24 Commits

Author	SHA1	Message	Date
Tom Boucher	ff4a57b78c	chore(#1671): migrate the remaining 13 LARGE/XL workflows to the fragment model — Phase 6.3 (#3030) ... * chore(#2994): fragmentize progress.md forensic audit onto the fragment model Extract the --forensic-gated forensic_audit step to workflows/progress/steps/forensic-audit.md behind a section marker, and repair progress.md's init line to forward --forensic so the atom is actually true in production rather than only under direct CLI tests. progress.md shrinks 32630 -> 27207 bytes. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore(#2994): fragmentize the four manifest-wired workflows new-project, quick, new-milestone and progress each already had a dedicated cmdInit* entry point but zero marked sections. Extract nine gated bodies to workflows/<wf>/steps/ behind section markers and repair each init line to forward its flags. Fold --full into the discuss/research/validate facts inside cmdInitQuick so the when= grammar never sees an OR, per the chunked-mode precedent. Fixes found while working, per the no-defer rule: - cmdInitProgress passed no phase info to buildSectionManifestField, so state:phase-mvp-mode was permanently false — an atom in the vocabulary whose fact could never be computed. - the quick init router folded flag tokens into the free-text description, which the new forwarding would have corrupted. - a #2508 dispatch note was nested inside quick.md's Agent(prompt=) fence, leaking orchestrator guidance into the subagent prompt. - progress.md had a 3-vs-4 backtick outer-fence imbalance. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore(#2994): fragmentize verify-work.md and admit state:ui-phase-active Wire cmdInitVerifyWork to buildSectionManifestField — it was a dedicated entry point that never emitted a manifest — and mark two sections. state:ui-phase-active folds (plan:pre hooks include an active ui step) OR (the phase dir holds a *-UI-SPEC.md) into one boolean in init.cts, so the grammar still sees a single operator-free atom. The inner Playwright-MCP check stays as prose inside the fragment: it is live session state and no init seam can precompute it. The MVP false-branch note is a real fallback, not redundant prose, so it sits outside the marker — gating it away would delete the text needed precisely when MVP mode is off. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * test(#2994): follow moved workflow content in drift guards Retarget every guard that asserted on content this branch moved into workflows/<wf>/steps/, mirroring 815b3d897. Each retargeted assertion was verified to still fail when its step file is blanked, so none was weakened into vacuity. Three assertions in verify-mvp-uat were genuinely red. Three more were worse than red — passing for the wrong reason: - quick-commit-boundary and worktree-cleanup anchored on indexOf('Step 5.6'), which matched a later cross-reference and sliced 16069 chars that coincidentally held the asserted substrings. Replaced with an expandWorkflowSections helper that splices step content back in place. - phase6-review-capabilities lost its end boundary and widened to EOF. - playwright-ui-verify matched 'UI' in an unrelated bullet and 'fall back' in a subagent-dispatch line after the real content moved. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore(#2994): fragmentize code-review and complete-milestone, admit three atoms Add dedicated cmdInitCodeReview and cmdInitCompleteMilestone entry points alongside the shared generic ones rather than modifying them — init.phase-op and init.manager carry a CRITICAL blast radius (179 dependents, 24 processes) and stay byte-identical for their other callers. Admit flag:--fix, state:fallow-enabled and state:git-create-tag, each with a consuming section and a fact its own entry point computes. Both sections had the resolver-in-body hazard: the fallow config-gate and the git.create_tag check each sat inside the very block being gated, so gating would have disabled the resolver that decides the gate. Both are hoisted into init and the bodies now consume the resolved fact. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * test(#2994): retarget code-review and milestone drift guards, fix two red tests Retarget guards that asserted on content moved into steps/, proving non-vacuity by blanking each step file and confirming failure. Also fixes two genuinely red tests found while working, per the no-defer rule: - workflow-fragments' frozen-vocabulary lock was missing state:ui-phase-active, so commit 7ef7f8336 shipped red. Lint and build both passed over it, which is why neither is sufficient verification. - code-review's quick.md capability-hook assertion carried a stale delimiter after the 18ff35d20 extraction. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore(#2994): fragmentize autonomous.md and admit state:plan-strategy-converge Five sections share one atom, the pattern plan-phase already uses for flag:--research-phase. The atom folds --converge OR --cross-ai into a single boolean in cmdInitAutonomous so the grammar stays operator-free. cmdInitAutonomous is additive; init.milestone-op, init.manager and init.phase-op are untouched and still consumed. The $PLAN_STRATEGY bash resolver is deliberately retained — ungated local-planning bullets still read it, so the init-side fact supplements it rather than replacing it. converge-fail-fast required splitting one bash fence so the always-run CONVERGENCE_ARGS construction stays outside the marker. All three flag-absent fallbacks were left outside their markers. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore(#2994): fragmentize review and discuss-phase-assumptions Admit state:reviewer-instances-configured (two peripheral notes share it; the core reviewer-lane dispatch stays unmarked — it is the workflow's primary always-evaluated logic, not an optional branch) and state:auto-advance-active, which folds --auto OR two config keys into one boolean so the grammar stays operator-free. discuss-phase-assumptions was the highest-risk edit in this PR. Its auto_advance step is a full if/elif/else; gating it whole would have deleted the flag-absent fallback needed exactly when --auto is off. Split verified exact: resolvers 636-651 and the 'End here' fallback 668-669 both stay outside the marker; only 653-667 is gated. Adds emitted-drift acks for the two files that grew — review.md (+55 B) and autonomous.md (+737 B from 80799211c, which had none and would have red-gated the push. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore(#2994): fragmentize docs-update, update, transition and new-milestone Part A Completes the 13-workflow rollout. Three of these had no init call at all and gained a dedicated entry point plus their first gsd_run query line. Admits state:is-monorepo and adds state:next-channel, state:workstream-active and state:flat-mode. Vocabulary 26 -> 30 atoms. Part A of new-milestone applies when NO workstream is active — the negation of state:workstream-active. Rather than teach the grammar negation, which is the Greenspun drift the frozen list exists to prevent, it gets a separate positively-phrased atom whose fact is the inverse. Part B, which always runs, stays outside the marker. flag:--verify-only is deliberately NOT admitted: docs-update has no contiguous purely-additive region for it, and an atom without a consuming section is dead vocabulary. Evidence recorded in the slice report. update.md reuses its existing resolved $GSD_TOOLS rather than prepending the canonical preamble, which would have clobbered it. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(#2994): stop automated-ui-verification re-resolving its own gate, retire dead vocabulary Two defects the new tests caught. The automated-ui-verification step re-ran gsd_run loop render-hooks and recomputed UI_PHASE_ACTIVE inside a body that is only read when that fact is already true — the circular self-disabling pattern this design forbids, introduced by 3c654b168. cmdInitVerifyWork now exposes ui_phase_active and the step consumes it. Its launcher preamble goes too: no gsd_run remains. The Playwright-MCP check stays as prose — that is live session state. Dead vocabulary predating this PR: flag:--full and state:needs-codebase-map were admitted with a gate-1 claim that never materialized. flag:--full is removed, redundant once quick folds it into discuss/research/validate. state:needs-codebase-map gets the real consumer it always lacked, gating new-project's codebase-map offer. Vocabulary 30 -> 29, and no atom is now without a consuming section. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * test(#2994): add the atom-admission, inversion and resolver-hoist gates The two existing parity guards prove vocabulary/predicate symmetry but never that a fact is computed — an atom no cmdInit* assembles evaluates false forever. These close that hole: - per-atom satisfiability for all 29 atoms, plus an anti-vacuity assertion so the loop cannot silently cover zero atoms - dead-vocabulary check against the shipped manifest - inversion guard: the flag-absent fallbacks in discuss-phase-assumptions and verify-work must stay outside their markers - data-driven resolver-hoist guard over the shipped manifest, so a future extraction cannot reintroduce the circular class - compound-fold coverage (--full, --cross-ai, --rc, config-only --auto) - null-vs-[] degraded/computed distinction, and flag value shapes Also repairs the frozen-vocabulary lock, which was stale and red for the seven atoms earlier commits on this branch shipped. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * docs(#2994): add changeset for the fragment-model rollout Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * test(#2994): cite the issue on the two new allow-test-rule exemptions ADR-456 requires an issue ref on the same line as the annotation. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * docs(#2994): correct the atom-count claims after retiring flag:--full The vocabulary doc comments still said 30 entries; it is 29 since flag:--full was removed as dead vocabulary. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(#2994): dedupe the phase-fallback block and harden --ws parsing Review findings. MAJOR: the three new init entry points each pasted a verbatim copy of the guardedFindPhase/guardedGetRoadmapPhase fallback, taking the repo from four copies to seven — DEFECT.GENERATIVE-FIX. Extracted applyRoadmapFallback and folded six of the seven; each call site keeps its own field-set via a closure. Duplication removed rather than papered over with a parity test. cmdInitPhaseOp stays out: its fallback omits has_reviews, so it is not a byte-identical copy, and it is CRITICAL-radius. LOW, pre-existing: GSD_WS captured [^[:space:]]+ and expands unquoted, so a workstream name holding glob metacharacters would expand against the filesystem. Narrowed to [A-Za-z0-9._-]+. The unquoted expansion is kept — it must word-split into two args and vanish when empty. Also restores the vocabulary ordering convention, and fixes a masked test bug the mandated run surfaced: the flag-forwarding guard checked only the first init line per workflow, but new-milestone has two, so a real failure was reporting exit 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(#2994): drop the stale new-milestone emitted-drift ack new-milestone.md was acked for a +406 B growth measured against an intermediate commit. Net against origin/next it SHRANK by 8 bytes, so nothing needed the ack and it explained nothing — which the differential attribution check reports as a stale acknowledgment, not a pass. update.md's entry stays: it genuinely grew +703 B. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(#2994): resolve the 15 failures from the full matrix run All 15 were real and identical on both lanes. REAL REGRESSION: autonomous.md hit 41479 chars against the #2196 guard's 40960 cap — a CHARS cap distinct from the LARGE tier byte cap, which the five section stubs pushed it over. Extracted the 3a.5 UI Design Contract body to references/; now 39968 chars, and the file nets -795 B vs base, so its growth ack is deleted rather than left stale. REAL DEFECT: docs referenced /gsd-transition, which is not a live registered command. Reworded. STALE FIXTURE: the emission byte-identity test hardcoded two marked workflows; this branch legitimately marks fifteen. Fixture corrected — the source was right. The rest were drift guards over the eight workflows the earlier sweep did not cover, retargeted at where the content now lives with non-vacuity proven by blanking each step file and confirming failure. The GSD_WS forwarding guard was checked as a possible real break and is not one: the charclass narrowing is intact and forwarding works end to end. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(#2994): drop the ack for a newly-added reference file A new file's emitted ripple is attributable to the diff that adds it, so the acknowledgment explained nothing and the differential check reports it as stale. Removing the last entry removes the fragment — an empty one signals nothing. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(#2994): retarget the UI-contract guards and clear two transitive advisories The §3a.5 extraction that brought autonomous.md under the #2196 char cap moved its body to references/autonomous-ui-design-contract.md, so ten guards in autonomous-ui-steps and check-ui-safety-gate were asserting it against the host. Retargeted via a combined read, each proven non-vacuous by blanking the reference file and confirming failure. This class had already bitten twice on this branch because each sweep was scoped to the workflows touched at that moment, so this one was exhaustive: ~70 test files across all 13 workflows, zero further broken or vacuous assertions found. Also clears two high transitive advisories the matrix flagged on one lane — fast-uri GHSA-7p8r-x3mc-p8w7 and three ip-address SSRF/trust-boundary issues. Both pre-date this branch: package-lock.json was untouched until now, so the production tree was byte-identical to the base. Lockfile-only, package.json unchanged, verified against a real npm ci install. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * chore(#2994): backfill changeset pr number to 3030 --------- Co-authored-by: sim <sim@local> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>	2026-08-03 19:59:58 -04:00
𝚌𝚕𝚎𝚣𝚌𝚘𝚍𝚒𝚗𝚐	88f6d9bd1b	fix(#2644): deduplicate Cursor slash menu (#2812) ... * fix(#2644): deduplicate Cursor slash menu * fix: preserve installer executable mode * chore: add changeset for PR #2812 * test(#2644): acknowledge Cursor emission changes * test(#2644): drop spent emitted drift acknowledgments * fix(#2644): remove retired Cursor command converter --------- Co-authored-by: clezcoding <clezcoding@users.noreply.github.com> Co-authored-by: Tom Boucher <trekkie@nomorestars.com>	2026-08-03 12:05:45 -04:00
Tom Boucher	067a4d1c6c	fix(#2650): bound and auto-recover plan-phase planner/plan-checker stalls (#3015) ... * test(#2650): add failing-first regression for plan-phase stall detection Regression test for gsd_stall_should_recover / gsd_stall_watch and the planner.stall_* config keys, none of which exist yet — proves RED before the fix lands in the next commit. * fix(#2650): bound and auto-recover plan-phase planner/plan-checker stalls Mirrors the already-shipped executor.stall_* pattern (execute-phase.md, bug #3212) but with a dispatch change the executor's prose-only surveillance lacks: the standard planner spawn, chunked-outline planner spawn, chunked-per-plan planner spawn, plan-checker spawn, and revision-loop planner respawn now dispatch with run_in_background=true and are followed by a real, bounded bash poll (gsd_stall_watch) that returns control to the orchestrator on its own schedule instead of waiting indefinitely on a subagent that may never return. On stall, the existing accept-plans/retry/ stop recovery menu (9a/11a) is auto-surfaced instead of requiring a manual interrupt. New config keys planner.stall_detect_interval_minutes (default 5) / planner.stall_threshold_minutes (default 10) mirror executor.stall_*. The helper functions (gsd_stall_should_recover, gsd_stall_watch) live in a new lazily-loaded gsd-core/workflows/plan-phase/steps/stall-detection- helpers.md rather than inline, and per-site prose is kept minimal, because plan-phase.md is frozen under the ADR-857 Phase 6 PRE_PHASE6 gate (tests/phase6-capstone-conformance.test.cjs) with ~36 bytes of headroom at baseline; the net effect is plan-phase.md.md ships slightly SMALLER than before (the old unconditional-wait ORCHESTRATOR RULE sentences are gone at the five touched sites, superseded by the bounded watcher). Also fixes a stale doc comment in tests/workflow-size-budget.test.cjs that still described the per-file workflow-size-baseline.json guard removed by #2724 (ADR-2719 Phase 4) as if it were still the enforcement mechanism — discovered while verifying this fix's own byte budget. Researcher and pattern-mapper spawns are untouched (out of scope per the issue's Agent Brief). * fix(#2650): make gsd_stall_watch single-cycle; harden numeric config inputs Two review findings addressed on top of the prior commit: 1. gsd_stall_watch previously looped internally for the full threshold+interval duration inside ONE Bash tool call (up to 15 min at defaults) — a single call blocking that long risks the host tool's own timeout killing it before it ever prints a result, silently defeating the fix. Redesigned to a single sleep-and-check cycle per call, taking an explicit dispatch_ts so the orchestrator prose can repeat the (short, default 5 min) call until it resolves; the outer threshold is now enforced by dispatch_ts accumulating across calls, not by one call's duration. Documented the resulting trade-off (up to one interval of added latency on the success path) in the changeset and reference doc. 2. PLANNER_STALL_INTERVAL_MINUTES/THRESHOLD_MINUTES are config-controlled values that flow into bash arithmetic ($(( ))). A review flagged this as command injection; empirically verified against both macOS bash 3.2.57 and Docker bash:5 that this is NOT actually exploitable (bash hard-errors on a `$(cmd)`-shaped arithmetic operand rather than invoking it) — but an unvalidated malformed value WOULD abort the stall-watcher itself with that bash error, silently defeating the exact hang-recovery this issue ships. Added integer validation with safe-default fallback, both at the config-resolution point and defensively inside gsd_stall_should_recover. Also adds the previously-missing integration coverage for gsd_stall_watch's real execution (grep/find/date plumbing), not just the pure classifier. * fix(#2650): correct AC2 self-test — helpers doc may name teams-status in prose The AC2 regression test asserted the stall-detection-helpers.md step file never contains the substring "teams-status" at all, but the file's own prose explicitly documents its independence from that guard (containing the word by design). Narrowed the assertion to what actually matters: no second `query teams-status` call site and no gating on it, not a blanket absence of the word. * test(#2650): regenerate golden install-tree fixtures for the new step file gsd-core/workflows/plan-phase/steps/stall-detection-helpers.md is an emitted file (installed for every runtime), so adding it changes the install tree even though it is invisible to docs/INVENTORY.md and docs/INVENTORY-MANIFEST.json (both explicitly scope to non-recursive gsd-core/workflows/*.md — verified against the execute-phase #2930 and pre-existing plan-phase step-file precedent, which are equally absent from both inventory artifacts). The golden install tree snapshots the sorted list of emitted relative paths per runtime, so a file invisible to the inventory is still visible here. Regenerated via `npm run gen:install-tree` — one line added per runtime fixture (19 files), no other drift. * fix(#2650): restore 7 ORCHESTRATOR RULE labels; sync runtime-launcher preamble Two more consequences of extracting helper bodies out of plan-phase.md, both caught by verification (0017e1a78, 9 unique failures): 1. tests/plan-phase-drift-guard.test.cjs (#913) requires at least 7 "ORCHESTRATOR RULE — ALL RUNTIMES" labels in plan-phase.md itself, one per agent spawn site. Moving the full explanatory blocks to plan-phase/steps/stall-detection-helpers.md carried 5 of the 7 labels out with them (only the untouched researcher/pattern-mapper sites kept theirs). Restored a short label at each of the 5 stall-watch sites, trimmed a few more redundant words ("Per 7.99, " — already established by the adjacent step-7.99 pointer) to stay under the frozen PRE_PHASE6 cap (94497 bytes, 21 bytes headroom). 2. tests/runtime-launcher-parity.test.cjs (#373) requires exactly one canonical gsd_run preamble, byte-equal to gsd-core/workflows/_runtime-launcher.snippet.sh, before the first gsd_run call in any workflow .md that calls it (recursive scan under gsd-core/workflows/, unlike the non-recursive inventory/step-tag-balance checks). The new step file's config-get calls use gsd_run without one. Fixed via `node scripts/sync-runtime-launcher.cjs`, verified: exactly 1 preamble occurrence, before the first call, including the .claude/ and .codex/ home fallback arms. Also verified (no fix needed, evidence recorded): the generic `gsd-core-verbatim` identity rule in tests/helpers/emitted-provenance.cjs (roots: ['gsd-core'], pattern matching workflows/.+) self-attributes any new gsd-core/workflows/** path to itself, so the new step file needs no drift-ack entry — consistent with plan-phase.md's own net shrinkage requiring none either. * test(#2650): acknowledge plan-phase.md's +14 byte drift Restoring the 5 ORCHESTRATOR RULE — ALL RUNTIMES labels (#913) flipped plan-phase.md from -142 bytes (post-extraction) to +14 bytes net growth against baseline (94483 -> 94497), which the differential attribution size ratchet (tests/emitted-attribution.test.cjs) correctly flags as unacknowledged growth. Added tests/emitted-drift-acks/2650-plan-phase- stall-detection.json, keyed on the bare filename plan-phase.md per the existing fragment schema (see tests/emitted-drift-acks/2649-diagnose- execute-plan-base-check.json), explaining the growth as exactly the 5 restored labels — still verified under the PRE_PHASE6 cap (94497 < 94519) and satisfying #913's 7-label requirement. * fix(#2650): bind {outputFile} from the real Agent() return — was dead code Independent review blocker: PLANNER_OUTPUT_FILE/CHECKER_OUTPUT_FILE were read by every gsd_stall_watch call but never assigned anywhere in the diff. With the variable permanently empty, `[ -f "$output_file" ]` was always false, marker_found could never become true, and marker_received was unreachable — the marker-based detection path was permanently dead. Worse for the plan-checker spawn specifically: a checker that PASSES touches no *-PLAN.md files, so it had no working completion signal at all without the marker path. A healthy plan-checker finishing cleanly in two minutes would be declared stalled once planner.stall_threshold_minutes elapsed and the recovery menu would fire on an already-succeeded agent — worse than the original unbounded hang. Fixed by replacing the dead bash variable with the `{outputFile}` orchestrator-substitution token, the same convention docs-update.md:471 already uses for a real run_in_background=true Agent() return ("Read tool: file_path: `{outputFile from README agent result}`"). This is a net BYTE SAVING at each site (`"{outputFile}"` is shorter than `"$PLANNER_OUTPUT_FILE"`), which funded moving the full binding explanation — including why plan-checker's *-PLAN.md glob alone is not a working completion signal — into the lazily-loaded reference file to stay under the frozen PRE_PHASE6 cap (94496 bytes, 22 headroom; net +13 over baseline, acknowledged in tests/emitted-drift-acks/2650-plan-phase- stall-detection.json). Added a regression test asserting plan-phase.md itself binds {outputFile} at all 5 spawn sites and contains no dangling $PLANNER_OUTPUT_FILE / $CHECKER_OUTPUT_FILE reference — the previous test suite only exercised gsd_stall_watch's behavior when handed a valid argument, which is why the dead production wiring survived two rounds of review. Also fixed tests/fix-2650-plan-phase-stall-detection.test.cjs:170-195's raw try/finally to use t.after(), per CONTRIBUTING's test-cleanup convention. * chore(#2650): backfill changeset PR number to 3015 * fix: normalize CRLF at the read boundary in all .md-bash-extraction tests Maintainer-authorized scope expansion, folded into this PR rather than deferred: the Windows CI lane on this PR's own tests/fix-2650-plan-phase- stall-detection.test.cjs exposed DEFECT.TEST-SHELL-PIPELINE-NONPORTABLE (CONTEXT.md; recurring since #1700) as a repo-wide latent class, not a one-off. Ten test files parse a fenced ```bash block out of a workflow .md file and execute it via spawnSync/execFileSync; a Windows checkout can yield CRLF line endings despite .gitattributes eol=lf, and bash then treats the trailing \r on every extracted line as part of the token — "unexpected EOF while looking for matching `"'" or a bare syntax error, partway through the script. Added tests/helpers.cjs:readFileNormalized() — strips \r\n -> \n at the read boundary, before any fence-slicing or regex runs, so every downstream operation is correct by construction. Migrated all ten call sites to it: Previously broken (fs.readFileSync with no normalization anywhere between read and spawn): - tests/worktree-cleanup.test.cjs (extractCwdGuardBash) — also fixes a misleading comment claiming the fence regex alone was "CRLF-safe"; it protected only the fence delimiters, never the captured body. - tests/new-milestone-clear-phases.test.cjs (extractFenceBetween, extractFenceContaining) - tests/code-review-pipeline-regression.test.cjs (extractPostProcessingScript) - tests/drift-detection.test.cjs (readGate/bashBlock, plus the snippet-file comparison read in the same test) - tests/graphify-visualization.test.cjs (extractStep3Block) - tests/pause-work-improvements.test.cjs (extractCheckBlock) - tests/plan-review-convergence.test.cjs (extractReviewerFlagsParseBlock and the inline post-config-gate resolution-block slices) Already correct (split(/\r?\n/) then join('\n')), migrated to the shared helper for consistency rather than a fourth/fifth/sixth copy of the same fix: - tests/git-base-branch.test.cjs (extractHandleBranchingBash) - tests/quick-branching.test.cjs (extractStep25Bash) - tests/runtime-launcher-parity.test.cjs (extractResolverSnippet) Verified against a simulated Windows CRLF checkout (not assumed): for both the worktree-cleanup.test.cjs and new-milestone-clear-phases.test.cjs extraction shapes, confirmed the pre-fix code produces a real bash syntax error on CRLF input and the post-fix code does not. One eslint follow-up: local/no-crlf-fragile-split statically flags any bare `\n` inside a markdown-fence-shaped regex, regardless of whether the receiver was already normalized — it cannot see the readFileNormalized() data-flow. Kept `\r?\n` in extractCwdGuardBash's fence regex (redundant but harmless on pre-normalized input) rather than fight the rule. Scope note: this diff is broader than issue #2650's own change (plan- phase.md stall detection) because the Windows lane surfaced a genuine repo-wide defect class while verifying that fix, and the maintainer authorized fixing it here rather than filing it separately and shipping a known-broken pattern. Runtime impact: none — this is a test-harness-only defect. The live orchestrator (Claude Code or another runtime) does not do a byte-exact extract-and-pipe of .md content into a shell the way these tests do; it reads the instructions and generates its own bash invocation text, which does not reproduce a raw CRLF pass-through the same way. Not touched: tests/plan-review-convergence.test.cjs's separate, tracked spawnSync ETIMEDOUT flake under bench load (#3005, reproduced on unmodified next) — unrelated load-sensitivity, not a CRLF symptom. * fix(#2650): remove stale drift-ack fragment — plan-phase.md is self-explaining tests/emitted-drift-acks/2650-plan-phase-stall-detection.json acknowledged plan-phase.md's own emitted-path hash move, but plan-phase.md is directly edited in this diff. Per the emitted-attribution law (ADR-2719, tests/emitted-attribution.test.cjs), a workflow's emitted key equals its own source path (gsd-core-verbatim identity rule), so a direct edit to the source is self-explaining and auto-attributed — no ack was ever needed. Verified via the pre-merge lint (scripts/lint-emitted-drift-ack.cjs, run through npm run lint:ci with a fully cleared eslint cache): it passes clean with the fragment removed, confirming no contradiction between the lint and the runtime attribution gate — this was simply an unnecessary fragment. * fix(#2650): restore plan-phase.md drift-ack — size ratchet demands it against next tests/emitted-drift-acks/2650-plan-phase-stall-detection.json was deleted in the previous commit because, against an earlier verification base, it was inert: it explained a moved emitted hash that a direct edit to plan-phase.md already self-attributes. Against origin/next@f1af47766a the demand is different: plan-phase.md is 13 bytes larger than the base copy, which trips the emitted-attribution size ratchet — a job this same ack also performs. Recreated in the documented shape, keyed on the bare filename plan-phase.md (not the full path, and not restating the byte delta per review guidance), describing the actual change: the {outputFile} binding fix for the dead PLANNER_OUTPUT_FILE/CHECKER_OUTPUT_FILE variables and the 5 restored ORCHESTRATOR RULE labels required by #913, both at the stall-watch spawn sites, with explanatory bodies living in the lazily-loaded gsd-core/workflows/plan-phase/steps/stall-detection-helpers.md reference. Confirmed no other fragment (on this branch or on next) claims the bare key "plan-phase.md" before recreating — scripts/lint-emitted-drift-ack.cjs's duplicate check is an exact string match, and the only other mention of plan-phase.md in tests/emitted-drift-acks/ (2658-trae-instruction-file-path.json) uses the full path as its key, so there is no collision. * fix(#2650): real cause of Windows CI failure — bash -c argv-transport, not CRLF The CRLF diagnosis for PR #3015's Windows failure was wrong. Proven wrong, not assumed: .gitattributes' blanket `* text=auto eol=lf` means a Windows checkout never receives CRLF for stall-detection-helpers.md, and the extracted fence's line 64 is byte-identical and correctly balanced on every platform. The real cause: runShouldRecover() passed a 70+ line, quote-dense script as ONE argv element to `spawnSync('bash', ['-c', script, arg0, ...])` PLUS four more positional args. Windows has no execve — Node serializes that whole argv into a single CreateProcess command-line string, and Git Bash's MSYS layer re-splits and unescapes it with its own rules. The boundary between the script and the trailing args was not stable across that round trip (live evidence: one failure's stderr was prefixed `gsd_stall_should_recover_test:` — arg0 arrived — another `/usr/bin/bash:` — arg0 did not). Fixed by writing the script to a temp file and running `bash <file> <args>` instead — the four values are now normal, quote-free positional args, and the script itself never enters argv transport at all. Mirrors tests/quick-branching.test.cjs's extractStep25Bash/runStep, which already uses this exact shape and is green on Windows on `next`. tests/worktree-cleanup.test.cjs's extractCwdGuardBash/runGuard stays on `bash -c` but never appends extra positional args beyond the script itself, so it never hits the same boundary — checked both siblings per review, not assumed. Corrected the now-actively-misleading CRLF comment in extractStallHelpersBash(), and corrected the changeset's claim that the repo-wide CRLF-normalization fix (folded into this branch, maintainer- authorized) explains this PR's own Windows failure — it doesn't, though it remains defensible on its own merits as general test-portability hardening. Separately, while auditing the shipped (non-test) gsd_stall_watch for Windows portability per review request, found and fixed a second, real user-facing defect: the artifact-freshness check used GNU find's `-newermt "@<epoch>"` shorthand, which the BSD find(1) actually shipped on macOS does NOT understand ("Can't parse date/time: @<epoch>", verified live against /usr/bin/find on both a stale and a genuinely fresh file). With the adjacent `2>/dev/null`, that failed silently and permanently degraded artifact_fresh to false on every macOS run — a plan-checker or planner actively writing plan files could still be reported "stalled." Replaced with `find $glob -mmin -N` ("modified less than N minutes ago"), which needs no date-string parsing and is supported identically by GNU find and BSD find; verified live that the old shape fails and the new shape passes against the same real fresh file. Added a real-execution regression test (gsd_stall_watch with `sleep` stubbed to a no-op so the test doesn't actually wait, but the real `find ... -mmin` line still runs) proving the fix, replacing the prior "not integration-tested" note for that path. Note: the remote gsd-test runner is Linux-only, so it cannot itself confirm the Windows fix — only the actual windows-latest CI lane can. * fix(#2650): route the third bash -c call site through the same temp-file seam runWatch() and a `-mmin` regression test still passed their script via `bash -c <script>` after the previous commit only converted runShouldRecover() — live Windows CI on 4b86cc57f confirmed the mechanism: failures went 11 -> 4, and `full test (windows-latest, 22, shard 1/3)` and `shard 2/3` flipped from fail to pass, but the remaining 4 failures (all in this file, all still `bash: -c:`) were exactly the gsd_stall_watch describe block, which runWatch() serves. runWatch() passes NO extra positional args at all, so this also rules out the trailing-args theory from the prior commit: the ~73-line, quote-dense script itself is what does not survive Windows argv serialization when passed as a single `-c` element, regardless of how many (if any) further argv elements follow it. Extracted one shared runBashScript(script, args, opts) helper — write to a fs.mkdtempSync'd file, run `bash <file> [args...]`, clean up in `finally` — and routed all three bash-invoking call sites in this file through it (runShouldRecover, runWatch, and the -mmin freshness test that builds its own script inline for the `sleep` stub). One transport seam means a fourth call site in this file cannot silently reintroduce the bug in isolation, which is exactly what happened here with a second call site. Corrected extractStallHelpersBash()'s doc comment a second time to state the mechanism precisely (script content, not argv-element count) and cite the live evidence (11->4 failures, shards 1 and 2 flipping green) so the next reader does not have to rediscover it. Audited every other bash-invoking call site in files this branch touches, per review request: - tests/code-review-pipeline-regression.test.cjs (runPostProcessing), tests/graphify-visualization.test.cjs (runBlock), and tests/drift-detection.test.cjs (two execFileSync('bash', ['-c', ...]) sites, one of them carrying the same giant runtime-launcher preamble text) — all pre-existing, UNCHANGED by this branch (only touched for the readFileNormalized() CRLF swap), and already exercised on `next`'s last six Windows CI runs per the reviewer's own citation. Left as-is: no evidence of failure, and converting untested pre-existing code outside #2650's scope on an unverifiable guess would be its own risk. - tests/git-base-branch.test.cjs (runHandleBranchingStep) and tests/quick-branching.test.cjs (runStep) already use the same temp-file pattern. No action needed. - tests/runtime-launcher-parity.test.cjs (runResolver) uses `bash -c` but is explicitly `if (process.platform === 'win32') return '';` guarded off on Windows entirely, for an unrelated extension-less-PATH-stub reason — never reaches Windows argv transport at all. No action needed. - tests/worktree-cleanup.test.cjs (runGuard) confirmed by the reviewer as correct and verified; not touched, per instruction. Do not touch: the -mmin fix, the drift-ack fragment, the changeset — all three confirmed correct in prior rounds and left untouched here. Note: the remote gsd-test runner is Linux-only and cannot confirm this; only the windows-latest lanes on #3015 can. * fix(#2650): give runBashScript a default timeout runShouldRecover() was the only one of the three call sites through runBashScript() with no timeout — runWatch() and the -mmin test both pass timeout: 10000 explicitly. Not a regression (this path never had a bound before), but CONTEXT.md's unbounded-subprocess guidance applies directly, and runShouldRecover() is driven repeatedly by a fast-check property test: one pathological input that fails to terminate would hang CI indefinitely instead of failing. timeout: 10000 is now the helper's own default, with ...opts spread after it so the two existing explicit timeout: 10000 call sites are unchanged and any future caller inherits a bound automatically. * fix(#2650): build the -mmin freshness test's glob with forward slashes Windows CI on d6ddda6ea reported the last failure: the -mmin regression test expected 'active' but got 'waiting' — find matched nothing, the same silent-degradation shape as the macOS -newermt defect, but this time in the test's own fixture rather than the shipped bash. Traced what production actually passes: every gsd_stall_watch call site in plan-phase.md builds artifact_glob as `"${PHASE_DIR}"'/*-PLAN.md'` — PHASE_DIR is a POSIX-style .planning/phases/NN-slug value, and the whole thing runs under Git Bash regardless of host OS, so production's glob is always forward-slash. The test instead built it with `path.join(tmp, '*-PLAN.md')`, which on Windows yields a backslash path (C:\Users\RUNNER~1\...\*-PLAN.md). In bash pathname expansion a backslash escapes the next character, so that pattern can never match a real path — find silently returns empty under the existing 2>/dev/null, same shape as the macOS bug. Confirmed as a test artifact, not a production defect: production never constructs the glob this way, so no Windows user is affected. Fixed by forward-slashing the tmp dir before appending the glob suffix, matching production's own convention, with a comment recording why (so a future "simplify this back to path.join" edit doesn't silently reintroduce the failure). The shipped bash's unquoted $artifact_glob is untouched — quoting it would break the multi-file glob expansion it exists for. Note: the remote runner is Linux-only and already passed clean at d6ddda6ea (0/29,603, both node lanes); only the windows-latest lanes on #3015 can confirm this fix. * fix(#2650): forward-slash the three remaining runWatch globs (vacuous-pass CR) The :353 fix (833c11da9) only converted the -mmin freshness test's glob. Three sibling tests in the same describe block still built theirs with path.join(tmp, '*-PLAN.md'), which yields a backslash path on Windows. Two of those three were silently passing for the wrong reason: the '-> stalled' and '-> waiting' tests both expect the glob to match nothing, and on Windows a backslash path matches nothing regardless of whether the directory is actually empty (bash eats each backslash as an escape before the pattern is even evaluated). They would have passed identically with glob expansion completely broken, which is a vacuous pass — not exercising what they claim to. The third ('-> marker_received') is outcome-independent of the glob, so it was merely inconsistent rather than wrong. Converted all three to the same `${tmp.replace(/\\/g, '/')}/*-PLAN.md` construction already used at the -mmin test, so every glob in the file now matches production's own forward-slash `"${PHASE_DIR}"'/*-PLAN.md'` shape, and the two negative tests are meaningful on Windows instead of accidentally correct. Reworded the trailing comment on the 'stalled' test's glob line: it now describes the fixture (the tmp dir contains no *-PLAN.md files) rather than the pattern, since "matches nothing" read as a property of the glob syntax when it's a property of what's on disk. No assertion, the sleep stub, runBashScript, or the shipped bash changed. Smoke-tested all three updated tests manually before committing (not via node --test): marker_received / stalled / waiting, all correct. * fix(#2650): fix own regression tests for #2993's plan-phase.md relocation 531101843's merge with origin/next brought in #2993 (unrelated, epic #1671 Phase 6.2), which extracted plan-phase.md's whole "Chunked Planning Mode" section into gsd-core/workflows/plan-phase/steps/chunked-planning-mode.md, leaving a <!-- gsd:section --> pointer behind. tests/plan-phase-drift-guard. test.cjs (#913) was already updated to read the combined surface (host file + every steps/*.md) so its label count didn't go blind — my own #2650 regression tests were not, and searched plan-phase.md alone for the two chunked spawn sites' headings, which no longer exist there. Two tests failed outright (indexOf returning -1); a third ("standard planner spawn") was silently weakened to an unbounded slice-to-EOF by the same relocation, since its own end-boundary heading also moved — passing by accident rather than by testing what it claimed. Promoted the drift guard's local readPlanPhaseCombined() to a shared, exported tests/helpers.cjs readWorkflowCombined(workflowPath) (host file + sorted steps/*.md, CRLF-normalized at the read boundary) so a second, divergent implementation is never written — the drift guard now delegates to it via a same-named local wrapper, unchanged at every existing call site. Fixed the three affected tests in tests/fix-2650-plan-phase-stall-detection. test.cjs: - "standard planner spawn (step 8)": end boundary changed from the now-gone "## 8.5. Chunked Planning Mode" heading to "## 9. Handle Planner Return", which still exists in plan-phase.md. - "chunked outline spawn (8.5.1)" / "chunked per-plan spawn (8.5.2)": now read gsd-core/workflows/plan-phase/steps/chunked-planning-mode.md directly (not the generic multi-file combined blob, whose file-sort ordering would put unrelated step files between 8.5.2's slice and any downstream anchor) — the same heading-to-heading slicing as before still works because the file is small and self-contained. - Extended the "no unbound $PLANNER_OUTPUT_FILE/$CHECKER_OUTPUT_FILE" check to also scan chunked-planning-mode.md, since two of the five spawn sites now live there. - Added a new count-based test asserting exactly 5 (not "at least one") `gsd_stall_watch "$TS" "{outputFile}"` invocations across the combined surface, mirroring #913's own label-count guard, so every one of the five spawns stays provably bounded and a future relocation can't silently drop one without a test noticing. Also added a small positive test that plan-phase.md's <!-- gsd:section --> pointer to chunked-planning-mode.md exists (#2993 is unrelated to #2650 but its presence is now load-bearing for where 2 of the 5 spawn sites live). Audited every other test file in the repo for a stale reference to content #2993 relocated (searched for the moved headings/prose and for "chunked-planning-mode"/"CHUNKED_MODE" across all *.test.cjs): only this file and the drift guard needed changes. tests/issue-2762-plan-reviews-chunked.test.cjs already reads chunked-planning-mode.md directly (brought in correct by the same merge). gen-section-manifest.test.cjs, init.test.cjs, and workflow-fragments.test.cjs reference "chunked-planning-mode" only as a manifest/section-id fixture value for #2993 itself, not as a stale pointer to relocated content. Did not touch: the ported ORCHESTRATOR RULE lines, run_in_background=true, the glob constructions, runBashScript, the -mmin change, the timeout default, or the drift-ack fragment (confirmed correct against the stale local `next` ref two rounds ago and left alone). --------- Co-authored-by: sim <sim@local>	2026-08-03 10:46:22 -04:00
Tom Boucher	ad3b9ec486	chore(#1671): fragmentize plan-phase.md and repair flag forwarding to the init bundle — Phase 6.2 (#3019) ... * chore(#2993): fragmentize plan-phase.md onto the fragment model Epic #1671 Phase 6.2. plan-phase.md is the largest workflow in the repo and carried zero markers; it was deferred out of the Phase 3 pilot for two reasons, both now dead. The 36-byte PRE_PHASE6 headroom was never the blocker it looked like — fragmentizing is net-negative on host source, so the trim is what creates the room. The --mvp interleaving was resolved by measurement in #2992 and no sub-line mechanism is built. - widen WHEN_VOCABULARY 14 -> 19 via a second coordinated ADR-1671 amendment: flag:--ingest, flag:--prd, flag:--research-phase, flag:--reviews, state:chunked-mode - state:chunked-mode is `--chunked` OR config workflow.plan_chunked, and that disjunction is resolved in the FACT, never in the grammar, so a compound condition never becomes an operator - parse the new flags on the plan-phase route; extract six gated bodies to gsd-core/workflows/plan-phase/steps/ behind manifest-gated stubs - prd-express-path.md was already extracted but read unconditionally; its wrapper is now gated, so the existing extraction finally pays off plan-phase.md 94,483 -> 87,575 bytes (cap 94,519): headroom goes from 36 bytes to 6,944. Also closes a surfaced docs gap: five real plan-phase flags (--chunked, --skip-ui, --bounce, --skip-bounce, --granularity) were documented in neither the argument-hint nor help. Making --chunked load-bearing without fixing its siblings would leave the defect class half-open. Refs #2993 * fix(#2993): forward flags to the init bundle so section gating actually fires Blocker found by the correctness review, confirmed directly, and missed by both the isolated reviewer and every test in this branch. Neither workflow forwarded its flags to the init CLI: plan-phase.md:71 INIT=$(gsd_run query init.plan-phase "$PHASE" $GRAN_PARAM) execute-phase.md:84 INIT=$(gsd_run query init.execute-phase "${PHASE_ARG}") So every flag: atom was permanently false in production and its section permanently excluded. For plan-phase that made the PRD express path UNREACHABLE — a regression, since it was an unconditional read before. For execute-phase this is PRE-EXISTING: #2932 shipped `flag:--wave` gating that has never once been true, so `--wave` silently dropped its own wave-filtering guidance. Fixed here under the no-defer rule. Why every test missed it: they drive the init CLI directly with flags, which works. Production goes through the workflow's bash line, which did not pass them — the exact "assert against the shape production uses" trap this branch's own test matrix warns about. - parse and forward --prd/--ingest/--research-phase/--reviews/--chunked (plan-phase) and --wave (execute-phase), using the anchored regex idiom the neighbouring GRAN_PARAM line already uses - add a regression guard DERIVED FROM THE MANIFEST: for every flag:--X section, the owning workflow's init line must forward --X. It fails against the pre-fix files and covers any future atom, rather than spot-checking today's six. Verified through the workflow shape, not the CLI shape: `3 --prd spec.md` now yields ["prd-express-gate"] (was []), `2 --wave 2` yields ["partial-wave"] (was []). Refs #2993 * test(#2993): acknowledge the execute-phase ripple and regenerate install-tree fixtures Remote matrix was red with 46 unique failures, identical on both lanes. Both causes are mechanical consequences of changing shipped workflow content, and neither is visible to any local gate. - emitted-attribution: execute-phase.md grew 163 bytes from the WAVE_PARAM forwarding fix and was unacknowledged, while the ack fragment named plan-phase.md, which SHRANK and therefore needed no ack at all — a stale entry is itself a failure. The reason now names the real ripple. The entry had to merge into the existing 2930 fragment: the ack linter does unconditional cross-fragment duplicate-key detection with no spent/live exception, so a second fragment declaring execute-phase.md collides even when the first is already merged and inert. Resolved per the linter's own guidance and that file's precedent of appending successive ripple reasons to one entry. - golden-install-tree: tests/fixtures/install-tree/*.json are committed and deliberately excluded from the ADR-2719 attribution cutover, so they must be regenerated when shipped tree content changes. Regenerated after build:lib per the ordering landmine. 19 runtimes each gained exactly the six new plan-phase step files; zero paths removed, which is the absolute failure shape those fixtures exist to catch. Refs #2993 * fix(#2993): restore the launcher preamble in an extracted step and follow moved content in its drift guards Second red run: 26 unique failures, identical on both lanes, in two classes. RUNTIME BUG (runtime-launcher-parity, 7 failures) — chunked-planning-mode.md calls gsd_run but carried no canonical launcher preamble, which is what DEFINES gsd_run(). On any non-Claude runtime that step would fail outright. The preamble is now copied verbatim from the canonical source of truth, gsd-core/workflows/_runtime-launcher.snippet.sh, and the fence dedented to column 0 to match the prd-express-path.md sibling (a list-continuation indent breaks the byte-equal preamble match). prd-express-path.md already had a correct one. This is the same defect #2932 hit when it extracted steps; the parity test caught a real bug, not a stale assertion. DRIFT GUARDS (plan-phase-drift-guard, issue-2762-plan-reviews-chunked, skill-frontmatter-contract) — these assert plan-phase.md contains content this branch moved into step files. Retargeted at where the content now lives, with the asserted property unchanged; the ALL-RUNTIMES label COUNT test now reads host + every step file so the count is preserved across the split rather than reduced. Each retargeted guard was verified to still fail when its step file is stripped, so none was weakened into vacuity. No emitted-drift ack was needed: currentSizes() enumerates gsd-core/workflows/*.md non-recursively, so files under plan-phase/steps/ are never in the size ratchet's scope. Refs #2993 * chore(#2993): backfill changeset pr number to 3019 --------- Co-authored-by: sim <sim@local>	2026-08-03 09:38:58 -04:00
Tom Boucher	a987cf2731	chore(#2932): emit a per-invocation section manifest from the init bundle (#2987) ... * chore(#2932): emit a per-invocation section manifest from init Extends the init bundle with a typed per-invocation section manifest so an invocation loads only the branch guidance it will actually take. The three flag/state-gated branches in execute-phase.md move into their own step files; the parent keeps its gsd:section markers wrapping a one-line on-demand reference, so each section's prose lives in exactly one file and the parent shrinks 93369 -> 89507 bytes. A new drift-guarded generator derives the shipped section manifest from those markers, and a new pure evaluator maps invocation facts to applicable section ids. The evaluator is a lookup over the frozen WHEN_VOCABULARY, never a parser (Greenspun's Tenth Rule, ADR-1671:69); a parity test asserts the vocabulary and the predicate map stay exhaustively in sync. Closes #2932 * fix(#2932): fail closed on prototype-chain when values An isolated adversarial review found WHEN_PREDICATES[section.when] was a bracket lookup on a plain-prototype object, so inherited Object.prototype members resolved as predicates: "constructor"/"toString"/"valueOf"/ "hasOwnProperty" returned truthy and SILENTLY INCLUDED the section, and "__proto__" threw an untyped TypeError carrying no .reason. Both violate the module's documented fail-closed contract, and the manifest is read from disk at run time so it cannot be assumed trustworthy. Builds the predicate map on a null prototype and guards the lookup with an explicit Object.hasOwn check. Adds table-driven coverage for nine Object.prototype-shaped keys asserting the TYPED reason (asserting only that it throws would still pass while broken) plus a fast-check property injecting a hostile value at an arbitrary document position. * test(#2932): retarget execute-phase step assertions at extracted step files * fix(#2932): emit typed reasons for generator lib-load and write failures * fix(#2932): restore launcher preamble in extracted steps and refresh derived fixtures * chore(#2932): backfill changeset pr number to 2987 --------- Co-authored-by: sim <sim@local>	2026-08-02 12:34:41 -04:00
Tom Boucher	4f6935e29b	fix(#2717): write CommonJS marker for cursor/windsurf/codex staged .js hooks (#2846) ... * test(#2717): CommonJS marker for cursor/windsurf/codex staged .js hooks Cursor/windsurf (skipSharedHooksInstall) and codex (!isCodex gate) stage .js hook scripts via dedicated paths that bypass installSharedHooksBundle — the only writer of the {"type":"commonjs"} marker. Under a config root declaring {"type":"module"}, Node loaded those scripts as ESM and every require() failed with 'require is not defined', silently disabling the runtime's hooks. Adds regression tests (RED first, fix lands next commit): - parametrized cursor/windsurf/codex install asserts hooks/package.json exists with exactly GSD's marker content; - end-to-end: a cursor require()-using hook loads under a planted ESM-typed config root without the require-is-not-defined error; - the ensureCommonJsMarker / removeCommonJsMarkerIfGsdOwned contract: GSD markers are removed on uninstall, user-authored package.json is never touched. * fix(#2717): write CommonJS marker for cursor/windsurf/codex staged .js hooks The {"type":"commonjs"} marker lived only inside installSharedHooksBundle, which cursor/windsurf (skipSharedHooksInstall) and codex (!isCodex gate) never reach. Their .js hooks are staged by dedicated paths, so under a config root declaring {"type":"module"} Node loaded them as ESM and every require() failed with 'require is not defined', silently disabling those runtimes' hooks. Decouple the marker write into a shared helper so any code path that stages .js hooks can ensure it lands in the SAME directory as the scripts: - src/runtime-hooks-surface.cts: add ensureCommonJsMarker(dir) + removeCommonJsMarkerIfGsdOwned(dir) (byte-identical content to installSharedHooksBundle's marker; preserves a user-authored package.json on both write and uninstall). Call ensureCommonJsMarker(hooksDir) from writeCursorHooksJson + writeWindsurfHooksJson; call removeCommonJsMarkerIfGsdOwned on their matching remove paths. Export both. - bin/install.js: call hooksSurface.ensureCommonJsMarker after the codex hook copy; call hooksSurface.removeCommonJsMarkerIfGsdOwned in the generic hooks-removal loop (safe no-op where no marker exists). No change to which runtimes receive the shared bundle, the !isCodex gate, skipSharedHooksInstall, or kimi/kimi-code/cline/copilot/trae/zcode (all unchanged — audit in the diagnosis). RED @ dbb7d2bb (6 failures: 3 missing markers + the ESM require error + missing helpers); GREEN pending. * docs(#2717): changeset fragment (pr:0, backfilled post-PR) * chore(#2717): regen codex/cursor/windsurf install-tree fixtures + attribution ack The fix adds hooks/package.json to those three runtimes' install trees (the new CommonJS marker), so the golden install-tree fixtures gain one path each (regenerated via npm run gen:install-tree). emitted-attribution (ADR-2719) flags the 3 emitted hooks/package.json paths under the hooks-built rule; acknowledge them. Also drops 5 spent ack entries left by now-merged PRs (#2694 code-review.md/code-review-fix.md, #2695 worker/registry, #2794 review.md) — they are stale on this branch (base already carries them). * fix(#2717): codex ESM-root behavioral test + hooks-built provenance for package.json Two review-driven follow-ups on the #2717 fix: - Adversarial review noted the ESM-root behavioral test covered only cursor; refactor it into a helper and add a codex case (the !isCodex-gated path most likely to regress, whose marker write lives in bin/install.js). gsd-check-update.js require()s at module load, so it surfaces the ESM failure immediately. - emitted-provenance flagged hooks/package.json as 'attributed source does not exist' — the marker is code-derived (a fixed literal emitted by ensureCommonJsMarker at install time), not built from a tracked source. Route the hooks-built rule's sources/transforms for package.json to the surface source file, mirroring the existing .cmd-shim sub-family. * chore(#2717): drop now-redundant hooks/package.json attribution ack The hooks-built provenance routing (prior commit) now self-attributes the emitted hooks/package.json to src/runtime-hooks-surface.cts, which IS in this diff — so the attribution is self-explaining and the emitted-drift-ack entry became stale. Delete the (now-empty) ack file per ADR-2719's empty-file rule. * docs(changeset): backfill #2717 PR number to 2846	2026-07-29 22:18:48 -04:00
Tom Boucher	c7c2fe3c2b	fix(#2587): resolve cursor hook workspace from workspace_roots, not cwd (#2680) ... * fix(#2587): resolve cursor hook workspace from workspace_roots, not cwd gsd-cursor-session-start.js and gsd-cursor-stop.js both resolved the project as path.join(process.cwd(), '.planning', 'STATE.md'). Under the cursor-agent CLI, hooks are invoked with cwd set to the Cursor config dir (~/.cursor), not the workspace — so the lookup always missed. sessionStart could only ever emit the "no .planning/ workflow found" nudge and stop's verify-work reminder could never fire, even with .planning/STATE.md sitting in the workspace. Slash commands were unaffected, which is why only the hook layer looked blind. Both hooks already buffered stdin into `raw` and never parsed it; the payload's workspace_roots carries the real path. Multi-root was left open in the report ("first root vs any root"). Resolved forward: prefer the first root that actually carries .planning/STATE.md, so a workspace whose GSD project is not the first root still resolves — strictly better than first-root-only and identical to it in the single-root CLI case. Falls back to roots[0], then to cwd, keeping IDE behavior unchanged if the IDE ever invokes hooks from the workspace. The resolver is duplicated verbatim across the two scripts rather than shared via hooks/lib/: these hooks ship standalone, and a new hooks/lib/ file must be registered in the GENERATED installer's GSD_HOOK_LIB_FILES allowlist — the installer-omits-shipped-file class that yields MODULE_NOT_FOUND at runtime. Per CLAUDE.md "Generative Fix Divergence", the duplication carries a parity assertion so the copies cannot drift. Failing-first, demonstrated by direct invocation with cwd != workspace: pre-fix sessionStart -> "no .planning/ workflow found" stop -> {} post-fix sessionStart -> ".planning/STATE.md is present" stop -> reminder tests/fix-2587-cursor-hook-workspace-roots.test.cjs spawns the real scripts as child processes with a cwd lacking .planning/ and workspace_roots pointing at it. Boundary coverage on the roots array (0 / 1 / 2 entries), plus malformed-JSON fail-open, junk-entry filtering, the parity assertion, and a guard that neither script resolves .planning from cwd again. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015TCwhbMuY37DzRMCfzTABJ * fix(#2587): extend workspace_roots fix to subagentStart; keep cwd a candidate Three findings from the isolated review, all fixed. 1. MISSED SITE (high). gsd-cursor-subagent-start.js carried the identical defect at line 43 — its own header documents workspace_roots in the input schema, but it resolved .planning/ from process.cwd() anyway. Under the cursor-agent CLI that meant every Cursor subagent (planner, executor, verifier) started with "no .planning/ workflow found" and no phase context. The report named only sessionStart and stop; the defect class was wider. Verified pre-fix vs post-fix by direct invocation with cwd != workspace. 2. SEMANTIC NARROWING (medium). The first cut searched only workspace_roots and fell back to cwd solely when the array was EMPTY. So when roots were supplied but none carried .planning/ while cwd did, the hook reported absent — where the pre-fix code, which always used cwd, reported present. That contradicted the fallback's own stated intent of preserving IDE behavior. cwd is now a CANDIDATE in the search (`[...roots, process.cwd()]`), so the fix is a strict superset of both the old behavior and the CLI fix, never a narrowing. 3. STALE GOLDEN FIXTURES (high, would have failed CI). The golden-install-parity fixtures store a content hash per installed file; these three hooks appear in 13 of the 19 runtime fixtures. Regenerated via `npm run gen:golden` — the diff is exactly the three hook hashes in exactly those 13 runtimes. Tests extended: subagentStart resolution via workspace_roots; the stop hook's absent branch (previously only session-start's was covered); an explicit regression guard that a project at cwd is still found when roots miss; parity now asserts all THREE copies byte-identical; and the cwd guard sweeps the whole RESOLVING_HOOKS list so a future hook in this family cannot be left on cwd. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015TCwhbMuY37DzRMCfzTABJ * refactor(#2587): extract cursor workspace resolution to a shared hooks/lib module The duplicate-plus-parity-test approach was the wrong call. The reported issue named two hooks; a third (subagentStart) had the identical defect. That is the signature of a systemic problem, and three copies of a resolver guarded by a parity assertion is a divergence risk maintained by hand rather than a fix. hooks/lib/cursor-workspace.js is now the single implementation. All three Cursor hooks require it; none defines a local copy. Divergence is prevented structurally instead of by asserting three copies stay byte-identical. The reason duplication looked necessary was real, and is fixed properly here rather than worked around: Cursor sets hostBehaviors.skipSharedHooksInstall (#2089), so it never reaches the installer's bulk hooks/lib copy — it was the ONE runtime shipping these hooks WITHOUT hooks/lib (verified against all 19 golden fixtures: cursor had the hook scripts, no lib). A naive require would have thrown MODULE_NOT_FOUND at load, BEFORE each hook's own try/catch, wedging every session on precisely the runtime this bug is about. writeCursorHooksJson (src/runtime-hooks-surface.cts) now stages the hooks/lib helpers the staged scripts actually require, discovered by scanning their require('./lib/…') calls rather than a hardcoded name — so a future helper cannot be silently omitted. This is narrower than flipping skipSharedHooksInstall, which would wrongly pull in every shared hook. cursor-workspace.js is also added to GSD_HOOK_LIB_FILES so uninstall and the manifest manage it for the runtimes that do receive hooks/lib. Verified against a REAL install (runMinimalInstall, cursor/global): the helper is staged, and all three INSTALLED hooks resolve the workspace end-to-end from a cwd that is not the project. Also closes the review gap that the stop hook was excluded from the cwd-candidate regression loop — it now sweeps RESOLVING_HOOKS. The byte-parity test is replaced by a structural guard (every hook requires the shared module, none redefines it) plus a new install test asserting the helper is staged and the installed hook actually loads against it. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015TCwhbMuY37DzRMCfzTABJ * fix(#2587): fail loud on a missing hook lib source; drop unsubstituted version marker Two findings from the installer-focused review. H1 — the staging step's `if (!fs.existsSync(libSrc)) continue;` silently defeated the very guarantee it was added for. Reproduced: delete hooks/lib/cursor-workspace.js from source, run the cursor install — it exits 0, prints "Done!", and ships the three hook scripts with an EMPTY hooks/lib/. The installed hook then throws `Cannot find module './lib/cursor-workspace.js'` at load, before its own try/catch, wedging every session — and nothing surfaces until a user hits it. The scan protected against a required-but-UNLISTED helper while leaving required-but-MISSING wide open (typo, bad rebase, an accidental delete). It now throws: a missing helper source is a packaging bug and aborts the install. M1 — hooks/lib/cursor-workspace.js carried a `gsd-hook-version: <placeholder>` marker that NOTHING substitutes: copyLibDir stamps .sh files only, and writeCursorHooksJson's staging applies just the colon-to-dash rewrite. Verified the literal was reaching disk on both the bulk (--claude) and Cursor (--cursor) paths. hooks/lib/git-cmd.js — the only pre-existing hooks/lib/*.js — carries no such marker, so this was newly introduced, not inherited. Marker removed, matching that precedent, with a note on why. (The explanatory comment deliberately does not spell the token out, or it would reintroduce the literal.) M2 — the require-scan regex demanded the exact compact form, so `require( "./lib/x.js" )` would silently fail to stage its helper and compound H1. Now tolerant of interior whitespace and either quote style. Regression test added for H1 — the reviewer confirmed the invariant had zero coverage repo-wide: a source tree carrying the hooks but no hooks/lib/ must make writeCursorHooksJson throw rather than produce a broken install. Re-verified end to end: the missing-source case throws, no unsubstituted literal ships, and the installed hook still resolves the workspace from a foreign cwd. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015TCwhbMuY37DzRMCfzTABJ * chore(#2587): backfill changeset pr number (#2680) --------- Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>	2026-07-26 19:57:58 -04:00
Tom Boucher	6ee4349272	fix(#2537): extract offer_next step to references/ (~3.3KB headroom restored) (#2642) ... * fix(#2537): extract offer_next step to references/ (~3.3KB headroom restored) * chore(#2537): backfill changeset pr to 2642	2026-07-25 05:30:20 -04:00
Tom Boucher	6ad30f74b6	feat(#2584): Phase 3 — scheduler consumer + isolation adapters (#2635) ... Final phase of #2584 (ADR-1239 Codex-binding amendment). execute-phase now negotiates dispatch.isolation and dispatches through the matching adapter, so a wave's independent plans run concurrently on six runtimes instead of one — with no runtime=== branch in the scheduler. harness-worktree passes the host's declared isolation flag (claude, cursor); orchestrator-worktree creates the worktree via the Phase-2 verb and spawns the executor into it with the resolved argv/cwd (codex, opencode, kimi, kimi-code); none stays sequential. Undeclared/unknown/unresolvable isolation degrades to none — never an unisolated parallel run. Fixes two shipped Phase-2 descriptors that per-host research found would fail at spawn: kimi lacked its headless flag (would launch the interactive TUI and hang the orchestrator), and kimi-code named a non-existent binary (Kimi Code installs as 'kimi'). Adds the worktree-path root confinement Phase 2 deferred here, and leading-dash guards on the resolver's prompt/cwd matching the existing git-argument guard. Closes #2627 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>	2026-07-25 01:50:20 -04:00
Tom Boucher	f654c24a3e	feat(#2505): Phase 4 — runtime-aware subagent dispatch (Option A; resolve-dispatch-type query) (#2525) ... * feat(#2508): Phase 4 Option A — runtime-aware subagent dispatch via resolve-dispatch-type query (#2505) * fix(#2508): prose-variant preamble (avoid scanner-tripping literals) + namedDispatch===false-only mapping * fix(#2508): remove leftover old-preamble lines (keep prose variant only) * fix #2508: prose-only reference file * test #2508: regen golden install parity after workflow preamble additions * fix #2508: remove preamble from plan-phase.md (Phase 6 capstone ceiling); regen size+golden baselines * docs(changeset): backfill PR #2525 for Phase 4 (#2508)	2026-07-22 10:22:42 -04:00
Tom Boucher	c5e0371775	feat(#1951): reversibility tagging — gate one-way-door decisions (#2471) ... * test(#1951): add failing-first tests for reversibility tagging Red phase for issue #1951 (reversibility tagging: classify decisions by undo cost, gate one-way doors behind a checkpoint:decision). Tests assert, per the issue's acceptance criteria: - discuss-phase CONTEXT.md template records a **Reversibility:** field with a rationale on captured decisions, and states it is optional - gsd-planner @-references planner-reversibility.md and stays under the 49152-char agent cap (LARGE_CAP, tests/agent-size-budget.test.cjs) - a one-way rating inserts a checkpoint:decision before the dependent task; reversible inserts none; costly is flagged but never blocks - the taxonomy defaults to reversible when unsure (checkpoint-fatigue guard) and inserting a checkpoint implies autonomous: false - docs/reference/plan-md.md documents <reversibility> as optional with all three ratings - --no-reversibility-gates parses to REVERSIBILITY_GATES=false, is injected into the planner prompt, and is advertised in the command argument-hint and help full mode (argument-hint parity) - the override suppresses the gate but still persists the rating - cmdVerifyPlanStructure accepts every rating and the absent case (additive-validator guarantee, behavioral via runGsdTools) - parity: thinking-models-planning.md #4 adopts the canonical three-level taxonomy and the binary REVERSIBLE/IRREVERSIBLE vocabulary is gone - no content loss from the planner extraction made to fit under the cap Prose-contract assertions are Red until the implementation lands. The behavioral validator assertions pass immediately — regression guards proving the validator already accepts unknown optional tags. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * feat(#1951): reversibility tagging — gate one-way-door decisions Classify planning decisions by what undoing them would cost, and give a one-way door a human beat before the agent walks through it (issue #1951, The Pragmatic Programmer Topic 15 'Reversibility'; Bezos's one-way/two-way door framing). Acceptance criteria met: - discuss-phase records an optional reversibility rating with a rationale on <decisions> entries in the phase CONTEXT.md template. Unrated decisions are treated as reversible, so existing phases are unaffected. - a one-way rating makes gsd-planner insert a checkpoint:decision before the task that implements the decision, reusing the existing checkpoint mechanism -- no new checkpoint machinery. - reversible ratings trigger no checkpoint; costly ratings are flagged in the plan but never block. - the rating persists on the task as the optional <reversibility rating=> element. cmdVerifyPlanStructure accepts every rating and the absent case; the structural validator does not reject unknown optional tags. - --no-reversibility-gates (REVERSIBILITY_GATES=false) suppresses checkpoint insertion for intentionally-unattended runs while still recording ratings -- the override changes what stops the run, not what the plan remembers. Single taxonomy, not two: references/thinking-models-planning.md #4 already shipped a binary REVERSIBLE/IRREVERSIBLE classification and is loaded by both gsd-planner and gsd-plan-checker. It is rewritten onto the canonical three-level vocabulary and now points at planner-reversibility.md as the taxonomy owner, with a parity test that fails if the surfaces diverge (DEFECT.GENERATIVE-FIX-DIVERGENCE). agents/gsd-planner.md sat 47 chars under the 49152 LARGE_CAP, so the checkpoint DO/DON'T guidance was relocated verbatim into planner-antipatterns.md -- already @-referenced from the same section for the same topic, so the planner still loads it and nothing was dropped. A test guards the relocation against content loss. Files: gsd-core/references/planner-reversibility.md (NEW, canonical taxonomy + emission rules + anti-patterns), gsd-planner.md, plan-phase workflow/command/help (flag wiring + parity), plan-md.md schema, discuss-phase context template, CONTEXT.md glossary, INVENTORY + manifest, size baselines, install goldens, plugin skills regen, changeset. Closes #1951 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(#1951): address orthogonal review findings Two isolated reviewers (correctness + security), neither of which authored the change. Every finding fixed: Security — the rationale is untrusted input (ADR-1577). It originates in conversation and flows CONTEXT.md -> planner -> PLAN.md -> executor, each hop an LLM reading the previous hop's output, with no validation on the path. planner-reversibility.md and the discuss-phase template now state it is data and never instructions, and name the </reversibility> early-termination hazard explicitly -- a rationale that closes its own element injects sibling structure the executor reads as real tasks. Four tests guard it. Correctness 1 — nothing machine-enforced the feature's own promise: a task rated one-way with no preceding checkpoint:decision validated as fully clean, so a planner error silently reopened the gap this feature exists to close. cmdVerifyPlanStructure now warns on an ungated one-way rating. A warning, not an error: <reversibility> stays additive and the plan stays valid. Four tests cover ungated (warns), gated (silent), still-valid, and reversible/costly never flagged. Correctness 2 — pass-always test. The --no-reversibility-gates parse test substring-matched the whole workflow file, and plan-phase.md prose mentions both tokens in one sentence, so it passed with the bash conditional deleted: it was testing the documentation, not the parser. Now scoped to the fenced bash blocks and matched as one physical line, with a negative control confirming prose alone cannot satisfy it. Correctness 3 — costly had no itemized emission rule, only one-way did, so two agents could diverge on whether to tag costly at all. Correctness 4 — template convention break: the example ratings were bare while every sibling field uses [...] to signal substitution, inviting an LLM to copy one-way/costly forward as boilerplate. Now bracketed. Correctness 5 — latent false-green: .includes('reversible') also matches inside irreversible/irreversibility, which appear in anti-pattern prose, so a surface that dropped the real taxonomy entry would still pass. Now word-boundary matched. ADR-857 phase-6 ceiling — the first gsd-test run caught plan-phase.md 1216 bytes over its frozen 94519 ceiling (it had 49 bytes of headroom on next). The ceiling may only rise for privileged host machinery, and reversibility gating is optional-feature logic, so the wiring was slimmed to its minimum and the explanatory prose moved to the reference files the planner already loads. plan-phase.md is now 94400 bytes -- 119 under the ceiling and 70 bytes SMALLER than on next, so the host loop shrank while gaining the feature, which is what phase 6 ratchets toward. The tracer contract (tests/tracer-bullet.test.cjs) is unchanged. Lint — fixed an unnecessary non-null assertion in verify.cts and a CRLF-fragile bare \n regex in the new test (DEFECT.WINDOWS-CRLF-TEST- PORTABILITY, the #1658/#1668/#2206/#2449/#2450 class). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * test(#1951): checkpoint fixture must carry the common task elements The gated-one-way fixture built a checkpoint:decision task from the abbreviated skeleton in gsd-planner.md, which shows only the checkpoint-specific elements (<decision>/<context>/<resume-signal>). cmdVerifyPlanStructure requires <name> and <action> on EVERY task regardless of type, so the fixture failed validation for reasons that had nothing to do with reversibility: errors: ["Task missing <name> element", "Task 'unnamed' missing <action>"] Caught by gsd-test on 14d14a39 (2 failures, both this fixture). The canonical shape is in tests/verify.test.cjs:266 — a checkpoint task carries <name>/<files>/<action>/<verify> like any other. Fixture corrected to match. Verified behaviorally against the real gsd-tools CLI across all four cases: gated one-way (valid, silent), ungated one-way (valid, warns), costly (valid, silent), absent (valid, silent). Not a product defect: the validator's every-task contract is intentional and pre-existing, and docs/reference/plan-md.md scopes its required-element list to type=auto/tracer only because those are the elements a planner must author, not because checkpoints are exempt from <name>. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * chore(#1951): backfill changeset pr number to 2471 * fix(#1951): CodeQL incomplete-sanitization + prompt-injection scan collision Both CI failures were real defects in code this PR added, not false positives. CodeQL js/incomplete-sanitization (high), reversibility-tagging.test.cjs:46 — the namesRating helper built its regex with `rating.replace(/[-]/g, '\\-')`, which escapes the hyphen but not backslash, so the escape was incomplete. It was also unnecessary: `-` carries no special meaning outside a character class. Replaced with a complete metacharacter escape (backslash included). Word-boundary behavior verified unchanged across all three ratings — notably that "irreversible" prose still does not satisfy a "reversible" match, which is the false-green this helper exists to prevent. Prompt injection scan — the checkpoint fixture used the human-verification child element inside <verify>. That tag name is a fake-instruction-boundary pattern in scripts/prompt-injection-scan.sh, and the scan runs over changed files, so copying the shape from tests/verify.test.cjs (unflagged only because it is not in this diff) tripped the gate. Switched to the documented plain-prose <verify> form. The first attempt at that fix failed the same gate a second time: the comment explaining the collision quoted the offending tag literally. The comment now names it in prose instead — the scanner does not care whether a match is code or commentary, which is the whole point of the DEFECT.PROMPT-INJECTION-SCAN-COLLISION note in CLAUDE.md. Verified locally before push: scan reports 0 findings across 57 changed files, eslint clean, and both fixtures still validate as designed (gated one-way silent, ungated one-way warns, neither errors). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * test(#1951): record measured cost and halve gsd-tools spawns The Windows shard 1/3 job timeout was traced to the sharding layer, not to this PR's assertions — see #2472. Two contributing factors were this file's own, and are fixed here. 1. tests/test-timings.json had no entry for reversibility-tagging.test.cjs, so scripts/run-tests.cjs weighted it at the table's median fallback (~315ms) for LPT chunk packing. It actually measures 5595ms — an 18x under-weight. Recorded the measured value from the green gsd-test run (max across the node22/node24 lanes, per gen-test-timings.cjs's convention). Only this one entry: a full regen churns 634 entries of run-to-run drift, and the table is explicitly advisory and un-gated, so a 637-line diff does not belong in a feature PR. 2. Each verifyPlan() spawns gsd-tools, which dominates this file's cost. Spawns cut from 9 to 6 with no coverage lost: - the ungated-one-way warning and its stays-valid assertion now share one plan instead of building the same plan twice; - the reversible/costly never-flagged-as-ungated test was strictly subsumed by the additive suite, which already runs those two ratings ungated and asserts no /reversibilit/ warning at all — and the gate warning's text contains both "reversibility" and "one-way", so the broader assertion catches it. It only re-spawned gsd-tools twice to prove the same thing. Both are symptom fixes. The shard imbalance itself (19/11/10 minutes against a 20-minute cap, from a cost-blind round-robin partition that also reshuffles downstream files whenever one is inserted) is tracked in #2472. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * test(#1951): checkpoint fixture adopts the #2444 type-branched contract Surfaced by rebasing onto next, which gained #2444 (branch plan-structure validation on task type=checkpoint:*) while this PR was in review. cmdVerifyPlanStructure no longer applies one required-element set to every task. A checkpoint:decision now requires <name> + <resume-signal> + <decision> + <options>, and is exempt from the <action>/<verify>/<done>/ <files> set that auto and tracer tasks carry. The gated-one-way fixture predated that split and failed on the new requirement: errors: ["Task 'Task 0: Confirm the on-disk format' missing <options>"] Fixture rewritten to mirror the checkpoint:decision contract exactly — real <options> with two <option> children — rather than padding it with fields checkpoints no longer need. That also drops the plain-prose <verify> the earlier revision carried purely to dodge the prompt-injection scan; a checkpoint task has no <verify> requirement at all, so the workaround is moot. Verified against the real gsd-tools CLI across all four cases: gated one-way (valid, silent), ungated one-way (valid, warns), costly (valid, silent), absent (valid, silent). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>	2026-07-21 10:44:55 -04:00
Tom Boucher	455ad49ae3	feat(#2296): config-gated provider escalation on quota-exceeded (#2458) ... * test(#2296): failing-first coverage for provider escalation on quota-exceeded Covers the provider-escalation ladder layered onto EXEC.CLASSIFY: back-compat (no escalation block without --failure-class), cap boundaries at min(max_escalations, list length) at limit-1/limit/limit+1, opt-in gating, malformed/hostile provider_escalation config, the --failure-class CLI negative matrix, config-key registration, and a fast-check budget-limit property. Red until the resolver, CLI flag, and manifest key land. Refs #2296 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * feat(#2296): config-gated provider escalation on quota-exceeded The dynamic_routing tier ladder escalates within one provider, which does not help when that provider is what ran out of quota. Add an opt-in provider ladder layered on the existing EXEC.CLASSIFY seam. - model-resolver: resolveProviderEscalation walks dynamic_routing.provider_escalation capped at min(max_escalations, list length), reporting from/to/attempted/exhausted. Invalid entries are dropped (ADR 227 shape validation). Stays a leaf module — the quota-class policy decision is the caller's, per the CONTEXT.md contract. - agent-command-router: export a frozen AGENT_FAILURE_CLASSES so the new CLI validator cannot drift from the classifier that produces the values. - resolve-execution: --failure-class flag; emits an escalation block ONLY when passed, so the existing JSON contract is byte-identical for every caller. - config-schema.manifest: register dynamic_routing.provider_escalation. - execute-phase step 7.1: auto-escalate, honor Retry-After, fail loudly naming every model tried once the ladder is spent. Refs #2296 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(#2296): extract quota recovery to a reference fragment; regen goldens The step 7.1a addition pushed gsd-core/workflows/execute-phase.md from 93390 to 95111 LF bytes, past the frozen ADR-857 Phase 6 ceiling (hard <93600, margin <=93400) asserted by tests/fix-2285-claude-orchestration-wiring.test.cjs. The base sat 10 bytes under the margin, so no inline wording would have fit. That gate's own rationale is that optional-feature detail belongs in a fragment, not the host loop. Moved BOTH the new provider-escalation branch and the pre-existing manual recovery prompt into gsd-core/references/execute-phase-quota-recovery.md, leaving step 7.1 as a one-line pointer. execute-phase.md is now 92880 bytes — 510 SMALLER than base. Also regenerates the fixtures that legitimately moved because three shipped files changed (gsd-tools.cjs, config-schema.manifest.json, execute-phase.md): golden-install-parity + install-tree for all 16 runtimes, INVENTORY.md + INVENTORY-MANIFEST.json for the new reference, and the workflow size baseline. Refs #2296 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * test(#2351): make the C1 orphan-reaping test load-independent tests/run-with-timeout.test.cjs C1 asserted the child heartbeat file exists after a 1s group-kill window, but the child only wrote it on the first 100ms setInterval tick. Nothing synchronized the two: on a loaded container the group is SIGKILLed before that tick lands, the file never appears, and the assertion fails for a reason unrelated to reaping. Observed failing on both linux-node22 and linux-node24. The behavior actually under test is the FREEZE assertion (heartbeat stops advancing => descendant was reaped, not orphaned). That is unaffected by sampling once more at t=0. Child now writes its first heartbeat synchronously at startup before arming the interval, and the kill window widens 1s -> 3s to cover child boot under load. Both remove the timing dependency; neither weakens what the test proves. Refs #2296 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * chore(#2296): backfill pr:2458 in .changeset/rapid-jays-bark.md * chore(#2296): regenerate fixtures after rebase onto #2402 The rebase conflicted on the generated golden-install-parity fixtures and workflow-size-baseline.json because #2402 (b6e6a22fc) regenerated the same artifacts. Conflict resolution picked a side to unblock the rebase; a true regeneration on the combined tree then produced further drift, confirming the resolved content was stale and would have dropped #2402's fixture changes. Regenerated goldens, install-tree, size baseline, and INVENTORY-MANIFEST from the merged tree. docs/INVENTORY.md keeps BOTH new reference rows. execute-phase.md is 92782 LF bytes with both #2402's and this PR's extractions applied — under the frozen ceiling (hard <93600, margin <=93400). Refs #2296 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>	2026-07-20 14:59:30 -04:00
Tom Boucher	b6e6a22fce	fix(#2402): honor response_language across orchestrator output + UAT checkpoint renderer (#2457) ... * fix(#2402): honor response_language across orchestrator output + UAT checkpoint renderer Replays the in-flight bot branch fix/2402-response-language-orchestrator-coverage (seven commits, never pushed) onto current origin/next as a single squashed commit. The original work was substantial and correct; this commit preserves its full scope, trimmed where rebase conflicts + workflow size budgets required it. Three independent layers where response_language was being dropped are closed: Layer 1 — orchestrator-facing directives across workflows. Adds the strong "All user-facing output in this workflow MUST be presented in {response_language}; technical terms, code, paths, and subagent prompts stay in English" directive to ~40 workflows that previously either lacked it entirely (verify-work, new-project, new-milestone, quick, manager, and ~35 more) or carried only the weak subagent-prompt-only form (plan-phase, execute-phase). The directive covers narration between tool calls and banner output, not just the AskUserQuestion prompts. Layer 2 — UAT checkpoint renderer (src/uat.cts). buildCheckpoint now accepts an optional responseLanguage parameter and renders the frame strings ("CHECKPOINT: Verification Required", "Type `pass` or describe what's wrong.") in any of 9 languages (English/Spanish/French/German/Portuguese/Japanese/ Chinese/Korean/Italian) with an alias table covering ~30 input variants (en, es, español, ja, 日本語, etc.). cmdRenderCheckpoint reads config.response_language via loadConfig(cwd) and passes it through, so the byte-for-byte block verify-work.md reprints verbatim is already localized when written — preserving the anti-injection hygiene rule at verify-work.md (the model is forbidden to translate after the fact). CJK display width is computed by East Asian Width property ranges (W/F) so the right ║ border of the banner stays aligned for full-width characters. English fallback is byte-identical to the pre-fix behavior when response_language is unset or unrecognized. Layer 3 — literal English report templates in execute-phase. The top-of- workflow directive covers all template sites (templates are a structural source, not literal output). Inline render-language notes that previously sat at each template site were removed during the squash because they pushed execute-phase.md over its frozen pre-phase-6 byte ceiling (93600 — ADR-857 Phase 6 capstone). The single top directive covers the same surface with fewer bytes. Also extends src/docs.cts and src/init.cts to propagate response_language into the init JSON bundle of the additional workflows so the directive can read it. Tests added: - tests/uat.test.cjs: buildCheckpoint with unset/unrecognized language falls back to English default; recognized language swaps only the two frame strings while structural lines stay untouched; CJK display-width regression (independent recomputation of East Asian Width W/F ranges). - tests/workspace.test.cjs, tests/docs-update.test.cjs: response_language wiring through docs.cts/init.cts. References: #2402; reporter's three-layer triage + Layer-4 follow-up; the byte-for-byte anti-injection hygiene rule at verify-work.md (the reason Layer 2 must be renderer-side, not model-translated). This is a squash of the in-flight bot branch — seven commits representing the original implementation plus its subsequent fix/CJK-padding/test/ changeset/regen cycles, none of which were ever pushed or PR'd. The squash captures the final coherent state. * chore(#2402): backfill pr:2457 in .changeset/2402-response-language-orchestrator-coverage.md * chore(#2402): regen golden + size baseline after rebase against #2315 (PR #2451) Rebase conflicts were entirely in generated artifacts (golden-install-parity fixtures + workflow-size-baseline.json). After taking theirs during rebase, regenerated cleanly against the merged source tree.	2026-07-20 14:22:27 -04:00
Tom Boucher	1720aacf0c	feat(#1949): <precondition> task element — Design by Contract (#2422) ... * test(#1949): add failing-first tests for <precondition> element Red phase for issue #1949 (Design by Contract: <precondition> element asserted before task execution). Tests assert: - docs/reference/plan-md.md documents the new <precondition> element - agents/gsd-planner.md @-references planner-preconditions.md and stays under the 49152-char cap (progressive-disclosure requirement) - gsd-core/references/planner-preconditions.md exists and documents the three emission cases mandated by the issue (user_setup / prior-phase artifact / env-var) and the contract triad mapping - agents/gsd-executor.md asserts <precondition> before task execution and routes unmet preconditions through existing checkpoint machinery - cmdVerifyPlanStructure (behavioral via runGsdTools) accepts plans both with and without <precondition> — the additive-validation guarantee - Parity assertion: plan-md.md and planner-preconditions.md agree on the canonical tag spelling (DEFECT.GENERATIVE-FIX-DIVERGENCE guard) Most prose-contract assertions are Red until the implementation lands. The behavioral validator assertions pass immediately (regression guards proving the validator already accepts unknown optional tags). * feat(#1949): <precondition> task element — Design by Contract Add an optional <precondition> element to <task> in PLAN.md (issue #1949, The Pragmatic Programmer Topic 23). The front-of-task side of the plan contract — preconditions (before) ↔ postconditions (<verify>/<done>/ <acceptance_criteria>, after) ↔ invariants (must_haves.truths, across the whole plan). Together with the tracer-bullet proposal (#1945), this closes both ends of the 'outrunning your headlights' failure mode for an autonomous AI executor. Acceptance criteria met: - <precondition> is an optional element on <task>; plans that omit it validate unchanged (cmdVerifyPlanStructure checks for presence of required tags, does not reject unknown optional tags). - gsd-executor evaluates the precondition before any other task work. Unmet halts execution with a checkpoint:human-verify and no partial commit; met or absent produces no visible change to execution flow. Unmet is never auto-approved under AUTO_CFG=true — a missing prerequisite is a fact the executor cannot establish on its own. - gsd-planner emits <precondition> in exactly the three cases the issue mandates: user_setup consumption, prior-phase artifact dependency, and env-var/runtime-config dependency. - Tests cover met, unmet, and absent preconditions plus the additive- validator guarantee. Files: - gsd-core/references/planner-preconditions.md (NEW): full emission rules, the three cases with worked examples, format guidance, anti-patterns, the contract triad mapping, and the executor assertion contract. Progressive disclosure. - agents/gsd-planner.md: slim <precondition> note in Task Anatomy with @-reference to the new file. To stay under the 49152-char agent-file cap (27-char headroom before this change), the inline <comment_text_discipline> and <region_scoped_negative_gate> summaries are compressed to one-line pointers — their full rules already live in planner-antipatterns.md, so no content is lost. - agents/gsd-executor.md: new step 0 'Precondition check' in the execute_tasks loop, before the type dispatch, routing unmet through checkpoint_return_format. - docs/reference/plan-md.md: new Preconditions section in the schema reference, with the canonical example and the three emission cases. - CONTEXT.md: Precondition glossary entry as a sibling of Tracer Bullet. - docs/INVENTORY.md + INVENTORY-MANIFEST.json: row for the new references/planner-preconditions.md (regen via gen-inventory-manifest). - tests/precondition-element.test.cjs: failing-first tests covering schema docs, planner emission contract, executor assertion contract, reference-file presence + the three cases, behavioral additive- validator guarantee, and a parity assertion (DEFECT.GENERATIVE-FIX- DIVERGENCE guard). - .changeset/quick-hawks-bark.md: Added fragment. Companion to #1945 (tracer bullets). * chore(#1949): regen agent-size baseline + install-tree goldens Documented baseline regenerations required by the feat(#1949) prose changes (RULESET.AGENT_SIZE_BUDGET + golden-install-parity): - npm run size:baseline — locks in the new gsd-executor.md size (+1050 bytes: the precondition-check step 0 block). gsd-planner.md is net smaller (-142 bytes: compressed two inline summary blocks whose full rules already lived in planner-antipatterns.md to make room for the slim <precondition> pointer). No hard-cap breach. - npm run gen:golden — pick up the new references/planner-preconditions.md + the two changed agent files across all 18 runtime install trees. Both regens are CI-mandated after intentional agent/reference changes; see CLAUDE.md 'RULESET.AGENT_SIZE_BUDGET' and the comments in tests/golden-install-parity.test.cjs. * fix(#1949): bound <precondition> checks to read-only (security review) Apply the security-review finding (LOW, isolated /security-review subagent): the executor's 'run the cheapest check' phrasing for a plan-author-controlled prose line was broader than ideal — a hostile plan author could craft a <precondition> whose 'cheapest check' is side-effecting (curl to an attacker host under the guise of verification, rm -rf before checking, secret emission). The risk is inherited from GSD's existing plan-trust model (<verify>, <action>, <done> already direct the executor to run arbitrary shell), so <precondition> does not materially expand it. But the new prose actively directs execution ('run the check') rather than passively consuming the element, so the bound is worth making explicit. Tightened across all four surfaces that describe the check shape: - agents/gsd-executor.md step 0: 'Verify with read-only checks only — file existence, env var presence (no value output), idempotent GET /health-style pings. Do NOT run commands with side effects (writes, network POSTs, secret emission) as the check; if a side-effecting check seems required, halt and surface via checkpoint instead.' - gsd-core/references/planner-preconditions.md Format section: same bound, plus the halt-and-surface escape hatch. - docs/reference/plan-md.md Preconditions section: mirrored. - CONTEXT.md Precondition glossary entry: mirrored. Regenerated agent-size baseline (executor grew 46186 -> 46440; still under the 49152 cap) and install-tree goldens. * chore(#1949): backfill changeset pr number 2422 Per CONTRIBUTING.md changeset workflow + feature-builder directive Step 8.7: backfill the placeholder pr:0 with the real PR number immediately after gh pr create returns. Avoids the fail_invalid_fragment gate. * fix(#1949): cite [#1949] on allow-test-rule exemption (ADR-456) CI's lint:ci runs lint-allow-test-rule-refs which per ADR-456 requires every // allow-test-rule: exemption on a NEW test file to carry an issue reference (#NNN or URL). My earlier push omitted it. Local 'npm run lint' (eslint) does NOT run this check — only 'npm run lint:ci' does. CLAUDE.md explicitly warns: 'lint:ci ≠ lint — CI runs lint:ci; a local pass is not the gate.' I should have run lint:ci before pushing; correcting now. Pattern matches the companion feature's test file: tests/tracer-bullet.test.cjs:1 // allow-test-rule: source-text-is-the-product [#1945]	2026-07-19 07:52:36 -04:00
Tom Boucher	8d2f8bcb23	fix(#2388): gate shared requirement completion on sibling plans, revert on gaps (#2424) ... * fix(#2388): gate shared-ID requirement marking and revert on gaps_found Adds requirements.ready-ids (execute-plan.md's update_requirements step) so a requirement ID declared by multiple plans in a phase only marks Complete once every declaring plan has produced a SUMMARY.md, and requirements.revert-phase (execute-phase.md's gaps_found branch) so a gaps_found verdict reverts the phase's own prematurely-Complete IDs before the gap report renders. Single-plan IDs still mark immediately. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * chore(#2388): regenerate fixtures + lint gate-prep * fix(#2388): repair failing tests after gate verification * chore(#2388): add changeset (#2424) --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>	2026-07-19 07:52:17 -04:00
Tom Boucher	dd5a2211c9	enhance(#1964): semantic knowledge-base recall via MemPalace (keyword fallback) (#2416) ... * test(#1964): add failing-first semantic-recall contract tests Epic #1957 Phase 3C (final). Source-text-is-the-product contract tests: semantic recall via MemPalace (top-k meaning-similar prior resolutions, catches same-root-cause/different-wording cases), indexing resolved sessions at archive, graceful degradation to keyword matching when MemPalace is absent, knowledge-base.md stays the durable plain-text source of truth, agent Phase 0 / Matching Logic is semantic-first (the stale 'keyword overlap, not semantic similarity' claim must go), and no new embedding/vector infra (reuse MemPalace). Failing-first: reference, the Matching Logic reframe, the Phase 0 consolidation, and the archive indexing step do not yet exist. * feat(#1964): semantic knowledge-base recall via MemPalace (keyword fallback) Epic #1957 Phase 3C (FINAL). Replaces keyword-overlap matching with semantic recall: at Phase 0 the debugger queries MemPalace with the current symptoms and surfaces the top-k meaning-similar prior resolutions, catching the same-root-cause/different-wording cases keyword overlap missed (the self-noted 'keyword overlap, not semantic similarity' limitation). Resolved sessions are indexed into MemPalace at archive (symptoms + root_cause(s) + fix + recurrence guard). knowledge-base.md remains the durable plain-text source of truth; when MemPalace is absent the debugger falls back to keyword-overlap matching (logged, never a silent skip). No new embedding/vector infrastructure — MemPalace is reused. Size-neutral agent edits: the Matching Logic section reframed (keyword-only -> semantic-first + keyword-fallback + @-include); Phase 0's three keyword bullets consolidated into one semantic-first bullet; one MemPalace-indexing step added at archive. Agent at 57222 B (122 B headroom — final phase). Full rules in gsd-core/references/debugger-semantic-recall.md. INVENTORY + manifest + agent-size baseline + install-parity goldens + AGENTS.md updated. * fix(#1964): address orthogonal review (invocation mechanism, index Resolution-not-symptoms + redaction, fallback detail) - HIGH: the 'query MemPalace' instruction was WHAT-level only; the agent has no MCP tools. Added an Invocation section naming the Bash CLI (mempalace search --wing <wing>) + MCP-when-registered + wing resolution (config.mempalace.wing -> project_code -> project dir), matching every other MemPalace integration. Without this the feature silently degraded to keyword matching even when MemPalace was present. - MEDIUM (security x2): index the agent-authored Resolution summary (root_cause + fix + recurrence_guard), NOT raw user-supplied Symptoms — excludes attacker-controlled prose from the cross-session index AND reduces secret/PII leakage. Redact secret-shaped values before indexing. Stated the write order (KB append + commit MUST succeed before indexing). - LOW: restored 'identifiers' + 'case-insensitive' to the keyword fallback; added a test asserting the fallback mechanics survived the Phase 0 consolidation (Error patterns field, 2+ token overlap, identifiers, case-insensitive). * chore(#1964): ratchet agent-size baseline downward (leaner archive bullet shrank gsd-debugger.md 57222->57197) * chore(#1964): backfill changeset pr number (PR #2416)	2026-07-18 19:01:04 -04:00
Tom Boucher	c67f301867	feat(#1963): emit blameless-postmortem Prevention block at resolution (#2410) ... * test(#1963): add failing-first prevention/postmortem contract tests Epic #1957 Phase 3B. Source-text-is-the-product contract tests: blameless 5-Whys that BRANCHES per Phase 2A RCA (not a single-cause chain; treats agent error as 'why was that possible?'), the 'why wasn't this caught?' question, the recurrence-guard taxonomy (regression test / assertion / lint rule / KB pattern), the KB-entry why_not_caught + recurrence_guard fields with backward compat, the session-manager prevention summary line, and the Zawinski scope-boundary (a block, not a subsystem). Failing-first: reference, archive_session edit, KB schema extension, and session-manager summary do not yet exist. * feat(#1963): emit blameless-postmortem Prevention block at resolution Epic #1957 Phase 3B. At archive_session the debugger now produces a Prevention block with three blame-free components: a branching 5-Whys causal chain (branches per Phase 2A RCA, not a single chain; 'agent error' prompts 'why was that possible?', never blame), a 'why wasn't this caught?' answer naming the missed gate (test/typecheck/lint/review/verify), and a concrete recurrence guard (regression test / assertion / lint rule / KB pattern). The knowledge-base entry gains two structured fields (why_not_caught + recurrence_guard) so future Phase-0 recall surfaces the prior prevention, not just the prior fix. Additive: old entries without the fields still load. The session-manager compact summary surfaces a one-line prevention summary. Full rules extracted to gsd-core/references/debugger-prevention.md (slim archive_session step + 2 KB fields kept in the agent). INVENTORY + manifest + agent-size baseline + install-parity goldens + AGENTS.md updated. * fix(#1963): address orthogonal review (CRITICAL append-template drift + Phase-0 consumption + parity test) - CRITICAL: the archive_session KB append template omitted Why not caught + Recurrence guard (only the Entry Format had them) — the feature's core deliverable silently did not happen. Added both fields to the append template the agent actually follows (nearest-instruction wins). - HIGH: Phase 0 (KB read) only surfaced root_cause + fix; the new fields were dead data. Extended the Phase 0 Evidence line to consume why_not_caught + recurrence_guard when present (absent on old entries — backward compat holds). - MEDIUM: added a cross-section parity test (every Entry-Format field must also appear in the append template — the guard that would have caught the Critical) + a Phase-0-consumption assertion. - MEDIUM: the 'branches per Phase 2A' claim is now wired — reuses reasoning_checkpoint.candidate_causes across the four categories. - MEDIUM: recurrence-guard taxonomy gains type refinement + config-default change; LOW: added 'build' gate to both surfaces for parity. - NIT: compact-summary fallback shape ('no gate existed'); verify the guard artifact exists before recording it. * test(#1963): anchor Phase-0 consumption test on the specific heading The regex /Phase 0[\s\S]{0,1200}/ matched the first 'Phase 0' in the file (in knowledge_base_protocol prose), not the Phase 0 block in investigation_loop. Anchor on '**Phase 0: Check knowledge base**' and widen to 1500 chars. * chore(#1963): backfill changeset pr number (PR #2410)	2026-07-18 17:38:54 -04:00
Tom Boucher	36a311c5bb	enhance(#1962): harden regression tests (PBT shrinking + oracle classification + boundaries) (#2409) ... * test(#1962): add failing-first repro-hardening contract tests Epic #1957 Phase 3A. Source-text-is-the-product contract tests: PBT shrinking (fast-check/Hypothesis, minimized seed, manual-minimization degradation), the four oracle types (specified/derived/metamorphic/implicit with implicit flagged weakest), boundary neighbors (off-by-one/min-max/empty-singleton tied to the equivalence class), oracle_type in DEBUG Resolution, and the Phase 1A tie-in (minimized seed + real oracle => the mutation guardrail bites). Failing-first: reference, agent cross-refs, and template field do not yet exist. * feat(#1962): harden regression tests (PBT shrinking + oracle classification + boundaries) Epic #1957 Phase 3A. Extends Minimal Reproduction (shrinking) and Test-First Debugging (oracle classification + boundary neighbors): - Shrinking: wrap an input-space failing input in a property (fast-check JS/TS, Hypothesis Python) and store the MINIMIZED counterexample as the regression seed; degrade to manual minimization when no PBT framework is present. - Oracle classification: state specified / derived (contract/model) / metamorphic / implicit (crash, weakest) before writing the assertion; record under Resolution.oracle_type; never default to implicit silently. - Boundary neighbors: off-by-one, min/max, empty/singleton around the fixed defect's equivalence class. Together they turn the regression test into a root-cause check — what the Phase 1A mutation guardrail needs to bite. Full rules extracted to gsd-core/references/ debugger-repro-hardening.md. INVENTORY + manifest + agent-size baseline + install-parity goldens + AGENTS.md + DEBUG template updated. * fix(#1962): address orthogonal review (bounding, provenance, oracle scope, sufficient-triple) - HIGH: added a 'Bound the property/shrink run' section (60s timeout, degrade- to-manual on timeout, do-not-raise-default-run-limits, argv-not-shell) — the gauntlet violation the sibling references already honored. - Medium: test-provenance caveat (the failing input often comes from the bug report — author the generator from a sanitized description, cross-ref debugger-fix-acceptance.md). - Medium: oracle scope note — the 4 types cover deterministic bugs; non- deterministic failures re-route to stability-stress per bug-taxonomy. - Medium: Phase 1A tie-in corrected — seed+oracle is necessary not sufficient; boundary neighbors close the adjacent-input escape; the sufficient triple is seed+oracle+neighbors. - Low: preserve the original noisy repro as a secondary reference; operationalize 'equivalence class' (the predicate the fix draws). Nit: degradation reworded. * chore(#1962): backfill changeset pr number (PR #2409) --------- Co-authored-by: sim <sim@local>	2026-07-18 15:46:42 -04:00
Tom Boucher	6baa2a8182	feat(#1961): add bug-taxonomy classification + strategy routing to gsd-debugger (#2407) ... * test(#1961): add failing-first bug-taxonomy routing contract tests Epic #1957 Phase 2B. Source-text-is-the-product contract tests (3 taxonomy classes, explicit class->technique routing table, Bohrbug->repro+SBFL+bisect, Heisenbug->record-replay/stability+SKIP-SBFL, Concurrency->atomicity/order/ deadlock checklist, bug_class in DEBUG Current Focus, supersede-not-append) plus a routing-table specification object pinning the documented decisions (SBFL forbidden on Heisenbug is the load-bearing 1B/2B seam). Failing-first: reference, Phase 1.75, and routing-table reframe do not yet exist. * feat(#1961): add bug-taxonomy classification + strategy routing to gsd-debugger Epic #1957 Phase 2B (reliability-critical). Adds Phase 1.75: classify the failure as Bohrbug / Heisenbug-Mandelbug / Concurrency, then route the investigation technique via an explicit class->technique table (Kernighan: no opaque heuristic). Bohrbug -> reproduction + SBFL (Phase 1.25) + git bisect; Heisenbug/Mandelbug -> record-replay (rr) + stability-stress + statistical sampling, with SBFL explicitly SKIPPED (a flaky spectrum poisons the Ochiai ranking — the load-bearing 1B/2B seam); Concurrency -> the atomicity/order/deadlock checklist first. Reframes (supersedes, not appends — Zawinski) the flat 'Technique Selection by situation' table into a class-routed table; the 11 techniques remain as routed targets. bug_class recorded in Current Focus (DEBUG template); common-bug- patterns catalog cross-referenced to the taxonomy. Full rules extracted to gsd-core/references/debugger-bug-taxonomy.md. INVENTORY + manifest + agent-size baseline + install-parity goldens + AGENTS.md updated. * fix(#1961): address orthogonal review (phase-name drift, General lane, revoke framing, row-scoped tests, bounding) - HIGH: reference said 'Phase 1B' (epic shorthand); corrected to the deployed 'Phase 1.25' (matches the agent + SBFL reference). - HIGH: 6 of 11 techniques (Rubber duck, Delta, Working backwards, Differential, Comment-out, Follow-the-indirection) were orphaned by the situation-table reframe. Added a 'General (any class, situation-cued)' lane to BOTH the reference routing table and the agent's Technique Selection table that re-homes them — supersede-not-append now holds. - MEDIUM: the SBFL-skip is structurally retroactive (Phase 1.25 runs before Phase 1.75 classification), so reframed the table column from 'Do NOT use' to 'Revoke if already run' + an explicit 'retroactive revocation, not proactive skip' note stating the ordering honestly. - MEDIUM: contract tests are now row-scoped (parse the table by class, assert per-row) instead of presence-only; added a guard that the previously- orphaned techniques now have a General-lane route. - LOW: pinned the canonical bug_class value form (lowercase-kebab: bohrbug|heisenbug-mandelbug|concurrency; prose may use title-case). - NIT: added a 'Bound the Heisenbug-chase runs' note (rr/stability/sampling timeouts) per the unbounded-subprocess gauntlet. * chore(#1961): backfill changeset pr number (PR #2407)	2026-07-18 14:42:29 -04:00
Tom Boucher	f8b16d1874	enhance(#1960): add RCA branching (fishbone + AND-gate) to gsd-debugger (#2405) ... * test(#1960): add failing-first RCA-branching contract + schema-invariant tests Epic #1957 Phase 2A. Source-text-is-the-product contract tests (fishbone >=2 categories, AND-gate, multi-cause root_cause, backward compat, reasoning checkpoint candidate_causes+and_gate fields, debugger-philosophy single-cause note, DEBUG template) plus behavioral schema-invariant checks on two fixtures: two contributing causes (AND-gate yes) -> both recorded; single-cause (AND-gate no) -> one root_cause, identical to today. Failing-first: reference, agent edits, and template note do not yet exist. * feat(#1960): add RCA branching (fishbone + AND-gate) to gsd-debugger Epic #1957 Phase 2A. Guards against 5-Whys single-cause bias: before committing root_cause, the debugger enumerates candidate causes across >=2 Ishikawa categories (code/config/environment/data) and explicitly answers an AND-gate question. When the AND-gate fires, every contributing cause is recorded, so a multi-cause fix no longer recurs via the unaddressed second cause. Resolution.root_cause may hold one OR a small set (additive; single-cause sessions are byte-identical to today). The Structured Reasoning Checkpoint gains candidate_causes + and_gate fields; debugger-philosophy.md adds the single-cause-bias trap. Full rules extracted to gsd-core/references/debugger-rca-branching.md (slim Phase 2 routing + 2 checkpoint fields kept in the agent). INVENTORY + manifest + agent-size baseline + install-parity goldens + AGENTS.md + DEBUG template updated. * fix(#1960): address orthogonal review (AND-gate self-consistency, parity guard, narrowed claim, ripples) - Reference: the collapse rule now enforces AND-gate self-consistency — and_gate=yes with a single confirmed cause is flagged as incomplete (return to Phase 3); a race/timing note clarifies such bugs bridge categories; the 'byte-identical' backward-compat claim narrowed to 'root_cause shape unchanged; reasoning_checkpoint gains 2 fields in every session'. - DEBUG.md: stale 'five-field' mirror prose -> seven-field (parallel-surface drift the reviewer flagged); new debug-session-management parity test pins the field-count claim to the gsd-debugger.md YAML keys (CRLF-safe). - Scalar-assuming consumers of set-valued root_cause updated: session-manager compact summaries (319/332), diagnose-only return (1062), archive entry (1216), ROOT CAUSE FOUND return (1322). - Test: added the AND-gate-yes/single-cause invariant + fixture; rephrased the fixture describe block honestly as a schema-invariant specification. - Phase 2 bullet phrasing clarified ('at hypothesis formation, before the Phase 4 commit'). * test(#1960): parity regex accepts word-form count ('seven-field' or '7-field') * test(#1960): parity regex counts array-valued YAML keys (no inline value) * chore(#1960): backfill changeset pr number (PR #2405)	2026-07-18 13:42:58 -04:00
Tom Boucher	56a5c6404c	feat(#1959): add spectrum-based fault localization (Ochiai) pre-filter to gsd-debugger (#2403) ... * test(#1959): add failing-first SBFL contract + Ochiai correctness tests Epic #1957 Phase 1B. Source-text-is-the-product contract tests (Ochiai formula documented, Tarantula fallback, top-N seeding, no-coverage skip logged, ranking->Evidence, Bohrbug gating) plus a behavioral Ochiai formula-correctness section: bound [0,1], max-score invariant, a known-fault fixture proving the fault ranks #1 (criterion 2), clean degradation on zero failing tests, and two fast-check properties. Failing-first: reference file and agent routing do not yet exist. * feat(#1959): add spectrum-based fault localization (Ochiai) pre-filter to gsd-debugger Epic #1957 Phase 1B. When a runnable test suite with per-test coverage exists (>=1 failing AND >=1 passing test), the debugger computes an Ochiai suspiciousness ranking over the coverage spectrum and seeds the top-N suspicious locations into Evidence as first-class hypothesis candidates, narrowing the search space deterministically before LLM reasoning. Tarantula documented as fallback. Degrades cleanly (logged, never silent) when there is no test suite, no failing tests, or no per-test coverage, and is explicitly not trusted on flaky/Heisenbug spectra (pairs with Phase 2B bug-taxonomy). Full rules extracted to gsd-core/references/debugger-sbfl.md (slim Phase 1.25 routing kept in the agent to respect the size cap). No new coverage framework — reuses the project's existing test/coverage runner. INVENTORY + manifest + agent-size baseline + install-parity goldens + AGENTS.md updated. * test(#1959): bound property generators to valid coverage counts The [0,1] property generated failedExec independently of totalFailed, but Ochiai's score is only bounded by 1 under the coverage invariant failedExec <= totalFailed (a failing test that executed s is one of the totalFailed failing tests). Out-of-domain inputs (failedExec=100, totalFailed=5) make the formula correctly return >1. Bound failedExec by totalFailed via fc.chain so the property tests the real domain. Also cleaned up the ranking property (removed dead code). * fix(#1959): address orthogonal review (monotonicity property, degradation row, coverage bounding) - Replace vacuous ranking property (true-by-sort-construction) with a non-trivial monotonicity property: holding totalFailed + passedExec fixed, ochiai is non-decreasing in failedExec. An inverted formula would fail it. - Add the missing 'no passing tests' degradation row (preconditions require >=1 passing test; Tarantula would divide by totalPassed=0). - Bound the coverage subprocess (CLAUDE.md gauntlet): cap the coverage run, degrade-to-skip on timeout, never hang the debug session. - Reword 'discard the ranking' -> 'mark the Evidence entry as revoked (do not delete)' per Kernighan auditability. * test(#1959): bound monotonicity-property generator to valid coverage (failedExecA <= totalFailed) * chore(#1959): backfill changeset pr number (PR #2403)	2026-07-18 07:55:28 -04:00
Tom Boucher	5e52350736	feat(#1958): add multi-signal fix-acceptance guardrail to gsd-debugger (#2396) ... * test(#1958): add failing-first guardrail contract tests Epic #1957 Phase 1A. Adds source-text-is-the-product tests asserting the 5-signal fix-acceptance guardrail contract (target test, mutation check, no-op/deletion detector, adjacent tests, revert-and-reconfirm), graceful degradation, FIX REJECTED BY GUARDRAIL return path, per-signal debug-file recording, and subprocess bounding. Failing-first: reference file and agent sections do not yet exist. * feat(#1958): add multi-signal fix-acceptance guardrail to gsd-debugger Epic #1957 Phase 1A. Prevents accepting a fix that merely greens the test (Goodhart defense / APR overfitting). Adds a 5-signal gate run before fix acceptance: target test, mutation check (Stryker), no-op/behavior-deleting detector, adjacent/held-out tests, revert-and-reconfirm. Degrades gracefully when Stryker or a test suite is absent (each skip logged, never a silent pass), records per-signal results under Resolution.verification, and returns a FIX REJECTED BY GUARDRAIL outcome the session-manager surfaces for revise / accept-as-debt / abandon. Full rules extracted to gsd-core/references/debugger-fix-acceptance.md (slim routing kept in the agent to respect the agent-size cap). Debug template + INVENTORY + manifest + agent-size baseline + AGENTS.md updated. * test(#1958): correct newline-tolerant assertion + regen install-parity goldens The revert-and-reconfirm assertion collapsed whitespace before matching so markdown line-wrapping does not break it. Regenerated the golden-install-parity and install-tree fixtures (npm run gen:golden) to absorb the intentional gsd-debugger.md / gsd-debug-session-manager.md / DEBUG.md / new reference-file changes to the installed artifact tree. * fix(#1958): tighten guardrail per orthogonal review Addresses the isolated reviewer's findings: - signal 5 now states its recorded-repro dependency and routes the no-repro case to the degradation row; revert mechanism specified (git stash / git revert -n); minimality flag tied to diff structure, not revert-ability. - bounded-subprocesses section now bounds the git subprocess (5-30s) too, requires argv-array argument passing, and scopes Stryker to the driving regression test (a mutant killed only by a non-driving test is a finding). - new test-provenance (security) clause: the driving test must be agent-authored; bug-report repro scripts are DATA, never executed verbatim. - tightened 3 contract assertions to bind to specific clauses (guardrail_verdict field, deletion-reject-unless-RCA, 60s+git bounding). - Goodhart framing softened to 'partially-independent'; DEBUG.md template verification field notes the nested map shape. * chore(#1958): backfill changeset pr number (PR #2396) * fix(#1958): add issue ref to allow-test-rule annotation (ADR-456) CI lint-allow-test-rule-refs requires every allow-test-rule exemption to carry a 'see #NNN' issue ref per ADR-456. The new test file's annotation lacked it; this adds (see #1958).	2026-07-18 00:39:28 -04:00
Tom Boucher	9ad2bab4be	fix(#2297): scope resolve_model_ids:"omit" to the resolving runtime (#2332) ... * fix(#2297): scope resolve_model_ids:"omit" to the resolving runtime The installer writes resolve_model_ids:"omit" for non-alias runtimes into the machine-wide ~/.gsd/defaults.json (#1156); any runtime read it back, so install order silently flipped Claude's adaptive tier aliases (executor->sonnet, planner->opus) to '' in no-project sessions. Resolution is now scoped to the runtime actually resolving, identified by a new per-install <install>/gsd-core/.gsd-runtime marker (installer writes it beside VERSION). The "omit" branch returns '' only when the PROJECT explicitly set omit (honored for all runtimes, #2517 finding #4) OR the active runtime lacks native aliases. Claude ignores a global-defaults-only omit and keeps its aliases; the active runtime is canonicalized (GSD_RUNTIME -> config.runtime -> marker -> claude) so alias/case spellings can't defeat the check; explicit project omit is workstream/project-scope aware; explicit true still materializes IDs. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs(#2297): backfill PR number 2332 into changeset Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-16 13:33:36 -04:00
Tom Boucher	89b1bef881	refactor(#2267): golden-parity file-set snapshot + anti-staleness CI selection (#2274) ... Phase 2 of golden-parity redesign (epic #2264). Adds an install file-set snapshot (golden-install-tree) and a ci-test-scope rule selecting golden-parity whenever any installed-source path changes, closing the silent-staleness hole behind the #2266 red. ADR-2264 amended (the copy/transform split premise was unsound). Closes #2267.	2026-07-14 19:22:13 -04:00