Skip to content

feat: /autoplan --ceo-only runs the CEO review alone and asks nothing - #3743

Closed
garrytan wants to merge 9 commits into
mainfrom
gsta215-ceo-only-skill
Closed

garrytan wants to merge 9 commits into
mainfrom
gsta215-ceo-only-skill

Conversation

@garrytan

@garrytan garrytan commented Oct 31, 2026 •

Copy link
Copy Markdown
Owner
{
  "schema_version": 1,
  "pr": 3743,
  "head": "82dbdda2bcbc823dcf2d96cb70700a7de88839f4",
  "version": "1.91.379.0",
  "base": "main",
  "gate": {
    "typecheck": {
      "pass": 0,
      "fail": 0,
      "skip": 0
    },
    "ceo-only": {
      "pass": 208,
      "fail": 0,
      "skip": 0
    }
  },
  "session_kind": "unattended",
  "head_tree": "ec9db302470d3ea2feb5066c718943ce31392f7e",
  "product_patch_id": "4fc8730907786e2f842a7353aab7e27a37b73adb",
  "gstack_version": "1.92.3.0",
  "review_depth": {
    "depth": "full",
    "class": "gate",
    "runtime_lines": 101,
    "rules": "150435b0a543019a",
    "base": "fd5fcb4318844ad103ab4c0340dac1562197fa35",
    "registry": "fd5fcb4318844ad103ab4c0340dac1562197fa35",
    "gate_scan": {
      "tagged": 1,
      "head": "82dbdda2bcbc823dcf2d96cb70700a7de88839f4"
    },
    "reasons": [
      "gate-class",
      "runtime=101>50"
    ]
  },
  "pregate": "requires-remote cleared @ec9db302470d (1 checks, current for 82dbdda2bcbc)",
  "requires_remote": [
    "free-tests.yml/macos-named-regressions: https://github.com/garrytan/gstack/actions/runs/41288244136",
    "windows-free-tests.yml/windows-free-shard: https://github.com/garrytan/gstack/actions/runs/41288244130",
    "pregate.json/remote_gate: remote-gate tree=ec9db302470d tests=20194"
  ],
  "issues": {
    "fixes": [],
    "refs": [],
    "flakes": []
  },
  "docs": {
    "status": "current",
    "scope": "docs/, README.md, CONTRIBUTING.md, AGENTS.md against base 2d1b55d7..ce100cbb"
  },
  "review_loop": {
    "passes": 1,
    "blocking_found": 0,
    "deferred": 0,
    "noted": 1,
    "fixed": 2,
    "scope": "frozen",
    "fix_checks": 4,
    "dispatches": {
      "specialist": 3,
      "red-team": 1
    }
  },
  "review_targeted": {
    "classes": [
      "gate"
    ],
    "rules": "baeb8f7ef7da92d0",
    "brief_sha": "7f92a0d0a8319c3c0e076fb3b1a4689c45120b2be2c14dfc7d4cb03aafa9d6a5",
    "product_patch_id": "4fc8730907786e2f842a7353aab7e27a37b73adb",
    "status": "done",
    "findings": 0,
    "raised_by": "targeted"
  },
  "carry": {
    "from": "e56602051aa74dba4523e28b3d741d8469d57770",
    "reason": "base merge + test-only change + release metadata",
    "product_patch_id": "4fc8730907786e2f842a7353aab7e27a37b73adb",
    "changed_paths": [
      "product:.github/workflows/free-tests.yml",
      "product:.gstack/ship-policy.json",
      "metadata:CHANGELOG.md",
      "product:README.md",
      "product:TODOS.md",
      "metadata:VERSION",
      "metadata:agents-digest/gstack-AGENTS.md",
      "product:autoplan/SKILL.md.tmpl",
      "product:bin/gstack-capy-install",
      "product:bin/gstack-docs-candidate",
      "product:bin/gstack-doctor-components.sh",
      "product:bin/gstack-eval-plan",
      "product:bin/gstack-ff-update",
      "product:bin/gstack-global-discover.ts",
      "product:bin/gstack-office-hours-review",
      "product:bin/gstack-plan-reality",
      "product:bin/gstack-redact-prepush",
      "product:bin/gstack-repo-mode",
      "product:bin/gstack-review-dispatch",
      "product:bin/gstack-review-log",
      "product:bin/gstack-review-plan",
      "product:bin/gstack-review-read",
      "product:bin/gstack-session-update",
      "product:bin/gstack-ship-queue",
      "product:bin/gstack-ship-receipt",
      "product:bin/gstack-skill-start",
      "product:bin/gstack-slug",
      "product:bin/gstack-tasks",
      "product:bin/gstack-upgrade",
      "product:browse/bin/remote-slug",
      "product:captain/SKILL.md",
      "product:captain/SKILL.md.tmpl",
      "product:captain/templates/CREW.md",
      "product:captain/templates/READY.md",
      "product:captain/templates/merge-train-peer.md",
      "product:capy/skill/gstack/captain.md",
      "product:careful/bin/hook-extract.sh",
      "product:design-consultation/SKILL.md.tmpl",
      "product:design-html/SKILL.md",
      "product:design-html/SKILL.md.tmpl",
      "product:design-review/SKILL.md.tmpl",
      "product:design-shotgun/SKILL.md.tmpl",
      "product:design/scripts/live-gemini-check.ts",
      "product:design/src/auth.ts",
      "product:design/src/check.ts",
      "product:design/src/cli.ts",
      "product:design/src/commands.ts",
      "product:design/src/design-to-code.ts",
      "product:design/src/diff.ts",
      "product:design/src/evolve.ts"
    ],
    "merge_commits": 1,
    "range_diff": "1:  7cf44db6d = 1:  7cf44db6d feat(autoplan): --ceo-only runs the CEO review alone with zero questions (GST-537)\n2:  8f9670372 = 2:  8f9670372 fix: pre-landing review fixes\n3:  45352544d = 3:  45352544d test: classify autoplan-ceo-only in the Codex host metadata\n4:  81863772a = 4:  81863772a fix: select autoplan-ceo-only on the skills it runs; say it needs Claude Code\n5:  303bdc68a = 5:  303bdc68a test: run autoplan-ceo-only in the marathon lane\n6:  ce100cbbe = 6:  ce100cbbe docs: changelog entry for /autoplan --ceo-only\n7:  e56602051 = 7:  e56602051 test: count the autoplan-ceo-only paid file in the shard inventory",
    "covers": [
      "pre-landing review",
      "adversarial review",
      "gate integrity",
      "documentation audit"
    ],
    "reruns": [
      "CI at head (gstack-ship-queue ready requires it); test and helper code changed since the reviewed head runs there unreviewed"
    ],
    "ancestry": "linear",
    "trees": [
      "2be180eb878215cf818ddb6021120b4d6c481ec9"
    ]
  }
}

What changed

New /autoplan --ceo-only section: CEO phase only, zero questions, ends status=reviewed and approves nothing

New /autoplan --ceo-only section (autoplan/sections/ceo-only.md): it runs the CEO phase only, asks no questions, ends status=reviewed and approves nothing.

gstack-ceo-mode-handoff --ceo-only: names Step 0E's rule instead of failing on an unknown flag

gstack-ceo-mode-handoff --ceo-only now names Step 0E's rule. Before, it failed on an unknown flag.

Text before/after
before: gstack-ceo-mode-handoff: unknown argument: --ceo-only   (exit 2)
after:  Auto-selected review mode → HOLD SCOPE (CEO-only run: Step 0E's rule). Approved decisions: none.   (exit 0)

Why

Garry wanted a CEO review that "just automatically does the right thing", and the planning eval (GST-538, due Nov 3) needs a gstack CEO arm that a harness can run without a simulated user. Before this change, /autoplan always went on to the Eng review and stopped at an approval question, and standalone /plan-ceo-review asks for the mode and offers to chain. Now /autoplan --ceo-only --no-outside runs the CEO review alone, takes every recommendation, and leaves a ceo-review.md report.

Summary

  • /autoplan --ceo-only runs Phase 0, the outside-reviewer preflight and the CEO phase. Every question takes its recommendation and gets an audit-trail row. User challenges are listed and never applied. The run ends GSTACK_RESULT: skill=autoplan status=reviewed run=<dir> with <run dir>/ceo-review.md. --no-outside keeps the whole review on one model.
  • The section is lazy. Only its section-index row is added to autoplan/SKILL.md, and a free test pins that no other autoplan file reads it, so a normal /autoplan run never loads it.
  • status=reviewed joins the GSTACK_RESULT statuses. docs/unattended.md gets a "CEO-only runs" section. It says the mode needs Claude Code for now, and that gstack-autoplan (the driver) and run.json get it in PR 2.
  • New paid case autoplan-ceo-only fails if the run asks anything, loads a skipped phase's file, misses a ceo-review.md heading, ends with another status, or leaves new files in HOME outside its folders.

Plan: GST-537 gate brief (captain drive plans/GSTA-215.md), autoplan run autoplan-20261031180042, approved with "Do it".

Blast radius

The prose change is one new section file plus one section-index row in autoplan's Claude render. The section is read only when the invocation names --ceo-only, and test/autoplan-ceo-only.test.ts checks that no other autoplan section, the driver or lib/autoplan-*.ts names it (script ran). ResultStatus widens by one value that parseResult accepts, and nothing in run.json writes it yet (file read: lib/headless-artifacts.ts). Non-Claude hosts inline autoplan and do not carry the section, so --ceo-only does nothing there. The docs say so.

Gate changes

  • test/helpers/carve-guards.ts: autoplan maxSizeRatio 1.1511 → 1.1723. That is the measured 119,545 / 101,979, which is +2,276 B for the section and its index row (GST-537, GStack Minder approved A1, 2026-10-31). A free test pins that a normal run never reads the section.
  • autoplan-ceo-only runs in the marathon lane (weekly, non-blocking). Autoplan PRs no longer run this case before merge. It measures 349–984 s, and gate shards must stay under 600 s (I5, test/paid-shards.test.ts). GStack Minder approved moving it to the periodic tier, but the periodic lane is at its 40-slice cap, so it sits in marathon (7 of 8 slots), like plan-ceo-split-overflow and design-motion-showcase. No workflow file changed.

Behavior changes

  • New terminal status reviewed in GSTACK_RESULT lines (lib/headless-artifacts.ts).
  • gstack-ceo-mode-handoff accepts --ceo-only; --auto with --ceo-only exits 2 ("--auto and --ceo-only conflict").

Approvals

Date Asked Exact words Outcome Covers Still pending
2026-10-31 Approve the plan "Plan: a CEO-only, zero-question mode for /autoplan (GST-537)" (autoplan run autoplan-20261031180042, 3 decisions) “Do it” (Garry (via GStack Minder), relayed by agent:jam_01M69HKBK0FV2CKVC2HN34D9NN) approved the reviewed plan (sha256 1a04aaa046a3), every recommendation taken none
2026-10-31 Raise autoplan's carve maxSizeRatio for the --ceo-only section “Minder approved A1: raise autoplan's maxSizeRatio to 1.1723, exactly as measured” (GStack Minder) approved test/helpers/carve-guards.ts autoplan ratio 1.1511 -> 1.1723 with the measurement and a no-read test none
2026-10-31 Keep autoplan-ceo-only in the gate tier (census cap raise) or move it out (B) “B: move it to the periodic tier and record the 860 s wall in the periodic seed. Leave the census workflow untouched” (GStack Minder) approved the paid case leaves the gate tier for a weekly lane; no workflow change none

Source: gstack-approvals record for gsta215-ceo-only-skill (display only; not an approval citation).

Test Coverage

All new code paths have test coverage: each of the 6 changed runtime files has a changed test that names it (deterministic coverage map).
Tests ran: typecheck count unavailable (exit 0)
Tests ran: ceo-only 208

Pre-Landing Review

No issues at the blocking floor. Pass 1 (specialists, then the red team) found 2 informational test gaps, both fixed: the skipped-phase check now reads Bash, Grep and Glob arguments, and the test's temp dirs are cleaned up. Four fix-checks found nothing. The final one ran on the frozen tree. A native adversarial pass on the frozen tree found nothing at the floor.
REVIEW_LOOP: passes=1 blocking_found=0 deferred=0 noted=1 fixed=2 scope=frozen fix_checks=4 dispatches=4
Gate edits: 1 listed, 1 read, 1 finding — 1 kept (reason below), 0 restored, 0 open

  • gate: carve size ratio, test/helpers/carve-guards.ts, kept: GStack Minder approved A1 on the measured ratio (GST-537, 2026-10-31)
    Outside review (openai/gpt-6.1-sol): request changes on two Medium items, both below the floor. Non-Claude hosts don't carry the section: documented as Claude Code only. ceo-review.md lives in the shared .gstack/tmp/autoplan dir, so a later run in the same repo replaces it: noted, and PR 2's driver gives each run its own folder.

Review notes

Below the blocking floor (advisory, informational, test-gap or wording items); recorded here and not fixed in this PR.

  • INFORMATIONAL lib/headless-artifacts.ts:206: reviewed is in ResultStatus but not in the run.json schema or the terminal sets (PR 2 adds it with the driver flag).
  • INFORMATIONAL autoplan/sections/ceo-only.md.tmpl:7: in a SESSION_KIND: unattended session, both this section and sections/unattended.md apply (PR 2's driver flag covers parent-driven runs).
  • INFORMATIONAL autoplan/SKILL.md:269: the section-index row comes after the prerequisite offer, so zero questions relies on the model reading ahead. All 5 paid sessions here asked nothing.
  • INFORMATIONAL autoplan/sections/ceo-only.md.tmpl:10: taking a preamble block's non-consenting default may record a decline on a first run.
  • INFORMATIONAL autoplan/sections/manifest.json:49: non-Claude hosts inline autoplan and do not carry the section.
  • INFORMATIONAL autoplan/sections/ceo-only.md.tmpl:31: ceo-review.md lives in the fixed .gstack/tmp/autoplan folder.
  • INFORMATIONAL test/skill-e2e-autoplan-ceo-only.test.ts:99: the stray-write check sees new files under HOME only. The changelog wording now says so.

Eval Results

  • Paid case autoplan-ceo-only (run gsta215-e2e-4, branch tree before the review fixes): PASS, $4.75, 62 turns, 860 s. Zero questions, status=reviewed, ceo-review.md complete, no stray writes. Earlier runs: run 2 was red only on Bun's cache under HOME, and run 3 only on the machine's git-wrapper log. Both were detector fixes.
  • No-loss smoke (R44, preregistered, n=3, claude-opus-5-5): the planted CEO-level flaw was caught by --ceo-only 3/3, standalone /plan-ceo-review 3/3, and the no-gstack arm 3/3. The blind judge (gpt-6.1-sol) scored all 3 decoys as misses. --ceo-only asked 0 questions. That is no detected loss at n=3. These home-field plans don't separate gstack from a plain review; GST-538 is the powered reading. Smoke cost: $21.54.

Plan Completion

PR 1 items 1–5 of the gate brief: the skill path, the zero-question test, the no-loss smoke, docs, and the gate-change note. Items 6–10 (the gstack-autoplan next --ceo-only driver flag) are PR 2.

TODOS

No TODO items completed in this PR.

Documentation

Status: current. No documentation edits were needed.

Scope: base 2d1b55d to head ce100cb (14 changed files, nothing staged, unstaged or untracked) in gsta215-ceo-only-skill. Authored docs, templates and the changelog fragment were audited against the code diff (lib/headless-artifacts.ts, bin/gstack-ceo-mode-handoff, autoplan/sections/ceo-only.md.tmpl).

Documentation health:

  • docs/unattended.md: current. The reviewed status, the CEO-only runs section and its phase scope match the code.
  • autoplan/SKILL.md, autoplan/sections/ceo-only.md, autoplan/sections/ceo-only.md.tmpl: current.
  • changelog.d/gsta215-ceo-only-skill.md: current, not modified.
  • AGENTS.md, README.md, docs/skills.md: not stale, but do not mention --ceo-only.

Coverage debt:

  • Reference for --ceo-only and --no-outside exists only in docs/unattended.md. docs/skills.md /autoplan does not list them (common gap).
  • No how-to, tutorial or explanation docs for CEO-only runs.
  • No architecture diagram drift.

Test plan

  • bun run typecheck: exit 0
  • bun test test/autoplan-ceo-only.test.ts test/codex-host.test.ts test/touchfiles.test.ts test/paid-shards.test.ts test/evals-workflow-wiring.test.ts test/parity-suite.test.ts test/skill-md-size-guard.test.ts: 208 pass
  • Remote pregate (Ubicloud), tree 2be180eb8782: 19,946 tests, 0 failed; macOS named regressions and Windows free shard cleared by PR CI runs 41241115601 and 41241115501 at e566020
  • Paid autoplan-ceo-only (gsta215-e2e-4): PASS

garrytan and others added 7 commits October 31, 2026 19:19
…ons (GST-537)

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>
…ude Code

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>
@trunk-io

trunk-io Bot commented Oct 31, 2026

Copy link
Copy Markdown

Merging to main in this repository is managed by Trunk.

  • To merge this pull request, check the box to the left or comment /trunk merge below.

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>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

# Conflicts:
#	test/eng-finding-retry-budget.test.ts
@capy-ai

capy-ai Bot commented Nov 1, 2026

Copy link
Copy Markdown
Contributor

Frozen in wave autoplan-e97beb7bf577 (branch wave/autoplan-e97beb7bf577) at 82dbdda. Push nothing here: a moved head drops this PR from the wave. Fixes go on the wave branch through its integrator.

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>
@capy-ai

capy-ai Bot commented Nov 2, 2026

Copy link
Copy Markdown
Contributor

Landed in wave #3788 as v1.92.50.0 (90a170c), merged from this PR's pin 82dbdda. Integrator changes touching this PR's files: 335e809, f6a37b4.

@capy-ai capy-ai Bot closed this Nov 2, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant