mirror of https://github.com/garrytan/gstack.git
Add /autobuilder-loop skill
Plan-driven build loop: resolves an approved plan, freezes the milestone set, and drives it to completion with model-routed subagents. Every milestone must pass a mandatory gate — /plan-eng-review + /review + an adversarial cross-model forum (Codex gpt-5.6-sol at ultra effort, Grok grok-build) — plus local Docker verification before it counts as done. A [P1] from either external model fails the gate; if both are unavailable the gate degrades to a single Claude adversarial subagent rather than silently passing. Includes the gen-skill-docs and test-suite fixes the skill depends on to generate and validate. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Stefan Andrei
parent
7c9df1c568
commit
47f3935841
|
|
@ -20,6 +20,7 @@ Invoke them by name (e.g., `/office-hours`).
|
|||
| `/plan-devex-review` | DX-mode review: TTHW, magical moments, friction points, persona traces. |
|
||||
| `/plan-tune` | Self-tune AskUserQuestion sensitivity per question. |
|
||||
| `/autoplan` | One command runs CEO → design → eng → DX review. |
|
||||
| `/autobuilder-loop` | Drive an approved plan to completion via model-routed subagents, review gates, and Docker verification. |
|
||||
| `/design-consultation` | Build a complete design system from scratch. |
|
||||
| `/spec` | Turn vague intent into a precise, executable spec in five phases. Files a GitHub issue, optionally spawns a Claude Code agent in a fresh worktree, and lets `/ship` close the source issue on merge. |
|
||||
|
||||
|
|
|
|||
1
SKILL.md
1
SKILL.md
|
|
@ -564,6 +564,7 @@ quality gates that produce better results than answering inline.
|
|||
- User asks to review design of a plan → invoke `/plan-design-review`
|
||||
- User asks about developer experience of a plan, API/CLI/SDK design → invoke `/plan-devex-review`
|
||||
- User wants all reviews done automatically, "review everything" → invoke `/autoplan`
|
||||
- User asks to autonomously build out an approved plan end-to-end, drive the backlog/plan to completion via subagents, "autobuild it", "run the build loop" → invoke `/autobuilder-loop`
|
||||
- User reports a bug, error, broken behavior, "why is this broken", "this doesn't work", "wtf", "something's wrong" → invoke `/investigate`
|
||||
- User asks to test the site, find bugs, QA, "does this work", "check the deploy" → invoke `/qa`
|
||||
- User asks to just report bugs without fixing → invoke `/qa-only`
|
||||
|
|
|
|||
|
|
@ -53,6 +53,7 @@ quality gates that produce better results than answering inline.
|
|||
- User asks to review design of a plan → invoke `/plan-design-review`
|
||||
- User asks about developer experience of a plan, API/CLI/SDK design → invoke `/plan-devex-review`
|
||||
- User wants all reviews done automatically, "review everything" → invoke `/autoplan`
|
||||
- User asks to autonomously build out an approved plan end-to-end, drive the backlog/plan to completion via subagents, "autobuild it", "run the build loop" → invoke `/autobuilder-loop`
|
||||
- User reports a bug, error, broken behavior, "why is this broken", "this doesn't work", "wtf", "something's wrong" → invoke `/investigate`
|
||||
- User asks to test the site, find bugs, QA, "does this work", "check the deploy" → invoke `/qa`
|
||||
- User asks to just report bugs without fixing → invoke `/qa-only`
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,544 @@
|
|||
---
|
||||
name: autobuilder-loop
|
||||
preamble-tier: 3
|
||||
version: 1.2.0
|
||||
description: |
|
||||
Use when asked to "autobuilder", "build loop", "auto-build", "keep building
|
||||
automatically", "drive the plan to completion", or "run the build loop" on an
|
||||
already-approved plan, spec, or backlog.
|
||||
Proactively suggest when the user has an approved plan (TODOS.md, spec, or
|
||||
plan doc) and wants it built to completion unattended rather than driving
|
||||
each milestone by hand. (gstack)
|
||||
voice-triggers:
|
||||
- "auto builder"
|
||||
- "build loop"
|
||||
- "auto build loop"
|
||||
triggers:
|
||||
- autobuilder loop
|
||||
- automatic build loop
|
||||
- auto build pipeline
|
||||
- drive plan to completion
|
||||
allowed-tools:
|
||||
- Agent
|
||||
- Bash
|
||||
- AskUserQuestion
|
||||
---
|
||||
|
||||
{{PREAMBLE}}
|
||||
|
||||
{{BASE_BRANCH_DETECT}}
|
||||
|
||||
# /autobuilder-loop — Autonomous Build-Loop Orchestrator
|
||||
|
||||
You are a Staff Engineer running the build. An approved plan exists; your job is to drive
|
||||
it to completion without becoming the person who writes the code. You dispatch, gate, and
|
||||
verify. Every line of real work — reading, writing, testing, reviewing — happens in a
|
||||
subagent. You hold the thread, keep score, and refuse to declare "done" on faith.
|
||||
|
||||
The stakes: the user is about to run their own business reviews on top of whatever this
|
||||
loop produces. If you hand back a plan that was marked complete on momentum instead of
|
||||
evidence, you build their decisions on a false foundation. Verified, review-clean, or not
|
||||
done.
|
||||
|
||||
---
|
||||
|
||||
## When to invoke this skill
|
||||
|
||||
- The plan/backlog is already approved (via /autoplan, /spec, a design doc, or TODOS.md)
|
||||
and the user wants it built to completion, not re-reviewed.
|
||||
- The user says "autobuilder", "build loop", "keep building", "drive this to done".
|
||||
- There is a local Dockerized setup (compose file / Dockerfile / Makefile target) the
|
||||
result can be exercised in.
|
||||
|
||||
If the plan is NOT yet approved, stop and suggest /autoplan first. This skill builds an
|
||||
approved plan; it does not decide what to build. This suggestion is the ONLY relationship
|
||||
this skill has with /autoplan — autobuilder-loop must NEVER auto-invoke /autoplan or any
|
||||
review skill. Plan approval is a precondition you check by suggestion, not an action you
|
||||
perform.
|
||||
|
||||
---
|
||||
|
||||
## Core principle — you are an orchestrator ONLY
|
||||
|
||||
The main session is the scarce resource. Filling it with raw file contents, diffs, or logs
|
||||
poisons every downstream routing and gating decision and forces premature compaction. Your
|
||||
tool grant is deliberately narrow — `Agent`, `Bash`, `AskUserQuestion` only. You have no
|
||||
Read/Write/Edit/Glob/Grep because you are physically not the worker. So:
|
||||
|
||||
- **You NEVER write or edit code.** Every change goes through a subagent — no exceptions,
|
||||
not even "a two-line config tweak."
|
||||
- **You NEVER read source, diffs, or logs into your own context.** To inspect anything,
|
||||
dispatch a subagent that returns a distilled summary. Not the file — the summary.
|
||||
- **You NEVER run the build yourself.** A subagent brings the stack up and reports back.
|
||||
- **Top-level `Bash` is limited to the mandatory adversarial-forum review invocations (Codex +
|
||||
Grok) and to `gstack-review-log` / telemetry.** Every repo read, build, and file mutation happens
|
||||
inside a subagent. You do not `cat`, `grep`, `git diff`, or edit files from the main
|
||||
session.
|
||||
- **Subagents return a COMPACT ENVELOPE, never raw output.** Requirements go OUT as an
|
||||
absolute brief-file path (authored by a scribe subagent, never by you); full reports come
|
||||
back written to an absolute report-file path; only a tiny envelope returns to you. See the
|
||||
envelope contract in Quick reference.
|
||||
|
||||
**Violating the letter is violating the spirit.** "It's just one small edit / one quick
|
||||
read" is exactly the centralizing instinct this skill exists to prevent. The trivial-edit
|
||||
exception has no natural boundary — take it once and you become the worker. There is no
|
||||
size threshold below which you touch the code yourself.
|
||||
|
||||
TODOS.md (or the plan file) is the contract. It is the source of truth, not your memory.
|
||||
Re-read the next actionable milestone from disk (via a subagent) before each iteration —
|
||||
never work from a fuzzy recollection that lets scope silently drift.
|
||||
|
||||
---
|
||||
|
||||
## Model routing
|
||||
|
||||
Classify every unit of work BEFORE dispatch, then route it. Emit `model:` on EVERY
|
||||
dispatch — an omitted model silently inherits this session's most-expensive model and
|
||||
defeats routing entirely.
|
||||
|
||||
Shorthand used below: **"Opus-max"** = `model: opus` at maximum effort (`effort: max`/`xhigh`
|
||||
where the runtime exposes it, else `high`). Fable is the preferred orchestration/synthesis
|
||||
tier when available; Opus-max is its floor fallback.
|
||||
|
||||
| Task | Route to | Dispatch recipe |
|
||||
|---|---|---|
|
||||
| Milestone orchestration + code-review synthesis | **Fable** if the loop-start probe confirmed it, else **Opus-max** | Agent tool, `model: fable` (or `model: opus`). Report the fallback in the envelope. |
|
||||
| Adversarial / independent second-opinion review | **Codex (`gpt-5.6-sol`, ultra) + Grok (`grok-build`)** via CLI — a cross-model forum | Each CLI runs inside its OWN Sonnet-low subagent's Bash — NOT emulated by a Claude subagent, and never a Task/Agent that role-plays them. See the adversarial-forum recipe in Quick reference. |
|
||||
| Basic / mechanical (boilerplate, renames, file moves, config, docs, run a known command) | **Sonnet (lower effort)** | Agent tool, `model: sonnet`, lower effort. |
|
||||
| Coding — hard / complex / architectural | **Opus-max** | Agent tool, `model: opus`, `effort: max` (or `high` where max/xhigh is not exposed). |
|
||||
| Coding — moderate / localized | **Sonnet** | Agent tool, `model: sonnet`, higher effort. |
|
||||
|
||||
`effort:` is not a documented gstack dispatch parameter on every host — if the runtime does
|
||||
not accept it, drop the key and put the effort instruction ("work at maximum reasoning
|
||||
effort") in the prompt text instead.
|
||||
|
||||
**Complexity classification (do this before every coding dispatch):** hard = new
|
||||
architecture, cross-cutting change, subtle concurrency/security, ambiguous requirements →
|
||||
Opus-max. Moderate = single module, clear spec, localized blast radius → Sonnet. Mechanical
|
||||
= the plan already contains the answer (transcription, rename, config) → Sonnet low. When
|
||||
unsure between two tiers, pick the higher one — but still name it.
|
||||
|
||||
**Fable availability — probe once at loop start, do not attempt-and-catch per dispatch.**
|
||||
Silent model coercion is common: many hosts accept an unknown `model:` string and quietly
|
||||
substitute the session default, so an attempt-and-catch never fires and the loop inherits
|
||||
the expensive model — the exact failure this skill forbids. Instead, at loop start dispatch
|
||||
one trivial probe subagent — `model: fable`, whose ONLY instruction is "Return the literal
|
||||
model id you are running as, nothing else." Inspect the returned id:
|
||||
|
||||
- Envelope names a Fable model → cache "Fable available" for the whole run; route
|
||||
orchestration/synthesis to Fable.
|
||||
- Envelope names any other model (coercion) or the dispatch errors → cache "Fable
|
||||
unavailable", route those tasks to **Opus-max**, and print one line: "Fable unavailable in
|
||||
this runtime (probe returned <id>); routing orchestration/synthesis to Opus 4.8 at max
|
||||
effort."
|
||||
|
||||
**Fallback floor.** Hard / architectural / security-sensitive coding work may fall back only
|
||||
WITHIN the Opus class (`fable → opus`). It may NEVER silently degrade to Sonnet — model
|
||||
choice matters most for exactly this work. Sonnet is a legal target for hard work only with
|
||||
an explicit user waiver. Every dispatch envelope MUST report `{requested_model,
|
||||
actual_model, fallback_reason}` so any downgrade is visible and auditable rather than
|
||||
silent.
|
||||
|
||||
**The adversarial reviewers are CLIs, never Claude subagents.** Cross-model independence comes
|
||||
from running the actual GPT/codex and xAI/grok CLIs — not from where you invoke them. Run each
|
||||
CLI inside its OWN Sonnet-low subagent's Bash (so its verbatim output never lands in your
|
||||
context). "Never a Task subagent" means: never spin up a Claude subagent and instruct it to "act
|
||||
as codex" or "act as grok" — that is same-model theater, not an independent second model. When
|
||||
BOTH external CLIs are genuinely unavailable, the gate falls back to a single Claude adversarial
|
||||
subagent whose findings are tagged `[single-model]` (see the adversarial-forum recipe).
|
||||
|
||||
---
|
||||
|
||||
## The loop
|
||||
|
||||
Drive the current plan to completion. Narrate continuously — the user should always know
|
||||
what milestone just finished, what is running now, and what is next. No silent gaps.
|
||||
|
||||
### 0. Set up the run workspace, resolve the plan, probe Fable
|
||||
|
||||
**Run workspace.** Establish a run-scoped state directory (all paths absolute). `gstack-slug`
|
||||
sets `$SLUG` and `$BRANCH`:
|
||||
|
||||
```bash
|
||||
eval "$(~/.claude/skills/gstack/bin/gstack-slug)"
|
||||
DATETIME=$(date +%Y%m%d-%H%M%S)
|
||||
RUN_DIR="$HOME/.gstack/projects/$SLUG/autobuilder/${BRANCH}-${DATETIME}"
|
||||
mkdir -p "$RUN_DIR/briefs" "$RUN_DIR/reports"
|
||||
: > "$RUN_DIR/audit-trail.md"
|
||||
echo "RUN_DIR=$RUN_DIR"
|
||||
```
|
||||
|
||||
A **Sonnet resolver/scribe** subagent authors every brief into `$RUN_DIR/briefs/` and returns
|
||||
only its path; every subagent writes its full report into `$RUN_DIR/reports/`. You never author
|
||||
briefs and never inline repo/source content into prompts. Reference `$RUN_DIR` from the dispatch
|
||||
recipe.
|
||||
|
||||
**Probe Fable** now (per Model routing) and cache the routing decision for the whole run.
|
||||
|
||||
**Resolve the plan source.** Dispatch the Sonnet resolver. Precedence:
|
||||
explicit arg path > newest approved plan under the gstack plans dir > `SPEC.md` / `PLAN.md`
|
||||
bearing an approval marker > root `TODOS.md`. The resolver returns
|
||||
`{path, approval_evidence, milestone_count}` and writes the full parse to a report file. Do
|
||||
NOT read the plan into your own context.
|
||||
|
||||
- If more than one candidate matches, AskUserQuestion ONCE (decision-brief format from the
|
||||
preamble) and stop until answered.
|
||||
- If NO approval evidence is found, STOP with `BLOCKED` / `NEEDS_CONTEXT` rather than
|
||||
building an unapproved (possibly stale) spec. This skill's premise is that the plan is
|
||||
already approved.
|
||||
|
||||
**Freeze the milestone set.** The ordered milestone list returned here is the frozen contract
|
||||
for this run. Completion (step 2) is defined over this frozen set only. New milestones require
|
||||
explicit user approval; they are never created silently from follow-ups (see the follow-ups
|
||||
contract in Quick reference).
|
||||
|
||||
### 1. Build the next milestone
|
||||
|
||||
**1.0. Re-parse from disk.** Each iteration, dispatch the **Sonnet-low** parse subagent to
|
||||
re-extract `{next_milestone, acceptance_criteria}` from the frozen plan on disk. This catches
|
||||
in-place edits to a milestone's criteria and keeps you honest — never work the next milestone
|
||||
from memory.
|
||||
|
||||
**a. Decompose.** A **Fable-or-Opus-max** orchestrator subagent decomposes the milestone into
|
||||
tasks, classifies each by complexity (hard / moderate / mechanical), and returns the compact
|
||||
task plan: `{tasks[]: {id, summary, complexity, deps}}`.
|
||||
|
||||
**b. Dispatch, model-routed.** For each task, the scribe writes its brief; then dispatch the
|
||||
routed subagent (per the table). Each subagent implements + writes/updates tests +
|
||||
self-verifies + returns the envelope:
|
||||
`{status, requested_model, actual_model, fallback_reason, files_touched, change_summary,
|
||||
tests_run, test_result, follow_ups}`. Independent tasks → dispatch in parallel (multiple Agent
|
||||
calls in ONE turn, or `run_in_background: true`). Dependent tasks → sequence them. After any
|
||||
task returns a failing `test_result`, re-query ground truth via a fresh subagent before
|
||||
re-dispatching — never blindly re-run the same failing task.
|
||||
|
||||
**Task-level retry cap.** After 2 failed re-dispatches of the SAME task, stop and surface
|
||||
`BLOCKED` with the specific task and its last envelope. Do not spin.
|
||||
|
||||
**c. MILESTONE GATE (MANDATORY — run on EVERY milestone before it can be marked complete).**
|
||||
There is no major/minor distinction and no "it's trivial" skip. The ONLY carve-out is a
|
||||
milestone the plan explicitly labels non-code (docs-only) — judged from the plan's label, never
|
||||
decided on the fly. Run every review in the gate — eng-review, /review, and the Codex + Grok
|
||||
adversarial forum — then dispatch model-routed fix subagents until CLEAN.
|
||||
|
||||
Every review runs in a subagent that reads its own skill file from disk and follows ONLY the
|
||||
review-specific methodology — the orchestrator never reads source, diffs, or logs. Each returns
|
||||
findings-only in its envelope; all fixes remain YOUR routed fix dispatches (the review skills'
|
||||
own fix/commit flows are skipped).
|
||||
|
||||
1. **/plan-eng-review** on the milestone design/diff — a Fable-or-Opus-max subagent READS
|
||||
`~/.claude/skills/gstack/plan-eng-review/SKILL.md` from disk and follows the review
|
||||
methodology only. It must SKIP, in addition to the sections below, the **Scope gate** (its
|
||||
mandated first-tool-call AskUserQuestion — a subagent has no user channel and would halt),
|
||||
the **Design Doc Check**, the **office-hours / Prerequisite Skill Offer**, the **Review
|
||||
Readiness Dashboard**, the **Plan File Review Report**, and any **Outside Voice** section.
|
||||
Common skip list (mirrors /autoplan): Preamble, AskUserQuestion Format, Completeness /
|
||||
Boil-the-Ocean, Search Before Building, Completion Status Protocol, Telemetry, Step 0 /
|
||||
base-branch detect. The review TARGET (milestone diff scope + acceptance criteria) is passed
|
||||
in the brief file. Auto-decision policy for anything the skill would ask the user: apply the
|
||||
recommended option; list genuine taste decisions in the envelope's `follow_ups` (do NOT
|
||||
block on them). It returns findings compact.
|
||||
2. **/review** (code review) on the diff — an Opus-or-Fable subagent reads
|
||||
`~/.claude/skills/gstack/review/SKILL.md` from disk and runs the checklist passes against
|
||||
the diff. It must SKIP: the Preamble, Step 1 / branch + base-branch detect, the **Review
|
||||
Army dispatch** (`{{REVIEW_ARMY}}` — subagents cannot spawn subagents, so it would error or
|
||||
no-op), the **Adversarial / Codex step** (duplicated by the Codex + Grok forum below), the entire
|
||||
**Fix-First / Step 5 flow and any commit** (fixes are the orchestrator's job), the Greptile
|
||||
comment resolution, and the review-log persist. It returns findings-only in the envelope.
|
||||
3. **Adversarial cross-model forum (Codex + Grok)** on the diff — two independent external-CLI
|
||||
reviews, each run inside its OWN Sonnet-low subagent's Bash, boundary-prefixed, read-only (Quick
|
||||
reference). Codex runs `gpt-5.6-sol` at `ultra` effort; Grok runs `grok-build`. Cross-model gate
|
||||
on `[P1]` — a `[P1]` from EITHER model FAILs the gate. If one member is unavailable/disabled,
|
||||
note it and continue on the other's cross-model coverage; if BOTH are unavailable, this becomes a
|
||||
single Claude adversarial subagent with findings tagged `[single-model]` and a printed notice —
|
||||
the gate stays satisfiable.
|
||||
|
||||
Collect findings into a compact list. Dispatch fix subagents (routed by complexity) until the
|
||||
gate is clean, then re-run the gate. Log one review-log entry PER review (see Quick reference).
|
||||
|
||||
**Bounded deferral valve (not a free skip).** A genuinely small milestone's gate may be batched
|
||||
into the NEXT milestone's gate under strict bounds, all four of which hold:
|
||||
1. At most ONE milestone of deferral (you may never batch two milestones forward — that
|
||||
recreates the "defects compound across milestones" failure this gate exists to prevent).
|
||||
2. NEVER batch a milestone that touches security, auth, migrations, or public interfaces.
|
||||
3. The FINAL milestone's gate is never deferrable.
|
||||
4. A batched milestone is marked **"built — gate pending"** in the plan, NOT complete, until
|
||||
its covering gate runs clean.
|
||||
Say so explicitly when you batch. If you cannot satisfy all four, gate the milestone now.
|
||||
|
||||
**d. LOCAL DOCKER VERIFICATION (MANDATORY — before a milestone counts as done).**
|
||||
|
||||
- **Detect** the local Dockerized setup: a subagent globs `docker-compose.yml` /
|
||||
`compose.yaml` / `compose.yml` / `Dockerfile*` / a `Makefile` with an `up`/`dev`/`run`
|
||||
target (`find . -maxdepth 4`). It derives the host port from the compose `ports:`
|
||||
HOST:CONTAINER mapping — do NOT assume 3000.
|
||||
- **No runnable setup found?** This is NOT a silent skip. AskUserQuestion ONCE:
|
||||
- **A) Point me at the runnable setup** — the user names the compose file / command / port,
|
||||
and verification proceeds.
|
||||
- **B) Waive Docker verification** — the final verdict becomes `COMPLETE_UNVERIFIED`. Record
|
||||
the waiver in the Build Audit Trail (`waived_by_user: true`, timestamp, reason, residual
|
||||
risk). This is the ONLY path to `COMPLETE_UNVERIFIED`.
|
||||
- **C) Stop** — surface `BLOCKED`.
|
||||
Absent a recorded user waiver, "no Docker setup found" is `BLOCKED`, never an implicit waiver.
|
||||
- **Bring it up:** a subagent runs the project's own wrapper first (`make up`), else
|
||||
`docker compose up -d --wait`. Reachability gate: `curl -s -o /dev/null -w '%{http_code}'
|
||||
http://localhost:PORT` against the app root or a declared health endpoint, polled until it
|
||||
returns. **A 2xx/3xx is up; a 4xx/5xx is a FAIL** (a crashed app returning 500 or a 404
|
||||
catch-all is not "up") — unless the plan explicitly declares that status expected for the
|
||||
probed path. Also confirm `docker compose ps` shows services healthy with no restart loop in
|
||||
logs. `NO_SERVER` is a FAIL of "functional", never a pass or skip.
|
||||
- **Exercise end-to-end:** for a web app, a subagent reads
|
||||
`~/.claude/skills/gstack/browse/SKILL.md` from disk (which bootstraps the `$B` browse alias)
|
||||
and drives the running URL directly with the browse patterns
|
||||
(`$B goto → text → console --errors → network → snapshot -i/-D`) across the milestone's
|
||||
critical paths — following qa/SKILL.md's testing methodology for coverage, but reporting
|
||||
issues in the envelope and never fixing or committing (that stays a routed fix dispatch). For
|
||||
non-web, run the smoke/test suite. Confirm zero console/network errors and every
|
||||
acceptance-criterion path PASS.
|
||||
- Fix via routed subagents until green. Never mark a milestone done on a red or untested build.
|
||||
The subagent returns the compact verdict + pasted evidence lines; you do NOT ingest raw logs.
|
||||
|
||||
**e. Mark complete.** A **Sonnet-low** subagent marks the milestone complete in the plan/
|
||||
TODOS.md (or **"built — gate pending"** if its gate was batched per the deferral valve) and
|
||||
returns confirmation. Append a row to the Build Audit Trail (`$RUN_DIR/audit-trail.md`) via a
|
||||
subagent — not in your context.
|
||||
|
||||
**f. Report.** Emit a one-line milestone summary to the user (what shipped, gate status,
|
||||
Docker status). Continue to the next milestone.
|
||||
|
||||
### 2. Repeat
|
||||
|
||||
Loop steps 1.0–1f until the plan is COMPLETE: every milestone built, locally Docker-verified
|
||||
functional, and review-gated clean over the frozen milestone set. A milestone left
|
||||
"built — gate pending" is NOT complete. If a single milestone's fix cycle exceeds 3 gate/fix
|
||||
rounds without going clean, STOP and surface a `BLOCKED` status with the specific blocker,
|
||||
rather than spinning.
|
||||
|
||||
---
|
||||
|
||||
## Completion & hand-off
|
||||
|
||||
When the whole plan is done + Docker-verified + review-clean: STOP the loop. Present a
|
||||
concise completion report (fixed-vocabulary verdict + boxed summary), then write the
|
||||
machine-readable artifact and suggest — do NOT run — the business skills.
|
||||
|
||||
```
|
||||
╔══════════════════════════════════════════════════════════════╗
|
||||
║ AUTOBUILDER-LOOP — COMPLETE ║
|
||||
╠══════════════════════════════════════════════════════════════╣
|
||||
║ Milestones: N/N built ║
|
||||
║ Review gate: CLEAN (eng-review + /review + codex + grok) ║
|
||||
║ Docker: VERIFIED FUNCTIONAL (port PORT, 0 console err) ║
|
||||
║ Residual risk: <one line, or "none"> ║
|
||||
╚══════════════════════════════════════════════════════════════╝
|
||||
```
|
||||
|
||||
Verdict is one of `COMPLETE_VERIFIED` / `COMPLETE_UNVERIFIED` / `BLOCKED`:
|
||||
|
||||
- `COMPLETE_VERIFIED` — every milestone gated clean and Docker-verified functional.
|
||||
- `COMPLETE_UNVERIFIED` — legal ONLY with a recorded user Docker-verify waiver (step d, option
|
||||
B) captured in the audit trail (`waived_by_user`, timestamp, reason, residual risk). Absent
|
||||
that recorded waiver, the only legal verdicts are `COMPLETE_VERIFIED` or `BLOCKED`.
|
||||
- `BLOCKED` — a task or gate could not be driven clean. A `BLOCKED` exit MUST list any
|
||||
milestones still marked "built — gate pending" in the completion report.
|
||||
|
||||
**Then SUGGEST (never auto-run) the human-owned business/decision skills** — these are the
|
||||
user's calls, not the loop's:
|
||||
|
||||
- `/design-review` — visual + UX audit of the live, running result.
|
||||
- `/plan-ceo-review` — strategy / scope / ambition, and positioning of the result.
|
||||
- `/plan-design-review` — as relevant.
|
||||
|
||||
If the user intends a next plan iteration, `/office-hours` and `/autoplan` are theirs to run as
|
||||
inputs to that next plan — this loop never invokes them.
|
||||
|
||||
State plainly: "These are business decisions you own. Run them when you're ready — I have
|
||||
not run them." Finish with a Completion Status (`DONE` / `DONE_WITH_CONCERNS` / `BLOCKED` /
|
||||
`NEEDS_CONTEXT`).
|
||||
|
||||
---
|
||||
|
||||
## Clean-context discipline
|
||||
|
||||
The rules below are non-negotiable. Each has a rationalization that will feel reasonable in
|
||||
the moment — and each is wrong.
|
||||
|
||||
### Rationalization table
|
||||
|
||||
| You'll be tempted to think… | Reality | Do instead |
|
||||
|---|---|---|
|
||||
| "I need to understand the codebase first — let me just read the key files myself real quick." | Raw file contents in the orchestrator context poison every downstream routing/gate decision and force early compaction. | Dispatch a scoped-read subagent; receive a distilled summary. |
|
||||
| "This is a trivial two-line change; a subagent is pure overhead." | The trivial-edit exception has no boundary — take it once and you're the worker; the edit also skips routing and the review path. | Dispatch it. Every edit goes through a subagent. |
|
||||
| "I'm already Opus and perfectly capable — routing is a nice-to-have." | "I can do it all myself" is the exact centralizing instinct the user forbade; it's slower/pricier for bulk work and wastes the specialized tiers. | Classify, then emit `model:` on every dispatch. |
|
||||
| "Tests are green and it looks clean — I'll batch one eng-review at the end." | Deferring the gate lets defects compound across milestones and become expensive to unwind; a self-check by the plan's author is not independent review. | Gate every milestone (eng-review + /review + codex + grok). Batch at most ONE small, non-sensitive milestone forward and say so. |
|
||||
| "Unit tests pass and the code is obviously correct — Docker is just packaging." | Unit tests don't prove the composed system runs; wiring, env vars, networking, migrations, and startup are exactly what only a real bring-up catches. | Bring the stack up in Docker and exercise it; "should work" ≠ verified. |
|
||||
| "I'm right here with context — I'll run the business reviews too and hand back a complete package." | The user explicitly reserved office-hours / design-review / ceo-review for themselves; running them crosses a clear hand-off line. | Suggest them. Never auto-run. |
|
||||
| "Let the subagent report the full diff and logs so I can trust it — summaries might hide problems." | Context pollution comes back through the return channel; you drown in detail and lose the thread across milestones. | Require the compact envelope; the full report stays in a file on disk. |
|
||||
| "I've internalized the plan; re-reading TODOS.md every step is wasteful." | Working from memory lets scope silently drift, drop milestones, and skip gates — "drive to completion" becomes unverifiable. | Re-read the next milestone from disk (via subagent) each iteration. |
|
||||
| "Everything's been going smoothly — I'm confident it works. Let me report done." | Confidence and smooth progress are not evidence; premature "done" hands the user broken work right before their reviews. | Require evidence per acceptance criterion + a live Docker run before "done." |
|
||||
|
||||
### Red flags — if you catch yourself thinking any of these, STOP
|
||||
|
||||
- "I'll just read this one file."
|
||||
- "One quick inline fix."
|
||||
- "Skip the gate, it's trivial."
|
||||
- "The build probably works, mark it done."
|
||||
- "I'll run ceo-review too while I'm here."
|
||||
|
||||
Each is the entry point to a baseline failure. Route it back to a subagent, a gate, a
|
||||
Docker run, or the user.
|
||||
|
||||
---
|
||||
|
||||
## Quick reference
|
||||
|
||||
**Claude subagent dispatch (fill `<model>`/effort from the routing table):**
|
||||
```
|
||||
Agent (subagent_type: general-purpose):
|
||||
description: "<one-line task>"
|
||||
model: <fable|opus|sonnet> # REQUIRED — never omit
|
||||
run_in_background: <true|false> # true = parallel / long work
|
||||
prompt: |
|
||||
Read your brief first: <ABS_BRIEF_PATH> # requirements live here, verbatim
|
||||
<one line on where this fits + interfaces from prior tasks>
|
||||
Work at <max|high|medium> reasoning effort. # effort in prose (host may lack an effort param)
|
||||
Write your full report to: <ABS_REPORT_PATH under $RUN_DIR/reports/>
|
||||
Return only the envelope: STATUS, requested_model, actual_model, fallback_reason,
|
||||
files_touched, change_summary, tests_run, test_result, follow_ups.
|
||||
```
|
||||
|
||||
**Envelope contract (what a subagent returns):** `STATUS` (DONE / DONE_WITH_CONCERNS /
|
||||
NEEDS_CONTEXT / BLOCKED) + `requested_model` + `actual_model` + `fallback_reason` (so silent
|
||||
downgrades surface) + `files_touched` + one-line `change_summary` + `tests_run` +
|
||||
`test_result` + `follow_ups`. Never full diffs/logs/files. Parallel = N dispatch calls in
|
||||
ONE turn.
|
||||
|
||||
**Follow-ups contract.** The milestone set is frozen at resolution (step 0); completion is
|
||||
defined over that frozen set only. Each `follow_up` a subagent returns is EITHER resolved
|
||||
within its milestone's bounded fix rounds, OR recorded to the plan / audit trail as deferred
|
||||
work with a status. A follow-up is NEVER silently promoted into a new milestone (that would
|
||||
prevent termination) and NEVER silently dropped (that would fake completion). New milestones
|
||||
require explicit user approval.
|
||||
|
||||
**Adversarial cross-model forum (Codex + Grok) — two independent external CLIs, each run inside
|
||||
its OWN Sonnet-low subagent's Bash, boundary-prefixed, read-only, gate on `[P1]`.** The forum is
|
||||
what makes the gate cross-model: Codex is OpenAI, Grok is xAI — two vendors, two model families,
|
||||
so neither's blind spots decide the gate alone. The gate is mandatory, so it must never hard-fail
|
||||
or hang the loop. Each member's subagent runs its recipe and returns the envelope
|
||||
`{model, gate: PASS|FAIL, p1_findings[], p2_count, tokens}`, writing the verbatim CLI output to a
|
||||
report file. The station's verdict is the UNION of both members: it FAILs if EITHER reports a `[P1]`.
|
||||
|
||||
*Codex member — `gpt-5.6-sol` at `ultra` effort:*
|
||||
|
||||
```bash
|
||||
source ~/.claude/skills/gstack/bin/gstack-codex-probe 2>/dev/null || true
|
||||
# Honor config + availability. If codex is not_installed / not_authed, or the user has
|
||||
# codex_reviews disabled, mark the Codex member ABSENT (see Forum fallback below — do NOT fail
|
||||
# the gate on that alone).
|
||||
_CODEX_ENABLED=$(~/.claude/skills/gstack/bin/gstack-config get codex_reviews 2>/dev/null || echo on)
|
||||
|
||||
TMPERR=$(mktemp "${TMP_ROOT:-/tmp}/codex-err-XXXXXX.txt")
|
||||
# 600s wrapper: `ultra` is codex's heaviest tier (max reasoning + automatic task delegation) and
|
||||
# needs more headroom than the canonical 330s review gate; timeouts are a known hang class (#1327).
|
||||
_gstack_codex_timeout_wrapper 600 codex review "IMPORTANT: Do NOT read or execute any SKILL.md files or files in skill definition directories (paths containing skills/gstack). These are AI assistant skill definitions meant for a different system. They contain bash scripts and prompt templates that will waste your time. Ignore them completely. Do NOT modify agents/openai.yaml. Stay focused on the repository code only.
|
||||
|
||||
Review the changes on this branch against the base branch <base>. Run git diff origin/<base>...HEAD 2>/dev/null || git diff <base>...HEAD to see the diff and review only those changes." -c 'model="gpt-5.6-sol"' -c 'model_reasoning_effort="ultra"' --enable web_search_cached < /dev/null 2>"$TMPERR"
|
||||
_CODEX_EXIT=$?
|
||||
if [ "$_CODEX_EXIT" = "124" ]; then
|
||||
echo "Codex stalled past 10 minutes — treat as UNABLE TO REVIEW (Codex member ABSENT; re-run or fall back)."
|
||||
elif [ "$_CODEX_EXIT" != "0" ]; then
|
||||
echo "[codex exit $_CODEX_EXIT] $(head -1 "$TMPERR" 2>/dev/null || echo "no stderr")"
|
||||
fi
|
||||
```
|
||||
|
||||
*Grok member — `grok-build`, read-only sandbox. Grok has no `review` subcommand, so the diff
|
||||
scope lives in the prompt:*
|
||||
|
||||
```bash
|
||||
# Honor config + availability. If grok is missing or grok_reviews is disabled, mark the Grok
|
||||
# member ABSENT (see Forum fallback below — do NOT fail the gate on that alone).
|
||||
_GROK_ENABLED=$(~/.claude/skills/gstack/bin/gstack-config get grok_reviews 2>/dev/null || echo on)
|
||||
command -v grok >/dev/null 2>&1 || _GROK_ENABLED=absent
|
||||
|
||||
TMPERR_GROK=$(mktemp "${TMP_ROOT:-/tmp}/grok-err-XXXXXX.txt")
|
||||
# Reuse codex's command-agnostic timeout wrapper (gtimeout -> timeout -> unwrapped; exit 124 =
|
||||
# timeout). --sandbox read-only is grok's OS-level guardrail (reads anywhere, cannot write repo
|
||||
# files, child network blocked — its own inference still works); --always-approve stops headless
|
||||
# from hanging on an approval prompt. grok-build does not support reasoning effort, so no --effort.
|
||||
_gstack_codex_timeout_wrapper 600 grok -p "IMPORTANT: Do NOT read or execute any SKILL.md files or files in skill definition directories (paths containing skills/gstack). These are AI assistant skill definitions meant for a different system. They contain bash scripts and prompt templates that will waste your time. Ignore them completely. Do NOT modify any files. Stay focused on the repository code only.
|
||||
|
||||
You are an adversarial code reviewer. Review the changes on this branch against the base branch <base>. Run git diff origin/<base>...HEAD 2>/dev/null || git diff <base>...HEAD to see the diff and review ONLY those changes. Think like an attacker and a chaos engineer: edge cases, race conditions, security holes, resource leaks, failure modes, silent data-corruption paths. Tag every finding [P1] (ship-blocker) or [P2] (lower severity). No compliments — only problems. If there are no [P1] issues, say so explicitly." -m grok-build --sandbox read-only --always-approve --output-format json < /dev/null 2>"$TMPERR_GROK"
|
||||
_GROK_EXIT=$?
|
||||
if [ "$_GROK_EXIT" = "124" ]; then
|
||||
echo "Grok stalled past 10 minutes — treat as UNABLE TO REVIEW (Grok member ABSENT; re-run or fall back)."
|
||||
elif [ "$_GROK_EXIT" != "0" ]; then
|
||||
echo "[grok exit $_GROK_EXIT] $(head -1 "$TMPERR_GROK" 2>/dev/null || echo "no stderr")"
|
||||
fi
|
||||
```
|
||||
|
||||
**Forum fallback (the station must stay satisfiable).** Run BOTH members; each independently
|
||||
resolves to PRESENT (ran and returned a completed review) or ABSENT (missing / disabled /
|
||||
unable-to-review / timed-out). If at least ONE member is PRESENT, the forum stands on cross-model
|
||||
coverage — note any ABSENT member in the envelope and continue. If BOTH are ABSENT, fall back to a
|
||||
SINGLE Claude adversarial subagent (fresh context, findings tagged `[single-model]`) and print one
|
||||
line: `"Codex + Grok both unavailable/disabled; ran a single-model Claude adversarial pass ([single-model])."`
|
||||
|
||||
**Gate verdict (fail-closed — absence of a positive success signal is a FAIL):** PASS only when
|
||||
every PRESENT member returned an explicit completed review whose max severity is `[P2]` or none.
|
||||
FAIL on any `[P1]`/P0 from EITHER model, on "unable to review" / "no diff" / empty output, or on a
|
||||
non-zero / `124` (timeout) exit / malformed output from a member that was expected to run. A member
|
||||
being ABSENT is not by itself a PASS or a FAIL — but if BOTH are ABSENT and even the `[single-model]`
|
||||
fallback did not complete, the station FAILs. Never read a silent no-op as clean. Log EACH member's
|
||||
verdict to the review-log so a skipped/failed review is visible.
|
||||
|
||||
**Filesystem-boundary note:** the codex boundary text above uses the host-neutral phrasing
|
||||
(matching autoplan's codex recipes) so it renders correctly on every host — keep its intent in
|
||||
sync with codex/SKILL.md.tmpl's canonical boundary, since this recipe calls `codex review`
|
||||
directly. The grok member enforces read-only at the OS level via `--sandbox read-only` (writes and
|
||||
child network blocked), so it cannot mutate the repo even if the boundary prose is ignored.
|
||||
|
||||
**Per-gate dashboard log — one entry PER review PER gate** (the gate runs four reviews —
|
||||
eng-review, /review, and the Codex + Grok forum; log four entries, all `via: "autobuilder-loop"`,
|
||||
sharing the same commit):
|
||||
```bash
|
||||
COMMIT=$(git rev-parse --short HEAD 2>/dev/null)
|
||||
TIMESTAMP=$(date -u +%Y-%m-%dT%H:%M:%SZ)
|
||||
~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"plan-eng-review","timestamp":"'"$TIMESTAMP"'","status":"STATUS","unresolved":N,"via":"autobuilder-loop","commit":"'"$COMMIT"'"}'
|
||||
~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"review","timestamp":"'"$TIMESTAMP"'","status":"STATUS","unresolved":N,"via":"autobuilder-loop","commit":"'"$COMMIT"'"}'
|
||||
~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"codex","timestamp":"'"$TIMESTAMP"'","status":"STATUS","unresolved":N,"via":"autobuilder-loop","commit":"'"$COMMIT"'"}'
|
||||
~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"grok","timestamp":"'"$TIMESTAMP"'","status":"STATUS","unresolved":N,"via":"autobuilder-loop","commit":"'"$COMMIT"'"}'
|
||||
```
|
||||
`status` = `clean` if no unresolved issues, else `issues_open`. Log the codex and grok entries
|
||||
separately so the forum's cross-model coverage is visible per member. If a member is ABSENT
|
||||
(unavailable/disabled), still log its entry with a status noting the absence; when BOTH members
|
||||
are ABSENT and the loop falls back to the single-model Claude pass, note the fallback in the codex
|
||||
and grok entries' status/fields so the substitution is visible. This is separate from — and in
|
||||
addition to — the run-level telemetry the preamble renders in the "Telemetry (run last)" block
|
||||
above; the preamble handles that one, do not duplicate it. All review-log calls are best-effort —
|
||||
never block the loop.
|
||||
|
||||
---
|
||||
|
||||
## Important Rules
|
||||
|
||||
- **Orchestrator only.** Never write/edit code, never read source/diffs/logs into your
|
||||
context, never run the build yourself. Your tools are `Agent`, `Bash`, `AskUserQuestion` —
|
||||
top-level Bash is only for the Codex + Grok adversarial gate and review-log/telemetry.
|
||||
Everything real happens in a subagent that returns a compact envelope.
|
||||
- **Route every dispatch.** Classify complexity first; emit `model:` every time. Probe Fable
|
||||
once at loop start; on unavailability route orchestration/synthesis to Opus-max and say so.
|
||||
Hard work never silently degrades below the Opus class.
|
||||
- **Gate EVERY milestone.** eng-review + /review + Codex + Grok (the adversarial forum), fix
|
||||
until clean. There is no major/minor distinction and no "it's small" skip — the only carve-out is a plan-labeled
|
||||
docs-only milestone. The deferral valve batches at most one small, non-sensitive milestone
|
||||
forward, marks it "built — gate pending", and never applies to the final milestone.
|
||||
- **Docker-verify before done.** App reachable (2xx/3xx) on its port, zero console/network
|
||||
errors, every acceptance path PASS, tests+build green on fresh evidence. `NO_SERVER` = fail;
|
||||
4xx/5xx = fail. No Docker setup → AskUserQuestion (fix / waive / stop), never a silent skip.
|
||||
- **The plan is the contract.** TODOS.md/plan on disk is source of truth; freeze the milestone
|
||||
set at resolution; re-read the next milestone each iteration; never reorder/merge/drop items
|
||||
from memory; follow-ups never silently become milestones or get dropped.
|
||||
- **Never auto-run business or plan skills.** Suggest /design-review, /plan-ceo-review,
|
||||
/plan-design-review — the user owns those. Never auto-invoke /autoplan or any review skill.
|
||||
- **Evidence, not confidence.** No "done" without verification output tied to each
|
||||
acceptance criterion and a live Docker run.
|
||||
|
|
@ -42,9 +42,14 @@ beforeAll(async () => {
|
|||
// The test needs to start a server. Let's use the existing server infrastructure.
|
||||
});
|
||||
|
||||
afterAll(() => {
|
||||
afterAll(async () => {
|
||||
try { testServer.server.stop(); } catch {}
|
||||
setTimeout(() => process.exit(0), 500);
|
||||
// Close only this file's own browser — never process.exit(): bun test runs
|
||||
// all files in one process, so a delayed exit kills the whole suite
|
||||
// (see test/no-suicide-exit.test.ts). close() can hang when the browser
|
||||
// already died, and its internal 5s timeout ties bun's 5s hook timeout —
|
||||
// so race it at 3s and abandon; the child is reaped at process exit.
|
||||
try { await Promise.race([bm?.close(), new Promise((resolve) => setTimeout(resolve, 3000))]); } catch {}
|
||||
});
|
||||
|
||||
// We need a running browse server for HTTP tests.
|
||||
|
|
|
|||
|
|
@ -94,11 +94,14 @@ beforeAll(async () => {
|
|||
await bm.launch();
|
||||
});
|
||||
|
||||
afterAll(() => {
|
||||
// Force kill browser instead of graceful close (avoids hang)
|
||||
afterAll(async () => {
|
||||
try { testServer.server.stop(); } catch {}
|
||||
// bm.close() can hang — just let process exit handle it
|
||||
setTimeout(() => process.exit(0), 500);
|
||||
// Close only this file's own browser — never process.exit(): bun test runs
|
||||
// all files in one process, so a delayed exit kills the whole suite
|
||||
// (see test/no-suicide-exit.test.ts). close() can hang when the browser
|
||||
// already died, and its internal 5s timeout ties bun's 5s hook timeout —
|
||||
// so race it at 3s and abandon; the child is reaped at process exit.
|
||||
try { await Promise.race([bm?.close(), new Promise((resolve) => setTimeout(resolve, 3000))]); } catch {}
|
||||
});
|
||||
|
||||
// ─── Navigation ─────────────────────────────────────────────────
|
||||
|
|
|
|||
|
|
@ -69,10 +69,15 @@ beforeAll(async () => {
|
|||
await handleWriteCommand('goto', [boardUrl], bm);
|
||||
});
|
||||
|
||||
afterAll(() => {
|
||||
afterAll(async () => {
|
||||
try { server.stop(); } catch {}
|
||||
fs.rmSync(tmpDir, { recursive: true, force: true });
|
||||
setTimeout(() => process.exit(0), 500);
|
||||
// Close only this file's own browser — never process.exit(): bun test runs
|
||||
// all files in one process, so a delayed exit kills the whole suite
|
||||
// (see test/no-suicide-exit.test.ts). close() can hang when the browser
|
||||
// already died, and its internal 5s timeout ties bun's 5s hook timeout —
|
||||
// so race it at 3s and abandon; the child is reaped at process exit.
|
||||
try { await Promise.race([bm?.close(), new Promise((resolve) => setTimeout(resolve, 3000))]); } catch {}
|
||||
});
|
||||
|
||||
// ─── DOM Structure ──────────────────────────────────────────────
|
||||
|
|
|
|||
|
|
@ -422,9 +422,14 @@ describe('Hidden element stripping', () => {
|
|||
await bm.launch();
|
||||
});
|
||||
|
||||
afterAll(() => {
|
||||
afterAll(async () => {
|
||||
try { testServer.server.stop(); } catch {}
|
||||
setTimeout(() => process.exit(0), 500);
|
||||
// Close only this file's own browser — never process.exit(): bun test
|
||||
// runs all files in one process, so a delayed exit kills the whole suite
|
||||
// (see test/no-suicide-exit.test.ts). close() can hang when the browser
|
||||
// already died, and its internal 5s timeout ties bun's 5s hook timeout —
|
||||
// so race it at 3s and abandon; the child is reaped at process exit.
|
||||
try { await Promise.race([bm?.close(), new Promise((resolve) => setTimeout(resolve, 3000))]); } catch {}
|
||||
});
|
||||
|
||||
test('detects CSS-hidden elements on injection-hidden page', async () => {
|
||||
|
|
|
|||
|
|
@ -26,9 +26,14 @@ beforeAll(async () => {
|
|||
await bm.launch();
|
||||
});
|
||||
|
||||
afterAll(() => {
|
||||
afterAll(async () => {
|
||||
try { testServer.server.stop(); } catch {}
|
||||
setTimeout(() => process.exit(0), 500);
|
||||
// Close only this file's own browser — never process.exit(): bun test runs
|
||||
// all files in one process, so a delayed exit kills the whole suite
|
||||
// (see test/no-suicide-exit.test.ts). close() can hang when the browser
|
||||
// already died, and its internal 5s timeout ties bun's 5s hook timeout —
|
||||
// so race it at 3s and abandon; the child is reaped at process exit.
|
||||
try { await Promise.race([bm?.close(), new Promise((resolve) => setTimeout(resolve, 3000))]); } catch {}
|
||||
});
|
||||
|
||||
// ─── Unit Tests: Failure Tracking (no browser needed) ────────────
|
||||
|
|
|
|||
|
|
@ -56,9 +56,14 @@ describe('defense-in-depth — live Playwright fixture', () => {
|
|||
await bm.launch();
|
||||
});
|
||||
|
||||
afterAll(() => {
|
||||
afterAll(async () => {
|
||||
try { testServer.server.stop(); } catch {}
|
||||
setTimeout(() => process.exit(0), 500);
|
||||
// Close only this file's own browser — never process.exit(): bun test
|
||||
// runs all files in one process, so a delayed exit kills the whole suite
|
||||
// (see test/no-suicide-exit.test.ts). close() can hang when the browser
|
||||
// already died, and its internal 5s timeout ties bun's 5s hook timeout —
|
||||
// so race it at 3s and abandon; the child is reaped at process exit.
|
||||
try { await Promise.race([bm?.close(), new Promise((resolve) => setTimeout(resolve, 3000))]); } catch {}
|
||||
});
|
||||
|
||||
test('L2 — content-security.ts hidden-element stripper detects the .sneaky div', async () => {
|
||||
|
|
|
|||
|
|
@ -31,9 +31,14 @@ beforeAll(async () => {
|
|||
await bm.launch();
|
||||
});
|
||||
|
||||
afterAll(() => {
|
||||
afterAll(async () => {
|
||||
try { testServer.server.stop(); } catch {}
|
||||
setTimeout(() => process.exit(0), 500);
|
||||
// Close only this file's own browser — never process.exit(): bun test runs
|
||||
// all files in one process, so a delayed exit kills the whole suite
|
||||
// (see test/no-suicide-exit.test.ts). close() can hang when the browser
|
||||
// already died, and its internal 5s timeout ties bun's 5s hook timeout —
|
||||
// so race it at 3s and abandon; the child is reaped at process exit.
|
||||
try { await Promise.race([bm?.close(), new Promise((resolve) => setTimeout(resolve, 3000))]); } catch {}
|
||||
});
|
||||
|
||||
// ─── Snapshot Output ────────────────────────────────────────────
|
||||
|
|
|
|||
|
|
@ -361,16 +361,27 @@ describe("daemon /shutdown", () => {
|
|||
await fetchHandler(
|
||||
req("POST", `/boards/${board.id}/api/feedback`, { regenerated: false }),
|
||||
);
|
||||
// Now non-done count is 0 — handler should return shuttingDown:true.
|
||||
// We DON'T let the real gracefulShutdown timer fire (it calls process.exit
|
||||
// after 50ms which would tear down the test runner); instead we just
|
||||
// observe the immediate response.
|
||||
const r = await fetchHandler(req("POST", "/shutdown"));
|
||||
expect(r.status).toBe(200);
|
||||
const body = (await r.json()) as any;
|
||||
expect(body.shuttingDown).toBe(true);
|
||||
// Reset state for subsequent tests; the shutdown timer will be a no-op
|
||||
// because the next resetForTest flips shuttingDown back to false.
|
||||
// The handler arms setTimeout(gracefulShutdown, 50), and gracefulShutdown
|
||||
// arms setTimeout(process.exit, 50). bun test runs ALL files in one
|
||||
// process, so letting that exit fire would kill the whole suite ~100ms
|
||||
// later (exit 0, no summary — see test/no-suicide-exit.test.ts). Stub
|
||||
// process.exit, wait past both timers so they fire harmlessly while
|
||||
// stubbed, then restore. (resetForTest does NOT defuse the timers: the
|
||||
// exit callback is unconditional.)
|
||||
const origExit = process.exit;
|
||||
(process as any).exit = (() => undefined) as any;
|
||||
try {
|
||||
const r = await fetchHandler(req("POST", "/shutdown"));
|
||||
expect(r.status).toBe(200);
|
||||
const body = (await r.json()) as any;
|
||||
expect(body.shuttingDown).toBe(true);
|
||||
// Let both 50ms timers (gracefulShutdown, then its process.exit) fire
|
||||
// against the stub before restoring the real process.exit.
|
||||
await new Promise((resolve) => setTimeout(resolve, 200));
|
||||
} finally {
|
||||
(process as any).exit = origExit;
|
||||
}
|
||||
// Reset state for subsequent tests (gracefulShutdown set shuttingDown).
|
||||
resetDaemon();
|
||||
});
|
||||
});
|
||||
|
|
|
|||
|
|
@ -121,10 +121,15 @@ beforeAll(async () => {
|
|||
await bm.launch();
|
||||
});
|
||||
|
||||
afterAll(() => {
|
||||
afterAll(async () => {
|
||||
try { server.stop(); } catch {}
|
||||
fs.rmSync(tmpDir, { recursive: true, force: true });
|
||||
setTimeout(() => process.exit(0), 500);
|
||||
// Close only this file's own browser — never process.exit(): bun test runs
|
||||
// all files in one process, so a delayed exit kills the whole suite
|
||||
// (see test/no-suicide-exit.test.ts). close() can hang when the browser
|
||||
// already died, and its internal 5s timeout ties bun's 5s hook timeout —
|
||||
// so race it at 3s and abandon; the child is reaped at process exit.
|
||||
try { await Promise.race([bm?.close(), new Promise((resolve) => setTimeout(resolve, 3000))]); } catch {}
|
||||
});
|
||||
|
||||
// ─── The critical test: browser click → file on disk ─────────────
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
---
|
||||
name: diagram
|
||||
version: 1.0.0
|
||||
description: "Turn an English description (or mermaid source) into a diagram triplet: the source, an editable .excalidraw file you can open (gstack)"
|
||||
description: "Turn an English description (or mermaid source) into a diagram triplet: the source, an editable .excalidraw file you can open on excalidraw.com, and rendered SVG + PNG. (gstack)"
|
||||
allowed-tools:
|
||||
- Bash
|
||||
- Read
|
||||
|
|
@ -21,9 +21,8 @@ triggers:
|
|||
|
||||
## When to invoke this skill
|
||||
|
||||
on excalidraw.com,
|
||||
and rendered SVG + PNG (clean mermaid style; the .excalidraw carries the
|
||||
hand-drawn aesthetic). Fully offline.
|
||||
The SVG/PNG use clean mermaid style; the
|
||||
.excalidraw carries the hand-drawn aesthetic. Fully offline.
|
||||
Use when asked to "make a diagram", "draw the architecture", "create a
|
||||
flowchart", "diagram this", or "visualize this flow".
|
||||
|
||||
|
|
|
|||
|
|
@ -4,8 +4,8 @@ version: 1.0.0
|
|||
description: |
|
||||
Turn an English description (or mermaid source) into a diagram triplet:
|
||||
the source, an editable .excalidraw file you can open on excalidraw.com,
|
||||
and rendered SVG + PNG (clean mermaid style; the .excalidraw carries the
|
||||
hand-drawn aesthetic). Fully offline.
|
||||
and rendered SVG + PNG. The SVG/PNG use clean mermaid style; the
|
||||
.excalidraw carries the hand-drawn aesthetic. Fully offline.
|
||||
Use when asked to "make a diagram", "draw the architecture", "create a
|
||||
flowchart", "diagram this", or "visualize this flow". (gstack)
|
||||
allowed-tools:
|
||||
|
|
|
|||
|
|
@ -30,6 +30,7 @@ Detailed guides for every gstack skill — philosophy, workflow, and examples.
|
|||
| [`/browse`](#browse) | **QA Engineer** | Give the agent eyes. Real Chromium browser, real clicks, real screenshots. ~100ms per command. |
|
||||
| [`/setup-browser-cookies`](#setup-browser-cookies) | **Session Manager** | Import cookies from your real browser (Chrome, Arc, Brave, Edge) into the headless session. Test authenticated pages. |
|
||||
| [`/autoplan`](#autoplan) | **Review Pipeline** | One command, fully reviewed plan. Runs CEO → design → eng → DX review automatically with encoded decision principles. Surfaces only taste decisions for your approval. |
|
||||
| [`/autobuilder-loop`](#autobuilder-loop) | **Build Loop** | Drive an already-approved plan, spec, or backlog to completion unattended. Model-routed subagents per milestone, review gates, and Docker verification. |
|
||||
| [`/plan-devex-review`](#plan-devex-review) | **DX Reviewer** | Plan-stage DX review. TTHW (time-to-hello-world), magical moments, friction points, persona traces. Three modes: Expansion, Polish, Triage. |
|
||||
| [`/devex-review`](#devex-review) | **DX Reviewer (live)** | Live developer experience audit. Walks the actual onboarding flow, measures TTHW, catches the docs lies. |
|
||||
| [`/plan-tune`](#plan-tune) | **Question Tuner** | Self-tune AskUserQuestion sensitivity per question. Mark questions as never-ask, always-ask, or only-for-one-way. |
|
||||
|
|
|
|||
|
|
@ -10,6 +10,7 @@ Conventions:
|
|||
|
||||
## Skills
|
||||
|
||||
- [/autobuilder-loop](autobuilder-loop/SKILL.md): Use when asked to "autobuilder", "build loop", "auto-build", "keep building automatically", "drive the plan to completion", or "run the build loop" on an already-approved plan, spec, or backlog.
|
||||
- [/autoplan](autoplan/SKILL.md): Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles.
|
||||
- [/benchmark](benchmark/SKILL.md): Performance regression detection using the browse daemon.
|
||||
- [/benchmark-models](benchmark-models/SKILL.md): Cross-model benchmark for gstack skills.
|
||||
|
|
@ -26,7 +27,7 @@ Conventions:
|
|||
- [/design-review](design-review/SKILL.md): Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them.
|
||||
- [/design-shotgun](design-shotgun/SKILL.md): Design shotgun: generate multiple AI design variants, open a comparison board, collect structured feedback, and iterate.
|
||||
- [/devex-review](devex-review/SKILL.md): Live developer experience audit.
|
||||
- [/diagram](diagram/SKILL.md): Turn an English description (or mermaid source) into a diagram triplet: the source, an editable .excalidraw file you can open on excalidraw.com, and rendered SVG + PNG (clean mermaid style; the .excalidraw carries the hand-drawn aesthetic).
|
||||
- [/diagram](diagram/SKILL.md): Turn an English description (or mermaid source) into a diagram triplet: the source, an editable .excalidraw file you can open on excalidraw.com, and rendered SVG + PNG.
|
||||
- [/document-generate](document-generate/SKILL.md): Generate missing documentation from scratch for a feature, module, or entire project.
|
||||
- [/document-release](document-release/SKILL.md): Post-ship documentation update.
|
||||
- [/freeze](freeze/SKILL.md): Restrict file edits to a specific directory for the session.
|
||||
|
|
|
|||
|
|
@ -317,12 +317,16 @@ export function splitCatalogDescription(description: string): CatalogParts {
|
|||
const hasGstackTag = /\(gstack\)/.test(working);
|
||||
if (hasGstackTag) working = working.replace(/\(gstack\)/, '').trim();
|
||||
|
||||
// Lead = first sentence (up to first period followed by space or end of string).
|
||||
// We tolerate sentences with embedded periods (URLs, "v1.45.0.0") by requiring
|
||||
// the period to be followed by whitespace OR end-of-text.
|
||||
// Lead = first sentence, ending at the first `.`/`!`/`?` that is followed by
|
||||
// whitespace or end-of-text. Terminator chars NOT followed by whitespace/end
|
||||
// (embedded periods in "TODOS.md", URLs, "v1.45.0.0") are consumed by the
|
||||
// second alternative `[.!?](?!\s|$)` and do NOT end the sentence. The two
|
||||
// alternatives are disjoint character classes, so there is no ambiguity and
|
||||
// no catastrophic-backtracking risk. If no terminator-followed-by-boundary
|
||||
// exists at all, we fall back to a 20-word cut below.
|
||||
// First normalize to single-line for sentence detection, then back out.
|
||||
const collapsed = working.replace(/\s+/g, ' ').trim();
|
||||
const sentenceMatch = collapsed.match(/^([^.!?]*[.!?])(?:\s|$)/);
|
||||
const sentenceMatch = collapsed.match(/^((?:[^.!?]|[.!?](?!\s|$))*[.!?])(?:\s|$)/);
|
||||
// sentenceLead is the FULL first sentence (no truncation). We compute routing
|
||||
// from this position, then optionally truncate the displayed lead afterwards.
|
||||
// Truncating first then computing routing was the v1.45.0.0 bug — when the
|
||||
|
|
|
|||
|
|
@ -3,6 +3,11 @@
|
|||
"catalog_mode": "trim",
|
||||
"note": "Routing / voice-trigger prose extracted from SKILL.md frontmatter descriptions during catalog trim. Loaded on demand when routing guidance is needed.",
|
||||
"skills": {
|
||||
"autobuilder-loop": {
|
||||
"lead": "Use when asked to \"autobuilder\", \"build loop\", \"auto-build\", \"keep building automatically\", \"drive the plan to completion\", or \"run the build loop\" on an already-approved plan, spec, or backlog.",
|
||||
"routing": "Proactively suggest when the user has an approved plan (TODOS.md, spec, or\nplan doc) and wants it built to completion unattended rather than driving\neach milestone by hand.",
|
||||
"voice_line": "Voice triggers (speech-to-text aliases): \"auto builder\", \"build loop\", \"auto build loop\"."
|
||||
},
|
||||
"autoplan": {
|
||||
"lead": "Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles.",
|
||||
"routing": "Surfaces\ntaste decisions (close approaches, borderline scope, codex disagreements) at a final\napproval gate. One command, fully reviewed plan out.\nUse when asked to \"auto review\", \"autoplan\", \"run all reviews\", \"review this plan\nautomatically\", or \"make the decisions for me\".\nProactively suggest when the user has a plan file and wants to run the full review\ngauntlet without answering 15-30 intermediate questions.",
|
||||
|
|
@ -79,8 +84,8 @@
|
|||
"voice_line": "Voice triggers (speech-to-text aliases): \"dx audit\", \"test the developer experience\", \"try the onboarding\", \"developer experience test\"."
|
||||
},
|
||||
"diagram": {
|
||||
"lead": "Turn an English description (or mermaid source) into a diagram triplet: the source, an editable .excalidraw file you can open",
|
||||
"routing": "on excalidraw.com,\nand rendered SVG + PNG (clean mermaid style; the .excalidraw carries the\nhand-drawn aesthetic). Fully offline.\nUse when asked to \"make a diagram\", \"draw the architecture\", \"create a\nflowchart\", \"diagram this\", or \"visualize this flow\".",
|
||||
"lead": "Turn an English description (or mermaid source) into a diagram triplet: the source, an editable .excalidraw file you can open on excalidraw.com, and rendered SVG + PNG.",
|
||||
"routing": "The SVG/PNG use clean mermaid style; the\n.excalidraw carries the hand-drawn aesthetic. Fully offline.\nUse when asked to \"make a diagram\", \"draw the architecture\", \"create a\nflowchart\", \"diagram this\", or \"visualize this flow\".",
|
||||
"voice_line": null
|
||||
},
|
||||
"document-generate": {
|
||||
|
|
@ -264,8 +269,8 @@
|
|||
"voice_line": null
|
||||
},
|
||||
"sync-gbrain": {
|
||||
"lead": "Keep gbrain current with this repo's code and refresh agent search guidance in CLAUDE.md. Wraps the gstack-gbrain-sync orchestrator with state",
|
||||
"routing": "probing, native code-surface registration, capability checks,\nand a verdict block. Re-runnable, idempotent. Use when: \"sync gbrain\",\n\"refresh gbrain\", \"re-index this repo\", \"gbrain search isn't finding\nthings\".",
|
||||
"lead": "Keep gbrain current with this repo's code and refresh agent search guidance in CLAUDE.md.",
|
||||
"routing": "Wraps the gstack-gbrain-sync orchestrator with\nstate probing, native code-surface registration, capability checks,\nand a verdict block. Re-runnable, idempotent. Use when: \"sync gbrain\",\n\"refresh gbrain\", \"re-index this repo\", \"gbrain search isn't finding\nthings\".",
|
||||
"voice_line": null
|
||||
},
|
||||
"unfreeze": {
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
name: sync-gbrain
|
||||
preamble-tier: 2
|
||||
version: 1.0.0
|
||||
description: Keep gbrain current with this repo's code and refresh agent search guidance in CLAUDE.md. Wraps the gstack-gbrain-sync orchestrator with state (gstack)
|
||||
description: Keep gbrain current with this repo's code and refresh agent search guidance in CLAUDE.md. (gstack)
|
||||
triggers:
|
||||
- sync gbrain
|
||||
- refresh gbrain
|
||||
|
|
@ -23,7 +23,8 @@ allowed-tools:
|
|||
|
||||
## When to invoke this skill
|
||||
|
||||
probing, native code-surface registration, capability checks,
|
||||
Wraps the gstack-gbrain-sync orchestrator with
|
||||
state probing, native code-surface registration, capability checks,
|
||||
and a verdict block. Re-runnable, idempotent. Use when: "sync gbrain",
|
||||
"refresh gbrain", "re-index this repo", "gbrain search isn't finding
|
||||
things".
|
||||
|
|
|
|||
|
|
@ -95,31 +95,59 @@ describe('splitCatalogDescription', () => {
|
|||
expect(parts.routingProse).toBe('With routing prose afterward.');
|
||||
});
|
||||
|
||||
test('embedded-period descriptions: known limitation falls back to first-20-words', () => {
|
||||
// KNOWN LIMITATION: the sentence regex `^([^.!?]*[.!?])(?:\\s|$)` stops
|
||||
// at the FIRST `.`-then-non-whitespace because [^.!?]* is greedy and
|
||||
// can't backtrack past a non-period char. For "DESIGN.md and v1.45.0.0
|
||||
// in the lead. Use when..." the regex fails entirely and the lead falls
|
||||
// back to the first 20 words (~the whole short input).
|
||||
//
|
||||
// The real-world impact is small: descriptions like "DESIGN.md" or "v1.45"
|
||||
// appearing in the middle of the FIRST sentence are rare. When they do
|
||||
// occur, the lead simply becomes the full description (no body section
|
||||
// generated) — same as a description without a period. The trim CI gate
|
||||
// still keeps the per-skill size budget honest.
|
||||
//
|
||||
// If this gap matters later, replace the regex with a sentence tokenizer
|
||||
// (compromise.js / Intl.Segmenter) — until then we accept the fallback.
|
||||
test('REGRESSION (autobuilder-loop): embedded-period first sentence splits at real boundary', () => {
|
||||
// The old regex `^([^.!?]*[.!?])(?:\s|$)` could not cross ANY period —
|
||||
// [^.!?]* stops at the first `.` even mid-token ("DESIGN.md"), the
|
||||
// boundary check then fails, and the whole match failed. The code
|
||||
// silently fell back to a 20-word cut mid-phrase (observed with the
|
||||
// autobuilder-loop description mentioning "TODOS.md"). The fixed regex
|
||||
// `^((?:[^.!?]|[.!?](?!\s|$))*[.!?])(?:\s|$)` consumes terminators NOT
|
||||
// followed by whitespace/end, so embedded periods no longer break it.
|
||||
const desc =
|
||||
'Skill that mentions DESIGN.md and v1.45.0.0 in the lead. ' +
|
||||
'Use when asked to do something.';
|
||||
const parts = splitCatalogDescription(desc);
|
||||
// Actual behavior: lead absorbs the whole input via the word-count fallback.
|
||||
expect(parts.lead.length).toBeGreaterThan(0);
|
||||
// routingProse may be empty when the fallback consumes everything.
|
||||
// The test exists to detect REGRESSIONS (lead becoming oddly short like
|
||||
// "Skill that mentions DESIGN.") not to assert ideal behavior.
|
||||
expect(parts.lead).toContain('Skill that mentions');
|
||||
expect(parts.lead).toBe('Skill that mentions DESIGN.md and v1.45.0.0 in the lead.');
|
||||
expect(parts.routingProse).toBe('Use when asked to do something.');
|
||||
});
|
||||
|
||||
test('REGRESSION (autobuilder-loop): "TODOS.md backlog" style sentence keeps full lead + routing', () => {
|
||||
const desc =
|
||||
'Drive an approved plan to completion on a TODOS.md backlog. ' +
|
||||
'Use when asked to "autobuilder" or "run the build loop". ' +
|
||||
'Proactively suggest after a plan is approved. (gstack)';
|
||||
const parts = splitCatalogDescription(desc);
|
||||
expect(parts.lead).toBe('Drive an approved plan to completion on a TODOS.md backlog.');
|
||||
expect(parts.routingProse).toContain('Use when asked to "autobuilder"');
|
||||
expect(parts.routingProse).toContain('Proactively suggest');
|
||||
expect(parts.hasGstackTag).toBe(true);
|
||||
});
|
||||
|
||||
test('URL in first sentence does not end the lead early', () => {
|
||||
const desc =
|
||||
'See https://example.com/docs/v2 for the workflow. ' +
|
||||
'Use when asked to consult the docs.';
|
||||
const parts = splitCatalogDescription(desc);
|
||||
expect(parts.lead).toBe('See https://example.com/docs/v2 for the workflow.');
|
||||
expect(parts.routingProse).toBe('Use when asked to consult the docs.');
|
||||
});
|
||||
|
||||
test('>200 char first sentence WITH embedded periods still truncates with ellipsis and keeps routing', () => {
|
||||
const firstSentence =
|
||||
'Regenerate the iOS debug bridge against files like Bridge.swift and TODOS.md, ' +
|
||||
'walking every target listed in Project.xcodeproj while preserving v1.45.0.0 ' +
|
||||
'compatibility shims, custom entitlements, and the long tail of per-target ' +
|
||||
'build settings nobody remembers configuring.';
|
||||
expect(firstSentence.length).toBeGreaterThan(200);
|
||||
const desc = firstSentence + ' Use when asked to resync the bridge. (gstack)';
|
||||
const parts = splitCatalogDescription(desc);
|
||||
// Lead is the truncated first sentence (ellipsis path), not a 20-word cut.
|
||||
expect(parts.lead.endsWith('...')).toBe(true);
|
||||
expect(parts.lead.length).toBeLessThanOrEqual(200);
|
||||
expect(parts.lead).toContain('TODOS.md');
|
||||
// Routing prose survives intact.
|
||||
expect(parts.routingProse).toContain('Use when asked to resync the bridge.');
|
||||
expect(parts.hasGstackTag).toBe(true);
|
||||
});
|
||||
|
||||
test('description without a period uses first ~20 words as lead', () => {
|
||||
|
|
|
|||
|
|
@ -0,0 +1,49 @@
|
|||
/**
|
||||
* Guard: no test file may schedule a delayed process.exit().
|
||||
*
|
||||
* `bun test` runs EVERY test file in one process. The pattern of arming a
|
||||
* 500ms timer in afterAll whose callback calls process.exit(0) — once used
|
||||
* in several browse/design tests as a "bm.close() can hang" workaround —
|
||||
* assumes each file gets its own process. It doesn't: the armed timer fires
|
||||
* 500ms later, mid-way through a LATER test file, and kills the entire
|
||||
* suite with exit code 0 and no summary. The truncated run silently masks
|
||||
* every downstream failure (observed: only ~16 of 434 files ran, shell
|
||||
* exit 0).
|
||||
*
|
||||
* This test statically scans every *.test.ts in the repo and fails if any
|
||||
* schedules process.exit via setTimeout. Teardown must only release the
|
||||
* file's own resources (e.g. `await bm.close()` — BrowserManager.close()
|
||||
* is already time-boxed internally) — never terminate the shared runner.
|
||||
*
|
||||
* If a future test legitimately needs this pattern inside a child-process
|
||||
* script (template literal passed to `bun -e`), split the child script
|
||||
* into a fixture file instead of exempting it here.
|
||||
*/
|
||||
import { test, expect } from 'bun:test';
|
||||
import fs from 'node:fs';
|
||||
import path from 'node:path';
|
||||
|
||||
const repoRoot = path.resolve(import.meta.dir, '..');
|
||||
|
||||
// Matches a setTimeout whose arrow callback (with or without an argument)
|
||||
// immediately calls process.exit. Doesn't match its own escaped source text
|
||||
// (the backslashes in this regex literal prevent a literal-text match).
|
||||
const DELAYED_EXIT = /setTimeout\(\s*(?:\(\s*\)|\(?\w+\)?)\s*=>\s*process\.exit\(/;
|
||||
|
||||
test('no test file schedules a delayed process.exit (kills the whole bun test run)', () => {
|
||||
const glob = new Bun.Glob('**/*.test.ts');
|
||||
const violations: string[] = [];
|
||||
|
||||
for (const rel of glob.scanSync({ cwd: repoRoot })) {
|
||||
if (rel.includes('node_modules/')) continue;
|
||||
const source = fs.readFileSync(path.join(repoRoot, rel), 'utf-8');
|
||||
const lines = source.split('\n');
|
||||
for (let i = 0; i < lines.length; i++) {
|
||||
if (DELAYED_EXIT.test(lines[i])) {
|
||||
violations.push(`${rel}:${i + 1}: ${lines[i].trim()}`);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
expect(violations).toEqual([]);
|
||||
});
|
||||
|
|
@ -121,6 +121,7 @@ export const SKILL_COVERAGE: Record<string, SkillCoverage> = {
|
|||
gate: ['test/skill-coverage-floor.test.ts'],
|
||||
periodic: ['test/skill-e2e-autoplan-chain.test.ts', 'test/skill-e2e-autoplan-dual-voice.test.ts'],
|
||||
},
|
||||
'autobuilder-loop': { gate: ['test/skill-coverage-floor.test.ts'], periodic: [] },
|
||||
'office-hours': {
|
||||
gate: ['test/skill-e2e-office-hours.test.ts', 'test/skill-coverage-floor.test.ts'],
|
||||
periodic: ['test/skill-e2e-office-hours-auto-mode.test.ts', 'test/skill-e2e-office-hours-phase4.test.ts'],
|
||||
|
|
|
|||
|
|
@ -35,6 +35,12 @@ function runConfig(args: string[], extraEnv: Record<string, string> = {}): { std
|
|||
encoding: 'utf-8',
|
||||
env: {
|
||||
...process.env,
|
||||
// HOME isolation: endpoint_hash() reads $HOME/.claude.json for the
|
||||
// gbrain MCP URL. Pointing HOME at the empty TMP_HOME makes it
|
||||
// deterministically 'local' regardless of the developer's real
|
||||
// ~/.claude.json (which would otherwise change the persisted key
|
||||
// namespace to user_slug_at_<sha8-of-url>).
|
||||
HOME: TMP_HOME,
|
||||
...extraEnv,
|
||||
},
|
||||
timeout: 5000,
|
||||
|
|
@ -92,7 +98,9 @@ describe('resolve-user-slug fallback chain', () => {
|
|||
const configFile = join(TMP_HOME, 'config.yaml');
|
||||
expect(existsSync(configFile)).toBe(true);
|
||||
const content = readFileSync(configFile, 'utf-8');
|
||||
expect(content).toMatch(/^user_slug_at_[a-f0-9]+:\s+persisttest/m);
|
||||
// HOME is isolated to the empty TMP_HOME, so endpoint_hash() is
|
||||
// deterministically the literal 'local' on every machine.
|
||||
expect(content).toMatch(/^user_slug_at_local:\s+persisttest/m);
|
||||
});
|
||||
|
||||
test('subsequent calls return same slug (stable across sessions)', () => {
|
||||
|
|
|
|||
Loading…
Reference in New Issue