1c93df04db
* test(#2711): derive the omit-rule guarded set from the corpus instead of a hand list The GUARDED array was a Goodhart metric: it reported green across 15 non-compliant workflows for no better reason than that nobody had added them to it. The guard now derives its set — every workflow emitting a model="{…}" dispatch site must state the omit-on-inherit/empty rule — and asserts the derivation is non-empty so a broken scan fails rather than passes. Rule detection stays a PROPERTY check, not a template match: plan-phase.md and execute-phase.md state it in different words and both are correct. RED expected on 15 workflows: audit-milestone, code-review, code-review-fix, debug, discuss-phase-assumptions, docs-update, map-codebase, new-milestone, new-project, quick, secure-phase, ui-phase, ui-review, validate-phase, verify-work. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01DPq9ovaovP2UvSVLjD4Lso * fix(#2711): propagate the #2517 omit-on-inherit rule to all 15 unguarded workflows 15 of the 19 model=-dispatching workflows carried no omit-on-inherit/empty guidance — 43 unguarded dispatch sites. Each would emit model="" whenever the bound *_model resolved empty, which is the DEFAULT state on non-Claude runtimes: the installer writes resolve_model_ids:"omit" into ~/.gsd/defaults.json for every one of them (references/model-profiles.md:101), and resolveModelInternal returns "" for that case (src/model-resolver.cts:383-386) and "inherit" for opus-tier agents and the inherit profile (:395). Both 404 on runtimes without native tier aliases — the failure #2517 documented and fixed in one file. Each file now carries a `<!-- #2517 model-omit-on-inherit -->` blockquote naming its own bound placeholders and linking the canonical statement in references/model-profile-resolution.md, mirroring the `<!-- #2508 runtime-aware-dispatch -->` block already present in all 15. The rule text lives in the reference; the workflows carry a pointer plus the one-line instruction, so the next revision edits one file rather than fifteen. plan-phase.md and execute-phase.md are deliberately untouched — they already state the rule in their own wording, and the guard checks the property rather than a template string. No dispatch site is edited and no placeholder renamed: the #2684 binding guard reports the same 19 files / 60 placeholders / 0 findings before and after, which is the independence proof that this change is additive prose only. There is no Hyrum's-Law routing change to disclose. Placement is span-aware. An initial pass anchored to the #2508 marker, but in six files that marker sits INSIDE the Agent(prompt="…") string, so the new paragraph's literal model= landed in a dispatch call span and tripped the #2284 fail-closed Hermes projection guard (bin/install.js:3704), refusing the install. Blocks are now anchored before the opening Agent( of the span owning the first dispatch, and verified to fall inside no span. gen:golden exits 0 across all 19 runtimes. Fixes #2711 Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01DPq9ovaovP2UvSVLjD4Lso * fix(#2711): cite the issue number in the changeset body and tidy block placement Review findings from the two orthogonal passes: - The changeset body ended (#0). Repo convention across every prior fragment (e.g. #2617/#2693, #2608, #2605) is that the trailing (#NNN) is the ISSUE number, known at authoring time; only the frontmatter pr: field carries the 0 placeholder pending backfill. (#0) would have rendered a dead link in the published release notes. - new-milestone.md glued the inserted block directly under the preceding paragraph with no blank line, inconsistent with the other 14 insertions. - The derived-guard non-vacuity floor was >=17 against an actual derived count of 19, tolerating a silent two-file regression. Tightened to >=19. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01DPq9ovaovP2UvSVLjD4Lso * fix(#2711): reword the omit block so it survives Hermes projection, and exempt quick.md by size The first block wording regressed two suites on the full matrix (4 failures on both linux-node22 and linux-node24). gen:golden passing was not sufficient evidence — it exercises the installer's own fail-closed guard, which is narrower than the dedicated tests. 1. tests/fix-2284-hermes-agent-delegate-task-projection.test.cjs asserts that the INSTALLED code-review-fix.md contains no `model=` anywhere outside a string literal — masked whole-file, not merely inside call spans. The block's backticked `model=` survived the mask. The assertion is right: on Hermes the projection strips the parameter because delegate_task has no per-call model at all, so instructing the orchestrator to "omit the model= parameter" is advice about a parameter that does not exist there. The block now says "the `model` parameter" and carries no bare `model=` token. 2. tests/prompt-injection-scan.security.test.cjs flagged quick.md at 50,164 normalized chars against a 50,000 prompt-stuffing threshold. quick.md sits just under the line on next, so any insertion trips it — the situation review.md is already documented for in SIZE_ONLY_WORKFLOWS ("sat at 49,971 chars — 29 below the threshold — so it was going to trip on whatever was added to it next"). quick.md joins it with the same justification. This is a size-finding exemption only: the file is still fully injection scanned, and every other security check still runs on it. Because the canonical block can no longer carry a literal `model=`, the guard's detector now accepts the `<!-- #2517 model-omit-on-inherit -->` marker as the canonical signal, falling back to the inline-prose property for the four files that predate it (plan-phase, execute-phase, scan, ship — all four match the legacy branch). That is strictly stronger than word-proximity matching, and it keeps the guard a property check rather than a template match. Verified: derived guard 19/19 with 0 missing; the #2684 binding guard unchanged at 19 files / 60 placeholders / 0 findings; no inserted block contains a bare model= token; the masked-projection assertion passes for code-review-fix.md; gen:golden exits 0 across all 19 runtimes; lint:ci exits 0. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01DPq9ovaovP2UvSVLjD4Lso * chore(#2711): backfill changeset PR number Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01DPq9ovaovP2UvSVLjD4Lso --------- Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
94 lines
2.4 KiB
JSON
94 lines
2.4 KiB
JSON
{
|
|
"add-backlog.md": 7176,
|
|
"add-phase.md": 7578,
|
|
"add-tests.md": 17247,
|
|
"add-todo.md": 11020,
|
|
"ai-integration-phase.md": 15356,
|
|
"analyze-dependencies.md": 3887,
|
|
"audit-fix.md": 12329,
|
|
"audit-milestone.md": 19425,
|
|
"audit-uat.md": 7469,
|
|
"autonomous.md": 42468,
|
|
"check-todos.md": 9771,
|
|
"cleanup.md": 10319,
|
|
"code-review-fix.md": 25301,
|
|
"code-review.md": 33490,
|
|
"complete-milestone.md": 31436,
|
|
"debug.md": 20555,
|
|
"diagnose-issues.md": 13444,
|
|
"discovery-phase.md": 13543,
|
|
"discuss-phase-assumptions.md": 28633,
|
|
"discuss-phase-power.md": 11273,
|
|
"discuss-phase.md": 31986,
|
|
"do.md": 10731,
|
|
"docs-update.md": 56876,
|
|
"edit-phase.md": 12927,
|
|
"eval-review.md": 10316,
|
|
"execute-phase.md": 90143,
|
|
"execute-plan.md": 35143,
|
|
"explore.md": 11127,
|
|
"extract-learnings.md": 13762,
|
|
"fast.md": 7613,
|
|
"forensics.md": 12531,
|
|
"graduation.md": 11987,
|
|
"health.md": 12246,
|
|
"help.md": 1722,
|
|
"import.md": 15599,
|
|
"inbox.md": 19299,
|
|
"ingest-docs.md": 19821,
|
|
"insert-phase.md": 8987,
|
|
"list-phase-assumptions.md": 4305,
|
|
"list-seeds.md": 6987,
|
|
"list-workspaces.md": 5699,
|
|
"manager.md": 27751,
|
|
"map-codebase.md": 22266,
|
|
"milestone-summary.md": 11842,
|
|
"mvp-phase.md": 13991,
|
|
"new-milestone.md": 39090,
|
|
"new-project.md": 67478,
|
|
"new-workspace.md": 11584,
|
|
"next.md": 20171,
|
|
"node-repair.md": 4173,
|
|
"note.md": 6563,
|
|
"onboard.md": 8877,
|
|
"pause-work.md": 14441,
|
|
"plan-milestone-gaps.md": 11809,
|
|
"plan-phase.md": 94427,
|
|
"plan-review-convergence.md": 26363,
|
|
"plant-seed.md": 12150,
|
|
"pr-branch.md": 15963,
|
|
"profile-user.md": 21624,
|
|
"progress.md": 32632,
|
|
"quick.md": 52730,
|
|
"reapply-patches.md": 20312,
|
|
"remove-phase.md": 8513,
|
|
"remove-workspace.md": 7916,
|
|
"resume-project.md": 17270,
|
|
"review.md": 59213,
|
|
"scan.md": 8880,
|
|
"secure-phase.md": 15006,
|
|
"session-report.md": 4044,
|
|
"settings-advanced.md": 40019,
|
|
"settings-integrations.md": 16257,
|
|
"settings.md": 33832,
|
|
"ship.md": 31658,
|
|
"sketch-wrap-up.md": 14267,
|
|
"sketch.md": 20369,
|
|
"smart-entry.md": 11489,
|
|
"spec-phase.md": 31987,
|
|
"spike-wrap-up.md": 15136,
|
|
"spike.md": 24939,
|
|
"stats.md": 6762,
|
|
"sync-skills.md": 6125,
|
|
"thread.md": 12508,
|
|
"transition.md": 22070,
|
|
"ui-phase.md": 27330,
|
|
"ui-review.md": 12548,
|
|
"ultraplan-phase.md": 10512,
|
|
"undo.md": 15323,
|
|
"update.md": 26024,
|
|
"validate-phase.md": 12235,
|
|
"verify-phase.md": 40949,
|
|
"verify-work.md": 41714
|
|
}
|