mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-04 15:57:33 +01:00
* 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>
196 lines
12 KiB
TypeScript
196 lines
12 KiB
TypeScript
/**
|
|
* autoplan-budget — the run budget of the unattended runner (field list 2,
|
|
* W5). Review rounds are counted per phase from `state.history` reopen events
|
|
* and capped by `run.json.max_rounds` (default 2 for new unattended runs; a
|
|
* resumed run keeps the value it persisted) plus the
|
|
* owner's per-phase grants at the gate. Unattended runs on Capy reserve a
|
|
* default per-voice estimate for unestimated host attempts, so `--spend-cap`
|
|
* binds. A dispatch the cap refuses stops the run at the terminal `incomplete`
|
|
* status with a structured `stop` object (`reason: budget_exhausted`) and
|
|
* printed recovery commands; `gstack-autoplan budget` journals the owner's cap
|
|
* change and `resume` lifts the stop only after one. Phase close at the cap
|
|
* lives in lib/autoplan-gate.ts (`closeDeferred`); `escalateLine` names the
|
|
* capped phases still holding High or Critical findings.
|
|
*/
|
|
import * as fs from 'node:fs';
|
|
import * as path from 'node:path';
|
|
import { ANSWERED_BY_RE, type GateItem } from './gate-list';
|
|
import { settledIds } from './autoplan-confirm';
|
|
import { sameProblem, type ConsensusRecord } from './autoplan-reconcile';
|
|
import { FILES, RunError, journal, now, readJournal, voiceRows, type RunState, type RunStop } from './autoplan-state';
|
|
import { readLedger, release, setCap, summarize } from './spend-ledger';
|
|
|
|
export const DEFAULT_MAX_ROUNDS = 2;
|
|
/** Reserved per voice for a host-subagent attempt with no `--estimate-usd` in an unattended run with a spend cap or on Capy. */
|
|
export const DEFAULT_HOST_ESTIMATE_USD = 5;
|
|
|
|
/** Round r of a phase: 1 plus the times it was reopened. */
|
|
export const roundOf = (state: RunState, phase: string): number => 1 + state.history.filter(h => h.event === 'reopened' && h.phase === phase).length;
|
|
/** The phase's round cap: max_rounds plus the owner's grants; null when the run is uncapped. */
|
|
export function roundCap(state: RunState, phase: string): number | null {
|
|
return state.max_rounds == null ? null : state.max_rounds + (state.round_grants?.[phase] ?? 0);
|
|
}
|
|
/** Reopening would pass the cap: the phase has used its last round. */
|
|
export const atCap = (state: RunState, phase: string): boolean => { const cap = roundCap(state, phase); return cap !== null && roundOf(state, phase) >= cap; };
|
|
/** The phase is about to open past its cap (a rerun-all reply reopened it). */
|
|
export const overCap = (state: RunState, phase: string): boolean => { const cap = roundCap(state, phase); return cap !== null && roundOf(state, phase) > cap; };
|
|
|
|
/** Open High or Critical findings of a closed phase: the deferred counts, else bound rows not settled or answered, an outside row naming the same problem (`sameProblem`) as a High or Critical native one counted once. */
|
|
function openHigh(state: RunState, phase: string): number {
|
|
const ps = state.phases[phase];
|
|
if (ps?.deferred) return (ps.deferred.counts.High ?? 0) + (ps.deferred.counts.Critical ?? 0);
|
|
const file = path.join(state.out, `${phase}-consensus.json`);
|
|
let rows: ConsensusRecord['rows'] = [];
|
|
try { rows = fs.existsSync(file) ? (JSON.parse(fs.readFileSync(file, 'utf8')) as ConsensusRecord).rows : []; } catch {}
|
|
const high = (s: string | undefined) => s === 'High' || s === 'Critical';
|
|
const native = voiceRows(state, phase, 'native');
|
|
const nativeHigh = new Set(native.filter(r => high(r.severity)).map(r => r.id));
|
|
const paired = new Set(rows.filter(r => r.native_id && sameProblem(r) && nativeHigh.has(r.native_id)).map(r => r.outside_id));
|
|
const answered = settledIds(state);
|
|
return [...native, ...voiceRows(state, phase, 'outside')]
|
|
.filter(r => !paired.has(r.id) && !(r as { settled_by?: string }).settled_by && !answered.has(r.id) && high(r.severity)).length;
|
|
}
|
|
|
|
/** At the round cap with High or Critical findings still open, more rounds buy nothing: the owner decides. */
|
|
export function escalateLine(state: RunState): string | undefined {
|
|
const held = state.phase_order.filter(p => state.phases[p]?.closed_at && atCap(state, p)).map(p => [p, openHigh(state, p)] as const).filter(([, n]) => n > 0);
|
|
return held.length ? `ESCALATE: evidence sufficient, decision needed (${held.map(([p, n]) => `${p}: ${n} High open`).join('; ')})` : undefined;
|
|
}
|
|
|
|
export function roundsLine(state: RunState): string {
|
|
const cell = (p: string) => `${p}=${roundOf(state, p)}/${roundCap(state, p) ?? 'none'}`;
|
|
return `ROUNDS: ${state.phase_order.map(cell).join(' ')} max_rounds=${state.max_rounds ?? 'none'} host_spend=unknown`;
|
|
}
|
|
|
|
/**
|
|
* The estimate one new attempt reserves: the flag, else the run's persisted `--estimate-usd`, else the default whenever
|
|
* the run has a spend cap (any session kind) or an unattended run is on Capy, else 0 (host spend unknown, not admitted).
|
|
* `run` prices its api attempts from the price table instead (NextOptions.price); an unpriced model falls back to this.
|
|
*/
|
|
export function attemptEstimate(state: RunState, flag: number | undefined, env: NodeJS.ProcessEnv): { usd: number; line?: string } {
|
|
const set = flag ?? state.estimate_usd;
|
|
if (set !== undefined) return { usd: set };
|
|
if (state.spend_cap_usd === null && (state.session_kind !== 'unattended' || env.GSTACK_CAPY !== '1')) return { usd: 0 };
|
|
return { usd: DEFAULT_HOST_ESTIMATE_USD, line: `ESTIMATE: ${DEFAULT_HOST_ESTIMATE_USD.toFixed(2)} per voice reserved for each host-subagent attempt (default under a spend cap, or unattended on Capy; --estimate-usd <n> sets it for the rest of the run); actual host spend stays unknown` };
|
|
}
|
|
|
|
/** Stop the run: terminal `incomplete` with the structured budget_exhausted stop, journaled. Returns the STOP and RECOVER lines. */
|
|
export function stopForBudget(state: RunState, phase: string, nextEstimate: number): string[] {
|
|
const s = summarize(readLedger(path.join(state.out, FILES.spend), state.spend_cap_usd));
|
|
const stop: RunStop = {
|
|
reason: 'budget_exhausted', phase, cap_usd: state.spend_cap_usd, max_rounds: state.max_rounds ?? null,
|
|
rounds: Object.fromEntries(state.phase_order.map(p => [p, roundOf(state, p)])), spent: s.spent_usd, reserved: s.reserved_usd,
|
|
unknown: s.unknown_usd, unknown_count: s.unknown_count, next_estimate_usd: nextEstimate, at: now(),
|
|
};
|
|
state.stop = stop;
|
|
state.status = 'incomplete';
|
|
journal(state.out, { event: 'stopped', ...stop });
|
|
return stopLines(state);
|
|
}
|
|
|
|
export function stopLines(state: RunState): string[] {
|
|
const s = state.stop;
|
|
if (!s) return [];
|
|
const rounds = Object.entries(s.rounds).map(([p, r]) => `${p}:${r}/${roundCap(state, p) ?? 'none'}`).join(',');
|
|
return [
|
|
`STOP: reason=${s.reason} phase=${s.phase ?? 'none'} cap=${s.cap_usd === null ? 'none' : s.cap_usd.toFixed(2)} spent=${s.spent.toFixed(2)} reserved=${s.reserved.toFixed(2)} unknown=${s.unknown_count}(${s.unknown.toFixed(2)}) next_estimate=${s.next_estimate_usd.toFixed(2)} rounds=${rounds}`,
|
|
...recoveryLines(state),
|
|
];
|
|
}
|
|
|
|
export function recoveryLines(state: RunState): string[] {
|
|
const phase = state.stop?.phase ?? '<phase>';
|
|
return [
|
|
`RECOVER: gstack-autoplan close --out ${state.out} --phase ${phase} --deferred "<reason>" --by <human|agent:<id>> (close ${phase} accepted-with-findings, deferred to the build)`,
|
|
`RECOVER: gstack-autoplan budget --out ${state.out} --spend-cap <usd> [--max-rounds <n>] --by <human|agent:<id>>, then gstack-autoplan resume --out ${state.out} (an owner-authorized cap raise)`,
|
|
];
|
|
}
|
|
|
|
/** Clear the stop into `stops` (its history) and leave the run resumable. */
|
|
export function liftStop(state: RunState, why: string): string[] {
|
|
if (!state.stop) return [];
|
|
(state.stops ??= []).push(state.stop);
|
|
delete state.stop;
|
|
state.status = 'running';
|
|
journal(state.out, { event: 'stop_lifted', why });
|
|
return [`STOP_LIFTED: ${why}`];
|
|
}
|
|
|
|
/** `resume` on a budget-stopped run: lifts the stop only when a budget change was journaled after it. */
|
|
export function resumeStop(state: RunState): string[] {
|
|
if (state.status !== 'incomplete' || state.stop?.reason !== 'budget_exhausted') return [];
|
|
const at = state.stop.at;
|
|
const raised = readJournal(state.out).some(r => r.event === 'budget_changed' && String(r.ts) >= at);
|
|
if (!raised) return [`STOPPED: budget_exhausted at ${at}; nothing changed the budget since`, ...recoveryLines(state)];
|
|
return liftStop(state, 'budget raised after budget_exhausted');
|
|
}
|
|
|
|
export interface BudgetChange { spendCap?: number; maxRounds?: number; by?: string }
|
|
|
|
/** `gstack-autoplan budget`: the owner's journaled change of the spend cap and/or the round cap. */
|
|
export function changeBudget(state: RunState, o: BudgetChange): string[] {
|
|
if (o.by === undefined || !ANSWERED_BY_RE.test(o.by)) throw new RunError('ANSWER_BY_REQUIRED', `budget records who authorized the change: pass --by human or --by agent:<id> (got ${JSON.stringify(o.by ?? null)})`, 3);
|
|
if (o.spendCap === undefined && o.maxRounds === undefined) throw new RunError('ARTIFACT_SCHEMA', 'budget needs --spend-cap <usd> and/or --max-rounds <n>', 1);
|
|
if (o.maxRounds !== undefined && (!Number.isInteger(o.maxRounds) || o.maxRounds < 1)) throw new RunError('ARTIFACT_SCHEMA', '--max-rounds needs an integer >= 1', 1);
|
|
const change: Record<string, unknown> = { event: 'budget_changed', by: o.by };
|
|
const parts: string[] = [];
|
|
if (o.spendCap !== undefined) {
|
|
change.spend_cap = { from: state.spend_cap_usd, to: o.spendCap };
|
|
parts.push(`spend_cap=${state.spend_cap_usd ?? 'none'}->${o.spendCap}`);
|
|
state.spend_cap_usd = o.spendCap;
|
|
setCap(path.join(state.out, FILES.spend), o.spendCap);
|
|
}
|
|
if (o.maxRounds !== undefined) {
|
|
change.max_rounds = { from: state.max_rounds ?? null, to: o.maxRounds };
|
|
parts.push(`max_rounds=${state.max_rounds ?? 'none'}->${o.maxRounds}`);
|
|
state.max_rounds = o.maxRounds;
|
|
}
|
|
journal(state.out, change);
|
|
const lines = [`BUDGET: ${parts.join(' ')} by=${o.by}`];
|
|
if (state.stop) lines.push(`NEXT: gstack-autoplan resume --out ${state.out}`);
|
|
return lines;
|
|
}
|
|
|
|
/** Reservations with no dispatch journaled (a crash between reserve and journal) are proven never dispatched, so released. */
|
|
export function releaseUndispatched(state: RunState): string[] {
|
|
const file = path.join(state.out, FILES.spend);
|
|
const dispatched = new Set(readJournal(state.out).filter(r => r.event === 'dispatched').map(r => r.attempt));
|
|
return readLedger(file).reserved.filter(r => !dispatched.has(r.attempt)).map(r => {
|
|
release(file, r.attempt);
|
|
journal(state.out, { event: 'released_undispatched', attempt: r.attempt, estimate_usd: r.estimate_usd });
|
|
return `RELEASED: ${r.attempt} (never dispatched)`;
|
|
});
|
|
}
|
|
|
|
export const pendingDeltas = (state: RunState) => (state.capped_deltas ?? []).filter(d => d.status === 'pending');
|
|
|
|
/**
|
|
* The owner's answers to cap items (deferred closes, deferred blockers, capped deltas) once the plan proceeds:
|
|
* `b` grants that phase one more round, journaled as a budget change, and adds it to the reopen set; Eng, which
|
|
* reruns last, gets its own grant unless it already has one;
|
|
* `a` accepts. Capped deltas record which.
|
|
*/
|
|
export function applyCapChoices(state: RunState, choices: Array<{ item: GateItem; chosen: string }>, reopen: Set<string>, by: string | undefined): string[] {
|
|
const lines: string[] = [];
|
|
const granted = new Set<string>();
|
|
for (const { item, chosen } of choices) {
|
|
const cap = item.cap;
|
|
if (!cap) continue;
|
|
const reopens = chosen === 'b';
|
|
for (const d of pendingDeltas(state)) if (d.phase === cap.phase && (cap.kind !== 'delta' || String(d.k) === cap.ref)) { d.status = reopens ? 'reopened' : 'accepted'; d.decided_at = now(); }
|
|
if (!reopens || granted.has(cap.phase)) continue;
|
|
granted.add(cap.phase);
|
|
(state.round_grants ??= {})[cap.phase] = (state.round_grants[cap.phase] ?? 0) + 1;
|
|
journal(state.out, { event: 'budget_changed', by: by ?? 'gate', round_grant: { phase: cap.phase, cap: roundCap(state, cap.phase) }, item: item.id });
|
|
reopen.add(cap.phase);
|
|
lines.push(`ROUND_GRANTED: ${cap.phase} cap=${roundCap(state, cap.phase)} (${item.id}b by ${by ?? 'gate'})`);
|
|
if (cap.phase === 'eng' || !state.phase_order.includes('eng') || granted.has('eng')) continue;
|
|
granted.add('eng');
|
|
state.round_grants.eng = (state.round_grants.eng ?? 0) + 1;
|
|
journal(state.out, { event: 'budget_changed', by: by ?? 'gate', round_grant: { phase: 'eng', cap: roundCap(state, 'eng') }, item: item.id, reason: `eng reruns after ${cap.phase}` });
|
|
reopen.add('eng');
|
|
lines.push(`ROUND_GRANTED: eng cap=${roundCap(state, 'eng')} (reruns after ${cap.phase}; ${item.id}b by ${by ?? 'gate'})`);
|
|
}
|
|
return lines;
|
|
}
|