Files
gstack/lib/gate-list.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

200 lines
12 KiB
TypeScript

/**
* gate-list — one gate list instead of four-option sequences (plan B9).
* A gate list is numbered items, each with a stable id, a recommended default
* and lettered options; `auto` items take their recommendation when
* unanswered, `approval` items stay pending until answered. One reply
* grammar: `all` (every item takes its recommendation), `<id><option>` tokens
* (`d3b uc1a`), or `all except <tokens>` (the same operation as listing the
* overrides, so there is no exclusion-vs-override ambiguity). Bare yes/no is
* ambiguous across multi-option items and is reported as unparsed, never
* guessed. A reply binds to the gate revision it answers (`gate_rev`).
* `all as-is` keeps every direction: each item takes its option that does not
* change the plan (`changes_plan: false`), so agreeing user challenges whose
* recommendation is the change can be declined in one token. Earlier answers
* at the same revision (`prior`) are kept unless a token names the item again:
* only unresolved items default.
* Rendered by bin/gstack-gate; rows land in decisions.jsonl (lib/headless-artifacts.ts).
*/
import type { DecisionRow } from './headless-artifacts';
/** `changes_plan`: choosing this option is an accepted plan change (reopens its phase plus Eng, prints APPLY:). */
export interface GateOption { key: string; text: string; changes_plan?: boolean }
export interface GateItem {
id: string; title: string; options: GateOption[]; recommended: string; kind: 'auto' | 'approval';
phase?: string; cost?: string; why?: string;
/** false: an agent decision; no option reopens a phase. */
reopens?: boolean;
/** Why `recommended` (e.g. `both voices; remedies shown`, `plan direction; voices disagree`). */
recommended_basis?: string; changes?: string;
/** Stable carry-forward identity (phase, finding ids, phase close, snapshot, option text). */
origin?: string;
/** Answered at an earlier revision on an unchanged proposal from a phase that did not rerun. */
carried?: { from: string; chosen: string; gate_rev: number };
}
export interface GateList { schema_version: 1; run: string; gate_rev: number; items: GateItem[]; title?: string }
export interface GateChoice { id: string; chosen: string; kind: 'auto' | 'approval'; how: 'recommended' | 'override' | 'auto_default'; prior?: boolean }
export interface ParsedReply {
valid: boolean; gate_rev: number; reply: string; choices: GateChoice[]; pending: string[]; unparsed: string[];
error?: 'GATE_REV_STALE' | 'GATE_REPLY_UNPARSED' | 'GATE_EMPTY';
}
export const PAGE_SIZE = 7;
const ID_RE = /^[a-z]*[0-9]+$/;
export function validateGateList(list: unknown): string[] {
const problems: string[] = [];
const g = list as Partial<GateList>;
if (!g || typeof g !== 'object') return ['gate list is not an object'];
if (g.schema_version !== 1) problems.push('schema_version must be 1');
if (typeof g.run !== 'string' || !g.run) problems.push('run is required');
if (!Number.isInteger(g.gate_rev) || (g.gate_rev as number) < 1) problems.push('gate_rev must be an integer >= 1');
if (!Array.isArray(g.items) || g.items.length === 0) return [...problems, 'items must be a non-empty array'];
const seen = new Set<string>();
g.items.forEach((item, i) => {
const at = `items[${i}]`;
if (typeof item.id !== 'string' || !ID_RE.test(item.id)) problems.push(`${at}.id must match [a-z]*[0-9]+ (lowercase label plus a number, e.g. d3, uc1, 12)`);
else if (seen.has(item.id)) problems.push(`${at}.id ${item.id} is duplicated`); else seen.add(item.id);
if (typeof item.title !== 'string' || !item.title) problems.push(`${at}.title is required`);
if (item.kind !== 'auto' && item.kind !== 'approval') problems.push(`${at}.kind must be auto or approval`);
if (!Array.isArray(item.options) || item.options.length < 2) problems.push(`${at}.options needs at least two options`);
else {
const keys = item.options.map(o => o?.key);
if (keys.some(k => typeof k !== 'string' || !/^[a-z]$/.test(k))) problems.push(`${at}.options[*].key must be one lowercase letter`);
if (new Set(keys).size !== keys.length) problems.push(`${at}.options keys repeat`);
if (!keys.includes(item.recommended)) problems.push(`${at}.recommended must be one of its option keys`);
}
});
return problems;
}
/** The `all` resolution: every item takes its recommendation; shown under the list so the reply shape is explicit. */
export function resolveAll(list: GateList): Record<string, string> {
return Object.fromEntries(list.items.map(i => [i.id, i.recommended]));
}
export function renderGate(list: GateList, page = 1, pageSize = PAGE_SIZE): string {
const pages = Math.max(1, Math.ceil(list.items.length / pageSize));
const current = Math.min(Math.max(1, page), pages);
const start = (current - 1) * pageSize;
const lines: string[] = [];
lines.push(`GATE: run=${list.run} gate_rev=${list.gate_rev} items=${list.items.length} page=${current}/${pages}${list.title ? ` — ${list.title}` : ''}`);
lines.push('');
list.items.slice(start, start + pageSize).forEach((item, i) => {
const n = start + i + 1;
lines.push(`${n}. [${item.id}] ${item.title} (${item.kind}; recommended: ${item.recommended}${item.recommended_basis ? ` (${item.recommended_basis})` : ''}${item.phase ? `; from ${item.phase}` : ''})`);
if (item.why) lines.push(` ${item.why}`);
if (item.carried) lines.push(` decided at gate_rev ${item.carried.gate_rev}: ${item.id}${item.carried.chosen} (carried forward; name it again to change it)`);
for (const o of item.options) lines.push(` ${item.id}${o.key}) ${o.text}${o.key === item.recommended ? ' (recommended)' : ''}`);
if (item.cost) lines.push(` cost: ${item.cost}`);
});
lines.push('');
if (pages > 1) lines.push(`Ids are stable across pages; render page N with \`gstack-gate render <file> --page N\`.`);
lines.push('Reply with exactly one of: `all` · `<id><option>` tokens, e.g. `' + exampleTokens(list) + '` · `all except <tokens>` · `all as-is` (keep every direction).');
lines.push('Items marked auto take their recommendation if unanswered; approval items stay pending until answered. Bare yes/no is not accepted.');
lines.push(`Reply binds to gate_rev=${list.gate_rev}. \`all\` resolves to: ${JSON.stringify({ gate_rev: list.gate_rev, choices: resolveAll(list) })}`);
return lines.join('\n') + '\n';
}
function exampleTokens(list: GateList): string {
return list.items.slice(0, 2).map(i => `${i.id}${i.options.find(o => o.key !== i.recommended)?.key ?? i.recommended}`).join(' ');
}
/** Tokenize a reply: lowercase, strip separators, merge `<id> <option>` pairs into one token. */
export function tokenize(reply: string, list: GateList): string[] {
const raw = reply.toLowerCase().replace(/[,;:=)]/g, ' ').split(/\s+/).filter(Boolean);
const ids = new Set(list.items.map(i => i.id));
const out: string[] = [];
for (let i = 0; i < raw.length; i++) {
const t = raw[i]!;
const next = raw[i + 1];
if (ids.has(t) && next && /^[a-z]$/.test(next)) { out.push(t + next); i++; continue; }
out.push(t);
}
return out;
}
/**
* Parse one reply against the list. Returns the resolved choices, the ids
* still pending (approval items with no answer), and unparsed tokens. Any
* unparsed token makes the whole reply invalid: nothing is guessed.
*/
export function parseReply(reply: string, list: GateList, gateRev?: number, prior: Record<string, string> = {}): ParsedReply {
const base: ParsedReply = { valid: false, gate_rev: list.gate_rev, reply, choices: [], pending: [], unparsed: [] };
if (gateRev !== undefined && gateRev !== list.gate_rev) return { ...base, error: 'GATE_REV_STALE' };
const tokens = tokenize(reply, list);
if (tokens.length === 0) return { ...base, error: 'GATE_EMPTY' };
let all = false;
let asIs = false;
let rest = tokens;
if (tokens[0] === 'all') {
all = true;
rest = tokens.slice(1);
if (rest[0] === 'as-is') { asIs = true; rest = rest.slice(1); }
if (rest[0] === 'except') rest = rest.slice(1);
else if (rest.length > 0) return { ...base, unparsed: rest, error: 'GATE_REPLY_UNPARSED' };
}
const overrides = new Map<string, string>();
const unparsed: string[] = [];
for (const token of rest) {
const m = /^([a-z]*[0-9]+)([a-z])$/.exec(token);
const item = m ? list.items.find(i => i.id === m[1]) : undefined;
const option = item?.options.find(o => o.key === m![2]);
if (!item || !option) { unparsed.push(token); continue; }
if (overrides.has(item.id) && overrides.get(item.id) !== option.key) { unparsed.push(`${token} (conflicts with ${item.id}${overrides.get(item.id)})`); continue; }
overrides.set(item.id, option.key);
}
if (unparsed.length) return { ...base, unparsed, error: 'GATE_REPLY_UNPARSED' };
const choices: GateChoice[] = [];
const pending: string[] = [];
const how = (item: GateItem, chosen: string) => (chosen === item.recommended ? 'recommended' : 'override') as GateChoice['how'];
for (const item of list.items) {
const chosen = overrides.get(item.id);
const earlier = prior[item.id] ?? item.carried?.chosen;
if (chosen !== undefined) choices.push({ id: item.id, chosen, kind: item.kind, how: how(item, chosen) });
else if (earlier !== undefined && item.options.some(o => o.key === earlier)) choices.push({ id: item.id, chosen: earlier, kind: item.kind, how: how(item, earlier), prior: true });
else if (asIs) { const keep = keepDirection(item); choices.push({ id: item.id, chosen: keep, kind: item.kind, how: how(item, keep) }); }
else if (all) choices.push({ id: item.id, chosen: item.recommended, kind: item.kind, how: 'recommended' });
else if (item.kind === 'auto') choices.push({ id: item.id, chosen: item.recommended, kind: item.kind, how: 'auto_default' });
else pending.push(item.id);
}
return { ...base, valid: true, choices, pending };
}
/** The option that keeps the plan's direction: the first with `changes_plan: false`; plan approval `a`; else the recommendation. */
export function keepDirection(item: GateItem): string {
return item.options.find(o => o.changes_plan === false)?.key ?? (item.id === 'p1' && item.options.some(o => o.key === 'a') ? 'a' : item.recommended);
}
/** The decisions.jsonl id for a gate item. Item ids restart at every gate revision, so revisions after the first carry `r<rev>-`. */
export function decisionId(run: string, gateRev: number, itemId: string): string {
return gateRev > 1 ? `${run}-r${gateRev}-${itemId}` : `${run}-${itemId}`;
}
/** decisions.jsonl rows for a gate list (status pending; `applyReply` fills chosen/status). */
export function decisionRows(list: GateList, extra: Partial<DecisionRow> = {}): DecisionRow[] {
return list.items.map(item => ({
schema_version: 1, run: list.run, id: decisionId(list.run, list.gate_rev, item.id), label: item.id.toUpperCase(), title: item.title,
options: item.options.map(o => o.key), recommended: item.recommended, kind: item.kind, status: 'pending',
default_if_unanswered: item.kind === 'auto' ? item.recommended : null, gate_rev: list.gate_rev,
...(item.phase ? { phase: item.phase } : {}), ...(item.cost ? { cost: item.cost } : {}),
...(item.recommended_basis ? { recommended_basis: item.recommended_basis } : {}), ...(item.changes ? { changes: item.changes } : {}),
...(item.origin ? { origin: item.origin } : {}), ...(item.reopens === false ? { source: 'agent' } : {}), ...extra,
}));
}
export function applyReply(rows: DecisionRow[], parsed: ParsedReply, answeredAt: string): DecisionRow[] {
if (!parsed.valid) return rows;
const byId = new Map(parsed.choices.map(c => [c.id, c]));
return rows.map(row => {
const choice = byId.get(row.label?.toLowerCase() ?? '') ?? byId.get(row.id.slice(row.run.length + 1).replace(/^r\d+-/, ''));
if (!choice || choice.prior || row.gate_rev !== parsed.gate_rev) return row;
return {
...row, chosen: choice.chosen, answered_at: answeredAt, reply: parsed.reply,
status: choice.how === 'override' ? 'overridden' : 'approved',
};
});
}