Commit Graph

5 Commits

Author SHA1 Message Date
Tom Boucher
77fa08f1e8 fix(#2773): feed the spec-phase edge probe English-translated requirement text (#3713)
* test(#2773): failing-first contract and premise tests for translated edge-probe input

Locks the Step 5.5 contract that a response_language project must feed the
edge probe an English translation of each requirement's text, and binds that
advice to measured engine behavior: the same requirement classifies to zero
shapes in Portuguese and to collection/adjacency/empty/ordering in English.

Also pins the honest limit — the issue's own repro sentence classifies to []
in English too, so translation is necessary but not sufficient and the
authored shapes override is the documented fallback.

Red before the doc change; the assertions are all false today.

Refs #2773

* fix(#2773): feed the spec-phase edge probe English-translated requirement text

The shape cues in src/edge-probe.cts are English word-boundary regexes, so a
project running with response_language set wrote its SPEC requirements into the
Step 5.5 $REQS_JSON heredoc in that language, matched no cue, classified to zero
shapes, and landed every row in the unclassified sentinel (#1110). The taxonomy
contributed nothing and --auto left it all unresolved — the probe was a silent
no-op for exactly the spec type it exists to harden.

Step 5.5 now states that the $REQS_JSON payload is engine input rather than
user-facing output, so the response_language rule does not govern it: each
requirement's text carries a faithful English translation, the SPEC keeps its
original language, and requirement ids are never translated or renumbered. The
instruction sits before the heredoc on purpose — the downstream APPLICABLE=0
warning fires only when every requirement is unclassified, so a partly-classified
non-English spec would otherwise slip through with no signal at all.

Measured against the compiled engine: the same requirement returns [] in
Portuguese and collection -> adjacency/empty/ordering in English. Also measured:
the issue's own repro sentence returns [] in English too, so translation is
necessary but not sufficient — the instruction therefore points at the authored
shapes override for prose carrying no cue in any language rather than promising
that translation restores classification.

Doc scope only, per the triage disposition on the issue. The compiled engine is
untouched; the lang-hint / per-language cue-set fix is a separate follow-up.

Closes #2773

* fix(#2773): clean up the edge-probe temp file on the placeholder-guard exit path

Surfaced by the isolated security review of this branch. Between the mktemp and
the unconditional cleanup, Step 5.5 has two sibling guards that disagreed about
their own invariant: the engine-failure guard runs rm -f "$REQS_JSON" before
exiting, while the empty/placeholder guard directly above it exited without one.
A spec run that tripped the placeholder check therefore stranded a temp file
holding the SPEC's requirement text in TMPDIR, once per failed run.

The added contract test walks the region between the mktemp and the
unconditional cleanup and asserts no exit path leaves the file behind, so the
two guards can no longer drift apart. Proven to bind: run against the pre-fix
file the walker reports the leaking exit; against the fixed file it reports none.

Refs #2773

* docs(#2773): record the edge probe's English-cue input constraint in the predicate store

The co-change gate flagged CONTEXT.md (13 co-changes with spec-phase.md) and
docs/CONFIGURATION.md (11) as candidate-missing-updates, and both were real
gaps rather than incidental coupling.

CONTEXT.md's EdgeCompletenessProbeModule entry documents the input contract for
classifyShape but did not record that SHAPE_CUES are English word-boundary
patterns — so the predicate store implied text was language-agnostic, which is
what a future agent reads before touching this seam.

docs/CONFIGURATION.md's response_language row is what a non-English project
reads when it turns the setting on; it now names the one deliberate exception
and links to the FEATURES.md explanation, so the interaction is discoverable
from the config key rather than only from the workflow.

CONTEXT-INDEX.json regenerated via gen-context-index.cjs --write. The drift-ack
fragment is updated for the final byte range and now also records the
placeholder-guard cleanup fix folded into the same block.

Refs #2773

* fix(#2773): append the growth rationale to the existing spec-phase.md ack entry

The remote runner caught this: emitted-attribution.test.cjs pins the
0000-legacy-migration.json spec-phase.md entry permanently (the #2914 migration
regression test asserts the exact '31987 -> 31997' delta text survives), so
removing it to avoid a duplicate-key collision with a new fragment broke that
test instead of satisfying the ratchet.

The entry is an accreting log, not a single-use slot — #2733, #3132 and #3102
were each appended to the same reason string by later PRs, which is how a shared
growth key coexists with the rule that two ack sources may never name the same
path. This appends the #2773 rationale the same way and drops the separate
fragment, whose spec-phase.md key was the collision.

Verified locally by reproducing both affected tests against the real fragment
before re-dispatching: the pinned delta survives, grown[0].acked is true,
staleAcks is empty, and all 35 entries still read as spent.

Refs #2773

* docs(#2773): add a how-to for probing edges in a non-English project

The phase gate's enablementSequence check caught a wrong call of mine. I had
recorded that no how-to was owed because the user takes zero extra steps — the
workflow translates the probe input itself. Written out, though, the sequence
from off to value is two steps and step 1 depends on response_language, a
setting owned by a different capability than the edge probe, which is exactly
the condition the how-to test names.

There is also real task content a reference table cannot carry: the three-way
split between a few unclassified rows (the classifier's recall gap), every row
unclassified (the probe could not read the spec at all), and the silent
partly-classified case where the APPLICABLE=0 warning never fires. That last
one is what a user would otherwise misread as a clean bill of health.

Shaped after the resolve-edge-coverage-findings / resolve-unreachable-guard
siblings and indexed from docs/README.md next to its closest relative.

Refs #2773

* chore(#2773): backfill the changeset PR number

pr:0 placeholder replaced with the real PR number now that #3713 exists.

Refs #2773

---------

Co-authored-by: sim <sim@local>
2026-08-20 13:36:00 -04:00
Rezolv
3dff700aaa fix(#3102): render edge-probe coverage report so the resolution loop consumes it (#3391)
* fix(#3102): render edge-probe coverage report so the resolution loop consumes it

Step 5.5 captured the edge-probe report into $COVERAGE, shape-checked it, and
reduced it to coverage.applicable — the engine's per-requirement items[] never
reached the model, so the resolution loop re-derived edge categories from prose
(the data-flow twin of #2733's control-flow discard). The block's own comment
claimed the opposite.

Render $COVERAGE RAW into context after the well-formedness guard (schema-agnostic
so an ADR-550 D7a-style re-cut cannot desync a bespoke renderer), and bind the rows
in the resolution loop as a deterministic FLOOR the model unions with its own
classification — floor, never ceiling, since the classifier has a measured recall
gap (ADR-857 §98 / ADR-550 D7b). --auto consumes the same floor. Comment corrected
to match. Regression test asserts a bare render of $COVERAGE, not a count-only cross.

* chore(#3102): add changeset for the Step 5.5 edge-coverage render fix

* chore(#3102): re-arm spec-phase.md emitted-drift ack for the Step 5.5 render growth

The render + floor-binding prose grows spec-phase.md ~1818 bytes (32238 -> 34056,
under the 40960 cap). Re-arms the existing spent spec-phase.md ack rather than adding
a new fragment (a second key would collide with the base-relative duplicate check).
2026-08-12 20:44:57 -04:00
Tom Boucher
3146ff36aa fix(#3132): realign retired covered/backstop-as-status vocab to resolved+verification (#3138)
* fix(#3132): realign spec/plan/ui-phase workflow prose from retired covered/backstop-as-status to resolved+verification

The edge-probe resolution model splits status (resolved|dismissed|unresolved)
from verification (explicit|backstop). The workflow prose in three files still
used the pre-re-cut covered/backstop-as-status vocabulary that validateResolution
rejects.

Swept all three prose surfaces:
- spec-phase.md: Step 5.5 resolution options, --auto mode + log line, comment, Step 6 row list
- plan-phase.md: lift rule (L778/L780), comments (L564/L706), quality gate (L826-827)
- ui-phase.md: resolution loop (L391), --auto mode (L405-409), write-back format (L415)

Added regression test in edge-probe-spec-phase-contract.test.cjs asserting the
retired vocab is absent and resolved+verification is used instead.

* chore(#3132): add changeset + emitted-drift ack for workflow vocab realignment

* fix(#3132): update planner contract tests for resolved+verification vocabulary

RR-02 and RR-03 tests asserted the old covered/backstop-as-status vocab.
Updated to match the realigned prose (resolved edge → must_haves).

* fix(#3132): fix specless-probe-fallback test assertion + merge duplicate ack

Test assertion was too strict (expected auto-resolved + verification:explicit
on same line). Split into two independent assertions.

Merged plan-phase.md ack into existing #2658 fragment to resolve duplicate-path
rule violation.

* fix(#3132): use bare filenames in ack keys (size map keys are bare, not full paths)

* fix(#3132): amend existing acks instead of duplicating — remove plan-phase from #2658, spec-phase from #3132, append #3132 reason to #0000 and #2650

* chore(#3132): backfill changeset PR number 3138

---------

Co-authored-by: sim <sim@local>
2026-08-07 04:45:30 -04:00
Tom Boucher
07603df8f2 fix(#2647): code-fixer worktree under .claude/worktrees/, not a hardcoded /tmp path (#2942)
* test(#2647): failing-first — fixer worktree path must be repo-relative not /tmp

* fix(#2647): place code-fixer worktree under .claude/worktrees/, not /tmp

The gsd-code-fixer agent hand-rolled its worktree at a hardcoded
`/tmp/sv-${padded_phase}-reviewfix-XXXXXX` mktemp path. On Windows/Git Bash
that landed OUTSIDE the project tree — outside the agent session's permission
allowlist, so every Read inside the worktree prompted (~25/run) — and mktemp's
MAX_PATH-avoidance substitute produced an un-removable `C:/mvwtNN` path.

Place the worktree repo-relative under `.claude/worktrees/` (the same dir the
harness-managed executor worktrees use: gitignored via `.claude/`, inside the
session's permission scope), with a $$-PID + epoch suffix for concurrency
uniqueness (replacing mktemp's XXXXXX). $main_repo is resolved the same way
the cleanup tail already resolves it.

Three sites updated: setup_worktree bash, concrete-steps prose, critical_rules.
The #2990 `-b "$reviewfix_branch"` invariant is preserved (the folded test
asserts it). Failing-first regression added to the #2990 suite in
tests/agent-frontmatter.test.cjs.

* test(#2647): update #2686 path assertion to expect .claude/worktrees/, not /tmp

The #2686 regression test encoded the worktree location as a hardcoded
`/tmp/sv-` path (matching sibling GSD agents at the time). #2647 showed that
breaks Windows/Git Bash (worktree outside the project tree → permission prompts;
mktemp MAX_PATH substitute un-removable). Update the #2686 path assertion to
require the repo-relative `.claude/worktrees/` location and forbid `/tmp/sv-`.
The #2686 isolation + cleanup assertions are unchanged.

* fix(#2647): word-boundary wt= parse + ack the fixer growth vs next

Two follow-ups to the #2647 GREEN run:
- parseWtAssignments matched `prior_wt=` (no word boundary), polluting the
  set and tripping the repo-relative + concurrency-unique assertions. Anchor
  on (?:^|\s)wt= so only the real worktree-path assignment is captured.
- emitted-attribution: gsd-code-fixer.md grew 1875 bytes vs origin/next. Update
  the emitted-drift-ack entry to attribute the #2647 worktree-path change
  (supersedes the prior #2825 attribution, whose growth is already in next).

* fix(#2647): address review — validate padded_phase at the sink + tighten test

Code-review + security-review both APPROVED with one actionable minor:
padded_phase is interpolated into a worktree PATH and a git BRANCH NAME, but
was only validated by the orchestrator (code-review-fix.md), not at the agent
sink. The agent prompt is a literal bash contract any caller can spawn, so add
a `[[ =~ ^[0-9]+(\.[0-9]+)?$ ]]` self-defense check rejecting traversal/shell
metachars (defense-in-depth; not a present vuln — the only caller validates).

Also tighten the concurrency-uniqueness test to require BOTH $$ AND $(date +%s)
(either-alone was too lax per review). Update the emitted-drift-ack reason to
cover the added validation growth.

* changeset(#2647): code-fixer worktree under .claude/worktrees not /tmp

* changeset(#2647): backfill PR number 2942

* chore(#2938): regenerate stale docs/CONTEXT-INDEX.json on next

#2938 (#2928) updated the CONTEXT.md RULESET prose for the new per-PR
emitted-drift-ack fragment mechanism (#2914) but shipped a CONTEXT-INDEX.json
generated from the OLD prose. lint:generated-sync fails on every PR that
rebases onto next after #2938 (the regen produces a 3-line diff bringing three
RULESET entries — AGENT_SIZE_BUDGET, EMITTED_ATTRIBUTION, WORKFLOW_SIZE_BUDGET
— in sync with the prose already on next). Mechanical regen via
`node scripts/gen-context-index.cjs --write`; idempotent; surfaced by the
#2647 rebase. No behavioral change.

---------

Co-authored-by: sim <sim@users.noreply.github.com>
2026-07-31 14:45:51 -04:00
Tom Boucher
c043f2946c fix(#2914): per-PR ack fragments instead of one shared mutable file (#2923)
* fix(#2914): never persist a spent emitted-drift ack on next

tests/emitted-drift-ack.json held 34 spent #2834 entries merged via #2900.
Every entry is scoped to the diff that introduced it (#2789), so once merged
to next it is at the base by definition -- spent and inert. Its presence is
still load-bearing though: each PR rewrites the paths map wholesale, making a
persistent base copy a shared cell. Five of six conflicting PRs in the open
queue collided on this file and nothing else.

Deletes the stale document and adds a push-to-next guard asserting it stays
absent. The guard is deliberately NOT wired into lint:ci -- a PR-lane check
against the base is the #2768 shape #2789 exists to end.

Closes #2914

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

* chore(#2914): backfill changeset pr number

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

* fix(#2914): per-PR ack fragments instead of one shared mutable file

The emitted-drift acknowledgment lived in a single tests/emitted-drift-ack.json
whose paths map every PR rewrote wholesale. That is a shared mutable cell: any
two PRs needing an ack edit the same lines and conflict. Five of six conflicting
PRs in the open queue collided on this file and nothing else.

Acks now live as per-PR fragments under tests/emitted-drift-acks/, the same
shape .changeset/ already uses to solve this exact problem. Two PRs pick
different filenames, so they cannot collide, and fragments lingering on next
are harmless rather than toxic.

The legacy file's 35 entries are MIGRATED into a fragment, not deleted. An
earlier delete-only attempt failed verification twice: the ratchet lost the
spec-phase.md acknowledgment from #2779 and reported a 10-byte growth with no
ack. Relocating preserves every acknowledgment.

The legacy single file is still READ (unioned with the fragments) because five
open PRs carry it; dropping support would break all of them. A duplicate path
key across sources is a hard error, never last-wins.

The push-to-next guard is retargeted accordingly: it now asserts only that the
legacy SHARED file never reappears on next. Fragments may persist harmlessly.

Closes #2914

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-07-31 13:15:29 -04:00