8249ebcf6e75a986598edc59c3159fca4d2ca07e
96 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Tom Boucher
|
8249ebcf6e |
fix(#3770): require intentional RED evidence before GREEN (#4279)
* test(3770): add failing tests for intentional RED evidence gate RED: classifyRedEvidence / buildRedEvidenceRecord / check tdd-red-evidence do not exist yet; every row fails on require. Per #3770 only an intentional target-test failure may authorize GREEN; zero-test discovery, fixture crashes, unrelated failures, and unexpected green are INVALID_RED. * fix(3770): require intentional RED evidence before GREEN Only an intentional failure of the TARGET test (distinctly named, TAP-reported assertion failure) classifies as RED_EVIDENCE_OK and authorizes GREEN. Zero-test discovery, fixture/load crashes (file-named failures), nonzero exits without a failing test, unrelated failures, unexpected greens, and malformed/missing records are INVALID_RED and block GREEN. - src/tdd-red-evidence.cts: pure classifier + persisted record builder (reuses the prohibition-enforcement TAP primitives; fail-closed, never throws) - check tdd-red-evidence <record.json>: validates the persisted record (command, exit code, failing test, expected, actual) - gsd-executor.md / references/tdd.md / references/execute-mvp-tdd.md: RED now requires the evidence record + gate verdict, not a nonzero exit or a RED: tag * chore(3770): regenerate inventory manifest for tdd-red-evidence.cjs * fix(3770): fit executor fail-fast under size cap, fix unrelated-failure fixture, ignore generated lib - gsd-executor.md: compress the #3770 fail-fast rule to one line (49149 B < 49152 cap; line-count parity keeps the #2751 PROSE_ALLOWLIST line 816 valid) - tests: the row-6 fixture used String.replace (first-occurrence), so the `not ok` line still named the target test and the classifier was right to accept it; replaceAll makes the failure genuinely unrelated - eslint.config.mjs: ignore tsc-generated bin/lib/tdd-red-evidence.cjs (lint the src/*.cts source, per ADR-457 migration rule) Emitted-Drift-Ack-Growth: gsd-executor.md — the #3770 fail-fast rule now requires intentional RED evidence (check tdd-red-evidence) before GREEN; +172 bytes, kept under the LARGE cap and on one line * chore(3770): add changeset * chore(3770): backfill PR number in changeset --------- Co-authored-by: sim <sim@local> |
||
|
Tom Boucher
|
97ce61dee2 |
fix(#3990): state the RED/GREEN/REFACTOR cycle once, embed tdd.md conditionally (#4228)
* test(#3990): the RED/GREEN/REFACTOR cycle is stated once, embedded conditionally * fix(#3990): state the cycle once — pointers in consumers, conditional tdd.md embeds Emitted-Drift-Ack-Growth: execute-phase.md — #3990 conditions the tdd.md embed on the dispatch being TDD * chore(#3990): changeset for the single-statement TDD cycle * chore(#3990): backfill changeset pr number * fix(#4228): linear cycle check — the lazy-span regex pinned a Windows core for the whole job cap * test(#3990): allowlist pin tracks the rebased line * fix(tests): npm-integrity gate names an empty audit output explicitly — empty stdout crashed the parse as a bare SyntaxError * fix: name an empty npm-audit stdout explicitly — it crashed the parse as a bare SyntaxError Observed on CI (several branches, all lanes): spawnSync npm ETIMEDOUT with empty stdout; the empty string survived the recovery path and surfaced as 'SyntaxError: Unexpected end of JSON input', hiding the captured error. The recovery path now requires non-empty stdout, and an empty result throws with the captured stdout/stderr/message so the actual error is on the record. Root cause of the ETIMEDOUT itself is NOT diagnosed here — this change only stops masking it. --------- Co-authored-by: sim <sim@local> |
||
|
Tom Boucher
|
3639ab0431 |
fix(#3968): measure commit claims at all three surfaces — ledger, verifier BLOCKER, porcelain HANDOFF (#4230)
* test(#3968): commit claims must be measured against git, never narrated * fix(#3968): measure commit claims at all three surfaces Emitted-Drift-Ack-Growth: gsd-executor.md — #3968 plan commit ledger and measured commits contract (held under the agent size cap) Emitted-Drift-Ack-Growth: verify-work.md — #3968 commit-claim reconciliation with the same rev-list instrument Emitted-Drift-Ack-Growth: pause-work.md — #3968 uncommitted_files from git status --porcelain * fix(#3968): retired slash syntax, allowlist line pin, git-compare test pin * fix(#3968): persist the ledger on disk and reconcile with the same rev-list instrument Emitted-Drift-Ack-Growth: gsd-executor.md — #3968 plan commit ledger and measured commits contract (held under the agent size cap) Emitted-Drift-Ack-Growth: verify-work.md — #3968 commit-claim reconciliation with the same rev-list instrument * fix(#3968): hold the gsd-executor size cap with a compact ledger contract Emitted-Drift-Ack-Growth: gsd-executor.md — #3968 plan commit ledger and measured commits contract (held under the agent size cap) * fix(#3968): allowlist pin and HALT regex track the final prose * chore(#3968): changeset for measured commit claims * chore(#3968): backfill changeset pr number * fix(#3968): quote the BASE expansion (SC2086) * ci: raise the test-lane budget 21 to 32 minutes (measured cost grew past the cap) --------- Co-authored-by: sim <sim@local> |
||
|
Tom Boucher
|
647365faf1 |
fix(#4011): key the TDD runtime gate on TDD_MODE alone (#4180)
* test(#4011): TDD gate keys on TDD_MODE alone, not the MVP intersection Contract updates: no shipped line may conjoin MVP_MODE with TDD_MODE as a gate condition, the end-of-phase escalation must not require MVP, the executor agent's gate section triggers on TDD_MODE alone, and the gate semantics reference loads without MVP_MODE. * fix(#4011): key the TDD runtime gate on TDD_MODE alone The RED-commit gate shipped as #76's MVP slice kept the paired invocation's conjunct, so workflow.tdd_mode=true was silently inert on every non-MVP phase, contradicting references/tdd.md's own contract. Drops the MVP conjunct from the per-task gate and the end-of-phase review escalation; rescopes execute-mvp-tdd.md's load condition, gsd-executor's gate section, and mvp-concepts' intersection claim. MVP remains free to imply TDD; the file is not renamed (stated assumption in the PR body). * test(#4011): scope no-conjunct detector to shell conditions; clean stale MVP+TDD phrasing Review follow-ups: the detector now only inspects if/[ condition lines so explanatory prose mentioning both flags cannot trip it; remaining 'under/outside MVP+TDD' phrases in execute-phase.md, the gate reference, and docs/INVENTORY.md now describe TDD-mode semantics. Emitted-Drift-Ack-Growth: execute-phase.md — TDD-gate decoupling comment + escalation rescoping (#4011) Emitted-Drift-Ack-Growth: gsd-executor.md — gate section trigger rescoped to TDD_MODE alone (#4011) * chore(#4011): backfill changeset pr number --------- Co-authored-by: sim <sim@local> |
||
|
Tom Boucher
|
192eb1dfbd |
fix(#3886): git commit timeout reported as commit_timeout; stale lock surfaced; 30s band (#4046)
* test(#3886): a timed-out git commit reports commit_timeout, not commit_failed (failing first) * fix(#3886): git commit timeout reported as commit_timeout; 30s band; stale-lock surfaced cmdCommit's git commit invocation did not distinguish a spawnSync timeout from a real non-zero exit (#2608 fixed this for the staging loop only): a slow pre-commit hook crossing the 10s cap was SIGTERM'd mid-hook and reported as reason commit_failed with whatever partial stderr git had flushed (in the reporter's case an incidental CRLF warning), while the kill left a stale .git/index.lock blocking the next attempt. All three commit sites now check isSpawnTimeout before the nothing-to-commit/ordinary-failure branches: cmdCommit reports reason commit_timeout + timed_out:true and names the stale lock's path (surfaced, not auto-deleted — deleting a lock a live git holds is destructive; the caller recovers deliberately); the subrepo counterparts do the same within their per-repo result / rollback error. The commit calls also move to the 30s band the push call already uses — husky+lint-staged alone idles ~4s on Windows before any task runs. * fix(#3886): review fold-ins — git-path lock resolution, shared band constant, executor contract row, precedence pin - The stale-lock path is resolved via git rev-parse --git-path index.lock, never a literal .git/index.lock join (#3588 row 8's class: a linked worktree's .git is a FILE, so the literal path cannot exist there while the real lock — under <gitdir>/worktrees/<name>/ — blocks the next commit; this repo leans on linked worktrees). - COMMIT_TIMEOUT_MS hoisted; all three sites and their messages build from it (the subrepo variant also regains the stdout fallback the primary site had). - agents/gsd-executor.md's commit-result contract gains the commit_timeout row with the OPPOSITE retry advice from staging_timeout (remove the stale lock, then retry once) — an executor matching the doc previously had no handling for the new reason. - Precedence pin: a timeout whose partial output contains 'nothing to commit' must still read as a timeout (branch-reorder mutant). Emitted-Drift-Ack-Growth: gsd-executor.md — #3886: +commit_timeout row to the commit-result contract with the retry guidance OPPOSITE staging_timeout's (remove the stale lock, then retry once); the executor previously had no handling for the new reason. * chore(#3886): changeset fragment (pr number backfilled after PR creation) * chore(#3886): backfill changeset PR number (4046) --------- Co-authored-by: sim <sim@local> |
||
|
Tom Boucher
|
52b11ee811 |
fix(#3763): pass --raw at every shipped config-get bash call site (#3961)
* test(#3763): guard every shipped config-get substitution on --raw * fix(#3763): pass --raw at every shipped config-get bash call site config-get without --raw prints JSON.stringify(value), so string-typed values reach bash with literal quotes and every string comparison silently never matches (#3763). --raw added at 75 command-substitution sites across shipped content; four JSON consumers (default_reviewers, sub_repos, pr_body_sections, code_review_depth_overrides) deliberately keep default JSON output. Emitted-Drift-Ack-Growth: ai-integration-phase.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: audit-fix.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: autonomous.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: cleanup.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: code-review.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: complete-milestone.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: discuss-phase-assumptions.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: do.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: eval-review.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: execute-phase.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: execute-plan.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: fast.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: graduation.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: gsd-executor.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: health.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: import.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: inbox.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: ingest-docs.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: mvp-phase.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: new-milestone.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: next.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: plan-phase.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: plan-review-convergence.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: plant-seed.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: profile-user.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: progress.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: quick.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: remove-workspace.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: secure-phase.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: settings-integrations.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: settings.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: ship.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: sketch-wrap-up.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: sketch.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: smart-entry.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: spike-wrap-up.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: spike.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: ui-phase.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: ui-review.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: undo.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted Emitted-Drift-Ack-Growth: validate-phase.md — #3763: bytes from '--raw' at config-get call sites so string-typed config values reach bash comparisons unquoted * chore(#3763): changeset fragment (pr number backfilled after PR creation) * chore(#3763): backfill changeset PR number (3961) --------- Co-authored-by: sim <sim@local> |
||
|
Tom Boucher
|
fb2d122d7f |
feat(#3841): assert gsd-tools identity on every state-mutating verb (#3848)
* feat(#3841): assert gsd-tools identity before any state-mutating verb only this package publishes. The path-based branches — a project-local install, a runtime config directory — had no such guarantee; they trusted their configured location. This closes them. Mechanism: once resolution finishes, and before any verb runs, the preamble probes the tool it picked with `runtime-identity --raw` and matches the answer with a shell `case` pattern ANCHORED to the start of the compact payload (`{"packageName":"@opengsd/gsd-core"`). An unanchored substring match accepts the decoy `{"packageName":"get-shit-done-cc","note":"@opengsd/gsd-core"}`, which any colliding package could publish. The outcome is exported as the two-valued `GSD_IDENTITY_STATUS` (`ok`/`unverified`), so the gate is asserted on a VALUE rather than on warning prose. Rollout is warn-then-fail per the #3146 ruling: `unverified` prints one line naming BOTH causes and continues, because `no_identity_verb` cannot tell a foreign package from an `@opengsd/gsd-core` older than the verb, and at rollout the old-version case is the common one. The blocker was byte budget, not design. The preamble is inlined into 112 shipped files and several sat within single-digit bytes of frozen ceilings (`gsd-verifier.md` 16 bytes, `gsd-executor.md` 33, `execute-phase.md` 234); a first attempt broke five of them. What made room was collapsing the resolver's twenty near-identical `elif [ -f … ]` arms into one candidate-list helper (`_gsd_at`), which buys far more than the assertion costs. The preamble is now 2,624 bytes against 4,500 — a net 1,876 bytes SMALLER per inlined file, so every capped file moved away from its ceiling rather than toward it. No cap raised, no size-budget exception added, no override token emitted. Resolution order, every runtime-home probe, the `unset -f gsd_run` re-source fix, the fail-closed `exit 1`, and the `CLAUDE_ENV_FILE` persistence are all preserved byte-for-byte in substring terms; the snippet still begins with `_GSD_SHIM_NAME=` and still ends with `fi`, which the parity extractors anchor on. `gsd-core/references/gsd-run-resolver.md` is re-synced byte-equal. Also fixes two stale claims found in passing: CONTEXT.md and FEATURES.md both described an `[ -x ]` guard as the load-bearing re-source defense. That guard was tried and REMOVED in #3831 — it rejected the bare function name, fell through every branch, and hit `exit 1`, which kills a sourced caller's shell. `unset -f gsd_run` is the actual mechanism. Refs #3841 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fix(#3841): pair the anchor's brace by requiring a closed identity payload The matrix went red on `tests/new-project-mvp-prompt.test.cjs` — "new-project.md has unbalanced braces: net depth 2" — plus a knock-on report from its parent `bug #1516` describe, which is the same failure counted once at the child and once at the block. Root cause: that guard (:182-189, mirroring #3784 bd53925f) walks characters and increments on `{`, decrements on `}`, with no awareness of shell quoting. It scans `new-project.md` PLUS every `new-project/steps/*.md`, and both `new-project.md` and `steps/auto-mode-config.md` carry one inlined preamble copy — hence net 2 from a snippet that was off by exactly one. The unpaired brace was the `{` inside the single-quoted `case` pattern of the identity anchor, which is correct shell and invisible to a text scanner. Fix in the snippet, not the guard. The pattern now anchors at BOTH ends: `'{"packageName":"@opengsd/gsd-core"'*'}'`. That balances 51/51 with a brace that does real work rather than a cosmetic pair — a truncated payload whose prefix matches now fails too, where before it verified. Safe for any future additive field: a JSON object's own closing brace is always the last character, whatever type the last value has, which is pinned by two negative-space tests (a nested object and an array-valued last key must both still verify). Cost: +3 bytes, against the 1,873 the resolver fold already gave back. The alternative considered and rejected was dropping the literal `{` for a `?` glob. It balances too, but weakens the anchor from "must be an opening brace" to "must be any one character", and the anchor is the entire point. Two guards added so this cannot recur silently: - runtime-launcher-parity (F0) pins brace balance at the SNIPPET, so the next edit to that pattern fails on the file it broke instead of surfacing three files downstream in a test whose name mentions neither the launcher nor this issue. It also asserts depth never goes negative, since a `}` preceding its `{` nets to zero while being unbalanced at every prefix. - runtime-identity gains behavioral truncated-payload and trailing-garbage fixtures, so the added `}` is proven load-bearing rather than merely present. Verified: snippet 51/51 braces; new-project combined net depth 0; the seven other preamble-bearing files with nonzero depth are unchanged from merged next (their own prose, not the preamble, and not in any guard's scan set); all 112 inlined copies and the resolver reference re-synced byte-equal; sync:launcher idempotent on the second run. Refs #3841 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * chore(#3841): backfill changeset PR number Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> --------- Co-authored-by: sim <sim@local> Co-authored-by: Claude Opus 5 <noreply@anthropic.com> |
||
|
Tom Boucher
|
63abcface9 |
feat(#3146): resolve gsd_run so workflows cannot reach a foreign gsd-tools (#3831)
* feat(#3146): resolve gsd_run so workflows cannot reach a foreign gsd-tools The predecessor package get-shit-done-cc publishes a colliding gsd-tools bin whose phases.clear DELETES where this package's ARCHIVES, and both print success-shaped output against a gitignored .planning/ -- which is how #3129 cost a user 43 phase directories with no error and nothing recoverable from git. The launcher's PATH branch now resolves gsd_run, published only by this package and self-locating via its own symlink chain to the sibling shim, instead of the colliding gsd-tools. A foreign handler becomes unreachable from PATH, and when no gsd_run is reachable the resolver fails closed rather than falling back -- that fallback was the vulnerability. This is smaller than the branch it replaces, which matters: the preamble is inlined into 113 shipped files and agents/gsd-verifier.md sits 2 bytes under a red-line size cap. unset -f gsd_run leads the preamble so a re-source is idempotent. Without it, command -v finds the shell function, returns a bare name, and the resolver falls through to an exit 1 that kills a sourced caller's shell. Adds gsd-tools runtime-identity, a manual diagnostic reporting this runtime's package coordinates over the baked package-identity (#498) and readHostVersion, with a strict total classifier: only a JSON object with an exact packageName verifies, since JSON.parse admits 0/"str"/[]/null/true. An inlined identity assertion was built and reviewed first, then withdrawn -- it breaks five frozen size ceilings and no assertion fits in 2 bytes. Closes #3146 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fix(#3146): stop sync:launcher relocating a deliberate preamble placement Pre-existing defect, surfaced by this PR because sync is a no-op unless the snippet content actually changes. transformFile inserts the preamble into the first block that CALLS gsd_run, but gsd-core/workflows/explore.md deliberately places it in a bootstrap-only block that DEFINES gsd_run without calling it -- its own comment explains why: declining the research offer must not leave Step 5's commit call unbootstrapped. Stripping empties that block of calls, so the preamble migrated forward and broke the define-before-use invariant tests/explore-command.test.cjs pins. Reproduced on a pristine origin/next checkout with the base snippet and base file, so this was not introduced here. The insertion target now honours a block that already carried the preamble, falling back to the first calling block for files that have none yet. Adds a behavioral regression test over a two-block fixture. Also updates three runtime-launcher-parity tests that pinned the removed PATH fallback to gsd-tools. Their intent is preserved -- the PATH stub is renamed gsd_run so it is reachable by the new resolver, and the RUNTIME_DIR-wins test still asserts the stub is never invoked. Fixture shebangs move to an absolute /bin/sh, because the fixture PATH is deliberately restricted and #!/usr/bin/env sh could not resolve. Refs #3146 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * chore(#3146): backfill changeset PR number Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * docs(#3146): document the FEATURES.md section-numbering practice The monotonically increasing section number in docs/FEATURES.md is the most frequent merge-conflict source in this repo, and it has TWO conflict cells, not one: the ### N. heading and the hand-maintained table of contents. Two PRs adding differently numbered features still collide on the TOC, so renumbering alone does not make a branch safe. This branch alone was renumbered 165 -> 166 -> 167 -> 168 across successive rebases. Adds a CONTRIBUTING section stating the practice: allocate the number last, never pre-emptively renumber, take max+1 after a rebase and update the TOC in the same commit, and never renumber someone else's section. Fork contributors are told explicitly they may leave the number to a maintainer at merge rather than chasing the counter. Agents are told to lease the allocation and to include the file in their published touched set. Records the durable fix as planned rather than pretending it exists: FEATURES.md should be generated from per-feature fragments the way CHANGELOG.md is generated from .changeset/, and the way tests/emitted-drift-acks/ works (#2914). Also renumbers this branch's own section to 168, leaving 167 to the PR already in flight. Refs #3146 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> --------- Co-authored-by: sim <sim@local> Co-authored-by: Claude Opus 5 <noreply@anthropic.com> |
||
|
Behruz Nassre Esfahani
|
622f43353c |
fix(#3299): tracer feedback gate honors workflow.human_verify_mode (#3390)
* fix(#3299): tracer feedback gate honors workflow.human_verify_mode
The tracer feedback gate (#2294) predates `workflow.human_verify_mode`
(#3309, whose scope was the planner and verifier only), and branched on
auto-mode alone. Under the documented `end-of-phase` default an
interactive run therefore halted after EVERY `type="tracer"` task,
synthesizing a `checkpoint:human-verify` no planner ever emitted and
asking the user to retype a verdict the executor had just computed —
at the cost of a full executor cold-start each time.
Planner-side suppression cannot reach this halt because the executor
synthesizes it at runtime, which is why #3309 did not close it.
The gate now branches on HUMAN_VERIFY_MODE in the interactive path:
under `end-of-phase` an automated-only tracer `<verify>` is re-run and,
on success, expansion continues with no checkpoint. HALT-on-failure is
unchanged. `mid-flight`, `gate="blocking-human"`, and tracers carrying
genuine `<human-check>` evidence all still stop; the autonomous branch
is untouched.
`--default end-of-phase` on the config read is load-bearing, not
decorative: `workflow.human_verify_mode` is absent from SCHEMA_DEFAULTS,
so a bare `config-get` exits non-zero with `Key not found` on any
project whose config.json predates #3309 — which is the reporter's
exact config and every pre-existing project.
Both copies of the rule (workflows/execute-plan.md and
agents/gsd-executor.md) are updated together; the reference doc records
the seam and the human-check-still-halts rationale so it cannot recur.
Fixes #3299
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* chore(#3299): add changeset
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix(#3299): reconcile the canonical schema table and the stale acceptance test
Review round 1 (trek-e) — three items, all in the drift class this PR is
about, two of them landed inside this PR's own diff.
1. docs/reference/plan-md.md:233 — CONTEXT.md names this file the canonical
schema reference for the tracer task-type contract, and its Task-types row
still claimed interactive runs unconditionally present a
checkpoint:human-verify. CONTEXT.md and docs/AGENTS.md were updated in the
first round; this one was missed, so the authoritative reference was the
wrong answer. The row now carries the human_verify_mode-conditional
behavior and points at the canonical precedence chain.
2. tests/tracer-bullet.test.cjs — the docs assertion only checked that a
tracer ROW EXISTS, never its content, which is why CI could not see the
drift. It now asserts the row's actual claims and rejects the pre-#3299
wording. Separately, the #1945 acceptance test named 'interactive run emits
checkpoint:human-verify after the tracer' kept passing only because its
substrings still occur in the fallback clause, while its name asserted the
opposite of shipped behavior. Renamed and narrowed to what #1945 still
guarantees, plus a new interactiveIsConditional pin so the unconditional
prose cannot be restored under a passing substring check.
3. plan-md.md's <verify> row now documents that the legacy bare-text form
(valid, and still shown at :179) does not reach the #3299 auto-continue —
only a <verify> carrying <automated> does — so the benefit is silently
unreachable for tracers using that format.
Mutation-verified: reverting the plan-md row fails 1 test; reverting the
executor's interactive branch fails 4.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* fix(#3299): make the tracer gate reachable from the planner template, and bind the assertions
Peer review round 3 found two Majors, both verified by reproducing the
mutation before fixing.
MAJOR 1 — the fix was largely inert on its own default path.
agents/gsd-planner.md's Nyquist Rule (:191) says every <verify> includes
<automated>, but the tracer-specific template twelve lines later emitted the
legacy bare-text form. The gate auto-continues only on a <verify> carrying
only <automated>, so every tracer produced from the canonical template fell
to the STOP fallback and #3299's benefit was unreachable for exactly the task
type it targets. Template now wraps in <automated>; a contract assertion pins
it so the two cannot drift apart again.
MAJOR 2 — the new assertions did not bind condition to action.
Appending 'Nevertheless, interactive runs always present a
checkpoint:human-verify' to the canonical row, and 'then immediately STOP and
return a checkpoint:human-verify' to the auto-continue clause in BOTH
operative copies, restored unconditional interactive checkpointing and left
the suite 35/35 green. Every required keyword still matched. Fixed by:
- clause 2 must now contain no STOP outcome and emit no checkpoint at all —
'never a checkpoint' has to be true OF the clause, not merely stated in it;
- interactiveIsConditional replaced with the ordered-clause parse plus the
same no-STOP property, instead of proving only that HUMAN_VERIFY_MODE
appears somewhere on the line;
- the plan-md.md Autonomy cell is now pinned EXACTLY rather than by keyword
presence. Deliberately brittle: CONTEXT.md names that table the canonical
schema reference, so a wording change must be a conscious edit in both
places.
Mutation-verified after the fix: the combined semantic regression now fails 3
tests; reverting the planner template fails 1.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* test(#3299): exact-pin the safety clauses instead of blacklisting outcome verbs
Peer review round 4. Blacklisting did not hold, twice over:
- Round 3 banned literal STOP and the 'return a'/'present a' checkpoint
forms in the auto-continue clause. Round 4 defeated that by appending
'then pause and invoke checkpoint_protocol with a checkpoint:human-verify
before expansion' — none of the banned tokens, same restored interruption
after every successful tracer. 36/36 passed.
- The planner guard looked for <automated> anywhere inside <verify>, so
'<verify>[...]<!--<automated>--></verify>' satisfied it while leaving the
legacy bare form operative. 107/107 passed across tracer, planner and the
three size-cap suites.
Synonyms are unbounded; the clauses are not. Both are now pinned exactly on
normalized whitespace, the same approach already proven on the plan-md.md
Autonomy cell, with defence-in-depth checks behind them: no checkpoint-emitting
or blocking outcome in any wording inside clause 2, and the planner's <verify>
body must be exactly one non-empty <automated> child with no commented markup.
These pins are deliberately brittle. Each is a safety contract, so changing the
behavior must be a conscious edit in both the prose and the expectation.
Mutation-verified: the synonym-checkpoint mutation fails 1; the commented-out
wrapper fails 1; the round-3 literal-STOP + contradictory-doc-row regression
fails 3.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* test(#3299): strip comments, require uniqueness, pin whole regions
Peer review round 5. Exact-pinning one clause was still bypassable two ways,
both reproduced before fixing (each left the suite fully green):
- COMMENTED DECOYS. Put the correct text in an HTML comment followed by a live
wrong copy: every extractor selected the commented decoy. Worked against the
planner template, the canonical plan-md.md row, and both executor branches.
- SURROUNDING OVERRIDE. Insert 'after every tracer, pause and invoke
checkpoint_protocol before expansion, regardless of the mode-specific rules
below' immediately ABOVE the pinned clause, or 'ignore row 3; always wait for
approval' below the canonical table. The pinned text was untouched, so
equality held while the shipped meaning inverted.
The shape that holds, applied to every operative surface:
1. strip HTML comments BEFORE selecting, so a decoy cannot be chosen;
2. require the structural anchor to occur EXACTLY ONCE, so a live second copy
cannot hide behind a correct first one;
3. pin the ENTIRE decision region, not one clause, so no unparsed prefix or
suffix can override what the pin proves.
Applied to: the executor's whole tracer branch, execute-plan.md's whole
dispatch line, checkpoints.md's whole precedence section, and plan-md.md's
Autonomy cell.
Also addresses the round-5 Minor: the planner template is now asserted
STRUCTURALLY (exactly one <verify> in the fenced block, body exactly one
non-empty <automated> child) rather than pinning the descriptive placeholder
verbatim, so behavior-preserving wording changes no longer false-fail. The
clause and section pins keep their exact form — those have a safety rationale
the placeholder copy does not.
Mutation-verified, all six rounds: override-above-clause 1; commented decoy row
1; commented decoy branch 1; ignore-row-3 override 1; synonym checkpoint 1;
commented-out wrapper 2.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* test(#3299): drop the superseded exact-placeholder planner assertion
Peer review round 6, Minor. The round-5 brittleness fix ADDED a structural
planner assertion but left the old exact-placeholder one in place, so the
over-brittleness it was meant to remove was still live: rewording the
descriptive placeholder while preserving exactly one non-empty direct
<automated> child failed the old test and passed the new one.
Removed the old test. The structural assertion is the real contract — the gate
auto-continues on the SHAPE of the verify, not on the wording of a placeholder.
Verified both directions: a behavior-preserving reword now passes; reverting the
template to bare <verify> still fails.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* test(#3299): select operative prose via parsePredicates, not a hand-rolled scanner
Peer review round 7. I had judged the round-6 selector bypass adversarial-only
and out of scope, intending to disclose it. Both premises were wrong, and the
review said so:
- 'Needs new src API' — false. parsePredicates is ALREADY a public export and
internally uses the repo's interleaved fence/comment scanner. Instrumenting
candidate lines as throwaway predicate declarations borrows that scanner with
no src change at all.
- 'Adversarial-only' — false, and this is the part that mattered. Two ORDINARY
edits silently turned the guards into decoy checks:
* a forgotten '-->' comments the live rule through to EOF, and the
balanced-only stripper still saw and accepted the commented rule;
* a normal fenced documentation example of the rule, plus a whitespace-only
reformat of the live list item, made the selector choose the example.
Neither needs intent. A dangling comment is a typo; a fenced example is good
documentation. Together they reproduce exactly the accidental drift #3299 came
from — with CI green.
The selection layer now defers to parsePredicates for operativeness, uses
whitespace-tolerant anchors so a reformat cannot decouple the live line from its
pin, extracts regions by operative line index rather than string search, and
carries a self-guard test proving fenced / balanced-commented /
after-unclosed-comment copies are all excluded. The helper also ignores indexes
it did not inject, so a pre-existing GSDTEST.CANDIDATE line cannot pollute it.
Verified both ordinary-edit scenarios now fail the suite (each was green before).
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* test(#3299): close the operative-selection gaps the maintainer blocked on
trek-e's Blocker: the operative-line selection layer had three gaps, all
reachable by ordinary future doc edits rather than sabotage. He independently
found a fourth I had not disclosed. All are fixed.
1. INDENTATION PROMOTION (his find, not in my disclosure). The instrumentation
replaced a matched candidate with an UNINDENTED marker regardless of the
original line's indentation. A 4-space-indented CommonMark code block is not
skipped by parsePredicates (it accepts indented declarations by design), so
stripping the indent PROMOTED an indented decoy to operative — the exact
inversion of the guard's purpose. The marker now preserves the original
indent, and a candidate that is itself indented 4+ spaces is never injected.
2. NO SET MEMBERSHIP. The filter accepted any in-range integer, so a
pre-existing literal GSDTEST.CANDIDATE=<valid index> in source text could
pollute the count. Now filters on a Set of the indexes actually injected on
this call.
3. RAW FENCE SELECTION (planner). The template test matched the first raw
```xml fence after the marker with no fence/comment awareness — the one
selection in the suite that was not operative-aware — so a commented-out
decoy template between the marker and the real one would be selected while
the live template regressed. The opener must now be operative AND the first
non-blank line after the marker.
4. RAW END ANCHOR (regionFrom). The end anchor was tested against raw lines, so
a fenced example containing a ### / <type line truncated the pinned region
early — a false FAILURE on a legitimate doc edit. End anchors now go through
the same operative filter as start anchors.
Mutation-verified: the indented-decoy + whitespace-varied-anchor combination
and the commented-out fence decoy each now fail the suite (both passed clean
before). Truncation is confirmed fixed by extraction — the region spans the
full section and retains the content following a fenced example, where it
previously stopped at it.
Note on the remaining brittleness: adding a fenced example INSIDE a pinned
region still fails the whole-region exact pin. That is the intended tradeoff
for a safety contract, not the truncation defect, and is called out as such.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* test(#3299): allow-list operative indentation; pin marker provenance
Review round 9.
BLOCKER — the round-8 indentation guard was written as a DENY-list,
/^(?: {4,}|\t)/, and CommonMark has more indented-code forms than that
enumerates: " \t", " \t" and " \t" all open an indented code block and all
slipped through, so an indented decoy was still promoted to operative while the
live rule regressed (34/34 green). Inverted to an allow-list — only 0-3 literal
spaces is ordinary block indentation; anything else is code. Enumerating the
bad shapes was the error, not the specific regex.
MINOR — the injected-index Set validated the marker's VALUE but not its SOURCE.
A pre-existing literal `GSDTEST.CANDIDATE=<n>` could name an index that some
other (skipped) candidate had contributed to the set, and be accepted. Now also
requires p.line - 1 === Number(p.value): the predicate must have been parsed
from the line it names.
MINOR (false negative) — ```xml title=x is a valid CommonMark info string, and
requiring exactly ```xml failed the suite (33/34) on a behavior-preserving edit.
Both the opener assertion and the extraction now accept an info string.
Mutation-verified: the mixed " \t" decoy and the forged-provenance marker each
now fail; the info-string fence no longer false-fails.
KNOWN LIMITATION, disclosed on the PR rather than papered over: parsePredicates
is a predicate parser, not a general CommonMark operativeness oracle. Two
standards-valid constructs still read as operative — a lazy blockquote
continuation line (state opens only on a line that literally starts with ">"),
and a comment opened mid-line ("prose <!--", where state opens only when the
trimmed line STARTS with "<!--"). Closing those means either teaching the shared
src/context-predicates.cts about container/lazy-continuation state — a change to
a module every health rule consumes, well outside a tracer-gate fix — or
hand-rolling a CommonMark parser inside a test, which is how this suite got into
trouble in the first place. Left for the maintainer to scope.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* chore(#3299): re-arm the execute-plan.md emitted-drift ack after the base merge
The #3299 ack rode on tests/emitted-drift-acks/2652-quick-diagnose-dispatch-isolation.json,
which upstream retired in
|
||
|
Tom Boucher
|
ec7e49a64c |
fix(#3576): repair all 43 dead references/ cites and gate the canonical resolvable form (#3596)
* test(#3576): gate shipped reference citations on the canonical resolvable form Failing-first gate for #3576: a backticked bare references/<name>.md cite resolves from no install location (agents, workflows, and references all install where a bare relative references/ path is dead). The gate walks the runtime-loaded trees the issue prescribes, strips @~/ include tokens PER-TOKEN (a line-skip guard would miss a bare cite sharing a line with an include — the issue-named trap), pins the genuinely relative ../ href and canonical forms as non-offenders, and checks canonical cite targets exist. 43 offenders today across 19 files. * fix(#3576): repair all 43 dead references/ cites to the canonical resolvable form Every backticked bare references/<name>.md cite across the 19 shipped files rewritten to gsd-core/references/<name>.md — the form every required_reading block and @~/ include already uses, and the only form that resolves from any install location. All 20 cited targets verified to exist; the one genuinely relative href (plan-phase.md's ../references/mvp-concepts.md) is untouched (the repair is backtick-anchored). Growth acks: new fragment for the three first-time paths, #3206-pattern appends to the five fragments already naming the other grown files (two ack sources may never name the same path). execute-phase.md lands at 93,391/93,400 and gsd-executor.md at 49,150/49,152 — exactly the issue's projections; every repair fits. * fix(#3576): drop stale default.md growth ack (nested modes file is hash-attributed, not growth-ratcheted) Review finding: the emitted-attribution ratchet covers only top-level workflows/ + agents/ files; discuss-phase/modes/default.md's delta is source-attributed, so acknowledging its growth is a stale entry the differential lane fails on. * chore(#3576): add changeset fragment * chore(#3576): backfill changeset pr number --------- Co-authored-by: sim <sim@local> |
||
|
Tom Boucher
|
8fc88f663d |
fix(#3210): gate unmet preconditions as blocking-human; cap blocker retries at needs_human (#3528)
* fix(#3210): gate unmet preconditions as blocking-human and cap blocker retries at needs_human * chore(#3210): add changeset fragment for PR #3528 * fix(#3210): restore blocking-human carve-out and CRLF-safe split --------- Co-authored-by: sim <sim@local> |
||
|
Tom Boucher
|
10da377794 |
fix(#3021): recognize worktree-wf_* branch namespace in all guards (#3109)
* fix(#3021): recognize worktree-wf_* branch namespace in all guards The Claude-orchestration Workflow backend (#1143) creates per-plan worktrees on branches named worktree-wf_<runid>-<n>. Four independent copies of the agent branch allow-list regex (^(worktree-)?agent-...) never learned this namespace: - hooks/gsd-worktree-path-guard.js:176 — FAILED OPEN (process.exit(0)), silently disabling path containment for exactly the concurrent dispatch mode where cross-worktree writes are most likely - src/worktree-safety.cts:21 — silently dropped cleanup-wave manifest entries - agents/gsd-executor.md:503 — FATAL halt on branch check - gsd-core/references/worktree-branch-check.md:33 — same FATAL halt Extended all four to ^((worktree-)?agent-|worktree-wf_)[A-Za-z0-9._/-]+$. The path guard now correctly blocks cross-worktree writes for Workflow- backend branches instead of no-op'ing. * chore(#3021): backfill changeset PR number 3109 --------- Co-authored-by: sim <sim@local> |
||
|
Tom Boucher
|
0bb7525a62 |
fix(#2943): rename get-library-docs -> query-docs; correct the ctx7 fallback rationale (#2963)
* test(#2943): parity guard against the nonexistent get-library-docs tool Second context7 naming drift after #2017 (which guarded the plugin-marketplace PREFIX). #2017's guard only checks tools: frontmatter lines, not prose bodies — which is where the broken tool NAME (get-library-docs) lived. The context7 MCP server registers only resolve-library-id and query-docs; get-library-docs is a stale copy from upstream's own README. Scans the shipped prose surface (agents/, gsd-core/references|workflows/, commands/gsd/, skills/) and fails if any artifact instructs an agent to call mcp__context7__get-library-docs. Excludes tests/ (a fixture may use the name as a negative input) and CHANGELOG/RELEASE-NOTES-LEGACY (history). Fails-first: 4 offenders today (gsd-executor.md:29, research-documentation-lookup.md:5, discovery-phase.md:68 & :104). * fix(#2943): rename get-library-docs to query-docs and correct the ctx7 fallback rationale The context7 MCP server registers only resolve-library-id and query-docs (verified against upstream packages/mcp/src/index.ts); get-library-docs is a stale name copied from upstream's own README. Four shipped prose sites instructed agents to call a tool the server does not register, so every research path that loaded the canonical reference either errored, fell through to the ctx7 CLI branch, or fabricated a result. - research-documentation-lookup.md, gsd-executor.md, discovery-phase.md (x2): get-library-docs -> query-docs, params context7CompatibleLibraryId/topic -> libraryId/query (the registered contract). - Same files' ctx7 CLI fallback rationale: the cited cause (anthropics/claude-code#13898 'strips MCP tools from agents with a tools: frontmatter restriction') was wrong on two counts — #13898 is closed and was never about tools: frontmatter. Rewritten to describe the real mechanism (custom subagents cannot see project-scoped .mcp.json; they only inherit user-scoped ~/.claude/mcp.json). The fallback itself is kept. - discovery-phase.md 'mode: code/info' dropped — query-docs takes libraryId + query only; the code-vs-concepts intent is now expressed via the query text. resolve-library-id is unchanged (still registered upstream). CHANGELOG and RELEASE-NOTES-LEGACY citations are historical record, left as-is. * chore(#2943): add changeset fragment (pr:0 placeholder) * test(#2943): widen parity-guard scan surface to docs/ (isolated-review finding) The isolated adversarial review flagged that SCAN_DIRS omitted docs/, which ships docs/AGENTS.md — agent-consumed prose carrying 8 mcp__context7__* refs. No false negative today (it uses only the wildcard), but a future banned-name addition there would slip through, recreating the exact drift this guard exists to prevent. Add docs/ to the scan surface, with an EXCLUDED_FILES set for historical record (docs/RELEASE-NOTES-LEGACY.md, CHANGELOG.md) that must not be rewritten to satisfy the guard. * fix(#2943): update shifted PROSE_ALLOWLIST line + acknowledge gsd-executor.md growth The gsd-test gate caught two real consequences of the rationale rewrite in agents/gsd-executor.md (the +2-line corrected mechanism description shifted line numbers below it): 1. tests/no-bare-gsd-tools-command-position.test.cjs: the legitimate 'gsd-tools query commit' descriptive mention moved from line 791 -> 793. Update the PROSE_ALLOWLIST entry to the new line (the mention is unchanged, just relocated by my edit above it). Without this the gate reports both a stale allowlist entry (791) and a new offender (793) for the same mention. 2. tests/emitted-drift-acks/2943-context7-tool-name.json: gsd-executor.md grew 95 bytes (the accurate mechanism rationale is longer than the wrong one-line #13898 attribution it replaces). Acknowledge the growth with the reason. Both are mandated by the gate, not optional. The rename itself (get-library-docs -> query-docs) is byte-neutral-ish; only the rationale rewrite grew the file. * chore(#2943): backfill changeset PR number 2963 --------- Co-authored-by: sim <sim@local> |
||
|
Tom Boucher
|
28e486faf7 |
fix(#2608): fail closed when git add fails during commit staging (#2693)
* fix(#2608): fail closed when `git add` fails during commit staging `cmdCommit` ignored `git add` failures. #2523 had already stopped a failed path entering the commit pathspec, but skipping it silently left two bad outcomes, both reproduced against the pre-fix build: - SOME paths fail -> `{"committed":true}`. `git commit` still ran and PARTIALLY committed the subset that happened to stage, under a message describing the full requested scope. - EVERY path fails -> `{"reason":"nothing_to_commit"}`, which is not what happened and points the operator nowhere. In both cases git's original `add` stderr was discarded, so the user saw a downstream `commit_failed` / pathspec error naming an innocent file — the symptom reported in the issue from a linked worktree whose git directory was outside the managed writable root. Staging failures are now collected and the command fails closed BEFORE `git commit` runs, returning the issue's specified shape: { committed: false, hash: null, reason: "staging_failed", file: "<first failing path>", error: "<original git add stderr>", failures: [ { file, error, timed_out }, ... ] } A timeout is distinguished as `staging_timeout` (issue AC5) using the projection's SIGTERM+ETIMEDOUT signal — the same idiom worktree-safety.cts uses. The check is placed ahead of the `nothing_to_commit` branch so an all-paths-failed run reports the staging cause rather than an empty changeset. Unchanged: successful staging still commits exactly the declared scope and leaves unrelated staged files alone; an explicitly-named file that does not exist is still skipped rather than staged as a deletion (#2014/#2523), and a request where every named file is missing still reports `nothing_to_commit` — no `git add` ran, so there is no staging failure to report. Regression tests inject the failure by monkeypatching `execGit` on the projection module (per CLAUDE.md, over `chmod 0o000`, which does not fault under root and would make the tests vacuous), driven in a `node -e` child because `output()` writes via `fs.writeSync(1, …)` and cannot be captured in-process. Pre-fix, 6 of the 10 assertions fail; post-fix all pass. Closes #2608 Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QT3ibz5qJuDuGqpTGRYVGf * fix(#2608): roll back the index, guard the sibling surfaces, document the new reasons Six findings from the orthogonal review of the first commit, all fixed here. 1. A `staging_failed` return left the index PARTIALLY STAGED. The paths that did stage stayed in the index with no commit made and no cleanup, so the next bare `git commit` would sweep them up — the same silent partial commit this fix exists to prevent, deferred one step. (Pre-fix the partial state at least got consumed by the incorrect commit.) The staging failure path now resets the paths it staged, matching cmdPrSubrepo's established rollback-then-error convention. The reset is scoped to what THIS call staged — paths the caller had already staged are captured up front and excluded, so a caller's own work is never destroyed — and is best-effort, since an unwritable index (the very failure being reported) cannot be reset either. 2. `cmdCommitToSubrepo` still had the identical defect: a failed `git add` was dropped silently and the function committed the subset that happened to stage, discarding git's stderr. It now fails closed per sub-repo with the same staging_failed/staging_timeout reasons and the same scoped rollback. 3. The `git rm --cached --ignore-unmatch` branch (default mode, for a planning file that no longer exists on disk) still discarded its result. It mutates the index exactly like `git add`, and `--ignore-unmatch` already makes "no such path" a success, so a non-zero exit there is a real I/O failure — now routed through the same staging-failure path. 4. `agents/gsd-executor.md` documented the commit envelope as an exhaustive three-shape enum and pattern-matched only `nothing_to_commit | commit_failed`. It is the sole consumer doc for this surface, so the new reasons are added with explicit guidance not to retry (a retry hits the same unwritable index), and the "one of three shapes" framing is corrected. 5. The default (non---files) staging path and `--amend` are now covered by tests. Both were already guarded by the first commit but unexercised. 6. The changeset framed the fix as `--files`-only; it applies to default and sub-repo commits too, and now mentions the rollback. Regenerated the agent size baseline and the 18 golden install-parity fixtures for the gsd-executor.md edit. 16 assertions across both surfaces verified against the built lib. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QT3ibz5qJuDuGqpTGRYVGf * test(#2608): update the #2523 out-of-repo contract to the new staging_failed reason The remote test run surfaced this: `#2523: out-of-repo --files path is rejected by git` asserted `reason: 'nothing_to_commit'`, and now gets `staging_failed`. This is a deliberate contract improvement, not a papered-over failure. The old reason existed only because a failed `git add` was skipped and the resulting empty `stagedPaths` fell through to the empty-changeset branch. But "nothing to commit" is not what happened — the caller named a file and git refused it — and that misreport is exactly the class of defect #2608 closes. The result now carries the offending path and git's own message ("… is outside repository at …"), which is strictly more actionable for the same condition. #2523's two substantive invariants are untouched and still asserted: no commit is created, and the index is left clean. Two assertions are ADDED (the path is named, git's message is preserved) so the richer contract is pinned rather than merely allowed. Per CONTRIBUTING, a stale-test correction rides its own commit. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QT3ibz5qJuDuGqpTGRYVGf * fix(#2608): compact the executor doc addition to stay under the agent LARGE cap The remote test run failed: `gsd-executor.md is 49217 bytes — exceeds the LARGE hard cap of 49152`. The file was already at 48596 (556 bytes of headroom) and the new commit-envelope documentation pushed it 65 bytes over. The cap is a red line, not a budget to raise, so the addition is compacted rather than the cap moved: four lines instead of eight, keeping the load-bearing facts — the two new reasons, that nothing was committed and the index was rolled back, that `file` + `error` should be surfaced, and that retrying is wrong because a retry hits the same cause. Dropped only the restatement of the linked-worktree example (already in the changeset and PR) and the `failures[]` field (a superset of `file`/`error`, discoverable from the payload). Net addition is now 276 bytes; the file sits at 48872 with 280 bytes of headroom. Extracting the agent's shared boilerplate to references/ would buy much more, but that is a restructuring of the executor agent and does not belong in a commit-staging bugfix. Agent size baseline and the golden install-parity fixtures regenerated. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QT3ibz5qJuDuGqpTGRYVGf * chore(#2608): backfill changeset PR number (#2693) --------- Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Tom Boucher
|
bd570618d4 |
feat(#2632): executor actuals and the closed estimate-calibration loop (#2672)
* feat(#2632): record executor actuals and close the estimate calibration loop * fix(#2632): calibrate against the raw projection so the loop converges * test(#2632): add closed-loop convergence guard and codify the feedback-loop rule * fix(#2632): pair calibration samples per plan; atomic write; amend adr * chore(#2632): backfill changeset pr to 2672 * fix(#2632): retry renameSync on transient windows errnos and clean up the temp |
||
|
Tom Boucher
|
77bf21b3a6 |
fix(#1995): widen worktree branch regex to accept agent-<id> namespace (#2548)
* test(#1995): regression test for agent-<id> branch namespace Add failing-first tests proving that normalizeCleanupManifestEntry and planWorktreeRecordAgent reject Claude Code's current agent-<id> isolation branches (only worktree-agent-<id> is accepted). Boundary tests cover both namespaces plus rejection cases. * fix(#1995): widen worktree branch regex to accept agent-<id> namespace Claude Code's isolation="worktree" branch naming changed from worktree-agent-<id> to agent-<id>. Widen the regex in all 7 locations from ^worktree-agent-[A-Za-z0-9._/-]+$ to ^(worktree-)?agent-[A-Za-z0-9._/-]+$ so both namespaces are accepted. Introduce a shared WORKTREE_AGENT_BRANCH_RE constant in src/worktree-safety.cts to prevent future drift. Closes #1995 * fix(#1995): update workflow guards, test assertions, and baselines Widen the branch-check regex in execute-phase.md and execute-plan.md. Update all test assertions that checked for ^worktree-agent- to expect the widened ^(worktree-)?agent- pattern. Regenerate golden-install-parity fixtures, agent-size-baseline, and workflow-size-baseline. Closes #1995 * fix(#1995): update extractCwdGuardBash sanity check for widened regex The e2e test's sanity check verified the extracted bash block contained 'worktree-agent-'. After widening to '(worktree-)?agent-', update the check to match the new pattern. * fix(#1995): widen missed workflow-guard branch check + changeset + lint fixes - hooks/gsd-workflow-guard.js: widen startsWith('worktree-agent-') to /^(worktree-)?agent-/ regex — same defect class, was missed in prior commit - tests/worktree.test.cjs: fix indentation regression from prior edit - Add .changeset/1995-worktree-agent-branch-namespace.md (pr:0 placeholder) Found by orthogonal code review (Step 4). * fix(#1995): regenerate golden + size baselines for workflow-guard change * docs(#1995): backfill changeset PR number (2548) |
||
|
Tom Boucher
|
d16a66479a |
feat(#1950): broken-windows ledger — cross-phase defect register gating ship (#2441)
* feat(#1950): broken-windows ledger — cross-phase defect register gating ship Adds a new capability (#1950) that operationalizes GSD's no-defer discipline as a tracked, enforced artifact: accumulates stubs, TODOs, skipped tests, unrun verifies, and unmet truths across phases, and /gsd-ship blocks while any entry is open. Implementation: - src/broken-windows.cts → gsd-core/bin/lib/broken-windows.cjs: typed IR + I/O entry points (parseLedger/renderLedger/appendWindow/markWaived/markFixed + cmdWindowsStatus/Append/Waive/MarkFixed). Frozen REASON enum for typed error assertions. Windows-safe atomic rename with retry on transient EPERM/EBUSY/EACCES. - gsd-tools.cjs: new subcommand (status | append | waive | fixed), wired via routeWindows + HOST_COMMAND_ROUTERS.windows. - capabilities/broken-windows/capability.json: one ship:pre gate with artifact-frontmatter-equals predicate on WINDOWS.md open_count == 0. activationKey windows.enabled (default true) + sibling windows.enforce (default true, separate so tracking can precede enforcement). - gsd-core/workflows/ship.md: capId==broken-windows branch in preflight, sibling to security — reads gsd_run windows status --raw, fails closed on open_count > 0 or unreadable ledger. - agents/gsd-executor.md: extends the existing ## Known Stubs instruction to also append to WINDOWS.md via gsd_run windows append (best-effort, never blocks execution). - agents/gsd-verifier.md: new Step 8b — record unmet truths + human-verify items in WINDOWS.md. - gsd-core/workflows/progress.md: surfaces open + waived counts. - docs/COMMANDS.md + CONTEXT.md glossary entry + docs/INVENTORY.md: document the gate, waiver mechanism, and new module. - tests/broken-windows.test.cjs: pure + CLI behavioral coverage + fast-check roundtrip property; fail-closed on malformed ledger; security boundary on path traversal in --file. Backward-compatible: a project with no .planning/WINDOWS.md reports open_count: 0 and ships cleanly. Disable enforcement per-project with gsd config-set windows.enforce false (tracking continues, gate stays open). * chore(#1950): ratchet size baselines, defer verifier integration - Workflow size baseline: ship.md 25575→27928, progress.md 31789→32632 (broken-windows preflight branch + open-windows surface). - Agent size baseline: gsd-executor.md 46644→47951 (Known Stubs → also appends to WINDOWS.md). gsd-verifier.md unchanged. - LARGE_CAP (49152) preempted the planned verifier integration (gsd-verifier.md was at 49140 pre-PR — 12 bytes of headroom, not the documented 'real headroom'). Verifier integration deferred to a follow-up PR that extracts the VERIFICATION.md template (lines 739-859) to gsd-core/references/ — a pre-existing cap-tightness defect this PR exposed but does not expand scope to fix. Verifier integration is not in the issue's acceptance criteria (executor writes is; unmet-truths recording was an enhancement, not a gate). * fix(#1950): gate default-off, rename to workflow.windows_enforce, regen goldens Test-failure-driven fixes after first gsd-test run on db8733c8f failed 44 cases (pre-existing structural tests encoded 'ship:pre has 1 gate' / 'all caps off → empty hooks'): - capability manifest: rename windows.enabled+windows.enforce (default true) → single federated key workflow.windows_enforce (default FALSE, opt-in). Matches security's workflow.security_enforce convention and makes the adr857 all-caps-off test pass without modification (the test's buildAllFalseConfig handles workflow.* out of the box). Default-OFF keeps the gate out of the registry's default ship:pre resolution so existing loop-hooks-ship-pre-e2e structural assertions (exactly 1 gate, capId 'security') stay valid; users opt in via gsd config-set workflow.windows_enforce true. - drop activationKey (security doesn't have one either; workflow.* key doubles as the activation toggle). - regenerate docs/reference/capability-matrix.md to include broken-windows (capability-matrix-sync test). - regenerate tests/fixtures/golden-install-parity/*.json (18 runtimes) — installer now emits the new capability + lib file. - update CONTEXT.md, docs/COMMANDS.md, docs/FEATURES.md, ship.md, agents/gsd-executor.md to use the new key name and /gsd:colon slash syntax (slash-command-namespace test). - restore accidentally-regressed /gsd:capture in progress.md. Tracking-only by default; enforcement is opt-in. Acceptance criterion '/gsd-ship fails while any ledger entry is open' is met when workflow.windows_enforce=true (test fixture enables it). * test(#1950): update ship:pre structural invariants for 2-gate registry - loop-hooks-ship-pre-e2e: the registry now declares 2 gates at ship:pre (security + broken-windows), regardless of activation. Activation tests above still pin security-only or empty behavior via fixtures; these structural tests pin the REGISTRY shape, which has 2 gates as of #1950. - workflow-size-baseline: ship.md 27928→27945 (workflow.windows_enforce rename added 17 bytes). * fix(#1950): review H1+H2+M1+M2+M3 — fence-injection, EACCES fail-closed, cleanup, strict line, stryker Adversarial isolated review (Step 6.3) found 2 HIGH findings that block the PR and 3 mediums. All addressed: H1 (HIGH): description containing the markdown 3-backtick fence would terminate the ledger's JSON code block early inside JSON.stringify output (JSON doesn't escape backticks), corrupting the file and bricking the next parse. Fix: use a 4-backtick fence (json ... ) which JSON.stringify cannot produce on its own, AND validate that no entry text field contains a 4-backtick run (reject at append time with new WINDOWS_INVALID_TEXT reason code). Locked by a regression test. H2 (HIGH): readLedgerOrNull swallowed ALL fs errors as 'no ledger', silently returning open_count:0 on EACCES/EPERM/EIO. The ship gate would then pass on an unreadable ledger — the precise vector the workflow doc claims is impossible. Fix: only ENOENT returns null; every other fs error propagates as WINDOWS_LEDGER_MALFORMED so the gate blocks and the operator sees a real diagnostic. Locked by a regression test that chmod 000s a ledger with open_count=1 and asserts the result is never a false-green 0. M1: writeLedgerAtomic left an orphaned .tmp file on rename failure. Wrapped renameWithRetry in try/catch with best-effort unlink. M2: validateLine silently coerced 'abc' → NaN → null, hiding type drift. Removed the line === 0 special case (was undocumented) and made the error message match the strict check. Now any non-positive- integer line value throws, including strings. M3: tests/broken-windows.test.cjs (with its fast-check property test) was not in stryker.config.mjs DEFAULT_TEST_CMD — Stryker would mutate src/broken-windows.cts but no test would catch the mutations, producing false surviving-mutant scores. Added to the list. L1 (dead throw e after error()), L7 (line boundary tests, H1/H2 regression tests, 4-backtick CLI test) also addressed. * docs(#1950): inline concurrency + busy-wait notes (review L2+L3) * fix(#1950): regen goldens against latest gsd-tools; correct --line 0 boundary test gsd-test v4 caught two issues: - goldens I regenerated earlier (commit 526682084) predated the L1 routeWindows catch-block cleanup (commit dd844d565). Regenerated via 'npm run gen:golden' against current HEAD so the install parity hash for gsd-tools.cjs matches. - 'append --line boundary' test expected --line 0 to succeed with null entry.line, but the M2 fix correctly rejects 0 (lines are 1-indexed; 0 is not a valid source line). Updated the boundary test to assert --line 0 fails alongside -1 and 'abc'. * chore(#1950): regen goldens after rebase onto next * chore(#1950): quick.md baseline 50699→50993 (correct resolution from next rebase) * chore(changeset): backfill pr:2441 in .changeset/broken-windows-ledger.md * fix(#1950): renderTable escapes backslash before pipe (CodeQL incomplete-sanitization) CodeQL flagged the markdown-table cell escaper: String(s ?? '').replace(/\|/g, '\\|') — it escapes pipe but not backslash first. A description containing '\|' would render as '\\|' which markdown parses as 'literal backslash' + 'cell separator', splitting the column. Fix: escape backslash FIRST (each \ → \\), then pipe (each | → \|). Now a description with '\|' renders as '\\\\|' (literal '\\' + escaped pipe), which markdown renders as a single '\|' inside the cell. The JSON code block (the parse source-of-truth) was already correctly escaped via JSON.stringify; only the display-only table was affected. Locked by a regression test that: 1. Verifies the JSON block reparses with the description intact. 2. Walks the rendered table row counting unescaped pipes — must be exactly 11 (the row separators for 10 cells), proving no in-cell pipe added a split. |
||
|
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] |
||
|
Tom Boucher
|
315d94f6d4 |
feat(#1945): tracer-first planning default + executor feedback gate (#2294)
* feat(#1945): tracer-first planning default + executor feedback gate Make "thin end-to-end slice first, verify, then expand" the default planning + execution discipline instead of the opt-in --mvp mode. - gsd-planner: first-class `type="tracer"` task; every plan LEADS with one production-quality end-to-end tracer slice by default; --no-tracer restores horizontal layers; --mvp/--tdd compose on top. - gsd-executor + execute-plan: post-tracer feedback gate — autonomous runs halt-on-fail before expansion, interactive runs emit checkpoint:human-verify after the tracer. - --no-tracer flag wired through plan-phase workflow/command/help/skill. - CONTEXT.md glossary defines tracer bullet vs prototype; docs + references reconciled. - tests/tracer-bullet.test.cjs: prose-contract + behavioral (verify plan-structure accepts tracer) coverage. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * chore(#1945): backfill changeset PR number to 2294 --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
Adnan
|
3592697bed |
fix(#2107): orchestrator honors gate="blocking-human" checkpoints in auto-mode (#2113)
* fix(execute-phase): honor gate="blocking-human" in auto-mode checkpoint handling The package-legitimacy gate (#2827) spans two layers. gsd-executor refuses to auto-approve a gate="blocking-human" checkpoint and escalates it so a human can vet the package. execute-phase's checkpoint_handling step then dispatched purely on checkpoint *type* and never read gate -- so under --auto/--chain it auto-approved the checkpoint the executor had just refused to auto-approve. Net effect: the slopsquatting defence was inert in exactly the unattended mode where it matters. An [ASSUMED]/[SUS] package reached install with no human ever seeing the prompt. - gsd-core/workflows/execute-phase.md: carve out gate="blocking-human" (and the package-legitimacy what-built markers) ahead of every auto-mode branch. - gsd-core/references/checkpoints.md: document the gate attribute and its two values. blocking-human previously appeared nowhere outside gsd-executor.md, so no planner had a documented way to author a non-auto-approvable checkpoint. - tests/package-legitimacy-gate.test.cjs: the existing regression test asserted the executor half only, which is why it stayed green while the gate was open. Now asserts the orchestrator half too. * chore(changeset): link to issue #2107 * chore(changeset): backfill PR number 2113 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JNR8m2pv5U7ubn4iiXVrMa * test(#2107): refresh golden-install-parity hashes for edited gsd-core files The golden fixtures pin content hashes for gsd-core/references/checkpoints.md and gsd-core/workflows/execute-phase.md, both edited by this fix. Regenerated via UPDATE_GOLDEN=1; only those two keys change across all 17 runtime fixtures. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JNR8m2pv5U7ubn4iiXVrMa * fix(#2107): keep the carve-out inside the ADR-857 host-loop budget The ADR-857 phase-6 ratchet pins execute-phase.md below 93600 LF bytes so optional-feature logic keeps migrating out of the host loop. The carve-out first landed 623 bytes over that ceiling. Move the two-layer rationale (why gsd-executor escalates these checkpoints) into references/checkpoints.md, where the gate is now documented, and reduce the workflow to the operative rule. execute-phase.md is 93589 bytes, under the ceiling; the gate token and both <what-built> marker strings are kept because the orchestrator matches on them. Refresh the two baselines the edit invalidates: golden-install-parity fixtures (only the checkpoints.md and execute-phase.md hashes move) and workflow-size-baseline.json (one line). The ADR-857 ceiling itself is untouched. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JNR8m2pv5U7ubn4iiXVrMa * fix(#2107): executor honors blocking-human on the decision branch + gate transport Review found the fix incomplete one layer down. Two executor-layer gaps: 1. Blocker — agents/gsd-executor.md auto-mode dispatch gated checkpoint:human-verify on gate="blocking-human" but the checkpoint:decision branch below auto-selected the first option with no gate check. The executor resolves a decision itself (auto-selects and continues) without returning it, so the orchestrator carve-out never runs for it. A planner following the new checkpoints.md rule 6 ("gate a decision whose default would be wrong to assume") would have it silently auto-selected under --auto/--chain — the exact #2107 harm, one checkpoint type over. The decision branch now STOPs and returns for an explicit human decision when gate="blocking-human". 2. Major (transport) — checkpoint_return_format carried no field conveying the gate to the freshly-spawned orchestrator, so recognition of the proactive pre-install checkpoint rested on freeform prose. Added a **Gate:** field to the return format and re-pointed the execute-phase carve-out at it ("If the returned Gate: is blocking-human"). Net byte-negative: execute-phase.md drops 93589 -> 93583, widening ADR-857 headroom from 11 to 17 bytes. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * test(#2107): cover decision carve-out + gate transport, de-vacuum conditional tests - New: 'auto mode does not auto-select a blocking-human decision checkpoint' asserts the executor decision branch STOPs on blocking-human. Verified red on the pre-fix executor (2 fail), green with the fix (27 pass). - New: 'checkpoint_return_format transports the gate ...' asserts the **Gate:** field carries blocking-human across the executor->orchestrator boundary. - New: 'auto-select rule for decision is conditional' — orchestrator-side mirror of the human-verify conditional test, for the execute-phase decision branch. - Fix vacuous test: both conditional tests now assert the anchor matched (length > 0) before iterating, so anchor drift can no longer pass with zero assertions. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * test(#2107): refresh golden + size baselines for executor + execute-phase edits Regenerated via UPDATE_GOLDEN=1 and update-size-baseline.cjs. Only the gsd-executor.md and gsd-core/workflows/execute-phase.md hashes move across the runtime fixtures (35 ins / 35 del, no keys added or removed); checkpoints.md is unchanged this round. Size baselines: gsd-executor.md 43607 -> 43973, execute-phase.md 93589 -> 93583 (still under the ADR-857 ceiling). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> Co-authored-by: Tom Boucher <trekkie@nomorestars.com> |
||
|
Tom Boucher
|
68a5258d45 |
fix(#2017): grant mcp__plugin_context7_context7__* for plugin-marketplace context7 (8 agents) (#2029)
* fix(#2017: grant mcp__plugin_context7_context7__* for plugin-marketplace context7 The 8 context7-using agents granted only mcp__context7__* (standalone server form). Claude Code's plugin-marketplace context7 install names tools mcp__plugin_context7_context7__*, so the grant never matched and every researcher/planner/executor silently lost doc lookup (fell back to WebSearch). - 8 agents: add mcp__plugin_context7_context7__* alongside mcp__context7__*. - scripts/research-profiles.cjs: update the researcher profile tools to match. - tests/context7-plugin-grant-parity.test.cjs: regression guard — no agent grants the standalone form without the plugin form. Closes #2017 * docs(#2017): backfill changeset pr 2029 |
||
|
Tom Boucher
|
9f0d785b61 |
fix(#2020): remove dead SDK file refs that triggered infinite find.exe on Windows (#2027)
* fix(#2020): remove dead SDK file refs that triggered infinite find.exe on Windows gsd-executor.md referenced sdk/src/query/QUERY-HANDLERS.md and reapply-patches.md referenced sdk/dist/cli.js — both retired with the SDK (ADR-0174). AI runtimes that locate doc refs via filesystem search ran find /, which on Git Bash for Windows traverses the whole drive (14h+, orphaned find.exe, 4M+ handles). - agents/gsd-executor.md: drop dead QUERY-HANDLERS.md ref. - workflows/reapply-patches.md: drop dead sdk/dist/cli.js clause. - tests/no-dead-sdk-refs.test.cjs: regression guard — no sdk/src|dist|handlers file refs in agents/workflows/references markdown. Closes #2020 * docs(#2020): backfill changeset pr 2027 |
||
|
Tom Boucher
|
a62079b2da |
fix(#1865): runtime launcher honors CLAUDE_CONFIG_DIR (#2024)
* fix(#1865): runtime launcher honors CLAUDE_CONFIG_DIR The gsd_run preamble resolved the Claude global install only at $HOME/.claude/gsd-core/bin/, but the installer honors CLAUDE_CONFIG_DIR — so a global install redirected via CLAUDE_CONFIG_DIR was invisible to every gsd_run call (every command failed with 'gsd-tools.cjs not found'). The Claude resolver arm now uses ${CLAUDE_CONFIG_DIR:-$HOME/.claude}, matching the installer + the other runtimes' ${VAR:-default} pattern. Default $HOME/.claude behavior is unchanged. - _runtime-launcher.snippet.sh: Claude arm honors CLAUDE_CONFIG_DIR. - sync-runtime-launcher.cjs re-run: 95 workflows/agents re-synced. - review.md / discuss-phase.md: trimmed to stay under their byte budgets. - runtime-launcher-parity.test.cjs: (A) substring updated for the new form + explicit #1865 assertion that the snippet honors CLAUDE_CONFIG_DIR. - goldens + size baselines recaptured. Closes #1865 * docs(#1865): backfill changeset pr 2024 |
||
|
Behruz Nassre Esfahani
|
7bef6a6496 |
fix(#1863): use named flags for state.* calls in executor + workflows (#1873)
* fix(#1863): use named flags for state.* calls in executor + workflows The named-only state-command router (parseNamedArgs) silently drops positional args, so state.cjs threw its required-arg error and metrics/decisions/blockers/session continuity were never recorded. Convert record-metric / add-decision / add-blocker / record-session in agents/gsd-executor.md to the named-flag form (mirroring execute-plan.md), and fix the two remaining positional record-session calls in gsd-core/workflows/milestone-summary.md and forensics.md. Recapture the golden-install-parity fixtures and size baselines for the edited files. Also fix a pre-existing detached-rebuild handle leak in tests/graphify-auto-update.slow.test.cjs: three dispatch tests returned after observing only the synchronous "running" status without awaiting the detached rebuild's terminal state. That leak was latent until the new #1863 regression block's added runtime shifted --test-force-exit timing and surfaced it as a non-zero chunk exit. The three tests now await terminal status via the file's existing waitForBuildStatus helper. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * chore(#1863): add 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> Co-authored-by: Tom Boucher <trekkie@nomorestars.com> |
||
|
Tom Boucher
|
3c13903dcd |
feat(#1866): agent-side self-load of configured agent_skills
Each of the 22 consumer agents now self-loads its configured agent_skills in its mandatory init step, so .planning/config.json agent_skills.<type> reaches the agent on every runtime — including Cursor and /gsd-autonomous, where Skill()-delegated workflow bash init did not reliably execute. - gsd-core/references/agent-skills-bootstrap.md: shared contract (query + Read + dedup guard that skips when <agent_skills> is already in the prompt, so Claude's orchestrator-side injection never doubles) - 22 agents/gsd-*.md: one self-load line naming the agent's own type - gsd-core/workflows/autonomous.md: note that delegated agents self-load - tests/agent-skills-bootstrap.test.cjs: regression + parity (CONSUMER_AGENTS bijection + fast-check property) — Generative-Fix-Divergence guard - docs: ADR-1866, CONFIGURATION dual-injection How It Works, INVENTORY row, Changed changeset Closes #1866 |
||
|
Tom Boucher
|
9540fe43b9 | fix: have executor self-report worktree metadata (#1349) | ||
|
Tom Boucher
|
cf68841220 |
enh(#1243): consume Claude plugin-provided skills in agent_skills (epic #1258 Phase B) (#1261)
* feat(#1243): consume Claude plugin-provided skills via native Skill-tool directive + grant Skill to agent_skills-consumer agents - Relax global skill name validation to accept namespaced form `^[A-Za-z0-9_-]+(:[A-Za-z0-9_-]+)*$` - Namespaced names (containing colon) on claude runtime emit a Skill-tool load directive instead of a @-include line - Namespaced names on non-claude runtimes are skipped with a warning - Bare unresolved names retain existing warn-and-skip behavior (no promotion to directive) - Grant `Skill` tool to all 22 agent_skills consumer agents; 5 generated agents updated via research-profiles.cjs + regen, 17 hand-authored agents edited directly - Add 16 TDD tests in describe('bug #1243') covering happy/mixed/precedence/negative/cross-runtime/regression/grant cases Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs(#1243): document plugin-provided skills in agent_skills Update the Agent Skills Injection reference in CONFIGURATION.md with the three entry forms (project-relative, global:<name>, global:<plugin>:<skill>), the Claude-only runtime behaviour of the namespaced form and the warn-skip on other runtimes, the plugin pre-install prerequisite, and the consumer-agent Skill tool grant. Add docs/how-to/attach-a-plugin-skill-to-a-gsd-agent.md with a step-by-step guide for installing the plugin, locating the namespaced skill name, wiring it into agent_skills, and verifying injection. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(#1243): align agent_skills docs with emitted block format + mixed-block regression test (code-review) - Replace two-section mixed-block example (bogus "Load these plugin-provided skills using the Skill tool:" header) with the actual single-section inline format in CONFIGURATION.md and docs/how-to/attach-a-plugin-skill-to-a-gsd-agent.md - Fix quoted warning text in how-to doc to exactly match the emitted string: [agent-skills] WARNING: Plugin-namespaced skill "global:<name>" requires a Skill-tool-capable runtime (claude) — skipping on runtime "<runtime>" - Replace phantom agent slugs (gsd-checker, gsd-researcher, gsd-advisor, gsd-synthesizer) in CONFIGURATION.md Supported Agent Types with real agents/gsd-*.md examples (gsd-plan-checker, gsd-phase-researcher, gsd-code-reviewer, gsd-ui-auditor, gsd-research-synthesizer) - Add byte-identical mixed-block regression test: one path-resolvable global skill + one plugin-namespaced skill on claude runtime → asserts r.ir.block === single-section interleaved block, no secondary header Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * chore(#1243): regenerate agent-size baseline for the Skill-tool grant The 22 agent_skills-consumer agents each grew +7 bytes from adding `Skill` to their tools list; refresh the committed per-agent size baseline (#1074 guard). * chore(#1243): add Added changeset fragment * fix(#1243): traceable allow-test-rule ref + separator-agnostic byte-identical tests (CI) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|
Tom Boucher
|
7c07fce70f |
fix(#381): make gsd_run launcher reachable in fresh-shell-per-block runtimes (#1084)
* fix(#381): make gsd_run launcher reachable in fresh-shell-per-block runtimes On runtimes that execute each fenced bash block in a separate shell process (e.g. Claude Code — documented behavior: each Bash command is a separate process; inline shell functions and exported vars do not persist between calls), the once-per-file gsd_run() function was undefined in every block after the preamble block, and the call was swallowed by `2>/dev/null || echo "{}"` into silent empty state. Fix (budget-neutral session-level resolution): - Ship gsd-core/bin/gsd_run, a POSIX sh wrapper that symlink-resolves its own location and execs the co-located gsd-tools.cjs. Exposed on PATH via the npm `bin` field (global installs) and shipped to local installs via the recursive gsd-core/ copy. - The per-file launcher preamble now appends `export PATH='<bindir>':"$PATH"` to the file named by $CLAUDE_ENV_FILE (Claude Code's documented env-persistence mechanism) so later fresh-shell blocks resolve gsd_run from PATH. Guarded as a strict no-op when CLAUDE_ENV_FILE is unset; the inline gsd_run() definition remains the fallback for all other runtimes. The single-quoted dir neutralizes shell metacharacters at source time. - Propagated via scripts/sync-runtime-launcher.cjs to all launcher-using files. - XL workflow byte budget 93000 -> 93200 (the ~130B clause pushes plan-phase.md to 93135; legitimate content growth, ratchet-up per #717). Regression tests (I)/(J) in runtime-launcher-parity.test.cjs cover wrapper delegation and end-to-end PATH persistence (sourcing the env file with a space-bearing install path). Known limitation: an install path containing a literal single-quote yields a malformed env-file line and falls back to the status quo (no regression); rare on sanitized home directories. Closes #381 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * docs(#381): add changeset for gsd_run fresh-shell reachability fix Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * test(#381): scope test (J) bare-PATH execution to POSIX (Windows Git Bash exec bit) Windows Git Bash (msys2) does not honor Node's chmod exec bit for PATH-executing extension-less scripts, so the bare `gsd_run` command lookup failed there even though the env-file PATH persistence was correct. The env-file content assertions (the fix's actual cross-platform logic) still run on every platform; only the final source-and-execute sub-step is gated to non-win32. Global installs on Windows are covered by npm's generated bin shim. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
Tom Boucher
|
1fab2e10ba |
fix(#1041): route all source agents through the canonical multi-runtime gsd-tools resolver (#1045)
* fix(#1041): route all source agents through the canonical multi-runtime gsd-tools resolver Source agents/*.md (gsd-planner, gsd-executor, gsd-verifier, gsd-plan-checker, gsd-intel-updater, gsd-debugger, …) called bare "gsd-tools …" in shell blocks. On a shim-only install — where gsd-tools.cjs exists under the runtime home but gsd-tools is NOT on PATH — those calls fail with "command not found" and the agent silently skips init/state/validate/commit ceremony, deferring to the orchestrator or bypassing GSD bookkeeping entirely. were never migrated, so it persisted on Claude Code and every other runtime that consumes the source agents directly. Only gsd-phase-researcher.md carried a resolver — and a stale, claude-only truncated one. Fix (all runtimes): - Inject the canonical multi-runtime gsd_run preamble (byte-equal to _runtime-launcher.snippet.sh — claude/codex/cursor/gemini/copilot/windsurf/ augment/trae/qwen/cline/opencode/kilo/hermes/antigravity homes) at the top of the first gsd_run block of all 12 gsd-tools-calling agents, and rewrite every command-position bare gsd-tools to gsd_run. - Upgrade gsd-phase-researcher.md's stale resolver to the canonical one. - Extend scripts/sync-runtime-launcher.cjs to maintain agents/ in parity (the sync caught and corrected a mis-placed preamble during development). - Extend the bare-gsd-tools (#2851) and launcher-parity (#373) regression guards to agents/ so no runtime can silently regress. Closes #1041 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * chore(#1041): backfill changeset PR number to 1045 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
Tom Boucher
|
a313a7e304 |
fix(#950): emit status: complete in quick-task SUMMARY frontmatter (#951)
* fix(#950): emit status: complete in quick-task SUMMARY frontmatter Add `status: complete` to all four SUMMARY templates (summary.md, summary-minimal.md, summary-standard.md, summary-complex.md), to the executor agent's documented frontmatter field list, and to the quick.md executor constraints block. The audit-open milestone-close scanner (scanQuickTasks) reads this field to decide whether a quick task is done; without it the scanner falls back to `[unknown]` and false-flags finished tasks as open. Writer-side fix; the scanner is correct and unchanged. Blast-radius: no other scanner reads `status:` from phase-plan SUMMARY files. Phase disk_status is derived from file-count heuristics only. Adding the field to the shared template is therefore safe and the value `complete` is semantically accurate for a finished plan. Regression test: tests/bug-950-quick-summary-status-complete.test.cjs - RED: 4 template-contract tests fail before fix, behavioral tests pass - GREEN: all 8 tests pass after fix Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * chore: add changeset for fix/950-quick-summary-status-complete (#951) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * test(#950): assert writer-path contract + scope template checks to YAML frontmatter (adversarial review) - Add `// allow-test-rule: source-text-is-the-product` at file top (before block comment) - Add `extractFrontmatter()` helper that handles both leading-frontmatter files (summary-minimal/standard/complex.md) and fenced-frontmatter files (summary.md, whose frontmatter is embedded inside a ```markdown fence) — assertions now target the actual YAML block, not the whole file - Scope all four [TEMPLATE CONTRACT] tests through extractFrontmatter() so a stray `status: complete` in prose/examples cannot produce a false green; error messages now print the extracted block to aid diagnosis - Add [WRITER-PATH] quick.md test: asserts the <constraints> block instructs the executor to write `status: complete` in SUMMARY frontmatter - Add [WRITER-PATH] gsd-executor.md test: asserts the Frontmatter spec documents `status: complete` as a required field - Sanity-checked: guards fail when `status: complete` is removed from a template or from quick.md, and pass once restored Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
Tom Boucher
|
1bea220d58 |
refactor(#720): lazy-load MVP-only reference bodies on non-MVP runs (#746)
* refactor(#720): lazy-load MVP-only reference bodies (eager @-import → gated Read) Convert eager @-imports of MVP-only reference bodies into lazy "Read" instructions gated on MVP_MODE / WALKING_SKELETON / MVP+TDD, so non-MVP planning/execution runs no longer pull MVP guidance into context. Covers both the workflow files and the planner/executor agent definitions (the dominant context-cost path): - workflows/plan-phase.md: planner-mvp-mode.md + skeleton-template.md (L146/936/937/941) - workflows/execute-phase.md: execute-mvp-tdd.md halt-report ref, now gated on gate-trip (L191) - agents/gsd-planner.md: planner-mvp-mode.md, user-story-template.md, skeleton-template.md - agents/gsd-executor.md: execute-mvp-tdd.md The dedicated always-MVP mvp-phase workflow keeps its eager imports (intentional). Behaviour is unchanged; non-MVP runs simply carry less loaded context. Adds a regression guard mirroring the discuss-phase lazy-load test, and documents the conformance in docs/ARCHITECTURE.md. Refs #720 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * docs(#720): add changeset fragment (pr #746) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
Tom Boucher
|
463cffd894 |
chore(#604): rename get-shit-done/ runtime directory to gsd-core/ (#615)
* chore(#604): rename get-shit-done/ runtime directory to gsd-core/ Renames the installed runtime directory `get-shit-done/` to `gsd-core/` so the on-disk name matches the package (`@opengsd/gsd-core`), repo, and binary (`gsd-tools`). The npm package name and binary are unchanged; npx/npm consumers are unaffected. Mechanical (bulk, ~90% of the diff): - `git mv get-shit-done gsd-core` - Swept path/identifier references across the repo via `perl -pe 's/get-shit-done(?!-\w)/gsd-core/g'`. The negative lookahead preserves the five legitimate slug variants that are NOT the directory: get-shit-done-{OLD,cc,classic,cli,redux} (old package/repo names). - Build/manifest wiring: package.json (bin, files, coverage globs), tsconfig.build.json (outDir), ~86 .gitignore build-output entries, stryker.config.mjs, scan-ignore files, install.js path strings. - Frozen (not rewritten): CHANGELOG.md history; translated docs (README.<locale>.md and docs/{ja-JP,ko-KR,pt-BR,zh-CN}/). New logic (review here): - src/installer-migrations/003-rename-get-shit-done-to-gsd-core.cts: a proper ADR-0008 installer migration. On upgrade it walks the legacy `~/.claude/get-shit-done/` tree, classifies each file via the prior install manifest, and emits remove-managed / backup-and-remove for managed files while PRESERVING unknown user-added files. Symlink-safe (skips a symlinked root and symlinked entries; bounds-checks every path under configDir). The framework rolls back on install failure. Emptied dirs may remain (framework has no recursive dir-removal primitive) — documented. - scripts/lint-legacy-dir-name.cjs: CI regression guard forbidding the bare `get-shit-done` directory token (split token to avoid self-match; case- insensitive; `(?!-\w)` lookahead allows the slug variants; allowlists CHANGELOG, translated docs, and `gsd-allow-legacy-name` marker lines). Wired into the lint-tests CI job. - Restored scripts/lint-package-identity-drift.cjs detection regexes (the mechanical sweep had wrongly rewritten the old-name patterns it exists to detect) and marked them as intentional legacy references. - TDD tests for the migration and the guard; do.md slash-command guard regex tightened so a `/gsd-core/bin` path segment is not mistaken for a command; changeset + docs/installer-migrations.md row added. Breaking: the installed runtime path moves `~/.claude/get-shit-done/` -> `~/.claude/gsd-core/`. Migration 003 removes the stale legacy dir's managed files (preserving user files) on upgrade. Users with custom hooks/configs hardcoding the old path must update them. Closes #604 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(#604): unsweep pending changesets + allowlist injection-example docs CI fixes for the rename PR: - Do not sweep pending .changeset/*.md (ephemeral release-note fragments, like CHANGELOG); reverted those body edits so 5 pre-existing malformed fragments (missing type/pr) no longer enter the PR diff and trip docs-lint. Allowlisted .changeset/ in the legacy-name guard accordingly. - Allowlisted TEST-EXAMPLES.md and docs/explanation/security-model.md in prompt-injection-scan.sh: they contain intentional injection examples / security-model prose; the path-reference rewrites are kept. CodeQL alerts on this PR are pre-existing (alert lines unchanged by this PR; none in the new migration/guard) and are out of scope for the rename. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(#604): resolve CodeQL alerts surfaced on this PR The rename diff touched files carrying pre-existing CodeQL findings; per the no-pre-existing-dismissal rule, fixing every surfaced alert rather than waving them off. All behavior-preserving: - scripts/ci-test-scope.cjs: build the config-path match from string .includes() instead of a RegExp over an arg-derived value (js/regex-injection). - src/profile-output.cts: escape backslashes before pipe-escaping desc/safeName so the table-cell escape is complete (js/incomplete-sanitization). - tests/{bug-2643,bug-2808,docs-parity-live-registry}: two-pass HTML-comment strip so a bare/unclosed `<!--` cannot survive (js/incomplete-multi-character-sanitization). - tests/inline-plan-threshold: drop the no-op `\s`->`\s` identity replace, keep the meaningful POSIX-class conversion (js/identity-replacement). Verified: build:lib green; the touched test files + ci-test-scope + profile-output suites pass; lint:legacy-name clean. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(#604): correctly resolve remaining CodeQL alerts (regex-injection + sanitization) The prior commit's fixes for two alerts were ineffective: - ci-test-scope.cjs js/regex-injection: the alert is the CLI-arg-derived `file` reaching static regex `.test(file)` calls (not the config rule). Removed ALL regex over file/t — startsWith/includes/=== string checks + an isWindowsHint helper — so there is no regex sink for the tainted value. - js/incomplete-multi-character-sanitization (3 test files): a single `.replace(/<!--...-->/g,'')` can let `<!--` re-form. Replaced with a fixpoint loop (replace until stable) plus a final bare-opener strip. Verified: no regex over file/t remains; ci-test-scope + the 3 test suites pass; lint:legacy-name clean. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(#604): make ci-test-scope + comment-strippers regex-free to clear CodeQL CodeQL flags the regex PATTERNS syntactically (regex-injection on the --files arg split; incomplete-multi-character-sanitization on the <!--...--> replace), so loop fixes do not satisfy it. Made these paths regex-free: - ci-test-scope.cjs splitFiles: char-by-char separator tokenizer (no /[,\\s]+/). - 3 test files: indexOf/slice HTML-comment stripper (no .replace(/<!--/)). Behavior preserved; ci-test-scope + the 3 suites pass; guard clean. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(#604): unblock security base64 scan on the large rename diff The security job hit its 10m timeout: base64-scan.sh choked on the binary test fixture tests/feat-3594-parser-property-style.test.cjs (embedded NUL/ non-UTF8 bytes -> thousands of bogus blobs + "ignored null byte" warnings), and the ~800-file rename diff is slow to scan regardless. - scripts/base64-scan.sh: skip binary-by-content files (grep -Iq .) — they can't carry base64-obfuscated *text* and feeding NUL bytes through the per-line scanner is pathologically slow. collect_files already filtered binary *extensions*; this catches binary *content* in text extensions. - .github/workflows/security-scan.yml: raise the security job timeout 10m->30m to accommodate very large diffs (the scan itself is unchanged). Verified locally: scan skips the fixture, 0 "ignored null byte" warnings, 0 findings, exit 0. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(#604): sweep get-shit-done refs introduced by merging next The branch was updated with next (#614/#384/#618 etc.), which reference the get-shit-done/ dir (still named that on next). Swept the stale references in the merged files to gsd-core so the rename stays consistent and lint:legacy-name passes: - commands/gsd/discuss-phase.md (runtime-launcher shim paths) - src/core.cts (getAgentsDir layout comments) - tests/bug-384-agents-runtime-aware.test.cjs (require path to runtime lib) Verified: guard 0 violations; build green. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(#604): exclude gsd-core/ path segments from bug-3683 command cross-ref invariant The #614 runtime-launcher shim added to discuss-phase.md references `${_GSD_RUNTIME_ROOT}/gsd-core/bin/...`. bug-3683's REF_PATTERN excluded path-y refs only via lookbehind, but `}` precedes `/gsd-core/` in the shim, so it mis-read the directory path as a dangling `/gsd-core` command ref (same class as the #604 bug-2954 fix). Added a trailing `(?![\w-]*\/)` so `/gsd-<x>/...` path segments are not treated as slash-command references. Verified locally on BOTH platforms before pushing: - mac (node 26) full suite: 0 failures - gsd-test-runner (linux, node22 image) full suite: 0 failures - bug-3683 + bug-2954 pass. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(#604): lazily resolve findProjectRoot in gsd-tools (harden flaky CI) CI intermittently failed state.test's gsd-tools subprocess with "findProjectRoot is not a function" (flip-flopping across legs; not reproducible on mac full suite, gsd-test linux full suite, test:unit, or state.test x8). findProjectRoot is a re-export from core.cjs (sourced from project-root.cjs); binding it via destructure at module-load can be undefined under a load-ordering edge. Resolve it lazily at call time via a small wrapper so the lookup happens after core.cjs is fully initialized. Verified green on BOTH platforms before pushing: - mac (node 26) full suite: 0 failures - gsd-test-runner (linux, node22) full suite: 0 failures - state.test.cjs: 106/106; gsd-tools loads cleanly. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * fix(#604): allowlist verification-patterns.md placeholder examples in secret scan The rename git-mv'd references/verification-patterns.md into gsd-core/, pulling it into the secret-scan diff. It documents stub/placeholder RED-FLAG env-var examples (illustrative Stripe test-key / database-URL / API-key placeholders) — not real credentials. Added it to .secretscanignore with the strict annotation, mirroring the existing gsd-core/workflows/plan-phase.md exception. Verified locally: secret-scan-lint --strict OK; secret-scan --diff origin/next exits 0 with 0 findings. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
Tom Boucher
|
a594f5175c |
fix(#214): apply OpenCode write-truncation contract to all large-file writer agents (#599)
* fix(#214): apply OpenCode write-truncation contract to all large-file writer agents Issue #214 / PR #598 fixed gsd-phase-researcher's OpenCode write-tool truncation by adding a single-Write-default + sentinel-based Write->Read->Edit incremental fallback contract to its Step 6. The root cause is upstream opencode#18108: OUTPUT_TOKEN_MAX=32000 is shared with the thinking budget, so a single oversized `write` tool call's JSON is truncated mid-payload (`JSON Parse error: Expected '}'`) and OpenCode doom-loops. The same failure affects every GSD subagent that writes a large file in one Write call. Mirror the phase-researcher write contract (adapted per output filename) into the other large-file writers: - gsd-research-synthesizer (SUMMARY.md) — extends the existing bug-222 hard-rules block with the truncation fallback as rule 6, preserving every original rule - gsd-planner (PLAN.md) - gsd-executor (SUMMARY.md) - gsd-domain-researcher (AI-SPEC.md Section 1b) - gsd-project-researcher (.planning/research/*.md) - gsd-ui-researcher (UI-SPEC.md) Each keeps the single-Write default (no behavior change for Claude Code and other non-truncating runtimes) and falls back to incremental, sentinel-based section-by-section writes only on a truncation/invalid-tool failure; never silently falls back to returning content. Locked with a parametrized prompt-contract regression test mirroring the bug-214 / bug-222 pattern across all six agents. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * chore(#214): set changeset pr to 599 Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
Colin Johnson
|
7a3822fce1 |
fix: replace removed gsd-sdk prompt references (#355)
* fix: replace removed gsd-sdk prompt references * chore: add changeset |
||
|
Tom Boucher
|
7e6ba56985 |
fix(3678): executor must respect commit_docs:false; teach SDK skip envelope (#3679)
* fix(3678): executor must respect commit_docs:false; teach SDK skip envelope Closes #3678 When `commit_docs: false` in `.planning/config.json`, the SDK's `cmdCommit` correctly short-circuits and returns `{committed: false, hash: null, reason: 'skipped_commit_docs_false'}` without staging or committing anything. The agent prompt at `agents/gsd-executor.md:710-720` (final_commit block) tells the executor to call `gsd-sdk query commit "docs(...)" --files .planning/...` but says NOTHING about how to interpret a skipped return. With no explicit instruction, the LLM improvises raw `git add` / `git add -f` / `git commit` to "fulfill" the per-plan commit step it was told to make, which leaks gitignored `.planning/` artifacts into the user's git history (exactly what the reporter observed). Three coordinated fixes: 1. **agents/gsd-executor.md final_commit block** — adds explicit handling text for all three SDK return envelopes (`committed:true`, `skipped:true commit_docs`, `skipped:true gitignored`, `committed:false other reasons`). States plainly: "Do not fall back to raw `git add` / `git commit` / `git add -f` when the SDK returns `skipped: true`." 2. **get-shit-done/bin/lib/commands.cjs cmdCommit** — adds `skipped: true` to both skip-path envelopes so agents see "skipped" as a first-class success signal rather than inferring "no commit happened, I must improvise" from absent `hash` / `committed:false`. Backward-compatible: existing callers reading `committed` / `hash` / `reason` are unaffected. 3. **tests/bug-3678-executor-commit-docs-respect.test.cjs** — 7-test regression covering: - A1/A2: agent prompt mentions the skip envelope AND explicitly forbids raw-git fallback (`source-text-is-the-product` exception) - B1: SDK envelope carries `committed:false`, `skipped:true`, canonical `reason: 'skipped_commit_docs_false'` (frozen enum) - B2: git index empty after commit_docs:false skip (no `.planning/` staged) - B3: HEAD unchanged after commit_docs:false skip - C1/C2: structural ban on `git add -f` / `git add --force` in any agent or workflow body (prohibition-sentence exception preserves audit prose) Verification: - node --test tests/bug-3678-*: 7/7 pass - Targeted regression (10 commit/executor-adjacent files): 135/135 pass - Full docker suite (gsd-test-summary): 11751/11740 pass / 0 fail (the 11 added are this test plus a few collateral pickups) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore(changeset): add fragment for #3678 fix (Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>) * chore(changeset): set PR number 3679 (Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>) * fix(3678): preserve skip-aware carve-out in executor completion checklist The new `final_commit` prose at lines 717-741 teaches the executor to treat `skipped:true` as success and forbids raw-git fallback, but the downstream completion checklist still contained an unconditional "Final metadata commit made" checkbox. An LLM executor reading an unchecked mandatory box may attempt to satisfy it via raw `git add`, re-introducing the exact regression this PR is meant to prevent. Update the checklist line to carve out the intentional-skip case and add a regression test asserting the carve-out remains present. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Tom Boucher
|
6e9f8101da | fix(3605): retire stale slash syntax and satisfy planner size gate | ||
|
Tom Boucher
|
18ffaa86cc |
fix(3605): scrub retired slash commands from agents/*.md
Six surviving references to /gsd-research-phase (deleted in #3042) and /gsd-insert-phase (consolidated into /gsd:phase insert in v1.40.0) remained in five agent contracts because every prior scrub pass (#3029, #3044, #3131) limited its SEARCH_DIRS to workflows/, references/, templates/, contexts/, commands/, and hooks/ — agents/ was outside scope. agents/gsd-executor.md:195 is user-facing: the executor surfaces it during a package-install failure recovery checkpoint, so a real user hits "Unknown command" while trying to recover from a stalled phase. Replacements: - /gsd-research-phase -> /gsd:plan-phase --research-phase <N> (agents/gsd-executor.md:195, agents/gsd-phase-researcher.md:17, agents/gsd-planner.md:186, agents/gsd-planner.md:991, agents/gsd-research-synthesizer.md:115) - /gsd-insert-phase -> /gsd:phase insert (agents/gsd-roadmapper.md:205) Adds tests/bug-3605-stale-research-insert-phase-agent-refs.test.cjs as the regression guard. It scans agents/*.md for any retired command name (/gsd-research-phase, /gsd-insert-phase, /gsd-add-phase, /gsd-remove-phase, /gsd-analyze-dependencies) with proper word-boundary matching so a future consolidation that misses agents/ fails CI. The guard mirrors tests/bug-2950-stale-command-refs.test.cjs which covers the same anti-pattern for workflows/. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Tom Boucher
|
85d7a8b4b1 |
fix(3542): prohibit git stash in executor agents — shared stash storage violates worktree isolation
Closes #3542 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Tom Boucher
|
a60e05c714 |
fix(claude): restore namespaced /gsd:<command> references (#3452)
* fix(claude): restore namespaced /gsd:<command> references * test(claude): align slash-command expectations to /gsd: form * test(claude): align generated command references to /gsd: * test(claude): finish /gsd: namespace expectation updates |
||
|
Tom Boucher
|
b37c487325 |
feat(security): package legitimacy gate against slopsquatting (#3215)
* feat(security): package legitimacy gate against slopsquatting (#2827) GSD's research → plan → execute pipeline had no install-time legitimacy gate: a hallucinated package name that passes `npm view` could flow all the way to `gsd-executor` running `npm install <malicious-pkg>` with no human checkpoint. This PR closes that gap. Changes: - gsd-phase-researcher: runs slopcheck on every recommended package; emits `## Package Legitimacy Audit` table; strips [SLOP] packages; ecosystem-specific verification (pip/npm/cargo); WebSearch-sourced packages tagged [ASSUMED]; ctx7 fallback uses `command -v` guard instead of `npx --yes` - gsd-planner: injects `checkpoint:human-verify` before [ASSUMED]/[SUS] installs; adds T-{phase}-SC STRIDE row to <threat_model> template; ctx7 fallback also uses `command -v` guard - gsd-executor: RULE 3 excludes package installs from auto-fix; failed installs surface as checkpoints, never silent substitutions - tests/package-legitimacy-gate.test.cjs: 24 structural assertions covering the full gate (node:test + node:assert, no raw .includes()) - docs: USER-GUIDE, COMMANDS, ARCHITECTURE updated with gate description - .changeset: Security fragment for v1.51 release notes Closes #2827 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * docs: expand Package Legitimacy Gate documentation Add full user-facing depth to the gate docs across USER-GUIDE, COMMANDS, and ARCHITECTURE: - USER-GUIDE: rewrite gate section with concrete RESEARCH.md/PLAN.md examples, slopcheck verdict table, [ASSUMED] WebSearch tagging explanation, slopcheck-unavailable troubleshooting, and graceful degradation behavior - COMMANDS.md: expand /gsd-plan-phase gate note with verdict bullets; add install-failure checkpoint behavior to /gsd-execute-phase - ARCHITECTURE.md: expand gate section with threat model rationale, layer table, claim provenance integration, ecosystem coverage, and graceful degradation semantics Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(security): harden package legitimacy checkpoint semantics * fix(planner): satisfy size gates and tighten package gate wording --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|
Tom Boucher
|
2d32ad82be |
fix(plan-phase): remove agent: directive that caused OpenCode subagent dispatch (#3156) (#3206)
* feat(roadmap): parse **Mode:** field on phase sections Adds a 'mode' field to roadmap.get-phase and roadmap.analyze outputs. Recognizes '**Mode:** mvp' lines in phase sections; lowercased + trimmed. Forward-compat: unrecognized values preserved verbatim, no enum check. Foundation for --mvp flag in plan-phase (PRD: vertical-mvp-slice). * feat(plan-phase): parse --mvp flag and resolve MVP_MODE Resolution order: CLI flag → ROADMAP **Mode:** field → workflow.mvp_mode config → false. Walking Skeleton gate fires for new-project Phase 1. Wires MVP_MODE + WALKING_SKELETON into gsd-planner subagent prompt. Per PRD vertical-mvp-slice Phase 1 (Q1, Q2, Q4). * docs(planner): add vertical-slice planning reference New reference loaded by gsd-planner when MVP_MODE=true. Defines slice ordering, Walking Skeleton rules, and anti-patterns. Referenced from plan-phase workflow MVP_MODE wiring. * docs(planner): add SKELETON.md template Template emitted by gsd-planner under WALKING_SKELETON=true. Captures architectural decisions and out-of-scope list for new-project Phase 1. * chore(inventory): register new planner references Added planner-mvp-mode.md and skeleton-template.md to INVENTORY.md and INVENTORY-MANIFEST.json. References now: 53. * feat(gsd-planner): add MVP Mode Detection section Mode-switched branch in the existing planner agent (per Q4: single agent). Vertical-slice decomposition rules, Walking Skeleton handling, and TDD-mode compatibility. Heavy guidance lives in references/planner-mvp-mode.md. * test(plan-phase): add --mvp resolution-chain integration cases Validates roadmap.get-phase --pick mode and confirms workflow.mvp_mode default is unset in fresh projects. * docs(changelog): announce --mvp vertical-slice planning (#2826) * feat(mvp-phase): add /gsd mvp-phase slash command Standalone command for vertical MVP planning. Frontmatter only; heavyweight workflow at get-shit-done/workflows/mvp-phase.md follows in next commit. Mirrors discuss-phase/edit-phase command shape. * docs(planner): add user-story-template reference Defines the canonical 'As a / I want to / So that' format and the ROADMAP.md / PLAN.md emit rules. Used by mvp-phase workflow and gsd-planner agent under MVP_MODE. * docs(planner): add SPIDR splitting reference Defines size signals, the five SPIDR axes (Spike/Paths/Interfaces/Data/Rules), the interactive workflow, and anti-patterns. Per PRD Q3 decision: full interactive flow, not lightweight check. Used by mvp-phase workflow. * fix(mvp-phase): trim description to fit 100-char budget * feat(mvp-phase): add mvp-phase workflow Standalone workflow: phase validation -> user story prompts (As a / I want to / So that) -> SPIDR splitting check -> ROADMAP write (Mode + Goal) -> delegation to plan-phase. Per PRD Phase 2 (Q3 full SPIDR; Phase-2-A/B/C/D decisions). Plan-phase auto-detects MVP via Phase 1's resolution chain, so no flags are needed when delegating. * feat(gsd-planner): emit user-story header in PLAN.md under MVP mode Extends the MVP Mode Detection section (added in Phase 1) so the planner sources the user story from ROADMAP **Goal:** and emits the bolded **As a** / **I want to** / **so that** form as the first content under the phase header in PLAN.md. References user-story-template.md. * test(mvp-phase): integration smoke test for ROADMAP mutation Validates roadmap.get-phase output after a workflow-spec'd ROADMAP write: mode=mvp and goal=full user story. Catches schema drift between workflow emit and parser expectation. Includes a long-story case (>120 chars) to confirm SPIDR-rejected stories still parse correctly. * chore(inventory): register mvp-phase command + 2 new references Adds /gsd mvp-phase to commands list, mvp-phase workflow to workflows list, and user-story-template.md + spidr-splitting.md to references. References count: 53 -> 55. * docs(changelog): announce /gsd mvp-phase command (#2826) * fix(mvp-phase): add TEXT_MODE plain-text fallback for non-Claude runtimes (#2012) * docs(executor): add MVP+TDD gate reference Defines the runtime gate semantics for execute-phase when both MVP_MODE and TDD_MODE are true: pre-task verification of failing-test commit, end-of-phase review escalation from advisory to blocking, behavior-adding task definition. Loaded conditionally by execute-phase workflow and gsd-executor agent. * feat(execute-phase): MVP+TDD runtime gate + blocking review Resolves MVP_MODE in Step 1 (CLI flag -> roadmap mode -> config -> false). Adds per-task gate that halts before behavior-adding tasks run if no failing-test commit exists for the plan. Escalates end-of-phase TDD review from advisory to blocking when both MVP_MODE and TDD_MODE active. Also updates INVENTORY-MANIFEST.json to register execute-mvp-tdd.md (added by Task 1) so manifest-sync tests pass. Per PRD vertical-mvp-slice Phase 3a (decisions Phase-3-A, Phase-3-Split). * feat(gsd-executor): add MVP+TDD Gate section Mirrors the planner's MVP Mode Detection pattern from Phase 1. Instructs halt-and-report when the runtime gate trips, references execute-mvp-tdd.md for full semantics. No agent changes outside the new section. * test(execute-phase): add MVP+TDD resolution-chain integration cases Validates roadmap.get-phase --pick mode and confirms workflow.mvp_mode default is unset in fresh projects. Mirrors the Phase 1 plan-phase resolution-chain integration test. * chore(inventory): register execute-mvp-tdd reference Bumps References count 55 -> 56. Registers execute-mvp-tdd.md. Adds "init" to PROSE_ALLOWLIST in registry integration test so bare `gsd-sdk query init` prose examples in plan docs don't trigger the unregistered-handler guard (real commands are all init.<subcommand>). * docs(changelog): announce MVP+TDD runtime gate in execute-phase (#2826) * docs(verifier): add verify-mvp-mode reference Defines UAT framing under MVP mode: user-flow walk-through first, technical checks deferred, coverage check as goal-backward narrowing to the user story's outcome clause. Loaded conditionally by verify-work workflow and gsd-verifier agent. * feat(verify-work): MVP-mode UAT framing — user flow first Resolves MVP_MODE from phase mode field. Under MVP mode, generates UAT in three ordered sections: user-flow walk-through (derived from user story), technical checks (deferred), coverage check (goal-backward). Falls back to standard UAT generation when mode is null/absent. User-story-format guard refuses to verify a mode:mvp phase with a non-user-story goal. Also updates docs/INVENTORY.md (56 references) and docs/INVENTORY-MANIFEST.json to register verify-mvp-mode.md added in Task 1. Per PRD vertical-mvp-slice Phase 3b (decisions Phase-3-B, Phase-3-Verify-Structure). * feat(gsd-verifier): add MVP Mode Verification section Narrows goal-backward verification to the user-story [outcome] clause when phase mode is mvp. References verify-mvp-mode.md. Preserves existing goal-backward methodology for non-MVP phases. User-story-format guard refuses to verify a mode:mvp phase with a non-user-story goal. * docs(changelog): announce MVP-mode UAT framing in verify-work (#2826) * feat(new-project): add Vertical MVP vs Horizontal Layers mode prompt Asks user at project init how to structure the project. Vertical MVP emits **Mode:** mvp on every initial roadmap phase (per-phase mode preserved per PRD Q1). Horizontal Layers falls back to standard template — no behavioral change for existing flows. Per PRD vertical-mvp-slice Phase 4 (decision Phase-4-Persistence). * feat(progress): add MVP-mode user-flow display When phase has **Mode:** mvp, progress renders user-flow status from PLAN.md task names alongside standard task progress. Tasks that aren't user-flow-shaped (technical-sounding) are filtered out of the user-flow sub-block. Falls back to standard display when mode is null/absent. Per PRD vertical-mvp-slice Phase 4 (decision Phase-4-Progress). * feat(stats): add MVP phase count summary Reads roadmap.analyze (which surfaces mode per phase from Phase 1) and emits 'Phases: N total | M MVP | K standard' summary line. Suppressed when MVP_COUNT == 0 to avoid clutter on non-MVP projects. Per PRD vertical-mvp-slice Phase 4. * feat(graphify): add MVP-mode visual differentiation MVP-mode phases render with #22c55e fill color AND ' (MVP)' label suffix — two-channel signaling for color-blind and grayscale renders. Standard phases unchanged. Per PRD vertical-mvp-slice Phase 4 (PRD Q5: distinct visual treatment). * docs(changelog): announce Phase 4 discovery & progress (#2826) * chore(release): bump dev to 1.50.0-canary.0 for first 1.50.0 canary Sets the base version that .github/workflows/canary.yml derives the canary tag from (strips suffix → base 1.50.0 → next available v1.50.0-canary.N). This kicks off the 1.50.0 release train, opened by the MVP/TDD/UAT vertical slice landed across PRs #2867, #2874, #2878, #2880, #2883. * docs: add CANARY stream README + v1.50.0-canary.1 release notes - docs/CANARY.md — explains the dev→@canary stream policy, install/rollback paths, and when (not) to install canary builds - docs/RELEASE-v1.50.0-canary.1.md — release notes for the first 1.50.0 canary cut: vertical MVP/TDD/UAT slice (#2867 + #2874 + #2878 + #2880 + #2883), opening the 1.50.0 train under PRD #2826 - docs/README.md — index entry + quick link for the canary stream * fix(ci/canary): publish gate checks dev branch, not main Four publish-step `if:` conditions in .github/workflows/canary.yml were checking `github.ref == 'refs/heads/main'`. Those steps (Tag and push, Publish to npm, Publish SDK to npm, Verify publish) therefore always skipped on every workflow_dispatch invocation since canary runs from dev, never main. The workflow's own header comment is unambiguous: `dev → @canary`. The gate was a copy-paste from release.yml (which correctly targets main for the @next/@latest streams) that was never corrected for the canary stream. This is why the 1.50.0-canary.1 publish hadn't materialized despite three green workflow runs. With the gate corrected, the next dispatch will actually publish. * ci(release-sdk): make release-sdk.yml dispatchable from the dev branch The workflow lives on main only, so the GitHub Actions "Use workflow from" dropdown doesn't list dev — meaning dev → @dev publishes can't be triggered from the dev branch directly. Add the file to dev so an operator can dispatch it with branch=dev and tag=dev. Per project release-stream policy: dev branch publishes canary (@dev). This is the stream that needs the file most, since main never publishes @dev itself (main does @next / @latest). File is byte-identical to main's release-sdk.yml — straight propagation, no behavioral change. Tracking issues #2925, #2929. * docs(mvp): canary-prep concept cleanup — CONTEXT.md, mvp-concepts index, --prd interaction (#3176) * chore(mvp): concept cleanup + cross-ref index for v1.50.0-canary.2 prep - CONTEXT.md gains 7 MVP domain terms (MVP Mode, User Story, Walking Skeleton, Vertical Slice, Behavior-Adding Task, MVP+TDD Gate, SPIDR Splitting) so the project glossary matches the shipped surface. - New get-shit-done/references/mvp-concepts.md indexes the six MVP reference files and concept-to-file map so agents and contributors can find the right canonical doc without grepping. - plan-phase.md Walking Skeleton block now documents that --mvp and --prd compose orthogonally on Phase 1; no precedence needed. - INVENTORY/INVENTORY-MANIFEST refreshed for the new reference (58 -> 59). No behavior change. Canary-prep cleanup ahead of v1.50.0-canary.2. Surfaced for follow-up (not in this PR): - MVP_MODE resolution shell block duplicated across plan-phase, execute-phase, verify-work workflows (needs a shared workflow-include mechanism; structural change). - Behavior-Adding Task predicate is prose-only; no shared utility. - User Story regex hardcoded in verify-work; would benefit from a central definition consumed by the verifier and the mvp-phase command. * chore(changeset): set PR number for mvp concept cleanup * feat(mvp): centralize resolution surfaces + fix SDK roadmap mode parity (#3178) Three new SDK query verbs replace the architectural duplication surfaced by the v1.50.0-canary.2 review against dev tip 12c4e565: phase.mvp-mode <N> [--cli-flag] Single canonical precedence resolver (CLI flag -> ROADMAP **Mode:** mvp -> workflow.mvp_mode config -> false). Replaces 4-8 lines of bash that were duplicated across plan-phase.md, execute-phase.md, verify-work.md, and progress.md. Returns {active, source, roadmap_mode, config_mvp_mode, cli_flag_present}. task.is-behavior-adding <plan-file> | --task-content <xml> Behavior-Adding Task predicate (tdd="true" + <behavior> block + non-test source files in <files>). Replaces prose-only specification in references/execute-mvp-tdd.md; gsd-executor agent now invokes the verb instead of re-inlining the three checks. Returns {is_behavior_adding, checks, reason}. user-story.validate <text> | --story <text> Owns the canonical User Story regex /^As a .+, I want to .+, so that .+\.$/ previously hardcoded in verify-work.md prose. Consumed by gsd-verifier (phase-goal guard) and /gsd-mvp-phase (interactive-prompt validation). Returns {valid, slots: {role, capability, outcome}, errors[]}. Bug fix bundled: sdk/src/query/roadmap.ts searchPhaseInContent now extracts the mode field from **Mode:**, restoring parity with roadmap.cjs:120-123. Without this, roadmap.get-phase --pick mode returned null on the native dispatch path even when the phase had **Mode:** mvp set, causing MVP_MODE to silently fall through to the config/false branch in every consuming workflow. The original PRs Phase 1 (#2885) shipped the CJS parser but the SDK port omitted the field; this fix brings them back to parity. Workflows + agents updated to call the verbs: - plan-phase.md, execute-phase.md, verify-work.md, progress.md call phase.mvp-mode (one line replaces the duplicated bash chains). - execute-phase.md MVP+TDD gate calls task.is-behavior-adding. - verify-work.md goal guard calls user-story.validate. - mvp-phase.md interactive prompt validates via user-story.validate. - gsd-executor agent references task.is-behavior-adding instead of prose. - gsd-verifier agent references user-story.validate instead of inlined regex. Tests: 24 new vitest tests in sdk/src/query/mvp.test.ts cover all three verbs + the regression. Two existing contract tests (progress, verify) updated to assert on the new verb shape. All 60 existing MVP contract tests pass; golden integration suite (38 + 42 tests) passes. Closes #3177 * fix(canary.2): unblock release gates for v1.50.0-canary.2 Run 25451329660 (Release SDK Bundle on dev, 2026-05-06T17:41) failed at the test-suite step with 3 deterministic content/structure gate failures, all attributable to the MVP umbrella integration in #3178 and the docs sweep in #3180. Failure 1: /gsd-mvp-phase undocumented in workflows/help.md - tests/bug-2954-help-md-slash-command-stubs.test.cjs requires every shipped commands/gsd/<X>.md to have a /gsd-<X> mention in help.md - PR #3180 updated docs/COMMANDS.md but missed help.md (which the AI agents load in-product) - Fix: add a /gsd-mvp-phase entry to help.md right before /gsd-plan-phase Failures 2 + 3: execute-phase.md (1727) and plan-phase.md (1714) over XL budget (1700) - PR #3178 added MVP-mode verb calls (phase.mvp-mode, task.is-behavior-adding, user-story.validate) to both workflow files, pushing them past 1700 lines - Fix: bump XL_BUDGET 1700 -> 1800 with inline comment pointing at the structural follow-up (extract MVP bodies to <workflow>/modes/mvp.md per the discuss-phase/modes/ precedent) - The structural extract is the right long-term fix but is bigger than canary unblock scope; will land in a follow-up after canary cycles Local verification: $ node --test tests/bug-2954-help-md-slash-command-stubs.test.cjs tests/workflow-size-budget.test.cjs tests 111 pass 111 fail 0 After this lands, re-trigger Release SDK Bundle on dev for v1.50.0-canary.2. * chore(changeset): set PR number for canary.2 unblock * fix(codex): generate-claude-md writes to AGENTS.md on Codex runtime When config.runtime === 'codex' or GSD_RUNTIME=codex, override the output target to AGENTS.md regardless of claude_md_path, so Codex projects no longer have GSD sections written to CLAUDE.md by mistake. Fixes both the CJS (gsd-tools) and SDK (profile-output.ts) paths. Explicit --output flags are still honoured in both paths. Closes #3163 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(plan-phase): remove agent: directive that caused OpenCode subagent dispatch On OpenCode, any command with `agent: <name>` in its frontmatter is auto-dispatched to a subagent context where the Agent tool is unavailable. plan-phase.md and mvp-phase.md both carried `agent: gsd-planner`, causing them to run inside gsd-planner's subagent context with no ability to spawn researcher/planner/checker subagents — the orchestrator fell back to inline execution for all three phases. Fix: remove `agent: gsd-planner` from both command files so they run in the main agent context. Also replace the stale `Task` tool in allowed-tools with `Agent` (the correct dispatcher tool name post-#3168 rename). Adds a structural regression test that parses YAML frontmatter of every commands/gsd/*.md file and asserts no command carries an `agent:` directive. Closes #3156 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(mvp): address CodeRabbit workflow and contract findings * fix(execute-phase): use registered state.update query command --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|
Tom Boucher
|
ba0409e04e |
fix(#3097, #3099): add cwd-drift sentinel + absolute-path guard to executor worktree protocol (#3144)
* fix(#3097, #3099): add cwd-drift + absolute-path guards to executor worktree protocol #3097 — cwd-drift sentinel (gsd-executor.md task_commit_protocol step 0a): A Bash cd out of the worktree makes [ -f .git ] false, silently skipping all HEAD/branch safety guards. Commits land on main's branch. Fix: on first commit, capture spawn-time toplevel into sentinel file at .git/worktrees/<name>/gsd-spawn-toplevel. Before every subsequent commit, verify ACTUAL_TL matches EXPECTED_TL. Exits 1 with recovery instructions if drift detected. #3099 — absolute-path guard (gsd-executor.md task_commit_protocol step 0b): Absolute paths constructed from the orchestrator's pwd (main repo root) resolve to the main repo inside worktrees. Edit/Write lands in wrong dir; git commit sees a clean worktree tree; work silently lost or leaks to main. Fix: before any absolute-path Edit/Write, verify path starts with WT_ROOT=/Users/thbouc/projects/get-shit-done. Prefer relative paths. Both guards are documented in references/worktree-path-safety.md, which is now loaded into every executor spawn prompt via <execution_context>. The <worktree_branch_check> footnote references all three steps (0/0a/0b). execute-phase.md: extracted worktree bash commands to reference file (safe embed — @ files are inlined before the executor processes the prompt). The blank line in <required_reading> was removed to stay at the XL=1700 line budget after adding the @ reference. Suite: 6986/6986. Closes #3097. Closes #3099. * fix(lint+executor+docs): allow-test-rule, fix [ -f .git ] guard, fail-closed abs-path check, fix INVENTORY count |
||
|
Tom Boucher
|
120113c42b | fix(sdk-guidance): point quick install hint and agent fallbacks to query-capable CLI | ||
|
Tom Boucher
|
8de8acee46 |
fix(workflows): assert HEAD on per-agent branch before worktree commits (#2924) (#2941)
* fix(workflows): assert HEAD on per-agent branch before worktree commits Worktree-mode setup could leave HEAD attached to a protected branch (master), causing agent commits to land there. The previous response was a destructive self-recovery via 'git update-ref refs/heads/master <sha>', which silently rewinds the protected branch and destroys concurrent commits in multi-active scenarios (parallel agents, user committing while agent runs). - Reorder <worktree_branch_check> in execute-phase.md and quick.md to assert HEAD via 'git symbolic-ref' BEFORE any 'git reset --hard'. HALT with a blocker if HEAD is on main/master/develop/trunk/release/* or detached. - Add a per-commit HEAD assertion (step 0) to gsd-executor.md <task_commit_protocol>; HEAD attachment can drift after 'git checkout <sha>'. - Forbid 'git update-ref refs/heads/<protected>' in <destructive_git_prohibition>; surface the blocker rather than self-heal. - Remove '--no-verify' as the worktree-mode default in execute-phase.md, execute-plan.md, quick.md, and references/git-integration.md. Hooks now run on every executor commit; opt out only via workflow.worktree_skip_hooks. - Add regression test that parses the worktree_branch_check blocks structurally and asserts the symbolic-ref check precedes the reset --hard, no workflow performs update-ref on a protected ref, and --no-verify is no longer the default in any parallel-execution prompt. * fix(#2924): address CodeRabbit review findings on worktree HEAD PR - Add positive worktree-agent-* allow-list to <task_commit_protocol> step 0 in gsd-executor.md and to <worktree_branch_check> in execute-phase.md and quick.md. The deny-list (main|master|develop|trunk|release/*) silently allowed feature/* and other arbitrary branches outside the agent namespace. - Register workflow.worktree_skip_hooks in both config schemas (sdk/src/query/config-schema.ts and get-shit-done/bin/lib/config-schema.cjs) and document it in docs/CONFIGURATION.md so config-set accepts it. - Fix stash lifecycle in execute-phase.md post-wave hook validation: stash under a named ref and pop after the hook run; warn on pop failure. - Pre-dispatch PLAN.md commit in quick.md: gate on git diff --cached --quiet for idempotency and exit 1 with a clear error on commit failure (both the --no-verify and the normal branches) — no more swallowing real errors. - Test fixes (tests/bug-2924-worktree-head-attachment.test.cjs): - Parse the protected-branch alternation structurally and require main, master, develop, trunk, release/.* (release/* was previously skipped by the \\b...\\b regex). - Use fs.readdirSync(dir, { recursive: true }) so workflows in nested subdirectories are also asserted against the update-ref ban. - Add allow-list assertions for execute-phase.md, quick.md, and gsd-executor.md to lock in the new positive namespace check. * test(#2924): assert sub-section end marker exists before slicing * test(#2924): use section boundary instead of fixed window for parallel-agents slice |
||
|
Tom Boucher
|
54e6da3126 |
fix(#2767): pass paths via --files to gsd-sdk query commit + lint guard (#2781)
* fix(#2767): pass paths via --files to gsd-sdk query commit + lint guard Workflows, agents, commands, and references passed file paths positionally to `gsd-sdk query commit`, which silently appended them to the commit subject and triggered the `.planning/` wholesale-stage fallback in sdk/src/query/commit.ts:136. Regression of #733/#798. Inserted `--files` before the path list at every site (81 invocations across 50 files). Added tests/bug-2767-gsd-sdk-commit-files-flag.test.cjs as a permanent lint that scans every shipped .md file and asserts each `gsd-sdk query commit[-to-subrepo]` invocation either uses `--files` or carries no path arguments. Closes #2767 * test(#2767): replace source-grep with behavioral SDK test The original test walked every shipped .md file and regex-tokenized `gsd-sdk query commit` invocations to assert `--files` was present. CONTRIBUTING.md prohibits this source-grep pattern. Rewrite as behavioral SDK tests against `sdk/dist/cli.js` over a real tmp git project (createTempGitProject helper). Cover both the well-formed (`--files <paths>`) form — clean subject, exactly-staged files, .planning/ left untouched — and the buggy positional form, asserting the documented misbehavior (paths leak into subject + the `.planning/` wholesale-stage fallback at commit.ts:136). Also asserts `commit-to-subrepo` rejects when `--files` is omitted (commit.ts:258). The doc-lint is retained as a supplementary defense-in-depth guard since agent-prompt markdown invocations cannot be exercised end-to-end — but it is no longer the primary contract. * docs(#2767): correct contradictory --files guidance in zh-CN/en docs + fix test docstring |
||
|
Rezolv
|
c5b1445529 |
feat(sdk): golden parity harness and query handler CJS alignment (#2302 Track A) (#2341)
* feat(sdk): golden parity harness and query handler CJS alignment (#2302 Track A) Golden/read-only parity tests and registry alignment, query handler fixes (check-completion, state-mutation, commit, validate, summary, etc.), and WAITING.json dual-write for .gsd/.planning readers. Refs gsd-build/get-shit-done#2341 * fix(sdk): getMilestoneInfo matches GSD ROADMAP (🟡, last bold, STATE fallback) - Recognize in-flight 🟡 milestone bullets like 🚧. - Derive from last **vX.Y Title** before ## Phases when emoji absent. - Fall back to STATE.md milestone when ROADMAP is missing; use last bare vX.Y in cleaned text instead of first (avoids v1.0 from shipped list). - Fixes init.execute-phase milestone_version and buildStateFrontmatter after state.begin-phase (syncStateFrontmatter). * feat(sdk): phase list, plan task structure, requirements extract handlers - Register phase.list-plans, phase.list-artifacts, plan.task-structure, requirements.extract-from-plans (SDK-only; golden-policy exceptions). - Add unit tests; document in QUERY-HANDLERS.md. - writeProfile: honor --output, render dimensions, return profile_path and dimensions_scored. * feat(sdk): centralize getGsdAgentsDir in query helpers Extract agent directory resolution to helpers (GSD_AGENTS_DIR, primary ~/.claude/agents, legacy path). Use from init and docs-init init bundles. docs(15): add 15-CONTEXT for autonomous phase-15 run. * feat(sdk): query CLI CJS fallback and session correlation - createRegistry(eventStream, sessionId) threads correlation into mutation events - gsd-sdk query falls back to gsd-tools.cjs when no native handler matches (disable with GSD_QUERY_FALLBACK=off); stderr bridge warnings - Export createRegistry from @gsd-build/sdk; add sdk/README.md - Update QUERY-HANDLERS.md and registry module docs for fallback + sessionId - Agents: prefer node dist/cli.js query over cat/grep for STATE and plans * fix(sdk): init phase_found parity, docs-init agents path, state field extract - Normalize findPhase not-found to null before roadmap fallback (matches findPhaseInternal) - docs-init: use detectRuntime + resolveAgentsDir for checkAgentsInstalled - state.cjs stateExtractField: horizontal whitespace only after colon (YAML progress guard) - Tests: commit_docs default true; config-get golden uses temp config; golden integration green Refs: #2302 * refactor(sdk): share SessionJsonlRecord in profile-extract-messages CodeRabbit nit: dedupe JSONL record shape for isGenuineUserMessage and streamExtractMessages. * fix(sdk): address CodeRabbit major threads (paths, gates, audit, verify) - Resolve @file: and CLI JSON indirection relative to projectDir; guard empty normalized query command - plan.task-structure + intel extract/patch-meta: resolvePathUnderProject containment - check.config-gates: safe string booleans; plan_checker alias precedence over plan_check default - state.validate/sync: phaseTokenMatches + comparePhaseNum ordering - verify.schema-drift: token match phase dirs; files_modified from parsed frontmatter - audit-open: has_scan_errors, unreadable rows, human report when scans fail - requirements PLANNED key PLAN for root PLAN.md; gsd-tools timeout note - ingest-docs: repo-root path containment; classifier output slug-hash Golden parity test strips has_scan_errors until CJS adds field. * fix: Resolve CodeRabbit security and quality findings - Secure intel.ts and cli.ts against path traversal - Catch and validate git add status in commit.ts - Expand roadmap milestone marker extraction - Fix parsing array-of-objects in frontmatter YAML - Fix unhandled config evaluations - Improve coverage test parity mapping * test: raise planner character extraction limit to 48K * fix(sdk): resolve TS build error in docs-init passing config |
||
|
Tom Boucher
|
e208e9757c | refactor(agents): consolidate emphasis-marker density in top 4 agents (#2368) (#2412) | ||
|
Tom Boucher
|
c5e77c8809 |
feat(agents): enforce size budget + extract duplicated boilerplate (#2361) (#2362)
Adds tiered agent-size-budget test to prevent unbounded growth in agent definitions, which are loaded verbatim into context on every subagent dispatch. Extracts two duplicated blocks (mandatory-initial-read, project-skills-discovery) to shared references under get-shit-done/references/ and migrates the 5 top agents (planner, executor, debugger, verifier, phase-researcher) to @file includes. Also fixes two broken relative @planner-source-audit.md references in gsd-planner.md that silently disabled the planner's source audit discipline. Closes #2361 Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
Rezolv
|
d3a79917fa |
feat: Phase 2 caller migration — gsd-sdk query in workflows, agents, commands (#2179)
* feat: Phase 2 caller migration — gsd-sdk query in workflows (#2122) Cherry-picked orchestration rewrites from feat/sdk-foundation (#2008, 4018fee) onto current main, resolving conflicts to keep upstream worktree guards and post-merge test gate. SDK stub registry omitted (out of Phase 2 scope per #2122). Refs: #2122 #2008 Made-with: Cursor * docs: add gsd-sdk query migration blurb Made-with: Cursor * docs(workflows): extend Phase 2 gsd-sdk query caller migration - Swap node gsd-tools.cjs for gsd-sdk query in review, plan-phase, execute-plan, ship, extract_learnings, ai-integration-phase, eval-review, next, thread - Document graphify CJS-only in gsd-planner; dual-path in CLI-TOOLS and ARCHITECTURE - Update tests: workstreams gsd-sdk path, thread frontmatter.get, workspace init.*, CRLF-safe autonomous frontmatter parse - CHANGELOG: Phase 2 caller migration scope Made-with: Cursor * docs(phase2): USER-GUIDE + remaining gsd-sdk query call sites - USER-GUIDE: dual-path CLI section; state validate/sync use full CJS path - Commands: debug (config-get+tdd), quick (security note), intel Task prompt - Agent: gsd-debug-session-manager resolve-model via jq - Workflows: milestone-summary, forensics, next, complete-milestone/verify-work (audit-open CJS notes), discuss-phase, progress, verify-phase, add/insert/remove phase, transition, manager, quick workflow; remove-phase commit without --files - Test: quick-session-management accepts frontmatter.get - CHANGELOG: Phase 2 follow-up bullet Made-with: Cursor * docs(phase2): align gsd-sdk query examples in commands and agents - init.* query names; frontmatter.get uses positional field name - state.* handlers use positional args; commit uses positional paths - CJS-only notes for from-gsd2 and graphify; learnings.query wording - CHANGELOG: Phase 2 orchestration doc pass Made-with: Cursor * docs(phase2): normalize gsd-sdk query commit to positional file paths - Strip --files from commit examples in workflows, references, commands - Keep commit-to-subrepo ... --files (separate handler) - git-planning-commit.md: document positional args - Tests: new-project commit line, state.record-session, gates CRLF, roadmap.analyze - CHANGELOG [Unreleased] Made-with: Cursor * feat(sdk): gsd-sdk query parity with gsd-tools and PR 2179 registry fixes - Route query via longest-prefix match and dotted single-token expansion; fall back to runGsdToolsQuery (same argv as node gsd-tools.cjs) for full CLI coverage. - Parse gsd-sdk query permissively so gsd-tools flags (--json, --verify, etc.) are not rejected by strict parseArgs. - resolveGsdToolsPath: honor GSD_TOOLS_PATH; prefer bundled get-shit-done copy over project .claude installs; export runGsdToolsQuery from the SDK. - Fix gsd-tools audit-open (core.output; pass object for --json JSON). - Register summary-extract as alias of summary.extract; fix audit-fix workflow to call audit-uat instead of invalid init.audit-uat (PR review). Updates QUERY-HANDLERS.md and CHANGELOG [Unreleased]. Made-with: Cursor * fix(sdk): Phase 2 scope — Trek-e review (#2179, #2122) - Remove gsd-sdk query passthrough to gsd-tools.cjs; drop GSD_TOOLS_PATH - Consolidate argv routing in resolveQueryArgv(); update USAGE and QUERY-HANDLERS - Surface @file: read failures in GSDTools.parseOutput - execute-plan: defer Task Commit Protocol to gsd-executor - stale-colon-refs: skip .planning/ and root CLAUDE.md (gitignored overlays) - CHANGELOG [Unreleased]: maintainer review and routing notes Made-with: Cursor |
||
|
Tibsfox
|
67f5c6fd1d |
docs(agents): standardize required_reading patterns across agent specs (#2176)
Closes #2168 Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |