mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-09 06:28:59 +02:00
* fix: pin the claude CLI to an exact version in the CI image + tripwire The image installed @anthropic-ai/claude-code UNPINNED and rebuilt weekly 'to pick up CLI updates' — while bun sat carefully pinned at 1.3.13 two RUN lines above. The PTY harness screen-scrapes this CLI's TUI, and that drift broke it three separate times (welcome-screen wedge on 2.1.233, skillify HOME discovery on 2.1.237, guard/freeze hooks on 2.1.162), each debugged as a flake first. Pin 2.1.251 (current latest), bump deliberately via a PR that runs the PTY gate, and enforce with test/ci-image-cli-pin.test.ts: any global npm install in Dockerfile.ci without an exact @X.Y.Z pin fails the free suite. The weekly ci-image cron stays as a cheap tag self-heal. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat: stamp the claude CLI version into every eval-store run record Three harness breakages were traced to claude-CLI TUI drift only after long flake hunts, because no run record said which CLI it actually exercised. EvalCollector now stamps claude_cli_version (claude --version, cached once per process, 'unknown' when the binary is absent) into both partial and finalized records — schema-additive optional field, no SCHEMA_VERSION bump. Correlating a flake wave with a CLI release becomes a grep over ~/.gstack/projects/<slug>/evals/ instead of archaeology. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: give the spinning-shard kill test load headroom (30s -> 90s) The test spawns and group-kills three real children (one a busy-loop burning a full core) while five sibling shard processes compete for eight vCPUs. Under full-suite load it blew bun's default 30s per-test ceiling at 30,009ms — while passing in isolation in 1.4s — and red the only required lane. Every assertion in it is event-based (statuses, group-kill proof, heartbeat lines); the sole latency claim is the <30s kill-deadline sanity bound, which stays. Explicit 90s headroom, not a weakened oracle. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat: green-by-skip census — skip counts in the classifier, all-skipped labeling in the paid runner bun's 'Ran N tests' line COUNTS skipped tests, so a codex/gemini shard whose every test self-skipped (binary absent on the runner — true of every CI runner today) exits 0, dodges the hollow-shard guard, and reads as coverage in the weekly census. The classifier now parses bun's ' N skip' / ' N pass' recap lines; ShardOutcome carries skippedTests; formatSummary and the fail-closed slices report label an all-skipped pass explicitly: 'all N tests SKIPPED — verified nothing'. Status stays 'passed' (external service availability is host state, not a repo regression) but the census can no longer mistake absence for coverage. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * refactor: extract composite actions for eval-lane setup; surviving lanes gain the fail-fast registry verification 'Fix bun temp' x3, 'Restore deps' x5, 'Seed claude interactive config' x3, and 'Register gstack skills' x3 were byte-near-identical copies across the legacy matrix, the sliced lane, and the periodic lane — and only the MATRIX copy of register-skills carried the 19-line dangling-symlink + frontmatter fail-fast loop written after a silent 'Unknown command' + 35-min-timeout incident. Extract all four into .github/actions/ composites; the register composite carries the verification loop (generalized over the skill list), so the sliced and periodic lanes — the lanes that SURVIVE the matrix deletion — now inherit the check they had silently dropped. Matrix-job inline copies are left untouched: that job is deleted next. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat: delete the legacy 17-row eval matrix — the sliced lane is the only paid lane Every PR paid twice: the hand-enumerated matrix (18 test files, 22.6 min, ~$21 API measured on run 33263204465) ran serialized AHEAD of the strictly superior sliced lane via 'needs: evals' — 35.5 min wall and ~2x paid spend for the same diff. 14 of 17 rows carried no tier:, so periodic Opus benchmarks leaked into every PR (the e2e-plan row alone: 12/12 tests, 21.7 min, $7.28 — the wall-clock bound of ALL of CI). Parity receipt (static, pre-deletion): the sliced lane's gate census (49 files, derived from the runner itself) strictly contains all 18 matrix test files, plus 31 files the matrix never ran. Pure deletion — one revert restores it. The PR comment moved into slices-report (same '## E2E Evals' upsert marker, now sourced from slice artifacts + carrying the fail-closed reconciliation verdict). plan-slices loses the needs edge; the dead workflow-level EVALS_TIER env goes with it. test/evals-workflow-matrix.test.ts (and its KNOWN_MATRIX_GAPS / KNOWN_TIER_UNSET burn-down ratchets — retired: the sliced census makes 'every gate file runs' true by construction) is rewritten as test/evals-workflow-wiring.test.ts: matrix stays deleted, planner/executor/ report tier + slice-count agreement, both surviving lanes on the shared register-skills composite with its fail-fast verification loop, PR comment survival. Expected: PR eval wall 35.5 -> ~13 min, per-PR paid spend ~halved. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: provider-runner timeouts kill the whole process GROUP; codex/gemini inherit the orphan-drain hardening All three provider runners (claude/codex/gemini) killed only the direct child on timeout: tool subprocesses the CLI spawned survived as orphans holding our pipes open and burning shared API rate (observed: a 600s timeout stretching past 1400s; a stalled run once burned a core for 15 hours). gstack-detach's watchdog had the same shape one level up — killpg SIGTERM, 5s grace, then a direct-child proc.kill() that orphaned grandchildren. Fix: spawn provider children via node:child_process with detached (own process group) and killProcessGroup(SIGKILL) in the timeout handler — runShardChild's proven pattern, EPERM/ESRCH fallbacks included. The codex and gemini copies also gain the reader.cancel() + stderr Promise.race hardening only the claude copy had (they still carried the blocked-drain hang it fixed). gstack-detach's watchdog now group-SIGKILLs after the grace. Regression net: test/session-runner-groupkill.test.ts drives the REAL runSkillTest against a fake claude shim (PATH override) that spawns a grandchild and wedges — the run must classify timeout within budget and leave neither shim nor grandchild alive — plus source pins on all three runners (detached + killProcessGroup, no bare timeout kill, no Bun.spawn reversion). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: skill-e2e-opus-47 renders SKILL.md fixtures into a mkdtemp — never the live tree mkEvalRoot ran gen-skill-docs with cwd=ROOT, regenerating every in-repo SKILL.md mid-run while concurrent paid shards copyFileSync those same files in their beforeAll (EVALS_JOBS>=4 locally, 2 per CI slice) — a sibling could capture a half-regenerated or opus-rendered SKILL.md, and a timeout before afterAll stranded the whole tree at the wrong model for every later shard. A cross-shard race that could flake ANY concurrent paid test. Render via the --out-dir flag gen-skill-docs grew for exactly this reason (mirrors the repo layout, which is all the fixture reads), read the skill heads from the render dir, delete it, and drop the afterAll restore-regen entirely. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: claude CLI version resolves in the runner parent, never on a test thread Eng-review finding: getClaudeCliVersion's fallback is a SYNCHRONOUS spawnSync on the same thread that polls concurrent PTY/session tests — the judgePtyState blocking class this overhaul kills elsewhere. The paid runner parent now resolves it once (cached) and stamps GSTACK_CLAUDE_CLI_VERSION into every shard's env; eval-store short-circuits on the env var, and the fallback spawn's budget tightens 10s -> 3s (bounded one-time stall, records 'unknown' on a slow CLI). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test: wire skippedTests end-to-end through runPaidShard The census unit tests hand-built outcomes and the classifier tests parsed strings; nothing proved a real child's ' N skip' recap flows into outcome.skippedTests and the formatSummary label. A commandFor fake now prints the recap shape and the test asserts the parsed counts, the all-skipped predicate, and the 'verified nothing' label. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: make the setup composites rerun-safe (codex diff-review hardenings) restore-deps: 'cp -r SRC node_modules' with an existing node_modules NESTS the copy and leaves stale deps active — rm first. register-gstack-skills: 'ln -snf' hard-errors under set -eu when a REAL directory occupies the gstack slot — clear a non-symlink leftover first. CI workspaces are fresh today; a reusable composite must survive dirty reruns. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: sweep — every sync spawn in the test trees carries a timeout (436 sites, 157 files) spawnSync/execSync/Bun.spawnSync BLOCK the main thread, so bun's in-process per-test timeout can never fire while one waits — a hung child (stdin read, network probe, dead daemon) wedges the whole shard until the runner's external wall-clock SIGKILL. This exact class reached main: free-tests run 33262077256, test/gstack-memory-ingest.test.ts (normally 2.3s) held shard 2 at the 360s wall while its five siblings finished in ~65s. Mechanical sweep in two waves (12 + 4 fan-out agents, every edit verified against its call site): default timeout: 30_000 (matches the free runner's per-test budget), 120_000 for genuinely slow ops (installs, builds, playwright, provider CLIs), helper wrappers fixed ONCE where call sites route through them. Sites that only LOOK like calls (string fixtures, grep needles, comments) were skipped with reasons — the enforcement commit that follows marks them exempt. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test: sync-spawn timeout tripwire — the wedge class stays extinct Free scanner over all test trees (test/, browse/test/, design/test/, make-pdf/test/, ios-qa, browser-skills): every spawnSync/execSync/ Bun.spawnSync call site must carry a timeout within a 30-line options window, or an explicit '// tripwire-exempt: <reason>' marker. Comment lines are skipped; exemptions are counted and ratcheted shrink-only (ceiling 6 = the 6 string-fixture/grep-needle sites where the pattern is CONTENT, not a call — marked in this commit). A scan-sanity test pins that the scanner still sees >100 real call sites so it can never rot to a vacuous green. Companion to the 436-site sweep in the previous commit. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat: paid-lane flake telemetry — record-level attempts, flaky_retries, report surfacing bun --retry leaves a retried pass INVISIBLE in its output: a fail-then-pass prints the error detail but no (fail) result line and recaps as a clean pass (probed live on 1.3.10). So attempts are recorded where they cannot lie: EvalCollector.addTest stamps a 1-based attempt on same-name re-records (a retried test runs its body again and re-records), finalized runs carry flaky_retries, printSummary warns loudly, and the fail-closed slices report lists every passed-only-on-retry test — recorded and ranked, never blocking and never silent. Cross-model confirmed (codex reached the same don't-parse -the-stream conclusion independently). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat: free-lane flake ledger — retry ON in CI, flaky-passes recorded and uploaded The runner's attribution-gated flaky-retry pass (cap 5, truncation veto) was OFF in the required lane and its FLAKY-PASS evidence was console-only — so a single timing flake red the merge gate while repeat offenders stayed unenumerable. free-tests.yml now sets GSTACK_FREE_RETRY_FLAKY=1 and points GSTACK_FLAKE_LEDGER at runner.temp; every flaky-pass appends a JSONL entry (SINGLE writer: the parent runner — no concurrent-append hazard by construction; fail-open with a loud warning so a broken ledger can never red the lane) and the artifact uploads UNCONDITIONALLY — a flaky-pass run is green, which is exactly when the evidence matters. Wiring pinned by free-tests-workflow-wiring; ledger behavior unit-tested incl. the fail-open path. Matches 2026 industry practice (retry for data, quarantine out of merge-blocking but never out of logging) with the repo's own receipts. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat: eval:flake-rank — the flake-telemetry dial Aggregates per-test series across every finalized eval-store run (shard dirs included) plus the free flake ledger: runs, fails, RETRIED PASSES (the flake signature), avg duration — ranked retries-first. This is the readable dial behind two policies: a flaky pass never blocks a merge but is always ranked here, and the WS16 required-check promotion needs weeks of clean flake-rank, not vibes. --json for machines, --dir for downloaded CI artifacts. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat: two-phase session timeout — silent APIs die at the startup grace, named The single spawn-armed timer charged API queue latency to the work budget: the recurring '0 turns / $0.00 / x3 attempts' failure with four budget-bump receipts (180->300s, 240->360s, 300->420s, 90->300s). Split: startup phase (no NDJSON byte yet) kills EARLY at min(grace, timeout) with the distinct exitReason 'timeout_startup' — an availability verdict, not transcript archaeology — and the work phase arms on the first byte for the REMAINING budget, so total wall never exceeds the timeout (tier envelopes are margin-free: tests pass timeout: CAPTURE_MS and bun-budget the same tier). Local grace 90s (observed queue latency 60-90s), CI floor 300s (TODOS-filed; shared runners queue harder), both pinned by the new grace tests with fake -claude shims covering the late-first-byte and silent-API paths. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: census integrity — 17 phantom selection keys deleted, reverse invariant added, gitignored dep patterns replaced, local map forks derived The merge-blocking gate census counted tests that could not run. Deleted (critic-verified against both quoted-occurrence and dep-registration liveness): 7 *-prosons-format keys with no declaring test, ship-plan- completion/-verification, review-plan-completion, design-shotgun-path/ session/full, autoplan-core (dead ~10 months), e2e-harness-audit (its namesake is a FREE-suite file), plus 2 dead LLM-judge keys and 2 free-file keys (budget-regression-pty, global-discover) misplaced in the PAID maps. Census: 191 -> 174 keys, gate 86 -> 78 honest. The new reverse invariant in touchfiles.test.ts makes the class structurally impossible: every key must be quoted in a living paid test file OR registered to an existing paid test file via its dep list (the constructed- name binding the 2026-08 self-registration sweep established) — zero exceptions needed today, with a live-file check on any future exception. Also: '.agents/skills/**' dep patterns replaced with the generator (scripts/gen-skill-docs.ts) — .agents/ is gitignored, so those patterns could NEVER match a git diff and review-template edits silently stopped selecting codex/gemini tests; the codex/gemini local touchfile maps are now DERIVED from the canonical map (loud throw if a key vanishes) instead of hand-forked copies that had already drifted. ios-qa-e2e demoted gate -> periodic: its gate declaration was never executable in CI (hardware exclusion only applies at tier=periodic), so every Linux PR planned a hollow shard. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: routing journeys lose their answer key and end at the routing decision The journey tests exist to catch skill-DESCRIPTION regressions (touchfiles: */SKILL.md.tmpl), but the fixture CLAUDE.md shipped an explicit prompt->skill lookup table — with the answer key in context, a badly regressed frontmatter description still routed correctly, so the tests could not fail on the exact class they select for. The fixture now carries only the generic invoke-skills nudge; the frontmatter carries the routing load. Also capped all 10 journeys at maxTurns 2 / tools [Skill, Read]: only the FIRST Skill call is asserted, so 5 turns of Read/Bash/Glob/Grep was pure spend — roughly halves each journey's cost. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: retire decided A/B experiments; vendor the pre-cut fixture; ban raw-SHA fixtures Three one-shot decision experiments kept re-running weekly as N=1 stochastic comparisons — flaky by construction with near-zero remaining information: skill-e2e-auq-repetition-cut-ab (its own header: gate "passed pre-landing, approved 2026-08-25"), skill-e2e-preamble-script-ab ("demoted post-Phase-3"), and opus-47's fanout arm-vs-arm (parA >= parB across two SINGLE stochastic runs — a coin flip). Deleted, with their selection keys; the SDK overlay-harness stays as the maintained instrument for the next experiment, and opus-47 keeps its routing-precision cases. verboseSkill() now reads the VENDORED test/fixtures/auq-pre-cut-...-SKILL.md instead of `git show ab66193e^:...` — a branch-local ref that dies on branch prune and already failed on shallow clones. New free tripwire (test/git-ref-fixture-tripwire.test.ts) bans the raw-SHA fixture class outright: quoted SHA:path rev-specs and gitRef-style hex defaults in the test trees fail the suite with the vendor-instead instruction. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: demote plan-ceo-review-expansion-energy to periodic Opus generator + a subjective 2-axis >=4/5 LLM-judge threshold sat in the MERGE-BLOCKING gate — the exact class its sibling posture tests were demoted for, with a receipt (a +21-line preamble change once flipped the score). CLAUDE.md's own tiering rule: Opus model test -> periodic. The weekly lane keeps the regression signal; merges stop paying a judge- temperament tax. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: paid shards get per-shard TMPDIR + CHROMIUM_PROFILE isolation and a kill-path cleanup backstop The free runner treats this isolation as MANDATORY (two concurrent shards on one Chromium profile kill each other's browser; shared tmp cross-contaminates) — the paid lane had none of it. Doubly load-bearing here: a shard that hits its 30-min wall is group-SIGKILLed, so per-test afterAll cleanup never runs; the rmSync backstop is the only thing keeping wedged runs from accumulating full git-repo workspaces in the shared tmpdir forever. This is the DAG prerequisite for raising EVALS_JOBS (next commit) — more concurrency on shared state amplifies exactly the shared-tree race class opus-47 exhibited. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * feat: paid-runner defaults 4x4 -> 8x2 — halve the local gate worst case 39 of 75 skill-e2e files hold exactly ONE test, so within-shard concurrency was dead weight for most shards: 4 jobs x 4 concurrency yielded only ~4-6 real in-flight sessions and a 13-wave local gate worst case (~6.5h). 8 jobs x 2 gives ~10-13 in-flight — under the documented-safe ~15 — and ~7 waves (~3.3h worst case). CI lanes keep their explicit EVALS_JOBS env (2 per slice; 4 for gate-census); this changes local defaults. Rollback trigger: sustained 429 storms in the WS1 telemetry across 2 PR cycles. test/eval-detach-timeout-floor.test.ts recomputed green (the raise LOWERS the worst-case floor). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: SHA-pin every action in the secrets-bearing eval lanes evals.yml and evals-periodic.yml execute PR-authored code with three provider API keys in env, yet rode mutable action tags (@v7/@v8/@v2/@v4) — while quality-gate.yml, osv-scanner.yml, and dependency-review.yml already model the SHA-pin pattern. All 30 uses sites across both lanes now pin the exact commit (tag noted in a trailing comment); dependabot's github-actions ecosystem keeps them fresh via PRs instead of silent tag moves. Pulled forward from the plan's endgame on the CEO-review + outside- voice agreement: supply-chain pins on secret lanes go first, not last. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: sweep wave 3 — the execFileSync family gets timeouts (90 sites, 17 files) The tripwire's regex covered spawnSync/execSync/Bun.spawnSync but not execFileSync — an entire blocking sync-spawn API family that could reintroduce the shard-wedge class undetected (ship review army). Same mechanical recipe as waves 1-2: timeout: 30_000 default, 120_000 for slow ops, shared wrappers fixed once, string-needle sites skipped with reasons. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * test: review-army + adversarial test hardening - Tripwire scans execFileSync too (ceiling 8: two more grep-needle string exemptions); merge-introduced timeout-less spawnSync in question-preference-hook fixed — the tripwire caught a site that landed on main AFTER the sweep, on its first day. - gstack-detach gains TWO watchdog kill regression tests: TERM-immune grandchild (the killpg-after-grace escalation) and the leader-dies variant (the pgid-at-spawn fix — the case the first test cannot see). - eval-flake-rank gets its unit suite (final-attempt accounting, artifact exclusion, shard recursion, recency bound). - Groupkill/startup-grace shim markers are per-run unique (pid-suffixed sleep durations): sibling Conductor worktrees run free suites with no machine lock, and fixed markers let one run pgrep/pkill the other's shims — a cross-run flake inside the anti-flake tests. - flake-ledger test pins the project-scoped local default; stale empty section headers in touchfiles-data deleted (they invited entries under deliberately retired categories). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: adversarial-review runtime fixes across the telemetry + kill paths - session-runner: exit-labeling keys off 'exit', not 'close' — an orphan holding the pipes could relabel a REAL exit (auth failure) as 'timeout_startup' availability noise; the kill path still always group-kills and cancels the reader (labeling and unblocking are separate concerns). Work phase arms on a flag, not firstResponseMs===0 (a same-ms first byte left the startup timer live all run). The CI startup grace is now a real FLOOR (Math.max), matching its name and pinning test. - gstack-detach: pgid captured AT SPAWN (== child pid under start_new_session) — resolving it after the grace raised ESRCH once the leader died on SIGTERM, orphaning TERM-immune grandchildren forever. - test-free-shards: ledger entries carry branch + git_sha (rev-parse split: '--abbrev-ref HEAD HEAD' printed the branch twice and recorded it as the sha); local ledger default is per-PROJECT, not the machine-global tmpdir. - eval-flake-rank: per-LINE ledger parse (one torn JSONL line vanished the whole series), 60-day recency bound (transcript-bearing files are MBs), shared isFinalizedEvalResultFile predicate (the artifact-taxonomy rule lived in three places); eval-store exports the predicate and finalize stops computing flakyRetries twice; paid-shards cleanup uses async rm (a SIGKILLed shard's git-workspace teardown blocked every sibling's stream classification on the parent event loop). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: CI trust-boundary + fail-closed repairs (adversarial findings) - Token/exec separation restored: slices-report (runs PR-authored code: bun install + the reconcile runner) drops to contents:read; the PR comment moves to a NEW slices-comment job holding the write token with ZERO repo code — no checkout, no bun, only downloaded artifacts + jq/gh. $GITHUB_ENV/BASH_ENV persistence is job-scoped, so the split is the boundary. The matrix-era report job had this property; the consolidation had regressed it. Pinned by the wiring test. - Reconcile exit captured via PIPESTATUS[0] in BOTH lanes: GitHub's default run-step shell has no pipefail, so `$?` after `| tee` was tee's exit — the fail-closed gate was silently fail-open. Wiring test pins it. - PR comment: final-attempt accounting restored the dropped COST accumulation (the dial read $0 forever), flaky passes render as the warning they are (never as failures), and a malformed tests[] artifact skips that file instead of aborting the whole comment under bash -e. - Remaining mutable action tags pinned (free-tests upload-artifact, ci-image checkout/docker trio — the image publisher holds packages:write and feeds the secret-bearing lanes). restore-deps fallback installs --frozen-lockfile; register-gstack-skills validates skill names before its rm -rf. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * chore: bump version and changelog (v1.77.0.0) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: update project documentation for v1.77.0.0 Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: cross-model doc-review fixes — flake-ledger env knobs, CI retry-on note, stale version comment Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs: correct CHANGELOG receipt numbers to measured values Gate census keys: 78 -> 77 (bun-imported E2E_TIERS count). Sweep receipt: 586 sites/176 files -> 499 sites/146 files, measured by running this branch's spawnsync-timeout-tripwire against origin/main (exit 1, 499 violations across 146 unique files; green on this branch). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: slices-comment creates the PR comment via REST — the write-token job has no git context The token/exec split gives slices-comment NO checkout by design, and gh's pr-comment subcommand resolves the repo FROM git — it died with 'not a git repository' on PR #2746's first run (the update-existing PATCH path was already explicit-repo REST and worked). Create now posts through gh api repos/.../issues/N/comments, and the wiring test pins that no git-context-requiring comment call can creep back into the job. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix: startup-grace probes clear CI for local semantics; new probe pins the floor clamp The two shim probes pass explicit 2s/4s graces, but in CI the runner clamps any explicit grace up to the 300s floor (deliberate adversarial-review fix), so 'silent API killed at the grace' died at the 30s work cap instead of 2s — a deterministic red on every CI run, green locally. The probes now pin LOCAL semantics with CI cleared (same save/restore pattern as their PATH shim), and a fourth probe pins the clamp itself: CI=1 + 2s grace + 6s timeout must kill at the 6s cap, still in the startup phase — proof an explicit low grace cannot bypass the floor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
674 lines
25 KiB
TypeScript
674 lines
25 KiB
TypeScript
/**
|
|
* /plan-tune tests (gate tier)
|
|
*
|
|
* Covers the foundation of /plan-tune v1:
|
|
* - Question registry schema validation
|
|
* - Registry completeness (every AskUserQuestion pattern has an id)
|
|
* - Id uniqueness (no duplicates)
|
|
* - One-way door safety declarations
|
|
* - Signal map references valid registry ids
|
|
*
|
|
* Binary-level tests (question-log, question-preference, developer-profile)
|
|
* and migration tests live in sibling files created as those binaries ship.
|
|
*/
|
|
|
|
import { describe, test, expect } from 'bun:test';
|
|
import {
|
|
QUESTIONS,
|
|
getQuestion,
|
|
getOneWayDoorIds,
|
|
getAllRegisteredIds,
|
|
getRegistryStats,
|
|
type QuestionDef,
|
|
} from '../scripts/question-registry';
|
|
import {
|
|
classifyQuestion,
|
|
isOneWayDoor,
|
|
DESTRUCTIVE_PATTERN_LIST,
|
|
ONE_WAY_SKILL_CATEGORY_SET,
|
|
} from '../scripts/one-way-doors';
|
|
import {
|
|
SIGNAL_MAP,
|
|
applySignal,
|
|
validateRegistrySignalKeys,
|
|
newDimensionTotals,
|
|
normalizeToDimensionValue,
|
|
ALL_DIMENSIONS,
|
|
} from '../scripts/psychographic-signals';
|
|
import {
|
|
ARCHETYPES,
|
|
FALLBACK_ARCHETYPE,
|
|
matchArchetype,
|
|
getAllArchetypeNames,
|
|
} from '../scripts/archetypes';
|
|
import * as fs from 'fs';
|
|
import * as path from 'path';
|
|
|
|
const ROOT = path.resolve(import.meta.dir, '..');
|
|
|
|
// -----------------------------------------------------------------------
|
|
// Schema validation
|
|
// -----------------------------------------------------------------------
|
|
|
|
describe('question-registry schema', () => {
|
|
test('every entry has required fields', () => {
|
|
for (const [key, q] of Object.entries(QUESTIONS as Record<string, QuestionDef>)) {
|
|
expect(q.id).toBeDefined();
|
|
expect(q.skill).toBeDefined();
|
|
expect(q.category).toBeDefined();
|
|
expect(q.door_type).toBeDefined();
|
|
expect(q.description).toBeDefined();
|
|
expect(q.description.length).toBeGreaterThan(0);
|
|
expect(q.id).toBe(key); // key and id must match
|
|
}
|
|
});
|
|
|
|
test('all ids are kebab-case and start with skill name', () => {
|
|
for (const q of Object.values(QUESTIONS as Record<string, QuestionDef>)) {
|
|
expect(q.id).toMatch(/^[a-z0-9-]+$/);
|
|
expect(q.id.startsWith(q.skill + '-')).toBe(true);
|
|
expect(q.id.length).toBeLessThanOrEqual(64);
|
|
}
|
|
});
|
|
|
|
test('no duplicate ids (keys and id fields are 1:1 by construction)', () => {
|
|
const ids = Object.values(QUESTIONS as Record<string, QuestionDef>).map((q) => q.id);
|
|
const unique = new Set(ids);
|
|
expect(unique.size).toBe(ids.length);
|
|
});
|
|
|
|
test('category is one of the allowed values', () => {
|
|
const ALLOWED = new Set(['approval', 'clarification', 'routing', 'cherry-pick', 'feedback-loop']);
|
|
for (const q of Object.values(QUESTIONS as Record<string, QuestionDef>)) {
|
|
expect(ALLOWED.has(q.category)).toBe(true);
|
|
}
|
|
});
|
|
|
|
test('door_type is one-way or two-way', () => {
|
|
for (const q of Object.values(QUESTIONS as Record<string, QuestionDef>)) {
|
|
expect(q.door_type === 'one-way' || q.door_type === 'two-way').toBe(true);
|
|
}
|
|
});
|
|
|
|
test('options (if present) are non-empty arrays of strings', () => {
|
|
for (const q of Object.values(QUESTIONS as Record<string, QuestionDef>)) {
|
|
if (q.options) {
|
|
expect(Array.isArray(q.options)).toBe(true);
|
|
expect(q.options.length).toBeGreaterThan(0);
|
|
for (const opt of q.options) {
|
|
expect(typeof opt).toBe('string');
|
|
expect(opt.length).toBeGreaterThan(0);
|
|
}
|
|
}
|
|
}
|
|
});
|
|
|
|
test('descriptions are short and informative (<= 200 chars, no newlines)', () => {
|
|
for (const q of Object.values(QUESTIONS as Record<string, QuestionDef>)) {
|
|
expect(q.description.length).toBeLessThanOrEqual(200);
|
|
expect(q.description.includes('\n')).toBe(false);
|
|
}
|
|
});
|
|
});
|
|
|
|
// -----------------------------------------------------------------------
|
|
// Runtime helpers
|
|
// -----------------------------------------------------------------------
|
|
|
|
describe('question-registry helpers', () => {
|
|
test('getQuestion returns entry for known id', () => {
|
|
const q = getQuestion('ship-test-failure-triage');
|
|
expect(q).toBeDefined();
|
|
expect(q?.skill).toBe('ship');
|
|
expect(q?.door_type).toBe('one-way');
|
|
});
|
|
|
|
test('getQuestion returns undefined for unknown id', () => {
|
|
expect(getQuestion('this-is-not-registered')).toBeUndefined();
|
|
});
|
|
|
|
test('getOneWayDoorIds returns Set of one-way ids', () => {
|
|
const ids = getOneWayDoorIds();
|
|
expect(ids.has('ship-test-failure-triage')).toBe(true);
|
|
expect(ids.has('review-sql-safety')).toBe(true);
|
|
expect(ids.has('land-and-deploy-merge-confirm')).toBe(true);
|
|
// And does NOT include a known two-way door:
|
|
expect(ids.has('ship-changelog-voice-polish')).toBe(false);
|
|
});
|
|
|
|
test('getAllRegisteredIds count matches QUESTIONS keys', () => {
|
|
expect(getAllRegisteredIds().size).toBe(Object.keys(QUESTIONS).length);
|
|
});
|
|
|
|
test('getRegistryStats totals are consistent', () => {
|
|
const stats = getRegistryStats();
|
|
expect(stats.total).toBe(Object.keys(QUESTIONS).length);
|
|
expect(stats.one_way + stats.two_way).toBe(stats.total);
|
|
const bySkillSum = Object.values(stats.by_skill).reduce((a, b) => a + b, 0);
|
|
expect(bySkillSum).toBe(stats.total);
|
|
const byCategorySum = Object.values(stats.by_category).reduce((a, b) => a + b, 0);
|
|
expect(byCategorySum).toBe(stats.total);
|
|
});
|
|
});
|
|
|
|
// -----------------------------------------------------------------------
|
|
// Safety contract — one-way doors
|
|
// -----------------------------------------------------------------------
|
|
|
|
describe('one-way door safety', () => {
|
|
test('every destructive/security question is declared one-way', () => {
|
|
// Safety-critical question ids must exist and be one-way.
|
|
const mustBeOneWay = [
|
|
'ship-test-failure-triage', // shipping broken tests
|
|
'review-sql-safety', // SQL injection path
|
|
'review-llm-trust-boundary', // LLM trust boundary
|
|
'cso-global-scan-approval', // scans outside branch
|
|
'cso-finding-fix', // security finding
|
|
'land-and-deploy-merge-confirm', // actual merge
|
|
'land-and-deploy-rollback', // rollback decision
|
|
'investigate-fix-apply', // applying a fix
|
|
'plan-ceo-review-premise-revise', // changing agreed premise
|
|
'plan-eng-review-arch-finding', // architecture change
|
|
'office-hours-landscape-privacy-gate',// sending data to search provider
|
|
'autoplan-user-challenge', // scope direction change
|
|
];
|
|
const oneWayIds = getOneWayDoorIds();
|
|
for (const id of mustBeOneWay) {
|
|
expect(getQuestion(id)).toBeDefined();
|
|
expect(oneWayIds.has(id)).toBe(true);
|
|
}
|
|
});
|
|
|
|
test('at least 10 one-way doors are declared', () => {
|
|
// Sanity check — if we lose one-way classification on critical questions,
|
|
// this fails before safety bugs ship.
|
|
expect(getOneWayDoorIds().size).toBeGreaterThanOrEqual(10);
|
|
});
|
|
});
|
|
|
|
// -----------------------------------------------------------------------
|
|
// Coverage breadth — make sure we span the high-volume skills
|
|
// -----------------------------------------------------------------------
|
|
|
|
describe('registry breadth', () => {
|
|
test('high-volume skills have at least one registered question', () => {
|
|
const stats = getRegistryStats();
|
|
const highVolume = [
|
|
'ship',
|
|
'review',
|
|
'office-hours',
|
|
'plan-ceo-review',
|
|
'plan-eng-review',
|
|
'plan-design-review',
|
|
'plan-devex-review',
|
|
'qa',
|
|
'investigate',
|
|
'land-and-deploy',
|
|
'cso',
|
|
];
|
|
for (const skill of highVolume) {
|
|
expect(stats.by_skill[skill] ?? 0).toBeGreaterThan(0);
|
|
}
|
|
});
|
|
|
|
test('preamble one-time prompts are registered (telemetry, proactive, routing)', () => {
|
|
expect(getQuestion('preamble-telemetry-consent')).toBeDefined();
|
|
expect(getQuestion('preamble-proactive-behavior')).toBeDefined();
|
|
expect(getQuestion('preamble-routing-injection')).toBeDefined();
|
|
});
|
|
|
|
test('/plan-tune itself registers its enable + setup + mutation-confirm', () => {
|
|
expect(getQuestion('plan-tune-enable-setup')).toBeDefined();
|
|
expect(getQuestion('plan-tune-declared-dimension')).toBeDefined();
|
|
expect(getQuestion('plan-tune-confirm-mutation')).toBeDefined();
|
|
});
|
|
});
|
|
|
|
// -----------------------------------------------------------------------
|
|
// Signal map consistency
|
|
// -----------------------------------------------------------------------
|
|
|
|
describe('psychographic signal map', () => {
|
|
test('signal_keys in registry are typed strings', () => {
|
|
for (const q of Object.values(QUESTIONS as Record<string, QuestionDef>)) {
|
|
if (q.signal_key !== undefined) {
|
|
expect(typeof q.signal_key).toBe('string');
|
|
expect(q.signal_key.length).toBeGreaterThan(0);
|
|
expect(q.signal_key).toMatch(/^[a-z0-9-]+$/);
|
|
}
|
|
}
|
|
});
|
|
|
|
test('every signal_key in registry has a SIGNAL_MAP entry', () => {
|
|
const { missing } = validateRegistrySignalKeys();
|
|
expect(missing).toEqual([]);
|
|
});
|
|
|
|
test('applySignal mutates dimension totals per mapping', () => {
|
|
const dims = newDimensionTotals();
|
|
const applied = applySignal(dims, 'scope-appetite', 'expand');
|
|
expect(applied.length).toBeGreaterThan(0);
|
|
expect(dims.scope_appetite).toBeCloseTo(0.06, 5);
|
|
});
|
|
|
|
test('applySignal returns [] for unknown signal_key', () => {
|
|
const dims = newDimensionTotals();
|
|
const applied = applySignal(dims, 'no-such-signal', 'anything');
|
|
expect(applied).toEqual([]);
|
|
expect(dims.scope_appetite).toBe(0);
|
|
});
|
|
|
|
test('applySignal returns [] for unknown user_choice', () => {
|
|
const dims = newDimensionTotals();
|
|
const applied = applySignal(dims, 'scope-appetite', 'definitely-not-a-real-choice');
|
|
expect(applied).toEqual([]);
|
|
});
|
|
|
|
test('normalizeToDimensionValue maps 0 → 0.5 (neutral)', () => {
|
|
expect(normalizeToDimensionValue(0)).toBeCloseTo(0.5, 5);
|
|
});
|
|
|
|
test('normalizeToDimensionValue returns values in [0, 1]', () => {
|
|
for (const total of [-10, -1, -0.5, 0, 0.5, 1, 10]) {
|
|
const v = normalizeToDimensionValue(total);
|
|
expect(v).toBeGreaterThanOrEqual(0);
|
|
expect(v).toBeLessThanOrEqual(1);
|
|
}
|
|
});
|
|
|
|
test('ALL_DIMENSIONS has 5 entries', () => {
|
|
expect(ALL_DIMENSIONS.length).toBe(5);
|
|
});
|
|
|
|
test('no extra SIGNAL_MAP keys without registry reference (informational)', () => {
|
|
// Extra keys are allowed (a signal might be reserved for upcoming registry
|
|
// entries). But list them so drift is visible.
|
|
const { extra } = validateRegistrySignalKeys();
|
|
// Allow up to 3 "reserved" extras before flagging. Tighten later.
|
|
expect(extra.length).toBeLessThanOrEqual(3);
|
|
});
|
|
});
|
|
|
|
// -----------------------------------------------------------------------
|
|
// Archetypes
|
|
// -----------------------------------------------------------------------
|
|
|
|
describe('archetypes', () => {
|
|
test('each archetype has name, description, center, tightness', () => {
|
|
for (const arch of ARCHETYPES) {
|
|
expect(arch.name).toBeDefined();
|
|
expect(arch.description).toBeDefined();
|
|
expect(arch.center).toBeDefined();
|
|
expect(arch.tightness).toBeGreaterThan(0);
|
|
for (const d of ALL_DIMENSIONS) {
|
|
expect(typeof arch.center[d]).toBe('number');
|
|
expect(arch.center[d]).toBeGreaterThanOrEqual(0);
|
|
expect(arch.center[d]).toBeLessThanOrEqual(1);
|
|
}
|
|
}
|
|
});
|
|
|
|
test('archetype names are unique', () => {
|
|
const names = ARCHETYPES.map((a) => a.name);
|
|
expect(new Set(names).size).toBe(names.length);
|
|
});
|
|
|
|
test('matchArchetype returns Cathedral Builder for boil-the-ocean profile', () => {
|
|
const dims = {
|
|
scope_appetite: 0.88,
|
|
risk_tolerance: 0.55,
|
|
detail_preference: 0.5,
|
|
autonomy: 0.5,
|
|
architecture_care: 0.85,
|
|
};
|
|
const match = matchArchetype(dims);
|
|
expect(match.name).toBe('Cathedral Builder');
|
|
});
|
|
|
|
test('matchArchetype returns Ship-It Pragmatist for small-scope/fast profile', () => {
|
|
const dims = {
|
|
scope_appetite: 0.22,
|
|
risk_tolerance: 0.78,
|
|
detail_preference: 0.25,
|
|
autonomy: 0.7,
|
|
architecture_care: 0.38,
|
|
};
|
|
const match = matchArchetype(dims);
|
|
expect(match.name).toBe('Ship-It Pragmatist');
|
|
});
|
|
|
|
test('matchArchetype returns Polymath for extreme-outlier profile', () => {
|
|
const dims = {
|
|
scope_appetite: 0.05,
|
|
risk_tolerance: 0.95,
|
|
detail_preference: 0.95,
|
|
autonomy: 0.05,
|
|
architecture_care: 0.05,
|
|
};
|
|
const match = matchArchetype(dims);
|
|
expect(match.name).toBe(FALLBACK_ARCHETYPE.name);
|
|
});
|
|
|
|
test('getAllArchetypeNames includes Polymath fallback', () => {
|
|
const names = getAllArchetypeNames();
|
|
expect(names).toContain('Polymath');
|
|
expect(names.length).toBe(ARCHETYPES.length + 1);
|
|
});
|
|
});
|
|
|
|
// -----------------------------------------------------------------------
|
|
// Registry completeness — warn about SKILL.md.tmpl AskUserQuestion calls
|
|
// that don't appear to map to any registry entry.
|
|
//
|
|
// This is NOT a strict CI failure. Many AskUserQuestion invocations are
|
|
// dynamic (agent generates question text at runtime), which is fine — the
|
|
// agent picks the best-fitting registry id or generates an ad-hoc id.
|
|
//
|
|
// The test reports a count for visibility. A future enhancement will scan
|
|
// for specific question_id references in template prose and require those
|
|
// referenced ids to exist in the registry.
|
|
// -----------------------------------------------------------------------
|
|
|
|
describe('AskUserQuestion template coverage (informational)', () => {
|
|
test('count of templates using AskUserQuestion is non-trivial', () => {
|
|
const templates = findAllTemplates();
|
|
const usingAsk = templates.filter((p) =>
|
|
fs.readFileSync(p, 'utf-8').includes('AskUserQuestion'),
|
|
);
|
|
// At the time of writing, ~35 templates reference AskUserQuestion.
|
|
// This sanity check catches an accidental global removal.
|
|
expect(usingAsk.length).toBeGreaterThan(20);
|
|
});
|
|
|
|
test('registry covers >= 10 skills from template files', () => {
|
|
const stats = getRegistryStats();
|
|
expect(Object.keys(stats.by_skill).length).toBeGreaterThanOrEqual(10);
|
|
});
|
|
});
|
|
|
|
// -----------------------------------------------------------------------
|
|
// One-way door classifier (belt-and-suspenders keyword fallback)
|
|
// -----------------------------------------------------------------------
|
|
|
|
describe('one-way-doors classifier', () => {
|
|
test('registry lookup wins when question_id is known', () => {
|
|
const result = classifyQuestion({ question_id: 'ship-test-failure-triage' });
|
|
expect(result.oneWay).toBe(true);
|
|
expect(result.reason).toBe('registry');
|
|
|
|
const safeResult = classifyQuestion({ question_id: 'ship-changelog-voice-polish' });
|
|
expect(safeResult.oneWay).toBe(false);
|
|
expect(safeResult.reason).toBe('registry');
|
|
});
|
|
|
|
test('unknown question_id falls through to other checks', () => {
|
|
const result = classifyQuestion({ question_id: 'some-ad-hoc-question-id' });
|
|
expect(result.reason).not.toBe('registry');
|
|
});
|
|
|
|
test('keyword fallback catches destructive summaries', () => {
|
|
const cases = [
|
|
'Delete this directory and all its contents?',
|
|
'Run rm -rf /tmp/scratch — proceed?',
|
|
'Force-push main?',
|
|
'git reset --hard origin/main — ok?',
|
|
'DROP TABLE users — confirm?',
|
|
'kubectl delete namespace prod',
|
|
'terraform destroy the staging cluster',
|
|
'rotate the API key',
|
|
'breaking change to the public API — ship anyway?',
|
|
];
|
|
for (const summary of cases) {
|
|
const result = classifyQuestion({ summary });
|
|
expect(result.oneWay).toBe(true);
|
|
expect(result.reason).toBe('keyword');
|
|
expect(result.matched).toBeDefined();
|
|
}
|
|
});
|
|
|
|
test('skill-category fallback fires for cso:approval and land-and-deploy:approval', () => {
|
|
expect(isOneWayDoor({ skill: 'cso', category: 'approval' })).toBe(true);
|
|
expect(isOneWayDoor({ skill: 'land-and-deploy', category: 'approval' })).toBe(true);
|
|
});
|
|
|
|
test('benign questions default to two-way', () => {
|
|
const benign = [
|
|
'Want to update the changelog voice?',
|
|
'Which mode should plan review use?',
|
|
'Open the essay in your browser?',
|
|
];
|
|
for (const summary of benign) {
|
|
const result = classifyQuestion({ summary });
|
|
expect(result.oneWay).toBe(false);
|
|
expect(result.reason).toBe('default-two-way');
|
|
}
|
|
});
|
|
|
|
test('keyword patterns are non-empty', () => {
|
|
expect(DESTRUCTIVE_PATTERN_LIST.length).toBeGreaterThan(15);
|
|
});
|
|
|
|
test('skill-category set covers security + deploy', () => {
|
|
expect(ONE_WAY_SKILL_CATEGORY_SET.has('cso:approval')).toBe(true);
|
|
expect(ONE_WAY_SKILL_CATEGORY_SET.has('land-and-deploy:approval')).toBe(true);
|
|
});
|
|
});
|
|
|
|
// -----------------------------------------------------------------------
|
|
// Preamble injection — the QUESTION_TUNING section must appear for tier >=2
|
|
// -----------------------------------------------------------------------
|
|
|
|
describe('preamble — QUESTION_TUNING injection', () => {
|
|
test('tier 2+ skills include the Question Tuning section', async () => {
|
|
const { generatePreamble } = await import('../scripts/resolvers/preamble');
|
|
const ctx = {
|
|
skillName: 'test-skill',
|
|
tmplPath: 'test.tmpl',
|
|
host: 'claude' as const,
|
|
paths: {
|
|
skillRoot: '~/.claude/skills/gstack',
|
|
localSkillRoot: '.claude/skills/gstack',
|
|
binDir: '~/.claude/skills/gstack/bin',
|
|
browseDir: '~/.claude/skills/gstack/browse/dist',
|
|
designDir: '~/.claude/skills/gstack/design/dist',
|
|
},
|
|
preambleTier: 2,
|
|
};
|
|
const out = generatePreamble(ctx);
|
|
// Phase 1: the config echo moved into bin/gstack-skill-start; the render's
|
|
// section gates itself on the echoed key.
|
|
const script = fs.readFileSync(
|
|
path.join(import.meta.dir, '..', 'bin', 'gstack-skill-start'),
|
|
'utf-8',
|
|
);
|
|
expect(script).toContain('echo "QUESTION_TUNING: $_QUESTION_TUNING"');
|
|
expect(out).toContain('QUESTION_TUNING: false');
|
|
expect(out).toContain('## Question Tuning');
|
|
expect(out).toContain('gstack-question-preference --check');
|
|
expect(out).toContain('gstack-question-log');
|
|
expect(out).toContain('profile-poisoning defense');
|
|
expect(out).toContain('inline-user');
|
|
});
|
|
|
|
test('tier 1 skills do NOT include Question Tuning section', async () => {
|
|
const { generatePreamble } = await import('../scripts/resolvers/preamble');
|
|
const ctx = {
|
|
skillName: 'test-skill',
|
|
tmplPath: 'test.tmpl',
|
|
host: 'claude' as const,
|
|
paths: {
|
|
skillRoot: '~/.claude/skills/gstack',
|
|
localSkillRoot: '.claude/skills/gstack',
|
|
binDir: '~/.claude/skills/gstack/bin',
|
|
browseDir: '~/.claude/skills/gstack/browse/dist',
|
|
designDir: '~/.claude/skills/gstack/design/dist',
|
|
},
|
|
preambleTier: 1,
|
|
};
|
|
const out = generatePreamble(ctx);
|
|
// QUESTION_TUNING config echo still fires (it's in the bash block which all tiers get),
|
|
// but the prose section should NOT be present for tier 1.
|
|
expect(out).not.toContain('## Question Tuning');
|
|
});
|
|
|
|
test('codex host produces different paths', async () => {
|
|
const { generateQuestionTuning } = await import('../scripts/resolvers/question-tuning');
|
|
const codexCtx = {
|
|
skillName: 'test',
|
|
tmplPath: 'x',
|
|
host: 'codex' as const,
|
|
paths: {
|
|
skillRoot: '$GSTACK_ROOT',
|
|
localSkillRoot: '.agents/skills/gstack',
|
|
binDir: '$GSTACK_BIN',
|
|
browseDir: '$GSTACK_BROWSE',
|
|
designDir: '$GSTACK_DESIGN',
|
|
},
|
|
};
|
|
const out = generateQuestionTuning(codexCtx);
|
|
expect(out).toContain('$GSTACK_BIN/gstack-question-preference');
|
|
expect(out).toContain('$GSTACK_BIN/gstack-question-log');
|
|
});
|
|
});
|
|
|
|
// -----------------------------------------------------------------------
|
|
// End-to-end: log → preference → derive pipeline
|
|
//
|
|
// Exercises the real binaries (not mocks) to make sure the schema contract
|
|
// between them actually holds.
|
|
// -----------------------------------------------------------------------
|
|
|
|
describe('end-to-end pipeline (binaries working together)', () => {
|
|
test('log many expand choices → derive pushes scope_appetite up', () => {
|
|
const tmpHome = fs.mkdtempSync(path.join(require('os').tmpdir(), 'gstack-e2e-'));
|
|
try {
|
|
// GSTACK_QUESTION_LOG_NO_DERIVE=1 suppresses gstack-question-log's
|
|
// fire-and-forget background `--derive` (it nohups one per write). Without
|
|
// it, the 5 rapid log writes spawn 5 racing background derives that collide
|
|
// with this test's explicit --derive below — a late background derive that
|
|
// only saw 3 entries can clobber developer-profile.json after the explicit
|
|
// one wrote sample_size=5, making the test flaky (~25-50% fail). The binary
|
|
// documents this flag for exactly this case. The explicit --derive still
|
|
// runs (it ignores the flag), so real derive behavior is still asserted.
|
|
const env = { ...process.env, GSTACK_HOME: tmpHome, GSTACK_QUESTION_LOG_NO_DERIVE: '1' };
|
|
const { spawnSync } = require('child_process');
|
|
const logBin = path.join(ROOT, 'bin', 'gstack-question-log');
|
|
const devBin = path.join(ROOT, 'bin', 'gstack-developer-profile');
|
|
|
|
for (let i = 0; i < 5; i++) {
|
|
const r = spawnSync(
|
|
logBin,
|
|
[
|
|
JSON.stringify({
|
|
skill: 'plan-ceo-review',
|
|
question_id: 'plan-ceo-review-mode',
|
|
question_summary: 'mode?',
|
|
user_choice: 'expand',
|
|
session_id: `s${i}`,
|
|
ts: `2026-04-0${i + 1}T10:00:00Z`,
|
|
}),
|
|
],
|
|
{ env, cwd: ROOT, encoding: 'utf-8', timeout: 30_000 },
|
|
);
|
|
expect(r.status).toBe(0);
|
|
}
|
|
|
|
const derive = spawnSync(devBin, ['--derive'], { env, cwd: ROOT, encoding: 'utf-8', timeout: 30_000 });
|
|
expect(derive.status).toBe(0);
|
|
|
|
const profileOut = spawnSync(devBin, ['--profile'], { env, cwd: ROOT, encoding: 'utf-8', timeout: 30_000 });
|
|
const p = JSON.parse(profileOut.stdout);
|
|
expect(p.inferred.sample_size).toBe(5);
|
|
expect(p.inferred.values.scope_appetite).toBeGreaterThan(0.5);
|
|
} finally {
|
|
fs.rmSync(tmpHome, { recursive: true, force: true });
|
|
}
|
|
});
|
|
|
|
test('preference blocks tune: write from inline-tool-output in full pipeline', () => {
|
|
const tmpHome = fs.mkdtempSync(path.join(require('os').tmpdir(), 'gstack-e2e-'));
|
|
try {
|
|
const env = { ...process.env, GSTACK_HOME: tmpHome };
|
|
const { spawnSync } = require('child_process');
|
|
const prefBin = path.join(ROOT, 'bin', 'gstack-question-preference');
|
|
|
|
const r = spawnSync(
|
|
prefBin,
|
|
[
|
|
'--write',
|
|
JSON.stringify({ question_id: 'fake-id', preference: 'never-ask', source: 'inline-tool-output' }),
|
|
],
|
|
{ env, cwd: ROOT, encoding: 'utf-8', timeout: 30_000 },
|
|
);
|
|
expect(r.status).toBe(2);
|
|
expect(r.stderr).toContain('poisoning');
|
|
|
|
// Verify no preference was written
|
|
const read = spawnSync(prefBin, ['--read'], { env, cwd: ROOT, encoding: 'utf-8', timeout: 30_000 });
|
|
const prefs = JSON.parse(read.stdout);
|
|
expect(prefs['fake-id']).toBeUndefined();
|
|
} finally {
|
|
fs.rmSync(tmpHome, { recursive: true, force: true });
|
|
}
|
|
});
|
|
|
|
test('migration preserves sessions, builder-profile shim still works', () => {
|
|
const tmpHome = fs.mkdtempSync(path.join(require('os').tmpdir(), 'gstack-e2e-'));
|
|
try {
|
|
const env = { ...process.env, GSTACK_HOME: tmpHome };
|
|
const { spawnSync } = require('child_process');
|
|
const devBin = path.join(ROOT, 'bin', 'gstack-developer-profile');
|
|
const shimBin = path.join(ROOT, 'bin', 'gstack-builder-profile');
|
|
|
|
// Seed a legacy file
|
|
fs.writeFileSync(
|
|
path.join(tmpHome, 'builder-profile.jsonl'),
|
|
[
|
|
{ date: '2026-01-01', mode: 'builder', project_slug: 'x', signals: ['taste'] },
|
|
{ date: '2026-02-01', mode: 'startup', project_slug: 'x', signals: ['named_users'] },
|
|
{ date: '2026-03-01', mode: 'builder', project_slug: 'y', signals: ['agency'] },
|
|
]
|
|
.map((e) => JSON.stringify(e))
|
|
.join('\n') + '\n',
|
|
);
|
|
|
|
// Migrate
|
|
const m = spawnSync(devBin, ['--migrate'], { env, cwd: ROOT, encoding: 'utf-8', timeout: 30_000 });
|
|
expect(m.status).toBe(0);
|
|
|
|
// Legacy shim should still return the same KEY: VALUE shape
|
|
const shimOut = spawnSync(shimBin, [], { env, cwd: ROOT, encoding: 'utf-8', timeout: 30_000 });
|
|
expect(shimOut.status).toBe(0);
|
|
expect(shimOut.stdout).toContain('SESSION_COUNT: 3');
|
|
expect(shimOut.stdout).toContain('TIER: welcome_back');
|
|
expect(shimOut.stdout).toContain('CROSS_PROJECT: true');
|
|
} finally {
|
|
fs.rmSync(tmpHome, { recursive: true, force: true });
|
|
}
|
|
});
|
|
});
|
|
|
|
function findAllTemplates(): string[] {
|
|
const results: string[] = [];
|
|
function walk(dir: string) {
|
|
let entries: fs.Dirent[];
|
|
try {
|
|
entries = fs.readdirSync(dir, { withFileTypes: true });
|
|
} catch {
|
|
return;
|
|
}
|
|
for (const entry of entries) {
|
|
const full = path.join(dir, entry.name);
|
|
if (entry.isDirectory()) {
|
|
// Skip node_modules and dotfiles
|
|
if (entry.name === 'node_modules' || entry.name.startsWith('.')) continue;
|
|
walk(full);
|
|
} else if (entry.isFile() && entry.name === 'SKILL.md.tmpl') {
|
|
results.push(full);
|
|
}
|
|
}
|
|
}
|
|
walk(ROOT);
|
|
return results;
|
|
}
|