* feat(#2632): record executor actuals and close the estimate calibration loop * fix(#2632): calibrate against the raw projection so the loop converges * test(#2632): add closed-loop convergence guard and codify the feedback-loop rule * fix(#2632): pair calibration samples per plan; atomic write; amend adr * chore(#2632): backfill changeset pr to 2672 * fix(#2632): retry renameSync on transient windows errnos and clean up the temp
This commit is contained in:
Tom Boucher
5
.changeset/vivid-cranes-click.md
Normal file
5
.changeset/vivid-cranes-click.md
Normal file
@@ -0,0 +1,5 @@
|
||||
---
|
||||
type: Added
|
||||
pr: 2672
|
||||
---
|
||||
**Estimates now calibrate against reality** — the executor records what a phase actually cost into SUMMARY.md, and `/gsd:extract-learnings` computes the estimate-vs-actual correction so future plan estimates improve for your project. (#2632)
|
||||
@@ -21,7 +21,7 @@ Module owning the pure phase-id parsing and matching helpers: phase-name normali
|
||||
Module owning phase create, rename, complete, remove, list, and plan-index operations, plus phase-dir prefix validation, STATE.md staleness detection, and auto-prune behaviour. Entry point: `gsd-core/bin/lib/phase.cjs` (CJS surface). Typed phase events: `GSDPhaseStartEvent`, `GSDPhaseStepStartEvent`, `GSDPhaseStepCompleteEvent`, `GSDPhaseCompleteEvent`. (The SDK native-query surface, the `types.ts` event definitions, `phase-runner.ts`, and `phase-prompt.ts` were retired with the SDK package per ADR-0174.)
|
||||
|
||||
### Phase Estimation Module
|
||||
Module owning phase-effort estimation and its calibration against measured reality (ADR-2629, epic #1952). Pure — no I/O, no config reads; the CLI seam (`src/estimate-cli.cts`, verbs `estimate-check` / `estimate-calibration`) owns reading `.planning/config.json` and `.planning/estimation-calibration.json`. Interface: `parseEstimate`/`renderEstimate` (the PLAN.md `estimate: {tokens, tasks, confidence}` block), `parseActuals`/`renderActuals` (the SUMMARY.md `actuals: {tokens, tasks, commits}` block), `deriveConfidence(sampleCount) → low|med|high`, `classifyAgainstBudget(estimate, budget) → {overBudget, ratio, recommendation, budgetValid}`, `computeCalibration(samples) → {factor, sampleCount, applied, confidence, clamped}`, `applyCalibration`, `parseCalibrationDocument`/`renderCalibrationDocument`, and `measureTokens` (a re-export of `prompt-budget`'s `estimateTokens`). **Domain terms: _smart zone_** — the usable prefix of a model's context window before output quality degrades, expressed as the configurable `workflow.smart_zone_tokens` budget (default 100000, a *policy default* rather than a benchmark constant since the effective ceiling is model/task-dependent); **_estimate/actuals_** — a projected phase cost recorded at plan time and the measured cost recorded at completion, both on the **same `estimateTokens` scale** so their ratio measures the miss rather than a difference between two measurement methods. Two invariants: (1) every signal is **exogenous** — the correction routes on a measured actual/estimate ratio and `confidence` routes on a calibration sample count, never on a model's self-assessment (this project measured self-rated confidence and found it weak — `gsd-core/references/honest-verifier.md:25-29`; see `.out-of-scope/general-purpose-agent-prompt-skills.md`); (2) the over-budget flag is **advisory** — a warning plus a split recommendation, never a block. Calibration is median-of-ratios, clamped to `[0.5, 3.0]`, and inert below 3 samples. Source of truth: `gsd-core/bin/lib/phase-estimation.cjs` (generated from `src/phase-estimation.cts`). Test anchor: `tests/phase-estimation.test.cjs`.
|
||||
Module owning phase-effort estimation and its calibration against measured reality (ADR-2629, epic #1952). Pure — no I/O, no config reads; the CLI seam (`src/estimate-cli.cts`, verbs `estimate-check` / `estimate-calibration`) owns reading `.planning/config.json` and `.planning/estimation-calibration.json`. Interface: `parseEstimate`/`renderEstimate` (the PLAN.md `estimate: {tokens, tasks, confidence}` block), `parseActuals`/`renderActuals` (the SUMMARY.md `actuals: {tokens, tasks, commits}` block), `deriveConfidence(sampleCount) → low|med|high`, `classifyAgainstBudget(estimate, budget) → {overBudget, ratio, recommendation, budgetValid}`, `computeCalibration(samples) → {factor, sampleCount, applied, confidence, clamped}`, `applyCalibration`, `parseCalibrationDocument`/`renderCalibrationDocument`, `extractFrontmatterBlock` (leading-`---`-anchored scalar-block reader; hand-rolled because core ships no external deps), `calibrationBasis` (returns `estimate.raw_tokens` when present, else `tokens` — calibration must measure actual/raw or the loop un-corrects itself), and `measureTokens` (a re-export of `prompt-budget`'s `estimateTokens`). **Domain terms: _smart zone_** — the usable prefix of a model's context window before output quality degrades, expressed as the configurable `workflow.smart_zone_tokens` budget (default 100000, a *policy default* rather than a benchmark constant since the effective ceiling is model/task-dependent); **_estimate/actuals_** — a projected phase cost recorded at plan time and the measured cost recorded at completion, both on the **same `estimateTokens` scale** so their ratio measures the miss rather than a difference between two measurement methods. Two invariants: (1) every signal is **exogenous** — the correction routes on a measured actual/estimate ratio and `confidence` routes on a calibration sample count, never on a model's self-assessment (this project measured self-rated confidence and found it weak — `gsd-core/references/honest-verifier.md:25-29`; see `.out-of-scope/general-purpose-agent-prompt-skills.md`); (2) the over-budget flag is **advisory** — a warning plus a split recommendation, never a block. Calibration is median-of-ratios, clamped to `[0.5, 3.0]`, and inert below 3 samples. CLI seam verbs: `estimate-check` (classify one figure; `--calibrated` when the input already has the factor applied — omitting it squares the correction), `estimate-calibration` (report the current factor), `estimate-calibrate` (#2632 — pair every completed phase's PLAN `estimate` with its SUMMARY `actuals`, rebuild `.planning/estimation-calibration.json` idempotently, and report the result; this is what closes the loop). Source of truth: `gsd-core/bin/lib/phase-estimation.cjs` (generated from `src/phase-estimation.cts`) and `src/estimate-cli.cts`. Test anchors: `tests/phase-estimation.test.cjs`, `tests/estimate-calibrate.test.cjs`.
|
||||
|
||||
### Verification Module
|
||||
Module owning the canonical phase-verification status projection shared by phase transition, progress, manager, autonomous, and closeout readiness paths. `readVerificationStatus(phaseDir, opts?)` reads the first `*-VERIFICATION.md` frontmatter `status`, maps it through `VERIFICATION_ROUTING_TABLE`, and fail-closes — only `{passed}` satisfies the canonical gate; `missing`/`unknown`/`gaps_found`/`human_needed`/`stale` all route away from "complete" (#1522). `findStaleVerificationSummary` flags a SUMMARY newer than the VERIFICATION file (status `stale`). Both honor a no-throw, degrade-to-safe contract (any FS error → `missing` / not-stale) and an injectable `opts.fs` seam. Source of truth: `gsd-core/bin/lib/verification.cjs` (generated from `src/verification.cts`).
|
||||
@@ -451,6 +451,7 @@ The prompt-level data/instruction isolation seam for untrusted web/document ingr
|
||||
`RULESET.TESTS.coderabbit-fix-prefer=behavioral tests (call exported fn, capture JSON, assert typed fields) over source-grep`
|
||||
`RULESET.TESTS.diagnostics=after JSON.parse, assert output shape (Array.isArray(output.phases)) with raw-output-prefix diagnostics before .map() — prevents opaque TypeErrors when CLI output shape changes`
|
||||
`RULESET.TESTS.boundary-coverage=tests MUST exercise inputs at and near the threshold/limit, not only trivial-fit and trivial-overflow; pick inputs where N ∈ {limit-1, limit, limit+1} and where pre-trim/pre-check accumulators ≈ effective limit; "very small" and "very large" inputs alone do not constitute edge-case coverage and routinely miss off-by-one + reservation-accounting bugs`
|
||||
`RULESET.TESTS.feedback-loop-convergence=when a feature's OUTPUT feeds back into its own INPUT (calibration, retry backoff, adaptive budgets, ratchets, any self-correcting signal), step-wise tests are NOT sufficient evidence of correctness: they assert `given X return Y` while the defect lives in the TRAJECTORY across iterations. Required: a closed-loop test that (a) drives the REAL end-to-end surface — not the pure core alone, since composition bugs live between surfaces — for N >= 2x the loop's window, (b) asserts convergence on the known-true value, (c) asserts the fixed point (an already-correct history must produce NO correction), and (d) asserts boundedness under an adversarial/oscillating history. Two defects shipped past a green ~26,800-test suite in epic #1952 for want of exactly this: calibration applied twice across two surfaces (factor^2, #2631) and calibration measured against its own corrected output so it oscillated to ~1.41 instead of converging on 2.0 (#2632). Every unit, boundary, property and round-trip test passed for both. HOW TO SPOT ONE (the detection tell, not a judgment call): the feature's own acceptance criterion carries a TEMPORAL QUANTIFIER — "after N phases", "subsequent", "over time", "improves", "learns", "adapts". That phrasing means the claim is about a TRAJECTORY, so a step-wise `given X return Y` test does not test the claim that was made. #1952's AC4 read "After N phases, the error is computed and applied as a correction to SUBSEQUENT estimates" — the tell was in plain sight and was still tested as a point. Survey of this repo (2026-07): estimation calibration is the ONLY true instance; size/mutation ratchets are exempt because they fail on both growth AND shrinkage (cannot self-satisfy), and retry ladders (node_repair_budget, plan_bounce_passes, provider_escalation) terminate rather than feed back. Test anchor: tests/estimate-loop-convergence.test.cjs`
|
||||
`RULESET.TESTS.boundary-coverage.fixtures=for any code with budget/limit/quota/threshold parameter, test suite MUST include: (a) input where SUT estimate == limit exactly, (b) input where estimate == limit - 1, (c) input where estimate == limit + 1, (d) input where any internal reserve/safety constant pushes baseline within reserve-distance of limit (catches early-pressure firing)`
|
||||
`RULESET.TESTS.boundary-coverage.anti-pattern=test suites that pair budget:1_000_000 (trivially fits) with budget:1 (trivially overflows) and skip the boundary region; failure mode that shipped PR #3708 UNNEEDED_TRIM + FALSE_HARDFAIL regressions (commit 2df566ed, fixed bde1ae8f)`
|
||||
`LEARNING.prompt-budget.boundary-gap=PR #3708 commit 2df566ed reserved NOTE_RESERVE_TOKENS in pressure-threshold AND in minSet pre-check; both buggy paths only fire when baseTokens ∈ (effectiveBudget - NOTE_RESERVE_TOKENS, effectiveBudget]; original test suite used budgets far from that band so neither path was exercised; fix bde1ae8f confines NOTE_RESERVE accounting to post-trim assembly path only; future budget/limit code MUST add boundary fixtures per RULESET.TESTS.boundary-coverage.fixtures`
|
||||
|
||||
@@ -638,7 +638,16 @@ This file is the canonical output of this step. The orchestrator reads `.plannin
|
||||
|
||||
**Use template:** @~/.claude/gsd-core/templates/summary.md
|
||||
|
||||
**Frontmatter:** phase, plan, subsystem, tags, dependency graph (requires/provides/affects), tech-stack (added/patterns), key-files (created/modified), decisions, metrics (duration, completed date), status (`status: complete` — required so the audit-open scanner recognises the summary as done).
|
||||
**Frontmatter:** phase, plan, subsystem, tags, dependency graph (requires/provides/affects), tech-stack (added/patterns), key-files (created/modified), decisions, metrics (duration, completed date), status (`status: complete` — required so the audit-open scanner recognises the summary as done), and `actuals` (#2632).
|
||||
|
||||
**`actuals` (required when the plan carried an `estimate`):** record what the phase ACTUALLY cost, on the SAME scale the estimate used — `estimateTokens` (chars/4) over the realized diff, NOT a harness token count. Mixing scales measures the measurement methods, not the miss.
|
||||
```yaml
|
||||
actuals:
|
||||
tokens: 74000 # chars/4 over the files you actually changed
|
||||
tasks: 5 # tasks completed
|
||||
commits: 7 # commits made
|
||||
```
|
||||
These pair with the plan's `estimate` to calibrate future estimates (ADR-2629). Do not round to look closer to the estimate — a flattering number corrupts every later projection.
|
||||
|
||||
**Title:** `# Phase [X] Plan [Y]: [Name] Summary`
|
||||
|
||||
|
||||
@@ -293,8 +293,8 @@ See @~/.claude/gsd-core/references/planner-guidance.md for dependency graph buil
|
||||
Full rules: @~/.claude/gsd-core/references/context-budget.md (Phase Sizing). Read before sizing.
|
||||
|
||||
- **2-3 tasks per plan.** **ALWAYS split if:** >3 tasks, multiple subsystems, or any task touching >5 files.
|
||||
- **Emit `estimate`** in PLAN.md frontmatter: run the `estimate-calibration` query, multiply your raw
|
||||
token projection by its calibration factor, and copy its `confidence` verbatim — derived from the
|
||||
- **Emit `estimate`**: run `estimate-calibration`; `tokens` = raw projection x factor, `raw_tokens` = that
|
||||
projection before the factor (calibration measures actual/raw), `confidence` verbatim — derived from
|
||||
sample count, never self-rated.
|
||||
- **Over the smart-zone budget?** Re-slice: tracer + expansion slices. Advisory, never a block.
|
||||
|
||||
@@ -318,6 +318,7 @@ user_setup: [] # Human-required setup (omit if empty)
|
||||
|
||||
estimate: # Projected execution cost (see Estimate Emission)
|
||||
tokens: 60000 # calibrated projection
|
||||
raw_tokens: 30000 # pre-factor projection
|
||||
tasks: 3 # task count the projection assumes
|
||||
confidence: low # low | med | high — DERIVED from sample count, never self-rated
|
||||
|
||||
|
||||
@@ -66,7 +66,7 @@ The effective ceiling is model-, task-, and distractor-dependent. **100k is a co
|
||||
### 4. Calibration: median ratio, clamped, with a minimum sample count
|
||||
|
||||
```
|
||||
ratio_i = actuals_i.tokens / estimate_i.tokens (phases with BOTH fields)
|
||||
ratio_i = actuals_i.tokens / estimate_i.raw_tokens (per PLAN, with BOTH fields)
|
||||
factor = clamp(median(ratio_i), 0.5, 3.0) when n >= 3
|
||||
factor = 1.0 when n < 3
|
||||
```
|
||||
@@ -74,6 +74,8 @@ factor = 1.0 when n < 3
|
||||
- **Median, not mean** — one pathological phase (an aborted run, a mass rename) must not swing the projection for every later phase.
|
||||
- **Clamped to [0.5, 3.0]** — bounds the blast radius of a degenerate history; a factor outside that range indicates the estimator is wrong in kind, not in degree, and should be fixed rather than amplified.
|
||||
- **`n >= 3` before any correction applies** — below that, the sample says more about variance than about bias.
|
||||
- **The denominator is the RAW projection, not the emitted (already-corrected) figure** — amended #2632. Measuring `actual / calibrated` is self-defeating: once the correction works the observed ratio approaches 1, which drags the median back toward 1 and un-corrects the next estimate. Simulated over 10 phases against a true 2x miss it oscillates and settles near 1.41 instead of converging on 2.0. Plans therefore record `estimate.raw_tokens` alongside the calibrated `estimate.tokens`, and `calibrationBasis()` prefers it (falling back to `tokens` for plans written before #2632, where no factor had yet been applied).
|
||||
- **Samples are per PLAN, not per phase** — amended #2632. A phase holds several `<NN>-<PP>-PLAN.md` files; pairing at phase granularity cross-pairs one plan's projection with another's cost and discards the rest.
|
||||
|
||||
Persisted to `.planning/estimation-calibration.json` with a `schema_version` field, written by `extract-learnings`, read at plan time. Versioned from the first write so the schema can migrate without a silent misread.
|
||||
|
||||
|
||||
@@ -73,7 +73,7 @@ must_haves:
|
||||
| `requirements` | Yes | array of IDs | Requirement IDs from ROADMAP.md that this plan addresses. Every phase requirement ID must appear in at least one plan's `requirements` field. Empty arrays are a BLOCKER. |
|
||||
| `user_setup` | No | array of objects | External-service setup steps that Claude cannot automate (account creation, secret retrieval, dashboard configuration). When present, execute-phase generates a `USER-SETUP.md` checklist for the developer. |
|
||||
| `status` | No | `superseded` | Marks a plan that was deliberately reassigned or abandoned mid-phase and will never be executed. A `status: superseded` plan is excluded from the phase's plan and summary counts, so it never holds the phase below 100%. See [Superseded plans](#superseded-plans). Any other value (or the field's absence) has no effect on counting. |
|
||||
| `estimate` | No | object | Projected execution cost: `{tokens, tasks, confidence}` (#2631, [ADR-2629](../adr/2629-phase-effort-estimation-calibration.md)). `tokens` is an `estimateTokens`-scale projection with the project's calibration factor **already applied** (which is why the plan-checker passes `--calibrated` to `estimate-check` — re-applying it would square the correction); `confidence` (`low`/`med`/`high`) is **derived from the calibration sample count, never self-rated**. Additive and optional — a plan without it behaves exactly as before. A plan estimated above `workflow.smart_zone_tokens` is flagged with a split recommendation at plan time; the flag is advisory and never blocks. |
|
||||
| `estimate` | No | object | Projected execution cost: `{tokens, raw_tokens, tasks, confidence}` (#2631, [ADR-2629](../adr/2629-phase-effort-estimation-calibration.md)). `tokens` is an `estimateTokens`-scale projection with the project's calibration factor **already applied** (which is why the plan-checker passes `--calibrated` to `estimate-check` — re-applying it would square the correction); `confidence` (`low`/`med`/`high`) is **derived from the calibration sample count, never self-rated**. Additive and optional — a plan without it behaves exactly as before. A plan estimated above `workflow.smart_zone_tokens` is flagged with a split recommendation at plan time; the flag is advisory and never blocks. |
|
||||
| `must_haves` | Yes | object | Goal-backward verification criteria. See below. |
|
||||
|
||||
### Superseded plans
|
||||
|
||||
@@ -189,6 +189,17 @@ See [PLAN.md schema](plan-md.md) for the full field reference.
|
||||
| **Produced by** | `execute-phase` executor agent (written at the end of each plan's execution). |
|
||||
| **Consumed by** | `/gsd-progress` (phase status); `gsd-planner` (when a subsequent plan has a genuine dependency on prior plan output); `milestone-summary`. |
|
||||
|
||||
**`actuals` frontmatter (#2632, [ADR-2629](../adr/2629-phase-effort-estimation-calibration.md)).** When the phase's PLAN carried an `estimate`, the executor records what it actually cost:
|
||||
|
||||
```yaml
|
||||
actuals:
|
||||
tokens: 74000 # estimateTokens scale (chars/4) over the realized diff
|
||||
tasks: 5
|
||||
commits: 7
|
||||
```
|
||||
|
||||
`tokens` uses the **same scale as the estimate**, not a harness-reported token count — an executor subagent cannot read its own consumption, and a ratio between two different measurement methods would measure the methods rather than the miss. `/gsd:extract-learnings` pairs each phase's estimate with its actuals via `gsd_run query estimate-calibrate`, writes `.planning/estimation-calibration.json`, and the planner applies the resulting factor to subsequent estimates. Additive and optional: a summary without `actuals` simply contributes no calibration sample.
|
||||
|
||||
### `<NN>-VERIFICATION.md`
|
||||
|
||||
| | |
|
||||
|
||||
@@ -2187,6 +2187,7 @@ const HOST_COMMAND_ROUTERS = {
|
||||
// rather than a family — ADR-2346 promotes to a family only at >=3.
|
||||
'estimate-check': ({ args, cwd, raw }) => estimateCli.cmdEstimateCheck(cwd, args.slice(1), raw),
|
||||
'estimate-calibration': ({ args, cwd, raw }) => estimateCli.cmdEstimateCalibration(cwd, args.slice(1), raw),
|
||||
'estimate-calibrate': ({ args, cwd, raw }) => estimateCli.cmdEstimateCalibrate(cwd, args.slice(1), raw),
|
||||
'config-new-project': routeConfigNewProject,
|
||||
'config-path': routeConfigPath,
|
||||
'migrate-config': routeMigrateConfig,
|
||||
|
||||
@@ -6,6 +6,10 @@ tags: [searchable tech]
|
||||
provides:
|
||||
- [bullet list of what was built/delivered]
|
||||
affects: [list of phase names or keywords]
|
||||
actuals:
|
||||
tokens: [chars/4 over files actually changed]
|
||||
tasks: [tasks completed]
|
||||
commits: [commits made]
|
||||
tech-stack:
|
||||
added: [libraries/tools]
|
||||
patterns: [architectural/code patterns]
|
||||
|
||||
@@ -6,6 +6,10 @@ tags: [searchable tech]
|
||||
provides:
|
||||
- [bullet list of what was built/delivered]
|
||||
affects: [list of phase names or keywords]
|
||||
actuals:
|
||||
tokens: [chars/4 over files actually changed]
|
||||
tasks: [tasks completed]
|
||||
commits: [commits made]
|
||||
tech-stack:
|
||||
added: [libraries/tools]
|
||||
patterns: [architectural/code patterns]
|
||||
|
||||
@@ -21,6 +21,13 @@ provides:
|
||||
- [bullet list of what this phase built/delivered]
|
||||
affects: [list of phase names or keywords that will need this context]
|
||||
|
||||
# Actuals (#2632) — pairs with the plan's `estimate` to calibrate future estimates.
|
||||
# Same estimateTokens scale (chars/4 over the realized diff), never a harness token count.
|
||||
actuals:
|
||||
tokens: [chars/4 over files actually changed]
|
||||
tasks: [tasks completed]
|
||||
commits: [commits made]
|
||||
|
||||
# Tech tracking
|
||||
tech-stack:
|
||||
added: [libraries/tools added in this phase]
|
||||
|
||||
@@ -186,6 +186,27 @@ The body follows this structure:
|
||||
```
|
||||
</step>
|
||||
|
||||
<step name="calibrate_estimates">
|
||||
Rebuild the estimate-vs-actual calibration from every completed phase (#2632, ADR-2629).
|
||||
|
||||
```bash
|
||||
gsd_run query estimate-calibrate
|
||||
```
|
||||
|
||||
This pairs each phase's PLAN `estimate` with its SUMMARY `actuals`, writes
|
||||
`.planning/estimation-calibration.json`, and reports the resulting correction factor.
|
||||
The planner reads it on the next `/gsd:plan-phase`, so estimates improve for THIS project
|
||||
over time.
|
||||
|
||||
Report the returned `factor`, `sample_count`, and `confidence` in the summary output.
|
||||
`applied: false` means fewer than 3 phases carry both an estimate and actuals — that is
|
||||
expected early and is not an error. The verb rebuilds from scratch each run, so it is safe
|
||||
to re-run and never accumulates duplicates.
|
||||
|
||||
Phases missing either side are skipped rather than guessed: a fabricated sample would
|
||||
steer every future estimate.
|
||||
</step>
|
||||
|
||||
<step name="update_state">
|
||||
Update STATE.md to reflect the learning extraction:
|
||||
|
||||
|
||||
@@ -33,6 +33,35 @@ const { output, error, ERROR_REASON } = io;
|
||||
const { planningDir } = planningWorkspace;
|
||||
const { CONFIG_DEFAULTS } = configLoader;
|
||||
|
||||
// WIN-1 parity (DEFECT.WINDOWS-FS-OPS): on Windows a concurrent reader, indexer,
|
||||
// or AV scanner can transiently hold the rename target open. Retry the transient
|
||||
// errnos with backoff, matching the writeLedger / writeConsentStore idiom.
|
||||
const RENAME_RETRY_ERRNOS = new Set(['EPERM', 'EBUSY', 'EACCES']);
|
||||
const RENAME_MAX_ATTEMPTS = 3;
|
||||
const RENAME_RETRY_BACKOFF_MS = 50;
|
||||
let _renameSleepBuf: Int32Array | null = null;
|
||||
function renameBackoff(): void {
|
||||
if (_renameSleepBuf === null) _renameSleepBuf = new Int32Array(new SharedArrayBuffer(4));
|
||||
Atomics.wait(_renameSleepBuf, 0, 0, RENAME_RETRY_BACKOFF_MS);
|
||||
}
|
||||
|
||||
/** Rename with a bounded retry on the transient Windows errnos. Rethrows anything else. */
|
||||
function renameWithRetry(from: string, to: string): void {
|
||||
for (let attempt = 1; ; attempt += 1) {
|
||||
try {
|
||||
fs.renameSync(from, to);
|
||||
return;
|
||||
} catch (err) {
|
||||
const code = (err as NodeJS.ErrnoException).code ?? '';
|
||||
if (attempt < RENAME_MAX_ATTEMPTS && RENAME_RETRY_ERRNOS.has(code)) {
|
||||
renameBackoff();
|
||||
continue;
|
||||
}
|
||||
throw err;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/** Filename of the persisted calibration document, written by extract-learnings (Phase 3). */
|
||||
export const CALIBRATION_FILENAME = 'estimation-calibration.json';
|
||||
|
||||
@@ -151,6 +180,130 @@ export function cmdEstimateCheck(cwd: string, args: string[], raw: boolean): voi
|
||||
}, raw);
|
||||
}
|
||||
|
||||
/**
|
||||
* Pair each completed phase's PLAN estimate with its SUMMARY actuals.
|
||||
*
|
||||
* A phase contributes a sample only when BOTH sides are present and well-formed.
|
||||
* A plan with no `estimate` block, a summary with no `actuals`, or a malformed
|
||||
* value is skipped rather than guessed — a fabricated sample would silently
|
||||
* steer every future estimate.
|
||||
*/
|
||||
export function collectCalibrationSamples(cwd: string): estimation.CalibrationSample[] {
|
||||
const phasesRoot = path.join(planningDir(cwd), 'phases');
|
||||
let phases: string[];
|
||||
try {
|
||||
phases = fs.readdirSync(phasesRoot, { withFileTypes: true })
|
||||
.filter((d) => d.isDirectory())
|
||||
.map((d) => d.name)
|
||||
.sort();
|
||||
} catch {
|
||||
return [];
|
||||
}
|
||||
|
||||
const readBlock = (file: string, key: string): Record<string, unknown> | null => {
|
||||
let text: string;
|
||||
try {
|
||||
text = fs.readFileSync(file, 'utf-8');
|
||||
} catch {
|
||||
return null;
|
||||
}
|
||||
return estimation.extractFrontmatterBlock(text, key);
|
||||
};
|
||||
|
||||
const samples: estimation.CalibrationSample[] = [];
|
||||
for (const phase of phases) {
|
||||
const dir = path.join(phasesRoot, phase);
|
||||
let files: string[];
|
||||
try {
|
||||
files = fs.readdirSync(dir).sort();
|
||||
} catch {
|
||||
continue;
|
||||
}
|
||||
|
||||
// Pair PER PLAN, keyed on the `<NN>-<PP>` stem, NOT per phase directory.
|
||||
// A phase routinely holds several plans (docs/reference/planning-artifacts.md:
|
||||
// "one file per plan"). Taking the first plan with an estimate and the first
|
||||
// summary with actuals independently cross-pairs one plan's projection with
|
||||
// another's cost — a fabricated sample — and discards every later plan.
|
||||
const stems = new Map<string, { plan?: string; summary?: string }>();
|
||||
for (const f of files) {
|
||||
const m = /^(.*?)-(PLAN|SUMMARY)\.md$/.exec(f);
|
||||
if (m === null) continue;
|
||||
const stem = m[1];
|
||||
const entry = stems.get(stem) ?? {};
|
||||
if (m[2] === 'PLAN') entry.plan = path.join(dir, f);
|
||||
else entry.summary = path.join(dir, f);
|
||||
stems.set(stem, entry);
|
||||
}
|
||||
|
||||
for (const stem of [...stems.keys()].sort()) {
|
||||
const { plan, summary } = stems.get(stem) as { plan?: string; summary?: string };
|
||||
if (plan === undefined || summary === undefined) continue;
|
||||
|
||||
const estimate = estimation.parseEstimate(readBlock(plan, 'estimate'));
|
||||
const actuals = estimation.parseActuals(readBlock(summary, 'actuals'));
|
||||
if (estimate === null || actuals === null) continue;
|
||||
|
||||
// Measure against the RAW projection — see PhaseEstimate.rawTokens for why
|
||||
// measuring against the calibrated figure makes the loop self-defeating.
|
||||
samples.push({
|
||||
estimateTokens: estimation.calibrationBasis(estimate),
|
||||
actualTokens: actuals.tokens,
|
||||
});
|
||||
}
|
||||
}
|
||||
return samples;
|
||||
}
|
||||
|
||||
/**
|
||||
* `estimate-calibrate` — rebuild the calibration document from completed phases.
|
||||
*
|
||||
* Rebuilds from scratch every run rather than appending, so it is idempotent and
|
||||
* a corrupt prior document is replaced rather than merged. This is the verb that
|
||||
* closes the loop (#1952 AC4): extract-learnings invokes it, and the planner's
|
||||
* next estimate reads the result.
|
||||
*/
|
||||
export function cmdEstimateCalibrate(cwd: string, _args: string[], raw: boolean): void {
|
||||
const samples = collectCalibrationSamples(cwd);
|
||||
const calibration = estimation.computeCalibration(samples);
|
||||
|
||||
const target = path.join(planningDir(cwd), CALIBRATION_FILENAME);
|
||||
let written = true;
|
||||
let writeError: string | null = null;
|
||||
try {
|
||||
// Write-then-rename: a direct writeFileSync can leave a truncated file if
|
||||
// interrupted, and parseCalibrationDocument treats malformed JSON exactly
|
||||
// like "no history yet" — so a torn write would silently erase the
|
||||
// calibration instead of surfacing.
|
||||
const tmp = `${target}.tmp-${String(process.pid)}`;
|
||||
try {
|
||||
fs.writeFileSync(tmp, estimation.renderCalibrationDocument(samples), 'utf-8');
|
||||
renameWithRetry(tmp, target);
|
||||
} catch (err) {
|
||||
// Never leave the temp behind for a later run to trip over.
|
||||
try { fs.rmSync(tmp, { force: true }); } catch { /* best effort */ }
|
||||
throw err;
|
||||
}
|
||||
} catch (err) {
|
||||
// Persisting is best-effort: a read-only .planning must not fail the phase.
|
||||
// But report WHY — a genuine bug and a benign permission issue are otherwise
|
||||
// indistinguishable to both the caller and the workflow.
|
||||
written = false;
|
||||
writeError = err instanceof Error ? (err.message || String(err)) : String(err);
|
||||
}
|
||||
|
||||
output({
|
||||
factor: calibration.factor,
|
||||
applied: calibration.applied,
|
||||
sample_count: calibration.sampleCount,
|
||||
confidence: calibration.confidence,
|
||||
clamped: calibration.clamped,
|
||||
min_samples: estimation.MIN_CALIBRATION_SAMPLES,
|
||||
written,
|
||||
write_error: writeError,
|
||||
}, raw);
|
||||
}
|
||||
|
||||
/**
|
||||
* `estimate-calibration` — report the current correction factor and the
|
||||
* history behind it.
|
||||
|
||||
@@ -56,6 +56,19 @@ export interface PhaseEstimate {
|
||||
tokens: number;
|
||||
tasks: number;
|
||||
confidence: Confidence;
|
||||
/**
|
||||
* The planner's UNCALIBRATED projection, before the correction factor was
|
||||
* applied. Optional for backward compatibility with plans written before
|
||||
* #2632.
|
||||
*
|
||||
* Calibration MUST measure actual/raw, not actual/calibrated. Measuring
|
||||
* against the already-corrected figure makes the loop self-defeating: once
|
||||
* the correction works, the observed ratio approaches 1, which drags the
|
||||
* median back toward 1, which un-corrects the next estimate. Simulated over
|
||||
* 10 phases with a true 2x underestimate, that oscillates and settles at
|
||||
* ~1.41 instead of converging on 2.0.
|
||||
*/
|
||||
rawTokens?: number;
|
||||
}
|
||||
|
||||
export interface PhaseActuals {
|
||||
@@ -230,6 +243,46 @@ export function applyCalibration(rawTokens: unknown, factor: unknown): number {
|
||||
return Math.min(Number.MAX_SAFE_INTEGER, Math.max(1, scaled));
|
||||
}
|
||||
|
||||
/**
|
||||
* Extract a two-space-indented scalar block (`estimate:` / `actuals:`) out of a
|
||||
* document's leading YAML frontmatter.
|
||||
*
|
||||
* Hand-rolled because gsd-core ships no external dependencies (CONTRIBUTING.md
|
||||
* "No external dependencies in core") — js-yaml is a devDependency and is not
|
||||
* available at runtime. Scope is deliberately narrow: the leading `---` block
|
||||
* only, so a `estimate:` line inside a fenced code block in the body cannot be
|
||||
* mistaken for frontmatter (the DEFECT.FRONTMATTER-SCALAR-BROAD-GREP class).
|
||||
*
|
||||
* Numeric-looking values are returned as numbers so parseEstimate/parseActuals
|
||||
* see the types they validate; everything else stays a string.
|
||||
*/
|
||||
export function extractFrontmatterBlock(text: unknown, key: string): Record<string, unknown> | null {
|
||||
if (typeof text !== 'string') return null;
|
||||
|
||||
// Anchor at byte 0 — CRLF-tolerant.
|
||||
const fm = /^---\r?\n([\s\S]*?)\r?\n---\r?(?:\n|$)/.exec(text);
|
||||
if (fm === null) return null;
|
||||
|
||||
const lines = fm[1].split(/\r?\n/);
|
||||
const startIdx = lines.findIndex((l) => l === `${key}:` || l.startsWith(`${key}:`));
|
||||
if (startIdx === -1) return null;
|
||||
|
||||
const out: Record<string, unknown> = Object.create(null) as Record<string, unknown>;
|
||||
for (let i = startIdx + 1; i < lines.length; i += 1) {
|
||||
const line = lines[i];
|
||||
if (!/^\s/.test(line)) break; // dedent ends the block
|
||||
const m = /^\s+([A-Za-z_][\w-]*):\s*(.*)$/.exec(line);
|
||||
if (m === null) continue;
|
||||
const rawValue = m[2].replace(/\s+#.*$/, '').trim();
|
||||
if (rawValue === '') continue;
|
||||
const asNumber = Number(rawValue);
|
||||
out[m[1]] = /^-?\d+(?:\.\d+)?$/.test(rawValue) && Number.isFinite(asNumber)
|
||||
? asNumber
|
||||
: rawValue.replace(/^['"]|['"]$/g, '');
|
||||
}
|
||||
return Object.keys(out).length > 0 ? { ...out } : null;
|
||||
}
|
||||
|
||||
/** Pull the `estimate:` mapping out of an already-parsed frontmatter object. */
|
||||
function estimateBlockOf(input: unknown): unknown {
|
||||
if (input === null || typeof input !== 'object') return null;
|
||||
@@ -256,7 +309,10 @@ export function parseEstimate(input: unknown): PhaseEstimate | null {
|
||||
|
||||
if (!isPositiveInt(tokens) || !isPositiveInt(tasks) || !isConfidence(confidence)) return null;
|
||||
|
||||
return { tokens, tasks, confidence };
|
||||
const rawTokens = record['raw_tokens'];
|
||||
return isPositiveInt(rawTokens)
|
||||
? { tokens, tasks, confidence, rawTokens }
|
||||
: { tokens, tasks, confidence };
|
||||
}
|
||||
|
||||
/** Pull the `actuals:` mapping out of an already-parsed frontmatter object. */
|
||||
@@ -292,12 +348,22 @@ export function parseActuals(input: unknown): PhaseActuals | null {
|
||||
* property test pins.
|
||||
*/
|
||||
export function renderEstimate(estimate: PhaseEstimate): string {
|
||||
return [
|
||||
const lines = [
|
||||
'estimate:',
|
||||
` tokens: ${estimate.tokens}`,
|
||||
` tasks: ${estimate.tasks}`,
|
||||
` confidence: ${estimate.confidence}`,
|
||||
].join('\n');
|
||||
];
|
||||
if (isPositiveInt(estimate.rawTokens)) lines.push(` raw_tokens: ${estimate.rawTokens}`);
|
||||
lines.push(` tasks: ${estimate.tasks}`, ` confidence: ${estimate.confidence}`);
|
||||
return lines.join('\n');
|
||||
}
|
||||
|
||||
/**
|
||||
* The figure calibration must measure against: the uncalibrated projection when
|
||||
* the plan recorded one, else the stored value (pre-#2632 plans, where the two
|
||||
* were the same because no factor had yet been applied).
|
||||
*/
|
||||
export function calibrationBasis(estimate: PhaseEstimate): number {
|
||||
return isPositiveInt(estimate.rawTokens) ? estimate.rawTokens : estimate.tokens;
|
||||
}
|
||||
|
||||
/** Render an actuals block for SUMMARY.md frontmatter. Inverse of parseActuals. */
|
||||
|
||||
@@ -14,7 +14,7 @@
|
||||
"gsd-domain-researcher.md": 7032,
|
||||
"gsd-eval-auditor.md": 12496,
|
||||
"gsd-eval-planner.md": 7008,
|
||||
"gsd-executor.md": 47955,
|
||||
"gsd-executor.md": 48596,
|
||||
"gsd-framework-selector.md": 6778,
|
||||
"gsd-integration-checker.md": 15238,
|
||||
"gsd-intel-updater.md": 18166,
|
||||
@@ -23,7 +23,7 @@
|
||||
"gsd-pattern-mapper.md": 12487,
|
||||
"gsd-phase-researcher.md": 40866,
|
||||
"gsd-plan-checker.md": 46363,
|
||||
"gsd-planner.md": 49251,
|
||||
"gsd-planner.md": 49311,
|
||||
"gsd-project-researcher.md": 22242,
|
||||
"gsd-research-synthesizer.md": 13847,
|
||||
"gsd-roadmapper.md": 22273,
|
||||
|
||||
365
tests/estimate-calibrate.test.cjs
Normal file
365
tests/estimate-calibrate.test.cjs
Normal file
@@ -0,0 +1,365 @@
|
||||
/**
|
||||
* estimate-calibrate — build the calibration document from completed phases.
|
||||
*
|
||||
* Epic #1952 Phase 3 (#2632). Design lock: docs/adr/2629-phase-effort-estimation-calibration.md.
|
||||
*
|
||||
* This is the verb that makes AC4 real. Phase 1 shipped the calibration MATH;
|
||||
* Phase 2 made the planner emit an estimate. Neither closes the loop, because
|
||||
* nothing pairs a plan's `estimate` with its summary's `actuals` and writes the
|
||||
* result. Leaving that to agent prose would make "estimates improve over time"
|
||||
* unverifiable — so the pairing and the write are deterministic here, and
|
||||
* extract-learnings just invokes them.
|
||||
*
|
||||
* The headline test is `a consistently-underestimated project produces an
|
||||
* upward correction`: that is epic acceptance criterion AC4 stated as an
|
||||
* executable claim.
|
||||
*/
|
||||
|
||||
const { describe, test } = require('node:test');
|
||||
const assert = require('node:assert/strict');
|
||||
const fs = require('node:fs');
|
||||
const path = require('node:path');
|
||||
|
||||
const { createTempProject, cleanup, runGsdTools } = require('./helpers.cjs');
|
||||
const est = require('../gsd-core/bin/lib/phase-estimation.cjs');
|
||||
|
||||
/** Write a phase dir containing a PLAN with an estimate and a SUMMARY with actuals. */
|
||||
function writePhase(tmpDir, phaseDir, { estTokens, actTokens, tasks = 3, commits = 4 }) {
|
||||
const dir = path.join(tmpDir, '.planning', 'phases', phaseDir);
|
||||
fs.mkdirSync(dir, { recursive: true });
|
||||
if (estTokens !== null) {
|
||||
fs.writeFileSync(path.join(dir, '01-PLAN.md'), [
|
||||
'---',
|
||||
'phase: ' + phaseDir,
|
||||
'plan: 01',
|
||||
'estimate:',
|
||||
` tokens: ${estTokens}`,
|
||||
` tasks: ${tasks}`,
|
||||
' confidence: low',
|
||||
'must_haves:',
|
||||
' truths: []',
|
||||
'---',
|
||||
'<objective>x</objective>',
|
||||
'',
|
||||
].join('\n'));
|
||||
}
|
||||
if (actTokens !== null) {
|
||||
fs.writeFileSync(path.join(dir, '01-SUMMARY.md'), [
|
||||
'---',
|
||||
'phase: ' + phaseDir,
|
||||
'plan: 01',
|
||||
'actuals:',
|
||||
` tokens: ${actTokens}`,
|
||||
` tasks: ${tasks}`,
|
||||
` commits: ${commits}`,
|
||||
'---',
|
||||
'## What shipped',
|
||||
'',
|
||||
].join('\n'));
|
||||
}
|
||||
return dir;
|
||||
}
|
||||
|
||||
describe('estimate-calibrate', () => {
|
||||
test('AC4: a consistently-underestimated project produces an upward correction', (t) => {
|
||||
const tmpDir = createTempProject();
|
||||
t.after(() => cleanup(tmpDir));
|
||||
|
||||
// Three phases that each cost ~2x their estimate.
|
||||
writePhase(tmpDir, '01-alpha', { estTokens: 50000, actTokens: 98000 });
|
||||
writePhase(tmpDir, '02-beta', { estTokens: 60000, actTokens: 121000 });
|
||||
writePhase(tmpDir, '03-gamma', { estTokens: 40000, actTokens: 82000 });
|
||||
|
||||
const r = runGsdTools('query estimate-calibrate', tmpDir);
|
||||
assert.ok(r.success, `estimate-calibrate should succeed: ${r.error}`);
|
||||
|
||||
const out = JSON.parse(r.output);
|
||||
assert.equal(out.sample_count, 3, 'all three phases pair up');
|
||||
assert.equal(out.applied, true);
|
||||
assert.ok(out.factor > 1, `expected an upward correction, got ${out.factor}`);
|
||||
|
||||
// The document must be persisted where estimate-calibration reads it.
|
||||
const docPath = path.join(tmpDir, '.planning', 'estimation-calibration.json');
|
||||
assert.ok(fs.existsSync(docPath), 'calibration document must be written');
|
||||
assert.deepEqual(
|
||||
est.parseCalibrationDocument(fs.readFileSync(docPath, 'utf8')).length, 3,
|
||||
'persisted document must carry all three samples',
|
||||
);
|
||||
|
||||
// And the read verb must now agree — this is the loop actually closing.
|
||||
const readBack = JSON.parse(runGsdTools('query estimate-calibration', tmpDir).output);
|
||||
assert.equal(readBack.factor, out.factor, 'estimate-calibration must see what estimate-calibrate wrote');
|
||||
assert.equal(readBack.applied, true);
|
||||
|
||||
// A subsequent estimate is therefore larger than the raw projection.
|
||||
const check = JSON.parse(runGsdTools('query estimate-check --tokens 50000', tmpDir).output);
|
||||
assert.ok(check.calibrated_tokens > 50000,
|
||||
`a later estimate must be corrected upward, got ${check.calibrated_tokens}`);
|
||||
});
|
||||
|
||||
test('a consistently-overestimated project produces a downward correction', (t) => {
|
||||
const tmpDir = createTempProject();
|
||||
t.after(() => cleanup(tmpDir));
|
||||
writePhase(tmpDir, '01-a', { estTokens: 100000, actTokens: 60000 });
|
||||
writePhase(tmpDir, '02-b', { estTokens: 80000, actTokens: 48000 });
|
||||
writePhase(tmpDir, '03-c', { estTokens: 90000, actTokens: 54000 });
|
||||
|
||||
const out = JSON.parse(runGsdTools('query estimate-calibrate', tmpDir).output);
|
||||
assert.ok(out.factor < 1, `expected a downward correction, got ${out.factor}`);
|
||||
});
|
||||
|
||||
test('boundary: inert below the minimum sample count, applied at it', (t) => {
|
||||
const tmpDir = createTempProject();
|
||||
t.after(() => cleanup(tmpDir));
|
||||
|
||||
writePhase(tmpDir, '01-a', { estTokens: 100, actTokens: 200 });
|
||||
writePhase(tmpDir, '02-b', { estTokens: 100, actTokens: 200 });
|
||||
let out = JSON.parse(runGsdTools('query estimate-calibrate', tmpDir).output);
|
||||
assert.equal(out.sample_count, 2);
|
||||
assert.equal(out.applied, false, '2 samples must not apply a correction');
|
||||
assert.equal(out.factor, 1);
|
||||
|
||||
writePhase(tmpDir, '03-c', { estTokens: 100, actTokens: 200 });
|
||||
out = JSON.parse(runGsdTools('query estimate-calibrate', tmpDir).output);
|
||||
assert.equal(out.sample_count, 3);
|
||||
assert.equal(out.applied, true, '3 samples must apply');
|
||||
assert.equal(out.factor, 2);
|
||||
});
|
||||
|
||||
test('phases missing either side are skipped, not guessed', (t) => {
|
||||
const tmpDir = createTempProject();
|
||||
t.after(() => cleanup(tmpDir));
|
||||
|
||||
writePhase(tmpDir, '01-paired', { estTokens: 100, actTokens: 200 });
|
||||
writePhase(tmpDir, '02-plan-only', { estTokens: 100, actTokens: null });
|
||||
writePhase(tmpDir, '03-summary-only', { estTokens: null, actTokens: 200 });
|
||||
|
||||
const out = JSON.parse(runGsdTools('query estimate-calibrate', tmpDir).output);
|
||||
assert.equal(out.sample_count, 1, 'only the fully-paired phase counts');
|
||||
});
|
||||
|
||||
test('a phase whose PLAN has no estimate block contributes nothing', (t) => {
|
||||
const tmpDir = createTempProject();
|
||||
t.after(() => cleanup(tmpDir));
|
||||
|
||||
const dir = path.join(tmpDir, '.planning', 'phases', '01-noest');
|
||||
fs.mkdirSync(dir, { recursive: true });
|
||||
fs.writeFileSync(path.join(dir, '01-PLAN.md'), '---\nphase: 01-noest\nplan: 01\n---\nbody\n');
|
||||
fs.writeFileSync(path.join(dir, '01-SUMMARY.md'), '---\nphase: 01-noest\nactuals:\n tokens: 5\n tasks: 1\n commits: 1\n---\nx\n');
|
||||
|
||||
const out = JSON.parse(runGsdTools('query estimate-calibrate', tmpDir).output);
|
||||
assert.equal(out.sample_count, 0);
|
||||
assert.equal(out.applied, false);
|
||||
});
|
||||
|
||||
test('no phases at all is a clean no-op, not an error', (t) => {
|
||||
const tmpDir = createTempProject();
|
||||
t.after(() => cleanup(tmpDir));
|
||||
|
||||
const r = runGsdTools('query estimate-calibrate', tmpDir);
|
||||
assert.ok(r.success, 'must not fail on an empty project');
|
||||
const out = JSON.parse(r.output);
|
||||
assert.equal(out.sample_count, 0);
|
||||
assert.equal(out.factor, 1);
|
||||
});
|
||||
|
||||
test('re-running is idempotent — it rebuilds, never appends duplicates', (t) => {
|
||||
const tmpDir = createTempProject();
|
||||
t.after(() => cleanup(tmpDir));
|
||||
writePhase(tmpDir, '01-a', { estTokens: 100, actTokens: 200 });
|
||||
writePhase(tmpDir, '02-b', { estTokens: 100, actTokens: 200 });
|
||||
writePhase(tmpDir, '03-c', { estTokens: 100, actTokens: 200 });
|
||||
|
||||
const first = JSON.parse(runGsdTools('query estimate-calibrate', tmpDir).output);
|
||||
const second = JSON.parse(runGsdTools('query estimate-calibrate', tmpDir).output);
|
||||
assert.deepEqual(second, first, 'a second run must produce an identical result');
|
||||
|
||||
const doc = est.parseCalibrationDocument(
|
||||
fs.readFileSync(path.join(tmpDir, '.planning', 'estimation-calibration.json'), 'utf8'),
|
||||
);
|
||||
assert.equal(doc.length, 3, 'samples must not accumulate across runs');
|
||||
});
|
||||
|
||||
test('a corrupt pre-existing document is replaced, not merged', (t) => {
|
||||
const tmpDir = createTempProject();
|
||||
t.after(() => cleanup(tmpDir));
|
||||
fs.writeFileSync(path.join(tmpDir, '.planning', 'estimation-calibration.json'), '{ not json');
|
||||
writePhase(tmpDir, '01-a', { estTokens: 100, actTokens: 200 });
|
||||
|
||||
const r = runGsdTools('query estimate-calibrate', tmpDir);
|
||||
assert.ok(r.success, 'a corrupt prior document must not fail the rebuild');
|
||||
const doc = est.parseCalibrationDocument(
|
||||
fs.readFileSync(path.join(tmpDir, '.planning', 'estimation-calibration.json'), 'utf8'),
|
||||
);
|
||||
assert.equal(doc.length, 1);
|
||||
});
|
||||
|
||||
test('the written document round-trips through the parser', (t) => {
|
||||
const tmpDir = createTempProject();
|
||||
t.after(() => cleanup(tmpDir));
|
||||
writePhase(tmpDir, '01-a', { estTokens: 12345, actTokens: 23456 });
|
||||
|
||||
runGsdTools('query estimate-calibrate', tmpDir);
|
||||
const raw = fs.readFileSync(path.join(tmpDir, '.planning', 'estimation-calibration.json'), 'utf8');
|
||||
const parsed = est.parseCalibrationDocument(raw);
|
||||
assert.deepEqual(parsed, [{ estimateTokens: 12345, actualTokens: 23456 }]);
|
||||
assert.equal(JSON.parse(raw).schema_version, est.CALIBRATION_SCHEMA_VERSION,
|
||||
'must stamp the current schema version so a future reader can refuse it');
|
||||
});
|
||||
});
|
||||
|
||||
// ─── convergence guard (#2632) ─────────────────────────────────────────────
|
||||
|
||||
describe('calibration converges instead of oscillating', () => {
|
||||
// The loop must measure actual/RAW, not actual/calibrated. Measuring against
|
||||
// the already-corrected figure is self-defeating: once the correction works
|
||||
// the observed ratio approaches 1, dragging the median back toward 1, which
|
||||
// un-corrects the next estimate. This test pins convergence over enough
|
||||
// phases for that oscillation to show up — it fails at ~1.41 if the basis
|
||||
// regresses to the calibrated value.
|
||||
const RAW = 50000;
|
||||
const TRUE_COST = 100000; // the planner is consistently 2x low
|
||||
|
||||
const simulate = (useRawBasis) => {
|
||||
const samples = [];
|
||||
for (let phase = 0; phase < 10; phase += 1) {
|
||||
const cal = est.computeCalibration(samples);
|
||||
const emitted = est.applyCalibration(RAW, cal.factor);
|
||||
const estimate = { tokens: emitted, rawTokens: RAW, tasks: 3, confidence: cal.confidence };
|
||||
samples.push({
|
||||
estimateTokens: useRawBasis ? est.calibrationBasis(estimate) : estimate.tokens,
|
||||
actualTokens: TRUE_COST,
|
||||
});
|
||||
}
|
||||
return est.computeCalibration(samples).factor;
|
||||
};
|
||||
|
||||
test('measuring against the raw projection converges on the true ratio', () => {
|
||||
assert.ok(Math.abs(simulate(true) - 2) < 1e-9,
|
||||
`expected convergence on 2.0, got ${simulate(true)}`);
|
||||
});
|
||||
|
||||
test('measuring against the calibrated figure does NOT converge', () => {
|
||||
// Negative proof that the basis choice is load-bearing, not incidental.
|
||||
assert.ok(simulate(false) < 1.9,
|
||||
'if this passes at ~2.0 the two bases are equivalent and this guard is vacuous');
|
||||
});
|
||||
|
||||
test('calibrationBasis prefers raw_tokens and falls back for older plans', () => {
|
||||
assert.equal(est.calibrationBasis({ tokens: 100000, rawTokens: 50000, tasks: 3, confidence: 'med' }), 50000);
|
||||
assert.equal(est.calibrationBasis({ tokens: 60000, tasks: 3, confidence: 'low' }), 60000,
|
||||
'a pre-#2632 plan with no raw_tokens must still contribute a sample');
|
||||
});
|
||||
|
||||
test('estimate-calibrate uses raw_tokens from the plan when present', (t) => {
|
||||
const tmpDir = createTempProject();
|
||||
t.after(() => cleanup(tmpDir));
|
||||
|
||||
// tokens=100000 (calibrated) but raw_tokens=50000; actual=100000.
|
||||
// Ratio must be 100000/50000 = 2, NOT 100000/100000 = 1.
|
||||
for (const phase of ['01-a', '02-b', '03-c']) {
|
||||
const dir = path.join(tmpDir, '.planning', 'phases', phase);
|
||||
fs.mkdirSync(dir, { recursive: true });
|
||||
fs.writeFileSync(path.join(dir, '01-PLAN.md'),
|
||||
`---\nphase: ${phase}\nestimate:\n tokens: 100000\n raw_tokens: 50000\n tasks: 3\n confidence: med\nmust_haves:\n---\nx\n`);
|
||||
fs.writeFileSync(path.join(dir, '01-SUMMARY.md'),
|
||||
`---\nphase: ${phase}\nactuals:\n tokens: 100000\n tasks: 3\n commits: 5\n---\nx\n`);
|
||||
}
|
||||
|
||||
const out = JSON.parse(runGsdTools('query estimate-calibrate', tmpDir).output);
|
||||
assert.equal(out.sample_count, 3);
|
||||
assert.equal(out.factor, 2,
|
||||
'ratio must be actual/raw (2.0), not actual/calibrated (1.0)');
|
||||
});
|
||||
});
|
||||
|
||||
// ─── multi-plan pairing (#2632 review BLOCKER) ─────────────────────────────
|
||||
|
||||
describe('multi-plan phases pair per plan, not per phase', () => {
|
||||
// A phase routinely holds several plans (`<NN>-<PP>-PLAN.md`, one per plan —
|
||||
// docs/reference/planning-artifacts.md). An earlier implementation took the
|
||||
// first PLAN carrying an estimate and the first SUMMARY carrying actuals
|
||||
// INDEPENDENTLY, which cross-paired one plan's projection with another plan's
|
||||
// cost and discarded every later plan. The whole suite passed because its
|
||||
// helper only ever wrote `01-PLAN.md`.
|
||||
|
||||
/** Write one plan/summary pair inside a phase, using the real `<NN>-<PP>` naming. */
|
||||
const writePlan = (tmpDir, phase, pp, { estTokens, actTokens }) => {
|
||||
const dir = path.join(tmpDir, '.planning', 'phases', phase);
|
||||
fs.mkdirSync(dir, { recursive: true });
|
||||
const nn = phase.slice(0, 2);
|
||||
if (estTokens !== null) {
|
||||
fs.writeFileSync(path.join(dir, `${nn}-${pp}-PLAN.md`),
|
||||
`---\nphase: ${phase}\nplan: ${pp}\nestimate:\n tokens: ${estTokens}\n`
|
||||
+ ` raw_tokens: ${estTokens}\n tasks: 3\n confidence: low\nmust_haves:\n---\nx\n`);
|
||||
} else {
|
||||
fs.writeFileSync(path.join(dir, `${nn}-${pp}-PLAN.md`), `---\nphase: ${phase}\nplan: ${pp}\n---\nx\n`);
|
||||
}
|
||||
fs.writeFileSync(path.join(dir, `${nn}-${pp}-SUMMARY.md`),
|
||||
`---\nphase: ${phase}\nplan: ${pp}\nactuals:\n tokens: ${actTokens}\n tasks: 3\n commits: 4\n---\nx\n`);
|
||||
};
|
||||
|
||||
test('never cross-pairs one plan\'s estimate with another plan\'s actuals', (t) => {
|
||||
const tmpDir = createTempProject();
|
||||
t.after(() => cleanup(tmpDir));
|
||||
|
||||
// Plan 01 has NO estimate but cheap actuals; plan 02 has both (true 2.5x).
|
||||
writePlan(tmpDir, '04-multi', '01', { estTokens: null, actTokens: 30000 });
|
||||
writePlan(tmpDir, '04-multi', '02', { estTokens: 80000, actTokens: 200000 });
|
||||
|
||||
runGsdTools('query estimate-calibrate', tmpDir);
|
||||
const doc = est.parseCalibrationDocument(
|
||||
fs.readFileSync(path.join(tmpDir, '.planning', 'estimation-calibration.json'), 'utf8'),
|
||||
);
|
||||
|
||||
assert.deepEqual(doc, [{ estimateTokens: 80000, actualTokens: 200000 }],
|
||||
'plan 02\'s estimate must pair with plan 02\'s actuals — cross-pairing fabricates a sample '
|
||||
+ 'and throws away the real signal');
|
||||
});
|
||||
|
||||
test('counts every correctly-paired plan in a multi-plan phase', (t) => {
|
||||
const tmpDir = createTempProject();
|
||||
t.after(() => cleanup(tmpDir));
|
||||
|
||||
// Three plans in ONE phase, each cleanly 2x.
|
||||
writePlan(tmpDir, '05-wave', '01', { estTokens: 40000, actTokens: 80000 });
|
||||
writePlan(tmpDir, '05-wave', '02', { estTokens: 50000, actTokens: 100000 });
|
||||
writePlan(tmpDir, '05-wave', '03', { estTokens: 60000, actTokens: 120000 });
|
||||
|
||||
const out = JSON.parse(runGsdTools('query estimate-calibrate', tmpDir).output);
|
||||
assert.equal(out.sample_count, 3, 'all three plans must contribute — not just the first');
|
||||
assert.equal(out.factor, 2);
|
||||
assert.equal(out.applied, true, 'three samples in one phase must reach the minimum');
|
||||
});
|
||||
|
||||
test('a plan with no matching summary contributes nothing', (t) => {
|
||||
const tmpDir = createTempProject();
|
||||
t.after(() => cleanup(tmpDir));
|
||||
|
||||
const dir = path.join(tmpDir, '.planning', 'phases', '06-partial');
|
||||
fs.mkdirSync(dir, { recursive: true });
|
||||
// 06-01 pairs; 06-02 is a plan with no summary (mid-execution).
|
||||
fs.writeFileSync(path.join(dir, '06-01-PLAN.md'),
|
||||
'---\nphase: 06-partial\nestimate:\n tokens: 100\n raw_tokens: 100\n tasks: 1\n confidence: low\nmust_haves:\n---\nx\n');
|
||||
fs.writeFileSync(path.join(dir, '06-01-SUMMARY.md'),
|
||||
'---\nphase: 06-partial\nactuals:\n tokens: 200\n tasks: 1\n commits: 1\n---\nx\n');
|
||||
fs.writeFileSync(path.join(dir, '06-02-PLAN.md'),
|
||||
'---\nphase: 06-partial\nestimate:\n tokens: 999999\n raw_tokens: 999999\n tasks: 1\n confidence: low\nmust_haves:\n---\nx\n');
|
||||
|
||||
const out = JSON.parse(runGsdTools('query estimate-calibrate', tmpDir).output);
|
||||
assert.equal(out.sample_count, 1, 'an in-flight plan must not contribute a half-sample');
|
||||
});
|
||||
|
||||
test('samples accumulate across BOTH plans and phases', (t) => {
|
||||
const tmpDir = createTempProject();
|
||||
t.after(() => cleanup(tmpDir));
|
||||
|
||||
writePlan(tmpDir, '01-a', '01', { estTokens: 100, actTokens: 200 });
|
||||
writePlan(tmpDir, '01-a', '02', { estTokens: 100, actTokens: 200 });
|
||||
writePlan(tmpDir, '02-b', '01', { estTokens: 100, actTokens: 200 });
|
||||
|
||||
const out = JSON.parse(runGsdTools('query estimate-calibrate', tmpDir).output);
|
||||
assert.equal(out.sample_count, 3, 'two plans in phase 1 plus one in phase 2');
|
||||
assert.equal(out.applied, true);
|
||||
});
|
||||
});
|
||||
146
tests/estimate-loop-convergence.test.cjs
Normal file
146
tests/estimate-loop-convergence.test.cjs
Normal file
@@ -0,0 +1,146 @@
|
||||
/**
|
||||
* Closed-loop convergence for phase-effort estimation.
|
||||
*
|
||||
* Epic #1952. Design lock: docs/adr/2629-phase-effort-estimation-calibration.md.
|
||||
*
|
||||
* WHY THIS FILE EXISTS
|
||||
* ────────────────────
|
||||
* Estimation is a feedback control loop: the correction derived from past
|
||||
* phases feeds back into the next estimate. Two real defects shipped past a
|
||||
* green suite of ~26,800 step-wise tests during this epic, because BOTH are
|
||||
* properties of the loop over time rather than of any single call:
|
||||
*
|
||||
* 1. Calibration applied twice (#2631 review). The planner emitted an
|
||||
* already-calibrated figure and `estimate-check` re-applied the factor, so
|
||||
* the effective correction was factor². Every unit test still passed —
|
||||
* each function was individually correct; the COMPOSITION was not.
|
||||
*
|
||||
* 2. Non-convergence (#2632). Calibration measured actual/calibrated instead
|
||||
* of actual/raw, so once the correction worked the observed ratio
|
||||
* approached 1, dragging the median back down. Simulated over 10 phases
|
||||
* the factor oscillated and settled near 1.41 instead of 2.0. Every
|
||||
* boundary fixture, property test and round-trip still passed.
|
||||
*
|
||||
* Neither is visible to a test that asserts "given X, return Y". Both are
|
||||
* visible here, because this drives the REAL verbs through many iterations and
|
||||
* asserts on the TRAJECTORY of the user-visible number.
|
||||
*
|
||||
* The rule this encodes (CONTEXT.md RULESET.TESTS.feedback-loop-convergence):
|
||||
* when a feature's output feeds back into its own input, a step-wise test is
|
||||
* not sufficient evidence of correctness. Simulate the loop and assert it
|
||||
* converges, stays bounded, and lands on the truth.
|
||||
*/
|
||||
|
||||
const { describe, test } = require('node:test');
|
||||
const assert = require('node:assert/strict');
|
||||
const fs = require('node:fs');
|
||||
const path = require('node:path');
|
||||
|
||||
const { createTempProject, cleanup, runGsdTools } = require('./helpers.cjs');
|
||||
|
||||
const RAW_PROJECTION = 50000; // what the planner would say with no history
|
||||
const TRUE_COST = 100000; // reality: consistently 2x the raw projection
|
||||
const TRUE_RATIO = TRUE_COST / RAW_PROJECTION;
|
||||
|
||||
/** Drive one full plan→execute→calibrate cycle and return what the user sees. */
|
||||
function runPhase(tmpDir, phaseIndex) {
|
||||
const factorRaw = runGsdTools('query estimate-calibration --pick factor --raw', tmpDir).output;
|
||||
const factor = Number(String(factorRaw).trim()) || 1;
|
||||
|
||||
// The planner emits tokens = raw x factor, and records the raw projection.
|
||||
const emitted = Math.max(1, Math.round(RAW_PROJECTION * factor));
|
||||
|
||||
const dir = path.join(tmpDir, '.planning', 'phases', `${String(phaseIndex).padStart(2, '0')}-p`);
|
||||
fs.mkdirSync(dir, { recursive: true });
|
||||
fs.writeFileSync(path.join(dir, '01-PLAN.md'),
|
||||
`---\nphase: p\nestimate:\n tokens: ${emitted}\n raw_tokens: ${RAW_PROJECTION}\n`
|
||||
+ ` tasks: 3\n confidence: low\nmust_haves:\n---\nx\n`);
|
||||
fs.writeFileSync(path.join(dir, '01-SUMMARY.md'),
|
||||
`---\nphase: p\nactuals:\n tokens: ${TRUE_COST}\n tasks: 3\n commits: 5\n---\nx\n`);
|
||||
|
||||
runGsdTools('query estimate-calibrate', tmpDir);
|
||||
|
||||
// What the checker actually compares against the budget for this plan.
|
||||
const check = JSON.parse(
|
||||
runGsdTools(`query estimate-check --tokens ${emitted} --calibrated`, tmpDir).output,
|
||||
);
|
||||
return { factor, emitted, userSees: check.calibrated_tokens };
|
||||
}
|
||||
|
||||
describe('estimation feedback loop', () => {
|
||||
test('converges on the true cost and stays there', (t) => {
|
||||
const tmpDir = createTempProject();
|
||||
t.after(() => cleanup(tmpDir));
|
||||
|
||||
const history = [];
|
||||
for (let i = 1; i <= 8; i += 1) history.push(runPhase(tmpDir, i));
|
||||
|
||||
// Early phases have no history, so no correction is applied yet.
|
||||
assert.equal(history[0].factor, 1, 'phase 1 has no history');
|
||||
assert.equal(history[0].emitted, RAW_PROJECTION);
|
||||
|
||||
// Once enough samples exist the correction must reach the TRUE ratio…
|
||||
const settled = history.slice(4);
|
||||
for (const step of settled) {
|
||||
assert.ok(Math.abs(step.factor - TRUE_RATIO) < 1e-9,
|
||||
`factor drifted to ${step.factor}; expected ${TRUE_RATIO}. `
|
||||
+ 'A factor that wanders means calibration is measuring against its own output.');
|
||||
assert.equal(step.emitted, TRUE_COST,
|
||||
`emitted estimate ${step.emitted} should equal the true cost ${TRUE_COST}`);
|
||||
}
|
||||
|
||||
// …and the number the USER is shown must equal the emitted estimate.
|
||||
// If anything re-applies the factor downstream this reads 2x and fails.
|
||||
for (const step of settled) {
|
||||
assert.equal(step.userSees, step.emitted,
|
||||
`the checker compared ${step.userSees} against the budget but the plan says ${step.emitted} — `
|
||||
+ 'a downstream surface is applying the correction a second time (factor²).');
|
||||
}
|
||||
});
|
||||
|
||||
test('stays bounded under a wildly inconsistent history', (t) => {
|
||||
const tmpDir = createTempProject();
|
||||
t.after(() => cleanup(tmpDir));
|
||||
|
||||
// Alternating 10x over and 10x under: the clamp must hold and the loop
|
||||
// must not run away in either direction.
|
||||
const costs = [500000, 5000, 500000, 5000, 500000, 5000];
|
||||
costs.forEach((cost, i) => {
|
||||
const dir = path.join(tmpDir, '.planning', 'phases', `${String(i + 1).padStart(2, '0')}-p`);
|
||||
fs.mkdirSync(dir, { recursive: true });
|
||||
fs.writeFileSync(path.join(dir, '01-PLAN.md'),
|
||||
`---\nphase: p\nestimate:\n tokens: 50000\n raw_tokens: 50000\n tasks: 3\n confidence: low\nmust_haves:\n---\nx\n`);
|
||||
fs.writeFileSync(path.join(dir, '01-SUMMARY.md'),
|
||||
`---\nphase: p\nactuals:\n tokens: ${cost}\n tasks: 3\n commits: 5\n---\nx\n`);
|
||||
});
|
||||
|
||||
const out = JSON.parse(runGsdTools('query estimate-calibrate', tmpDir).output);
|
||||
assert.ok(out.factor >= 0.5 && out.factor <= 3.0,
|
||||
`factor ${out.factor} escaped the clamp under an adversarial history`);
|
||||
|
||||
const check = JSON.parse(runGsdTools('query estimate-check --tokens 50000', tmpDir).output);
|
||||
assert.ok(check.calibrated_tokens >= 25000 && check.calibrated_tokens <= 150000,
|
||||
`a corrected estimate of ${check.calibrated_tokens} is outside the clamp's reachable range`);
|
||||
});
|
||||
|
||||
test('an all-accurate history leaves estimates unchanged (fixed point)', (t) => {
|
||||
const tmpDir = createTempProject();
|
||||
t.after(() => cleanup(tmpDir));
|
||||
|
||||
// A project whose estimates are already right must not be "corrected".
|
||||
for (let i = 1; i <= 5; i += 1) {
|
||||
const dir = path.join(tmpDir, '.planning', 'phases', `${String(i).padStart(2, '0')}-p`);
|
||||
fs.mkdirSync(dir, { recursive: true });
|
||||
fs.writeFileSync(path.join(dir, '01-PLAN.md'),
|
||||
`---\nphase: p\nestimate:\n tokens: 60000\n raw_tokens: 60000\n tasks: 3\n confidence: low\nmust_haves:\n---\nx\n`);
|
||||
fs.writeFileSync(path.join(dir, '01-SUMMARY.md'),
|
||||
`---\nphase: p\nactuals:\n tokens: 60000\n tasks: 3\n commits: 5\n---\nx\n`);
|
||||
}
|
||||
|
||||
const out = JSON.parse(runGsdTools('query estimate-calibrate', tmpDir).output);
|
||||
assert.equal(out.factor, 1, 'an accurate project must be a fixed point — no correction applied');
|
||||
|
||||
const check = JSON.parse(runGsdTools('query estimate-check --tokens 60000', tmpDir).output);
|
||||
assert.equal(check.calibrated_tokens, 60000, 'an accurate estimate must pass through unchanged');
|
||||
});
|
||||
});
|
||||
@@ -16,7 +16,7 @@
|
||||
"agents/gsd-domain-researcher.md": "1db46cac3f4d9889",
|
||||
"agents/gsd-eval-auditor.md": "1b8391f1aafb067f",
|
||||
"agents/gsd-eval-planner.md": "3d10fd11147f6857",
|
||||
"agents/gsd-executor.md": "041c6d658e8e1002",
|
||||
"agents/gsd-executor.md": "f9bd85ba91a2a042",
|
||||
"agents/gsd-framework-selector.md": "daa62c79619c76bf",
|
||||
"agents/gsd-integration-checker.md": "0643cd2d779b131c",
|
||||
"agents/gsd-intel-updater.md": "26c1f1e028c6346a",
|
||||
@@ -25,7 +25,7 @@
|
||||
"agents/gsd-pattern-mapper.md": "e62ee90d39084802",
|
||||
"agents/gsd-phase-researcher.md": "cff1196c8e8bb4fa",
|
||||
"agents/gsd-plan-checker.md": "893e88036b4ad419",
|
||||
"agents/gsd-planner.md": "8af42f4321c34bc9",
|
||||
"agents/gsd-planner.md": "e916e99dab32a95b",
|
||||
"agents/gsd-project-researcher.md": "85de7f562872ee9b",
|
||||
"agents/gsd-research-synthesizer.md": "18a2e1b30ff7ae3a",
|
||||
"agents/gsd-roadmapper.md": "7a8465ac6d4dd29e",
|
||||
@@ -39,7 +39,7 @@
|
||||
"gsd-core/VERSION": "ef0deccd81a6723c",
|
||||
"gsd-core/bin/check-latest-version.cjs": "e4a224058c8f4d74",
|
||||
"gsd-core/bin/ensure-runtime-build.cjs": "ea841e2865248e74",
|
||||
"gsd-core/bin/gsd-tools.cjs": "b28392bf9a4dc9bb",
|
||||
"gsd-core/bin/gsd-tools.cjs": "974871b2efcd2b7b",
|
||||
"gsd-core/bin/gsd_run": "62d9b647ede212e6",
|
||||
"gsd-core/bin/shared/config-defaults.manifest.json": "3a3581ea768cbe6a",
|
||||
"gsd-core/bin/shared/config-schema.manifest.json": "377dc46be7b56fe8",
|
||||
@@ -204,9 +204,9 @@
|
||||
"gsd-core/templates/spec.md": "8734f0df4df3a34b",
|
||||
"gsd-core/templates/state.md": "a45a134631efe3f9",
|
||||
"gsd-core/templates/summary-complex.md": "a5e40574fd8894dc",
|
||||
"gsd-core/templates/summary-minimal.md": "7d09b5e709e2e67c",
|
||||
"gsd-core/templates/summary-standard.md": "e8d9cf4a8377cdff",
|
||||
"gsd-core/templates/summary.md": "23c40f6503b3ea98",
|
||||
"gsd-core/templates/summary-minimal.md": "d5f40260721e307d",
|
||||
"gsd-core/templates/summary-standard.md": "a4fb6df80f41b545",
|
||||
"gsd-core/templates/summary.md": "85f4d37fcee6852b",
|
||||
"gsd-core/templates/user-profile.md": "52abe2af968e8533",
|
||||
"gsd-core/templates/user-setup.md": "1da2382725db080f",
|
||||
"gsd-core/templates/verification-report.md": "78ab9264ce63ed7e",
|
||||
@@ -257,7 +257,7 @@
|
||||
"gsd-core/workflows/execute-phase/steps/worktree-recovery-policy.md": "be84efbd71e1513e",
|
||||
"gsd-core/workflows/execute-plan.md": "5c6fcb36e16f5bf7",
|
||||
"gsd-core/workflows/explore.md": "965e1c0ede05f40c",
|
||||
"gsd-core/workflows/extract-learnings.md": "167ea7f0e23bf496",
|
||||
"gsd-core/workflows/extract-learnings.md": "82f8b60ab36e4818",
|
||||
"gsd-core/workflows/fast.md": "568e6c3ec00b6e00",
|
||||
"gsd-core/workflows/forensics.md": "b64f0309b8c3fde1",
|
||||
"gsd-core/workflows/graduation.md": "c892887f212c9cff",
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
"agents/gsd-domain-researcher.md": "671c9ea949889c4a",
|
||||
"agents/gsd-eval-auditor.md": "fcaec7b00f94c435",
|
||||
"agents/gsd-eval-planner.md": "a4a5b4b3f7828ba3",
|
||||
"agents/gsd-executor.md": "00d887a16c249765",
|
||||
"agents/gsd-executor.md": "3f03ad10b7251f68",
|
||||
"agents/gsd-framework-selector.md": "4b77eebbe9288d80",
|
||||
"agents/gsd-integration-checker.md": "fa53e2d78be1de74",
|
||||
"agents/gsd-intel-updater.md": "fa40e685d7441ace",
|
||||
@@ -25,7 +25,7 @@
|
||||
"agents/gsd-pattern-mapper.md": "43c6021cf7caabfa",
|
||||
"agents/gsd-phase-researcher.md": "f1f6fd6a3e67c7a8",
|
||||
"agents/gsd-plan-checker.md": "d9aca5f75d649fc0",
|
||||
"agents/gsd-planner.md": "5b018b0a2df93e37",
|
||||
"agents/gsd-planner.md": "5143e54864af6a63",
|
||||
"agents/gsd-project-researcher.md": "4531b7cc8f5e5f7d",
|
||||
"agents/gsd-research-synthesizer.md": "4a4f68e6c75b133a",
|
||||
"agents/gsd-roadmapper.md": "bb2f57695dbab32c",
|
||||
@@ -110,7 +110,7 @@
|
||||
"gsd-core/VERSION": "ef0deccd81a6723c",
|
||||
"gsd-core/bin/check-latest-version.cjs": "e4a224058c8f4d74",
|
||||
"gsd-core/bin/ensure-runtime-build.cjs": "51bc64467ab30f62",
|
||||
"gsd-core/bin/gsd-tools.cjs": "ec98734a021c6157",
|
||||
"gsd-core/bin/gsd-tools.cjs": "0b356a34f3654051",
|
||||
"gsd-core/bin/gsd_run": "62d9b647ede212e6",
|
||||
"gsd-core/bin/shared/config-defaults.manifest.json": "3a3581ea768cbe6a",
|
||||
"gsd-core/bin/shared/config-schema.manifest.json": "377dc46be7b56fe8",
|
||||
@@ -275,9 +275,9 @@
|
||||
"gsd-core/templates/spec.md": "26d55bce940f0288",
|
||||
"gsd-core/templates/state.md": "4d123aa6cea167fe",
|
||||
"gsd-core/templates/summary-complex.md": "a5e40574fd8894dc",
|
||||
"gsd-core/templates/summary-minimal.md": "7d09b5e709e2e67c",
|
||||
"gsd-core/templates/summary-standard.md": "e8d9cf4a8377cdff",
|
||||
"gsd-core/templates/summary.md": "23c40f6503b3ea98",
|
||||
"gsd-core/templates/summary-minimal.md": "d5f40260721e307d",
|
||||
"gsd-core/templates/summary-standard.md": "a4fb6df80f41b545",
|
||||
"gsd-core/templates/summary.md": "85f4d37fcee6852b",
|
||||
"gsd-core/templates/user-profile.md": "20749f23e4c413fc",
|
||||
"gsd-core/templates/user-setup.md": "78b7d718b6e8d67c",
|
||||
"gsd-core/templates/verification-report.md": "dd5faa6254183731",
|
||||
@@ -328,7 +328,7 @@
|
||||
"gsd-core/workflows/execute-phase/steps/worktree-recovery-policy.md": "be84efbd71e1513e",
|
||||
"gsd-core/workflows/execute-plan.md": "334bb2053908a049",
|
||||
"gsd-core/workflows/explore.md": "3f3b4f83e23349bc",
|
||||
"gsd-core/workflows/extract-learnings.md": "b6f01ca3d8f58de4",
|
||||
"gsd-core/workflows/extract-learnings.md": "ab26f2cbb14efef2",
|
||||
"gsd-core/workflows/fast.md": "11f5cd10ae5cc7d3",
|
||||
"gsd-core/workflows/forensics.md": "0d500a3f5ab26913",
|
||||
"gsd-core/workflows/graduation.md": "973dcebcd17e1b10",
|
||||
|
||||
@@ -15,7 +15,7 @@
|
||||
"agents/gsd-domain-researcher.md": "f1e03df842ddfb95",
|
||||
"agents/gsd-eval-auditor.md": "d0f45fff7370bb0b",
|
||||
"agents/gsd-eval-planner.md": "9cc049b82897daa4",
|
||||
"agents/gsd-executor.md": "406dfda62f0f8428",
|
||||
"agents/gsd-executor.md": "c6a3f08a31afc6bf",
|
||||
"agents/gsd-framework-selector.md": "85005d716f9d98f7",
|
||||
"agents/gsd-integration-checker.md": "17a8ee731986564d",
|
||||
"agents/gsd-intel-updater.md": "4953a465db9dadc1",
|
||||
@@ -24,7 +24,7 @@
|
||||
"agents/gsd-pattern-mapper.md": "b45b5e106775bec1",
|
||||
"agents/gsd-phase-researcher.md": "4772d9eada32e8bd",
|
||||
"agents/gsd-plan-checker.md": "b3f510f1257ff383",
|
||||
"agents/gsd-planner.md": "831977f45c361561",
|
||||
"agents/gsd-planner.md": "a22751cc49456236",
|
||||
"agents/gsd-project-researcher.md": "d7f355894519f9fe",
|
||||
"agents/gsd-research-synthesizer.md": "1c738df9932d325a",
|
||||
"agents/gsd-roadmapper.md": "453e9471ad27c7ea",
|
||||
@@ -109,7 +109,7 @@
|
||||
"gsd-core/VERSION": "ef0deccd81a6723c",
|
||||
"gsd-core/bin/check-latest-version.cjs": "e4a224058c8f4d74",
|
||||
"gsd-core/bin/ensure-runtime-build.cjs": "51bc64467ab30f62",
|
||||
"gsd-core/bin/gsd-tools.cjs": "ec98734a021c6157",
|
||||
"gsd-core/bin/gsd-tools.cjs": "0b356a34f3654051",
|
||||
"gsd-core/bin/gsd_run": "62d9b647ede212e6",
|
||||
"gsd-core/bin/shared/config-defaults.manifest.json": "3a3581ea768cbe6a",
|
||||
"gsd-core/bin/shared/config-schema.manifest.json": "377dc46be7b56fe8",
|
||||
@@ -274,9 +274,9 @@
|
||||
"gsd-core/templates/spec.md": "7dc900c355098d8b",
|
||||
"gsd-core/templates/state.md": "73e424b8c70b765c",
|
||||
"gsd-core/templates/summary-complex.md": "a5e40574fd8894dc",
|
||||
"gsd-core/templates/summary-minimal.md": "7d09b5e709e2e67c",
|
||||
"gsd-core/templates/summary-standard.md": "e8d9cf4a8377cdff",
|
||||
"gsd-core/templates/summary.md": "23c40f6503b3ea98",
|
||||
"gsd-core/templates/summary-minimal.md": "d5f40260721e307d",
|
||||
"gsd-core/templates/summary-standard.md": "a4fb6df80f41b545",
|
||||
"gsd-core/templates/summary.md": "85f4d37fcee6852b",
|
||||
"gsd-core/templates/user-profile.md": "20749f23e4c413fc",
|
||||
"gsd-core/templates/user-setup.md": "78b7d718b6e8d67c",
|
||||
"gsd-core/templates/verification-report.md": "dd5faa6254183731",
|
||||
@@ -327,7 +327,7 @@
|
||||
"gsd-core/workflows/execute-phase/steps/worktree-recovery-policy.md": "be84efbd71e1513e",
|
||||
"gsd-core/workflows/execute-plan.md": "724d726833e222ed",
|
||||
"gsd-core/workflows/explore.md": "fabe8e5553de16c0",
|
||||
"gsd-core/workflows/extract-learnings.md": "fd75072c339b58bd",
|
||||
"gsd-core/workflows/extract-learnings.md": "3778273aaba5d477",
|
||||
"gsd-core/workflows/fast.md": "7f7687b920d79b29",
|
||||
"gsd-core/workflows/forensics.md": "857d7b064f4cca21",
|
||||
"gsd-core/workflows/graduation.md": "7a1d9e1327dce4e7",
|
||||
|
||||
14
tests/fixtures/golden-install-parity/claude.json
vendored
14
tests/fixtures/golden-install-parity/claude.json
vendored
@@ -15,7 +15,7 @@
|
||||
"agents/gsd-domain-researcher.md": "5f7d366251b957fe",
|
||||
"agents/gsd-eval-auditor.md": "fea2759beff0a642",
|
||||
"agents/gsd-eval-planner.md": "112f6730f23854e3",
|
||||
"agents/gsd-executor.md": "16391af53f8922bb",
|
||||
"agents/gsd-executor.md": "dc6785301ba81da4",
|
||||
"agents/gsd-framework-selector.md": "c350ee693cb1aa4e",
|
||||
"agents/gsd-integration-checker.md": "c8b4e65dee89c8ea",
|
||||
"agents/gsd-intel-updater.md": "5b41e05f90ce89d9",
|
||||
@@ -24,7 +24,7 @@
|
||||
"agents/gsd-pattern-mapper.md": "b45b5e106775bec1",
|
||||
"agents/gsd-phase-researcher.md": "85217c69c1ed2ac6",
|
||||
"agents/gsd-plan-checker.md": "670e4ad7132a66ca",
|
||||
"agents/gsd-planner.md": "0f5d0199fbce83f8",
|
||||
"agents/gsd-planner.md": "cef4c830e0fa2bd8",
|
||||
"agents/gsd-project-researcher.md": "f468e96f8339d1e0",
|
||||
"agents/gsd-research-synthesizer.md": "7be02e47f4fd901b",
|
||||
"agents/gsd-roadmapper.md": "8a7f1f1256a6aed5",
|
||||
@@ -38,7 +38,7 @@
|
||||
"gsd-core/VERSION": "ef0deccd81a6723c",
|
||||
"gsd-core/bin/check-latest-version.cjs": "e4a224058c8f4d74",
|
||||
"gsd-core/bin/ensure-runtime-build.cjs": "51bc64467ab30f62",
|
||||
"gsd-core/bin/gsd-tools.cjs": "ec98734a021c6157",
|
||||
"gsd-core/bin/gsd-tools.cjs": "0b356a34f3654051",
|
||||
"gsd-core/bin/gsd_run": "62d9b647ede212e6",
|
||||
"gsd-core/bin/shared/config-defaults.manifest.json": "3a3581ea768cbe6a",
|
||||
"gsd-core/bin/shared/config-schema.manifest.json": "377dc46be7b56fe8",
|
||||
@@ -203,9 +203,9 @@
|
||||
"gsd-core/templates/spec.md": "7dc900c355098d8b",
|
||||
"gsd-core/templates/state.md": "73e424b8c70b765c",
|
||||
"gsd-core/templates/summary-complex.md": "a5e40574fd8894dc",
|
||||
"gsd-core/templates/summary-minimal.md": "7d09b5e709e2e67c",
|
||||
"gsd-core/templates/summary-standard.md": "e8d9cf4a8377cdff",
|
||||
"gsd-core/templates/summary.md": "23c40f6503b3ea98",
|
||||
"gsd-core/templates/summary-minimal.md": "d5f40260721e307d",
|
||||
"gsd-core/templates/summary-standard.md": "a4fb6df80f41b545",
|
||||
"gsd-core/templates/summary.md": "85f4d37fcee6852b",
|
||||
"gsd-core/templates/user-profile.md": "20749f23e4c413fc",
|
||||
"gsd-core/templates/user-setup.md": "78b7d718b6e8d67c",
|
||||
"gsd-core/templates/verification-report.md": "dd5faa6254183731",
|
||||
@@ -256,7 +256,7 @@
|
||||
"gsd-core/workflows/execute-phase/steps/worktree-recovery-policy.md": "be84efbd71e1513e",
|
||||
"gsd-core/workflows/execute-plan.md": "da0c2286b1aed11d",
|
||||
"gsd-core/workflows/explore.md": "9348b54b526b8938",
|
||||
"gsd-core/workflows/extract-learnings.md": "d8177b0c13b7e5ee",
|
||||
"gsd-core/workflows/extract-learnings.md": "13929ce8a04013e0",
|
||||
"gsd-core/workflows/fast.md": "41a6568b873aef99",
|
||||
"gsd-core/workflows/forensics.md": "c01da0178fb97b21",
|
||||
"gsd-core/workflows/graduation.md": "973dcebcd17e1b10",
|
||||
|
||||
14
tests/fixtures/golden-install-parity/cline.json
vendored
14
tests/fixtures/golden-install-parity/cline.json
vendored
@@ -19,7 +19,7 @@
|
||||
"agents/gsd-domain-researcher.md": "0fecdaea86466a56",
|
||||
"agents/gsd-eval-auditor.md": "36c44303085df2f8",
|
||||
"agents/gsd-eval-planner.md": "3ddea88a69b4da3f",
|
||||
"agents/gsd-executor.md": "a20e280c9e648f5b",
|
||||
"agents/gsd-executor.md": "eb82990b9b81e39d",
|
||||
"agents/gsd-framework-selector.md": "564669d479433f15",
|
||||
"agents/gsd-integration-checker.md": "1bbbdd3d420b994e",
|
||||
"agents/gsd-intel-updater.md": "42c40fffbc720d0b",
|
||||
@@ -28,7 +28,7 @@
|
||||
"agents/gsd-pattern-mapper.md": "b526065fd2efa19c",
|
||||
"agents/gsd-phase-researcher.md": "c507db2ba66038f4",
|
||||
"agents/gsd-plan-checker.md": "70ccc072a52cc4ce",
|
||||
"agents/gsd-planner.md": "aab8d4d2db4c3d93",
|
||||
"agents/gsd-planner.md": "4aaa7d9fab92a01e",
|
||||
"agents/gsd-project-researcher.md": "049f816c6caa4316",
|
||||
"agents/gsd-research-synthesizer.md": "2f7dcbff50371d4c",
|
||||
"agents/gsd-roadmapper.md": "bbb23d3097911516",
|
||||
@@ -42,7 +42,7 @@
|
||||
"gsd-core/VERSION": "ef0deccd81a6723c",
|
||||
"gsd-core/bin/check-latest-version.cjs": "e4a224058c8f4d74",
|
||||
"gsd-core/bin/ensure-runtime-build.cjs": "476aa24e8c4f03cf",
|
||||
"gsd-core/bin/gsd-tools.cjs": "695c409ab2407247",
|
||||
"gsd-core/bin/gsd-tools.cjs": "50e8f67219cfb620",
|
||||
"gsd-core/bin/gsd_run": "62d9b647ede212e6",
|
||||
"gsd-core/bin/shared/config-defaults.manifest.json": "3a3581ea768cbe6a",
|
||||
"gsd-core/bin/shared/config-schema.manifest.json": "377dc46be7b56fe8",
|
||||
@@ -207,9 +207,9 @@
|
||||
"gsd-core/templates/spec.md": "26d55bce940f0288",
|
||||
"gsd-core/templates/state.md": "4d123aa6cea167fe",
|
||||
"gsd-core/templates/summary-complex.md": "a5e40574fd8894dc",
|
||||
"gsd-core/templates/summary-minimal.md": "7d09b5e709e2e67c",
|
||||
"gsd-core/templates/summary-standard.md": "e8d9cf4a8377cdff",
|
||||
"gsd-core/templates/summary.md": "23c40f6503b3ea98",
|
||||
"gsd-core/templates/summary-minimal.md": "d5f40260721e307d",
|
||||
"gsd-core/templates/summary-standard.md": "a4fb6df80f41b545",
|
||||
"gsd-core/templates/summary.md": "85f4d37fcee6852b",
|
||||
"gsd-core/templates/user-profile.md": "20749f23e4c413fc",
|
||||
"gsd-core/templates/user-setup.md": "78b7d718b6e8d67c",
|
||||
"gsd-core/templates/verification-report.md": "dd5faa6254183731",
|
||||
@@ -260,7 +260,7 @@
|
||||
"gsd-core/workflows/execute-phase/steps/worktree-recovery-policy.md": "be84efbd71e1513e",
|
||||
"gsd-core/workflows/execute-plan.md": "204a0ac94a4bb545",
|
||||
"gsd-core/workflows/explore.md": "db9e1a79dbe88090",
|
||||
"gsd-core/workflows/extract-learnings.md": "6f39375b7dc775f9",
|
||||
"gsd-core/workflows/extract-learnings.md": "9a39a7b2b7592141",
|
||||
"gsd-core/workflows/fast.md": "e4f74a454b6ca5e8",
|
||||
"gsd-core/workflows/forensics.md": "9fc65a8eed5d8bfc",
|
||||
"gsd-core/workflows/graduation.md": "68d83a47e9cfaa7a",
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
"agents/gsd-domain-researcher.md": "1c1a800108a2b225",
|
||||
"agents/gsd-eval-auditor.md": "99012004b14ea602",
|
||||
"agents/gsd-eval-planner.md": "4ebdd7fe9cbb0cfe",
|
||||
"agents/gsd-executor.md": "d9dca78de04bdc1c",
|
||||
"agents/gsd-executor.md": "412ddd97399607a2",
|
||||
"agents/gsd-framework-selector.md": "7726fccc86bfeb50",
|
||||
"agents/gsd-integration-checker.md": "2d8339790bbb2dc3",
|
||||
"agents/gsd-intel-updater.md": "c51339956197cbd3",
|
||||
@@ -25,7 +25,7 @@
|
||||
"agents/gsd-pattern-mapper.md": "92cfa2e6c2a06bf3",
|
||||
"agents/gsd-phase-researcher.md": "6338474da1a5d65e",
|
||||
"agents/gsd-plan-checker.md": "3fdccb7353c69340",
|
||||
"agents/gsd-planner.md": "55445462761df7b3",
|
||||
"agents/gsd-planner.md": "c482d13228f2efd8",
|
||||
"agents/gsd-project-researcher.md": "e43c59f7f1f2f37a",
|
||||
"agents/gsd-research-synthesizer.md": "87955470c3c129b2",
|
||||
"agents/gsd-roadmapper.md": "20b69eff61a7a9fa",
|
||||
@@ -110,7 +110,7 @@
|
||||
"gsd-core/VERSION": "ef0deccd81a6723c",
|
||||
"gsd-core/bin/check-latest-version.cjs": "e4a224058c8f4d74",
|
||||
"gsd-core/bin/ensure-runtime-build.cjs": "51bc64467ab30f62",
|
||||
"gsd-core/bin/gsd-tools.cjs": "ec98734a021c6157",
|
||||
"gsd-core/bin/gsd-tools.cjs": "0b356a34f3654051",
|
||||
"gsd-core/bin/gsd_run": "62d9b647ede212e6",
|
||||
"gsd-core/bin/shared/config-defaults.manifest.json": "3a3581ea768cbe6a",
|
||||
"gsd-core/bin/shared/config-schema.manifest.json": "377dc46be7b56fe8",
|
||||
@@ -275,9 +275,9 @@
|
||||
"gsd-core/templates/spec.md": "26d55bce940f0288",
|
||||
"gsd-core/templates/state.md": "4d123aa6cea167fe",
|
||||
"gsd-core/templates/summary-complex.md": "a5e40574fd8894dc",
|
||||
"gsd-core/templates/summary-minimal.md": "7d09b5e709e2e67c",
|
||||
"gsd-core/templates/summary-standard.md": "e8d9cf4a8377cdff",
|
||||
"gsd-core/templates/summary.md": "23c40f6503b3ea98",
|
||||
"gsd-core/templates/summary-minimal.md": "d5f40260721e307d",
|
||||
"gsd-core/templates/summary-standard.md": "a4fb6df80f41b545",
|
||||
"gsd-core/templates/summary.md": "85f4d37fcee6852b",
|
||||
"gsd-core/templates/user-profile.md": "20749f23e4c413fc",
|
||||
"gsd-core/templates/user-setup.md": "78b7d718b6e8d67c",
|
||||
"gsd-core/templates/verification-report.md": "dd5faa6254183731",
|
||||
@@ -328,7 +328,7 @@
|
||||
"gsd-core/workflows/execute-phase/steps/worktree-recovery-policy.md": "be84efbd71e1513e",
|
||||
"gsd-core/workflows/execute-plan.md": "874689d8678e6186",
|
||||
"gsd-core/workflows/explore.md": "3f3b4f83e23349bc",
|
||||
"gsd-core/workflows/extract-learnings.md": "b6f01ca3d8f58de4",
|
||||
"gsd-core/workflows/extract-learnings.md": "ab26f2cbb14efef2",
|
||||
"gsd-core/workflows/fast.md": "11f5cd10ae5cc7d3",
|
||||
"gsd-core/workflows/forensics.md": "0d500a3f5ab26913",
|
||||
"gsd-core/workflows/graduation.md": "973dcebcd17e1b10",
|
||||
|
||||
18
tests/fixtures/golden-install-parity/codex.json
vendored
18
tests/fixtures/golden-install-parity/codex.json
vendored
@@ -102,8 +102,8 @@
|
||||
"agents/gsd-eval-auditor.toml": "9b81d61b3c5f722d",
|
||||
"agents/gsd-eval-planner.md": "73f2ad2ff2797a51",
|
||||
"agents/gsd-eval-planner.toml": "09468ad1a34ac468",
|
||||
"agents/gsd-executor.md": "697b7ed099fff17d",
|
||||
"agents/gsd-executor.toml": "9a8aa31bbde42448",
|
||||
"agents/gsd-executor.md": "cd4dac78e03debd1",
|
||||
"agents/gsd-executor.toml": "427bb38fc924d3e8",
|
||||
"agents/gsd-framework-selector.md": "ebae32430887d2e0",
|
||||
"agents/gsd-framework-selector.toml": "637e4e021b7ec380",
|
||||
"agents/gsd-integration-checker.md": "9cc875676cf7d741",
|
||||
@@ -120,8 +120,8 @@
|
||||
"agents/gsd-phase-researcher.toml": "44a3d510cd0ce3bd",
|
||||
"agents/gsd-plan-checker.md": "9ba8ea7643f0a7f5",
|
||||
"agents/gsd-plan-checker.toml": "03488397d892ea09",
|
||||
"agents/gsd-planner.md": "88283bc1d8da011e",
|
||||
"agents/gsd-planner.toml": "1b24b3f19b8afecc",
|
||||
"agents/gsd-planner.md": "932266ed67ea0947",
|
||||
"agents/gsd-planner.toml": "8fd81d2367979851",
|
||||
"agents/gsd-project-researcher.md": "959f2e57c3d69ed8",
|
||||
"agents/gsd-project-researcher.toml": "f395e8e8c4baf1ed",
|
||||
"agents/gsd-research-synthesizer.md": "497f85adf53259ef",
|
||||
@@ -145,7 +145,7 @@
|
||||
"gsd-core/VERSION": "ef0deccd81a6723c",
|
||||
"gsd-core/bin/check-latest-version.cjs": "e4a224058c8f4d74",
|
||||
"gsd-core/bin/ensure-runtime-build.cjs": "51bc64467ab30f62",
|
||||
"gsd-core/bin/gsd-tools.cjs": "ec98734a021c6157",
|
||||
"gsd-core/bin/gsd-tools.cjs": "0b356a34f3654051",
|
||||
"gsd-core/bin/gsd_run": "62d9b647ede212e6",
|
||||
"gsd-core/bin/shared/config-defaults.manifest.json": "3a3581ea768cbe6a",
|
||||
"gsd-core/bin/shared/config-schema.manifest.json": "377dc46be7b56fe8",
|
||||
@@ -310,9 +310,9 @@
|
||||
"gsd-core/templates/spec.md": "34cb8124f37c9b14",
|
||||
"gsd-core/templates/state.md": "3bac0c4a26c094f9",
|
||||
"gsd-core/templates/summary-complex.md": "a5e40574fd8894dc",
|
||||
"gsd-core/templates/summary-minimal.md": "7d09b5e709e2e67c",
|
||||
"gsd-core/templates/summary-standard.md": "e8d9cf4a8377cdff",
|
||||
"gsd-core/templates/summary.md": "f612660bfd0a325a",
|
||||
"gsd-core/templates/summary-minimal.md": "d5f40260721e307d",
|
||||
"gsd-core/templates/summary-standard.md": "a4fb6df80f41b545",
|
||||
"gsd-core/templates/summary.md": "c95dfa4653791314",
|
||||
"gsd-core/templates/user-profile.md": "52abe2af968e8533",
|
||||
"gsd-core/templates/user-setup.md": "1da2382725db080f",
|
||||
"gsd-core/templates/verification-report.md": "78ab9264ce63ed7e",
|
||||
@@ -363,7 +363,7 @@
|
||||
"gsd-core/workflows/execute-phase/steps/worktree-recovery-policy.md": "be84efbd71e1513e",
|
||||
"gsd-core/workflows/execute-plan.md": "e4723e1669f7c508",
|
||||
"gsd-core/workflows/explore.md": "d12f68770c65093a",
|
||||
"gsd-core/workflows/extract-learnings.md": "f716aa03fcb5f8da",
|
||||
"gsd-core/workflows/extract-learnings.md": "44efe9756da774f9",
|
||||
"gsd-core/workflows/fast.md": "e4ed60f96a7b3ac8",
|
||||
"gsd-core/workflows/forensics.md": "2e8a01b5b44e65f3",
|
||||
"gsd-core/workflows/graduation.md": "973dcebcd17e1b10",
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
"agents/gsd-domain-researcher.agent.md": "d603239b3e9fe428",
|
||||
"agents/gsd-eval-auditor.agent.md": "3c03009564de55c8",
|
||||
"agents/gsd-eval-planner.agent.md": "14751876fc2b5f16",
|
||||
"agents/gsd-executor.agent.md": "6bf98b78fd75c347",
|
||||
"agents/gsd-executor.agent.md": "d8439a4f44e7e6eb",
|
||||
"agents/gsd-framework-selector.agent.md": "cafeec0b3489be45",
|
||||
"agents/gsd-integration-checker.agent.md": "30439b804927acc7",
|
||||
"agents/gsd-intel-updater.agent.md": "238c1a886f35a25c",
|
||||
@@ -25,7 +25,7 @@
|
||||
"agents/gsd-pattern-mapper.agent.md": "b1f488b0fa6a2395",
|
||||
"agents/gsd-phase-researcher.agent.md": "03cfb510a766fe93",
|
||||
"agents/gsd-plan-checker.agent.md": "0d68eb258b85e24e",
|
||||
"agents/gsd-planner.agent.md": "0c222d93778eb371",
|
||||
"agents/gsd-planner.agent.md": "aaef800d164c3475",
|
||||
"agents/gsd-project-researcher.agent.md": "d73bdbe986ffa8a6",
|
||||
"agents/gsd-research-synthesizer.agent.md": "f03eed4aa89e47c5",
|
||||
"agents/gsd-roadmapper.agent.md": "322048cf8ddcb4e5",
|
||||
@@ -40,7 +40,7 @@
|
||||
"gsd-core/VERSION": "ef0deccd81a6723c",
|
||||
"gsd-core/bin/check-latest-version.cjs": "e4a224058c8f4d74",
|
||||
"gsd-core/bin/ensure-runtime-build.cjs": "ea841e2865248e74",
|
||||
"gsd-core/bin/gsd-tools.cjs": "b28392bf9a4dc9bb",
|
||||
"gsd-core/bin/gsd-tools.cjs": "974871b2efcd2b7b",
|
||||
"gsd-core/bin/gsd_run": "62d9b647ede212e6",
|
||||
"gsd-core/bin/shared/config-defaults.manifest.json": "3a3581ea768cbe6a",
|
||||
"gsd-core/bin/shared/config-schema.manifest.json": "377dc46be7b56fe8",
|
||||
@@ -205,9 +205,9 @@
|
||||
"gsd-core/templates/spec.md": "8734f0df4df3a34b",
|
||||
"gsd-core/templates/state.md": "a45a134631efe3f9",
|
||||
"gsd-core/templates/summary-complex.md": "a5e40574fd8894dc",
|
||||
"gsd-core/templates/summary-minimal.md": "7d09b5e709e2e67c",
|
||||
"gsd-core/templates/summary-standard.md": "e8d9cf4a8377cdff",
|
||||
"gsd-core/templates/summary.md": "23c40f6503b3ea98",
|
||||
"gsd-core/templates/summary-minimal.md": "d5f40260721e307d",
|
||||
"gsd-core/templates/summary-standard.md": "a4fb6df80f41b545",
|
||||
"gsd-core/templates/summary.md": "85f4d37fcee6852b",
|
||||
"gsd-core/templates/user-profile.md": "52abe2af968e8533",
|
||||
"gsd-core/templates/user-setup.md": "1da2382725db080f",
|
||||
"gsd-core/templates/verification-report.md": "78ab9264ce63ed7e",
|
||||
@@ -258,7 +258,7 @@
|
||||
"gsd-core/workflows/execute-phase/steps/worktree-recovery-policy.md": "be84efbd71e1513e",
|
||||
"gsd-core/workflows/execute-plan.md": "c82c959f78a1917d",
|
||||
"gsd-core/workflows/explore.md": "35431c40bb1b245a",
|
||||
"gsd-core/workflows/extract-learnings.md": "f34d0b1927545b18",
|
||||
"gsd-core/workflows/extract-learnings.md": "6ed17a7b6c9f68a6",
|
||||
"gsd-core/workflows/fast.md": "66821090b6b8ed3b",
|
||||
"gsd-core/workflows/forensics.md": "459644dce26ee2ef",
|
||||
"gsd-core/workflows/graduation.md": "343e287b8bfac6b2",
|
||||
|
||||
14
tests/fixtures/golden-install-parity/cursor.json
vendored
14
tests/fixtures/golden-install-parity/cursor.json
vendored
@@ -16,7 +16,7 @@
|
||||
"agents/gsd-domain-researcher.md": "56395dbdabf076f6",
|
||||
"agents/gsd-eval-auditor.md": "ad2840fd5cd76172",
|
||||
"agents/gsd-eval-planner.md": "2049dac060d00eda",
|
||||
"agents/gsd-executor.md": "026606d319f6c338",
|
||||
"agents/gsd-executor.md": "4246bd0e27197e6e",
|
||||
"agents/gsd-framework-selector.md": "4b77eebbe9288d80",
|
||||
"agents/gsd-integration-checker.md": "5da30584d06b878c",
|
||||
"agents/gsd-intel-updater.md": "b8971c5d96e63b38",
|
||||
@@ -25,7 +25,7 @@
|
||||
"agents/gsd-pattern-mapper.md": "1229c215677f740d",
|
||||
"agents/gsd-phase-researcher.md": "982d59921bed463d",
|
||||
"agents/gsd-plan-checker.md": "30bc89279d6586b7",
|
||||
"agents/gsd-planner.md": "61d89d16ac357320",
|
||||
"agents/gsd-planner.md": "1c0d5aaa124f56ab",
|
||||
"agents/gsd-project-researcher.md": "beeac940d3a10e76",
|
||||
"agents/gsd-research-synthesizer.md": "6315f016d55176f4",
|
||||
"agents/gsd-roadmapper.md": "d28e7d4bac46dde2",
|
||||
@@ -110,7 +110,7 @@
|
||||
"gsd-core/VERSION": "ef0deccd81a6723c",
|
||||
"gsd-core/bin/check-latest-version.cjs": "e4a224058c8f4d74",
|
||||
"gsd-core/bin/ensure-runtime-build.cjs": "2525f1ae8b086828",
|
||||
"gsd-core/bin/gsd-tools.cjs": "1b15863444a36838",
|
||||
"gsd-core/bin/gsd-tools.cjs": "c9dfb100e7f40b7f",
|
||||
"gsd-core/bin/gsd_run": "62d9b647ede212e6",
|
||||
"gsd-core/bin/shared/config-defaults.manifest.json": "3a3581ea768cbe6a",
|
||||
"gsd-core/bin/shared/config-schema.manifest.json": "377dc46be7b56fe8",
|
||||
@@ -275,9 +275,9 @@
|
||||
"gsd-core/templates/spec.md": "7dc900c355098d8b",
|
||||
"gsd-core/templates/state.md": "73e424b8c70b765c",
|
||||
"gsd-core/templates/summary-complex.md": "a5e40574fd8894dc",
|
||||
"gsd-core/templates/summary-minimal.md": "7d09b5e709e2e67c",
|
||||
"gsd-core/templates/summary-standard.md": "e8d9cf4a8377cdff",
|
||||
"gsd-core/templates/summary.md": "23c40f6503b3ea98",
|
||||
"gsd-core/templates/summary-minimal.md": "d5f40260721e307d",
|
||||
"gsd-core/templates/summary-standard.md": "a4fb6df80f41b545",
|
||||
"gsd-core/templates/summary.md": "85f4d37fcee6852b",
|
||||
"gsd-core/templates/user-profile.md": "20749f23e4c413fc",
|
||||
"gsd-core/templates/user-setup.md": "78b7d718b6e8d67c",
|
||||
"gsd-core/templates/verification-report.md": "dd5faa6254183731",
|
||||
@@ -328,7 +328,7 @@
|
||||
"gsd-core/workflows/execute-phase/steps/worktree-recovery-policy.md": "be84efbd71e1513e",
|
||||
"gsd-core/workflows/execute-plan.md": "09ea0688882eb30e",
|
||||
"gsd-core/workflows/explore.md": "9348b54b526b8938",
|
||||
"gsd-core/workflows/extract-learnings.md": "d8177b0c13b7e5ee",
|
||||
"gsd-core/workflows/extract-learnings.md": "13929ce8a04013e0",
|
||||
"gsd-core/workflows/fast.md": "77b49793e26b3323",
|
||||
"gsd-core/workflows/forensics.md": "a65f817d4a515291",
|
||||
"gsd-core/workflows/graduation.md": "0c0f4e6258ae482f",
|
||||
|
||||
14
tests/fixtures/golden-install-parity/hermes.json
vendored
14
tests/fixtures/golden-install-parity/hermes.json
vendored
@@ -16,7 +16,7 @@
|
||||
"agents/gsd-domain-researcher.md": "412cdbb05ba252ea",
|
||||
"agents/gsd-eval-auditor.md": "4ffb265063c318e5",
|
||||
"agents/gsd-eval-planner.md": "03448fc9c5774b56",
|
||||
"agents/gsd-executor.md": "3ec54684a756e830",
|
||||
"agents/gsd-executor.md": "53379f898b45b192",
|
||||
"agents/gsd-framework-selector.md": "ea9981d65d6b3429",
|
||||
"agents/gsd-integration-checker.md": "35b4f2969d279871",
|
||||
"agents/gsd-intel-updater.md": "5fe5edfae2719cb8",
|
||||
@@ -25,7 +25,7 @@
|
||||
"agents/gsd-pattern-mapper.md": "cea092600aeb3978",
|
||||
"agents/gsd-phase-researcher.md": "2bd0402f33d757ca",
|
||||
"agents/gsd-plan-checker.md": "c31dc063b5506aaf",
|
||||
"agents/gsd-planner.md": "d1fe1e2653cb12de",
|
||||
"agents/gsd-planner.md": "3be8aff696060e6c",
|
||||
"agents/gsd-project-researcher.md": "425a7df7f37a5c06",
|
||||
"agents/gsd-research-synthesizer.md": "9d31c87fc2c87ffa",
|
||||
"agents/gsd-roadmapper.md": "64dce5d5f9fa5654",
|
||||
@@ -39,7 +39,7 @@
|
||||
"gsd-core/VERSION": "ef0deccd81a6723c",
|
||||
"gsd-core/bin/check-latest-version.cjs": "e4a224058c8f4d74",
|
||||
"gsd-core/bin/ensure-runtime-build.cjs": "3a3409215044af9f",
|
||||
"gsd-core/bin/gsd-tools.cjs": "fb40ca85a5fc3f9b",
|
||||
"gsd-core/bin/gsd-tools.cjs": "06878bab8a74e8c1",
|
||||
"gsd-core/bin/gsd_run": "62d9b647ede212e6",
|
||||
"gsd-core/bin/shared/config-defaults.manifest.json": "3a3581ea768cbe6a",
|
||||
"gsd-core/bin/shared/config-schema.manifest.json": "377dc46be7b56fe8",
|
||||
@@ -204,9 +204,9 @@
|
||||
"gsd-core/templates/spec.md": "7dc900c355098d8b",
|
||||
"gsd-core/templates/state.md": "73e424b8c70b765c",
|
||||
"gsd-core/templates/summary-complex.md": "a5e40574fd8894dc",
|
||||
"gsd-core/templates/summary-minimal.md": "7d09b5e709e2e67c",
|
||||
"gsd-core/templates/summary-standard.md": "e8d9cf4a8377cdff",
|
||||
"gsd-core/templates/summary.md": "23c40f6503b3ea98",
|
||||
"gsd-core/templates/summary-minimal.md": "d5f40260721e307d",
|
||||
"gsd-core/templates/summary-standard.md": "a4fb6df80f41b545",
|
||||
"gsd-core/templates/summary.md": "85f4d37fcee6852b",
|
||||
"gsd-core/templates/user-profile.md": "20749f23e4c413fc",
|
||||
"gsd-core/templates/user-setup.md": "78b7d718b6e8d67c",
|
||||
"gsd-core/templates/verification-report.md": "dd5faa6254183731",
|
||||
@@ -257,7 +257,7 @@
|
||||
"gsd-core/workflows/execute-phase/steps/worktree-recovery-policy.md": "be84efbd71e1513e",
|
||||
"gsd-core/workflows/execute-plan.md": "0c5e0455252b5a46",
|
||||
"gsd-core/workflows/explore.md": "843e66f101a56dfa",
|
||||
"gsd-core/workflows/extract-learnings.md": "e9e167c718949c0b",
|
||||
"gsd-core/workflows/extract-learnings.md": "7f44f65fbf32a427",
|
||||
"gsd-core/workflows/fast.md": "c801145115755524",
|
||||
"gsd-core/workflows/forensics.md": "91961b811917c5c4",
|
||||
"gsd-core/workflows/graduation.md": "938c71f1e7650da0",
|
||||
|
||||
14
tests/fixtures/golden-install-parity/kilo.json
vendored
14
tests/fixtures/golden-install-parity/kilo.json
vendored
@@ -16,7 +16,7 @@
|
||||
"agents/gsd-domain-researcher.md": "a3874d80bcbc7380",
|
||||
"agents/gsd-eval-auditor.md": "630d4cd3bd6ea195",
|
||||
"agents/gsd-eval-planner.md": "3db12cde12aeb2c1",
|
||||
"agents/gsd-executor.md": "bea8102bf46ddb7a",
|
||||
"agents/gsd-executor.md": "2dfa6f871d65bab1",
|
||||
"agents/gsd-framework-selector.md": "ad5f2c6b9bec6270",
|
||||
"agents/gsd-integration-checker.md": "c503e2f4a3d8ec05",
|
||||
"agents/gsd-intel-updater.md": "231393da62a45b2e",
|
||||
@@ -25,7 +25,7 @@
|
||||
"agents/gsd-pattern-mapper.md": "6a5408fd11d70391",
|
||||
"agents/gsd-phase-researcher.md": "94818f28c498bb26",
|
||||
"agents/gsd-plan-checker.md": "2546e311f7e8e0e8",
|
||||
"agents/gsd-planner.md": "72996d1f61ad7b0f",
|
||||
"agents/gsd-planner.md": "e6bc5cf0ac9e9c06",
|
||||
"agents/gsd-project-researcher.md": "60573a38d3dfd9fe",
|
||||
"agents/gsd-research-synthesizer.md": "1f7cd286c5783c86",
|
||||
"agents/gsd-roadmapper.md": "277e0a3252553ab7",
|
||||
@@ -110,7 +110,7 @@
|
||||
"gsd-core/VERSION": "ef0deccd81a6723c",
|
||||
"gsd-core/bin/check-latest-version.cjs": "e4a224058c8f4d74",
|
||||
"gsd-core/bin/ensure-runtime-build.cjs": "51bc64467ab30f62",
|
||||
"gsd-core/bin/gsd-tools.cjs": "ec98734a021c6157",
|
||||
"gsd-core/bin/gsd-tools.cjs": "0b356a34f3654051",
|
||||
"gsd-core/bin/gsd_run": "62d9b647ede212e6",
|
||||
"gsd-core/bin/shared/config-defaults.manifest.json": "3a3581ea768cbe6a",
|
||||
"gsd-core/bin/shared/config-schema.manifest.json": "377dc46be7b56fe8",
|
||||
@@ -275,9 +275,9 @@
|
||||
"gsd-core/templates/spec.md": "8734f0df4df3a34b",
|
||||
"gsd-core/templates/state.md": "a45a134631efe3f9",
|
||||
"gsd-core/templates/summary-complex.md": "a5e40574fd8894dc",
|
||||
"gsd-core/templates/summary-minimal.md": "7d09b5e709e2e67c",
|
||||
"gsd-core/templates/summary-standard.md": "e8d9cf4a8377cdff",
|
||||
"gsd-core/templates/summary.md": "23c40f6503b3ea98",
|
||||
"gsd-core/templates/summary-minimal.md": "d5f40260721e307d",
|
||||
"gsd-core/templates/summary-standard.md": "a4fb6df80f41b545",
|
||||
"gsd-core/templates/summary.md": "85f4d37fcee6852b",
|
||||
"gsd-core/templates/user-profile.md": "52abe2af968e8533",
|
||||
"gsd-core/templates/user-setup.md": "1da2382725db080f",
|
||||
"gsd-core/templates/verification-report.md": "78ab9264ce63ed7e",
|
||||
@@ -328,7 +328,7 @@
|
||||
"gsd-core/workflows/execute-phase/steps/worktree-recovery-policy.md": "be84efbd71e1513e",
|
||||
"gsd-core/workflows/execute-plan.md": "731d2947b623be4f",
|
||||
"gsd-core/workflows/explore.md": "e6c94f8b6f083109",
|
||||
"gsd-core/workflows/extract-learnings.md": "d8177b0c13b7e5ee",
|
||||
"gsd-core/workflows/extract-learnings.md": "13929ce8a04013e0",
|
||||
"gsd-core/workflows/fast.md": "41a6568b873aef99",
|
||||
"gsd-core/workflows/forensics.md": "c01da0178fb97b21",
|
||||
"gsd-core/workflows/graduation.md": "636df3c43e9b3bca",
|
||||
|
||||
@@ -44,7 +44,7 @@
|
||||
"agents/gsd-domain-researcher.md": "049f588663814fa2",
|
||||
"agents/gsd-eval-auditor.md": "54870d3b07433525",
|
||||
"agents/gsd-eval-planner.md": "552e9fa164c51ce8",
|
||||
"agents/gsd-executor.md": "98424ccf4346c9d1",
|
||||
"agents/gsd-executor.md": "258fcf3cc19fb411",
|
||||
"agents/gsd-framework-selector.md": "8a795f230436ad2e",
|
||||
"agents/gsd-integration-checker.md": "c1760a0bbd4f7bf5",
|
||||
"agents/gsd-intel-updater.md": "944f1d903e2e9e09",
|
||||
@@ -53,7 +53,7 @@
|
||||
"agents/gsd-pattern-mapper.md": "68ecefd60811a669",
|
||||
"agents/gsd-phase-researcher.md": "2235f61764d8e969",
|
||||
"agents/gsd-plan-checker.md": "f3caf89525709445",
|
||||
"agents/gsd-planner.md": "bf4304ea220f3874",
|
||||
"agents/gsd-planner.md": "88acabd0285bb25b",
|
||||
"agents/gsd-project-researcher.md": "f572892f138734ff",
|
||||
"agents/gsd-research-synthesizer.md": "29949bf3f049a8f1",
|
||||
"agents/gsd-roadmapper.md": "840ac933e3b094f9",
|
||||
@@ -67,7 +67,7 @@
|
||||
"gsd-core/VERSION": "ef0deccd81a6723c",
|
||||
"gsd-core/bin/check-latest-version.cjs": "e4a224058c8f4d74",
|
||||
"gsd-core/bin/ensure-runtime-build.cjs": "51bc64467ab30f62",
|
||||
"gsd-core/bin/gsd-tools.cjs": "ec98734a021c6157",
|
||||
"gsd-core/bin/gsd-tools.cjs": "0b356a34f3654051",
|
||||
"gsd-core/bin/gsd_run": "62d9b647ede212e6",
|
||||
"gsd-core/bin/shared/config-defaults.manifest.json": "3a3581ea768cbe6a",
|
||||
"gsd-core/bin/shared/config-schema.manifest.json": "377dc46be7b56fe8",
|
||||
@@ -232,9 +232,9 @@
|
||||
"gsd-core/templates/spec.md": "26d55bce940f0288",
|
||||
"gsd-core/templates/state.md": "4d123aa6cea167fe",
|
||||
"gsd-core/templates/summary-complex.md": "a5e40574fd8894dc",
|
||||
"gsd-core/templates/summary-minimal.md": "7d09b5e709e2e67c",
|
||||
"gsd-core/templates/summary-standard.md": "e8d9cf4a8377cdff",
|
||||
"gsd-core/templates/summary.md": "23c40f6503b3ea98",
|
||||
"gsd-core/templates/summary-minimal.md": "d5f40260721e307d",
|
||||
"gsd-core/templates/summary-standard.md": "a4fb6df80f41b545",
|
||||
"gsd-core/templates/summary.md": "85f4d37fcee6852b",
|
||||
"gsd-core/templates/user-profile.md": "20749f23e4c413fc",
|
||||
"gsd-core/templates/user-setup.md": "78b7d718b6e8d67c",
|
||||
"gsd-core/templates/verification-report.md": "dd5faa6254183731",
|
||||
@@ -285,7 +285,7 @@
|
||||
"gsd-core/workflows/execute-phase/steps/worktree-recovery-policy.md": "be84efbd71e1513e",
|
||||
"gsd-core/workflows/execute-plan.md": "74de71f01739f7ac",
|
||||
"gsd-core/workflows/explore.md": "3f3b4f83e23349bc",
|
||||
"gsd-core/workflows/extract-learnings.md": "b6f01ca3d8f58de4",
|
||||
"gsd-core/workflows/extract-learnings.md": "ab26f2cbb14efef2",
|
||||
"gsd-core/workflows/fast.md": "11f5cd10ae5cc7d3",
|
||||
"gsd-core/workflows/forensics.md": "0d500a3f5ab26913",
|
||||
"gsd-core/workflows/graduation.md": "973dcebcd17e1b10",
|
||||
|
||||
14
tests/fixtures/golden-install-parity/kimi.json
vendored
14
tests/fixtures/golden-install-parity/kimi.json
vendored
@@ -61,7 +61,7 @@
|
||||
"agents/subagents/gsd-eval-auditor.yaml": "e3d868bd5fefe938",
|
||||
"agents/subagents/gsd-eval-planner.md": "70f8c5727bfb9876",
|
||||
"agents/subagents/gsd-eval-planner.yaml": "df8499f7af297ec2",
|
||||
"agents/subagents/gsd-executor.md": "8fdf9332233a66bd",
|
||||
"agents/subagents/gsd-executor.md": "77f6d8e414227fcd",
|
||||
"agents/subagents/gsd-executor.yaml": "e29422986636fd64",
|
||||
"agents/subagents/gsd-framework-selector.md": "a15b7aa1e0576e16",
|
||||
"agents/subagents/gsd-framework-selector.yaml": "fb52c31cde27b0e3",
|
||||
@@ -79,7 +79,7 @@
|
||||
"agents/subagents/gsd-phase-researcher.yaml": "7633c8e82617e7cc",
|
||||
"agents/subagents/gsd-plan-checker.md": "410639f4c4f16e7a",
|
||||
"agents/subagents/gsd-plan-checker.yaml": "8295181071121db8",
|
||||
"agents/subagents/gsd-planner.md": "0384e53e5b5b50e5",
|
||||
"agents/subagents/gsd-planner.md": "ddf881be44151dbd",
|
||||
"agents/subagents/gsd-planner.yaml": "2e83ee194bcd7fbd",
|
||||
"agents/subagents/gsd-project-researcher.md": "39bc2ec5a8b18283",
|
||||
"agents/subagents/gsd-project-researcher.yaml": "ce12586b0347e2dc",
|
||||
@@ -103,7 +103,7 @@
|
||||
"gsd-core/VERSION": "ef0deccd81a6723c",
|
||||
"gsd-core/bin/check-latest-version.cjs": "e4a224058c8f4d74",
|
||||
"gsd-core/bin/ensure-runtime-build.cjs": "51bc64467ab30f62",
|
||||
"gsd-core/bin/gsd-tools.cjs": "ec98734a021c6157",
|
||||
"gsd-core/bin/gsd-tools.cjs": "0b356a34f3654051",
|
||||
"gsd-core/bin/gsd_run": "62d9b647ede212e6",
|
||||
"gsd-core/bin/shared/config-defaults.manifest.json": "3a3581ea768cbe6a",
|
||||
"gsd-core/bin/shared/config-schema.manifest.json": "377dc46be7b56fe8",
|
||||
@@ -268,9 +268,9 @@
|
||||
"gsd-core/templates/spec.md": "26d55bce940f0288",
|
||||
"gsd-core/templates/state.md": "4d123aa6cea167fe",
|
||||
"gsd-core/templates/summary-complex.md": "a5e40574fd8894dc",
|
||||
"gsd-core/templates/summary-minimal.md": "7d09b5e709e2e67c",
|
||||
"gsd-core/templates/summary-standard.md": "e8d9cf4a8377cdff",
|
||||
"gsd-core/templates/summary.md": "23c40f6503b3ea98",
|
||||
"gsd-core/templates/summary-minimal.md": "d5f40260721e307d",
|
||||
"gsd-core/templates/summary-standard.md": "a4fb6df80f41b545",
|
||||
"gsd-core/templates/summary.md": "85f4d37fcee6852b",
|
||||
"gsd-core/templates/user-profile.md": "20749f23e4c413fc",
|
||||
"gsd-core/templates/user-setup.md": "78b7d718b6e8d67c",
|
||||
"gsd-core/templates/verification-report.md": "dd5faa6254183731",
|
||||
@@ -321,7 +321,7 @@
|
||||
"gsd-core/workflows/execute-phase/steps/worktree-recovery-policy.md": "be84efbd71e1513e",
|
||||
"gsd-core/workflows/execute-plan.md": "74de71f01739f7ac",
|
||||
"gsd-core/workflows/explore.md": "3f3b4f83e23349bc",
|
||||
"gsd-core/workflows/extract-learnings.md": "b6f01ca3d8f58de4",
|
||||
"gsd-core/workflows/extract-learnings.md": "ab26f2cbb14efef2",
|
||||
"gsd-core/workflows/fast.md": "11f5cd10ae5cc7d3",
|
||||
"gsd-core/workflows/forensics.md": "0d500a3f5ab26913",
|
||||
"gsd-core/workflows/graduation.md": "973dcebcd17e1b10",
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
"agents/gsd-domain-researcher.md": "71250e759ca9e723",
|
||||
"agents/gsd-eval-auditor.md": "c88890105f32ace6",
|
||||
"agents/gsd-eval-planner.md": "60bddb70a937f796",
|
||||
"agents/gsd-executor.md": "14423bfb4dee14b8",
|
||||
"agents/gsd-executor.md": "3fdbe96e721a8099",
|
||||
"agents/gsd-framework-selector.md": "1c0a10355e787675",
|
||||
"agents/gsd-integration-checker.md": "a9de5928e5a5c649",
|
||||
"agents/gsd-intel-updater.md": "493e07482fa6198a",
|
||||
@@ -25,7 +25,7 @@
|
||||
"agents/gsd-pattern-mapper.md": "7c6d1d9817a9c1e7",
|
||||
"agents/gsd-phase-researcher.md": "9874110700b41f48",
|
||||
"agents/gsd-plan-checker.md": "f39aca1ea261d720",
|
||||
"agents/gsd-planner.md": "15c78c3192e53c9b",
|
||||
"agents/gsd-planner.md": "50f660afd4ddd599",
|
||||
"agents/gsd-project-researcher.md": "dae210ae0b3c6e2b",
|
||||
"agents/gsd-research-synthesizer.md": "e02c6ad5d1b74171",
|
||||
"agents/gsd-roadmapper.md": "1658a40b20d8b575",
|
||||
@@ -110,7 +110,7 @@
|
||||
"gsd-core/VERSION": "ef0deccd81a6723c",
|
||||
"gsd-core/bin/check-latest-version.cjs": "e4a224058c8f4d74",
|
||||
"gsd-core/bin/ensure-runtime-build.cjs": "51bc64467ab30f62",
|
||||
"gsd-core/bin/gsd-tools.cjs": "ec98734a021c6157",
|
||||
"gsd-core/bin/gsd-tools.cjs": "0b356a34f3654051",
|
||||
"gsd-core/bin/gsd_run": "62d9b647ede212e6",
|
||||
"gsd-core/bin/shared/config-defaults.manifest.json": "3a3581ea768cbe6a",
|
||||
"gsd-core/bin/shared/config-schema.manifest.json": "377dc46be7b56fe8",
|
||||
@@ -275,9 +275,9 @@
|
||||
"gsd-core/templates/spec.md": "8734f0df4df3a34b",
|
||||
"gsd-core/templates/state.md": "a45a134631efe3f9",
|
||||
"gsd-core/templates/summary-complex.md": "a5e40574fd8894dc",
|
||||
"gsd-core/templates/summary-minimal.md": "7d09b5e709e2e67c",
|
||||
"gsd-core/templates/summary-standard.md": "e8d9cf4a8377cdff",
|
||||
"gsd-core/templates/summary.md": "23c40f6503b3ea98",
|
||||
"gsd-core/templates/summary-minimal.md": "d5f40260721e307d",
|
||||
"gsd-core/templates/summary-standard.md": "a4fb6df80f41b545",
|
||||
"gsd-core/templates/summary.md": "85f4d37fcee6852b",
|
||||
"gsd-core/templates/user-profile.md": "52abe2af968e8533",
|
||||
"gsd-core/templates/user-setup.md": "1da2382725db080f",
|
||||
"gsd-core/templates/verification-report.md": "78ab9264ce63ed7e",
|
||||
@@ -328,7 +328,7 @@
|
||||
"gsd-core/workflows/execute-phase/steps/worktree-recovery-policy.md": "be84efbd71e1513e",
|
||||
"gsd-core/workflows/execute-plan.md": "bb0ce725dcf12aa2",
|
||||
"gsd-core/workflows/explore.md": "a514b88e98609441",
|
||||
"gsd-core/workflows/extract-learnings.md": "92b3c0979604b7d0",
|
||||
"gsd-core/workflows/extract-learnings.md": "38b09022eca429d8",
|
||||
"gsd-core/workflows/fast.md": "12187b242e6af970",
|
||||
"gsd-core/workflows/forensics.md": "9354cb830152fd28",
|
||||
"gsd-core/workflows/graduation.md": "589b9b303cff8643",
|
||||
|
||||
10
tests/fixtures/golden-install-parity/pi.json
vendored
10
tests/fixtures/golden-install-parity/pi.json
vendored
@@ -6,7 +6,7 @@
|
||||
"gsd-core/VERSION": "ef0deccd81a6723c",
|
||||
"gsd-core/bin/check-latest-version.cjs": "e4a224058c8f4d74",
|
||||
"gsd-core/bin/ensure-runtime-build.cjs": "51bc64467ab30f62",
|
||||
"gsd-core/bin/gsd-tools.cjs": "ec98734a021c6157",
|
||||
"gsd-core/bin/gsd-tools.cjs": "0b356a34f3654051",
|
||||
"gsd-core/bin/gsd_run": "62d9b647ede212e6",
|
||||
"gsd-core/bin/shared/config-defaults.manifest.json": "3a3581ea768cbe6a",
|
||||
"gsd-core/bin/shared/config-schema.manifest.json": "377dc46be7b56fe8",
|
||||
@@ -171,9 +171,9 @@
|
||||
"gsd-core/templates/spec.md": "26d55bce940f0288",
|
||||
"gsd-core/templates/state.md": "4d123aa6cea167fe",
|
||||
"gsd-core/templates/summary-complex.md": "a5e40574fd8894dc",
|
||||
"gsd-core/templates/summary-minimal.md": "7d09b5e709e2e67c",
|
||||
"gsd-core/templates/summary-standard.md": "e8d9cf4a8377cdff",
|
||||
"gsd-core/templates/summary.md": "23c40f6503b3ea98",
|
||||
"gsd-core/templates/summary-minimal.md": "d5f40260721e307d",
|
||||
"gsd-core/templates/summary-standard.md": "a4fb6df80f41b545",
|
||||
"gsd-core/templates/summary.md": "85f4d37fcee6852b",
|
||||
"gsd-core/templates/user-profile.md": "20749f23e4c413fc",
|
||||
"gsd-core/templates/user-setup.md": "78b7d718b6e8d67c",
|
||||
"gsd-core/templates/verification-report.md": "dd5faa6254183731",
|
||||
@@ -224,7 +224,7 @@
|
||||
"gsd-core/workflows/execute-phase/steps/worktree-recovery-policy.md": "be84efbd71e1513e",
|
||||
"gsd-core/workflows/execute-plan.md": "3168b13c3758ed84",
|
||||
"gsd-core/workflows/explore.md": "3f3b4f83e23349bc",
|
||||
"gsd-core/workflows/extract-learnings.md": "b6f01ca3d8f58de4",
|
||||
"gsd-core/workflows/extract-learnings.md": "ab26f2cbb14efef2",
|
||||
"gsd-core/workflows/fast.md": "11f5cd10ae5cc7d3",
|
||||
"gsd-core/workflows/forensics.md": "0d500a3f5ab26913",
|
||||
"gsd-core/workflows/graduation.md": "973dcebcd17e1b10",
|
||||
|
||||
14
tests/fixtures/golden-install-parity/qwen.json
vendored
14
tests/fixtures/golden-install-parity/qwen.json
vendored
@@ -16,7 +16,7 @@
|
||||
"agents/gsd-domain-researcher.md": "bd054bb27beed2a7",
|
||||
"agents/gsd-eval-auditor.md": "57cc7458ab5de6b7",
|
||||
"agents/gsd-eval-planner.md": "01b665728dde4ccf",
|
||||
"agents/gsd-executor.md": "b6baf92a0d0ab516",
|
||||
"agents/gsd-executor.md": "ebca30765efc0b68",
|
||||
"agents/gsd-framework-selector.md": "82ba6abea84226b7",
|
||||
"agents/gsd-integration-checker.md": "90835dbc7dfa1691",
|
||||
"agents/gsd-intel-updater.md": "3cc4f6ddd04676ec",
|
||||
@@ -25,7 +25,7 @@
|
||||
"agents/gsd-pattern-mapper.md": "83c66c7722e8b165",
|
||||
"agents/gsd-phase-researcher.md": "284e55a86ae46d7f",
|
||||
"agents/gsd-plan-checker.md": "e80e6d51017be405",
|
||||
"agents/gsd-planner.md": "f3c8b934ee07020c",
|
||||
"agents/gsd-planner.md": "303c956e286d83dd",
|
||||
"agents/gsd-project-researcher.md": "b5baac64a15c85e2",
|
||||
"agents/gsd-research-synthesizer.md": "6cd9b501dc97bd50",
|
||||
"agents/gsd-roadmapper.md": "c357a77ab919e9e5",
|
||||
@@ -39,7 +39,7 @@
|
||||
"gsd-core/VERSION": "ef0deccd81a6723c",
|
||||
"gsd-core/bin/check-latest-version.cjs": "e4a224058c8f4d74",
|
||||
"gsd-core/bin/ensure-runtime-build.cjs": "6e98d76e955e35a2",
|
||||
"gsd-core/bin/gsd-tools.cjs": "4cc7b3241d1422b6",
|
||||
"gsd-core/bin/gsd-tools.cjs": "94b222441497e080",
|
||||
"gsd-core/bin/gsd_run": "62d9b647ede212e6",
|
||||
"gsd-core/bin/shared/config-defaults.manifest.json": "3a3581ea768cbe6a",
|
||||
"gsd-core/bin/shared/config-schema.manifest.json": "377dc46be7b56fe8",
|
||||
@@ -204,9 +204,9 @@
|
||||
"gsd-core/templates/spec.md": "7dc900c355098d8b",
|
||||
"gsd-core/templates/state.md": "73e424b8c70b765c",
|
||||
"gsd-core/templates/summary-complex.md": "a5e40574fd8894dc",
|
||||
"gsd-core/templates/summary-minimal.md": "7d09b5e709e2e67c",
|
||||
"gsd-core/templates/summary-standard.md": "e8d9cf4a8377cdff",
|
||||
"gsd-core/templates/summary.md": "23c40f6503b3ea98",
|
||||
"gsd-core/templates/summary-minimal.md": "d5f40260721e307d",
|
||||
"gsd-core/templates/summary-standard.md": "a4fb6df80f41b545",
|
||||
"gsd-core/templates/summary.md": "85f4d37fcee6852b",
|
||||
"gsd-core/templates/user-profile.md": "20749f23e4c413fc",
|
||||
"gsd-core/templates/user-setup.md": "78b7d718b6e8d67c",
|
||||
"gsd-core/templates/verification-report.md": "dd5faa6254183731",
|
||||
@@ -257,7 +257,7 @@
|
||||
"gsd-core/workflows/execute-phase/steps/worktree-recovery-policy.md": "be84efbd71e1513e",
|
||||
"gsd-core/workflows/execute-plan.md": "ea93d7a5c3d483e8",
|
||||
"gsd-core/workflows/explore.md": "c412905fb86f3f12",
|
||||
"gsd-core/workflows/extract-learnings.md": "dd4fdb88605de49a",
|
||||
"gsd-core/workflows/extract-learnings.md": "5791168e144ec997",
|
||||
"gsd-core/workflows/fast.md": "93ed453edddd8c0c",
|
||||
"gsd-core/workflows/forensics.md": "82800a3138ac1da9",
|
||||
"gsd-core/workflows/graduation.md": "5d5004de086db1c8",
|
||||
|
||||
14
tests/fixtures/golden-install-parity/trae.json
vendored
14
tests/fixtures/golden-install-parity/trae.json
vendored
@@ -16,7 +16,7 @@
|
||||
"agents/gsd-domain-researcher.md": "b80f76874c04e515",
|
||||
"agents/gsd-eval-auditor.md": "470bf16303ec4d2e",
|
||||
"agents/gsd-eval-planner.md": "22334fde85723c9d",
|
||||
"agents/gsd-executor.md": "00768988ee91ad9f",
|
||||
"agents/gsd-executor.md": "191215b38db8bb1b",
|
||||
"agents/gsd-framework-selector.md": "7726fccc86bfeb50",
|
||||
"agents/gsd-integration-checker.md": "7cd2072984411c7f",
|
||||
"agents/gsd-intel-updater.md": "83de6ba9172891c3",
|
||||
@@ -25,7 +25,7 @@
|
||||
"agents/gsd-pattern-mapper.md": "b5d7a4abb1baecb9",
|
||||
"agents/gsd-phase-researcher.md": "2256f1f82212c757",
|
||||
"agents/gsd-plan-checker.md": "aaa9e928de1abba9",
|
||||
"agents/gsd-planner.md": "ca48b09c8688e70d",
|
||||
"agents/gsd-planner.md": "c99c8a75226d19b7",
|
||||
"agents/gsd-project-researcher.md": "ddf7794e81300032",
|
||||
"agents/gsd-research-synthesizer.md": "a124b00271748d07",
|
||||
"agents/gsd-roadmapper.md": "493ef92b42b12cf4",
|
||||
@@ -39,7 +39,7 @@
|
||||
"gsd-core/VERSION": "ef0deccd81a6723c",
|
||||
"gsd-core/bin/check-latest-version.cjs": "e4a224058c8f4d74",
|
||||
"gsd-core/bin/ensure-runtime-build.cjs": "de4627dff103d527",
|
||||
"gsd-core/bin/gsd-tools.cjs": "83769f08d1cc0216",
|
||||
"gsd-core/bin/gsd-tools.cjs": "11117cf7fe37c77d",
|
||||
"gsd-core/bin/gsd_run": "62d9b647ede212e6",
|
||||
"gsd-core/bin/shared/config-defaults.manifest.json": "3a3581ea768cbe6a",
|
||||
"gsd-core/bin/shared/config-schema.manifest.json": "377dc46be7b56fe8",
|
||||
@@ -204,9 +204,9 @@
|
||||
"gsd-core/templates/spec.md": "7dc900c355098d8b",
|
||||
"gsd-core/templates/state.md": "73e424b8c70b765c",
|
||||
"gsd-core/templates/summary-complex.md": "a5e40574fd8894dc",
|
||||
"gsd-core/templates/summary-minimal.md": "7d09b5e709e2e67c",
|
||||
"gsd-core/templates/summary-standard.md": "e8d9cf4a8377cdff",
|
||||
"gsd-core/templates/summary.md": "23c40f6503b3ea98",
|
||||
"gsd-core/templates/summary-minimal.md": "d5f40260721e307d",
|
||||
"gsd-core/templates/summary-standard.md": "a4fb6df80f41b545",
|
||||
"gsd-core/templates/summary.md": "85f4d37fcee6852b",
|
||||
"gsd-core/templates/user-profile.md": "20749f23e4c413fc",
|
||||
"gsd-core/templates/user-setup.md": "78b7d718b6e8d67c",
|
||||
"gsd-core/templates/verification-report.md": "dd5faa6254183731",
|
||||
@@ -257,7 +257,7 @@
|
||||
"gsd-core/workflows/execute-phase/steps/worktree-recovery-policy.md": "be84efbd71e1513e",
|
||||
"gsd-core/workflows/execute-plan.md": "3abba98d19b31036",
|
||||
"gsd-core/workflows/explore.md": "f4d0db08c11545a8",
|
||||
"gsd-core/workflows/extract-learnings.md": "3fcc858b20d0d0e6",
|
||||
"gsd-core/workflows/extract-learnings.md": "1ee1ee86b7d8bb43",
|
||||
"gsd-core/workflows/fast.md": "0f05b1e008ac2fc2",
|
||||
"gsd-core/workflows/forensics.md": "665546666547875d",
|
||||
"gsd-core/workflows/graduation.md": "defc0dfcbfeb68d2",
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
"agents/gsd-domain-researcher.md": "56395dbdabf076f6",
|
||||
"agents/gsd-eval-auditor.md": "fb64fc5acf359747",
|
||||
"agents/gsd-eval-planner.md": "2049dac060d00eda",
|
||||
"agents/gsd-executor.md": "10341df8e1f390bb",
|
||||
"agents/gsd-executor.md": "09666c96d441ecfa",
|
||||
"agents/gsd-framework-selector.md": "4b77eebbe9288d80",
|
||||
"agents/gsd-integration-checker.md": "4ffb37fb230c2b90",
|
||||
"agents/gsd-intel-updater.md": "a81d77c143c02108",
|
||||
@@ -25,7 +25,7 @@
|
||||
"agents/gsd-pattern-mapper.md": "ada0c169daa2f0ec",
|
||||
"agents/gsd-phase-researcher.md": "2a45ebde829555ec",
|
||||
"agents/gsd-plan-checker.md": "c68b9bd6382a22a7",
|
||||
"agents/gsd-planner.md": "b63b7203e0bc7beb",
|
||||
"agents/gsd-planner.md": "f9e2d99c4daf51de",
|
||||
"agents/gsd-project-researcher.md": "f6697b316b5995ba",
|
||||
"agents/gsd-research-synthesizer.md": "04036f38c1d373ea",
|
||||
"agents/gsd-roadmapper.md": "fb62e1e3de84b5f9",
|
||||
@@ -39,7 +39,7 @@
|
||||
"gsd-core/VERSION": "ef0deccd81a6723c",
|
||||
"gsd-core/bin/check-latest-version.cjs": "e4a224058c8f4d74",
|
||||
"gsd-core/bin/ensure-runtime-build.cjs": "5636ca0b726871b2",
|
||||
"gsd-core/bin/gsd-tools.cjs": "1ef071e09d8edcb6",
|
||||
"gsd-core/bin/gsd-tools.cjs": "41a13dea56716a55",
|
||||
"gsd-core/bin/gsd_run": "62d9b647ede212e6",
|
||||
"gsd-core/bin/shared/config-defaults.manifest.json": "3a3581ea768cbe6a",
|
||||
"gsd-core/bin/shared/config-schema.manifest.json": "377dc46be7b56fe8",
|
||||
@@ -204,9 +204,9 @@
|
||||
"gsd-core/templates/spec.md": "7dc900c355098d8b",
|
||||
"gsd-core/templates/state.md": "73e424b8c70b765c",
|
||||
"gsd-core/templates/summary-complex.md": "a5e40574fd8894dc",
|
||||
"gsd-core/templates/summary-minimal.md": "7d09b5e709e2e67c",
|
||||
"gsd-core/templates/summary-standard.md": "e8d9cf4a8377cdff",
|
||||
"gsd-core/templates/summary.md": "23c40f6503b3ea98",
|
||||
"gsd-core/templates/summary-minimal.md": "d5f40260721e307d",
|
||||
"gsd-core/templates/summary-standard.md": "a4fb6df80f41b545",
|
||||
"gsd-core/templates/summary.md": "85f4d37fcee6852b",
|
||||
"gsd-core/templates/user-profile.md": "20749f23e4c413fc",
|
||||
"gsd-core/templates/user-setup.md": "78b7d718b6e8d67c",
|
||||
"gsd-core/templates/verification-report.md": "dd5faa6254183731",
|
||||
@@ -257,7 +257,7 @@
|
||||
"gsd-core/workflows/execute-phase/steps/worktree-recovery-policy.md": "be84efbd71e1513e",
|
||||
"gsd-core/workflows/execute-plan.md": "2ff04f06b000fe26",
|
||||
"gsd-core/workflows/explore.md": "e5ff3269f8ee77b6",
|
||||
"gsd-core/workflows/extract-learnings.md": "af793bdf4ffd1c8a",
|
||||
"gsd-core/workflows/extract-learnings.md": "894218dd99cf2131",
|
||||
"gsd-core/workflows/fast.md": "b03b9f595892479a",
|
||||
"gsd-core/workflows/forensics.md": "3d1ce16b5f605592",
|
||||
"gsd-core/workflows/graduation.md": "0783b074a1c7013b",
|
||||
|
||||
14
tests/fixtures/golden-install-parity/zcode.json
vendored
14
tests/fixtures/golden-install-parity/zcode.json
vendored
@@ -16,7 +16,7 @@
|
||||
"agents/gsd-domain-researcher.md": "049f588663814fa2",
|
||||
"agents/gsd-eval-auditor.md": "54870d3b07433525",
|
||||
"agents/gsd-eval-planner.md": "552e9fa164c51ce8",
|
||||
"agents/gsd-executor.md": "98424ccf4346c9d1",
|
||||
"agents/gsd-executor.md": "258fcf3cc19fb411",
|
||||
"agents/gsd-framework-selector.md": "8a795f230436ad2e",
|
||||
"agents/gsd-integration-checker.md": "c1760a0bbd4f7bf5",
|
||||
"agents/gsd-intel-updater.md": "944f1d903e2e9e09",
|
||||
@@ -25,7 +25,7 @@
|
||||
"agents/gsd-pattern-mapper.md": "68ecefd60811a669",
|
||||
"agents/gsd-phase-researcher.md": "2235f61764d8e969",
|
||||
"agents/gsd-plan-checker.md": "f3caf89525709445",
|
||||
"agents/gsd-planner.md": "bf4304ea220f3874",
|
||||
"agents/gsd-planner.md": "88acabd0285bb25b",
|
||||
"agents/gsd-project-researcher.md": "f572892f138734ff",
|
||||
"agents/gsd-research-synthesizer.md": "29949bf3f049a8f1",
|
||||
"agents/gsd-roadmapper.md": "840ac933e3b094f9",
|
||||
@@ -110,7 +110,7 @@
|
||||
"gsd-core/VERSION": "ef0deccd81a6723c",
|
||||
"gsd-core/bin/check-latest-version.cjs": "e4a224058c8f4d74",
|
||||
"gsd-core/bin/ensure-runtime-build.cjs": "51bc64467ab30f62",
|
||||
"gsd-core/bin/gsd-tools.cjs": "ec98734a021c6157",
|
||||
"gsd-core/bin/gsd-tools.cjs": "0b356a34f3654051",
|
||||
"gsd-core/bin/gsd_run": "62d9b647ede212e6",
|
||||
"gsd-core/bin/shared/config-defaults.manifest.json": "3a3581ea768cbe6a",
|
||||
"gsd-core/bin/shared/config-schema.manifest.json": "377dc46be7b56fe8",
|
||||
@@ -275,9 +275,9 @@
|
||||
"gsd-core/templates/spec.md": "26d55bce940f0288",
|
||||
"gsd-core/templates/state.md": "4d123aa6cea167fe",
|
||||
"gsd-core/templates/summary-complex.md": "a5e40574fd8894dc",
|
||||
"gsd-core/templates/summary-minimal.md": "7d09b5e709e2e67c",
|
||||
"gsd-core/templates/summary-standard.md": "e8d9cf4a8377cdff",
|
||||
"gsd-core/templates/summary.md": "23c40f6503b3ea98",
|
||||
"gsd-core/templates/summary-minimal.md": "d5f40260721e307d",
|
||||
"gsd-core/templates/summary-standard.md": "a4fb6df80f41b545",
|
||||
"gsd-core/templates/summary.md": "85f4d37fcee6852b",
|
||||
"gsd-core/templates/user-profile.md": "20749f23e4c413fc",
|
||||
"gsd-core/templates/user-setup.md": "78b7d718b6e8d67c",
|
||||
"gsd-core/templates/verification-report.md": "dd5faa6254183731",
|
||||
@@ -328,7 +328,7 @@
|
||||
"gsd-core/workflows/execute-phase/steps/worktree-recovery-policy.md": "be84efbd71e1513e",
|
||||
"gsd-core/workflows/execute-plan.md": "4f43b65cf80d8f2e",
|
||||
"gsd-core/workflows/explore.md": "3f3b4f83e23349bc",
|
||||
"gsd-core/workflows/extract-learnings.md": "b6f01ca3d8f58de4",
|
||||
"gsd-core/workflows/extract-learnings.md": "ab26f2cbb14efef2",
|
||||
"gsd-core/workflows/fast.md": "11f5cd10ae5cc7d3",
|
||||
"gsd-core/workflows/forensics.md": "0d500a3f5ab26913",
|
||||
"gsd-core/workflows/graduation.md": "973dcebcd17e1b10",
|
||||
|
||||
@@ -27,7 +27,7 @@
|
||||
"execute-phase.md": 90143,
|
||||
"execute-plan.md": 35143,
|
||||
"explore.md": 11127,
|
||||
"extract-learnings.md": 12893,
|
||||
"extract-learnings.md": 13762,
|
||||
"fast.md": 7613,
|
||||
"forensics.md": 12531,
|
||||
"graduation.md": 11987,
|
||||
|
||||
Reference in New Issue
Block a user