diff --git a/.changeset/sturdy-lemurs-snooze.md b/.changeset/sturdy-lemurs-snooze.md new file mode 100644 index 000000000..f034c9cc7 --- /dev/null +++ b/.changeset/sturdy-lemurs-snooze.md @@ -0,0 +1,5 @@ +--- +type: Fixed +pr: 4804 +--- +**The UI consideration probe reads an optional `text_en` field** — in a `response_language` project every UI element used to classify to zero categories and land in `unclassified`, dropping the whole state-coverage axis; a faithful English translation per element now classifies exactly like its English equivalent. Mirrors the edge probe's #3717 remedy; an empty or whitespace `text_en` fails closed. (#4657) diff --git a/CONTEXT.md b/CONTEXT.md index 84ad3be60..c441a72b3 100644 --- a/CONTEXT.md +++ b/CONTEXT.md @@ -614,6 +614,7 @@ The prompt-level data/instruction isolation seam for untrusted web/document ingr `PROBE.prohib.verification=test|judgment` `PROBE.ui.verification=explicit|backstop` `PROBE.ui.axis=MIXED — closed compiled shape-rooted 8 (empty/loading/error/populated/partial/overflow/zero-one-many/long-text) via ui-consideration-probe adapter; open UX (real-time/a11y/i18n-RTL) prose-owned in references/domain-probes.md, NOT compiled (#1867)` +`PROBE.ui.text_en=optional English translation of Element.text read by classification (text_en ?? text), engine input never user-facing output; mirrors the edge adapter's #3717 field; empty/whitespace/non-string fails closed (#4657)` `PROBE.ui.seam=ui-phase Step 9.5 post-verification: element-cue classify -> propose-then-confirm (partial-cue mitigation, Goodhart) -> autoResolve --auto floor (never dismiss; unclassified stays unresolved #1110) -> ## UI Considerations write-back -> plan-phase `## UI Considerations` lift rule (#1867)` `PROBE.ci.surface=the contract (parse/validate, projection round-trip, fail-closed guards), NEVER the LLM judgment (ADR-550 D5)` `PROHIB.recall=LLM-prose; no compiled prohibition-probe recall engine (only the schema/projection layer is code, ADR-550 D7b)` diff --git a/docs/CONTEXT-INDEX.json b/docs/CONTEXT-INDEX.json index deb0ccba6..a21b16798 100644 --- a/docs/CONTEXT-INDEX.json +++ b/docs/CONTEXT-INDEX.json @@ -1,6 +1,6 @@ { "schemaVersion": 1, - "count": 285, + "count": 286, "classes": { "ARCH": 1, "CI": 2, @@ -14,7 +14,7 @@ "PLANNING": 3, "PR": 2, "PRED": 68, - "PROBE": 11, + "PROBE": 12, "PROC": 14, "PROHIB": 10, "RELEASE-NOTES": 31, @@ -646,6 +646,11 @@ "klass": "PROBE", "value": "ui-phase Step 9.5 post-verification: element-cue classify -> propose-then-confirm (partial-cue mitigation, Goodhart) -> autoResolve --auto floor (never dismiss; unclassified stays unresolved #1110) -> ## UI Considerations write-back -> plan-phase `## UI Considerations` lift rule (#1867)" }, + { + "id": "PROBE.ui.text_en", + "klass": "PROBE", + "value": "optional English translation of Element.text read by classification (text_en ?? text), engine input never user-facing output; mirrors the edge adapter's #3717 field; empty/whitespace/non-string fails closed (#4657)" + }, { "id": "PROBE.ui.verification", "klass": "PROBE", diff --git a/examples/dynamic-context-management/CONTEXT-INDEX.json b/examples/dynamic-context-management/CONTEXT-INDEX.json index 7e7841a4b..a46283479 100644 --- a/examples/dynamic-context-management/CONTEXT-INDEX.json +++ b/examples/dynamic-context-management/CONTEXT-INDEX.json @@ -1,6 +1,6 @@ { "schemaVersion": 1, - "count": 285, + "count": 286, "classes": { "ARCH": 1, "CI": 2, @@ -14,7 +14,7 @@ "PLANNING": 3, "PR": 2, "PRED": 68, - "PROBE": 11, + "PROBE": 12, "PROC": 14, "PROHIB": 10, "RELEASE-NOTES": 31, @@ -30,1711 +30,1717 @@ "id": "ARCH.SKILL.improve-codebase.next-candidates", "klass": "ARCH", "value": "[Workstream Progress Projection Module]", - "line": 697 + "line": 721 }, { "id": "CI.GATE.changeset-lint", "klass": "CI", "value": "hard-fail for user-facing code diffs unless .changeset/* or PR has no-changelog label", - "line": 681 + "line": 705 }, { "id": "CI.GATE.issue-link-required", "klass": "CI", "value": "hard-fail if PR body lacks closes/fixes/resolves #", - "line": 680 + "line": 704 }, { "id": "CONFIG.LOCATION.SEAM.in-process-scrub", "klass": "CONFIG", "value": "TEST_ENV_BASE reaches CHILD env only; a test calling install() IN-PROCESS must additionally use helpers.scrubConfigLocationEnv() in beforeEach + its restorer in afterEach — HOME/USERPROFILE sandboxing is NOT sufficient because getGlobalConfigDir is env-FIRST", - "line": 717 + "line": 741 }, { "id": "CONFIG.LOCATION.SEAM.kimi-two-homes", "klass": "CONFIG", "value": "kimi declares TWO config-location vars: KIMI_CONFIG_DIR (registry, generic Agent-Skills root via resolveKimiGlobalDir) and KIMI_SHARE_DIR (KIMI_HOOKS_TOML_DESCRIPTOR, kimi's OWN native config.toml carrying GSD's [[hooks]] block via resolveKimiHooksTomlDir); a registry-only derivation covers the first and silently misses the second", - "line": 716 + "line": 740 }, { "id": "CONFIG.LOCATION.SEAM.scrub-set", "klass": "CONFIG", "value": "tests/helpers.cjs CONFIG_LOCATION_ENV_KEYS is DERIVED from five sources rather than maintained as one hand-written list (source 4 IS a literal residue list, for vars that fit no other rung — what is never hand-listed is the SET): capability-registry runtimes[].runtime.configHome.env AND [].configHome.skillsHome.env + runtime-homes NON_REGISTRY_CONFIG_HOME_DESCRIPTORS[].env AND [].skillsHome.env (a descriptor is a descriptor — BOTH descriptor rungs walk skillsHome, which resolves independently via resolveSkillsBaseFromDescriptor) + runtime-homes GSD_LOCATION_ENV_KEYS + a residue list (GROK_AGENTS_HOME, GSD_RUNTIME, GSD_PROJECT, GSD_WORKSTREAM) + WRITE_ESCAPE_PERMISSION_ENV_KEYS (GSD_ALLOW_SYMLINKED_DEST — a permission, not a location: it names no path but disarms the symlink-escape guard, so blanking it makes the guard STRICTER, never looser); adding a config-location var means making it ENUMERABLE at one of those sources, not appending a literal", - "line": 714 + "line": 738 }, { "id": "CONFIG.LOCATION.SEAM.two-families", "klass": "CONFIG", "value": "runtime configHomes (where a third-party runtime keeps config, registry- or descriptor-declared) and GSD's OWN location vars (GSD_HOME -> $GSD_HOME/.gsd store, GSD_AGENTS_DIR -> getAgentsDir priority 1) are DISTINCT families; no registry derivation reaches the second, and treating a miss there as a registry gap is what produced review round 2", - "line": 715 + "line": 739 }, { "id": "CONFIG.SEAM.loadConfig-context", "klass": "CONFIG", "value": "loadConfig(cwd,{workstream}) replaces env-mutation fallback; no temporary process.env GSD_WORKSTREAM rewrites", - "line": 713 + "line": 737 }, { "id": "EXEC.CLASSIFY.classes", "klass": "EXEC", "value": "{class:'quota-exceeded'|'classify-handoff-bug'|'unknown-failure', sentinel?, retryAfterSeconds?}", - "line": 943 + "line": 967 }, { "id": "EXEC.CLASSIFY.cross-runtime", "klass": "EXEC", "value": "Anthropic/CC: usage limit|rate limit|quota|429|retry-after; Copilot CLI: rate_limit (stem); Codex CLI: 429|usage_limit_reached|too many requests", - "line": 945 + "line": 969 }, { "id": "EXEC.CLASSIFY.handler", "klass": "EXEC", "value": "gsd-core/bin/lib/agent-command-router.cjs:classifyAgentFailure (registered via command-aliases.cjs; mutation:false outputMode:json)", - "line": 941 + "line": 965 }, { "id": "EXEC.CLASSIFY.precedence", "klass": "EXEC", "value": "quota sentinel wins over classifyHandoffIfNeeded bug when both appear", - "line": 946 + "line": 970 }, { "id": "EXEC.CLASSIFY.proactive-signal-not-usable", "klass": "EXEC", "value": "Anthropic exposes anthropic-ratelimit-* headers + Agent SDK RateLimitEvent; Claude Code subprocess does NOT forward to hooks/statusline today (upstream #33820, #22407, #32796)", - "line": 948 + "line": 972 }, { "id": "EXEC.CLASSIFY.retry-after-parser", "klass": "EXEC", "value": "\\bretry[-_ ]after[:\\s]+(\\d+)\\b avoids embedded-word false matches like noretry-after", - "line": 947 + "line": 971 }, { "id": "EXEC.CLASSIFY.sentinel-order", "klass": "EXEC", "value": "most specific first: 429 beats too-many-requests; resource_exhausted beats quota (array order in src/agent-command-router.cts QUOTA_SENTINELS checks resource_exhausted before quota); case-insensitive; canonical sentinel value is lower-cased form", - "line": 944 + "line": 968 }, { "id": "EXEC.CLASSIFY.workflow", "klass": "EXEC", "value": "gsd-core/workflows/execute-phase.md step 7; class-distinct prompts (quota-to-wait-for-reset; classify-handoff-bug-to-spot-check; unknown-to-continue/stop)", - "line": 942 + "line": 966 }, { "id": "GSD-RESEARCH.CONTEXT-DISCIPLINE", "klass": "GSD-RESEARCH", "value": "less-context levers: subagent isolation + compact provider output + fetches-to-disk + cache-returns-digest; API clear_tool_uses/memory tool are the conceptual model, not a Claude Code harness knob", - "line": 463 + "line": 486 }, { "id": "GSD-RESEARCH.INTEGRATION.L2-hybrid", "klass": "GSD-RESEARCH", "value": "code owns cache+legitimacy+confidence+provider-pick (gsd-tools query research-plan/research-store/package-legitimacy); MCP owns the fetch; agent returns RESEARCH.md path, never raw fetches", - "line": 461 + "line": 484 }, { "id": "GSD-RESEARCH.MODULE.package-legitimacy", "klass": "GSD-RESEARCH", "value": "registry-API verdicts (npm/PyPI/crates.io injectable adapters) computed from thresholds {minAgeDays:30,minWeeklyDownloads:1000,requireRepo:true}; verdict OK|SUS|SLOP per package; slopcheck=optional adapter that can only escalate, never the install-or-degrade gate", - "line": 460 + "line": 483 }, { "id": "GSD-RESEARCH.MODULE.research-provider", "klass": "GSD-RESEARCH", "value": "single source of truth PROVIDER_WATERFALL (docs Context7->Ref->Jina->websearch; web Exa->Tavily->Perplexity->Brave->websearch; scrape Firecrawl->Jina); planResearch returns cache-hits+fetch-plan; classifyConfidence stamps HIGH|MEDIUM|LOW by provider AUTHORITY + verification EVIDENCE (HIGH requires code-computed ground-truth corroboration e.g. legitimacyVerdict OK; provider authority alone caps at MEDIUM; SLOP caps at LOW); Firecrawl is scrape-only (not in the docs or web legs)", - "line": 459 + "line": 482 }, { "id": "GSD-RESEARCH.MODULE.research-store", "klass": "GSD-RESEARCH", "value": "content-addressed cache; key=sha256(ecosystem+library+version+query+kind); getResearch->{hit,stale} never throws (mirrors graphify staleness); ttlForSource curated HIGH 30d|MED 7d|web LOW 1d; tiers: curated-doc kinds -> ~/.gsd/research-cache (cross-project), web/synthesis -> project .planning/research/.cache", - "line": 458 + "line": 481 }, { "id": "GSD-RESEARCH.PROVIDER.availability", "klass": "GSD-RESEARCH", "value": "config flags brave_search/exa_search/firecrawl/tavily_search/ref_search/perplexity/jina (env _API_KEY or ~/.gsd/_api_key); context7/jina/websearch always available; planResearch falls through waterfall to websearch terminal", - "line": 462 + "line": 485 }, { "id": "LEARNING.prompt-budget.boundary-gap", "klass": "LEARNING", "value": "PR #3708 commit 2df566ed reserved NOTE_RESERVE_TOKENS in pressure-threshold AND in minSet pre-check; both buggy paths only fire when baseTokens ∈ (effectiveBudget - NOTE_RESERVE_TOKENS, effectiveBudget]; original test suite used budgets far from that band so neither path was exercised; fix bde1ae8f confines NOTE_RESERVE accounting to post-trim assembly path only; future budget/limit code MUST add boundary fixtures per RULESET.TESTS.boundary-coverage.fixtures", - "line": 626 + "line": 650 }, { "id": "LIVE-CONFIG.GUARD.SEAM.ci-blind", "klass": "LIVE-CONFIG", "value": "the AMBIENT-ENV half stays CI-blind — CI never has these vars set, so green CI is not evidence for it; what strict mode catches in CI is the suite's own default-root leaks (HOME/USERPROFILE-derived), the guard remains the only loud signal for ambient-var escapes", - "line": 723 + "line": 747 }, { "id": "LIVE-CONFIG.GUARD.SEAM.module", "klass": "LIVE-CONFIG", "value": "scripts/live-config-guard.cjs (deliberately NOT scripts/lib/, which the installer copies to users wholesale while uninstall removes only an allowlist; excluded from the npm tarball via package.json files[] together with its whole require chain run-tests.cjs/affected-tests-lib.cjs/run-affected-tests.cjs — a partial exclusion trips the #2858 shipped-requires-only-shipped gate); exports [resolveLiveConfigRoots, resolveExtraWatchTargets, snapshotLiveConfig, diffLiveConfig, formatViolations, newestMtime]; driven by scripts/run-tests.cjs pre/post suite", - "line": 718 + "line": 742 }, { "id": "LIVE-CONFIG.GUARD.SEAM.non-root-targets", "klass": "LIVE-CONFIG", "value": "resolveExtraWatchTargets covers THREE live write surfaces that are not runtime config ROOTS (skills bases are a DELIBERATE non-target — the config-root layout misfires beneath them, so they need their own layout): $GSD_HOME/.gsd watched WHOLESALE (exclusively GSD-owned, so the shared-root trap does not apply) plus ONE config.toml per NON_REGISTRY_CONFIG_HOME_DESCRIPTORS entry, each watched as a SINGLE FILE (those roots belong to their products) — today three targets, since #2755 split Kimi CLI (~/.kimi, KIMI_SHARE_DIR) from Kimi Code (~/.kimi-code, KIMI_CODE_HOME); the targets are DERIVED by iterating that array, never by calling a named resolver, so a further descriptor is picked up without editing the guard PROVIDED it owns the same NON_REGISTRY_OWNED_FILE ('config.toml') — one that owns a different filename needs a per-descriptor mapping, the named residual the guard states at its own definition. SECOND RESIDUAL: config.toml is not all GSD writes into those roots — installSharedHooksBundle also populates /hooks/, which is UNWATCHED; closing it is a layout decision, like skills bases; passed to snapshotLiveConfig explicitly so a fixture-root caller cannot pull the real ~/.gsd into its snapshot", - "line": 720 + "line": 744 }, { "id": "LIVE-CONFIG.GUARD.SEAM.scope", "klass": "LIVE-CONFIG", "value": "ownership-based, never whole-root: GSD_OWNED_ENTRIES top-level footprint + children whose name startsWith GSD_ARTIFACT_PREFIX ('gsd-') under GSD_PREFIXED_PARENTS (dirs shared with the host agent); watching a shared root wholesale false-positives on the host's own writes and a guard that cries wolf gets disabled", - "line": 719 + "line": 743 }, { "id": "LIVE-CONFIG.GUARD.SEAM.severity", "klass": "LIVE-CONFIG", "value": "reports by default locally; CI wires GSD_STRICT_LIVE_CONFIG_GUARD=1 on Linux/macOS lanes (test.yml, all three test jobs) so a suite-produced leak FAILS those runs; Windows lanes stay report-only pending the documented pre-existing USERPROFILE sweep (~190 test sites sandbox HOME alone) — promote once that lands; skipped by GSD_SKIP_LIVE_CONFIG_GUARD=1", - "line": 722 + "line": 746 }, { "id": "LIVE-CONFIG.GUARD.SEAM.truncation", "klass": "LIVE-CONFIG", "value": "MAX_ENTRIES/MAX_DEPTH bound the walk; a bound hit sets truncated and diffLiveConfig emits kind:'unverified' — a truncated scan MUST NOT read as clean; boundary covered at {limit-1,limit,limit+1} via newestMtime's injected budget plus fast-check monotonicity, per RULESET.TESTS.boundary-coverage + RULESET.TESTS.property-based-testing", - "line": 721 + "line": 745 }, { "id": "META.RULE.brief-must-cite-doc", "klass": "META", "value": "agent prompts MUST quote the canonical doc line being applied; paraphrasing from predicate memory drifts and produces violations", - "line": 782 + "line": 806 }, { "id": "META.RULE.brief-no-paraphrase", "klass": "META", "value": "writing \"k040 — never leave changelog box unchecked\" caused 5 of 8 agents to edit CHANGELOG.md in violation of CONTRIBUTING.md L110", - "line": 783 + "line": 807 }, { "id": "META.RULE.canonical-source-precedence", "klass": "META", "value": "CONTRIBUTING.md > docs/adr/* > CONTEXT.md > agent memory", - "line": 780 + "line": 804 }, { "id": "META.RULE.read-contributing-first", "klass": "META", "value": "read CONTRIBUTING.md sections \"Pull Request Guidelines\" + \"CHANGELOG Entries\" before EVERY agent dispatch", - "line": 781 + "line": 805 }, { "id": "PHASE.REQ-LINE.SEAM.cap", "klass": "PHASE", "value": "REQ_TOKEN_SCAN_LIMIT=2048 bounds every predicate including each range participant's NEIGHBOURS, not just the operator; a bound hit sets oversizedTokens and takes the unverified kind — an unexaminable token MUST NOT read as clean, and the cap bounds the WORK, never the warning; boundary covered at {2047,2048,2049} across BOTH capped predicate families per RULESET.TESTS.boundary-coverage", - "line": 728 + "line": 752 }, { "id": "PHASE.REQ-LINE.SEAM.census-domains", "klass": "PHASE", "value": "TWO open domains, each censused in-source with its NOT-reached consequence: range-operator spellings (reached: ..+, seven Unicode dashes plus ASCII -, …, to/thru/through; not reached: →, ~, ..=, ..<, until, up to) and comma-SUBSTITUTE separators (round 4's 26-spelling sweep concluded 'exactly ; and : ' because it swept the ONE-SIDED form for ;/: and only the BARE and SYMMETRIC forms for every other separator — different members tested in different shapes, so the answer was forced; re-swept round 5 FULLY CROSSED at 21 separators x {bare,trailing-space,leading-space,both} = 84, driven: 26 select both, 24 already warn, 34 UNDER-SELECT SILENTLY and all 34 are one-sided attachment — | / + & \\ > . ! ? • · ؛ ； ， － ~ and/plus — so R4 covers TWO CHARACTERS of a WIDE-OPEN domain, never the whole of it); R4's own NOT-reached set is therefore styling-only decoration, every non-;/: attachment, anything inside a MATCHED parenthetical, and any decorated id whose prefix is on NO selected id (REQ-01, FOO-02: x stays silent even when FOO-02 is real); the prefix gate is NOT complete in the other direction either — a citation SHARING a selected prefix (REQ-01, see REQ-7: sec 3) still fires and nothing at token level separates it from a real drop", - "line": 730 + "line": 754 }, { "id": "PHASE.REQ-LINE.SEAM.gap-checker-divergence", "klass": "PHASE", "value": "normalizePhaseReqIds (src/gap-checker.cts) is a SECOND parser of the same ROADMAP value and DIVERGES on four axes — ranges (expanded there, never here, deliberately per #3697) | placeholder vocabulary (whole trimmed value after stripping parens there, LEAD token here) | parentheses (stripped there, not here) | ID shape (PHASE_REQ_ID_SHAPE_RE is wider) — pinned in BOTH directions by #3697-17 rather than unified, because unifying would change what phase.complete MARKS; consequence is user-visible: RANGE-01..RANGE-05 reports 5 requirements to gap analysis and 0 to phase complete", - "line": 731 + "line": 755 }, { "id": "PHASE.REQ-LINE.SEAM.kinds", "klass": "PHASE", "value": "three, carried as a machine code BESIDE the prose, never instead of it — req-line-misparse (ID-shaped content demonstrably not selected) | req-line-range-reading (R2 alone fired on selected endpoints and NO RULE NAMED A DROPPED ID — rule-scoped, never line-global: an unselected parenthetical is carried by the skipped-text rider, not by this code — so the voice must NOT claim a parse failure; it defers to req-line-unverified when the cap left a token UNCLASSIFIED, which is narrower than 'a token past the cap' — a long token the SELECTOR ITSELF took can be exempt, so the condition is oversizedTokens being non-empty, never the mere presence of a long token — see SEAM.cap for the exemption's own rule) | req-line-unverified (a token past the cap: the line was not classified, which is not the same as clean); emitted as the additive result field requirements_line_warning, because warnings[] is a documented string[] rendered by execute-phase.md and re-typing its elements is a breaking output-contract change; ABSENT entirely on a clean line", - "line": 727 + "line": 751 }, { "id": "PHASE.REQ-LINE.SEAM.module", "klass": "PHASE", "value": "src/phase.cts owns the ROADMAP **Requirements**: line seam as TWO module-scope functions, extracted so the parser is directly testable (a closure inside cmdPhaseComplete is reachable only by spawning the CLI, which no fast-check property can do): analyzeRequirementsLine(rawLine) -> RequirementsLineAnalysis, formatRequirementsLineWarning(phaseNum,rawLine,analysis) -> {code,message}|null; both exported, plus REQ_LINE_WARNING_CODE", - "line": 724 + "line": 748 }, { "id": "PHASE.REQ-LINE.SEAM.placeholder", "klass": "PHASE", "value": "TBD/NONE as the LEAD token only, and R3b's non-empty test keys on VISIBLE content (a line of only zero-width/bidi/variation-selector codepoints is empty; an invisible INSIDE a token is decoration and R4 reports the drop); that gate — not the ID-shape gate — is what holds the whole #2334/#2339 negative space silent under R3b (measured: 15 of 15 fixtures held by non-zero selection or placeholderLed, 0 by ID shape)", - "line": 729 + "line": 753 }, { "id": "PHASE.REQ-LINE.SEAM.rules", "klass": "PHASE", "value": "R1 whole-token range | R2 spaced operator between two selected interior-implying endpoints | R2' operator glued to one endpoint | R3 zero selection with ID-shaped residue | R3b zero selection on any non-placeholder non-empty line (#3697 AC-1b/AC-4) | R4 an ID the selector dropped to DECORATION — the TRIGGER is exactly a glued ;/: at either end OR an embedded invisible, never styling: quotes/backticks/emphasis are TOLERATED around the id (shaved before the test) but do NOT fire on their own, so `**REQ-01**, REQ-02` and `**REQ-01**; REQ-02` are BOTH silent — plus outside any MATCHED parenthetical AND sharing a prefix with a SELECTED id (square brackets stripped as the selector strips them; parentheses deliberately NOT, they are the citation marker) | over-cap unclassified; warn is their disjunction, named rather than inlined in the return literal", - "line": 726 + "line": 750 }, { "id": "PHASE.REQ-LINE.SEAM.selector-identity", "klass": "PHASE", "value": "citedReqIds is BYTE-IDENTICAL to the pre-extraction expression and is the ONLY thing that reaches the ledger; every rule below adds to warnings[] and NOTHING else — a change that alters what phase.complete MARKS is out of this seam's contract, not a refinement of it", - "line": 725 + "line": 749 }, { "id": "PLANNING.PATH.PARITY.project-scope", "klass": "PLANNING", "value": ".planning/ (never .planning/projects/); mirror planning-workspace.cjs planningDir()", - "line": 708 + "line": 732 }, { "id": "PLANNING.PATH.SEAM.helpers", "klass": "PLANNING", "value": "helpers.planningPaths delegates to workspacePlanningPaths + resolveWorkspaceContext; precedence explicit-ws > env-ws > env-project > root", - "line": 709 + "line": 733 }, { "id": "PLANNING.PATH.SEAM.init-handlers", "klass": "PLANNING", "value": "[initExecutePhase, initPlanPhase, initPhaseOp, initMilestoneOp] consume helpers.planningPaths().planning (no direct relPlanningPath join)", - "line": 710 + "line": 734 }, { "id": "PR.3267.POSTMORTEM.recovery", "klass": "PR", "value": "[issue#3270 created, label approved-enhancement applied, PR reopened, body includes \"Closes #3270\", label no-changelog applied]", - "line": 685 + "line": 709 }, { "id": "PR.3267.POSTMORTEM.root-cause", "klass": "PR", "value": "[missing issue link, missing changeset/no-changelog]", - "line": 684 + "line": 708 }, { "id": "PRED.k320.canonical-source", "klass": "PRED", "value": "CONTRIBUTING.md L193-211", - "line": 786 + "line": 810 }, { "id": "PRED.k320.ci-enforcement", "klass": "PRED", "value": "scripts/changeset/lint.cjs", - "line": 792 + "line": 816 }, { "id": "PRED.k320.ci-paths-monitored", "klass": "PRED", "value": "bin/ gsd-core/ src/ agents/ commands/ hooks/ sdk/src/ sdk/prompts/", - "line": 793 + "line": 817 }, { "id": "PRED.k320.cure", "klass": "PRED", "value": "drop .changeset/--.md fragment ONLY", - "line": 788 + "line": 812 }, { "id": "PRED.k320.evidence", "klass": "PRED", "value": "PR #3302 merge-conflict against #3308 CHANGELOG.md row 2026-05-09", - "line": 795 + "line": 819 }, { "id": "PRED.k320.opt-out-label", "klass": "PRED", "value": "no-changelog", - "line": 791 + "line": 815 }, { "id": "PRED.k320.recovery", "klass": "PRED", "value": "open Removed-typed cleanup PR deleting only the redundant row", - "line": 794 + "line": 818 }, { "id": "PRED.k320.rule", "klass": "PRED", "value": "do not edit CHANGELOG.md in feature/fix/enhancement PRs", - "line": 787 + "line": 811 }, { "id": "PRED.k320.signal", "klass": "PRED", "value": "changelog-direct-edit-forbidden", - "line": 785 + "line": 809 }, { "id": "PRED.k320.tool", "klass": "PRED", "value": "npm run changeset -- --type --pr --body \"...\"", - "line": 789 + "line": 813 }, { "id": "PRED.k320.types", "klass": "PRED", "value": "Added|Changed|Deprecated|Removed|Fixed|Security", - "line": 790 + "line": 814 }, { "id": "PRED.k321.evidence", "klass": "PRED", "value": "PRs #3304/#3305 (2026-05-09): real Minor/Major findings in body, 0 threads", - "line": 801 + "line": 825 }, { "id": "PRED.k321.poll-shape", "klass": "PRED", "value": "parse pulls//reviews body AND graphql reviewThreads", - "line": 799 + "line": 823 }, { "id": "PRED.k321.resolution", "klass": "PRED", "value": "address in code; no GraphQL resolveReviewThread needed for body-only findings", - "line": 800 + "line": 824 }, { "id": "PRED.k321.shape", "klass": "PRED", "value": "CR posts \"[!CAUTION] outside the diff\" findings in review BODY, not in reviewThreads", - "line": 798 + "line": 822 }, { "id": "PRED.k321.signal", "klass": "PRED", "value": "cr-outside-diff-range-finding", - "line": 797 + "line": 821 }, { "id": "PRED.k322.cure-1", "klass": "PRED", "value": "2nd retrigger ~10min after first ack", - "line": 806 + "line": 830 }, { "id": "PRED.k322.cure-2", "klass": "PRED", "value": "if silent at 50min, treat as silent-pass with maintainer flag in merge-commit body", - "line": 807 + "line": 831 }, { "id": "PRED.k322.distinct-from", "klass": "PRED", "value": "k080", - "line": 804 + "line": 828 }, { "id": "PRED.k322.evidence", "klass": "PRED", "value": "PR #3306 (2026-05-09): 0 reviews after 50min + 2 retriggers", - "line": 809 + "line": 833 }, { "id": "PRED.k322.merge-gate-impact", "klass": "PRED", "value": "k070 real_coderabbit_review_present unsatisfied; requires maintainer judgment", - "line": 808 + "line": 832 }, { "id": "PRED.k322.shape", "klass": "PRED", "value": "ack posted, real review never lands within [5s, 410s] cooldown after burst of N PRs <15min", - "line": 805 + "line": 829 }, { "id": "PRED.k322.signal", "klass": "PRED", "value": "cr-sustained-throttle", - "line": 803 + "line": 827 }, { "id": "PRED.k323.cure-alt", "klass": "PRED", "value": "consolidate into single PR when 2+ issues share root cause", - "line": 814 + "line": 838 }, { "id": "PRED.k323.cure-pre-dispatch", "klass": "PRED", "value": "brief one agent canonical-owner; brief others to EXCLUDE shared site", - "line": 813 + "line": 837 }, { "id": "PRED.k323.evidence", "klass": "PRED", "value": "#3300 (#3297) overlapped #3306 (#3298) on add-backlog.md hunks 2026-05-09", - "line": 816 + "line": 840 }, { "id": "PRED.k323.recovery", "klass": "PRED", "value": "close smaller PR as \"subsumed by #N\" or rebase second to drop overlap hunk", - "line": 815 + "line": 839 }, { "id": "PRED.k323.shape", "klass": "PRED", "value": "2+ open issues touch same canonical bug site; each fix's sibling-audit produces overlapping diff", - "line": 812 + "line": 836 }, { "id": "PRED.k323.signal", "klass": "PRED", "value": "sibling-audit-cross-pr-overlap", - "line": 811 + "line": 835 }, { "id": "PRED.k324.cure", "klass": "PRED", "value": "verify via gh api on every agent-completion notification; never trust narrative", - "line": 820 + "line": 844 }, { "id": "PRED.k324.evidence", "klass": "PRED", "value": "2026-05-09 session: 5+ mid-monitor terminations across PRs #3232/#3271/#3251/#3255/#3262", - "line": 822 + "line": 846 }, { "id": "PRED.k324.k095-restatement", "klass": "PRED", "value": "k095 confirmed shape: agent reports \"waiting for monitor\" / \"tests still running\" then terminates", - "line": 819 + "line": 843 }, { "id": "PRED.k324.poll-shape", "klass": "PRED", "value": "gh pr view --json mergeStateStatus,statusCheckRollup + pulls//reviews + graphql reviewThreads + issues//comments tail", - "line": 821 + "line": 845 }, { "id": "PRED.k324.signal", "klass": "PRED", "value": "agent-terminates-mid-monitor", - "line": 818 + "line": 842 }, { "id": "PRED.k325.cleanup", "klass": "PRED", "value": "git worktree remove --force for aged agent worktrees", - "line": 827 + "line": 851 }, { "id": "PRED.k325.cure", "klass": "PRED", "value": "detached-HEAD: git checkout --detach $(git ls-remote origin ); modify; commit; git push --force-with-lease=: origin HEAD:refs/heads/", - "line": 826 + "line": 850 }, { "id": "PRED.k325.evidence", "klass": "PRED", "value": "2026-05-09 CHANGELOG.md strip on PRs #3300/#3302/#3304/#3305 required detached-HEAD", - "line": 828 + "line": 852 }, { "id": "PRED.k325.shape", "klass": "PRED", "value": "git checkout errors \"already used by worktree at \"", - "line": 825 + "line": 849 }, { "id": "PRED.k325.signal", "klass": "PRED", "value": "worktree-branch-lock-on-force-push", - "line": 824 + "line": 848 }, { "id": "PRED.k326.cure", "klass": "PRED", "value": "quote canonical doc verbatim in brief; mentally simulate \"if all N agents follow this brief literally, do they violate any rule?\"", - "line": 832 + "line": 856 }, { "id": "PRED.k326.evidence", "klass": "PRED", "value": "2026-05-09 brief \"k040 — update CHANGELOG.md\" → 5 of 8 agents violated CONTRIBUTING.md L110", - "line": 833 + "line": 857 }, { "id": "PRED.k326.shape", "klass": "PRED", "value": "N parallel agents amplify a single brief-vs-doc contradiction into N violations", - "line": 831 + "line": 855 }, { "id": "PRED.k326.signal", "klass": "PRED", "value": "brief-contradicts-canonical-doc", - "line": 830 + "line": 854 }, { "id": "PRED.k327.ack-shape", "klass": "PRED", "value": "body \"✅ Actions performed - Full review triggered\"", - "line": 836 + "line": 860 }, { "id": "PRED.k327.cooldown-normal", "klass": "PRED", "value": "[5s, 410s]", - "line": 839 + "line": 863 }, { "id": "PRED.k327.cooldown-throttled", "klass": "PRED", "value": "k322", - "line": 840 + "line": 864 }, { "id": "PRED.k327.distinguish-key", "klass": "PRED", "value": "len(pulls//reviews) — ack=0, real=≥1", - "line": 838 + "line": 862 }, { "id": "PRED.k327.real-review-shape", "klass": "PRED", "value": "body starts \"Actionable comments posted: N\" OR \"[!CAUTION] Some comments are outside the diff\"", - "line": 837 + "line": 861 }, { "id": "PRED.k327.signal", "klass": "PRED", "value": "cr-ack-vs-real-review", - "line": 835 + "line": 859 }, { "id": "PRED.k328.audit-list", "klass": "PRED", "value": "[heading-matches-class, closing-keyword-present, changeset-fragment-or-no-changelog-label]", - "line": 845 + "line": 869 }, { "id": "PRED.k328.canonical-source", "klass": "PRED", "value": "CONTRIBUTING.md L48,L64,L81 (template links) + .github/PULL_REQUEST_TEMPLATE/{fix,enhancement,feature}.md L1 (heading text)", - "line": 843 + "line": 867 }, { "id": "PRED.k328.k100-restatement", "klass": "PRED", "value": "heading must match issue class: bug→## Fix PR, enhancement→## Enhancement PR, feature→## Feature PR", - "line": 844 + "line": 868 }, { "id": "PRED.k328.signal", "klass": "PRED", "value": "pr-template-typed-heading-required", - "line": 842 + "line": 866 }, { "id": "PRED.k329.body", "klass": "PRED", "value": "**** — . (#)", - "line": 851 + "line": 875 }, { "id": "PRED.k329.canonical-source", "klass": "PRED", "value": "CONTRIBUTING.md L196-202 + .changeset/README.md", - "line": 848 + "line": 872 }, { "id": "PRED.k329.filename", "klass": "PRED", "value": ".changeset/--.md", - "line": 849 + "line": 873 }, { "id": "PRED.k329.frontmatter", "klass": "PRED", "value": "---\\\\ntype: \\\\npr: \\\\n---", - "line": 850 + "line": 874 }, { "id": "PRED.k329.observed-clean", "klass": "PRED", "value": "#3299 sunny-ibex-wave, #3301 sturdy-rams-caper, #3306 3298-phase-dir-prefix-drift-workflows", - "line": 852 + "line": 876 }, { "id": "PRED.k329.signal", "klass": "PRED", "value": "changeset-fragment-canonical-shape", - "line": 847 + "line": 871 }, { "id": "PRED.k330.fallback", "klass": "PRED", "value": "append predicate-format findings directly to CONTEXT.md", - "line": 856 + "line": 880 }, { "id": "PRED.k330.shape", "klass": "PRED", "value": "mempalace MCP tools require explicit user call; AI cannot trigger", - "line": 855 + "line": 879 }, { "id": "PRED.k330.signal", "klass": "PRED", "value": "mempalace-diary-not-callable-by-ai", - "line": 854 + "line": 878 }, { "id": "PRED.k331.cure", "klass": "PRED", "value": "gh pr close with NO --comment flag", - "line": 861 + "line": 885 }, { "id": "PRED.k331.evidence", "klass": "PRED", "value": "2026-05-09 wave-3: violation on #3300 close, deleted within 30s", - "line": 863 + "line": 887 }, { "id": "PRED.k331.k101-restatement", "klass": "PRED", "value": "k101 includes close-time --comment flag; rationale belongs in subsuming PR's squash-merge body", - "line": 860 + "line": 884 }, { "id": "PRED.k331.recovery", "klass": "PRED", "value": "if violation lands, gh api -X DELETE repos///issues/comments/", - "line": 862 + "line": 886 }, { "id": "PRED.k331.shape", "klass": "PRED", "value": "instruction \"close with no comment (rationale)\" — parenthetical is rationale, NOT comment body", - "line": 859 + "line": 883 }, { "id": "PRED.k331.signal", "klass": "PRED", "value": "close-with-no-comment-is-literal", - "line": 858 + "line": 882 }, { "id": "PROBE.ci.surface", "klass": "PROBE", "value": "the contract (parse/validate, projection round-trip, fail-closed guards), NEVER the LLM judgment (ADR-550 D5)", - "line": 595 + "line": 619 }, { "id": "PROBE.core.seam", "klass": "PROBE", "value": "analyzeCoverage(items,resolutions?,validators) ingests ALREADY-proposed items; does NOT assume deterministic propose (ADR-550 D7b)", - "line": 588 + "line": 611 }, { "id": "PROBE.edge.verification", "klass": "PROBE", "value": "explicit|backstop", - "line": 590 + "line": 613 }, { "id": "PROBE.family", "klass": "PROBE", "value": "edge-probe(shape-axis)+prohibition-probe(must-NOT-axis)+ui-consideration-probe(UI-state-axis), shared probe-core, run as spec-phase/ui-phase soft gates (ADR-550 D7; #1867)", - "line": 586 + "line": 609 }, { "id": "PROBE.item.axes", "klass": "PROBE", "value": "status{resolved|dismissed|unresolved} x verification{|null} — orthogonal; the lifecycle enum carries no verification fact (ADR-550 D7a)", - "line": 589 + "line": 612 }, { "id": "PROBE.principle", "klass": "PROBE", "value": "verifier-reach-equals-spec-reach (a goal-backward verifier only checks assertions that exist; probes make omitted assertions exist before code) — ADR-857 verification-substrate boundary; docs/design/verifier-reach.md", - "line": 585 + "line": 608 }, { "id": "PROBE.prohib.verification", "klass": "PROBE", "value": "test|judgment", - "line": 591 + "line": 614 }, { "id": "PROBE.protocol", "klass": "PROBE", "value": "recall(adversarial over-generate)->precision(drop routine-engineering); dismissals require a non-empty reason", - "line": 587 + "line": 610 }, { "id": "PROBE.ui.axis", "klass": "PROBE", "value": "MIXED — closed compiled shape-rooted 8 (empty/loading/error/populated/partial/overflow/zero-one-many/long-text) via ui-consideration-probe adapter; open UX (real-time/a11y/i18n-RTL) prose-owned in references/domain-probes.md, NOT compiled (#1867)", - "line": 593 + "line": 616 }, { "id": "PROBE.ui.seam", "klass": "PROBE", "value": "ui-phase Step 9.5 post-verification: element-cue classify -> propose-then-confirm (partial-cue mitigation, Goodhart) -> autoResolve --auto floor (never dismiss; unclassified stays unresolved #1110) -> ## UI Considerations write-back -> plan-phase `## UI Considerations` lift rule (#1867)", - "line": 594 + "line": 618 + }, + { + "id": "PROBE.ui.text_en", + "klass": "PROBE", + "value": "optional English translation of Element.text read by classification (text_en ?? text), engine input never user-facing output; mirrors the edge adapter's #3717 field; empty/whitespace/non-string fails closed (#4657)", + "line": 617 }, { "id": "PROBE.ui.verification", "klass": "PROBE", "value": "explicit|backstop", - "line": 592 + "line": 615 }, { "id": "PROC.AGENT-DISPATCH.completion-verify", "klass": "PROC", "value": "run k324.poll-shape on every agent-completion notification", - "line": 867 + "line": 891 }, { "id": "PROC.AGENT-DISPATCH.parallel-overlap-audit", "klass": "PROC", "value": "before dispatching N sibling-audit fixers, compute file-set union and assign canonical owners", - "line": 866 + "line": 890 }, { "id": "PROC.AGENT-DISPATCH.preflight", "klass": "PROC", "value": "[read-CONTRIBUTING.md-fresh, read-relevant-ADRs, cite-specific-line-in-brief, require-closing-keyword, require-changeset-fragment, forbid-CHANGELOG.md-edit, require-isolation-worktree, forbid-self-PR-comment, mandate-trust-but-verify]", - "line": 865 + "line": 889 }, { "id": "PROC.MERGE-WAVE.changelog-strip-pattern", "klass": "PROC", "value": "detached-HEAD per k325 + git checkout main -- CHANGELOG.md + commit + force-with-lease", - "line": 871 + "line": 895 }, { "id": "PROC.MERGE-WAVE.merge-tool", "klass": "PROC", "value": "gh pr merge --squash --delete-branch", - "line": 872 + "line": 896 }, { "id": "PROC.MERGE-WAVE.merge-tool-warning", "klass": "PROC", "value": "delete-branch may fail with \"used by worktree at\" — harmless; remote branch still deleted", - "line": 873 + "line": 897 }, { "id": "PROC.MERGE-WAVE.ordering", "klass": "PROC", "value": "[wave1: isolated-files, wave2: CHANGELOG-only-overlap (better: strip per k320), wave3: same-file-overlap with explicit decision]", - "line": 869 + "line": 893 }, { "id": "PROC.MERGE-WAVE.preflight", "klass": "PROC", "value": "gh pr view --json files for every PR; identify overlap pairs; surface to maintainer", - "line": 870 + "line": 894 }, { "id": "PROC.PARALLEL-FIX-DISPATCH.observed", "klass": "PROC", "value": "#3541 + #3542 dispatched simultaneously this session; PRs #3546 #3547 opened green; one syntax slip caught by AGENT-RETIRED-SLASH-SYNTAX-DRIFT and fixed before second PR opened", - "line": 952 + "line": 976 }, { "id": "PROC.PARALLEL-FIX-DISPATCH.pattern", "klass": "PROC", "value": "bot triage brief → worktree per branch → parallel sub-agents do rubber-duck/RCA/TDD implementation only → top-level orchestrator owns commit + gsd-test + push + PR + changeset-pr-backfill", - "line": 950 + "line": 974 }, { "id": "PROC.PARALLEL-FIX-DISPATCH.rationale", "klass": "PROC", "value": "long-running test runs need cross-turn notifications (orchestrator-only); CONTRIBUTING.md gh-templates-first hook requires session-scoped Read calls sub-agents wouldn't otherwise make; sequencing test runs avoids GSD-TEST-CONCURRENT-OUTPUT-COLLISION", - "line": 951 + "line": 975 }, { "id": "PROC.TRIAGE.comment-shape", "klass": "PROC", "value": "lead with \"duplicate of #NNNN, fixed by PR #MMMM, in v1.X.Y\"; show current code snippet proving bug-surface gone; give @latest and @next upgrade commands; close", - "line": 955 + "line": 979 }, { "id": "PROC.TRIAGE.no-duplicate-label", "klass": "PROC", "value": "this repo has no duplicate label; framing lives in comment text + closing the issue", - "line": 956 + "line": 980 }, { "id": "PROC.TRIAGE.routing-incoming", "klass": "PROC", "value": "stale-bug-already-fixed to close as duplicate of originating issue + cite fix PR + first stable tag; release-publish-or-backport to ready-for-human; reporter-can-self-test to awaiting-retest", - "line": 954 + "line": 978 }, { "id": "PROHIB.canon-referral", "klass": "PROHIB", "value": "OWASP/GDPR/fairness-canon are REFERRED to /gsd:secure-phase+eslint, never minted as prohibitions (ADR-550 D6)", - "line": 597 + "line": 621 }, { "id": "PROHIB.descriptor.shape", "klass": "PROHIB", "value": "5 FLAT scalars (check_kind,check_target,check_rule,check_violation_fixture,check_clean_fixture) — NEVER a nested check:{} (parseMustHavesBlock is a flat parser, src/frontmatter.cts)", - "line": 602 + "line": 626 }, { "id": "PROHIB.enforce.adr", "klass": "PROHIB", "value": "docs/adr/1606-prohibition-enforcement-verify-seam.md (verify-time enforcement seam) + docs/adr/550-spec-phase-probe-contract.md (spec-phase contract)", - "line": 605 + "line": 629 }, { "id": "PROHIB.enforce.causation", "klass": "PROHIB", "value": "clean-fixture control proves the red is content-caused not env-var-set; MANDATORY for node-test (#1906 supersedes #1346 opt-in) — absent clean-fixture ⇒ node-test un-provable/fail-closed; lint-rule needs none (its subject IS the linted file)", - "line": 601 + "line": 625 }, { "id": "PROHIB.enforce.failfirst", "klass": "PROHIB", "value": "MACHINE-PROVEN against an author-supplied violation fixture (#1279); caller failFirst attestation DEMOTED to a non-authoritative hint (FF-08)", - "line": 600 + "line": 624 }, { "id": "PROHIB.enforce.green-rule", "klass": "PROHIB", "value": "passed iff provenFailFirst===true && run.passed===true (runProhibitionEnforcement); every miss/fail/un-provable HARD-GATES both modes via dispositionForProhibition's fail-closed default", - "line": 598 + "line": 622 }, { "id": "PROHIB.enforce.kinds", "klass": "PROHIB", "value": "node-test (non-vacuous red via isNonVacuousNodeTestRed; pass-side vacuity via isNonVacuousNodeTestPass) | lint-rule (eslint --format json filtered by ruleId)", - "line": 599 + "line": 623 }, { "id": "PROHIB.judgment-tier", "klass": "PROHIB", "value": "never-silent / never-hard-halt soft gate; autonomous emits \"unverified-prohibition — human review recommended\" (exogenous grading, ADR-550 D4)", - "line": 604 + "line": 628 }, { "id": "PROHIB.rail", "klass": "PROHIB", "value": "core verify rail, non-toggleable (ADR-857 verification-substrate boundary / decision #6); the verifier<->predicate contract is NOT an off-by-default capability", - "line": 603 + "line": 627 }, { "id": "PROHIB.recall", "klass": "PROHIB", "value": "LLM-prose; no compiled prohibition-probe recall engine (only the schema/projection layer is code, ADR-550 D7b)", - "line": 596 + "line": 620 }, { "id": "RELEASE-NOTES.ANTI-PATTERN", "klass": "RELEASE-NOTES", "value": "raw \"What's Changed\" PR list as final body for hotfix or feature release; \"Full Changelog only\" body for tagged release with >0 user-facing fixes", - "line": 762 + "line": 786 }, { "id": "RELEASE-NOTES.ANTI-PATTERN.implementation-first", "klass": "RELEASE-NOTES", "value": "do not lead bullet with file path or function name; lead with symptom/user-visible behavior", - "line": 763 + "line": 787 }, { "id": "RELEASE-NOTES.ANTI-PATTERN.risk-commentary", "klass": "RELEASE-NOTES", "value": "do not include \"may break\", \"be careful\", \"test thoroughly\" - release notes state what changed, not hedges about what might go wrong", - "line": 764 + "line": 788 }, { "id": "RELEASE-NOTES.DEFAULT-STATE", "klass": "RELEASE-NOTES", "value": "auto-generated body is \"What's Changed\" PR list + Full Changelog link; treat as draft, not final", - "line": 738 + "line": 762 }, { "id": "RELEASE-NOTES.EXAMPLE.hotfix", "klass": "RELEASE-NOTES", "value": "v1.41.1 (https://github.com/open-gsd/gsd-core/releases/tag/v1.41.1) - 14 fixes grouped by 6 subgroups", - "line": 766 + "line": 790 }, { "id": "RELEASE-NOTES.EXAMPLE.minor-auto-acceptable", "klass": "RELEASE-NOTES", "value": "v1.41.0 - kept auto-generated body; many small fixes with clean conventional-commit titles", - "line": 768 + "line": 792 }, { "id": "RELEASE-NOTES.EXAMPLE.rc", "klass": "RELEASE-NOTES", "value": "v1.7.0-rc.1 (https://github.com/open-gsd/gsd-core/releases/tag/v1.7.0-rc.1) - intro + Added/Changed/Fixed/Documentation taxonomy", - "line": 767 + "line": 791 }, { "id": "RELEASE-NOTES.GATE.hotfix", "klass": "RELEASE-NOTES", "value": "manual edit required; auto-generated body for vX.Y.{Z>0} is \"Full Changelog only\" and must be replaced with structured body", - "line": 739 + "line": 763 }, { "id": "RELEASE-NOTES.GATE.minor", "klass": "RELEASE-NOTES", "value": "auto-generated body acceptable when PR titles are clean; promote to structured body when >20 PRs or contains feature+refactor+fix mix", - "line": 741 + "line": 765 }, { "id": "RELEASE-NOTES.GATE.rc", "klass": "RELEASE-NOTES", "value": "manual edit recommended; auto-generated PR list is acceptable for early RCs but final RC before vX.Y.0 should match standard", - "line": 740 + "line": 764 }, { "id": "RELEASE-NOTES.RELEASE-STREAM.main-branch", "klass": "RELEASE-NOTES", "value": "next (RCs) + latest (stable); install via @next or @latest", - "line": 773 + "line": 797 }, { "id": "RELEASE-NOTES.RELEASE-STREAM.rule", "klass": "RELEASE-NOTES", "value": "streams do not mix; do not document @next in hotfix/stable notes", - "line": 774 + "line": 798 }, { "id": "RELEASE-NOTES.SCOPE", "klass": "RELEASE-NOTES", "value": "GitHub Releases body for tags vX.Y.Z, vX.Y.Z-rc.N; not CHANGELOG.md (changeset workflow owns that)", - "line": 737 + "line": 761 }, { "id": "RELEASE-NOTES.SOURCE.changesets", "klass": "RELEASE-NOTES", "value": ".changeset/*.md (frontmatter pr: + body bullets)", - "line": 753 + "line": 777 }, { "id": "RELEASE-NOTES.SOURCE.commits", "klass": "RELEASE-NOTES", "value": "git log .. --pretty=format:'%s%n%n%b' --no-merges", - "line": 752 + "line": 776 }, { "id": "RELEASE-NOTES.SOURCE.pr-bodies", "klass": "RELEASE-NOTES", "value": "gh pr view --json title,body for fixes lacking a changeset", - "line": 754 + "line": 778 }, { "id": "RELEASE-NOTES.SOURCE.precedence", "klass": "RELEASE-NOTES", "value": "changeset body > commit body > PR body > commit subject (prefer authored content over auto-generated)", - "line": 755 + "line": 779 }, { "id": "RELEASE-NOTES.STANDARD.bullet-shape", "klass": "RELEASE-NOTES", "value": "**Bold user-visible change** — explanation of what was broken or what's new, leading with symptom not implementation. Trailing (#NNN) PR ref.", - "line": 745 + "line": 769 }, { "id": "RELEASE-NOTES.STANDARD.footer.full-changelog", "klass": "RELEASE-NOTES", "value": "**Full Changelog**: https://github.com/open-gsd/gsd-core/compare/...", - "line": 749 + "line": 773 }, { "id": "RELEASE-NOTES.STANDARD.footer.hotfix", "klass": "RELEASE-NOTES", "value": "Install/upgrade: \\`npx @opengsd/gsd-core@latest\\`", - "line": 747 + "line": 771 }, { "id": "RELEASE-NOTES.STANDARD.footer.rc", "klass": "RELEASE-NOTES", "value": "Install for testing: \\`npx @opengsd/gsd-core@next\\` (per branch->dist-tag policy)", - "line": 748 + "line": 772 }, { "id": "RELEASE-NOTES.STANDARD.heading-level", "klass": "RELEASE-NOTES", "value": "## for category, ### for subgroup (area), - for bullet", - "line": 744 + "line": 768 }, { "id": "RELEASE-NOTES.STANDARD.intro", "klass": "RELEASE-NOTES", "value": "optional one-paragraph framing for RC/feature releases; omit for pure-fix hotfixes", - "line": 750 + "line": 774 }, { "id": "RELEASE-NOTES.STANDARD.subgroups", "klass": "RELEASE-NOTES", "value": "phase-planning-state | workstream | query-dispatch-cli | code-review | install | capture | docs | architecture | security", - "line": 746 + "line": 770 }, { "id": "RELEASE-NOTES.STANDARD.taxonomy", "klass": "RELEASE-NOTES", "value": "Keep-a-Changelog 1.1.0: Added | Changed | Deprecated | Removed | Fixed | Security | Documentation", - "line": 743 + "line": 767 }, { "id": "RELEASE-NOTES.TEMPLATE.hotfix", "klass": "RELEASE-NOTES", "value": "## Fixed\\n\\n### \\n- **** — . (#)\\n\\n---\\n\\nInstall/upgrade: \\`npx @opengsd/gsd-core@latest\\`\\n\\n**Full Changelog**: ", - "line": 770 + "line": 794 }, { "id": "RELEASE-NOTES.TEMPLATE.rc", "klass": "RELEASE-NOTES", "value": "\\n\\n## Added\\n### \\n- **** — . (#)\\n\\n## Changed\\n### Architecture\\n- **** — . (#)\\n\\n## Fixed\\n### \\n- **** — . (#)\\n\\n## Documentation\\n- **** — . (#)\\n\\n---\\n\\nThis is a release candidate. Install for testing:\\n\\`\\`\\`bash\\nnpx @opengsd/gsd-core@next\\n\\`\\`\\`\\n\\n**Full Changelog**: ", - "line": 771 + "line": 795 }, { "id": "RELEASE-NOTES.WORKFLOW.edit", "klass": "RELEASE-NOTES", "value": "gh release edit --notes-file ", - "line": 757 + "line": 781 }, { "id": "RELEASE-NOTES.WORKFLOW.idempotency", "klass": "RELEASE-NOTES", "value": "gh release edit overwrites body wholesale; safe to re-run after refining", - "line": 760 + "line": 784 }, { "id": "RELEASE-NOTES.WORKFLOW.token", "klass": "RELEASE-NOTES", "value": "must use .envrc GITHUB_TOKEN per RULESET.GH.AUTH.DEFAULT (this doc); never ambient gh auth", - "line": 759 + "line": 783 }, { "id": "RELEASE-NOTES.WORKFLOW.view", "klass": "RELEASE-NOTES", "value": "gh release view --json body --jq .body", - "line": 758 + "line": 782 }, { "id": "RULESET.ADR-HEADER", "klass": "RULESET", "value": "every docs/adr/NNNN-*.md must open with - **Status:** Accepted|Proposed|Superseded (by [ADR-NNNN](file.md))|Legacy + - **Date:** YYYY-MM-DD immediately after title", - "line": 652 + "line": 676 }, { "id": "RULESET.AGENT_SIZE_BUDGET", "klass": "RULESET", "value": "agent-size-budget (#1074; sibling of WORKFLOW_SIZE_BUDGET; BYTES not lines per #717/#683, rebased from lines in PR 3/3) = differential attribution size ratchet (PRIMARY anti-creep since #2724/ADR-2719 §4, same mechanism and same `Emitted-Drift-Ack-Growth:` commit trailer (ADR-3942, superseding ADR-2719 §3's fragment model) as WORKFLOW_SIZE_BUDGET, scoped to agents/gsd-*.md) + loose tier hard caps (red lines, never raised on approach: XL<=57344 / LARGE<=49152 / DEFAULT<=24576); net-new agents are DEFAULT-tier (no separate new-file cap). Sizes are measured via the shared scripts/workflow-size.cjs measureMdFiles(dir,predicate) counter (tests/helpers/emitted-runtime.cjs's currentSizes() and the guard's own tier-cap checks both import it). A grown agent fails the differential guard — ack + justify, or extract LAZILY to gsd-core/references/. DISTINCT from DEFECT.AGENT-FILE-SIZE-CAP-BREACH (a separate 45K-CHAR extraction-evidence threshold on gsd-planner via planner-decomposition/reachability tests): that guard proves mode-sections were extracted; this one bounds total agent bytes. Two guards, two units (chars vs bytes), two purposes. The prior per-file baseline (tests/agent-size-baseline.json, `npm run size:baseline`) is REMOVED by #2724", - "line": 641 + "line": 665 }, { "id": "RULESET.ALLOWED-TOOLS-FRONTMATTER", "klass": "RULESET", "value": "command's allowed-tools must cover every tool the workflow calls (including Write for file creation); thin-wrapper pattern makes this easy to miss", - "line": 648 + "line": 672 }, { "id": "RULESET.ARGUMENTS-SANITIZE", "klass": "RULESET", "value": "any workflow step constructing .planning/.../{SLUG}.md path from user input ($ARGUMENTS, parsed remainder) must sanitize inline ([a-z0-9-] only, reject ..//\\\\, max-length) — \"(already sanitized)\" must trace back to explicit guard; RESUME/fallback modes need own guards", - "line": 649 + "line": 673 }, { "id": "RULESET.AUDIT.search-source-not-generated", "klass": "RULESET", "value": "verify an invariant/validation EXISTS by searching the AUTHORED source (src/*.cts OR the scripts/gen-*.cjs generator), never the generated bin/lib/*.cjs (gitignored, ADR-457); gen-time checks live in gen-*.cjs not the .cts it consumes → search BOTH before declaring absent; read generated .cjs only for output drift. Repro: grep src/*.cts for VALID_CONVERTER_NAMES → false \"5e ConverterName unenforced\"; actually enforced in gen-capability-registry.cjs. cf RULESET.TESTS.no-source-grep", - "line": 637 + "line": 661 }, { "id": "RULESET.CAPABILITY.cutover-self-gating", "klass": "RULESET", "value": "a phase-6 per-feature cutover moves the host's phase-context detection + mode/flag logic INTO the skill (self-gating, per ADR-894); the loop hook is intentionally COARSE — \"invoke skill X at point Y when config Z\" — and carries no detection/mode. WORKED EXAMPLE: plan-phase.md §5.6 UI gate (frontend-detection via ui-safety-gate.cjs + --auto/manual branch + --skip-ui bypass) must move into gsd-ui-phase before its plan:pre hook can replace the inline call without behavior loss. Spike #1018 finding.", - "line": 411 + "line": 434 }, { "id": "RULESET.CAPABILITY.off-means-off", "klass": "RULESET", "value": "the host derives shared outputs from the ACTIVE hook set (via loop.render-hooks); a hook may ADD a labeled block or be COUNTED into a host-computed aggregate (e.g. a score denominator), but NEVER mutates host source — so a disabled capability yields the base output by construction, not by authoring discipline. Ratify in ADR-894; proven by spike #1018.", - "line": 409 + "line": 432 }, { "id": "RULESET.CAPABILITY.precedence-engine-single-owner", "klass": "RULESET", "value": "the config-key four-level precedence walk (loadConfig result → workstream config.json → root config.json → registry.configSchema default → absent) is owned solely by src/capability-activation.cts: raw-value primitive resolveConfigKey(dotKey, {config,cwd,registry}) and boolean wrapper _resolveActivationValue(dotKey,config,cwd,registry); loop-resolver.cts imports the engine (no duplicate); resolveConfigValues in loop-resolver.cts delegates to resolveConfigKey; resolveCapabilityRuntimeState does NOT return registry/config — callers import capability-registry.cjs and call loadConfig(cwd) directly. #3661 adds a THIRD export from the same engine, _resolvePointGate(pointFrom,point,config,cwd,registry): a step's optional pointFrom field names a dotted enum config key; the step is active for its own `point` only when that key resolves to a value === point (found:false or a type/value mismatch → false). loop-resolver.cts's isActive and capability-state.cts's processHooks both call it (ANDed with the existing when gate) so a capability can register the same logical step at more than one loop point with config selecting which registration is live — see capabilities/code-review/capability.json's execute:post/execute:wave:post pair for the reference shape. capability-validator.cjs's validateAgainstContract requires pointFrom to reference an enum cap.config key whose values include the declaring step's own point (mirrors the pre-existing when-must-be-a-cap.config-key check for `when`).", - "line": 415 + "line": 438 }, { "id": "RULESET.CAPABILITY.step-additive-gate-blocks", "klass": "RULESET", "value": "a `step` hook is purely additive (invoke skill + produce artifacts, NEVER halts the host); host-blocking preconditions are `gate`s (blocking:true, onError:halt); runtime/mode context (auto/chain vs manual) self-gates IN THE SKILL, not via `when` (config-only). §5.6 = plan:pre step (ui-phase; skill self-gates on frontend+pipeline, auto-fires only in pipelines) + a NEW plan:pre gate (frontend-and-no-UI-SPEC → halt, when:workflow.ui_safety_gate); the loop.render-hooks dispatch template handles steps AND gates. Resolves #1022.", - "line": 413 + "line": 436 }, { "id": "RULESET.CODERABBIT.GUARD.COMPLETE", "klass": "RULESET", "value": "required_checks_green && coderabbit_check_pass && graphQL(reviewThreads.unresolved_count)==0", - "line": 674 + "line": 698 }, { "id": "RULESET.CODERABBIT.GUARD.GRAPHQL", "klass": "RULESET", "value": "reviewThreads(first:100){nodes{id isResolved comments{nodes{author body path line originalLine url}}}}; use unresolved threads as authoritative, not badge text alone", - "line": 675 + "line": 699 }, { "id": "RULESET.CODERABBIT.GUARD.OPEN_PRS", "klass": "RULESET", "value": "gh pr list --repo open-gsd/gsd-core --author @me --state open; repeat near end because open PR set can change mid-run", - "line": 673 + "line": 697 }, { "id": "RULESET.CODERABBIT.GUARD.RERUN", "klass": "RULESET", "value": "after every push wait for CodeRabbit completion, then re-query unresolved threads; CodeRabbit can add new findings after earlier threads were resolved", - "line": 676 + "line": 700 }, { "id": "RULESET.CODERABBIT.GUARD.RESOLVE", "klass": "RULESET", "value": "fix validated finding -> focused tests -> commit/push -> resolveReviewThread(threadId) -> wait CI/CodeRabbit -> final unresolved_count query", - "line": 677 + "line": 701 }, { "id": "RULESET.CODERABBIT.GUARD.SCOPE", "klass": "RULESET", "value": "if a new @me open PR appears during final list, include it in the same guard pass before declaring all-open-PRs complete", - "line": 678 + "line": 702 }, { "id": "RULESET.CONTENT-PATH-NORMALIZATION", "klass": "RULESET", "value": "filesystem paths substituted into markdown body text (@-references, workflow .md, agent .md, generated docs, command bodies) MUST be normalized to POSIX forward slashes via .replace(/\\\\/g,'/') at the production source BEFORE substitution; never push normalization to tests; cross-platform content is POSIX-only; applies to: computePathPrefix output, install-path rewrites, generated shim paths emitted into .md bodies; idempotent on POSIX so unconditional; mechanically enforced by local/normalize-path-in-content (eslint, src/**/*.cts; #1733)", - "line": 889 + "line": 913 }, { "id": "RULESET.CONTRIB.CLASSIFY.enhancement", "klass": "RULESET", "value": "requires approved-enhancement before implementation", - "line": 667 + "line": 691 }, { "id": "RULESET.CONTRIB.CLASSIFY.feature", "klass": "RULESET", "value": "requires approved-feature before implementation", - "line": 668 + "line": 692 }, { "id": "RULESET.CONTRIB.CLASSIFY.fix", "klass": "RULESET", "value": "requires confirmed-bug before implementation (legacy 'confirmed' label is back-compat only for duplicate-sweep exemption, not a valid implementation gate)", - "line": 666 + "line": 690 }, { "id": "RULESET.CONTRIB.GATE.ORDER", "klass": "RULESET", "value": "issue-first -> approval-label -> code -> PR-link -> changeset/no-changelog", - "line": 665 + "line": 689 }, { "id": "RULESET.CR-THREAD-RESOLVE", "klass": "RULESET", "value": "after adding // allow-test-rule: to silence lint, resolve existing inline CR threads via graphql resolveReviewThread mutation before merge — open threads mislead future reviewers; pattern: gh api graphql -f query='mutation { resolveReviewThread(input:{threadId:\"PRRT_...\"}) { thread { isResolved } } }'", - "line": 659 + "line": 683 }, { "id": "RULESET.EMITTED_ATTRIBUTION", "klass": "RULESET", "value": "the emitted-artifact family (ADR-2719, epic #2719) — POST-CUTOVER (#2724, Phase 4). Historically tests/fixtures/golden-install-parity/*.json (19 path→hash manifests) + tests/workflow-size-baseline.json + tests/agent-size-baseline.json were all committed, PURE FUNCTIONS of the source tree whose correct merge was ALWAYS \"recompute\" — 140 of 143 conflicted-file instances across the open PR queue were these files. #2724 DELETES all three, the golden test (tests/golden-install-parity.test.cjs), the generator (scripts/gen-golden-install-parity-zcode.cjs), `npm run gen:golden`, `UPDATE_GOLDEN`, the merge-driver bridge (scripts/git-merge-regen-driver.cjs, `npm run setup:merge-driver`, the .gitattributes merge=gsd-regen block), and scripts/update-size-baseline.cjs (`npm run size:baseline`). The differential attribution check (tests/emitted-attribution.test.cjs + tests/emitted-provenance.test.cjs) is now the SOLE gate for emitted-artifact propagation AND size growth — no committed artifact, nothing to hand-merge, nothing to regenerate. `npm run regen:derived` still exists for what remains committed and derived: build, registry, ADR index, capability matrix, inventory manifest, manifest versions, and `tests/fixtures/install-tree/*.json` (now `npm run gen:install-tree`, folded into `regen:derived`). tests/fixtures/install-tree/*.json is DELIBERATELY EXCLUDED from the cutover (ADR-2719 §7): it conflicts on 0 of 7, its diffs are readable, and it preserves \"the installer stopped shipping X\" as a hard absolute failure — capturing it would convert that absolute into an attribution-free auto-resolve. The baseline the differential compares against is now published by `scripts/gen-emitted-baseline.cjs` on every push to `next` (cached, keyed on sha) and restored in PR lanes via `GSD_EMITTED_BASELINE`/`resolveBaseline()` (tests/helpers/emitted-baseline.cjs); a cache miss falls back to an in-job build via a throwaway `git worktree` (tests/helpers/emitted-runtime.cjs's `buildBaselineAtRef`). REMEDIATION IS PART OF THE GATE (#2778): the failure output names its own remedy, because a gate that states a requirement and withholds the means of satisfying it is a maintainer round-trip, not a gate — ADR-2719 §3's \"conspicuous declaration\" only works if the contributor can discover how to make it. Both failing branches name the commit trailer to add — `Emitted-Drift-Ack-Hash:` or `Emitted-Drift-Ack-Growth:` (ADR-3942) — print its exact grammar (` — `, key and reason split on the FIRST em dash), and repeat \"do NOT regenerate anything\" — post-#2724 there is nothing left to regenerate, and hunting for a deleted baseline is the predictable wrong guess. The two branches key on DIFFERENT, now STRUCTURALLY DISTINCT trailer key spaces (separate maps since ADR-3942, closing a latent defect where a growth key could satisfy a hash lookup by naming coincidence and vice versa) and each says which: the hash pass keys on the EMITTED PATH (always contains a `/`, `Emitted-Drift-Ack-Hash:`), the size ratchet keys on the BARE FILENAME (`Emitted-Drift-Ack-Growth:`; `currentSizes` writes `sizes[entry.name]` from readdirSync over `gsd-core/workflows/` + `agents/`). A stale-ack failure additionally says to drop the trailer line (amending the commit) when removing its last entry, since a lingering unused trailer signals nothing; post-#2789 it also offers CORRECTING the reason to name the ripple actually made, which is the other honest resolution and the one a contributor usually wants. NOT ack-able and deliberately given no ack text: the `NEW_FILE_CAP` branch, whose remedy is extraction. Text is sourced from one frozen `REMEDIATION` export in tests/helpers/emitted-diff.cjs, whose example line is rendered via `renderAckTrailer` (`: — `, ADR-3942) so the taught grammar cannot drift from what `parseAckTrailers` actually accepts (a round-trip test feeds the printed line back through the parser); a key that is reserved (`__proto__`/`constructor`/`prototype`) or contains `<`, `>`, or whitespace is rejected loudly, and a doc example like ` — ` must never parse as a real declaration. Note the ADR's Consequences originally called the #2724 migration \"terminal\"; #2778 corrected that — it is terminal only for a PR that grows no shipped file. The ack was PR-lifetime data kept in permanent, shared, merge-path state, and each fix generated the next defect until ADR-3942 moved it off the tree entirely (see `### Emitted Artifact Provenance`): the single shared `tests/emitted-drift-ack.json` was a guaranteed merge-conflict cell (#2789; 5 of 6 conflicting PRs in one open queue collided on it and nothing else); #2914 replaced it with per-PR fragments under `tests/emitted-drift-acks/` — the `.changeset/` shape — ending the FILE conflict but not the KEY conflict, since two sources could never name the same path; #3078 found a fully-spent fragment left on `next` still walled off every key it owned (measured at the sweep: 45 fragments owning 403 paths, up from 13/272 at triage 19 days earlier) and added the post-merge-only `guard-no-ack-on-next` job plus a manual sweep; #3842's hand sweep handed three in-flight external PRs a `modify/delete` conflict each; #3823's hand-authored sweep, computed at branch time against a guard that evaluates at merge time, lost the race to a fragment merged mid-flight and left `next` red for 24 consecutive pushes; #3875's timed sweeper workflow automated the remedy but could not merge its own PRs (three independent, deterministic defects — bad conventional-title match, wrong CI-lane classification, no auto-merge path). ADR-3942 ends the chain: the escape hatch is now a commit trailer scoped to the PR's own commits, so there is no shared file, no shared key namespace, and nothing to sweep — the fragment directory, the next-lane guard job, the scheduled sweep workflow and the standalone ack linter are all DELETED (named by ROLE rather than by filename on purpose: a backticked path here asserts a LIVE repo path and `check-glossary-refs.cjs` fails on one that does not exist, while `lint-removed-but-needed.cjs` additionally fails on a deleted file's bare BASENAME appearing anywhere it scans — and this predicate's generated projection lands in docs/, which it does scan. ADR-3942 carries the exact paths; it sits under docs/adr/, which that guard exempts as a historical record). cf `RULESET.WORKFLOW_SIZE_BUDGET`, `RULESET.AGENT_SIZE_BUDGET`; see `### Emitted Artifact Provenance`", - "line": 642 + "line": 666 }, { "id": "RULESET.GENERATIVE-FIX", "klass": "RULESET", "value": "parallel implementations diverge silently when no parity test enforces equality at the test layer; for any new constant/array/parser shared between two parallel surfaces (two workflow surfaces, or a generated artifact and its hand-authored source), the same commit MUST add a parity assertion that fails when the two diverge; exemplar: tests/runtime-launcher-parity.test.cjs (asserts every workflow bash block uses the canonical gsd_run launcher)", - "line": 887 + "line": 911 }, { "id": "RULESET.GH.AUTH.DEFAULT", "klass": "RULESET", "value": "source .envrc GITHUB_TOKEN before gh; exception=ambient allowed only when user explicitly says machine-only fallback", - "line": 672 + "line": 696 }, { "id": "RULESET.HARNESS.test-memory-guard", "klass": "RULESET", "value": "~/.claude/hooks/test-memory-guard.sh fires on every Bash PreToolUse; if argv[0]∈{node|vitest|jest|mocha|tsx|ts-node|tap|ava|playwright|cypress} OR matches (npm|pnpm|yarn|bun) (run )?(t|test|tests|vitest|jest); blocks via hookSpecificOutput.permissionDecision=deny when sum(RSS of running matching procs, excluding tsserver|*-mcp|claude|Electron|...) ≥ 4 GiB OR when argv[0] basename matches a running process's argv[0]. Exception: node --version|-v|--help|-h|-p|-e are trivial probes and skip the check. Designed for a 24 GB Mac where prior accidental fan-out exhausted RAM", - "line": 931 + "line": 955 }, { "id": "RULESET.MANIFEST-CANONICAL-KEY", "klass": "RULESET", "value": "docs/INVENTORY-MANIFEST.json has a single top-level key: families; ALL EIGHT families.* arrays (agents/commands/workflows/references/cli_modules/hooks flat, plus workflow_modes/workflow_steps nested — #2996, epic #1671 Phase 6.5) are canonical, consumed by test suites — tests/inventory-manifest-sync.test.cjs reads all eight, edit-phase/enh-2380/enh-2430 tests read commands+workflows; the six flat families are keyed by BARE BASENAME while the two nested families are keyed by // path, deliberately, because two workflows may each own a same-named step file and a basename key would silently drop one under a JSON-equality comparison; recursion is bounded at exactly one named subdirectory, never a general walk; the family tables live ONCE in scripts/gen-inventory-manifest.cjs and are IMPORTED by the test (the test formerly redeclared them, a DEFECT.GENERATIVE-FIX divergence that let a new family be verified by nobody while still reporting green); the old generated date field and the stale top-level workflows key are both gone; regen via node scripts/gen-inventory-manifest.cjs --write, AFTER build:lib; #3762 added the ROSTER half — tests/inventory-manifest-sync.test.cjs now also asserts every manifest entry has a hand-written row in docs/INVENTORY.md, via the pure matcher in tests/helpers/inventory-roster.cjs. Scope is the SIX FLAT families only, each searched inside its own `## ` section; workflow_steps/workflow_modes are DELIBERATELY exempt because docs/INVENTORY.md §\"Workflow Sub-Files\" is a shipped decision that they carry no hand-written per-file rows. Matching is whole-CELL-exact (never substring — the rostered host-integration-adapters/imperative-hook-bus.cjs must not satisfy the separate top-level hook-bus.cjs) and section-scoped (smart-entry.md and smart-entry.cjs are different families), EXCEPT commands, which match on the row's Source-column link to ../commands/gsd/.md because the six ns-* namespace routers deliberately RENDER a name that is not their file stem (/gsd-workflow ← ns-workflow.md) — DEFECT.DISPLAY-VALUE-AS-IDENTITY. Landing the gate required backfilling 32 pre-existing unrostered surfaces on next", - "line": 653 + "line": 677 }, { "id": "RULESET.PR-FLOW.docker-before-push", "klass": "RULESET", "value": "before ANY git push of any fix to any PR, run gsd-test (docker on the remote, mirrors ubuntu CI) and confirm exit 0. macOS-local node --test is NOT a substitute — many failures are platform-specific (path separators, case sensitivity, locale, fs semantics). Watchdog with Monitor on the output log; never set a sleep/timer and walk away. Source: user feedback 2026-05-16 — \"we don't set a timer we actively watch and record results in real time as possible\". SUPERSEDED 2026-07-17: 'confirm exit 0' is a false-green trap — piping/backgrounding can report exit 0 on a failed suite; gate on the verdict-line outcome:\"passed\" for the exact HEAD sha instead. See CLAUDE.md's gsd-test rule and the gsd-test-is-ref-based-commit-first predicate for the current, correct gating contract.", - "line": 933 + "line": 957 }, { "id": "RULESET.PR-FLOW.templates-mandatory", "klass": "RULESET", "value": "every gh pr create|edit|gh issue create|edit MUST first invoke the gh-templates-first skill and Read (Read tool, not Bash cat — k321 read-tracking) the matching template in .github/. Apply ALL required sections; never write freeform bodies. Repo enforces this via gsd-pr-template-policy GitHub Action which flags any non-templated body — the bot allows the PR to stay open only because authors are contributors-or-higher, but the warning is a real complaint that must be cured. Source: user feedback 2026-05-16 (multi-message escalation) — \"the whole reason i have that github action is because you fucking blow through and ignore using the templates\"", - "line": 935 + "line": 959 }, { "id": "RULESET.PR-SCOPE.one-concern-per-pr", "klass": "RULESET", "value": "split unrelated changes into separate PRs; cherry-pick doc changes to dedicated docs/ branch immediately, then force-push original to remove the commit", - "line": 655 + "line": 679 }, { "id": "RULESET.SHARED-HELPERS-LINT-VS-TEST", "klass": "RULESET", "value": "when a lint script and test suite both implement same constant (CANONICAL_TOOLS) or parser (parseFrontmatter, executionContextRefs), extract to scripts/*-helpers.cjs required by both — silent divergence otherwise", - "line": 650 + "line": 674 }, { "id": "RULESET.TESTS.CODERABBIT_FIX", "klass": "RULESET", "value": "prefer exported-function behavioral tests over source-grep; lint-no-source-grep rejects readFileSync source assertions without allow-test-rule", - "line": 679 + "line": 703 }, { "id": "RULESET.TESTS.boundary-coverage", "klass": "RULESET", "value": "tests MUST exercise inputs at and near the threshold/limit, not only trivial-fit and trivial-overflow; pick inputs where N ∈ {limit-1, limit, limit+1} and where pre-trim/pre-check accumulators ≈ effective limit; \"very small\" and \"very large\" inputs alone do not constitute edge-case coverage and routinely miss off-by-one + reservation-accounting bugs", - "line": 622 + "line": 646 }, { "id": "RULESET.TESTS.boundary-coverage.anti-pattern", "klass": "RULESET", "value": "test suites that pair budget:1_000_000 (trivially fits) with budget:1 (trivially overflows) and skip the boundary region; failure mode that shipped PR #3708 UNNEEDED_TRIM + FALSE_HARDFAIL regressions (commit 2df566ed, fixed bde1ae8f)", - "line": 625 + "line": 649 }, { "id": "RULESET.TESTS.boundary-coverage.fixtures", "klass": "RULESET", "value": "for any code with budget/limit/quota/threshold parameter, test suite MUST include: (a) input where SUT estimate == limit exactly, (b) input where estimate == limit - 1, (c) input where estimate == limit + 1, (d) input where any internal reserve/safety constant pushes baseline within reserve-distance of limit (catches early-pressure firing)", - "line": 624 + "line": 648 }, { "id": "RULESET.TESTS.clock-seam", "klass": "RULESET", "value": "concurrency logic must accept an optional {clock=Date} parameter; tests control time via t.mock.timers.enable(['Date']) + t.mock.timers.setTime(0) + t.mock.timers.tick(N); real OS scheduler races are not a permitted test pattern after ADR 456 (2026-05-28); real-race tests are deleted once deterministic seam tests cover the same logical path; clock.cjs realClock adds nowIso() (→ new Date(this.now()).toISOString()) and today() (→ nowIso().split('T')[0]) so all date-stamping in state.cjs routes through the seam; subprocess time-pin adapter: set GSD_TEST_MODE=1 + GSD_NOW_MS= in runGsdTools env to pin the date written by the SUT without touching real wall-clock (issue #474)", - "line": 629 + "line": 653 }, { "id": "RULESET.TESTS.coderabbit-fix-prefer", "klass": "RULESET", "value": "behavioral tests (call exported fn, capture JSON, assert typed fields) over source-grep", - "line": 620 + "line": 644 }, { "id": "RULESET.TESTS.delete-bad-tests", "klass": "RULESET", "value": "pass-always / vacuous-truth / source-grep / elapsed-time / real-race / permanent-allow-test-rule tests are DELETED and replaced with compliant tests in the same PR; not skipped, not commented out, not permanently exempted; replacement must cover the same logical path via typed-surface assertion or clock-seam pattern", - "line": 634 + "line": 658 }, { "id": "RULESET.TESTS.diagnostics", "klass": "RULESET", "value": "after JSON.parse, assert output shape (Array.isArray(output.phases)) with raw-output-prefix diagnostics before .map() — prevents opaque TypeErrors when CLI output shape changes", - "line": 621 + "line": 645 }, { "id": "RULESET.TESTS.escape-regex", "klass": "RULESET", "value": "new RegExp(\"prefix${var}\") must escapeRegex(var); phase-id.cjs exports escapeRegex (core.cjs re-export spine retired in epic #1267); phase IDs like 5.1 contain . which is metacharacter", - "line": 617 + "line": 641 }, { "id": "RULESET.TESTS.eslint-harness", "klass": "RULESET", "value": "ADR 452 (2026-05-28): ESLint flat config + typescript-eslint + eslint-plugin-n + eslint-plugin-no-only-tests + local plugin at eslint-rules/ (repo root, NOT scripts/eslint-rules/); replaces scripts/lint-*.cjs regex scanners (fully removed in #632); all three test-rigor rules now ship at error in tests/**/*.test.cjs scope: local/no-source-grep and local/no-magic-sleep-in-tests promoted by #3313, local/no-elapsed-assertion promoted by #3331 once #3314 delivered its ADR-456 §(a) precondition (epic #1885 was subsumed into epic #3053 and closed stale before this promotion landed)", - "line": 635 + "line": 659 }, { "id": "RULESET.TESTS.feedback-loop-convergence", "klass": "RULESET", "value": "when a feature's OUTPUT feeds back into its own INPUT (calibration, retry backoff, adaptive budgets, ratchets, any self-correcting signal), step-wise tests are NOT sufficient evidence of correctness: they assert `given X return Y` while the defect lives in the TRAJECTORY across iterations. Required: a closed-loop test that (a) drives the REAL end-to-end surface — not the pure core alone, since composition bugs live between surfaces — for N >= 2x the loop's window, (b) asserts convergence on the known-true value, (c) asserts the fixed point (an already-correct history must produce NO correction), and (d) asserts boundedness under an adversarial/oscillating history. Two defects shipped past a green ~26,800-test suite in epic #1952 for want of exactly this: calibration applied twice across two surfaces (factor^2, #2631) and calibration measured against its own corrected output so it oscillated to ~1.41 instead of converging on 2.0 (#2632). Every unit, boundary, property and round-trip test passed for both. HOW TO SPOT ONE (the detection tell, not a judgment call): the feature's own acceptance criterion carries a TEMPORAL QUANTIFIER — \"after N phases\", \"subsequent\", \"over time\", \"improves\", \"learns\", \"adapts\". That phrasing means the claim is about a TRAJECTORY, so a step-wise `given X return Y` test does not test the claim that was made. #1952's AC4 read \"After N phases, the error is computed and applied as a correction to SUBSEQUENT estimates\" — the tell was in plain sight and was still tested as a point. Survey of this repo (2026-07): estimation calibration is the ONLY true instance; size/mutation ratchets are exempt because they fail on both growth AND shrinkage (cannot self-satisfy), and retry ladders (node_repair_budget, plan_bounce_passes, provider_escalation) terminate rather than feed back. Test anchor: tests/estimate-loop-convergence.test.cjs", - "line": 623 + "line": 647 }, { "id": "RULESET.TESTS.guard-toplevel-readFileSync", "klass": "RULESET", "value": "module-level const src = readFileSync(...) throws before any test() registers — wrap in try/catch in test() or use lazy load", - "line": 619 + "line": 643 }, { "id": "RULESET.TESTS.mutation-runner", "klass": "RULESET", "value": "Stryker executes every shard through the OFFICIAL @stryker-mutator/tap-runner (testRunner:'tap'), never the built-in 'command' runner (#3915); 'command' is the one runner Stryker excludes from coverage analysis, which forced coverageAnalysis:'off' and made cost strictly linear in (mutants x whole-shard test time) — the frontmatter shard measured 1751s on run 33021042847 vs 212s for the next slowest. tap.testFiles is injected per shard via MUTATION_TEST_FILES (mutation.yml env <- matrix.tests <- scripts/mutation-matrix.cjs buildResult); resolveMutationTestFiles is the SINGLE fail-closed reader and existence-checks every entry, because the tap runner's findTestyLookingFiles resolves the list with glob() and a non-matching pattern yields an EMPTY list SILENTLY (a fast, confident, meaningless run). tap.forceBail is FALSE by measurement, not preference: 3 of 26 shard test files spawn subprocesses (config-schema.property, core-utils, feat-3881-yaml-parser-consequences) and bail fires on every KILLED mutant, so leaving it on kills processes mid-spawnSync and orphans their children; Stryker's separate disableBail still skips remaining FILES, which is most of the win. tap.nodeArgs and top-level buildCommand stay UNSET so no rebuild lands between mutation and test (ADR-457). Coverage granularity is per FILE, not per test (\"a test is always a test file\"), so the #2790 excludeTests bans on spawn-heavy integration files remain necessary and unchanged", - "line": 632 + "line": 656 }, { "id": "RULESET.TESTS.mutation-score", "klass": "RULESET", "value": "Stryker runs incremental (--since origin/next) on ubuntu-latest/Node24 CI leg; default threshold 80% killed/total; surviving mutants in scope block merge unless path is listed in stryker.config.mjs with documented reason; treat surviving mutant as a failing test specification", - "line": 631 + "line": 655 }, { "id": "RULESET.TESTS.mutation-score-denominator", "klass": "RULESET", "value": "the gated number is mutation-testing-metrics' mutationScore = totalDetected/totalValid, which counts NoCoverage in the denominator EXACTLY as Survived; both Stryker's own thresholds.break (core dist/src/reporters/mutation-test-report-helper.js) and scripts/check-mutation-score-ratchet.cjs read THAT field, which is what makes the #3915 coverageAnalysis 'off'->'perTest' switch score-neutral. NEVER gate on mutationScoreBasedOnCoveredCode — it EXCLUDES NoCoverage and inflates sharply under perTest (measured on a synthetic report: 8 killed/2 survived = 80 and 80; 8 killed/2 noCoverage = 80 and 100), so swapping to the better-sounding field would make every minScore floor trivially satisfiable and the gate decorative. Under the pre-#3915 coverageAnalysis:'off' the two fields were ALWAYS identical (noCoverage was structurally 0), which is why nothing had ever pinned the choice; tests/mutation-score-ratchet.test.cjs now pins it with a non-vacuity assertion that the two numbers genuinely diverge", - "line": 633 + "line": 657 }, { "id": "RULESET.TESTS.no-dead-regex-in-includes", "klass": "RULESET", "value": "src.includes(\"foo.*bar\") is always false — .* is regex metacharacter not wildcard; use new RegExp(...).test(src) or delete", - "line": 618 + "line": 642 }, { "id": "RULESET.TESTS.no-duplicate-fold-marker", "klass": "RULESET", "value": "local/no-duplicate-fold-marker ESLint AST rule (eslint-rules/no-duplicate-fold-marker.cjs, #3271) reports the 2nd and every later __foldDescribe(\"folded: ...\") call carrying a marker already seen in the SAME file, naming the first occurrence's line; error in tests/**/*.cjs. The key is the WHITESPACE-delimited token after folded:, NOT a [a-z0-9-]* slice — a slice truncates at \".\" and collides feat-443-effort-fast-mode.integration with feat-443-effort-fast-mode (two distinct suites coexisting in tests/model-resolver.test.cjs), and NOT the whole title, so a re-fold under a different batch label (\"B1 #1970\" vs \"B5 #1975\") is still caught. Deliberately silent on: a __foldDescribe title with no folded: prefix (the alias is reused for one ordinary describe in tests/review-default-reviewers-workflow.test.cjs), a plain describe(), a non-literal title, and the same marker in two DIFFERENT files (the defect class is intra-file).", - "line": 614 + "line": 638 }, { "id": "RULESET.TESTS.no-duplicate-fold-marker.why", "klass": "RULESET", "value": "consolidation epic #1969 folds are self-contained blocks, so a second verbatim copy parses, registers and PASSES twice — nothing reports it; #3271 found 25 such copies (~5,800 lines) in tests/install.test.cjs (18), tests/install-minimal-hooks.test.cjs (5) and tests/install-write-confinement.test.cjs (2), all from one stale-base re-application in 6d072435d (#1975 re-applying #1970's hunks, 2026-07-03). Ref DEFECT.GENERATIVE-FIX: the two copies drift apart silently when a contributor fixes one and leaves the other asserting the old behavior, with the suite still green.", - "line": 615 + "line": 639 }, { "id": "RULESET.TESTS.no-source-grep", "klass": "RULESET", "value": "local/no-source-grep ESLint AST rule (eslint-rules/no-source-grep.cjs) rejects readFileSync of a source .cjs/.js/.ts path bound to a var later hit with .includes()/.match()/.startsWith()/.endsWith()/.indexOf()/.search(); error in tests/**/*.test.cjs, warn in gsd-core/bin/**/*.cjs + scripts/**/*.cjs (ADR 452 retired the old regex script, removed for good in #632)", - "line": 611 + "line": 635 }, { "id": "RULESET.TESTS.no-source-grep.exemption", "klass": "RULESET", "value": "// allow-test-rule: with one-line justification; reserved for tests where the file content IS the product surface (STATE.md, config.toml, hooks.json, agent .md). Migration to typed-IR parser tracked in #2974.", - "line": 612 + "line": 636 }, { "id": "RULESET.TESTS.no-source-grep.tmp-file-traps", "klass": "RULESET", "value": "reading tmp files written by the SUT in tests still trips lint; round-trip through CLI (e.g. frontmatter get) instead of readFileSync+.includes()", - "line": 613 + "line": 637 }, { "id": "RULESET.TESTS.no-timing-assertion", "klass": "RULESET", "value": "do not assert on wall-clock elapsed time (Date.now() delta, performance.now(), process.hrtime() comparison); such assertions test the host machine not the SUT and flake on loaded CI runners; enforcement: local/no-elapsed-assertion ESLint rule, error (promoted by #3331 once #3314 delivered the ADR-456 §(a) reachability rule + deterministic backfill precondition); canonical replacement: clock-seam pattern with node:test mock.timers", - "line": 628 + "line": 652 }, { "id": "RULESET.TESTS.property-based-testing", "klass": "RULESET", "value": "modules implementing parsing / transformation / budget-limit / bijective contracts must include at least one fast-check (fc) property test asserting a domain invariant; invariant categories: round-trip, monotonicity, boundary-containment, idempotency; property tests live in *.test.cjs alongside unit tests; CI signal: Stryker mutation score below 80% blocks merge", - "line": 630 + "line": 654 }, { "id": "RULESET.TRIAGE-EXISTING-WORK", "klass": "RULESET", "value": "before writing agent brief for confirmed bug, check (1) local branches git branch -a | grep , (2) untracked/modified files on that branch, (3) stash, (4) open PRs with matching head branch — recover existing work rather than re-implement", - "line": 657 + "line": 681 }, { "id": "RULESET.WORKFLOW.COVERAGE-METADATA", "klass": "RULESET", "value": "#1602 SUMMARY frontmatter `coverage:` block (list of {id,description,requirement?,verification:[{kind∈unit|integration|e2e|automated_ui|manual_procedural|other, ref, status∈pass|fail|unknown}],human_judgment:bool,rationale?}) is the per-deliverable RTM consumed DETERMINISTICALLY by verify-work extract_tests via `gsd-tools uat classify-coverage --summary ` (src/coverage.cts → bin/lib/coverage.cjs). AUTHORING: execute-plan create_summary populates it from task results; every deliverable MUST be classified; fail-safe default = human_judgment:true + rationale. CLASSIFY CONTRACT: auto-pass (skip human) ONLY when human_judgment===false (strict boolean) AND verification non-empty AND every status==='pass' AND zero validation errors — else PRESENT to human. mode:legacy (no block) ⇒ byte-identical prose `## Accomplishments` fall-through; `coverage: []` ⇒ mode:coverage, zero entries (single-confirmation). Frozen IR: MODE/PRESENT_REASON/ERROR_CODE enums locked by tests/coverage-metadata-parser.test.cjs. extractFrontmatter CANNOT parse it (scalars-only `-` items) → dedicated parser, sibling of parseMustHavesBlock. Asymmetry by design: false-negative=redundant prompt (status quo); false-positive=shipped bug UAT existed to catch", - "line": 646 + "line": 670 }, { "id": "RULESET.WORKFLOW_EXECUTE_END_TO_END", "klass": "RULESET", "value": "standard for single-workflow commands is \"Execute end-to-end.\" (no bolded **Follow the X workflow** fragments); flag-dispatch routing uses \"execute the X workflow end-to-end.\" in routing bullets — convention verified live across ~20 commands/gsd/*.md files; no ADR currently documents this specific phrasing rule (ADR-0002 covers the adjacent but distinct command-contract/@-ref-resolution seam, not this convention)", - "line": 645 + "line": 669 }, { "id": "RULESET.WORKFLOW_EXECUTION_CONTEXT", "klass": "RULESET", "value": "@-ref in commands/gsd/*.md must resolve to an existing file on disk; regression test in tests/docs-update.test.cjs (folds former \\`bug-3135-capture-backlog-workflow\\`, consolidation epic #1969); INVENTORY.md row + INVENTORY-MANIFEST.json families.workflows must stay in sync; \"Invoked by\" attribution must move when a flag absorbs a micro-skill", - "line": 644 + "line": 668 }, { "id": "RULESET.WORKFLOW_FILE_NAMES", "klass": "RULESET", "value": "workflow files use hyphens; XML attributes must match (extract-learnings not extract_learnings); tests should pin exact hyphenated name", - "line": 643 + "line": 667 }, { "id": "RULESET.WORKFLOW_MARKDOWN.FENCES", "klass": "RULESET", "value": "preserve opening language fence when editing shell snippets in workflow markdown; malformed fence creates fresh CR threads (MD040)", - "line": 639 + "line": 663 }, { "id": "RULESET.WORKFLOW_SIZE_BUDGET", "klass": "RULESET", "value": "workflow size enforcement (#1074; BYTES not lines per #717; LF-normalized per #683) = differential attribution size ratchet (PRIMARY anti-creep since #2724/ADR-2719 §4: tests/emitted-attribution.test.cjs's real-tree test reports growth in any gsd-core/workflows/*.md with its exact byte delta vs `next`, no committed snapshot, requires an `Emitted-Drift-Ack-Growth:` commit trailer on the PR's own commits (ADR-3942, superseding ADR-2719 §3's fragment model — key is the bare filename, reason follows ` — `)) + loose tier hard caps (outer red lines, NEVER raised on approach: XL<=98304 / LARGE<=61440 / DEFAULT<=40960) + discuss-phase<32000; a file that grew fails the differential guard — add an ack entry naming the file and reason, justify the growth in the PR (or extract LAZILY-loaded content; eager @-imports don't reduce loaded context); crossing a hard cap means EXTRACT, not bump. The prior per-file baseline (tests/workflow-size-baseline.json, `npm run size:baseline`) is REMOVED by #2724. Its new-file cap (ADR-1610 Decision point 3, un-baselined files <=32768, the Codex anchor) is REVIVED inside the differential's size ratchet itself (`NEW_FILE_CAP` in tests/helpers/emitted-diff.cjs) rather than lost: \"not yet baselined\" is exactly \"present in sizeCurrent, absent from sizeBaseline\", a signal the ratchet already computes for its own reasons. NOT ack-able — same as the tier hard caps, the fix is extraction. Narrower than the original: this check cannot see XL/LARGE tiering (tests/workflow-size-budget.test.cjs's classification, invisible to the pure differential module), so a legitimately large NEW file must extract rather than tier in, one release earlier than an existing file would need to — a disclosed, deliberate simplification", - "line": 640 + "line": 664 }, { "id": "SEAM.capability-activation-precedence-owner.enforced-by", "klass": "SEAM", "value": "test:tests/capability-precedence-parity.test.cjs", - "line": 417 + "line": 440 }, { "id": "SEAM.capability-activation-precedence-owner.owns", "klass": "SEAM", "value": "the config-key four-level precedence walk (loadConfig result → workstream config.json → root config.json → registry.configSchema default → absent), owned solely by src/capability-activation.cts", - "line": 416 + "line": 439 }, { "id": "SEAM.git-query-readonly-seam.enforced-by", "klass": "SEAM", "value": "test:tests/git-base-branch.test.cjs", - "line": 209 + "line": 227 }, { "id": "SEAM.git-query-readonly-seam.owns", "klass": "SEAM", "value": "bounded, never-throw git repository introspection — base-branch detection, worktree-info detection, phase change-set detection", - "line": 208 + "line": 226 }, { "id": "SEAM.package-identity.enforced-by", "klass": "SEAM", "value": "test:tests/package-identity.test.cjs", - "line": 286 + "line": 304 }, { "id": "SEAM.package-identity.owns", "klass": "SEAM", "value": "GSD's published-package coordinates (packageName, binName, repoSlug, changelogRawUrl, manualInstallCommand) — single seam so a repoint/rename is a one-line change", - "line": 285 + "line": 303 }, { "id": "SEAM.phase-locator-milestone-enum.enforced-by", "klass": "SEAM", "value": "test:tests/phase-locator.test.cjs", - "line": 39 + "line": 45 }, { "id": "SEAM.phase-locator-milestone-enum.owns", "klass": "SEAM", "value": "listMilestonePhaseDirs(phasesDir, opts) is the single canonical owner of milestone-scoped phase-directory enumeration (ADR-3180 Decision 1, Phase 3, #3185)", - "line": 38 + "line": 44 }, { "id": "SEAM.shellcmdproj-win-binary-resolution.enforced-by", "klass": "SEAM", "value": "lint-rule:no-private-binary-resolution", - "line": 898 + "line": 922 }, { "id": "SEAM.shellcmdproj-win-binary-resolution.owns", "klass": "SEAM", "value": "Windows binary resolution (resolveExecutableBinary, projectSpawnInvocation) — which file a declared command name actually names, and cmd.exe mediation", - "line": 897 + "line": 921 }, { "id": "SEAM.verification-isphasecomplete.enforced-by", "klass": "SEAM", "value": "test:tests/verification-status.test.cjs", - "line": 30 + "line": 36 }, { "id": "SEAM.verification-isphasecomplete.owns", "klass": "SEAM", "value": "isPhaseComplete(phaseDir, deps?) is the single canonical owner of \"is phase P complete?\" (ADR-3180 §7.4, issue #3186)", - "line": 29 + "line": 35 }, { "id": "SEAM.worktree-safety-policy.enforced-by", "klass": "SEAM", "value": "test:tests/worktree-safety.test.cjs", - "line": 707 + "line": 731 }, { "id": "SEAM.worktree-safety-policy.owns", "klass": "SEAM", "value": "Worktree Safety Policy Module — resolveWorktreeContext, parseWorktreePorcelain, planWorktreePrune, executeWorktreePrunePlan, W017 classification (see WORKTREE.SEAM.* above for full interface/invariant detail)", - "line": 706 + "line": 730 }, { "id": "SESSION.2026-05-05", "klass": "SESSION", "value": "[PRED.k320..k331 introduced; DEFECT.SOURCE-GREP-IN-NEW-TESTS, DEFECT.CHANGESET-PR-FIELD-DRIFT, DEFECT.PHASE-DIR-PREFIX-DRIFT, DEFECT.PROMPT-INJECTION-SCAN-COLLISION; ADR-0002 thin-wrapper pattern findings folded into RULESET.WORKFLOW_*]", - "line": 921 + "line": 945 }, { "id": "SESSION.2026-05-05.sdk-bridge", "klass": "SESSION", "value": "PR #3158 SDK Runtime Bridge — observability isolation rule; strict-mode dispatchMode reporting invariant; transport decision ordering (guard before event emission); folded into Dispatch Policy Module glossary", - "line": 922 + "line": 946 }, { "id": "SESSION.2026-05-09", "klass": "SESSION", "value": "[8-PR triage wave, 7 merged + 1 subsumed; META.RULE.* introduced; WAVE.LESSON.* captured; k320/k322/k323/k326/k331 evidence; AI Ops Memory predicate format established]", - "line": 923 + "line": 947 }, { "id": "SESSION.2026-05-10", "klass": "SESSION", "value": "[ai-ops memory consolidation; release-notes standard taxonomy + templates; RELEASE-NOTES.* predicates introduced]", - "line": 924 + "line": 948 }, { "id": "SESSION.2026-05-13", "klass": "SESSION", "value": "[Shell Command Projection Module expansion (#3465-#3468); ADR-0009 superseded; new exports for subprocess dispatch and platform file I/O; phase-gated migration plan; PR #3464 three-gate invariant CI+CR+unresolved=0; PR #3470 stash-include-untracked rebase pattern]", - "line": 925 + "line": 949 }, { "id": "SESSION.2026-05-14", "klass": "SESSION", "value": "[#3095/PR #3490 EXEC.CLASSIFY.* introduced (Anthropic/Copilot/Codex/Gemini [runtime removed #1928] cross-runtime rate-limit sentinel coverage); #3489/PR #3499 DEFECT.STATE-TRAMPLE.idempotency-oracle (STATE.md current_phase field is oracle for state.complete-phase); #3488/PR #3501 DAG resolver same-phase short-form depends_on (shortFormToId index added to sdk/src/query/phase.ts); #3491/PR #3502 DEFECT.NESTED-GIT-INIT (gitWorktreeInfoInternal helper); #3493/PR #3500 extractCurrentMilestone generic Phase Details continuation past planned-milestone siblings; #3503/PR #3504 DEFECT.PATH-SUBSTRING-CHECK (trailing-slash anchor for homedir checks); #3346/PR #3505 codex AoT TOML leaf-key via extractFlatHookEventName; #3506/PR #3507 label-scoped stale-bot sub-job pattern; multi-PR triage operational lessons folded into PROC.TRIAGE.*; #3508 DEFECT.AGENT-ISOLATION-SILENT-FAIL; gsd-test image-missing auto-build (locally-built image via embedded heredoc Dockerfile); refined PRED.k322 threshold to 3 PRs/<10min]", - "line": 926 + "line": 950 }, { "id": "SESSION.2026-05-15", "klass": "SESSION", "value": "[#3537/PR #3538 DEFECT.PHASE-REGEX-FANOUT — phaseMarkdownRegexSource promoted to core.cjs and wired to 7 sites; parity-style regression test established as DEFECT.GENERATIVE-FIX exemplar; trek-e/gsd-test-runner#1 filed for DEFECT.GSD-TEST-MIRROR-POISONED — chown-back-before-exec legacy gap (poisoned holodeck mirror unstuck via authorized docker chown to remote 1000:1000); RULESET.PR-FLOW.* codified from project CLAUDE.md load-bearing rule; first dispatch under run-tests-before-create held cleanly (PR #3520 worker stopped on Docker exit 12 infra failure, orchestrator opened PR after unblock); CONTEXT.md refactored from 882 lines of mixed prose+predicates into ~500 lines of pure-predicate format with chronological session log]", - "line": 927 + "line": 951 }, { "id": "SESSION.2026-05-15.parallel-fix-dispatch", "klass": "SESSION", "value": "[#3542/PR #3546 prohibit git stash family in executor agents (shared refs/stash across worktrees); #3541/PR #3547 non-TTY resolution for installer prompt-user actions (default remove for SDK build artifacts, keep for skills/gsd-*/SKILL.md); #3545 filed for gsd-test-summary concurrent /tmp output collision; new predicates DEFECT.HOOK-OVER-ENFORCEMENT.read-tool-tracking, DEFECT.GSD-TEST-CONCURRENT-OUTPUT-COLLISION, DEFECT.SUBAGENT-LONG-RUNNING-BG-STALL, DEFECT.AGENT-RETIRED-SLASH-SYNTAX-DRIFT, PROC.PARALLEL-FIX-DISPATCH; agent-trust-but-verify caught /gsd-update retired-syntax comment slip in #3541 implementation before PR open]", - "line": 928 + "line": 952 }, { "id": "SESSION.2026-05-16", "klass": "SESSION", "value": "[multi-PR triage wave (#3577/3581/3640/3641/3642/3648/3649/3637/3639). Established global PreToolUse hook ~/.claude/hooks/test-memory-guard.sh denying new node/test spawns when sum(RSS of node|vitest|jest|...) >= 4 GiB on the 24 GB Mac OR when a same-runner process is already in argv[0] — hard deny via hookSpecificOutput.permissionDecision=deny. PR #3577 fix: revert config-ensure-section dispatch to CJS cmdConfigEnsureSection (SDK author wrote single-section semantics under a name whose legacy callers expect full-default config init); plus 3 SDK parity carve-outs (configNewProject defaults align with sdk/shared/config-defaults.manifest.json, return relative .planning/config.json path, drop quotes from Unknown config key, lead malformed-JSON error with \"Failed to read config.json:\"). PR #3649 fix: chunk node --test spawn at 28K argv ceiling (Windows CreateProcess lpCommandLine cap 32,767 was instantly aborting unchunked spawn of 546 paths). Chunking fix surfaced 14 pre-existing Windows-only test bugs (4010 pass / 14 fail; vs 0/0 before — entire suite was un-runnable on Windows). PRs #3639 + #3637 confirmed unable to stand alone (legitimately depend on Phase 6 scaffolding only present on feat/3575-enforcement-hardening) — user decision: cherry-pick into #3577 and close. Five other PRs each had ≤1 unresolved CR thread of the changeset-pr-number / null-vs-throw / implicit-Claude-runtime / docs-stale-guidance / hardcoded-tests-path family — all quick wins. New predicates: DEFECT.SDK-PORT-NAME-COLLISION, DEFECT.WINDOWS-ARGV-OVERFLOW, DEFECT.STACKED-PR-CANNOT-STAND-ALONE, DEFECT.CANARY-VERSION-LEAK, DEFECT.GSD-TEST-HOST-MID-RUN-DEATH, RULESET.HARNESS.test-memory-guard, RULESET.PR-FLOW.docker-before-push, RULESET.PR-FLOW.templates-mandatory]", - "line": 929 + "line": 953 }, { "id": "WAVE.LESSON.agent-narrative-unreliable", "klass": "WAVE", "value": "k095/k324 confirmed at scale: 5 of 8 agents terminated mid-monitor with stale claims requiring direct verification", - "line": 880 + "line": 904 }, { "id": "WAVE.LESSON.changelog-policy-violation-multiplier", "klass": "WAVE", "value": "brief contradicting CONTRIBUTING.md's changelog-fragment policy (\"CHANGELOG Entries — Drop a Fragment\" section) produced violations on 5 of 8 PRs (#3300, #3302, #3304, #3305, #3308); k326 + k320 capture", - "line": 877 + "line": 901 }, { "id": "WAVE.LESSON.cr-throttle-burst-correlation", "klass": "WAVE", "value": "8 PRs in <15min triggered k322 sustained-throttle on multiple PRs (#3306 worst case)", - "line": 878 + "line": 902 }, { "id": "WAVE.LESSON.k101-still-trips", "klass": "WAVE", "value": "even after CONTEXT.md k101 reinforcement, agent of record posted self-PR comment on close; k331 adds explicit close-time literal-instruction guard", - "line": 881 + "line": 905 }, { "id": "WAVE.LESSON.sibling-audit-overlap", "klass": "WAVE", "value": "k015-family parallel dispatch on #3297 + #3298 produced k323 add-backlog.md cross-PR overlap", - "line": 879 + "line": 903 }, { "id": "WORKSTREAM.INVARIANT.migrate-name", "klass": "WORKSTREAM", "value": "must normalize through canonical slug policy", - "line": 693 + "line": 717 }, { "id": "WORKSTREAM.INVARIANT.slug-contract", "klass": "WORKSTREAM", "value": "all .planning/workstreams/ must be addressable by set/get/status/complete", - "line": 694 + "line": 718 }, { "id": "WORKSTREAM.NAME.POLICY.cjs-module", "klass": "WORKSTREAM", "value": "gsd-core/bin/lib/workstream-name-policy.cjs owns toWorkstreamSlug + active-name/path-segment validation", - "line": 711 + "line": 735 }, { "id": "WORKSTREAM.POINTER.SEAM.cjs-module", "klass": "WORKSTREAM", "value": "gsd-core/bin/lib/active-workstream-store.cjs owns read/write self-heal for .planning/active-workstream", - "line": 712 + "line": 736 }, { "id": "WORKSTREAM.REGRESSION.test-anchor", "klass": "WORKSTREAM", "value": "tests/workstream.test.cjs::normalizes --migrate-name to a valid workstream slug", - "line": 695 + "line": 719 }, { "id": "WORKTREE.SEAM.caller-rule", "klass": "WORKTREE", "value": "verify.cjs must consume inspectWorktreeHealth for W017 classification; no ad-hoc porcelain parsing in callers", - "line": 703 + "line": 727 }, { "id": "WORKTREE.SEAM.current", "klass": "WORKTREE", "value": "Worktree Safety Policy Module", - "line": 687 + "line": 711 }, { "id": "WORKTREE.SEAM.decision-1", "klass": "WORKTREE", "value": "retain non-destructive default; destructive path only as explicit future opt-in scaffold", - "line": 691 + "line": 715 }, { "id": "WORKTREE.SEAM.default-prune-policy", "klass": "WORKTREE", "value": "metadata_prune_only (non-destructive)", - "line": 690 + "line": 714 }, { "id": "WORKTREE.SEAM.files", "klass": "WORKTREE", "value": "[gsd-core/bin/lib/worktree-safety.cjs]", - "line": 688 + "line": 712 }, { "id": "WORKTREE.SEAM.interface", "klass": "WORKTREE", "value": "[resolveWorktreeContext, parseWorktreePorcelain, planWorktreePrune, executeWorktreePrunePlan, planWorktreeRecordAgent, cmdWorktreeRecordAgent]", - "line": 689 + "line": 713 }, { "id": "WORKTREE.SEAM.invariant", "klass": "WORKTREE", "value": "parser failure must degrade to metadata_prune_only and never escalate to destructive removal", - "line": 701 + "line": 725 }, { "id": "WORKTREE.SEAM.inventory-interface", "klass": "WORKTREE", "value": "[listLinkedWorktreePaths, inspectWorktreeHealth]", - "line": 702 + "line": 726 }, { "id": "WORKTREE.SEAM.inventory-snapshot", "klass": "WORKTREE", "value": "snapshotWorktreeInventory(repoRoot,{staleAfterMs,nowMs}) is canonical linked-worktree health snapshot for callers", - "line": 705 + "line": 729 }, { "id": "WORKTREE.SEAM.test-anchor-w017", "klass": "WORKTREE", "value": "tests/orphan-worktree-detection.test.cjs + tests/worktree-safety.test.cjs", - "line": 704 + "line": 728 }, { "id": "WORKTREE.SEAM.test-anchors", "klass": "WORKTREE", "value": "[resolveWorktreeContext:has_local_planning|linked_worktree|not_git_repo|main_worktree, planWorktreePrune:git_list_failed|worktrees_present|no_worktrees|parser_throw_fallback, executeWorktreePrunePlan:missing_plan|skip_passthrough|unsupported_action|metadata_prune_only]", - "line": 700 + "line": 724 }, { "id": "WORKTREE.SEAM.test-policy", "klass": "WORKTREE", "value": "cover all decision branches in policy module before changing prune behavior", - "line": 699 + "line": 723 } ], "duplicates": [] diff --git a/gsd-core/references/ui-consideration-probe.md b/gsd-core/references/ui-consideration-probe.md index cfd6e967c..d5abfb779 100644 --- a/gsd-core/references/ui-consideration-probe.md +++ b/gsd-core/references/ui-consideration-probe.md @@ -15,11 +15,16 @@ here. Forcing them into a closed compiled taxonomy is the wrong model. ## Inputs -A list of UI elements, each a `{ id, text, elements? }` record where `text` is the -researcher-authored description and `elements` is an optional author-supplied override of the -element classification. The six element kinds are: `form`, `list-collection`, `nav`, `media`, -`interactive-control`, `static-content`. When `elements` is absent, a heuristic classifier -proposes kinds from the prose (propose-then-confirm) — the author may correct the kind. +A list of UI elements, each a `{ id, text, text_en?, elements? }` record where `text` is the +researcher-authored description, `elements` is an optional author-supplied override of the +element classification, and `text_en` is an optional English translation of `text` +(#4657). The element cues are English word-boundary patterns, so a non-English `text` (a +project running with `response_language` set) classifies to zero kinds unless `text_en` +carries a faithful English rendering — engine input, never user-facing output; `text` +itself keeps the UI-SPEC's own language and is never translated. The six element kinds are: +`form`, `list-collection`, `nav`, `media`, `interactive-control`, `static-content`. When +`elements` is absent, a heuristic classifier proposes kinds from the prose +(`text_en ?? text`, propose-then-confirm) — the author may correct the kind. ## Taxonomy (8 categories) diff --git a/gsd-core/workflows/ui-phase.md b/gsd-core/workflows/ui-phase.md index 1be560eb0..6a09558e8 100644 --- a/gsd-core/workflows/ui-phase.md +++ b/gsd-core/workflows/ui-phase.md @@ -305,6 +305,27 @@ section (re-run), the write-back is idempotent (it REPLACES that section, never runtime is non-Claude and the probe engine cannot be resolved, the shim FAILS LOUD (below) — it never silently no-ops (a silent skip would drop the whole state-coverage axis). +**Non-English projects — `text_en` carries the classifier-facing translation; the UI-SPEC is +not.** The element cues the classifier matches are **English** word-boundary patterns, so +element prose written in another language matches nothing, classifies to zero kinds, and lands +every element in `unclassified` (#1110) — the taxonomy contributes nothing and `--auto` leaves +it all `unresolved`. When this project has `response_language` set, add an optional `text_en` +key to each `$ELEMENTS_JSON` entry: a faithful **English** translation of that element's +`text`. `text_en` is **engine input, never user-facing output**, so the `response_language` +rule at the top of this workflow does not govern it — but `text` itself is NOT translated: +write it as the element's own wording, exactly as it appears in the UI-SPEC. The UI-SPEC keeps +the original language — only `text_en` is translated, and element `id`s are never translated +or renumbered (coverage rows join back on `id`). Populate `text_en` for **every** element, not +only the ones that look UI-relevant: the zero-applicable guard below fires when `$APPLICABLE` +is `0` and again on the all-unclassified case (`$UNCLASSIFIED = $APPLICABLE`, #4656), so a +partly-classified surface slips through both arms with no signal at all. When +`response_language` is unset (an English-language project), omit `text_en` — +`text` is already English and the engine falls back to it automatically (`text_en ?? text`). +If an element still classifies to zero kinds with `text_en` populated, it carries no cue in +any language (the recorded recall gap — ADR-857 §98 / ADR-550 D7b, not a translation failure); +author an explicit `elements` array on that element instead of relying on the prose classifier. +(#4657) + **Runtime coverage compute — resolve and invoke ui-consideration-probe.cjs:** ```bash @@ -345,8 +366,9 @@ fi # Element extraction (MANUAL BY DESIGN — not an oversight): the agent reads the researcher-authored # UI-SPEC prose (the described surfaces — the Design System / Copywriting rows and any element the -# researcher named) and writes ONE object per UI element/surface: {"id","text"} where text is the -# prose describing it. This mirrors spec-phase Step 5.5's edge-probe REQS_JSON step VERBATIM — a +# researcher named) and writes ONE object per UI element/surface: {"id","text","text_en"?} where +# text is the prose describing it. This mirrors spec-phase Step 5.5's edge-probe REQS_JSON step +# VERBATIM — a # hand-populated heredoc guarded by the fail-loud check below — the established, shipped # pattern for feeding a probe from a prose spec. It is NOT mechanized on purpose: a UI-SPEC has no # single machine-parseable "elements" column — surfaces are distributed across design-token tables @@ -355,7 +377,10 @@ fi # element). The agent-authored heredoc + fail-loud guard is the conservative choice, identical to the # requirement-side edge-probe path (RR-04). If a future UI-SPEC gains a canonical element table, # revisit to parse it. Populate the heredoc from the UI-SPEC; the guard below fails loud on a -# forgotten substitution (never a no-op). +# forgotten substitution (never a no-op). When `response_language` is set, ALSO add `text_en` — a +# faithful ENGLISH translation of `text` (see the Non-English projects note above); the element +# cues are English-only, so original-language `text` alone classifies to zero kinds. `text` itself +# stays the UI-SPEC's own wording and is never translated. ELEMENTS_JSON=$(mktemp "${TMPDIR:-/tmp}/ui-probe-elements-XXXXXX") && mv "$ELEMENTS_JSON" "${ELEMENTS_JSON}.json" && ELEMENTS_JSON="${ELEMENTS_JSON}.json" || exit 1 cat > "$ELEMENTS_JSON" <<'JSON' [ diff --git a/scripts/lint-test-file-count.allowlist.json b/scripts/lint-test-file-count.allowlist.json index d51dae86f..03950816e 100644 --- a/scripts/lint-test-file-count.allowlist.json +++ b/scripts/lint-test-file-count.allowlist.json @@ -1,6 +1,15 @@ { - "_doc": "Baseline of modules currently exceeding the 2-test-file limit. Each entry locks in TODAY's exact test filenames as the allowlisted set (identity ratchet). Adding a NEW test file to a capped module fails (novel). Removing one requires pruning this list (stale, ratchet-down). When a cluster drops to \u2264 2, remove its entry entirely. New entries require justification in PR description.", + "_doc": "Baseline of modules currently exceeding the 2-test-file limit. Each entry locks in TODAY's exact test filenames as the allowlisted set (identity ratchet). Adding a NEW test file to a capped module fails (novel). Removing one requires pruning this list (stale, ratchet-down). When a cluster drops to ≤ 2, remove its entry entirely. New entries require justification in PR description.", "modules": { + "ui-consideration-probe": { + "files": [ + "ui-consideration-probe-docs-fixtures.test.cjs", + "ui-consideration-probe-ui-phase-contract.test.cjs", + "ui-consideration-probe.test.cjs" + ], + "issue": "4657", + "justification": "The ui-consideration-probe cluster gains its workflow-prose contract file (tests/ui-consideration-probe-ui-phase-contract.test.cjs, #4657), mirroring the edge probe's split (edge-probe.test.cjs / edge-probe-docs-fixtures.test.cjs / edge-probe-spec-phase-contract.test.cjs). The contract file reads shipped gsd-core/workflows/ui-phase.md under the source-text-is-the-product exception, which the unit file deliberately does not carry (it asserts typed returns only)." + }, "adr-parser": { "files": [ "adr-parser.property.test.cjs", @@ -40,7 +49,7 @@ "frontmatter.unit.test.cjs" ], "issue": "3881", - "justification": "Grandfathered by #3227 for the original 4-file cluster (pre-existing over-cap, not new sprawl). #3881 (ADR-3473 \u00a78.1, the js-yaml parser migration) adds two more: frontmatter-golden-parity.test.cjs (D-series golden-corpus diff against the legacy parser, ~900 real documents \u2014 cannot be folded into an existing file without losing its independent-of-current-parser provenance) and frontmatter-roundtrip.property.test.cjs (fast-check property coverage the migration's bijective-contract rule requires). Both are migration-specific, not incidental sprawl." + "justification": "Grandfathered by #3227 for the original 4-file cluster (pre-existing over-cap, not new sprawl). #3881 (ADR-3473 §8.1, the js-yaml parser migration) adds two more: frontmatter-golden-parity.test.cjs (D-series golden-corpus diff against the legacy parser, ~900 real documents — cannot be folded into an existing file without losing its independent-of-current-parser provenance) and frontmatter-roundtrip.property.test.cjs (fast-check property coverage the migration's bijective-contract rule requires). Both are migration-specific, not incidental sprawl." }, "graphify": { "files": [ @@ -140,7 +149,7 @@ "verify-work-deferred-promotion.test.cjs", "verify.test.cjs" ], - "issue": "#3813 \u2014 the live-path #1883 suite drives buildPlanningSnapshot in-process with an fs fault; the verify module suites are CLI-driving and cannot host an fs monkeypatch", + "issue": "#3813 — the live-path #1883 suite drives buildPlanningSnapshot in-process with an fs fault; the verify module suites are CLI-driving and cannot host an fs monkeypatch", "justification": "verify-command-grounding added by #2401/#3678; allowlist follow-up landed with #3606 (base was red on this lane). #4546 adds verify-work-deferred-promotion (deferred-follow-up promotion writer contract + parity)." }, "install": { @@ -155,7 +164,7 @@ "install-write-confinement.test.cjs", "install.test.cjs" ], - "issue": "#3798 \u2014 the profile-closure spawn test reads the real repo surface (commands+workflows+agents); consolidating it into install.test.cjs would put a whole-repo scan behind the suite's heaviest file" + "issue": "#3798 — the profile-closure spawn test reads the real repo surface (commands+workflows+agents); consolidating it into install.test.cjs would put a whole-repo scan behind the suite's heaviest file" }, "edge-probe": { "files": [ @@ -253,8 +262,8 @@ "docs-state-md-locale-parity.test.cjs", "docs-update.test.cjs" ], - "issue": "3873 | #3839 \u2014 the hook-event parity suite cross-checks the four docs hook tables against src/runtime-hooks-surface.cts registrations; a generated-docs concern distinct from content freshness and registry parity", - "justification": "ADR-3473 \u00a78.8 makes docs/reference/state-md.md and its four locale siblings generated-and-committed and adds the repo's first locale-parity check (verified: no locale-parity lint precedent exists here). That check is a distinct concern from docs-update (content freshness) and docs-parity-live-registry (registry parity); folding it into either would place an unrelated subject inside them purely to satisfy a count. The section it guards is absent from all four translations today and documents the status enum behind #3853." + "issue": "3873 | #3839 — the hook-event parity suite cross-checks the four docs hook tables against src/runtime-hooks-surface.cts registrations; a generated-docs concern distinct from content freshness and registry parity", + "justification": "ADR-3473 §8.8 makes docs/reference/state-md.md and its four locale siblings generated-and-committed and adds the repo's first locale-parity check (verified: no locale-parity lint precedent exists here). That check is a distinct concern from docs-update (content freshness) and docs-parity-live-registry (registry parity); folding it into either would place an unrelated subject inside them purely to satisfy a count. The section it guards is absent from all four translations today and documents the status enum behind #3853." }, "audit": { "files": [ @@ -266,7 +275,7 @@ "audit-uat-summary-segmentation.test.cjs", "audit-workstream-layouts.test.cjs" ], - "issue": "#3804/#3805 \u2014 audit-layout and acknowledged-marker suites drive the real audit-uat CLI against on-disk fixtures | #3817 \u2014 regression suite proving countReal counts the truncation remainder marker instead of treating it as one phantom item | #3783 \u2014 dedicated suite for the summary.current_milestone/archived segmentation, matching this module's one-file-per-feature-slice precedent (e.g. audit-uat-acknowledged.test.cjs) rather than growing the unrelated 6900+ line tests/uat.test.cjs (a different module, keyed off uat.cjs)" + "issue": "#3804/#3805 — audit-layout and acknowledged-marker suites drive the real audit-uat CLI against on-disk fixtures | #3817 — regression suite proving countReal counts the truncation remainder marker instead of treating it as one phantom item | #3783 — dedicated suite for the summary.current_milestone/archived segmentation, matching this module's one-file-per-feature-slice precedent (e.g. audit-uat-acknowledged.test.cjs) rather than growing the unrelated 6900+ line tests/uat.test.cjs (a different module, keyed off uat.cjs)" }, "shell-command-projection": { "files": [ @@ -274,7 +283,16 @@ "shell-command-projection-md-normalize.test.cjs", "shell-command-projection-path-sep.test.cjs" ], - "issue": "#3854 \u2014 the tight-list suite pins the markdown write-normalizer's blank-line policy through the exported normalizeContent/platformWriteSync seam; a distinct concern from dispatch routing and path separation" + "issue": "#3854 — the tight-list suite pins the markdown write-normalizer's blank-line policy through the exported normalizeContent/platformWriteSync seam; a distinct concern from dispatch routing and path separation" + }, + "ui-consideration-probe": { + "files": [ + "ui-consideration-probe-docs-fixtures.test.cjs", + "ui-consideration-probe-ui-phase-contract.test.cjs", + "ui-consideration-probe.test.cjs" + ], + "issue": "4657", + "justification": "The ui-consideration-probe cluster gains its workflow-prose contract file (tests/ui-consideration-probe-ui-phase-contract.test.cjs, #4657), mirroring the edge probe's split (edge-probe.test.cjs / edge-probe-docs-fixtures.test.cjs / edge-probe-spec-phase-contract.test.cjs). The contract file reads shipped gsd-core/workflows/ui-phase.md under the source-text-is-the-product exception, which the unit file deliberately does not carry (it asserts typed returns only)." } } } diff --git a/src/ui-consideration-probe.cts b/src/ui-consideration-probe.cts index 209a42719..9869015a7 100644 --- a/src/ui-consideration-probe.cts +++ b/src/ui-consideration-probe.cts @@ -55,10 +55,22 @@ export interface TaxonomyEntry { consideration: string; } -/** A UI element to probe; `elements` is an optional authored override of classification. */ +/** + * A UI element to probe; `elements` is an optional authored override of classification. + * + * `text_en` (#4657) is an optional English translation of `text`, read by element + * classification in preference to `text` when present (`text_en ?? text`). `UI_CUES` + * are English-only word-boundary patterns, so a non-English `text` (e.g. a project + * running with `response_language` set) classifies to zero kinds and lands every + * element in the `unclassified` soft signal unless `text_en` supplies an English + * rendering. `text` itself is unaffected and keeps its own meaning (the element's own + * description, in whatever language the UI-SPEC uses) — only classification reads + * `text_en` preferentially. Mirrors the edge adapter's `Requirement.text_en` (#3717). + */ export interface Element { id: string; text?: string; + text_en?: string; elements?: UIElementKind[]; } @@ -146,7 +158,7 @@ export const UI_VALIDATORS: Validators = { */ export function validateRequirement(element: Element): void { coreValidateRequirement(element); - const r = element as unknown as { elements?: unknown; text?: unknown }; + const r = element as unknown as { elements?: unknown; text?: unknown; text_en?: unknown }; if (r.elements != null && !Array.isArray(r.elements)) { throw new Error(`element ${element.id} elements must be an array when present`); } @@ -155,6 +167,15 @@ export function validateRequirement(element: Element): void { `element ${element.id} text must be a non-empty string when no elements override is provided`, ); } + // text_en (#4657) is optional, but when present it must be a non-empty string. An empty + // string is NOT caught by `??` (only null/undefined are), so an unvalidated `text_en: ''` + // would silently win `text_en ?? text` and classify against '' — the same fail-open shape + // #1110/#2773 already exist to eliminate, just moved one field over. Validated + // unconditionally (not gated on whether `elements` will make it unused) so bad data fails + // closed even when it happens to be dead for this particular call. + if (r.text_en != null && !(typeof r.text_en === 'string' && r.text_en.trim())) { + throw new Error(`element ${element.id} text_en must be a non-empty string when present`); + } } /** Validate a UI-consideration resolution against the UI verification vocabulary (delegated, D-06). */ @@ -184,7 +205,11 @@ export function proposeConsiderations(element: Element): UIConsideration[] { } kinds = element.elements; } else { - kinds = classifyElement(element.text as string); + // #4657: prefer the English translation when present — UI_CUES are English-only + // word-boundary patterns, so a non-English `text` (e.g. response_language projects) + // would otherwise classify to zero kinds. validateRequirement (called above) has + // already guaranteed text_en, if present, is a non-empty string. + kinds = classifyElement((element.text_en ?? element.text) as string); if (kinds.length === 0) { // Prose present but no element cue matched. Do NOT silently drop it (#1110): a UI element // whose phrasing missed every cue would otherwise vanish from coverage with no signal — the @@ -270,7 +295,7 @@ export function proposeElements(elements: Element[]): ElementProposal[] { const considerations = proposeConsiderations(el); const kinds: UIElementKind[] = Array.isArray(el.elements) ? el.elements // already validated inside proposeConsiderations - : classifyElement(el.text as string); + : classifyElement((el.text_en ?? el.text) as string); // #4657: text_en ?? text const unclassified = !Array.isArray(el.elements) && kinds.length === 0; const categories = unclassified ? [] : applicableCategories(kinds); return { id: el.id, kinds, categories, considerations, unclassified }; diff --git a/tests/ui-consideration-probe-docs-fixtures.test.cjs b/tests/ui-consideration-probe-docs-fixtures.test.cjs index 8178e8f41..c84c3d1b2 100644 --- a/tests/ui-consideration-probe-docs-fixtures.test.cjs +++ b/tests/ui-consideration-probe-docs-fixtures.test.cjs @@ -55,6 +55,15 @@ describe('ui-consideration-probe doc/code parity (ADPT-02)', () => { const md = fs.readFileSync(docPath, 'utf8'); assert.match(md, /domain-probes\.md/); }); + + test('Inputs section documents the text_en translation channel (#4657)', () => { + // PARSED from the `## Inputs` section only (never a whole-file substring) — a reformat + // that preserves the data does not fail; a dropped field does. + const md = fs.readFileSync(docPath, 'utf8'); + const inputs = md.split(/^## Inputs/m)[1].split(/^## /m)[0]; + assert.match(inputs, /text_en/, 'Inputs must document the optional text_en field'); + assert.match(inputs, /English/, 'Inputs must say text_en is the classifier-facing English rendering'); + }); }); describe('UI-SPEC template `## UI Considerations` section (WIRE-02 SC3 de-dup)', () => { diff --git a/tests/ui-consideration-probe-ui-phase-contract.test.cjs b/tests/ui-consideration-probe-ui-phase-contract.test.cjs new file mode 100644 index 000000000..405bb6c8a --- /dev/null +++ b/tests/ui-consideration-probe-ui-phase-contract.test.cjs @@ -0,0 +1,104 @@ +// ui-phase.md Step 9.5 is the deployed workflow runtime contract under assertion; its text IS +// what the runtime loads. These checks lock the #4657 text_en wiring so the Non-English +// guidance cannot silently rot the way it did for the edge adapter before #3717 — mirroring +// tests/edge-probe-spec-phase-contract.test.cjs onto the ui-phase probe step. +// Assertions scope to the extracted Step 9.5 block to avoid false positives from incidental +// mentions elsewhere in the file. + +'use strict'; + +process.env.GSD_TEST_MODE = '1'; + +const { describe, test } = require('node:test'); +const assert = require('node:assert/strict'); +const fs = require('node:fs'); +const path = require('node:path'); +const fc = require('./helpers/fast-check-setup.cjs'); + +const UI_PHASE_PATH = path.join(__dirname, '..', 'gsd-core', 'workflows', 'ui-phase.md'); +const { proposeConsiderations } = require( + path.join(__dirname, '..', 'gsd-core', 'bin', 'lib', 'ui-consideration-probe.cjs'), +); + +function readUiPhase() { + // allow-test-rule: source-text-is-the-product (#4657) + // The workflow file's text IS the deployed runtime contract; assertions below match on it. + return fs.readFileSync(UI_PHASE_PATH, 'utf8'); +} + +// Slice the Step 9.5 block: from the "## 9.5." heading to the next "## " heading. Scopes +// assertions to the probe step only. +function extractStep95Block(content) { + const startIdx = content.indexOf('## 9.5.'); + if (startIdx === -1) return ''; + const rest = content.slice(startIdx + '## 9.5.'.length); + const nextHeading = rest.search(/\n## /); + if (nextHeading === -1) return content.slice(startIdx); + return content.slice(startIdx, startIdx + '## 9.5.'.length + nextHeading); +} + +describe('ui-consideration-probe ui-phase contract: text_en (#4657)', () => { + test('Step 9.5 documents the Non-English text_en remedy (mirrors spec-phase Step 5.5, #3717)', () => { + const block = extractStep95Block(readUiPhase()); + assert.ok(block.length > 0, 'Step 9.5 block must be extractable from ui-phase.md'); + assert.match(block, /Non-English/i, 'Step 9.5 must carry the Non-English projects guidance'); + assert.match(block, /text_en/, 'Step 9.5 must name text_en — the classifier-facing translation field'); + assert.match(block, /response_language/, 'Step 9.5 must tie the remedy to response_language projects'); + assert.match(block, /every element/i, 'Step 9.5 must instruct populating text_en for EVERY element, not only UI-obvious ones'); + assert.match(block, /engine input/i, 'text_en is engine input, never user-facing output (ADR-550)'); + }); + + test('Step 9.5 ELEMENTS_JSON shape comment includes the optional text_en key', () => { + const block = extractStep95Block(readUiPhase()); + assert.match(block, /"text_en"\?/, 'the element record shape must document text_en? alongside id/text/elements'); + }); + + // Property (deterministic: pinned seed, bounded runs, counterexample printed on failure): + // for English element prose built from the classifier's own cue vocabulary, a cue-free + // Danish rendering as `text` plus the original English as `text_en` must classify + // identically to the English original — and the Danish rendering alone must stay + // unclassified. Document-shaped inputs: the English words ARE cue words UI_CUES matches; + // the Danish translations are verified cue-free by the property itself on every run. + test('property: text_en carries classification for any cue-matching prose under a cue-free Danish rendering', () => { + const enToDa = [ + ['form', 'formular'], + ['input', 'indtastning'], + ['list', 'liste'], + ['table', 'tabel'], + ['tabs', 'faner'], + ['pagination', 'sideinddeling'], + ['image', 'billede'], + ['gallery', 'galleri'], + ['button', 'knap'], + ['dropdown', 'rullemenu'], + ['heading', 'overskrift'], + ['title', 'titel'], + ]; + const enWords = enToDa.map(([en]) => en); + const daOf = (w) => enToDa.find(([en]) => en === w)[1]; + + fc.assert( + fc.property( + fc.constantFrom(...enWords), + fc.constantFrom(...enWords), + fc.nat(2), + (w1, w2, extra) => { + const english = [w1, w2, ...Array(extra).fill(w2)].join(' '); + const danish = [w1, w2, ...Array(extra).fill(w2)].map(daOf).join(' '); + const cats = (el) => proposeConsiderations(el).map((c) => c.category); + assert.deepEqual( + cats({ id: 'P', text: danish }), + ['unclassified'], + `the Danish rendering must be cue-free (counterexample text: ${JSON.stringify(danish)})`, + ); + assert.deepEqual( + cats({ id: 'P', text: danish, text_en: english }), + cats({ id: 'P', text: english }), + `translated element must classify as its English original (counterexample text_en: ${JSON.stringify(english)})`, + ); + }, + ), + { seed: 4657, numRuns: 200 }, + ); + }); +}); diff --git a/tests/ui-consideration-probe.test.cjs b/tests/ui-consideration-probe.test.cjs index d2add5a8e..5663f5f5e 100644 --- a/tests/ui-consideration-probe.test.cjs +++ b/tests/ui-consideration-probe.test.cjs @@ -19,7 +19,12 @@ process.env.GSD_TEST_MODE = '1'; const { test, describe } = require('node:test'); const assert = require('node:assert/strict'); +const fs = require('node:fs'); const path = require('node:path'); +const { runNode } = require('./helpers/process-seam.cjs'); +const { PROBE_TIMEOUT_MS } = require('./helpers/timeouts.cjs'); +const { throwIfFailed } = require('./helpers/git-fixture.cjs'); +const { cleanup, createTempDir } = require('./helpers.cjs'); const BUILT_SCRIPT = path.join(__dirname, '..', 'gsd-core', 'bin', 'lib', 'ui-consideration-probe.cjs'); const uc = require(BUILT_SCRIPT); @@ -307,3 +312,140 @@ describe('ui-consideration-probe WIRE-02: backward-compat + format-match + idemp assert.deepEqual(uc.proposeElements(els), uc.proposeElements(els)); }); }); + +// ══ #4657 — the text_en language channel (mirrors #3717/#4156 onto the UI adapter) ═════════ +// UI_CUES are English word-boundary patterns; a non-English element classifies to zero kinds +// and lands in the #1110 unclassified soft signal. text_en carries the classifier-facing +// English translation — engine input, never user-facing output. (The ADR-550 amendment's +// record scopes to the edge adapter's Requirement; #4657 extends the same remedy shape to +// the UI Element.) classifyElement's own signature stays untouched; the text_en ?? text +// selection lives at the two classification call sites (proposeConsiderations, proposeElements). +describe('ui-consideration-probe: text_en language-aware classification (#4657)', () => { + // The reproduction pair from the issue: Danish UI-SPEC prose + faithful English translations. + const daList = 'En liste over projektorer med knapper til at forbinde og afbryde.'; + const daForm = 'En formular hvor brugeren indtaster IP-adresse og adgangskode.'; + const enList = 'A list of projectors with buttons to connect and disconnect.'; + const enForm = 'A form where the user enters IP address and password.'; + + test('proposeConsiderations: text_en present is used for classification instead of text (failing-first regression)', () => { + // text alone (non-English) classifies to zero kinds -> the unclassified sentinel. + const nonEnglishOnly = uc.proposeConsiderations({ id: 'U1', text: daList }); + assert.deepEqual(nonEnglishOnly.map((c) => c.category), ['unclassified']); + + // text_en present -> classification runs against the English translation (list-collection + // from "list", interactive-control from "buttons"). + const withTextEn = uc.proposeConsiderations({ id: 'U1', text: daList, text_en: enList }); + assert.deepEqual( + withTextEn.map((c) => c.category), + ['empty', 'loading', 'error', 'populated', 'partial', 'overflow', 'zero-one-many', 'long-text'], + ); + }); + + test('#4657: a non-English element with text_en classifies identically to its English equivalent', () => { + for (const [da, en] of [[daList, enList], [daForm, enForm]]) { + const englishOnly = uc.proposeConsiderations({ id: 'U1', text: en }); + const nonEnglishWithTranslation = uc.proposeConsiderations({ id: 'U1', text: da, text_en: en }); + assert.deepEqual( + nonEnglishWithTranslation.map((c) => c.category), + englishOnly.map((c) => c.category), + `a translated non-English element must raise the same categories as the English original (${da})`, + ); + } + }); + + test('proposeConsiderations: text_en absent falls back to text (back-compat — English projects unchanged)', () => { + const withoutTextEn = uc.proposeConsiderations({ id: 'U1', text: enForm }); + assert.deepEqual(withoutTextEn.map((c) => c.category), ['empty', 'loading', 'error', 'partial', 'long-text']); + }); + + test('validateRequirement: text_en: null is treated as absent (no throw)', () => { + assert.doesNotThrow(() => uc.validateRequirement({ id: 'U1', text: 'A results table', text_en: null })); + }); + + test('proposeConsiderations: text_en: null falls back to text', () => { + const viaNull = uc.proposeConsiderations({ id: 'U1', text: enForm, text_en: null }); + assert.deepEqual(viaNull.map((c) => c.category), ['empty', 'loading', 'error', 'partial', 'long-text']); + }); + + test('validateRequirement: rejects empty-string text_en (?? does not catch \'\')', () => { + // Nullish coalescing only falls back on null/undefined — an empty string would otherwise + // win `text_en ?? text` and silently classify against '', degrading to zero kinds with no + // signal (the exact fail-open #1110/#2773 exist to eliminate). + assert.throws( + () => uc.validateRequirement({ id: 'U1', text: daList, text_en: '' }), + /text_en must be a non-empty string when present/i, + ); + }); + + test('validateRequirement: rejects whitespace-only text_en', () => { + assert.throws( + () => uc.validateRequirement({ id: 'U1', text: daList, text_en: ' ' }), + /text_en must be a non-empty string when present/i, + ); + }); + + test('validateRequirement: rejects non-string text_en (number/array/object)', () => { + for (const bad of [42, ['x'], {}]) { + assert.throws( + () => uc.validateRequirement({ id: 'U1', text: daList, text_en: bad }), + /text_en must be a non-empty string when present/i, + ); + } + }); + + test('validateRequirement: rejects empty text_en even when an elements override makes it unused', () => { + // Validation is unconditional — it does not skip the text_en check just because the + // authored-elements branch would never classify prose. Bad data fails closed regardless. + assert.throws( + () => uc.validateRequirement({ id: 'U1', text: daList, text_en: '', elements: ['form'] }), + /text_en must be a non-empty string when present/i, + ); + }); + + test('proposeConsiderations: authored elements override still wins when text_en is also present', () => { + // nav is an applicable element kind for loading, error, overflow AND long-text. + const override = uc.proposeConsiderations({ id: 'U9', text: daList, text_en: enList, elements: ['nav'] }); + assert.deepEqual(override.map((c) => c.category), ['loading', 'error', 'overflow', 'long-text']); + }); + + test('proposeConsiderations: zero-cue text_en still surfaces the unclassified soft signal (#1110)', () => { + const zeroCue = uc.proposeConsiderations({ id: 'U1', text: daForm, text_en: 'Purple elephant dreams.' }); + assert.deepEqual(zeroCue.map((c) => c.category), ['unclassified']); + }); + + test('proposeElements: kinds derive from text_en when present (confirm surface sees the translation)', () => { + const [translated] = uc.proposeElements([{ id: 'U1', text: daList, text_en: enList }]); + assert.deepEqual(translated.kinds, ['list-collection', 'interactive-control']); + assert.equal(translated.unclassified, false); + // and without text_en the same element stays on the unclassified path + const [plain] = uc.proposeElements([{ id: 'U1', text: daList }]); + assert.equal(plain.unclassified, true); + assert.deepEqual(plain.kinds, []); + }); + + test('analyzeCoverage: the reproduction pair — Danish text + text_en yields the English report\'s categories', () => { + const english = uc.analyzeCoverage([{ id: 'U1', text: enList }, { id: 'U2', text: enForm }]); + const translated = uc.analyzeCoverage([{ id: 'U1', text: daList, text_en: enList }, { id: 'U2', text: daForm, text_en: enForm }]); + assert.equal(translated.coverage.applicable, english.coverage.applicable); + assert.equal(translated.coverage.unclassified, 0); + assert.deepEqual( + translated.items.map((c) => c.category), + english.items.map((c) => c.category), + ); + }); + + test('CLI: elements file with text_en classifies through the built engine (exit 0, no unclassified)', (t) => { + const dir = createTempDir('ui-probe-4657-'); + t.after(() => cleanup(dir)); + const elementsPath = path.join(dir, 'elements.json'); + fs.writeFileSync(elementsPath, JSON.stringify([ + { id: 'U1', text: daList, text_en: enList }, + { id: 'U2', text: daForm, text_en: enForm }, + ])); + const r = runNode([BUILT_SCRIPT, elementsPath], { timeoutMs: PROBE_TIMEOUT_MS }); + throwIfFailed(r, `node ${BUILT_SCRIPT} ${elementsPath}`); + const rep = JSON.parse(r.stdout); + assert.equal(rep.coverage.unclassified, 0); + assert.ok(rep.coverage.applicable > 0, 'translated elements must raise applicable categories'); + }); +});