mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-03 23:37:53 +01:00
Merge main e85005482 (v1.93.27.0, train 94) into wave/review-53cfb5bfe011 (rule 19 grant)
Conflicts resolved keeping both sides: bin/gstack-review-dispatch (main's targetedRead record plus the wave's exclude digest on the rendered event); bin/gstack-ship-receipt (main's receiptTargetedAtHead and targetedClassesSince plus the wave's receiptReviewAtHead and receiptExclude; both help paragraphs); docs/troubleshooting.md (main's targeted-refusal fix plus the wave's review_exclude, REVIEW_DIFF_TOO_LARGE, REVIEW_DIFF_UNREADABLE and REVIEW_EXCLUDE_REFERENCE entries); ship/DRIVER.md.tmpl (main's line, DRIVER.md 12,241 B); test/review-packets-removed.test.ts (both replay lists, the wave's placeholder brief-body hashes under main's GST-986 test). test/review-targeted.test.ts follows main's DRIVER wording ([--review-targeted @<f>]), which main's own copy of that check in test/review-targeted-record.test.ts pins.
This commit is contained in:
commit
feeec2e760
74 files changed
+1618
-316
No files matched your search
@@ -17,7 +17,7 @@
|
||||
"scripts/lib/published-text.ts": {"blob":"3f2e4d616b5dd0204035710c66b64d49055c5714","since":6},
|
||||
"scripts/lib/shard-engine.ts": {"blob":"dc714d7d897aed185c0ec3d2c92ad22d954039e5","since":6,"nonBehavioral":"createShardSandbox drops the Capy launch markers (GSTACK_SESSION_KIND, GSTACK_CAPY, GSTACK_EPHEMERAL, GSTACK_INSTALL_VERDICT) from shard environments; CI never sets them, so no case's input or verdict changes there, and on a Capy machine fixtures now see the session kind they set themselves instead of the installer's"},
|
||||
"scripts/test-paid-shards.ts": {"blob":"5439d0a8f6e1569fa7c924af20d67c30c81d5d30","since":6,"nonBehavioral":"credential rejections are classed infra instead of assertion: no case's pass or fail changes; only failed trials whose provider rejected the run's key move class, so no rerun spends on a rejected key"},
|
||||
"scripts/test-pr-profile.ts": {"blob":"44ae88bebf8f716f70a3bd836c8bedb03e6653e8","since":6,"nonBehavioral":"FREE_ONLY_PR_FILES gains scripts/lib/shard-jobs.ts (free-runner module) and .github/workflows/windows-smoke.yml (a workflow no paid case reads); both change only which PR paths select paid cases, never how a case runs or is judged"},
|
||||
"scripts/test-pr-profile.ts": {"blob":"dd0ca92bcf8493fd5c1e9d399cc3bc74ec70c469","since":6,"nonBehavioral":"FREE_ONLY_PR_FILES gains USING_GBRAIN_WITH_GSTACK.md (a root guide no skill prompt or paid fixture reads); it changes only which PR paths select paid cases, never how a case runs or is judged (GST-1027)"},
|
||||
"scripts/test-strict-output.ts": {"blob":"01185d20dc9761b04b9b2f751ec98664fe0eaf93","since":6},
|
||||
"test/helpers/agent-sdk-runner.ts": {"blob":"d66dac458b8c13250973e550edf8087d4044cd0b","since":6,"nonBehavioral":"Cost attribution only (GSTA-150 PR 2): a display-label record carries cost_case_id from runSkillTest's testName and the report binds its cost by it while the failed record and failure class still come from the named records (test/paid-report-cost.test.ts pins both); an aborted Agent SDK session logs its streamed usage as streamed_cost_usd, used only when a case has no record; a listed model-free case with no record or session is a known $0. No case's execution, outcome, failure class, rerun eligibility or panel verdict changes, so no pass-rate series resets. Also: runAgentSdkTest now validates systemPrompt before starting; every live caller already passed the claude_code preset, so the prompt the model sees is unchanged and no verdict can change"},
|
||||
"test/helpers/auq-substance-panel.ts": {"blob":"4881260ef793668e4963a062db6d06a5e1f7a40f","since":6},
|
||||
|
||||
@@ -245,6 +245,7 @@ export const FREE_ONLY_PR_FILES = [
|
||||
'scripts/paid-test-durations.json',
|
||||
'scripts/ubicloud/**',
|
||||
'capy/skill/**', // The vendored Capy skill (Drive bootstrapper): run by Capy agents, read by no paid case; test/capy-skill-wrapper.test.ts covers it.
|
||||
'USING_GBRAIN_WITH_GSTACK.md', // The /setup-gbrain guide: README, docs/gbrain-quick-tour.md and free tests read it; no skill prompt or paid fixture does (GST-1027).
|
||||
'captain/templates/**', // The /captain crew templates (CREW.md, merge-ask.md, slot-call.md, …): copied into a Captain's drive by people and Captains, read by no paid case; free test/captain-skill.test.ts covers them (#3499).
|
||||
'tsconfig.test.json', // Read only by `tsc -p tsconfig.test.json` (typecheck:test); Bun's runtime reads tsconfig.json.
|
||||
'.gitignore', // Changes which untracked files git reports, never tracked content a case reads.
|
||||
|
||||
Reference in new issue
Block a user