mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-05 16:34:00 +01:00
Garry Tanandcapy-ai[bot]
295b32e2c4
* feat(autoplan): gates print their cost, --owner-standing rec cites a standing approval, approvals mirror to the Captain's drive
E16: GATE_SPEND and GATE_REC_COST under every GATE line (lib/autoplan-gate-cost.ts), and a
Cost so far sentence in the owner brief; host-subagent attempts stay priced unknown.
E21: gstack-autoplan answer --owner-standing rec --by agent:<id> answers rec by citing the
newest standing approval covering autoplan recommendations from any branch's record; the
id lands on every decision row, in run.json and in the approvals import; refused with
STANDING_APPROVAL_ABSENT or STANDING_APPROVAL_INAPPLICABLE (urgent finding).
E22: the approvals mirror honours the approvals/ directory a Captain created in its drive,
between GSTACK_APPROVALS_DIR and the private project-user folder; gstack-approvals path
names the rule.
E23: the Eng phase asks for a performance budget and a bench step on hot-path changes.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(autoplan): review pass 1 — standing answers bind to the run's project and refuse recommend-edited gates, cost is an upper bound and reaches JSON and the Captain brief
Review pass 1 (6 specialists + red team) on the standing-approval and gate-cost change:
- the standing lookup resolves the approvals record of the repository the run's plan lives in,
never the caller's cwd (red team: project A's row answered project B's gate)
- standingAnswer refuses a gate that `recommend` edited (rec_rev > 0 or recommended_by), a
missing or unreadable findings.jsonl, and an outside-plan finding; the STANDING line flattens
control characters so a crew-writable row cannot forge a protocol line
- coversAutoplanRec matches the recommendation words in the owner's words only and rejects
negations; STANDING_APPROVAL_ABSENT's fix names every required gstack-approvals flag
- recReopens is the upper bound of the answer/revise rules (a plan change counts every phase,
a round grant its phase plus Eng); gate_cost rides the JSON payloads, `run` prints the lines
at its final gate, and `gstack-owner-brief render --captain` appends a ### Cost section
- locate keeps the other mirror roots as read_also so rows mirrored under an earlier rule stay
visible; gstack-approvals path prints READ_ALSO
- the Eng phase edit is size-neutral: five nearby phrases shortened so every host's autoplan
SKILL.md stays at its size-guard pin
- tests: isolated fixtures, the run's plan inside its own git repo, cross-project refusal,
amend_pending vs complete, recommend-then-standing, injection, gate_cost JSON, Captain brief
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (pass 2)
Standing approvals: the newest row about autoplan recommendations decides, so a later refusal
blocks older grants; rows whose id or date is not the recorded shape are never cited; the
project is fixed at init from the plan's physical path (run.json project_root) so a symlinked
plans folder or a checkpoint restore cannot borrow another repository's record. Gate cost:
recReopens counts every phase revise can keep or add and prices answers already recorded at
the gate; run --json emits one payload; the Captain brief's ### Cost sits above the relaying
trailer.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (pass 4, rule-23 exception)
Standing grammar fails closed: the newest standing row mentioning autoplan decides and grants only
with the canonical scope and affirmative owner words; same-id copies keep the newest recorded; id and
date are type-checked before the regexes. Gate cost prices the effective choices exactly as answer
does (p1d, carried overrides, non-recommended options). The run records project_slug beside
project_root so a restored run names its record on another machine, and project_root is a recorded
root for export --public.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* refactor(autoplan): drop --owner-standing rec (E21) from this PR
Pass-4 review (red team + Codex adversarial) still found that the keyword
grammar over the owner's standing words could read a refusal as a grant
("I won't take the recommendations", "Taking the recommendations is
forbidden" granted under the canonical scope) and that gstack-approvals add
deduped a same-day scope revocation as the grant. A free-text negation
parser cannot fail closed, so the standing answer leaves this change and
returns with a structured grant in its own PR.
Kept: GATE_SPEND/GATE_REC_COST cost lines and gate_cost (E16), the
Captain-drive approvals mirror with READ_ALSO (E22), the Eng perf-budget
question (E23). Removed: standingAnswer, standingRecApproval,
coversAutoplanRec, citableRow, project_root/project_slug in run.json,
STANDING_APPROVAL_* result codes and anchors, the standing DRIVER
paragraph and docs, test/autoplan-standing.test.ts (its E16/E22 cases move
to test/autoplan-gate-cost.test.ts).
Focused: 793 pass / 0 fail across 45 files; typecheck, typecheck:test,
format: cso:check clean; renders regenerated with gen:skill-docs --host all.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* RESTAMP: 1.91.268.0 -> 1.91.269.0 (stamped; queue_mode=stamp-at-merge base=origin/main@76aa68fc9e7a policy=base origin/main@76aa68fc9e7a:.gstack/ship-policy.json)
ship, next in queue at 1.91.269.0
STAMP_VERSION: 1.91.269.0
claims: ignored (stamp-at-merge)
stage version: done (wrote 1.91.269.0)
stage release_tool: done (bun scripts/gen-agents-digest.ts)
stage changelog: done (Unreleased -> 1.91.269.0)
stage stamp_paths: skipped (no stamp_paths in policy)
stage mirror: skipped (no mirror in policy)
stage apply: done (4 file(s))
diff --git a/CHANGELOG.md b/CHANGELOG.md
index e4e28308c..566bb525c 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,6 +1,6 @@
# Changelog
-## [Unreleased]
+## [1.91.269.0] - 2026-10-27
**An autoplan gate now arrives with its price, and the approvals record lands where the whole crew can read it.** Captains reported the same two frictions: review rounds and reviewer subagents had no credit figure at the gate, and the approvals mirror sat in a private project-user folder no sibling thread could read. The Eng phase also gains the performance-budget question, after a correctness pass doubled a consumer's p95 with no bench step to catch it. (The standing "take the recommendations" answer planned beside these, `answer --owner-standing rec`, was cut from this release after review: a keyword grammar over the owner's words could still read a refusal as a grant, so it returns with a structured grant in its own change.)
diff --git a/VERSION b/VERSION
index c31f84688..6437fa3e4 100644
--- a/VERSION
+++ b/VERSION
@@ -1 +1 @@
-1.91.268.0
+1.91.269.0
diff --git a/agents-digest/gstack-AGENTS.md b/agents-digest/gstack-AGENTS.md
index 3548eb690..4bdc2879f 100644
--- a/agents-digest/gstack-AGENTS.md
+++ b/agents-digest/gstack-AGENTS.md
@@ -1,4 +1,4 @@
-# gstack digest v1.91.268.0 — regenerate/re-copy after upgrading gstack
+# gstack digest v1.91.269.0 — regenerate/re-copy after upgrading gstack
Behavioral rules from gstack (https://github.com/garrytan/gstack), compressed
for agent hosts without a full skill install. The full skills add workflows,
diff --git a/node_modules b/node_modules
new file mode 120000
index 000000000..1de79460f
--- /dev/null
+++ b/node_modules
@@ -0,0 +1 @@
+/workspace/gstack-ap/node_modules
\ No newline at end of file
diff --git a/package.json b/package.json
index 7a672beb5..26a9702da 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
{
"name": "gstack",
- "version": "1.91.268",
+ "version": "1.91.269",
"description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
"license": "MIT",
"type": "module",
FILES: CHANGELOG.md VERSION agents-digest/gstack-AGENTS.md package.json
MERGE_CONDITION: sha=624f0eedec7c3aebdd0cecd70be4e4ebd10eb4af
next: NEW_VERSION=1.91.269.0; commit and push only the stamp diff above (FILES), with no edit of your own: the train's verify accepts the CHANGELOG only as the base's plus this PR's entry re-headed; merge with the expected head 624f0eedec and recompute on a stale queue.
GSTACK_RESULT: skill=restamp status=complete run=/workspace/gstack-ap/.gstack/tmp/restamp-journal.json
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>
85 lines
5.8 KiB
Cheetah
85 lines
5.8 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: `. <the GSTACK_LAUNCH_FILE it printed>` in the shell that runs the command,
|
|
never `export $(...)`, `env`, `printenv` or a bare `set` in a tool fence (a bare `export` prints every variable, credentials included). 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 with the two cost lines printed under `GATE:`: `GATE_SPEND:` (spent, worst case, cap, headroom, attempts; host-subagent attempts are priced unknown and counted at their reservation, so quote their real figure from the host's cost view) and `GATE_REC_COST:` (the phases `rec` can reopen and the estimate for them, an upper bound; `gate_cost` in `--json`).
|
|
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.
|
|
- Plans carry `## Before → after`, `## Why it matters`, `## What caused this work`, `## Big decisions`;
|
|
relay the printed `RELAY: gstack-owner-brief render --captain` output to your Captain (or the person),
|
|
then `gstack-approvals import --autoplan <dir>` after `answer` (`capy/skill/gstack/captain.md`).
|
|
|
|
### 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}}
|
|
|
|
Decision trail. A lane keeps `<run dir>/decisions.tsv` through `gstack-decision-trail <file> <phase> <decision> <why> <evidence> <result>` (one row per fork, unit, revert or blocker; evidence a pointer that resolves) and opens it with `gstack-decision-trail start <file> <run id>` when another run wrote it first. Before done it audits the trail against the transcript, superseding a wrong row with a new one rather than editing it, has a reviewer on another model family read the trail, and ends its report with an `Attention` section (`reviewed by <model>`, then the flags, or `No flags`). The full rule is [docs/unattended.md](../docs/unattended.md#the-decision-trail).
|