mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-03 07:18:03 +01:00
* feat(loadouts): Opus 5.5 lite loadout with explicit model detection (GSTA-161)
modules/loadouts.json gains the lite loadout (eleven coaching preamble
pieces dropped; upgrade-check and brain-sync kept) and a models map that
sends only claude-opus-5-5 (and its dated snapshots) to it. Detection is
explicit: Capy passes --model to the installer, Claude Code opts in with
./setup --loadout lite; anything unmapped, invalid or unreadable serves full.
The checkout always stays the full render.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(loadouts): Opus 5.5 lite, detection order, Capy SKILL_ROOT, setup --loadout; troubleshooting anchors; changelog fragment (GSTA-161)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(loadouts): claude_loadout read through CONFIG_BIN; capy skill context ceiling for the --model line (GSTA-161)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (prune keeps a reused loadout folder, GSTACK_LOADOUT_SKILL_ROOT, claude_loadout guard test) (GSTA-161)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (Capy skill passes the model as GSTACK_MODEL so an older installer ignores it) (GSTA-161)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (prune only owned, unused folders; full root from the canonical Claude install; fallback reason and source) (GSTA-161)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: loadout source example, install and resolve commands, Capy launch-file note (GSTA-161)
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>
* 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: 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>
* test: run autoplan-ceo-only in the marathon lane
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>
* 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>
* feat: gstack-autoplan next --ceo-only runs the CEO review alone and ends reviewed (GST-537)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: budget and close recover a budget-stopped CEO-only run; reviewed is at rest for checkpoints
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: CEO-only finish leaves owner-only cap items undecided, refuses marker phase flags and a plan at the report path, and replaces ceo-review.md atomically
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: the CEO-only report-path guard compares real paths and refuses at the finish when the report file is the plan
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: CEO_ONLY_CONFLICT covers a plan linked to the report path
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(browse): failing-first device and touch tests (GSTA-227 F3, #3058)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: the report-path guard keeps the lexical check, skips safe hard links and compares bigint file ids
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* browse: per-session tabs for parallel agents; tab pins stop moving the shared active tab (#1961)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* browse: keep the server.ts tab-pin anchor comment for source guards
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat(browse): per-tab phone emulation and touch input ($B device, tap, swipe, pinch, touch; #3058, GSTA-227 F3)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: copy lib/result-codes-autoplan.ts into the fixtures that copy the result-code tables, and keep it out of derived closures
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(qa, aside): touch pointer in /qa, Aside touch recipe verified on Aside 1.26, report Phones row (GSTA-227 F3, #3058)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* browse: drop the sessions paragraph from /browse to stay inside the parity cap
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* changelog: F3 phone emulation and touch entry
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* browse: hide the ps window in the session harness walk
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: the decisions.jsonl status list names auto_kept
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(browse): session cap, LRU eviction, headed release and scoped auto-session rows
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* browse: sessions keep tab <id> picks, sidebar claude stays on the user's tab, pinned rebuild and state load rebind the scope
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (touch cancel with no finger held is a no-op)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: Step 11 review fixes (headed tab adoption, pinned viewport reset, CLI retry keeps --session, rebuild id remap, --json notice, evicted-session reset, device kept after annotated captures, render opts out of sessions, session: client ids reserved)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: headed viewport auto keeps the user's active tab; render's closetab opts out of sessions
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: sessions, phone emulation and touch in BROWSER.md; session: client ids reserved; TODOS #1961/#3058 shipped
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: copy lib/result-codes-browse.ts into the fixtures that copy the result-code modules
lib/result-codes.ts imports ./result-codes-browse, so fixtures with an explicit
lib list failed with 'Cannot find module'. pr-dependencies lists it with the other
reason-code modules as selection data. GSTA-227
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat: gstack-clean reclaims per-repo .gstack scratch and logs, dry run by default (#2627)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* browse: name the Aside touch recipe's coordinates <tap-x>/<tap-y> with a numeric grammar
The generated-bash lint (INV-3) rejected the free-text <x>/<y> placeholders. GSTA-227
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(clean): leave hard-linked and unreadable logs alone; cut through a no-follow descriptor checked against the evaluated inode
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(clean): tests that expect tmp removal see a quiet ps, so a codex elsewhere on the host cannot flake them
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(clean): an unlistable tmp/ skips its group; liveness asked once per group on apply; BROWSER.md says which logs reset at daemon start
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(clean): write output synchronously so --json reaches a pipe whole; test fixes for root, wrapper git and the ps stub
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(clean): every change rechecks the verified folder and the measured file; full writes; EPIPE ends output quietly
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(clean): the early-close test checks the bin's own exit status
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: list gstack-clean among the standalone CLIs
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(clean): copied-install fixtures and the dependency list carry lib/result-codes-clean.ts
The remote pregate failed 11 cases in gstack-doctor, plan-tune-cathedral and
timeline-stop-hook-slug: each copies an explicit list of lib/result-codes-*.ts
files into a temp install, and lib/result-codes.ts now imports
./result-codes-clean. Same lists GSTA-168 extended for result-codes-eval.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore: regenerate gstack-doctor-components.sh for the gstack-clean result codes
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* qa: fold the touch pointer into the Phases sentence to fit the parity size cap after the main merge
qa's union was 95988 bytes (ratio 1.142 > maxSizeRatio 1.142, train 75). Now 95975 (1.1419). GSTA-227
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: #3058 troubleshooting 'Fixed in' lines name v1.92.10.0 after the main merge
GSTA-227
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(clean): classify gstack-tasks rows files (tasks-*) as kept, after main added the producer
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: #3058 troubleshooting 'Fixed in' lines name v1.92.20.0 after the main merge
GSTA-227
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (restore the lib/result-codes-plan.ts ratchet row the base merge dropped)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(clean): the producer scan ends a name at a colon, so prose after a path names the file (train 78)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: #3058 troubleshooting 'Fixed in' lines name v1.92.30.0 after the main merge
GSTA-227
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* outside-voice-api: caller receipts, stop_reason, OpenAI max_completion_tokens
A caller can write its own egress receipt (sink, consent, payload class);
the default stays the outside-voice receipt, so existing callers send and
record the same bytes. The result carries the provider's stop reason, and
an OpenAI request gets max_completion_tokens only when the caller sets an
output limit (GST-537 PR 3).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* autoplan gate: item classes and the owner's answer provenance
Gate items carry item_class, ruleKept() names the keep-direction pick, and
answered decision rows record owner_mode, owner_named, rec_hash and
answered_role parsed from the owner's own words (GST-537 PR 3).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* autoplan: shadow-mode decider module, frozen prompt and spend accounting
The switch (off by default, fixed at init), the lease, one model call per
gate with a page retry and a truncation retry under one deadline, the
once-per-revision record with its journaled sha256, the 10% audit mark,
and shadow-labeled ledger rows that count against the cap, show as
shadow= on GATE_SPEND and stay out of the per-voice price (GST-537 PR 3).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* gstack-autoplan: shadow every published gate, the shadow export, config and docs
Every driver command that prints a gate records the shadow first and
checkpoints after it; answer waits for a live lease and records a dead
one retrospectively; gstack-autoplan shadow exports answered revisions
for taste-replay R2 (SHADOW_BEFORE_ANSWER otherwise); gstack-config
autoplan_shadow / autoplan_shadow_model; gstack-artifact validate checks
the record's hash (GST-537 PR 3).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* changelog: shadow mode for the CEO-only decider (GST-537 PR 3)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* autoplan shadow: /ship review fixes
- register test/fixtures/shadow-fake-model.ts in FREE_FIXTURES (free-fixtures inventory failed)
- withRunLock: count dead-owner reclaims apart from waitMs iterations, so a long wait can still reclaim
- buildPage: fill the decider template in one pass, so slot names inside the plan stay plan text
- revise regate: the shared publish step prints the GATE and ESCALATE lines once
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* autoplan shadow: reply files never follow a link; the retry reserves against the current cap
- a model reply is written by temp file and rename, so a link at the reply path is replaced, not written through
- each shadow reservation reads the run's current spend cap, so a budget change during the call is not undone
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* outside-voice-api: write the egress receipt under the caller's env
callModel resolved the receipt's state root from process.env even when the caller passed env, so the shadow
tests wrote to the real ~/.gstack (the free-suite home-containment guard caught it). The receipt now uses
req.env; the shadow tests give the fake model a private HOME, GSTACK_HOME and GSTACK_STATE_ROOT, and the receipt
test no longer sets process.env to pass.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(autoplan): CEO-only runs leave main's open Critical/High finding items to the owner (no decision row)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(autoplan): shadow pages carry main's finding items; a finding item is never ceo_eligible
After merging #3767 (main 90a170c), open Critical/High findings are gate items
(item_class finding). The shadow records one row per gate item, so its pages now
include them. A CEO-only run leaves those items to the owner, so their rows are
ceo_eligible false (rule_pick was already null). The shadow fixtures follow
main's gate (items, counts, "Do it" tokens); the two merge adapters follow
main's doNext(out, rest, price) and its per-voice reservation (--estimate-usd).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: #3058 troubleshooting 'Fixed in' lines name v1.92.61.0 after the main merge
GSTA-227
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(investigate): drop the five-phase step procedure (GST-938)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* changelog: GST-938 fragment wording
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(investigate): keep the web-search sanitize guard; update BROWSER.md and docs/skills.md (review pass 1)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* changelog: GST-938 wording
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(investigate): pin the web-search guard; changelog size (adversarial review)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(clean): classify restamp-staging.json, the restamp producer main gained after #3779's base (wave browse)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: pre-landing review fixes (wave browse): scoped newtab keeps a concurrent tab switch; shadow validate catches a deleted record; a failed shadow publish is journaled
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: a failed shadow publish journals under the run lock and never throws (wave browse review pass 2)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(unattended): shadow publish failures and the missing-record validate check (wave browse docs audit)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* changelog: wave browse integrator fixes fragment
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix: shadow reader dedupes by run folder, so two runs started in the same second both count (wave browse CI free-suite 16)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore: regenerate doctor result anchors in generator order (wave browse rebuild without #3818)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* changelog: name the wave fragment after the rebuilt wave
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>
129 lines
9.9 KiB
TypeScript
129 lines
9.9 KiB
TypeScript
/**
|
|
* autoplan-shadow-reader — the read side of shadow mode (lib/autoplan-shadow.ts,
|
|
* docs/unattended.md#shadow-mode). `exportShadow` is `gstack-autoplan shadow
|
|
* --out <dir> | --runs <file>`, the export gstack-evals reads for taste-replay
|
|
* R2: one row per item of each answered gate revision, with the shadow's
|
|
* status (recorded, malformed, failed with its code, missing, retrospective, or
|
|
* off when the run never turned shadow on), the shadow fields when present, and
|
|
* the owner's answer with its provenance (owner_mode, owner_named, carried,
|
|
* answered_role, rec_hash at record and at answer). It computes no agreement
|
|
* number, only counts. A revision whose plan approval is unanswered or answered
|
|
* c (interrogate) refuses SHADOW_BEFORE_ANSWER (a courtesy for honest tools,
|
|
* not access control: the journaled sha256 is the tamper evidence), and a
|
|
* CEO-only run CEO_ONLY_NO_GATE. Read-only. `validateShadow` is the private
|
|
* check `gstack-artifact validate <run.json>` adds: each record's schema and
|
|
* its journaled sha256.
|
|
*/
|
|
import { createHash } from 'node:crypto';
|
|
import * as fs from 'node:fs';
|
|
import * as path from 'node:path';
|
|
import { previousGate } from './autoplan-gate';
|
|
import { readDecisions, readJournal, readState } from './autoplan-state';
|
|
import type { ResultCodeName } from './result-codes';
|
|
import type { ValidationError } from './headless-artifacts';
|
|
import { RECORD_RE, SHADOW_ACTIONS, recordFile, shadowDir } from './autoplan-shadow';
|
|
|
|
export type ShadowStatus = 'recorded' | 'malformed' | 'failed' | 'missing' | 'retrospective' | 'off';
|
|
export interface ShadowExportRow {
|
|
run: string; gate_rev: number; item: string; decision: string; item_class: string | null; ceo_eligible: boolean; status: ShadowStatus; code?: string;
|
|
shadow: Record<string, unknown> | null;
|
|
owner: { chosen: string | null; status: string; owner_mode: string | null; owner_named: boolean | null; carried: boolean; carried_from: string | null; answered_role: string | null; answered_by: string | null; rec_hash_at_answer: string | null; rec_hash_at_record: string | null };
|
|
}
|
|
export interface ShadowExport { rows: ShadowExportRow[]; counts: Record<string, Record<string, number>>; refused: Array<{ run: string; gate_rev?: number; code: ResultCodeName; detail: string }> }
|
|
|
|
const readRows = (file: string) => fs.readFileSync(file, 'utf8').split('\n').filter(Boolean).map(l => JSON.parse(l) as Record<string, any>);
|
|
|
|
/** Every answered revision of every run, deduped by run folder, gate_rev and item (two runs can share a run id). */
|
|
export function exportShadow(dirs: string[]): ShadowExport {
|
|
const rows = new Map<string, ShadowExportRow>();
|
|
const refused: ShadowExport['refused'] = [];
|
|
for (const dir of dirs) {
|
|
let state;
|
|
try { state = readState(dir); } catch (e: any) { refused.push({ run: dir, code: e.code ?? 'RUN_NOT_INITIALIZED', detail: `${dir}: ${e.detail ?? e.message}` }); continue; }
|
|
if (state.ceo_only) { refused.push({ run: state.run, code: 'CEO_ONLY_NO_GATE', detail: `${dir} is CEO-only run ${state.run}: no gate, nothing answered` }); continue; }
|
|
const key = fs.realpathSync(dir);
|
|
const decisions = readDecisions(dir).filter(r => r.gate_rev >= 1);
|
|
const journal = readJournal(dir);
|
|
for (const rev of [...new Set(decisions.map(r => r.gate_rev))].sort((a, b) => a - b)) {
|
|
const revRows = decisions.filter(r => r.gate_rev === rev);
|
|
const p1 = revRows.find(r => (r.label ?? '').toLowerCase() === 'p1');
|
|
if (!p1?.chosen || p1.status === 'pending' || p1.chosen === 'c') {
|
|
refused.push({ run: state.run, gate_rev: rev, code: 'SHADOW_BEFORE_ANSWER', detail: `${dir} gate_rev ${rev}: the plan approval is ${p1?.chosen === 'c' ? 'answered c (interrogate)' : 'unanswered'}; the export waits for the owner` });
|
|
continue;
|
|
}
|
|
const record = fs.existsSync(recordFile(dir, rev)) ? new Map(readRows(recordFile(dir, rev)).map(r => [String(r.item), r])) : undefined;
|
|
const failed = journal.find(r => r.event === 'shadow_failed' && r.gate_rev === rev);
|
|
const gate = previousGate(dir, rev);
|
|
for (const d of revRows) {
|
|
const item = (d.label ?? d.id).toLowerCase();
|
|
const s = record?.get(item);
|
|
const status: ShadowStatus = s ? (s.retrospective ? 'retrospective' : s.status) : failed ? 'failed' : state.shadow?.enabled ? 'missing' : 'off';
|
|
const gateItem = gate?.items.find(i => i.id === item);
|
|
const row: ShadowExportRow = {
|
|
run: state.run, gate_rev: rev, item, decision: d.id, item_class: s?.item_class ?? gateItem?.item_class ?? null, ceo_eligible: s?.ceo_eligible ?? ((s?.item_class ?? gateItem?.item_class) !== 'finding' && (item === 'p1' || d.phase === 'ceo')), status,
|
|
...(status === 'failed' ? { code: String(failed!.code) } : {}),
|
|
shadow: s ? Object.fromEntries(['action', 'pick', 'confidence', 'cites', 'reason', 'malformed', 'rule_pick', 'audit', 'model', 'prompt_version', 'prompt_sha256', 'rec_hash', 'rec_rev', 'recorded_at', 'retrospective'].filter(k => k in s).map(k => [k, s[k]])) : null,
|
|
owner: { chosen: d.chosen ?? null, status: d.status, owner_mode: d.owner_mode ?? null, owner_named: d.owner_named ?? null, carried: !!(d.carried_from || d.carried_gate_from), carried_from: d.carried_from ?? d.carried_gate_from ?? null,
|
|
answered_role: d.answered_role ?? null, answered_by: d.answered_by ?? null, rec_hash_at_answer: d.rec_hash ?? null, rec_hash_at_record: s?.rec_hash ?? null },
|
|
};
|
|
rows.set(`${key}|${rev}|${item}`, row);
|
|
}
|
|
}
|
|
}
|
|
const all = [...rows.values()];
|
|
const count = (key: (r: ShadowExportRow) => string) => all.reduce<Record<string, number>>((c, r) => { const k = key(r); c[k] = (c[k] ?? 0) + 1; return c; }, {});
|
|
return { rows: all, refused, counts: { status: count(r => r.status), item_class: count(r => r.item_class ?? 'unknown'), owner_mode: count(r => r.owner.owner_mode ?? 'none'), ceo_eligible: count(r => String(r.ceo_eligible)) } };
|
|
}
|
|
|
|
export function renderShadowExport(r: ShadowExport): string[] {
|
|
const counts = Object.entries(r.counts).map(([k, c]) => `SHADOW_COUNTS: ${k} ${Object.entries(c).map(([v, n]) => `${v}=${n}`).join(' ') || 'none'}`);
|
|
return [...r.rows.map(row => `SHADOW_ROW: ${JSON.stringify(row)}`), ...counts, `SHADOW_EXPORT: rows=${r.rows.length} refused=${r.refused.length} (no agreement number: gstack-evals computes it)`];
|
|
}
|
|
|
|
/** The private check behind gstack-artifact validate: each shadow record matches its journaled sha256 and its rows the schema. */
|
|
export function validateShadow(runDir: string): ValidationError[] {
|
|
const dir = shadowDir(runDir);
|
|
const journal = readJournal(runDir);
|
|
const missing = (present: Set<number>): ValidationError[] => [...new Set(journal.filter(r => r.event === 'shadow_recorded').map(r => Number(r.gate_rev)))]
|
|
.filter(rev => !present.has(rev))
|
|
.map(rev => ({ code: 'ARTIFACT_STALE', path: `shadow/${path.basename(recordFile(runDir, rev))}`, message: `the journal records gate_rev ${rev}, but its shadow record is missing` }));
|
|
let st: fs.Stats;
|
|
try { st = fs.lstatSync(dir); } catch { return missing(new Set()); }
|
|
if (!st.isDirectory()) return [{ code: 'ARTIFACT_PATH_ESCAPE', path: 'shadow', message: 'the shadow folder is a symlink or not a directory' }];
|
|
const errors: ValidationError[] = [];
|
|
const present = new Set<number>();
|
|
for (const name of fs.readdirSync(dir)) {
|
|
const m = RECORD_RE.exec(name);
|
|
if (!m) continue;
|
|
const rev = Number(m[1]);
|
|
present.add(rev);
|
|
const rel = `shadow/${name}`;
|
|
const bytes = fs.readFileSync(path.join(dir, name));
|
|
const recorded = journal.filter(r => r.event === 'shadow_recorded' && r.gate_rev === rev).at(-1);
|
|
const sha = createHash('sha256').update(bytes).digest('hex');
|
|
if (!recorded) errors.push({ code: 'ARTIFACT_STALE', path: rel, message: `no shadow_recorded journal row names gate_rev ${rev}` });
|
|
else if (recorded.sha256 !== sha) errors.push({ code: 'ARTIFACT_STALE', path: rel, message: `sha256 ${sha.slice(0, 12)} is not the journaled ${String(recorded.sha256).slice(0, 12)}` });
|
|
bytes.toString('utf8').split('\n').filter(Boolean).forEach((line, i) => {
|
|
let row: Record<string, any>;
|
|
try { row = JSON.parse(line); } catch { errors.push({ code: 'ARTIFACT_SCHEMA', path: `${rel}:${i + 1}`, message: 'not JSON' }); return; }
|
|
const problem = rowProblem(row, rev);
|
|
if (problem) errors.push({ code: 'ARTIFACT_SCHEMA', path: `${rel}:${i + 1}`, message: problem });
|
|
});
|
|
}
|
|
return [...errors, ...missing(present)];
|
|
}
|
|
|
|
function rowProblem(r: Record<string, any>, rev: number): string | undefined {
|
|
if (r.schema_version !== 1 || r.gate_rev !== rev) return `schema_version 1 and gate_rev ${rev} expected`;
|
|
for (const k of ['run', 'decision', 'item', 'model', 'prompt_sha256', 'recorded_at']) if (typeof r[k] !== 'string' || !r[k]) return `${k} must be a non-empty string`;
|
|
if (typeof r.retrospective !== 'boolean' || typeof r.audit !== 'boolean' || typeof r.ceo_eligible !== 'boolean') return 'retrospective, audit and ceo_eligible must be booleans';
|
|
if (r.status === 'malformed') return r.pick === null && !r.audit ? undefined : 'a malformed row carries no pick and no audit mark';
|
|
if (r.status !== 'recorded') return `status ${JSON.stringify(r.status)} is not recorded or malformed`;
|
|
if (!SHADOW_ACTIONS.includes(r.action)) return 'action must be decide, send_back or hold';
|
|
if (typeof r.pick !== 'string' || !Array.isArray(r.item_frozen?.options) || !r.item_frozen.options.some((o: { key?: string }) => o.key === r.pick)) return 'pick must be one of the frozen item\'s options';
|
|
if (typeof r.confidence !== 'number' || !(r.confidence >= 0 && r.confidence <= 1)) return 'confidence must be a number from 0 to 1';
|
|
if (!Array.isArray(r.cites) || typeof r.reason !== 'string' || r.reason.length > 400) return 'cites must be a list and reason a string of at most 400 characters';
|
|
if (r.audit && r.action !== 'decide') return 'only a decide row carries the audit mark';
|
|
return undefined;
|
|
}
|