Files
gstack/lib/autoplan-state.ts
T
Garry Tanandcapy-ai[bot] 945ac301a9 v1.91.97.0 fix: closable unattended /autoplan runs on Capy (field wave B, items 6-13) (#3165)
* docs(designs): gstack field wave plan (2026-10-12) and the shared simulated Capy host fixture

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

* fix(autoplan): scope keys on rendered surfaces, per-axis provenance, --no-dx and a read-only plan marker

UI scope reads the Implementation plan only and needs a rendered file path or a UI
term next to a visual noun; bare UI words stay weak evidence (sections load, no
Design phase). Scope records sources {ui,dx} (flag|marker|detected), --no-dx turns
DX off, a first-line <!-- gstack-autoplan-scope: ... --> marker is read and never
written, and the first next prints SCOPE: evidence plus a SCOPE_PIN hint. The
snapshot tool's scope output carries uiRequired from the same detector and
autoplan Step 2 uses it instead of a prose grep (field wave item 11).

Intentional pin change: test/review-checklists.test.ts Scope literal and the
source= line shape (source=ui:detected,dx:detected).

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

* fix(plan-reality): a receipt per measured number, the rule text for a rule claim, dot-path receipts

Each clause stating a measured quantity (a unit, or a number after measured/costs/
takes/took) needs its own receipt; misses print unreceipted_numbers=<n> and one
NUMBER_UNRECEIPTED: <clause> line each. A line claiming a decision rule must quote
it or link its file:line (unquoted=<n>). Either miss maps to the existing verdict
(incomplete unattended, repair otherwise). RECEIPT_RE accepts dot paths and needs
a hex letter or a commit/backtick context for a sha. New pure checkPlanReality(planText)
runs the same checks over plan prose for gstack-autoplan submit (field wave item 12).
The unreceipted= text token is now pinned as well as the JSON.

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

* feat(autoplan): generated DRIVER.md, the compact entry for a parent driving gstack-autoplan

autoplan/DRIVER.md (from autoplan/DRIVER.md.tmpl) is what a parent agent on any host
reads instead of autoplan/SKILL.md: phase order and scope flags, the next/submit/
answer/revise/export loop with the plan-specified submit --record/--attest/
--unavailable, revise --incorporates/--withdraw and next --scaffold, the reviewer
RESULT FORMAT, the gate grammar including all as-is, the run files, the result codes
and the coordinator contract, every list rendered from code (117 lines). gen:skill-docs
emits it as a Claude asset, so normal, out-dir and dry-run inventories and the
freshness check cover it. gstack-autoplan --help and the first next print
DRIVER: <root>/autoplan/DRIVER.md, resolved through an install root's recorded
.source-path (new lib/source-root.ts) (field wave item 13).

Intentional pin change: test/gen-skill-docs-checks.test.ts asset inventory gains
autoplan/DRIVER.md.

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

* feat(doctor): --min-revision, a launch Bun found off PATH, planning-only pins SKIP

gstack-doctor --check gains --min-revision <v>|unknown: below it the revision
row FAILs with REVISION_BELOW_MINIMUM naming the Capy wrapper or
bin/gstack-upgrade; unknown says so and never claims the minimum. The runtime
and pins rows name a supported Bun found in $BUN_INSTALL/bin (not on PATH)
with the export/GSTACK_LAUNCH fix (gstack_bun_launch_dir, one helper in
bin/gstack-bun-version.sh). --for a planning-only workflow (autoplan, the plan
reviews, office-hours) reports a repo test-pin mismatch as SKIP pins
(planning-only; ...). New result codes UPGRADE_REFUSED, UPGRADE_FETCH_FAILED,
REVISION_BELOW_MINIMUM, CAPY_WRAPPER_STALE, INSTALL_UNVERIFIED with
troubleshooting anchors; REVISION_UNMET's fix names bin/gstack-upgrade.

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

* feat(install): install verdict and install admission at skill start

bin/gstack-install-verdict.sh (Bash) and lib/install-verdict.ts (TypeScript)
are the one reader of the install verdict gstack-capy-install writes to
<state root>/install-verdicts/<sha256(checkout realpath)>.json (checkout,
HEAD, workflow and required components, planning-only pins, trailer). The
source checkout and capy/support.env resolve through gstack_source_root /
sourceRoot, which follow an installed root's .source-path.

gstack-skill-start, after SESSION_KIND: an unattended session (any host)
refuses on a PATH Bun below the supported minimum; with GSTACK_CAPY=1 an
unattended or explicit spawned session also refuses without a passing
verdict for this checkout, HEAD and workflow (INSTALL_UNVERIFIED). A refusal
prints the INSTALL: row, an install-refused instruction block bound to its
SESSION_ID, GSTACK_RESULT ... status=refused run=- and exits 3. Ambient
spawned sessions warn; GSTACK_ALLOW_UNSUPPORTED_RUNTIME=1 admits and says so.
capy/support.env declares GSTACK_MIN_REVISION and GSTACK_CAPY_MIN_WRAPPER.

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

* feat(capy-install): launch PATH, Bun reuse and CI pins, setup skip on HEAD, verdict, --check

The GSTACK_LAUNCH line carries PATH=<dir>:$PATH when the certified Bun is not
first on PATH, plus GSTACK_CAPY=1 and GSTACK_INSTALL_VERDICT, and
GSTACK_LAUNCH_PATH: <dir>; the doctor runs with that PATH. A supported Bun in
$BUN_INSTALL/bin is reused instead of downloaded again. Project pins are read
with bin/gstack-runtime-pins.ts (CI lanes included): when every exact pin is
gstack's verified version the archive is installed alongside a different PATH
Bun; any other exact pin is RUNTIME_PIN_CONFLICT. Both ./setup runs are
skipped when this HEAD was set up with the same hosts, model and browser flag
and the check passes (never after a fast-forward); a failed setup ends with
gstack: fail setup and is retried next run. --check certifies only;
GSTACK_CAPY_LOCK_HELD=1 accepts the bootstrapper's held lock; result anchors
come from the generated components table; REV_NOTE names bin/gstack-upgrade.

Intentional pin change: test/gstack-capy-install.test.ts --revision trailer
now names <root>/bin/gstack-upgrade (the old text named a command that never
existed).

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

* result codes: PLAN_SECTIONS_INVALID, PLAN_AMEND_PENDING, GSTACK_VERSION_CHANGED, INSTALL_VERDICT_FAILED, ARTIFACT_GATE_UNSETTLED

Troubleshooting anchors for each and the regenerated doctor components table (field wave lane B-core).

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

* artifact contract: changes, recommended_basis, carried decisions, attested count, settled-gate check

Findings and decisions carry the user challenge's `changes` value; decisions record recommended_basis, origin,
carried_from and chosen_text; validate refuses a complete run with an unsettled gate (ARTIFACT_GATE_UNSETTLED) and
prints attested=<n>. The gate reply grammar gains `all as-is` and resolves partial replies against prior answers
(field wave B2a/B2b).

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

* autoplan: run-state fields, plan-text hashing, version migration and admission modules

RunState gains gstack_version, plan_input/heading, scope_flags, plan_revision, amendments and plan_reality; voices
record receipt kind and reviewed hash. New pure modules: Implementation-plan review hash, scaffold and drift lines
(B1c); gstack_version stamp and legacy decision-id migration (B1a); install-verdict and Bun-minimum admission
with a local verdict shim until lane A's lib/install-verdict.ts lands.

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

bin/gstack-autoplan-snapshot.ts exports its section scanner and review projection, and initializes only a plan with
no section headings by wrapping it.

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

* autoplan: closable runs - submit --record/--attest/--unavailable, revise, amendment interlock, agreeing-UC defaults, admission

B1a: an older run directory prints GSTACK_VERSION_CHANGED once and migrates legacy decision ids; a newer one refuses.
B1b: submit binds hand-run records (fence, table, severity list, No findings.), attested binds need --attempt,
--attempt is optional with one open attempt, --unavailable/--failed close an outside voice native_only, and submit
caches the plan-reality report by Implementation-plan hash.
B1c: revise reviews a revised plan in the same run as one recoverable transaction (reopen on hash drift plus Eng,
add newly in-scope phases, .r<rev>/.v<k> archives, gate_rev+1 at the gate); PLAN_SECTIONS_INVALID and next --scaffold;
PLAN_CHANGED / PLAN_SOURCE_CHANGED drift hints.
B2a/B2b: user challenges carry changes; agreeing voices with the same changes on a confirmed finding recommend b with
both remedies shown (or the reconcile proposal); accepted changes print APPLY and become pending amendments that next
and export refuse past until revise --incorporates names them or --withdraw drops one; all as-is; partial replies,
DECIDED block, carry-forward and rerun demotion.
Mutating verbs pass admission (GSTACK_CAPY install verdict; unattended Bun minimum; override recorded as a deviation).
Intentional pin rewrite: test/autoplan-answer-invalidation.test.ts reopen tests now revise --incorporates before rerun.

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

* feat(upgrade): bin/gstack-upgrade, the unattended fast-forward every fix line names

--check fetches and prints current|behind <installed> -> <remote> (<n>
commits); the default fast-forwards to the remote default branch tip and
reinstalls (bin/gstack-capy-install on a Capy install, else ./setup
--refresh-registered), completing a pending reinstall on the next run. It
refuses (UPGRADE_REFUSED, exit 3, nothing changed) a dirty tracked byte, a
diverged commit, a pinned checkout, the incoming Bun floor and a held
.setup-lock; never stashes or resets; an unreachable remote is
UPGRADE_FETCH_FAILED. Fetches are receipted (fail-open). The unattended
skill-end UPGRADE_AVAILABLE line is followed by UPGRADE_COMMAND naming it.

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

* feat(capy): vendored Capy skill, frozen bootstrapper and full wrapper bin/gstack-capy-session

capy/skill/gstack/ is the Drive skill's source of truth. scripts/install.sh
is a frozen bootstrapper: it prints gstack-capy-skill: wrapper <n> (<path>),
clones or fetches under .gstack-capy-install.lock, reads the remote
capy/support.env (FETCH_HEAD), fast-forwards a clean unpinned checkout below
GSTACK_MIN_REVISION (refusing dirty, diverged or pinned checkouts with the
exact commands; GSTACK_CAPY_AUTO_UPGRADE=0 disables), and execs the
checkout's own bin/gstack-capy-session with GSTACK_CAPY_LOCK_HELD=1 so the
held lock is never taken twice. Offline it says the remote minimum is
unknown. A Drive copy older than GSTACK_CAPY_MIN_WRAPPER prints an owner
action (CAPY_WRAPPER_STALE). SKILL.md: check at session start, install
lazily before the first workflow, the GSTACK_LAUNCH line, the trailer rule,
the subagent first-report line, gstack-pregate sealed before any push, and
the autoplan/DRIVER.md pointer. The context-budget fixture gains the skill's
entry.

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

* docs: Capy install layers, lazy install, snapshot bake, forward-only recovery, raising the minimum

docs/capy-install.md describes the three layers (Drive bootstrapper, full
wrapper, installer), the lazy install, the GSTACK_LAUNCH line, install
admission, baking gstack into a Capy snapshot, and that recovery after an
interrupted fast-forward completes or refuses the pending install stages
(checking out an older commit is not a rollback). docs/CHANGELOG_STYLE.md
(the release doc; there is no docs/RELEASING.md) says when
GSTACK_MIN_REVISION may be raised.

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

* refactor(capy): the stale-copy owner action moves from the frozen bootstrapper to bin/gstack-capy-session

The checkout-owned full wrapper reads GSTACK_CAPY_MIN_WRAPPER through
gstack_support_env_get(gstack_source_root) and compares it with the
bootstrapper revision it was handed, so the rule can change without
recopying the Drive skill. The bootstrapper keeps only what a stale checkout
cannot do: clone, fetch, read the remote minimum, fast-forward, exec.

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

* v1.91.96.0: honest install and self-upgrade on Capy; supported minimum 1.91.96.0

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

* v1.91.97.0: closable unattended autoplan runs on Capy

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

* test: drop the helper-only Capy host fixture test (test-of-test ratchet); lane tests exercise the helper

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

* fix(autoplan): revise naming a non-pending decision refuses with AMENDMENT_UNKNOWN, not PLAN_AMEND_PENDING

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

* test: bound the new sync spawns in the install-verdict and wrapper tests (spawnSync tripwire)

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

* test(autoplan): pin CLI refusals to the result-code registry's fix text

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

* fix(gen-skill-docs): emit autoplan/DRIVER.md only when the autoplan template is in the tree (setup fixtures with a skill subset)

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

* fix(autoplan): run.lock is linked into place with its owner written; a fresh unreadable lock is held, not stolen

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

* ci(paid-pr-profile): the vendored Capy skill is free-only; free-only files are not prompts needing paid coverage

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

* chore(harness): non-behavioral HARNESS_VERSION decision for the PR-profile free-only rule

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

* test(doctor): lane A runtime and pins cases are platform-neutral (bash paths; a lane-free .bun-version pin)

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

* docs(designs): field wave plan with amendments and the gate rev 2-3 review record (ARTIFACT_VALID, 3 gate revisions)

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

* fix(capy-install): follow a project's exact Bun pin above the minimum when gstack has its verified archive (adds Bun 1.4.3)

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

* docs: the installer follows a verified exact project Bun pin (capy-install, troubleshooting, changelog)

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

* fix(capy-install): the install reason names the project's pin and gstack's real minimum

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

* ci: run the main-targeted checks after retargeting #3165 to main

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

* test(autoplan-admission): the PATH-Bun refusal case needs the POSIX Capy host stub; skip it on Windows

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>
2026-10-13 15:17:39 +00:00

107 lines
6.9 KiB
TypeScript

/**
* autoplan-state — the unattended runner's on-disk state (plan B2): the
* RunState shape (the B0 run manifest plus the runner's own fields), the
* typed RunError every command maps to a result code and exit code, the fixed
* file names, the append-only attempts journal, atomic run.json writes, and
* the per-voice reads the gate and export share. No command logic lives here.
*/
import * as fs from 'node:fs';
import * as path from 'node:path';
import type { Phase, Scope } from './autoplan-prompts';
import type { DecisionRow, FindingRow, RunManifest, VoiceOutcome } from './headless-artifacts';
import { readJsonl } from './headless-artifacts';
import type { ResultCodeName } from './result-codes';
export type Voice = 'native' | 'outside';
export interface AttemptState { attempt: string; state: 'dispatched' | 'submitted' | 'execution_unknown' | 'cancelled' | 'superseded'; prompt: string; result: string; estimate_usd: number; dispatched_at: string; terminal_at?: string }
export interface VoiceState extends VoiceOutcome {
attempt?: string; attempts?: AttemptState[]; result_sha256?: string; findings?: number; label?: string; usage?: Record<string, unknown>; detail?: string;
/** verified: the INPUT receipt matched the snapshot; attested: a --record bound without one, on the parent's word (attest_reason). */
receipt?: 'verified' | 'attested'; attest_reason?: string; findings_source?: 'fence' | 'table' | 'list' | 'none'; reviewed_sha256?: string;
}
/** An accepted plan change (gate option with changes_plan) the plan must absorb before the run continues. */
export interface Amendment { decision: string; title: string; chosen: string; text: string; gate_rev: number; status: 'pending' | 'incorporated' | 'withdrawn'; at: string; settled_at?: string }
export interface PhaseState {
snapshot?: string; snapshot_dir?: string; snapshot_path?: string; methodology?: string; opened_at?: string; closed_at?: string;
native?: VoiceState; outside?: VoiceState; consensus?: Record<string, unknown>; skipped?: string;
prompts?: { native: string; outside: string; nativeResult: string; outsideResult: string };
sections?: { loaded: string[]; skipped: string[]; checklist: boolean };
}
export interface RunState extends RunManifest {
revision: number; out: string; plan_source: string; active_plan: string; restore: string; scope: Scope; phase_order: Phase[];
phases: Record<string, PhaseState>; native_model?: string; outside_model?: string; outside_enabled: boolean; attempt_counter: number;
spend_cap_usd: number | null; deadline_at?: string; light?: boolean; history: Array<Record<string, unknown>>; created_at: string; updated_at: string;
/** The gstack that last wrote this run (lib/autoplan-migrate.ts); absent on runs written before 1.91.96. */
gstack_version?: string;
/** The --plan file the owner edits (drift hints, revise), the --plan-heading it was cut from, and the scope flags revise re-detects with. */
plan_input?: string; plan_heading?: string; scope_flags?: Record<string, boolean | undefined>; scaffolded?: boolean;
plan_revision?: number; amendments?: Amendment[];
plan_reality?: { plan_sha256: string; checker: string; verdict: string; line: string };
}
export const TERMINAL_VOICE_STATUSES = ['completed', 'disabled', 'unavailable', 'failed', 'skipped'] as const;
/** The one terminal-voice predicate `next`, `submit`, `resume` and phase close share: a terminal voice is never dispatched or resurrected. */
export function voiceTerminal(v: { status?: string } | undefined): boolean {
return (TERMINAL_VOICE_STATUSES as readonly string[]).includes(String(v?.status));
}
export const pendingAmendments = (state: RunState): Amendment[] => (state.amendments ?? []).filter(a => a.status === 'pending');
export class RunError extends Error {
constructor(public code: ResultCodeName, public detail: string, public exit: 1 | 3 = 1) { super(`${code}: ${detail}`); }
}
export const FILES = { run: 'run.json', journal: 'attempts.jsonl', lock: 'run.lock', spend: 'spend.json', active: 'plan-active.md', restore: 'restore.md', source: 'plan-source.md' } as const;
export const now = () => new Date().toISOString();
export function journal(out: string, row: Record<string, unknown>): void {
fs.appendFileSync(path.join(out, FILES.journal), JSON.stringify({ ts: now(), ...row }) + '\n');
}
export function readJournal(out: string): Array<Record<string, any>> {
const file = path.join(out, FILES.journal);
if (!fs.existsSync(file)) return [];
return fs.readFileSync(file, 'utf8').split('\n').filter(Boolean).flatMap(l => { try { return [JSON.parse(l)]; } catch { return []; } });
}
export function writeState(state: RunState): void {
state.revision += 1;
state.updated_at = now();
const file = path.join(state.out, FILES.run);
const tmp = `${file}.${process.pid}.tmp`;
fs.writeFileSync(tmp, JSON.stringify(state, null, 2) + '\n');
fs.renameSync(tmp, file);
}
export function readState(out: string): RunState {
const file = path.join(out, FILES.run);
if (!fs.existsSync(file)) throw new RunError('RUN_NOT_INITIALIZED', out, 3);
const state = JSON.parse(fs.readFileSync(file, 'utf8')) as RunState;
// The directory may have been moved or copied: paths inside it are re-rooted on every read.
const previous = state.out;
state.out = path.resolve(out);
if (previous && previous !== state.out) {
const reroot = (p: string | undefined) => (p && p.startsWith(previous + path.sep) ? path.join(state.out, path.relative(previous, p)) : p);
state.active_plan = reroot(state.active_plan)!; state.restore = reroot(state.restore)!;
for (const ps of Object.values(state.phases)) {
ps.snapshot_dir = reroot(ps.snapshot_dir); ps.snapshot_path = reroot(ps.snapshot_path); ps.methodology = reroot(ps.methodology);
if (ps.prompts) for (const k of Object.keys(ps.prompts) as Array<keyof typeof ps.prompts>) ps.prompts[k] = reroot(ps.prompts[k])!;
for (const v of [ps.native, ps.outside]) for (const a of v?.attempts ?? []) { a.prompt = reroot(a.prompt)!; a.result = reroot(a.result)!; }
}
}
return state;
}
/** The canonical rows one completed voice returned (`<phase>-<voice>.md.findings.jsonl`). */
export function voiceRows(state: RunState, phase: string, voice: Voice): FindingRow[] {
const v = state.phases[phase]?.[voice];
if (v?.status !== 'completed' || !v.output) return [];
const file = path.join(state.out, `${v.output}.findings.jsonl`);
return fs.existsSync(file) ? (readJsonl(file).rows as unknown as FindingRow[]) : [];
}
export function readDecisions(out: string): DecisionRow[] {
const file = path.join(out, 'decisions.jsonl');
return fs.existsSync(file) ? (readJsonl(file).rows as unknown as DecisionRow[]) : [];
}
export function writeDecisions(out: string, rows: DecisionRow[]): void {
const file = path.join(out, 'decisions.jsonl');
const tmp = `${file}.${process.pid}.tmp`;
fs.writeFileSync(tmp, rows.map(r => JSON.stringify(r)).join('\n') + (rows.length ? '\n' : ''));
fs.renameSync(tmp, file);
}