Repository navigation
Conversation
…aim 2) The DX error contract told both autoplan DX voices to title capped findings exactly CAP4:<path>:<item>, so gates, tasks and reconcile saw a bare code. The title is now CAP4:<path>:<item> <what fails>; the grader already parses that shape. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…(GBRA-223 claim 1) Plan reviews name files, rarely lines, and reconcile associated by location only when both findings had a line, so findings both voices raised on one file were filed new and native-only. A same-file pair with a missing line is now associated as unverified (basis file), never confirmed; a CAP code no longer counts in title comparison. DRIVER.md names submit --reconcile. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…y items (GBRA-223 claim 3) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…-usd persists; DRIVER names --usage-usd (GBRA-223 claim 4) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…onse, --max-tokens; DRIVER documents run (GBRA-223 claim 6) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
… nothing new (GBRA-223 claim 7) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…nder its size pin Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…s reserve no host default, cross-file title pairing, paired severity counted) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…ass pairing, partial replies keep p1-dependent defaults open, outside refusal degrades) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
… carry an agent's own words, import each row under its own answerer (GEVA-2) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…end the output limit they reserve for) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
…ests; bind run-api limit to DEFAULT_MAX_TOKENS Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
|
Merging to
After your PR is submitted to the merge queue, this comment will be automatically updated with its status. If the PR fails, failure details will also be posted here |
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> # Conflicts: # test/fixtures/skill-md-size-allowlist.json
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> # Conflicts: # test/fixtures/skill-md-size-allowlist.json
Contributor
|
Frozen in wave |
garrytan
added a commit
that referenced
this pull request
Nov 1, 2026
…ze after #3781's DX trim Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
capy-ai Bot
added a commit
that referenced
this pull request
Nov 2, 2026
* fix(eval-plan): per-arm pilot projection and --seat-metered arms (#3653) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): guard tolerates Claude Code's cwd-reset footer and recovers after an unreadable init (#3651) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (journal reader strips the cwd-reset footer; an init with no text block no longer locks the session) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: journal reader skips a failed or unreadable init, as invocation() does Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(autoplan): --ceo-only runs the CEO review alone with zero questions (GST-537) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(eval-plan): all-seat pilot, single-attempt arm and --seat-metered CLI wiring Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(eval-plan): summed deviation adds arm deviations, matching the summed band (arms share rows) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (test pins an unpriced seat-metered arm) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (seat-metered declaration fixed per --out, price row still required, a real charge settles as spent) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: classify autoplan-ceo-only in the Codex host metadata Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: a seat-metered arm that settles a charge is projected as a priced arm Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: select autoplan-ceo-only on the skills it runs; say it needs Claude Code Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(skills): /eval-plan --seat-metered and per-arm projection Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(eval-plan): skill prose stays under its context budget and carries no $N token Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: run autoplan-ceo-only in the marathon lane Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(skills): a seat-metered arm leaves the seat set once it settles a charge Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: changelog entry for /autoplan --ceo-only Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(autoplan): init_failed covers unreadable init output and the cwd-reset line (#3651) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: count the autoplan-ceo-only paid file in the shard inventory Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(autoplan): #3651 tests pass the test-code type ratchet Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(dx): CAP finding titles carry a one-line description (GBRA-223 claim 2) The DX error contract told both autoplan DX voices to title capped findings exactly CAP4:<path>:<item>, so gates, tasks and reconcile saw a bare code. The title is now CAP4:<path>:<item> <what fails>; the grader already parses that shape. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): reconcile pairs same-file findings that carry no line (GBRA-223 claim 1) Plan reviews name files, rarely lines, and reconcile associated by location only when both findings had a line, so findings both voices raised on one file were filed new and native-only. A same-file pair with a missing line is now associated as unverified (basis file), never confirmed; a CAP code no longer counts in title comparison. DRIVER.md names submit --reconcile. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): open Critical and High findings reach the gate as apply items (GBRA-223 claim 3) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): a spend cap binds on every unattended host; --estimate-usd persists; DRIVER names --usage-usd (GBRA-223 claim 4) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): run binds complete api results, names a truncated response, --max-tokens; DRIVER documents run (GBRA-223 claim 6) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(autoplan): carry an item-by-item answer when the later gate asks nothing new (GBRA-223 claim 7) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(dx): trim the compact error contract so plan-devex-review stays under its size pin Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes (p1b applies finding fixes, api attempts reserve no host default, cross-file title pairing, paired severity counted) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: review fixes (priced api reservations, no file-only twins, two-pass pairing, partial replies keep p1-dependent defaults open, outside refusal degrades) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * P7: record whose words answered a gate (--words-by agent:<id>), never carry an agent's own words, import each row under its own answerer (GEVA-2) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: review pass 2 (p1b needs --rec-hash after recommend; api calls send the output limit they reserve for) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * changelog: fragment for the /autoplan field-report wave (GST-672) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: captain record notes --words-by agent attribution Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: follow finding apply items in approval-class and Captain flow tests; bind run-api limit to DEFAULT_MAX_TOKENS Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * wave autoplan: lower the gemini plan-devex-review pin to its exact size after #3781's DX trim Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): CAP titles on different paths never match by title in reconcile or confirm rounds (wave review) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): a truncated api call settles its cost and a retry is admitted afresh against the cap Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): an applied finding stays open until the revised plan is reviewed; a shared location alone never twins two findings Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(approval): a plan gate answered in an agent's own words is not owner approval Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(gate): a new answer replaces the earlier answer's authorship and words Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): a failed api call with no usage keeps its attempt open; reservations price the bound prompt (wave fix-check) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): a spend cap fails closed: only a call refused before sending keeps its attempt; a sent call with unknown usage settles at its reservation Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(autoplan): the 16384 output default applies to both providers; changelog for the wave's integrator fixes Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(autoplan): how run settles a failed api call; changelog scopes it to the native voice Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): a spend cap fails closed on every exit of run; an unpriced model reserves the default once a cap is set Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(autoplan): every sent call settles; an unpriced model under a cap reserves the default Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(autoplan): DRIVER and help say a cap reserves in any session kind and how run settles a sent call Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --------- Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What changed
The /autoplan gate on the same plan: before, two Critical and two High findings never reached it; now each is an item, and
recapplies its fix.Text before/after
Before:
GATE: gate_rev=1 items=3with only uc1, uc2 and p1 (p1a approve as-isrecommended). After:GATE: gate_rev=1 items=7adds d1 (Critical: the install check lies by omission), d2 (High: gate reuse on tree equality alone is unsound), and d3 and d4 (the same findings from Eng). Each hasa) apply the fix to the plan(recommended) orb) carry it into the build as a blocking task, andp1b approve with the recommended changes: d1a, d2a, d3a, d4ais now recommended.Why
OpenClaw ran /autoplan on a real plan and hit six problems in one run (GBRA-223). Findings without a line number counted as new from both voices, open Critical findings never reached the gate, a spend cap did nothing on an unattended host,
runwith the API runner never bound a result, and an earlier item-by-item answer was asked again. We reproduced each on main with a failing test first (GST-672), and each is fixed here. A follow-up from GEVA-2 found that an agent's own words were stored as the owner's reply, so the gate now records whose words answered it.Blast radius
The changes stay inside gstack-autoplan (reconcile, gate list, answer, carry, budget, run), the outside-voice API caller, the DX cap titles and gstack-approvals import. The answer and carry changes alter what counts as the owner's consent, so the two consent notes below name exactly what moved. After merging main (fd5fcb4, v1.92.20.0), the remote gate ran the free suite, 20343 tests with 0 failures, on tree d5796b33 (script ran), and Free Tests and Windows Free Tests passed on 2a55f70. A scratch merge of this branch with #3751, #3762 and #3743 together merged cleanly, and the skill size guard plus the four overlapping test files (374 tests) passed on it.
Consent change 1 (P6, approved by the Captain). When a later gate revision asks nothing new (every item is carried by origin), the owner's earlier
p1choice is replayed and their exact tokens are recorded as the basis. Any new or changed item still goes to the owner, and the carry refuses.Consent change 2 (P7, design A, approved by the Captain).
gstack-autoplan answer --words-by agent:<id>records an agent's own words asanswer_wordsandwords_by, never asowner_reply. The default staysowner. P6 never carries those words forward (CARRY: no (gate_rev N was answered in agent:X's own words, not the owner's)), andgstack-approvals importlists that row under the agent, while--bynames only rows holding the owner's words.Approvals
Source: gstack-approvals record for gsta232-autoplan-wave (display only; not an approval citation).
The first row is the separately approved claim-5 plan (
--evidence). It is built in a later PR, not in this one.Summary
Seven fixes from the field report, each its own commit with a failing-first test. Reconcile now pairs same-file findings that carry no line, and a same-file pair never merges into one gate item. DX cap findings carry a one-line description. Open Critical and High findings become gate items that
recapplies. A spend cap binds on any unattended host, andrunreserves each API call's priced worst case before settling at real token cost.runbinds complete API results and names a truncated one. An unchanged item-by-item answer carries forward.answer --words-by agent:<id>keeps an agent's words out ofowner_reply.Test Coverage
New failing-first tests: test/autoplan-pairing.test.ts, test/autoplan-gate-judgment.test.ts, test/autoplan-budget.test.ts, test/autoplan-run-api.test.ts (a local fake provider, no key or network), test/autoplan-carry.test.ts and test/approval-record.test.ts. Each was shown failing on the pre-fix source before passing. Existing tests that answered a gate with bare
recorallnow carry the fixture's finding items with<id>b(test/helpers/autoplan-run-fixture.tsrecCarrying), becauserecnow applies those fixes and leaves the run amend_pending.Tests ran: typecheck count unavailable
Tests ran: remote_gate 20343
Pre-Landing Review
Three passes. Pass 1 (five readers plus the outside voice) found 16 findings and fixed every blocking one. Pass 2 (fix-check plus targeted money readers) found two blocking findings, both fixed in 7be60fd:
p1bskipped GATE_REC_STALE afterrecommendchanged the gate, so a reply could take recommendations the owner never saw; andrunsent OpenAI nomax_completion_tokens, so the spend it reserved did not bound the call. The review plan then said stop, so there was no third full pass. Three test expectations that broke on the remote gate were fixed in ec83ea8; one fix-check read those hunks and returned NO FINDINGS.REVIEW_LOOP: passes=3 blocking_found=12 deferred=0 noted=1 fixed=18 scope=frozen dispatches=2
Gate edits: 47 listed, 38 read, 0 findings — 0 kept, 0 restored, 0 open
Outside review: ran on pass 1 (openai), findings judged and fixed.
Review notes
Eval Results
Paid DX eval (plan-devex-review behavior, three trials) passed, $1.09 total (t1 $0.3765, t2 $0.3704, t3 $0.3405
total_cost_usd).Plan Completion
P1 to P7 from the approved fix plans are all built. Claim 5 (
--evidence) is approved separately and ships in a later PR.TODOS
No TODO items completed in this PR.
Documentation
Status: current. Re-audit after the test-only commit ec83ea8; no doc edits were needed.
Scope: branch gsta232-autoplan-wave against ca7bd68 at ec83ea8 (43 files, committed only, no staged, unstaged or new files). Since the accepted gsta232-docs-1 audit, only test/approval-classes.test.ts, test/capy-captain-flow.test.ts and test/autoplan-run-api.test.ts changed. Their gate answers (
all except <finding>b, approving with p1=b) and the DEFAULT_MAX_TOKENS (16384) binding match behavior the docs already describe.Documentation health:
Coverage debt: --words-by, --max-tokens, --estimate-usd and --usage-usd have reference coverage in autoplan/DRIVER.md and how-to coverage in docs/unattended.md, and the truncated outside-review error has a troubleshooting entry. No tutorial covers the api-runner
runpath, a common gap. Diagram drift: none found.Test plan
bun run typecheck: pass (finish lane, tree 300ab834)UBI_OWNER=gsta232 gstack-pregate --stage tests --remote: 20343 tests, 0 failed, $0.06, tree d5796b33 (after the main merge)