Skip to content

fix(autoplan): field report fixes, findings reach the gate, spend caps bind, run binds API results (GBRA-223) - #3781

Closed
garrytan wants to merge 16 commits into
mainfrom
gsta232-autoplan-wave
Closed

garrytan wants to merge 16 commits into
mainfrom
gsta232-autoplan-wave

Conversation

@garrytan

@garrytan garrytan commented Nov 1, 2026 •

Copy link
Copy Markdown
Owner
{
  "schema_version": 1,
  "pr": 3781,
  "head": "2a55f70e676b102ddea744436a47bc130f83df1f",
  "version": "1.92.20.0",
  "base": "main",
  "gate": {
    "typecheck": {
      "pass": 1,
      "fail": 0,
      "skip": 0
    },
    "remote_gate": {
      "pass": 20343,
      "fail": 0,
      "skip": 0
    }
  },
  "session_kind": "unattended",
  "head_tree": "d5796b3394c311e36f615605a9025245fddfb076",
  "product_patch_id": "51419523193a97cfdc351f37fa0ba12a45060cb1",
  "gstack_version": "1.92.20.0",
  "review_depth": {
    "depth": "full",
    "class": "gate",
    "runtime_lines": 352,
    "rules": "150435b0a543019a",
    "base": "fd5fcb4318844ad103ab4c0340dac1562197fa35",
    "registry": "fd5fcb4318844ad103ab4c0340dac1562197fa35",
    "gate_scan": {
      "tagged": 0,
      "head": "2a55f70e676b102ddea744436a47bc130f83df1f"
    },
    "reasons": [
      "gate-class",
      "runtime=352>50"
    ]
  },
  "pregate": "requires-remote cleared @d5796b3394c3 (1 checks, current for 2a55f70e676b)",
  "requires_remote": [
    "free-tests.yml/macos-named-regressions: https://github.com/garrytan/gstack/actions/runs/41288253305",
    "windows-free-tests.yml/windows-free-shard: https://github.com/garrytan/gstack/actions/runs/41288253315",
    "pregate.json/remote_gate: remote-gate tree=d5796b3394c3 tests=20343"
  ],
  "issues": {
    "fixes": [],
    "refs": [],
    "flakes": []
  },
  "docs": {
    "status": "current",
    "scope": "README.md, docs/, autoplan/DRIVER.md, plan-devex-review generated sections; branch gsta232-autoplan-wave at ec83ea8 (re-audit gsta232-docs-2)"
  },
  "review_loop": {
    "passes": 3,
    "blocking_found": 12,
    "deferred": 0,
    "noted": 1,
    "fixed": 18,
    "scope": "frozen",
    "dispatches": {
      "specialist": 1,
      "red-team": 1
    }
  },
  "review_targeted": {
    "classes": [
      "money"
    ],
    "rules": "baeb8f7ef7da92d0",
    "brief_sha": "7f92a0d0a8319c3c0e076fb3b1a4689c45120b2be2c14dfc7d4cb03aafa9d6a5",
    "product_patch_id": "51419523193a97cfdc351f37fa0ba12a45060cb1",
    "status": "done",
    "findings": 1,
    "raised_by": "targeted"
  }
}

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 rec applies its fix.

The /autoplan gate on the same plan: before, two Critical and two High findings never reached it; now each is an item, and rec applies its fix.

Text before/after

Before: GATE: gate_rev=1 items=3 with only uc1, uc2 and p1 (p1a approve as-is recommended). After: GATE: gate_rev=1 items=7 adds 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 has a) apply the fix to the plan (recommended) or b) carry it into the build as a blocking task, and p1b approve with the recommended changes: d1a, d2a, d3a, d4a is 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, run with 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 p1 choice 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 as answer_words and words_by, never as owner_reply. The default stays owner. P6 never carries those words forward (CARRY: no (gate_rev N was answered in agent:X's own words, not the owner's)), and gstack-approvals import lists that row under the agent, while --by names only rows holding the owner's words.

Approvals

Date Asked Exact words Outcome Covers Still pending
2026-10-31 Approve the plan "Cited evidence for /autoplan reviewers (GBRA-223 claim 5)" (autoplan run run-20261031220749, 4 decisions) “Do it” (Garry Tan, relayed by agent:GSTA-36) approved the reviewed plan (sha256 ae1e036c08e0), every recommendation taken none
2026-10-31 Approve fix plans P1–P5 for the GBRA-223 /autoplan field report “Fix plans approved: P1–P5, with P3 at Critical+High (your pick).” (GStack Minder (agent:GSTA-36)) approved P1–P5 as one /autoplan-area wave PR none
2026-10-31 Approve P6 (carry an owner's verbatim words forward only for unchanged items) “P6 go... Keep the refusal for any new or changed item, record the verbatim words as the basis, and put the consent change in the PR body so the train reviewer sees it. Fold it into the wave” (GStack Minder (agent:GSTA-36)) approved P6 consent change, folded into the wave none
2026-10-31 Pick the design for agent-worded gate answers (P7) “A. The gate accepts an agent's own words, recorded honestly as `words_by: agent:<id>` in `answer_words`, never in `owner_reply`, and never carried forward by P6... doesn't need Garry. Fold P7 into the wave so review pass 2 covers it.” (GStack Minder (agent:GSTA-36)) approved P7 design A, folded into the wave none

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 rec applies. A spend cap binds on any unattended host, and run reserves each API call's priced worst case before settling at real token cost. run binds 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 of owner_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 rec or all now carry the fixture's finding items with <id>b (test/helpers/autoplan-run-fixture.ts recCarrying), because rec now 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: p1b skipped GATE_REC_STALE after recommend changed the gate, so a reply could take recommendations the owner never saw; and run sent OpenAI no max_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

  • Targeted money reader, rerun at the frozen head after the main merge: one INFORMATIONAL finding. bin/gstack-autoplan:322 prices an API call's input at prompt bytes / 3 tokens, which is an estimate rather than a bound, so a symbol-dense prompt can settle slightly above its reservation. The output side, which dominates cost, is capped by the output limit.
  • Noted, not fixed: lib/outside-voice-api.ts:70 detects truncation only from the provider's max-tokens stop reason. A provider that cuts a response for another reason (a content filter) binds whatever partial text came back if it still holds a findings fence.

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:

  • docs/captain.md: Current (the --words-by attribution edit from 6a7f991 is present)
  • docs/unattended.md: Current
  • docs/troubleshooting.md: Current
  • docs/agent-ready-errors.md: Current
  • autoplan/DRIVER.md: Current
  • plan-devex-review/dx-hall-of-fame.md, plan-devex-review/sections/review-sections.md: Current

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 run path, 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)
  • Free Tests run 41288253305 and Windows Free Tests run 41288253315 (pull_request) on 2a55f70: success
  • Focused autoplan suite after the main merge (78 files): 1632 pass, 0 fail

garrytan and others added 14 commits October 31, 2026 22:19
…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>
@trunk-io

trunk-io Bot commented Nov 1, 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>

# 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
@capy-ai

capy-ai Bot commented Nov 1, 2026

Copy link
Copy Markdown
Contributor

Frozen in wave autoplan-e97beb7bf577 (branch wave/autoplan-e97beb7bf577) at 2a55f70. Push nothing here: a moved head drops this PR from the wave. Fixes go on the wave branch through its integrator.

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>
@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 2a55f70. Integrator changes touching this PR's files: d1909fa, f5e603c, da4fd19, 2317063, 033319e, 95a8f33, 167638d, 3b4968b, 4d9e0ac, 335e809, 97b04e0, f6a37b4, 4efc21a.

@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