a33cbe72f569e75e72d94de85d0930296d1ca1df
17 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Tom Boucher
|
f5fe5bc063 |
fix(config): allow model_overrides.<agent-id> in config-set (#3227) (#3253)
* test: reproduce config-set rejecting model_overrides.<agent-id> (#3227) * fix(config): allow model_overrides.<agent-id> in config-set (#3227) * changeset: pr=3253 for #3227 |
||
|
Tom Boucher
|
96ce608ee6 |
fix(config): add resolve_model_ids to VALID_CONFIG_KEYS; accept workflow._auto_chain_active via RUNTIME_STATE_KEYS
Fixes #3162 `resolve_model_ids` is a documented top-level config key (CONFIGURATION.md) read by core.cjs and session-runner.ts, but was missing from the CJS and SDK VALID_CONFIG_KEYS allowlists — causing config-set to reject it with "Unknown config key". `workflow._auto_chain_active` is internal runtime state intentionally excluded from VALID_CONFIG_KEYS by #2530, but plan-phase, execute-phase, discuss-phase, transition, and new-project workflows all write it via `config-set`. Without a valid write path these calls emit spurious errors (silenced with `|| true` but noisy in logs). A new RUNTIME_STATE_KEYS set in config-schema.cjs holds keys that isValidConfigKey() accepts without exposing them as user-settable options — preserving the #2530 intent while fixing the runtime error. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|
Tom Boucher
|
e1d661ece0 |
feat(#3024): dynamic routing with failure-tier escalation (#3031)
* feat(#3024): dynamic routing with failure-tier escalation Adds a `dynamic_routing` block to .planning/config.json that lets the resolver start agents on a cheap tier and escalate one tier up when the orchestrator detects a soft failure (verification inconclusive, plan-check FLAG, etc.). Solves the "pay Opus rates as insurance" anti-pattern by making escalation observed-quality-driven. Architecture: - AGENT_DEFAULT_TIERS map (light/standard/heavy) — every agent in MODEL_PROFILES declares a default tier; tests assert coverage so adding a new agent without updating the map fails CI. - nextTier(currentTier) helper — light → standard → heavy → heavy (heavy stays at heavy; can't go further). - resolveModelForTier(cwd, agentType, attempt) — new resolver. The orchestrator tracks the attempt counter and passes 0 for the first spawn, 1+ on escalation. The resolver caps internally at max_escalations so the orchestrator can blindly bump the counter. - Schema validation: dynamic_routing.enabled / escalate_on_failure / max_escalations / tier_models.<light|standard|heavy>. Unknown tiers and unknown sub-keys rejected at config-set time. - SDK schema mirror updated to keep CJS/SDK in lockstep (#2653). Resolution precedence (highest → lowest): 1. model_overrides[<agent>] (full IDs accepted) 2. dynamic_routing.tier_models[<tier>] (NEW; escalation-aware) 3. models[<phase_type>] (#3023 phase-type map) 4. model_profile (per-agent column) 5. Runtime default Backward compatibility: dynamic_routing is disabled by default (enabled: false or block omitted). resolveModelForTier short- circuits to resolveModelInternal in that case, so callers can adopt unconditionally without breaking existing behavior. This PR delivers the JS-layer infrastructure: schema + tier map + resolver. Orchestrator adoption (workflow markdown updates that detect soft failures and call resolveModelForTier with attempt+1) is incremental follow-up — verifier / plan-checker / integration- checker each adopt the protocol when ready. Tests (23 cases, all structural-IR — no stdout grep): - Schema invariants: AGENT_DEFAULT_TIERS coverage, VALID_AGENT_TIERS exact match, every assignment uses a valid tier - nextTier helper: light→standard→heavy→heavy, null on invalid input - Disabled mode: no block + enabled:false both no-op (back-compat) - Enabled mode: attempt=0 returns default tier model, attempt=1 escalates, beyond max_escalations caps, heavy agents stay heavy, default max_escalations=1 when omitted - Precedence: per-agent override beats dynamic_routing, dynamic_routing beats phase-type models - Validation: every settings key accepted, unknown tiers/sub-keys rejected, bare `dynamic_routing` rejected as config-set target Documentation: - get-shit-done/references/model-profiles.md — full reference section - docs/CONFIGURATION.md — full settings table + escalation flow - docs/USER-GUIDE.md — task-oriented "Cheap-by-default" section - docs/FEATURES.md — config row cross-link Verification: - 23/23 pass on regression test - 6843/6843 full suite (23 net new from 6820) - lint-no-source-grep clean (376 test files) - SDK schema mirror keeps CJS/SDK in sync per #2653 parity test Closes #3024 * fix(#3024): honor escalate_on_failure:false + 3 CR follow-ups CodeRabbit on PR #3031 (4 findings — 1 Major + 2 Minor + 1 Nitpick): 1. **Major (inline)** — get-shit-done/bin/lib/core.cjs:1668 resolveModelForTier ignored dynamic_routing.escalate_on_failure. When the user set it to false, escalation should be disabled, but the resolver only checked attempt/max_escalations. An orchestrator that always passes attempt+1 on retry would silently escalate despite the user opting out. Fix: gate effectiveAttempt on `dr.escalate_on_failure !== false` so false short-circuits every attempt back to the default tier. 2. **Minor (inline)** — docs/CONFIGURATION.md:123-126 The dynamic_routing rows in the Core Settings table had 4 cells instead of 5 (missing the Options column), breaking the table structure. Added explicit Options values for enabled / escalate_on_failure / max_escalations rows. 3. **Minor (outside-diff)** — references/model-profiles.md:179-195 "Resolution Logic" sketch was pre-#3024 and didn't include dynamic_routing in the precedence ladder. Updated to a 6-step block with dynamic_routing at step 3 (between override and phase-type). 4. **Nitpick** — tests/feat-3024-dynamic-routing.test.cjs:189+ Tests used `if (lightAgent) { ... }` guards that silent-pass when AGENT_DEFAULT_TIERS drifts. Replaced all 5 conditional skips with `assert.ok(lightAgent, '...')` preconditions so a tier-mapping change surfaces as a test failure. Plus: 2 new regression tests for the Major fix: - escalate_on_failure:false caps every attempt at default tier - escalate_on_failure:true (explicit) still escalates normally Verification: - 25/25 pass on regression test (23 prior + 2 escalate_on_failure) - 6845/6845 full suite (2 net new) - lint-no-source-grep clean * docs(#3024): align precedence + add fence language tags (CR follow-up) CodeRabbit (3 minor): 1. docs/CONFIGURATION.md:691 — "Per-Phase-Type Models → Resolution precedence" was a 4-step block written pre-#3024; readers got contradictory rules between the per-phase-type section and the later dynamic_routing section. Updated to the same 5-step ladder with dynamic_routing at step 2, and noted that dynamic_routing is disabled by default so this section's behavior is unchanged when the kill-switch is off. 2. docs/CONFIGURATION.md:770 — escalation-flow code fence missing language tag (MD040). Added `text`. 3. references/model-profiles.md:184 — resolution-ladder code fence missing language tag (MD040). Added `text`. No code changes; docs only. Verification: regression test still 25/25. * docs(#3024): clarify precedence prose — five layers, not four (CR nitpick) CodeRabbit nitpick: the "Per-Phase-Type Models → Resolution precedence" prose said "The four layers compose..." but the ladder above lists five (including Runtime default). Also "dynamic_routing escalates per-attempt above all of them" misreads as suggesting dynamic_routing wins over model_overrides — actually overrides still win at step 1. Reworded top-down so the precedence direction is unambiguous: - model_profile = base - models = phase-level override - dynamic_routing = per-attempt escalation - model_overrides = per-agent exception (top) - runtime default = fallback No code changes; docs only. * docs(#3024): note escalate_on_failure:false in escalation-flow diagram (CR) CodeRabbit nitpick: the escalation-flow diagram in docs/CONFIGURATION.md described the soft-failure → respawn → tier_models[next_tier_up] path, but didn't surface the `dynamic_routing.escalate_on_failure: false` kill-switch right next to it. Users reading the flow diagram (which is the canonical place to understand attempt behavior) wouldn't see that the kill-switch overrides the soft-failure branch. Added a one-paragraph note immediately after the flow listing, before the tier-sequence example, so the kill-switch is visible exactly where users decide whether escalation will happen. No code changes; docs only. |
||
|
Tom Boucher
|
d812c66020 |
feat(#3023): per-phase-type model map in .planning/config.json (#3030)
* feat(#3023): per-phase-type model map in .planning/config.json Adds a new `models` block to .planning/config.json with six phase-type slots (planning / discuss / research / execution / verification / completion). Lets users express coarse tuning ("Opus for planning, Sonnet for the rest") without learning the agent taxonomy. Resolution precedence (highest → lowest): 1. Per-agent `model_overrides[agent]` (full IDs; targeted exception) 2. Phase-type `models[phase_type]` (NEW; tier alias) 3. Profile table (`model_profile`) (per-agent column) 4. Runtime default The three layers compose: `models` defaults a phase, `model_overrides` carves an exception. Phase-type values are tier aliases (opus/sonnet/ haiku/inherit) so the runtime-resolution chain (#2517) stays correct end-to-end without further branching. Implementation: - model-profiles.cjs: new AGENT_TO_PHASE_TYPE map + VALID_PHASE_TYPES set. Each agent in MODEL_PROFILES gets one phase-type assignment; tests assert coverage so adding a new agent without updating the table fails CI. - core.cjs (resolveModelInternal): inserts phase-type tier lookup between per-agent override and profile-derived tier. Skips runtime resolution when the resolved tier is 'inherit' (was previously gated only on profile === 'inherit'; phase-type can now produce inherit independently). - core.cjs (loadConfig): pass `parsed.models` through both code paths so resolveModelInternal can read it. - config-schema.cjs + sdk/src/query/config-schema.ts: dynamic-pattern validator accepts only the six known phase-types; unknown slots rejected at config-set time. Backward compat: configs without `models` behave exactly as today. Tests (15 cases, all structural-IR — no stdout grep): - Schema: AGENT_TO_PHASE_TYPE coverage, VALID_PHASE_TYPES exact match - Resolver: phase-type alone; per-agent override beats phase-type; phase-type beats profile; issue's full example; "inherit"; empty block is no-op; no block is no-op - Validation: each of the 6 slots accepted; unknown slot rejected; bare `models` (no slot) rejected Verification: - 15/15 pass on new regression test - 6808/6808 full suite (5 net new), 0 fail - lint-no-source-grep clean across 375 test files Closes #3023 * docs(#3023): document `models` per-phase-type config in user-facing docs Adds `models` block coverage to the three user-facing docs that ship with each release: 1. docs/CONFIGURATION.md - New "Per-Phase-Type Models" section between "Per-Agent Overrides" and "Non-Claude Runtimes" with: * full example mixing models + model_overrides * phase-type → agent mapping table * resolution-precedence pseudocode * accepted values (tier alias only) * "When to use which" decision matrix * validation behavior + example error - Added `"models": {}` to the Full Schema snippet - Added a row for `models.<phase_type>` to the config keys table (next to model_profile_overrides for adjacency) 2. docs/FEATURES.md - Added a row for models.<phase_type> in the Configurable Settings table (right under model_profile) - Cross-link to CONFIGURATION.md for the full surface 3. docs/USER-GUIDE.md - New task-oriented "Tuning model cost by phase" section above "Using Non-Claude Runtimes" — leads with the concrete config and shows the override pattern (one-shot phase + targeted exception) - Cross-link to CONFIGURATION.md Verification: - 29/29 pass on config-schema-docs-parity + docs-update + new feature test (parity-check passes, so the config-schema entry I added in the feature commit is now matched by a docs row) - 6808/6808 full suite pass - lint-no-source-grep clean Doc style follows the same pattern used by the existing model_profile, model_overrides, and model_profile_overrides sections — example-led, table-backed, cross-referenced. Each doc surfaces the feature at the right depth (reference / settings table / task guide). * fix(#3023): mirror phase-type tier in resolveReasoningEffortInternal (CR Major) CodeRabbit caught a real Codex correctness bug + 3 minor docs/test issues: 1. **Major (outside-diff)** — resolveReasoningEffortInternal in core.cjs derived its tier exclusively from the profile table, ignoring the models.<phase_type> override added in #3023. Failure mode on Codex: Config: model_profile=balanced, models.execution=opus, agent=gsd-executor resolveModelInternal: tier=opus → gpt-5.4 resolveReasoningEffortInternal: tier=sonnet → reasoning_effort=medium ↑ WRONG — should be xhigh (opus tier on Codex) The runtime received a mismatched (model, effort) pair. Mirrored the phase-type lookup from resolveModelInternal so both functions derive from the same tier source. 'inherit' phase-type returns null effort (no runtime entry maps to 'inherit'; let runtime decide). 2. Minor — .changeset/per-phase-type-models.md `pr: TBD` → `pr: 3030`. 3. Minor (outside-diff) — model-profiles.md "Resolution Logic" section omitted the new phase-type tier. Updated the 4-step block to a 5-step block including `models[phase_type]` between override and profile, plus a paragraph noting that `model` and `reasoning_effort` derive from the same tier source. 4. Nitpick — added 2 typo-safety tests: - models.research = "haiku3" (typo) → falls through to profile - models.research = "openai/gpt-5" (full ID) → falls through to profile Plus 5 new reasoning_effort tests covering the Major fix: - exported correctly - phase-type override flips both model AND effort to same tier - inherit phase-type returns null effort - per-agent override still bypasses phase-type for effort - claude runtime ignores models.* (no effort propagation) Verification: - 24/24 pass on regression test (15 original + 2 typo-safety + 5 effort + 2 outside-diff related) - 6815/6815 full suite (7 net new from 6808) - lint-no-source-grep clean The reasoning_effort tests are written semantically (phase-type override must produce the SAME effort as a profile-only opus config) rather than hard-coding tier-specific effort strings, so changes to the runtime tier map don't break them. * fix(#3023): phase-type override beats profile=inherit (CR Major round 2) CodeRabbit caught another precedence inversion: when { model_profile: 'inherit', models: { execution: 'opus' } } both resolvers short-circuited on `profile === 'inherit'` BEFORE the phase-type override could be honored. Result: model returned 'inherit' and reasoning_effort returned null — both contradicting the documented precedence where models[phase_type] wins over model_profile. Fix in resolveModelInternal: - Compute tier from phase-type FIRST. If phase-type is a valid alias, it wins. Otherwise, fall back to profile-derived tier OR 'inherit' (when profile === 'inherit'). - Gate the runtime-resolution branch on `tier !== 'inherit'` (was `profile !== 'inherit'`) so phase-type=opus can flip runtime mapping on even when profile=inherit. - Gate the inherit-return on `tier === 'inherit'` (was `profile === 'inherit'`). Fix in resolveReasoningEffortInternal: - Remove the `if (profile === 'inherit') return null;` early-return. - Compute tier from phase-type first, fall back to profile. If phase-type is explicitly 'inherit' OR the resolved tier is 'inherit', return null (no runtime entry maps to inherit). Tests added (5 new): - model: phase-type wins over profile=inherit (with explicit opus, with haiku for one phase + planner-without-slot still inheriting) - model: profile=inherit + no models block → all agents inherit (no regression on existing inherit semantics) - model: profile=inherit + models block but agent has no slot → that agent inherits, agents with slots get phase-type tier - effort: phase-type opus + profile=inherit → produces opus-tier effort, NOT null (the original bug) Verification: - 27/27 pass on regression test (24 prior + 3 model + 1 effort) - 6820/6820 full suite (5 net new) - lint-no-source-grep clean The effort test reads the expected value by running a profile-only opus config and comparing — semantic check, not hard-coded effort string. So runtime tier map changes don't break the test. |
||
|
Tom Boucher
|
8de8acee46 |
fix(workflows): assert HEAD on per-agent branch before worktree commits (#2924) (#2941)
* fix(workflows): assert HEAD on per-agent branch before worktree commits Worktree-mode setup could leave HEAD attached to a protected branch (master), causing agent commits to land there. The previous response was a destructive self-recovery via 'git update-ref refs/heads/master <sha>', which silently rewinds the protected branch and destroys concurrent commits in multi-active scenarios (parallel agents, user committing while agent runs). - Reorder <worktree_branch_check> in execute-phase.md and quick.md to assert HEAD via 'git symbolic-ref' BEFORE any 'git reset --hard'. HALT with a blocker if HEAD is on main/master/develop/trunk/release/* or detached. - Add a per-commit HEAD assertion (step 0) to gsd-executor.md <task_commit_protocol>; HEAD attachment can drift after 'git checkout <sha>'. - Forbid 'git update-ref refs/heads/<protected>' in <destructive_git_prohibition>; surface the blocker rather than self-heal. - Remove '--no-verify' as the worktree-mode default in execute-phase.md, execute-plan.md, quick.md, and references/git-integration.md. Hooks now run on every executor commit; opt out only via workflow.worktree_skip_hooks. - Add regression test that parses the worktree_branch_check blocks structurally and asserts the symbolic-ref check precedes the reset --hard, no workflow performs update-ref on a protected ref, and --no-verify is no longer the default in any parallel-execution prompt. * fix(#2924): address CodeRabbit review findings on worktree HEAD PR - Add positive worktree-agent-* allow-list to <task_commit_protocol> step 0 in gsd-executor.md and to <worktree_branch_check> in execute-phase.md and quick.md. The deny-list (main|master|develop|trunk|release/*) silently allowed feature/* and other arbitrary branches outside the agent namespace. - Register workflow.worktree_skip_hooks in both config schemas (sdk/src/query/config-schema.ts and get-shit-done/bin/lib/config-schema.cjs) and document it in docs/CONFIGURATION.md so config-set accepts it. - Fix stash lifecycle in execute-phase.md post-wave hook validation: stash under a named ref and pop after the hook run; warn on pop failure. - Pre-dispatch PLAN.md commit in quick.md: gate on git diff --cached --quiet for idempotency and exit 1 with a clear error on commit failure (both the --no-verify and the normal branches) — no more swallowing real errors. - Test fixes (tests/bug-2924-worktree-head-attachment.test.cjs): - Parse the protected-branch alternation structurally and require main, master, develop, trunk, release/.* (release/* was previously skipped by the \\b...\\b regex). - Use fs.readdirSync(dir, { recursive: true }) so workflows in nested subdirectories are also asserted against the update-ref ban. - Add allow-list assertions for execute-phase.md, quick.md, and gsd-executor.md to lock in the new positive namespace check. * test(#2924): assert sub-section end marker exists before slicing * test(#2924): use section boundary instead of fixed window for parallel-agents slice |
||
|
Tom Boucher
|
b40110111d |
feat(#2306): plan-review-convergence v2 — CYCLE_SUMMARY contract, config gate, local model reviewers (#2718)
* feat(#2306): plan-review-convergence v2 — CYCLE_SUMMARY contract, config gate, local model reviewers Fixes the false-stall detection bug in the plan→review→replan convergence loop. REVIEWS.md accumulates history across cycles so raw grep inflated HIGH counts; HIGH count now comes from a per-cycle CYCLE_SUMMARY contract emitted in the review agent's return message. Key changes: - workflow.plan_review_convergence config gate (disabled by default, same pattern as workflow.code_review / workflow.nyquist_validation) - Review agent prompt defines CYCLE_SUMMARY: current_high=<N> contract with PARTIALLY RESOLVED / FULLY RESOLVED counting rules - Orchestrator aborts on absent/malformed CYCLE_SUMMARY (distinguishes both) - Warns when HIGH_COUNT > 0 but ## Current HIGH Concerns section is missing - Stall detection and --ws forwarding preserved and tested - Local model reviewers: --ollama, --lm-studio, --llama-cpp flags added to convergence workflow and review workflow; all three use OpenAI-compatible /v1/chat/completions endpoint with jq --rawfile for safe JSON encoding - review.ollama_host / review.lm_studio_host / review.llama_cpp_host config keys registered and documented (default to localhost:11434/1234/8080) - review.models.ollama / .lm_studio / .llama_cpp model-name config support - 58 tests (up from 29 in PR #2339), all passing Closes #2306 Closes #2339 Co-authored-by: Tom Boucher <trekkie@nomorestars.com> Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(ci): sync sdk/src/query/config-schema.ts with CJS schema (#2306) Add workflow.plan_review_convergence, review.ollama_host, review.lm_studio_host, and review.llama_cpp_host to the SDK-side TypeScript mirror — required by the CJS↔SDK parity test (#2653). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(#2306): resolve CodeRabbit review findings - Anchor HIGH_COUNT extraction with head -1 to prevent multi-match when agent return message contains multiple CYCLE_SUMMARY lines (e.g. quoted back from prompt context) - Replace hardcoded reviewers list in REVIEWS.md frontmatter template with runtime-derived placeholder — the static list did not reflect which reviewers were actually invoked - Broaden workflow.plan_review_convergence docs to include local reviewers (Ollama, LM Studio, llama.cpp) alongside cloud reviewers Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(ci): restore reviewers frontmatter list with runtime note The cursor-reviewer.test.cjs (and equivalent per-reviewer tests) assert that each supported reviewer appears on the reviewers: line — these are wiring tests that catch when a new reviewer is added to invocation but not to the REVIEWS.md template. Replacing the list with a placeholder broke those tests. Restore the full static list and add an inline comment clarifying that the actual committed frontmatter should be filtered to only the reviewers invoked that run — satisfying both the per-reviewer tests and the CodeRabbit correctness note. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|
Tom Boucher
|
b7ff14fe51 |
fix(#2687): derive KNOWN_TOP_LEVEL from DYNAMIC_KEY_PATTERNS to eliminate read-side drift (#2706)
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|
Tom Boucher
|
387c8a1f9c |
fix(#2653): eliminate SDK↔CJS config-schema drift (#2670)
The SDK's config-set kept its own hand-maintained allowlist (28-key drift vs. get-shit-done/bin/lib/config-schema.cjs), so documented keys accepted by the CJS config-set — planning.sub_repos, workflow.code_review_command, workflow.security_*, review.models.*, model_profile_overrides.*, etc. — were rejected with "Unknown config key" when routed through the SDK. Changes: - New sdk/src/query/config-schema.ts mirrors the CJS schema exactly (exact-match keys + dynamic regex sources). - config-mutation.ts imports VALID_CONFIG_KEYS / DYNAMIC_KEY_PATTERNS from the shared module instead of rolling its own set and regex branches. - Drop hand-coded agent_skills.* / features.* regex branches — now schema-driven so claude_md_assembly.blocks.*, review.models.*, and model_profile_overrides.<runtime>.<tier> are also accepted. - Add tests/config-schema-sdk-parity.test.cjs (node:test) as the CI drift guard: asserts CJS VALID_CONFIG_KEYS set-equals the literal set parsed from config-schema.ts, and that every CJS dynamic pattern source has an identical counterpart in the SDK. Parallel to the CJS↔docs parity added in #2479. - Vitest #2653 specs iterate every CJS key through the SDK validator, spot-check each dynamic pattern, and lock in planning.sub_repos. - While here: add workflow.context_coverage_gate to the CJS schema (already in docs and SDK; CJS previously rejected it) and sync the missing curated typo-suggestions (review.model, sub_repos, plan_checker, workflow.review_command) into the SDK. Fixes #2653. |
||
|
Tom Boucher
|
1a3d953767 |
feat: add unified post-planning gap checker (closes #2493) (#2610)
* feat: add unified post-planning gap checker (closes #2493) Adds a unified post-planning gap checker as Step 13e of plan-phase.md. After all plans are generated and committed, scans REQUIREMENTS.md and CONTEXT.md <decisions> against every PLAN.md in the phase directory and emits a single Source | Item | Status table. Why - The existing Requirements Coverage Gate (§13) blocks/re-plans on REQ gaps but emits two separate per-source signals. Issue #2493 asks for one unified report after planning so that requirements AND discuss-phase decisions slipping through are surfaced in one place before execution starts. What - New workflow.post_planning_gaps boolean config key, default true, added to VALID_CONFIG_KEYS, CONFIG_DEFAULTS, hardcoded.workflow, and cmdConfigSet (boolean validation). - New get-shit-done/bin/lib/decisions.cjs — shared parser for CONTEXT.md <decisions> blocks (D-NN entries). Designed for reuse by the related #2492 plan/verify decision gates. - New get-shit-done/bin/lib/gap-checker.cjs — parses REQUIREMENTS.md (checkbox + traceability table forms), reads CONTEXT.md decisions, walks PHASE_DIR/*-PLAN.md, runs word-boundary coverage detection (REQ-1 must not match REQ-10), formats a sorted report. - New gsd-tools gap-analysis CLI command wired through gsd-tools.cjs. - workflows/plan-phase.md gains §13e between §13d (commit plans) and §14 (Present Final Status). Existing §13 gate preserved — §13e is additive and non-blocking. - sdk/prompts/workflows/plan-phase.md gets an equivalent post_planning_gaps step for headless mode. - Docs: CONFIGURATION.md, references/planning-config.md, INVENTORY.md, INVENTORY-MANIFEST.json all updated. Tests - tests/post-planning-gaps-2493.test.cjs: 30 test cases covering step insertion position, decisions parser, gap detector behavior (covered/not-covered, false-positive guard, missing-file resilience, malformed-input resilience, gate on/off, deterministic natural sort), and full config integration. - Full suite: 5234 / 5234 pass. Design decisions - Numbered §13e (sub-step), not §14 — §14 already exists (Present Final Status); inserting before it preserves downstream auto-advance step numbers. - Existing §13 gate kept, not replaced — §13 blocks/re-plans on REQ gaps; §13e is the unified post-hoc report. Per spec: "default behavior MUST be backward compatible." - Word-boundary ID matching avoids REQ-1 matching REQ-10 and avoids brittle semantic/substring matching. - Shared decisions.cjs parser so #2492 can reuse the same regex. - Natural-sort keys (REQ-02 before REQ-10) for deterministic output. - Boolean validation in cmdConfigSet rejects non-boolean values matches the precedent set by drift_threshold/drift_action. Closes #2493 * fix(#2493): expose post_planning_gaps in loadConfig() + sync schema example Address CodeRabbit review on PR #2610: - core.cjs loadConfig(): return post_planning_gaps from both the config.json branch and the global ~/.gsd/defaults.json fallback so callers can rely on config.post_planning_gaps regardless of whether the key is present (comment 3127977404, Major). - docs/CONFIGURATION.md: add workflow.post_planning_gaps to the Full Schema JSON example so copy/paste users see the new toggle alongside security_block_on (comment 3127977392, Minor). - tests/post-planning-gaps-2493.test.cjs: regression coverage for loadConfig() — default true when key absent, honors explicit true/false from workflow.post_planning_gaps. |
||
|
Tom Boucher
|
cc17886c51 |
feat: make model profiles runtime-aware for Codex/non-Claude runtimes (closes #2517) (#2609)
* feat: make model profiles runtime-aware for Codex/non-Claude runtimes (closes #2517) Adds an optional top-level `runtime` config key plus a `model_profile_overrides[runtime][tier]` map. When `runtime` is set, profile tiers (opus/sonnet/haiku) resolve to runtime-native model IDs (and reasoning_effort where supported) instead of bare Claude aliases. Codex defaults from the spec: opus -> gpt-5.4 reasoning_effort: xhigh sonnet -> gpt-5.3-codex reasoning_effort: medium haiku -> gpt-5.4-mini reasoning_effort: medium Claude defaults mirror MODEL_ALIAS_MAP. Unknown runtimes fall back to the Claude-alias safe default rather than emit IDs the runtime cannot accept. reasoning_effort is only emitted into Codex install paths; never returned from resolveModelInternal and never written to Claude agent frontmatter. Backwards compatible: any user without `runtime` set sees identical behavior — the new branch is gated on `config.runtime != null`. Precedence (highest to lowest): 1. per-agent model_overrides 2. runtime-aware tier resolution (when `runtime` is set) 3. resolve_model_ids: "omit" 4. Claude-native default 5. inherit (literal passthrough) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(#2517): address adversarial review of #2609 (findings 1-16) Addresses all 16 findings from the adversarial review of PR #2609. Each finding is enumerated below with its resolution. CRITICAL - F1: readGsdRuntimeProfileResolver(targetDir) now probes per-project .planning/config.json AND ~/.gsd/defaults.json with per-project winning, so the PR's headline claim ("set runtime in project config and Codex TOML emit picks it up") actually holds end-to-end. - F2: resolveTierEntry field-merges user overrides with built-in defaults. The CONFIGURATION.md string-shorthand example `{ codex: { opus: "gpt-5-pro" } }` now keeps reasoning_effort from the built-in entry. Partial-object overrides like `{ opus: { reasoning_effort: 'low' } }` keep the built-in model. Both paths regression-tested. MAJOR - F3: resolveReasoningEffortInternal gates strictly on the RUNTIMES_WITH_REASONING_EFFORT allowlist regardless of override presence. Override + unknown-runtime no longer leaks reasoning_effort. - F4: runtime:"claude" is now a no-op for resolution (it is the implicit default). It no longer hijacks resolve_model_ids:"omit". Existing tests for `runtime:"claude"` returning Claude IDs were rewritten to reflect the no-op semantics; new test asserts the omit case returns "". - F5: _readGsdConfigFile in install.js writes a stderr warning on JSON parse failure instead of silently returning null. Read failure and parse failure are warned separately. Library require is hoisted to top of install.js so it is not co-mingled with config-read failure modes. - F6: install.js requires for core.cjs / model-profiles.cjs are hoisted to the top of the file with __dirname-based absolute paths so global npm install works regardless of cwd. Test asserts both lib paths exist relative to install.js __dirname. - F7: docs/CONFIGURATION.md `runtime` row no longer lists `opencode` as a valid runtime — install-path emission for non-Codex runtimes is explicitly out of scope per #2517 / #2612, and the doc now points at #2612 for the follow-on work. resolveModelInternal still accepts any runtime string (back-compat) and falls back safely for unknown values. - F8: Tests now isolate HOME (and GSD_HOME) to a per-test tmpdir so the developer's real ~/.gsd/defaults.json cannot bleed into assertions. Same pattern CodeRabbit caught on PRs #2603 / #2604. - F9: `runtime` and `model_profile_overrides` documented as flat-only in core.cjs comments — not routed through `get()` because they are top-level keys per docs/CONFIGURATION.md and introducing nested resolution for two new keys was not worth the edge-case surface. - F10/F13: loadConfig now invokes _warnUnknownProfileOverrides on the raw parsed config so direct .planning/config.json edits surface unknown runtime values (e.g. typo `runtime: "codx"`) and unknown tier values (e.g. `model_profile_overrides.codex.banana`) at read time. Warnings only — preserves back-compat for runtimes added later. Per-process warning cache prevents log spam across repeated loadConfig calls. MINOR / NIT - F11: Removed dead `tier || 'sonnet'` defensive shortcut. The local is now `const alias = tier;` with a comment explaining why `tier` is guaranteed truthy at that point (every MODEL_PROFILES entry defines `balanced`, the fallback profile). - F12: Extracted resolveTierEntry() in core.cjs as the single source of truth for runtime-aware tier resolution. core.cjs and bin/install.js both consume it — no duplicated lookup logic between the two files. - F14: Added regression tests for findings #1, #2, #3, #4, #6, #10, #13 in tests/issue-2517-runtime-aware-profiles.test.cjs. Each must-fix path has a corresponding test that fails against the pre-fix code and passes against the post-fix code. - F15: docs/CONFIGURATION.md `model_profile` row cross-references #1713 / #1806 next to the `adaptive` enum value. - F16: RUNTIME_PROFILE_MAP remains in core.cjs as the single source of truth; install.js imports it through the exported resolveTierEntry helper rather than carrying its own copy. Doc files (CONFIGURATION.md, USER-GUIDE.md, settings.md) intentionally still embed the IDs as text — code comment in core.cjs flags that those doc files must be updated whenever the constant changes. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Tom Boucher
|
1a694fcac3 |
feat: auto-remap codebase after significant phase execution (closes #2003) (#2605)
* feat: auto-remap codebase after significant phase execution (#2003) Adds a post-phase structural drift detector that compares the committed tree against `.planning/codebase/STRUCTURE.md` and either warns or auto-remaps the affected subtrees when drift exceeds a configurable threshold. ## Summary - New `bin/lib/drift.cjs` — pure detector covering four drift categories: new directories outside mapped paths, new barrel exports at `(packages|apps)/*/src/index.*`, new migration files, and new route modules. Prioritizes the most-specific category per file. - New `verify codebase-drift` CLI subcommand + SDK handler, registered as `gsd-sdk query verify.codebase-drift`. - New `codebase_drift_gate` step in `execute-phase` between `schema_drift_gate` and `verify_phase_goal`. Non-blocking by contract — any error logs and the phase continues. - Two new config keys: `workflow.drift_threshold` (int, default 3) and `workflow.drift_action` (`warn` | `auto-remap`, default `warn`), with enum/integer validation in `config-set`. - `gsd-codebase-mapper` learns an optional `--paths <p1,p2,...>` scope hint for incremental remapping; agent/workflow docs updated. - `last_mapped_commit` lives in YAML frontmatter on each `.planning/codebase/*.md` file; `readMappedCommit`/`writeMappedCommit` round-trip helpers ship in `drift.cjs`. ## Tests - 55 new tests in `tests/drift-detection.test.cjs` covering: classification, threshold gating at 2/3/4 elements, warn vs. auto-remap routing, affected-path scoping, `--paths` sanitization (traversal, absolute, shell metacharacter rejection), frontmatter round-trip, defensive paths (missing STRUCTURE.md, malformed input, non-git repos), CLI JSON output, and documentation parity. - Full suite: 5044 pass / 0 fail. ## Documentation - `docs/CONFIGURATION.md` — rows for both new keys. - `docs/ARCHITECTURE.md` — section on the post-execute drift gate. - `docs/AGENTS.md` — `--paths` flag on `gsd-codebase-mapper`. - `docs/USER-GUIDE.md` — user-facing behavior note + toggle commands. - `docs/FEATURES.md` — new 27a section with REQ-DRIFT-01..06. - `docs/INVENTORY.md` + `docs/INVENTORY-MANIFEST.json` — drift.cjs listed. - `get-shit-done/workflows/execute-phase.md` — `codebase_drift_gate` step. - `get-shit-done/workflows/map-codebase.md` — `parse_paths_flag` step. - `agents/gsd-codebase-mapper.md` — `--paths` directive under parse_focus. ## Design decisions - **Frontmatter over sidecar JSON** for `last_mapped_commit`: keeps the baseline attached to the file, survives git moves, survives per-doc regeneration, no extra file lifecycle. - **Substring match against STRUCTURE.md** for `isPathMapped`: the map is free-form markdown, not a structured manifest; any mention of a path prefix counts as "mapped territory". Cheap, no parser, zero false negatives on reasonable maps. - **Category priority migration > route > barrel > new_dir** so a file matching multiple rules counts exactly once at the most specific level. - **Empty-tree SHA fallback** (`4b825dc6…`) when `last_mapped_commit` is absent — semantically correct (no baseline means everything is drift) and deterministic across repos. - **Four layers of non-blocking** — detector try/catch, CLI try/catch, SDK handler try/catch, and workflow `|| echo` shell fallback. Any single layer failing still returns a valid skipped result. - **SDK handler delegates to `gsd-tools.cjs`** rather than re-porting the detector to TypeScript, keeping drift logic in one canonical place. Closes #2003 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs(mapper): tag --paths fenced block as text (CodeRabbit MD040) Comment 3127255172. * docs(config): use /gsd- dash command syntax in drift_action row (CodeRabbit) Comment 3127255180. Matches the convention used by every other command reference in docs/CONFIGURATION.md. * fix(execute-phase): initialize AGENT_SKILLS_MAPPER + tag fenced blocks Two CodeRabbit findings on the auto-remap branch of the drift gate: - 3127255186 (must-fix): the mapper Task prompt referenced ${AGENT_SKILLS_MAPPER} but only AGENT_SKILLS (for gsd-executor) is loaded at init_context (line 72). Without this fix the literal placeholder string would leak into the spawned mapper's prompt. Add an explicit gsd-sdk query agent-skills gsd-codebase-mapper step right before the Task spawn. - 3127255183: tag the warn-message and Task() fenced code blocks as text to satisfy markdownlint MD040. * docs(map-codebase): wire PATH_SCOPE_HINT through every mapper prompt CodeRabbit (review id 4158286952, comment 3127255190) flagged that the parse_paths_flag step defined incremental-remap semantics but did not inject a normalized variable into the spawn_agents and sequential_mapping mapper prompts, so incremental remap could silently regress to a whole-repo scan. - Define SCOPED_PATHS / PATH_SCOPE_HINT in parse_paths_flag. - Inject ${PATH_SCOPE_HINT} into all four spawn_agents Task prompts. - Document the same scope contract for sequential_mapping mode. * fix(drift): writeMappedCommit tolerates missing target file CodeRabbit (review id 4158286952, drift.cjs:349-355 nitpick) noted that readMappedCommit returns null on ENOENT but writeMappedCommit threw — an asymmetry that breaks first-time stamping of a freshly produced doc that the caller has not yet written. - Catch ENOENT on the read; treat absent file as empty content. - Add a regression test that calls writeMappedCommit on a non-existent path and asserts the file is created with correct frontmatter. Test was authored to fail before the fix (ENOENT) and passes after. --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Tom Boucher
|
9c0a153a5f |
feat: /gsd-settings-advanced — power-user config tuning command (closes #2528) (#2603)
* feat: /gsd-settings-advanced — power-user config tuning command (closes #2528) Adds a second-tier interactive configuration command covering the power-user knobs that don't belong in the common-case /gsd-settings prompt. Six sectioned AskUserQuestion batches cover planning, execution, discussion, cross-AI, git, and runtime settings (19 config keys total). Current values are pre-selected; numeric fields reject non-numeric input; writes route through gsd-sdk query config-set so unrelated keys are preserved. - commands/gsd/settings-advanced.md — command entry - get-shit-done/workflows/settings-advanced.md — six-section workflow - get-shit-done/workflows/settings.md — advertise advanced command - get-shit-done/bin/lib/config-schema.cjs — add context_window to VALID_CONFIG_KEYS - docs/COMMANDS.md, docs/CONFIGURATION.md, docs/INVENTORY.md — docs + inventory - tests/gsd-settings-advanced.test.cjs — 81 tests (files, frontmatter, field coverage, pre-selection, merge-preserves-siblings, VALID_CONFIG_KEYS membership, confirmation table, /gsd-settings cross-link, negative scenarios) All 5073 tests pass; coverage 88.66% (>= 70% threshold). * docs(settings-advanced): clarify per-field numeric bounds and label fenced blocks Addresses CodeRabbit review on PR #2603: - Numeric-input rule now states min is field-specific: plan_bounce_passes and max_discuss_passes require >= 1; other numeric fields accept >= 0. Resolves the inconsistency between the global rule and the field-level prompts (CodeRabbit comment 3127136557). - Adds 'text' fence language to seven previously unlabeled code blocks in the workflow (six AskUserQuestion sections plus the confirmation banner) to satisfy markdownlint MD040 (CodeRabbit comment 3127136561). * test(settings-advanced): tighten section assertion, fix misleading test name, add executable numeric-input coverage Addresses CodeRabbit review on PR #2603: - Required section list now asserts the full 'Runtime / Output' heading rather than the looser 'Runtime' substring (comment 3127136564). - Renames the subagent_timeout coercion test to match the actual key under test (was titled 'context_window' but exercised workflow.subagent_timeout — comment 3127136573). - Adds two executable behavioral tests at the config-set boundary (comment 3127136579): * Non-numeric input on a numeric key currently lands as a string — locks in that the workflow's AskUserQuestion re-prompt loop is the layer responsible for type rejection. If a future change adds CLI-side numeric validation, the assertion flips and the test surfaces it. * Numeric string on workflow.max_discuss_passes is coerced to Number — locks in the parser invariant for a second numeric key. |
||
|
Tom Boucher
|
533973700c |
feat(#2538): add last: /cmd suffix to statusline (opt-in) (#2594)
Adds a `statusline.show_last_command` config toggle (default: false) that appends ` │ last: /<cmd>` to the statusline, showing the most recently invoked slash command in the current session. The suffix is derived by tailing the active Claude Code transcript (provided as transcript_path in the hook input) and extracting the last <command-name> tag. Reads only the final 256 KiB to stay cheap per render. Graceful degradation: missing transcript, no recorded command, unreadable config, or parse errors all silently omit the suffix without breaking the statusline. Closes #2538 |
||
|
Tom Boucher
|
c47a6a2164 |
fix: correct VALID_CONFIG_KEYS — remove internal state key, add missing public keys, migration hints (#2561)
* fix(#2530-2535): correct VALID_CONFIG_KEYS set — remove internal state key, add missing public keys, add migration hints - Remove workflow._auto_chain_active from VALID_CONFIG_KEYS (internal runtime state, not user-settable) (#2530) - Add hooks.workflow_guard to VALID_CONFIG_KEYS (read by gsd-workflow-guard.js hook, already documented) (#2531) - Add workflow.ui_review to VALID_CONFIG_KEYS (read in autonomous.md via config-get) (#2532) - Add workflow.max_discuss_passes to VALID_CONFIG_KEYS (read in discuss-phase.md via config-get) (#2533) - Add CONFIG_KEY_SUGGESTIONS entries for sub_repos → planning.sub_repos and plan_checker → workflow.plan_check (#2535) - Document workflow.ui_review and workflow.max_discuss_passes in docs/CONFIGURATION.md - Clear INTERNAL_KEYS exemption in parity test (workflow._auto_chain_active removed from schema entirely) - Add regression test file tests/bug-2530-valid-config-keys.test.cjs covering all 6 bugs Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: align SDK VALID_CONFIG_KEYS with CJS — remove internal key, add missing public keys - Remove workflow._auto_chain_active from SDK (internal runtime state, not user-settable) - Add workflow.ui_review, workflow.max_discuss_passes, hooks.workflow_guard to SDK - Add ui_review and max_discuss_passes to Full Schema example in CONFIGURATION.md Resolves CodeRabbit review on #2561. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|
Tom Boucher
|
b2534e8a05 |
feat(plan-phase): chunked mode + filesystem fallback for Windows stdio hang (#2499)
* feat(plan-phase): chunked mode + filesystem fallback for Windows stdio hang (#2310) Addresses the 2026-04-16 Windows incident where gsd-planner wrote all 5 PLAN.md files to disk but Task() never returned, hanging the orchestrator for 30+ minutes. Two mitigations: 1. Filesystem fallback (steps 9a, 11a): when Task() returns with an empty/truncated response but PLAN.md files exist on disk, surface a recoverable prompt (Accept plans / Retry planner / Stop) instead of silently failing. Directly addresses the post-restart recovery path. 2. Chunked mode (--chunked flag / workflow.plan_chunked config): splits the single long-lived planner Task into a short outline Task (~2 min) followed by N short per-plan Tasks (~3-5 min each). Each plan is committed individually for crash resilience. A hang loses one plan, not all of them. Resume detection skips plans already on disk on re-run. RCA confirmed: task state mtime 14:29 vs PLAN.md writes 14:32-14:52 = subagent completed normally, IPC return was dropped by Windows stdio deadlock. Neither mitigation fixes the root cause (requires upstream Task() timeout support); both bound damage and enable recovery. New reference file planner-chunked.md keeps OUTLINE COMPLETE / PLAN COMPLETE return formats out of gsd-planner.md (which sits at 46K near its size limit). Closes #2310 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(plan-phase): address CodeRabbit review comments on #2499 - docs/CONFIGURATION.md: add workflow.plan_chunked to full JSON schema example - plan-phase.md step 8.5.1: validate PLAN-OUTLINE.md with grep for OUTLINE COMPLETE marker before reusing (not just file existence) - plan-phase.md step 8.5.2: validate per-plan PLAN.md has YAML frontmatter (head -1 grep for ---) before skipping in resume path - plan-phase.md: add language tags (text/javascript/bash) to bare fenced code blocks in steps 8.5, 9a, 11a (markdownlint MD040) - Rejected: commit_docs gate on per-plan commits (gsd-sdk query commit already respects commit_docs internally — comment was a false positive) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(plan-phase): route Accept-plans through step 9 PLANNING COMPLETE handling Honors --skip-verify / plan_checker_enabled=false in 9a fallback path. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|
Tom Boucher
|
2b494407e5 |
feat(assembly): add link mode for CLAUDE.md @-reference sections (#2484)
* feat(assembly): add link mode for CLAUDE.md @-reference sections (#2415) Adds `claude_md_assembly.mode: "link"` config option that writes `@.planning/<source>` instead of inlining content between GSD markers, reducing typical CLAUDE.md size by ~65%. Per-block overrides available via `claude_md_assembly.blocks.<section>`. Falls back to embed for sections without a real source file (workflow, fallbacks). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(test): add positive assertion for embedded workflow content (CodeRabbit #2484) The negative assertion only confirmed @GSD defaults wasn't written. Add assert.ok(content.includes('GSD Workflow Enforcement')) to verify the workflow section is actually embedded inline when link mode falls back. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|
Tom Boucher
|
62eaa8dd7b |
docs: close doc drift vectors — bidirectional parity, manifest, schema-driven config (#2479)
Option A — ghost-entry guard (INVENTORY ⊆ actual): tests/inventory-source-parity.test.cjs parses every declared row in INVENTORY.md and asserts the source file exists. Catches deletions and renames that leave ghost entries behind. Option B — auto-generated structural manifest: scripts/gen-inventory-manifest.cjs walks all six family dirs and emits docs/INVENTORY-MANIFEST.json. tests/inventory-manifest-sync.test.cjs fails CI when a new surface ships without a manifest update, surfacing exactly which entries are missing. Option C — schema-driven config validation + docs parity: get-shit-done/bin/lib/config-schema.cjs extracted from config.cjs as the single source of truth for VALID_CONFIG_KEYS and dynamic patterns. config.cjs now imports from it. tests/config-schema-docs-parity.test.cjs asserts every exact-match key appears in docs/CONFIGURATION.md, surfacing 14 previously undocumented keys (planning.sub_repos, workflow.ai_integration_phase, git.base_branch, learnings.max_inject, and 10 others) — all now documented in their appropriate sections. Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> |