mirror of
https://github.com/jparkerweb/plan2code.git
synced 2026-07-21 18:33:22 -07:00
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.
This commit is contained in:
@@ -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 +1,219 @@
|
||||
/**
|
||||
* 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));
|
||||
|
||||
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,
|
||||
};
|
||||
}
|
||||
|
||||
// ── 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 +1,574 @@
|
||||
/**
|
||||
* 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('—')}`);
|
||||
} 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)}`);
|
||||
}
|
||||
|
||||
// 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 +1,474 @@
|
||||
/**
|
||||
* 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,
|
||||
} 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,
|
||||
};
|
||||
}
|
||||
|
||||
// ── 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),
|
||||
};
|
||||
|
||||
// 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 +1,18 @@
|
||||
// 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,
|
||||
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 +1,100 @@
|
||||
# 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 |
|
||||
|
||||
---
|
||||
|
||||
## 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 +1,92 @@
|
||||
# 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.
|
||||
- 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 +1,162 @@
|
||||
// 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 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;
|
||||
}
|
||||
|
||||
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;
|
||||
}
|
||||
|
||||
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 },
|
||||
} 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'],
|
||||
},
|
||||
});
|
||||
Reference in New Issue
Block a user