Files
gstack/autoplan/DRIVER.md.tmpl
T
Garry Tanandcapy-ai[bot] c71d764ba4 v1.91.115.0 feat: field list 2 wave A: autoplan round cap and public export, eval-plan diagnostics and model rules, --for review-voice (#3234)
* fix(capy): the install trailer says behind=<n> and its fix, so a stale install shows in every relayed trailer (field list 2 item 13, #2378)

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

* fix(capy): a lease records its holder's start identity, so a pid reused after a wake is reclaimed; a skipped session-start upgrade ends fail behind, never ok (GBRA-105, GBRA-106)

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

* fix(lease): stale needs proof (unreadable or malformed identities keep the lease), ps identity is timezone-independent, and reclaim never deletes a concurrent renewal

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

* feat(autoplan): enforced round cap and spend budget, deferred close, public export without machine paths, opt-in durable checkpoints (field list 2 W5-W7)

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

* fix(lease): one directory lock for publish, prune and reclaim; reclaim rereads the record judged stale, so a renewal is never deleted or hidden

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

* fix(lease): the directory lock names its holder; broken only when the holder is dead or its pid reused, unlock removes only its own lock, touch exits 3 under a live holder

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

* fix(lease): breakers serialize on .lock.break and reread the lock before removing it; gstack-skill-start reports a lease the held lock kept out

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

* docs(lease): name the double-crash limit of breaking a dead lock

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

* feat(capy): --for review-voice install profile, no-Drive bootstrap command, reviewer prompt trailer (field list 2 W11)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
(cherry picked from commit 89bf556c11)

* test: pin review-voice row, helpers row and the no-Drive fallback in existing install tests

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
(cherry picked from commit 7f6c70459a)

* test: the DRIVER template names the reviewer trailer relay (pregate lane)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
(cherry picked from commit 2545d9a6d2)

* test(context-budget): capy skill eager ceiling for the review-voice subagent paragraph (W11; ratchet protocol, capture value)

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

* feat(eval-plan): prereg diagnostics dry run (W8) and .gstack/eval-models.json lint (W9), WIP

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
(cherry picked from commit b509096218)

* feat(eval-plan): W8/W9 tests, docs/eval-models.md, troubleshooting anchors, /eval-plan steps

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
(cherry picked from commit 9335e45de2)

* test(eval-plan): eval-plan/SKILL.md names only defined codes and accepted flags

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
(cherry picked from commit a7a974d268)

* test(review-voice): the launch line points at the verdict's bun-only directory (#3233's launch contract)

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

* test(third-party-actions): the Aside drive-offer detector matches the product name, not the English idiom (paid run 38988927989 tpa-absent-linux false positive)

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

* fix(autoplan): export refuses artifact paths outside the run before writing; a deferred close keeps earlier undecided findings; reopening CEO grants Eng its rerun (review of #3234)

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

* test(autoplan-budget): bind the reservation expectation to lib/autoplan-budget's default estimate (test-of-test ratchet)

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

* fix(evals): the docs observer accepts the spawned-prefixed gstack-skill-start --help read

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

* fix(windows): curate capy-review-voice out of the Windows subset (POSIX launcher contract)

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

* docs: changelog entry for field list 2 wave A

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

* chore: stamp v1.91.115.0

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>
2026-10-17 02:40:45 +00:00

82 lines
4.3 KiB
Cheetah

# /autoplan driver: run the review loop from a parent agent
Read this file instead of `autoplan/SKILL.md` when you (a parent agent on any host) drive an
unattended /autoplan run through `gstack-autoplan`: the reviewers are subagents you dispatch,
and the runner keeps the state. The commands live in `<root>/bin/`, where `<root>` is the
folder that holds this `autoplan/` directory; `gstack-autoplan --help` and the first `next`
print `DRIVER: <root>/autoplan/DRIVER.md`. Run every command with the `GSTACK_LAUNCH`
assignments your installer printed. Read printed lines and files, never prose: every workflow
command ends with `GSTACK_RESULT: skill=autoplan status=<s> run=<dir>`, and every error line
ends with `(<CODE>)`.
## Phases and scope
{{AUTOPLAN_DRIVER_PHASES}}
The first `next` prints `SCOPE: ui=… (terms; visual; files) dx=… (detected) source=ui:<s>,dx:<s>`
(each axis is `flag`, `marker` or `detected`). UI needs a rendered file path or a UI term next
to a visual noun in the Implementation plan. To keep flags for later runs on the same plan, add
the `SCOPE_PIN:` marker it prints (`<!-- gstack-autoplan-scope: … -->`) as the plan's first
line yourself; gstack never writes the plan.
## The loop
1. `next` prints one `ATTEMPT: <id> phase=<p> voice=native|outside prompt=<file> result=<file>`
per voice. Dispatch the native prompt to a subagent on your model and the outside prompt to
a subagent on another model family (or `gstack-outside-voice run`). Each writes `result=`.
2. Submit each voice exactly once (`BOUND:`). Both voices in closes the phase (`PHASE_CLOSED:`).
3. Repeat `next` until `status=gate_pending` (`GATE: gate_rev=<n>`); render it with
`gstack-gate render <dir>/gate.json --all` and relay every page. You never approve the
gate for the owner. Offer `rec` (every recommendation, plan changes included) as the default.
4. `answer` with the owner's reply and `--by human` (the owner typed the tokens) or
`--by agent:<id> --owner-reply "<their words>"` (you relayed them); without `--by` an
unattended run refuses (`ANSWER_BY_REQUIRED`). `APPLY: <id> <title> -> <change>` lines are
accepted plan changes (status `amend_pending`): edit the plan, then `revise` (the printed
`NEXT:` names it), or `revise --settle <id>` when the line says no plan edit is needed. Until
then `next` refuses with `PLAN_AMEND_PENDING` and `export` will not mark the run complete.
5. `REOPENED: <phases>` means loop `next` again (Eng last). `APPROVED:` means `export`.
### On Capy
- Always drive `gstack-autoplan`; never hand-adapt `autoplan/SKILL.md`. A plan you reviewed by
hand is not an autoplan run: do not present it as one.
- Every prompt ends with a `GSTACK TRAILER` block: the reviewer runs the `--for review-voice`
install on its own machine (no ./setup, no skills; seconds when warm) and starts its reply
with the `gstack:` line. Never tell a reviewer that no install is needed; relay each
reviewer's line with its result, and treat a missing line as `gstack: fail not-installed`.
- Set `GSTACK_AUTOPLAN_CHECKPOINT_DIR` to the private project-user Drive folder (or opt every run in
with `gstack-config set autoplan_checkpoint drive`) so a run survives machine replacement: a
generation is published at rest, after each bound voice and after each phase transition; restore
with `resume --out <new dir> --from <dir>/<run>`, which never redispatches a bound voice.
### Commands
{{AUTOPLAN_DRIVER_COMMANDS}}
## Reviewer result format
Every prompt ends with this contract; `submit --result` enforces it, `submit --record` accepts
the looser record shapes above.
{{AUTOPLAN_DRIVER_RESULT_FORMAT}}
## Gate replies
A reply binds to the `gate_rev` you read (`--gate-rev`). Bare `yes`/`no` is unparsed, never guessed.
{{AUTOPLAN_DRIVER_GATE}}
## Run directory
{{AUTOPLAN_DRIVER_FILES}} Reviewer files: `<phase>-native-prompt.md`,
`<phase>-outside-prompt.md`, `<phase>-<voice>.<attempt>.md` (the reviewer writes it), its sealed
`<phase>-<voice>.<attempt>.bound.md` (what submit bound), `<phase>-consensus.{json,md}`,
`gate.json`, `decisions.jsonl`. `export` writes `plan.md`, `review-record.md`, `findings.jsonl`,
`tasks.jsonl`, `timing.json` and rehashes `run.json`; `gstack-artifact validate <dir>/run.json`
is the completion check. Copy the whole directory, never single files.
## Result codes
{{AUTOPLAN_DRIVER_CODES}}
{{COORDINATOR_CONTRACT}}