
  if (agent === 'claude-code') {
    // Write prompt to temp file — more reliable than stdin on Windows
    const tempFile = join(tmpdir(), `plan2code-metrics-prompt-${Date.now()}.txt`);
    writeFileSync(tempFile, prompt, 'utf-8');
    try {
      const args: string[] = [
        '--print',
        '--dangerously-skip-permissions',
      ];
      if (model) {
        args.push('--model', model);
      }
      const result = await execa(def.command, args, {
        inputFile: tempFile,
        timeout,
      });
      return result.stdout;
    } finally {
      try { unlinkSync(tempFile); } catch { /* ignore cleanup errors */ }
    }
  } else {
    // Copilot CLI: pipe prompt via stdin string
    const args: string[] = [];
    if (model) {
      args.push('--model', model);
    }
    args.push('--allow-all-tools', '-s');
    const result = await execa(def.command, args, {
      input: prompt,
      timeout,
    });
    return result.stdout;
  }
 }
@@ -0,0 +1,101 @@
 # PLAN2CODE METRICS ANALYSIS REQUEST
 You are a senior AI systems analyst specializing in prompt engineering quality assessment. Your role is to diagnose weaknesses in the plan2code workflow prompts by examining aggregated run metrics.
 **IMPORTANT:** Do NOT propose specific edits in this response. Diagnosis only. The improvement step is separate.
 ---
 ## Aggregated Run Metrics
 The following JSON contains metrics aggregated from real plan2code project runs, grouped by prompt "generation" (a cohort is identified by the SHA fingerprint of the src/plan2code-*.md prompt files at collection time):
 ```json
 {{aggregatedMetrics}}
 ```
 ---
 ## Current Prompt File Contents
 The following are the current contents of the plan2code workflow prompt files being evaluated:
 {{promptContents}}
 ---
 ## Metric Targets Reference
 | Metric | Target | Direction |
 |--------|--------|-----------|
 | avg_confidence (Step 1) | ≥ 90 | higher is better |
 | avg_clarification_rounds (Step 1) | ≤ 2.0 | lower is better |
 | avg_verification_gaps_found (Step 1) | ≤ 2.0 | lower is better |
 | avg_parallel_groups (Step 2) | ≥ 0.5 | higher is better |
 | avg_verification_items_added (Step 2) | ≤ 1.5 | lower is better |
 | avg_task_completion_rate (Step 3) | ≥ 0.95 | higher is better |
 | avg_blocker_count (Step 3) | ≤ 1.5 | lower is better |
 | avg_completion_marker_success_rate (Step 3) | ≥ 0.95 | higher is better |
 | avg_verification_failures_found (Step 4) | ≤ 1.0 | lower is better |
 | archival_success_rate (Step 4) | ≥ 0.99 | higher is better |
 | avg_user_rating (Feedback) | ≥ 7.0 | higher is better (1-10 scale, null if no feedback) |
 ---
 ## Analysis Instructions
 1. Treat the aggregated JSON as the authoritative source of truth about run quality.
 2. Compare each metric against its target. Calculate delta (actual − target).
 3. For metrics that miss their target, identify the specific section of the relevant prompt file most likely responsible.
 4. Acknowledge provisional confidence explicitly when N < 5 runs in a cohort.
 5. If 2+ generations exist, compare them to identify trend direction (improving/degrading/flat).
 6. Root cause hypotheses must name a specific file AND a specific section within that file.
 7. Do not invent metrics not present in the JSON. If a metric is null, note it as "insufficient data."
 ---
 ## Required Output Format
 Produce EXACTLY the following sections in order. Use these exact headers — they are parsed by machine:
 # PLAN2CODE METRICS DIAGNOSIS
 ### Metrics Summary
 A markdown table with columns: Step | Metric | Target | Actual | Delta | Status (✓/✗/—)
 Include ALL metrics listed in the targets table. Use "—" for null values.
 ### Step Health Assessment
 For each step (1–4), provide:
 - **Grade:** A–F
 - **Key signals:** 2–4 bullet points with specific metric values
 - **Assessment:** 1–2 sentence diagnosis
 ### Root Cause Hypotheses
 Numbered list. For each underperforming metric:
 1. **Metric:** [metric name] | **Value:** [actual] | **Target:** [target]
   - **File:** [plan2code-X--name.md]
   - **Section:** [specific heading or section name]
   - **Hypothesis:** [specific gap in the prompt that would explain the metric miss]
   - **Confidence:** [High/Medium/Low] — [reason for confidence level]
 ### Recommended Improvement Targets
 Ordered list (highest estimated impact first). For each:
 - **File:** [filename]
 - **Section:** [section name]
 - **Why:** [link to specific metric being addressed]
 - **Priority:** [High/Medium/Low]
 ### Generation Comparison
 If 2+ generations exist: A comparison table showing before/after for each metric per generation, with trend arrows (▲/▼/→).
 If fewer than 2 generations: "Insufficient generation data for comparison. Current generation: [cohort_key], [N] runs."
 ---
 End of analysis request.
@@ -0,0 +1,93 @@
 # PLAN2CODE PROMPT IMPROVEMENT REQUEST
 You are a senior AI prompt engineer. Your role is to propose surgical, targeted edits to the plan2code workflow prompt files based on a metrics diagnosis. You make precise, minimal changes — NOT rewrites.
 ---
 ## Metrics Diagnosis
 The following diagnosis was produced by the analysis step:
 {{diagnosisContent}}
 ---
 ## Current Prompt File Contents (with char counts)
 {{promptContents}}
 ---
 ## Character Count Status
 {{charCounts}}
 ---
 ## Hard Constraints — ALL must be satisfied:
 1. **Char limit:** Each target file MUST stay under 11,000 characters after your edit is applied. This is enforced by code — edits that violate it will be automatically rejected.
 2. **Maximum 5 edits per cycle.** Focus on the highest-impact changes only.
 3. **Each edit must cite a specific metric** in its `expected_metric_impact` field (e.g., "avg_completion_marker_success_rate", "avg_blocker_count").
 4. **`old_text` must be verbatim** from the file. Copy-paste exactly — include surrounding whitespace/newlines as they appear. Edits with mismatched old_text will be automatically rejected.
 5. **Do NOT modify Role sections** (lines starting with "You are" at the top of each file) or step headings (lines starting with `#`).
 6. **Each edit must be independently applicable** — no edit should depend on another edit being applied first.
 7. **Prefer additive guidance over deletions.** Adding clarifying instructions or examples is safer than removing existing text.
 8. **Do not change the overall structure** or flow of any prompt file.
 ---
 ## Edit Strategy Guidelines
 - Target the specific sections identified in "Recommended Improvement Targets" from the diagnosis.
 - For high `avg_clarification_rounds`: Add more upfront specification examples or decision criteria to Step 1.
 - For low `avg_completion_marker_success_rate`: Clarify or simplify the completion marker format in Step 3.
 - For high `avg_blocker_count`: Add blocker-recovery guidance or prerequisite check instructions.
 - For low `avg_confidence`: Strengthen the confidence calculation instructions with clearer rubrics.
 - For low `avg_parallel_groups`: Add explicit guidance for identifying parallel tasks in Step 2.
 - For low `avg_user_rating`: Review user feedback themes (what_went_well, what_went_poorly) for systemic issues.
 - Keep each `new_text` as short as possible while still addressing the root cause.
 ---
 ## Required Output Format
 Produce EXACTLY the following sections. The JSON block is parsed by machine — it must be syntactically valid.
 # PLAN2CODE PROMPT IMPROVEMENT PROPOSAL
 ### Improvement Rationale
 2–3 paragraphs explaining:
 1. Which metrics are being addressed and why they matter
 2. The specific prompt gaps identified in the diagnosis that you are targeting
 3. Why the proposed edits are expected to improve those metrics
 ### Proposed Edits
 ```json
 [
  {
    "file": "plan2code-X--name.md",
    "rationale": "One sentence explaining what this edit fixes",
    "expected_metric_impact": "avg_metric_name: expected direction and magnitude",
    "char_count_before": 0,
    "char_count_after": 0,
    "char_count_delta": 0,
    "old_text": "exact verbatim text from the file to replace",
    "new_text": "replacement text"
  }
 ]
 ```
 Set `char_count_before`, `char_count_after`, and `char_count_delta` to your best estimate (the system will verify and correct these automatically).
 ### Character Count Verification
 A table with columns: File | Before | Projected After | Delta | Limit | Status (✓/✗)
 Verify that NO file exceeds 11,000 characters after your proposed edits.
 ---
 End of improvement request.
@@ -0,0 +1,175 @@
 // All TypeScript interfaces for plan2code-metrics
 export interface PromptVersions {
  plan: string;           // sha256:... plan2code-1--plan.md
  revise_plan: string;    // plan2code-1b--revise-plan.md
  document: string;       // plan2code-2--document.md
  implement: string;      // plan2code-3--implement.md
  finalize: string;       // plan2code-4--finalize.md
  init: string;           // plan2code---init.md
  init_update: string;    // plan2code---init-update.md
  quick_task: string;     // plan2code---quick-task.md
 }
 export interface Step1PlanMetrics {
  present: boolean;
  final_confidence: number | null;
  confidence_breakdown: {
    requirements: number | null;
    feasibility: number | null;
    integration: number | null;
    risk: number | null;
  } | null;
  clarification_rounds: number | null;
  tech_stack_revision_rounds: number | null;
  verification_gaps_found: number | null;
  functional_requirements_count: number | null;
  non_functional_requirements_count: number | null;
  risk_count: number | null;
  phase_count: number | null;
 }
 export interface Step2DocumentMetrics {
  present: boolean;
  total_tasks: number | null;
  tasks_per_phase: number[] | null;
  phase_count: number | null;
  parallel_groups_identified: number | null;
  requirement_coverage_percent: number | null;
  verification_items_added: number | null;
 }
 export interface Step3ImplementMetrics {
  present: boolean;
  used_loop_mode: boolean;
  loop_mode: 'task' | 'phase' | null;
  task_completion_rate: number | null;
  tasks_completed: number | null;
  tasks_total: number | null;
  blocker_count: number | null;
  blocker_categories: string[] | null;
  total_iterations: number | null;
  avg_iteration_duration_ms: number | null;
  exit_code_distribution: Record<string, number> | null;
  completion_marker_success_rate: number | null;
 }
 export interface Step4FinalizeMetrics {
  present: boolean;
  completion_rate_at_audit: number | null;
  verification_failures_found: number | null;
  documentation_updates_needed: number | null;
  archival_succeeded: boolean | null;
 }
 export interface UserFeedback {
  overall_rating: number;   // 1-10
  rating_reason: string;
  what_went_well: string;
  what_went_poorly: string;
 }
 export interface RunMetrics {
  schema_version: '1.0';
  run_id: string;
  plan2code_version: string;
  prompt_versions: PromptVersions;
  project: {
    name: string;
    started_at: string | null;
    completed_at: string | null;
  };
  step1_plan: Step1PlanMetrics;
  step2_document: Step2DocumentMetrics;
  step3_implement: Step3ImplementMetrics;
  step4_finalize: Step4FinalizeMetrics;
  user_feedback: UserFeedback | null;
 }
 export interface PromptEdit {
  file: string;
  rationale: string;
  expected_metric_impact: string;
  char_count_before: number;
  char_count_after: number;
  char_count_delta: number;
  old_text: string;
  new_text: string;
 }
 export interface PromptProposal {
  proposal_id: string;
  created_at: string;
  based_on_runs: string[];
  analyst_model: string;
  proposals: PromptEdit[];
  status: 'pending' | 'applied' | 'rejected';
  diagnosis_file: string | null;
 }
 // Aggregated metrics schema
 export interface CohortMetrics {
  cohort_key: string;          // hash of sorted prompt_versions
  prompt_versions: PromptVersions;
  run_count: number;
  run_ids: string[];
  first_seen: string;
  last_seen: string;
  // Step 1 averages
  avg_confidence: number | null;
  avg_clarification_rounds: number | null;
  avg_verification_gaps_found: number | null;
  avg_functional_requirements_count: number | null;
  avg_non_functional_requirements_count: number | null;
  avg_risk_count: number | null;
  avg_phase_count_step1: number | null;
  // Step 2 averages
  avg_total_tasks: number | null;
  avg_phase_count_step2: number | null;
  avg_parallel_groups: number | null;
  avg_requirement_coverage_percent: number | null;
  avg_verification_items_added: number | null;
  // Step 3 averages (loop only)
  loop_run_count: number;
  avg_task_completion_rate: number | null;
  avg_blocker_count: number | null;
  avg_total_iterations: number | null;
  avg_iteration_duration_ms: number | null;
  avg_completion_marker_success_rate: number | null;
  // Step 4 averages
  avg_completion_rate_at_audit: number | null;
  avg_verification_failures_found: number | null;
  avg_documentation_updates_needed: number | null;
  archival_success_rate: number | null;
  // User feedback
  avg_user_rating: number | null;
  feedback_count: number;
 }
 export interface AggregatedMetrics {
  schema_version: '1.0';
  last_updated: string;
  total_runs: number;
  cohorts: CohortMetrics[];
  current_cohort_key: string | null;
 }
 // Metric targets for health assessment
 export const METRIC_TARGETS = {
  avg_confidence: { target: 90, direction: 'gte' as const },
  avg_clarification_rounds: { target: 2.0, direction: 'lte' as const },
  avg_verification_gaps_found: { target: 2.0, direction: 'lte' as const },
  avg_parallel_groups: { target: 0.5, direction: 'gte' as const },
  avg_verification_items_added: { target: 1.5, direction: 'lte' as const },
  avg_task_completion_rate: { target: 0.95, direction: 'gte' as const },
  avg_blocker_count: { target: 1.5, direction: 'lte' as const },
  avg_completion_marker_success_rate: { target: 0.95, direction: 'gte' as const },
  avg_verification_failures_found: { target: 1.0, direction: 'lte' as const },
  archival_success_rate: { target: 0.99, direction: 'gte' as const },
  avg_user_rating: { target: 7.0, direction: 'gte' as const },
 } as const;
@@ -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-metrics': 'src/bin/plan2code-metrics.ts',
    index: 'src/index.ts',
  },
  format: ['esm'],
  dts: true,
  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'],
  },
 });
@@ -140,10 +140,12 @@ Check for other AI agent config files and offer to replace with AGENTS.md refere
 ### If Files Found
 ```
->   ╭───╮
+   o     o
->   │ ● │
+    \   /
->   │ ~ │   Found other AI agent configs!
+    +---+
->   ╰───╯
+    | o |
    | ~ |   Found other AI agent configs!
    +---+
 ```
 > Found AI config files that could reference AGENTS.md:
@@ -17,7 +17,7 @@ Check for `./AGENTS.md` first:
   > ```
   > ⋅
   >     ╭───╮  
-   >     │ ● │
+   >     │ ● │   ?
   >     │ ~ │   Hmm, I don't see an AGENTS.md...
   >     ╰───╯
   > ```
@@ -142,13 +142,9 @@ Then tell user: "Created `specs/<feature-name>/PLAN-DRAFT-<date>.md`. Start new
 ---
 ```
 ⋅
   o     o
    ╲   ╱
    ╭───╮
    │ ★ │
    │ ◡ │   Plan ready! What do you think?
    ├───┤
    │ · │
    ╰───╯
 ```
@@ -16,7 +16,7 @@ Check if `./AGENTS.md` exists:
   > ```
   > ⋅
   >     ╭───╮
-   >     │ ● │
+   >     │ ● │  ?
   >     │ ~ │   Hmm, I don't see an AGENTS.md...
   >     ╰───╯
   > ```
@@ -76,13 +76,9 @@ Present findings and confirm understanding before proceeding.
 ```
 ⋅
   o     o
    ╲   ╱  ?
    ╭───╮
    │ ● │
    │ ~ │   Here's the plan. What do you think?
    ├───┤
    │ · │
    ╰───╯
 ```
@@ -194,13 +194,13 @@ Sections: Summary (2-3 sentences), Tasks Completed (Y/Z + blocked list), Test Re
 On user "approved":
 1. Mark `[/]` → `[x]` in overview.md, update phase-X.md status to "Complete"
-2. Show Mascot art with completion message
+2. Show Planny art with completion message
 3. Provide: `git add -A && git commit -m "Complete Phase X: [Phase Name]" -m "AI Assisted"`
 4. **If more phases:** "NEXT STEP: Start NEW conversation and run: `/plan2code-3--implement`"
 5. **If final phase:** "NEXT STEP: Start NEW conversation and run: `/plan2code-4--finalize`"
 6. Mention `/plan2code-1b--revise` option
-continuing:
+Planny (continuing):
 ```
 ⋅
    ╭───╮
@@ -209,7 +209,7 @@ continuing:
    ╰───╯
 ```
-final phase:
+Planny (final phase):
 ```
 ⋅
    ╭───╮
@@ -235,7 +235,7 @@ If user says "abort", "cancel", or similar:
 |-------|----------|
 | Lost context mid-phase | Attach specs, say "resume from Task X.Y" |
 | Spec unclear/conflicting | Mark task blocked, ask user |
-| Need to change plan | Pause, use `/plan2code-1b--revise` |
+| Need to change plan | Pause, use `/plan2code-1b--revise-plan` |
 ## Learning Capture
@@ -177,7 +177,7 @@ Add this summary to `overview.md` under `## Completion Summary`.
 Report: table of documents needing updates with proposed changes. List each document with specific additions.
-If updates needed, show Mascot and ask for approval:
+If updates needed, show Planny and ask for approval:
 ```
 ⋅
@@ -193,9 +193,39 @@ Do NOT make documentation changes without user approval.
 ---
-### STEP 5: Spec Cleanup
+### STEP 5: User Feedback (Optional)
-`🧹 [FINALIZATION STEP 5: Spec Cleanup]`
+`🧹 [FINALIZATION STEP 5: User Feedback]`
 **Objective:** Collect optional user feedback before archival.
 Ask the user: "Would you like to provide feedback on this workflow run? (optional)"
 If yes, collect:
 1. **Rating** (1-10): "How would you rate this workflow run overall?"
 2. **Reason**: "Brief reason for your rating?"
 3. **Went Well**: "What went well?"
 4. **Went Poorly**: "What went poorly or could improve?"
 Append to `overview.md` (in the active spec directory):
 ```markdown
 ## User Feedback
 | Field | Value |
 |-------|-------|
 | Rating | [1-10] |
 | Reason | [response] |
 | Went Well | [response] |
 | Went Poorly | [response] |
 ```
 If the user declines, skip and proceed to Step 6 (Spec Cleanup).
 ---
 ### STEP 6: Spec Cleanup
 `🧹 [FINALIZATION STEP 6: Spec Cleanup]`
 **Objective:** Archive completed specifications.
@@ -222,9 +252,9 @@ specs--completed/
 ---
-### STEP 6: Final Confirmation
+### STEP 7: Final Confirmation
-`🧹 [FINALIZATION STEP 6: Final Confirmation]`
+`🧹 [FINALIZATION STEP 7: Final Confirmation]`
 **Objective:** Confirm all finalization steps complete.
@@ -242,8 +272,9 @@ specs--completed/
 - [x] Step 2: Implementation Verification
 - [x] Step 3: Implementation Summary
 - [x] Step 4: Documentation Review
- [x] Step 5: Spec Cleanup
+- [x] Step 5: User Feedback (Optional)
- [x] Step 6: Final Confirmation
+- [x] Step 6: Spec Cleanup
 - [x] Step 7: Final Confirmation
 ### Files Created/Modified During Finalization
 - `specs/<feature-name>/overview.md` - Added completion summary
@@ -268,6 +299,9 @@ specs--completed/
 > Specs archived to `specs--completed/<feature-name>/`.
 > Thank you for using the Plan2Code workflow!
 ### Metrics Capture (Contributors)
 To help improve plan2code's prompts, run `plan2code-metrics` in the project root.
 ### Handling Incomplete Implementations
 | Completion | Action |
@@ -1,6 +1,6 @@
 {
  "name": "Plan2Code",
-  "version": "1.6.1",
+  "version": "1.8.1",
  "description": "A structured 4-step workflow methodology for AI-assisted software development",
  "keywords": [
    "ai",
@@ -17,5 +17,7 @@
    "url": "https://github.com/jparkerweb/plan2code"
  },
  "homepage": "https://plan2code.jparkerweb.com",
  "releaseDate": "2026-02-20",
  "mode": "utility"
 }
Author	SHA1	Message	Date
jparkerweb	628e688ab9	Planny hit the gym and lost some weight Trimmed the mascot ASCII art across all prompts and installer. Planny is now more aerodynamic and 40% less chunky.	2026-02-22 21:48:13 -08:00
jparkerweb	157e55ef2e	docs: update AGENTS.md with plan2code-metrics section and corrections - Add plan2code-metrics to architecture tree, dev commands, installer menu - Add full metrics section (data flow, CLI menu, key files, feedback format, metric targets) - Fix Code Style: split install.js (CommonJS) vs loop/metrics (TypeScript+ESM) - Update finalize prompt description to reflect 7 steps - Add metrics-specific gotchas (internal prompts, feedback table format)	2026-02-22 21:47:45 -08:00
jparkerweb	02fd4efa40	v1.8.1 — add user feedback collection to plan2code-metrics	2026-02-22 21:41:16 -08:00
jparkerweb	348c8ed7b2	feat: add user feedback collection to plan2code-metrics - Add UserFeedback type (rating 1-10, reason, went well, went poorly) - Collector parses ## User Feedback table from overview.md - Aggregator computes avg_user_rating and feedback_count per cohort - CLI offers interactive feedback collection with pipe-safe escaping - Finalize prompt collects optional feedback as Step 5 (before archival) - Analysis/improvement prompts reference avg_user_rating metric target	2026-02-22 21:38:58 -08:00
jparkerweb	5c2f70a37c	v1.8.0 — add plan2code-metrics recursive self-improvement toolchain New package for contributors to collect, aggregate, analyze, and improve workflow prompts based on real project data. Includes unit tests (vitest), installer integration, and loop/finalize hints.	2026-02-22 19:57:40 -08:00
jparkerweb	de46275b51	v1.7.0	2026-02-22 12:58:08 -08:00