mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-02 11:45:20 +02:00
Merge remote-tracking branch 'origin/main' into garrytan/openclaw-browser-ctrl
# Conflicts: # CHANGELOG.md # VERSION
This commit is contained in:
Garry Tan
+266
-5
@@ -86,6 +86,8 @@ fi
|
||||
_ROUTING_DECLINED=$(~/.claude/skills/gstack/bin/gstack-config get routing_declined 2>/dev/null || echo "false")
|
||||
echo "HAS_ROUTING: $_HAS_ROUTING"
|
||||
echo "ROUTING_DECLINED: $_ROUTING_DECLINED"
|
||||
# Detect spawned session (OpenClaw or other orchestrator)
|
||||
[ -n "$OPENCLAW_SESSION" ] && echo "SPAWNED_SESSION: true" || true
|
||||
```
|
||||
|
||||
If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
|
||||
@@ -212,6 +214,13 @@ Say "No problem. You can add routing rules later by running `gstack-config set r
|
||||
|
||||
This only happens once per project. If `HAS_ROUTING` is `yes` or `ROUTING_DECLINED` is `true`, skip this entirely.
|
||||
|
||||
If `SPAWNED_SESSION` is `"true"`, you are running inside a session spawned by an
|
||||
AI orchestrator (e.g., OpenClaw). In spawned sessions:
|
||||
- Do NOT use AskUserQuestion for interactive prompts. Auto-choose the recommended option.
|
||||
- Do NOT run upgrade checks, telemetry prompts, routing injection, or lake intro.
|
||||
- Focus on completing the task and reporting results via prose output.
|
||||
- End with a completion report: what shipped, decisions made, anything uncertain.
|
||||
|
||||
## Voice
|
||||
|
||||
You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
|
||||
@@ -571,6 +580,16 @@ You are running the `/ship` workflow. This is a **non-interactive, fully automat
|
||||
- Auto-fixable review findings (dead code, N+1, stale comments — fixed automatically)
|
||||
- Test coverage gaps within target threshold (auto-generate and commit, or flag in PR body)
|
||||
|
||||
**Re-run behavior (idempotency):**
|
||||
Re-running `/ship` means "run the whole checklist again." Every verification step
|
||||
(tests, coverage audit, plan completion, pre-landing review, adversarial review,
|
||||
VERSION/CHANGELOG check, TODOS, document-release) runs on every invocation.
|
||||
Only *actions* are idempotent:
|
||||
- Step 4: If VERSION already bumped, skip the bump but still read the version
|
||||
- Step 7: If already pushed, skip the push command
|
||||
- Step 8: If PR exists, update the body instead of creating a new PR
|
||||
Never skip a verification step because a prior `/ship` run already performed it.
|
||||
|
||||
---
|
||||
|
||||
## Step 1: Pre-flight
|
||||
@@ -1649,7 +1668,244 @@ Present Codex output under a `CODEX (design):` header, merged with the checklist
|
||||
|
||||
Include any design findings alongside the code review findings. They follow the same Fix-First flow below.
|
||||
|
||||
4. **Classify each finding as AUTO-FIX or ASK** per the Fix-First Heuristic in
|
||||
## Step 3.55: Review Army — Specialist Dispatch
|
||||
|
||||
### Detect stack and scope
|
||||
|
||||
```bash
|
||||
source <(~/.claude/skills/gstack/bin/gstack-diff-scope <base> 2>/dev/null) || true
|
||||
# Detect stack for specialist context
|
||||
STACK=""
|
||||
[ -f Gemfile ] && STACK="${STACK}ruby "
|
||||
[ -f package.json ] && STACK="${STACK}node "
|
||||
[ -f requirements.txt ] || [ -f pyproject.toml ] && STACK="${STACK}python "
|
||||
[ -f go.mod ] && STACK="${STACK}go "
|
||||
[ -f Cargo.toml ] && STACK="${STACK}rust "
|
||||
echo "STACK: ${STACK:-unknown}"
|
||||
DIFF_INS=$(git diff origin/<base> --stat | tail -1 | grep -oE '[0-9]+ insertion' | grep -oE '[0-9]+' || echo "0")
|
||||
DIFF_DEL=$(git diff origin/<base> --stat | tail -1 | grep -oE '[0-9]+ deletion' | grep -oE '[0-9]+' || echo "0")
|
||||
DIFF_LINES=$((DIFF_INS + DIFF_DEL))
|
||||
echo "DIFF_LINES: $DIFF_LINES"
|
||||
# Detect test framework for specialist test stub generation
|
||||
TEST_FW=""
|
||||
{ [ -f jest.config.ts ] || [ -f jest.config.js ]; } && TEST_FW="jest"
|
||||
[ -f vitest.config.ts ] && TEST_FW="vitest"
|
||||
{ [ -f spec/spec_helper.rb ] || [ -f .rspec ]; } && TEST_FW="rspec"
|
||||
{ [ -f pytest.ini ] || [ -f conftest.py ]; } && TEST_FW="pytest"
|
||||
[ -f go.mod ] && TEST_FW="go-test"
|
||||
echo "TEST_FW: ${TEST_FW:-unknown}"
|
||||
```
|
||||
|
||||
### Read specialist hit rates (adaptive gating)
|
||||
|
||||
```bash
|
||||
~/.claude/skills/gstack/bin/gstack-specialist-stats 2>/dev/null || true
|
||||
```
|
||||
|
||||
### Select specialists
|
||||
|
||||
Based on the scope signals above, select which specialists to dispatch.
|
||||
|
||||
**Always-on (dispatch on every review with 50+ changed lines):**
|
||||
1. **Testing** — read `~/.claude/skills/gstack/review/specialists/testing.md`
|
||||
2. **Maintainability** — read `~/.claude/skills/gstack/review/specialists/maintainability.md`
|
||||
|
||||
**If DIFF_LINES < 50:** Skip all specialists. Print: "Small diff ($DIFF_LINES lines) — specialists skipped." Continue to the Fix-First flow (item 4).
|
||||
|
||||
**Conditional (dispatch if the matching scope signal is true):**
|
||||
3. **Security** — if SCOPE_AUTH=true, OR if SCOPE_BACKEND=true AND DIFF_LINES > 100. Read `~/.claude/skills/gstack/review/specialists/security.md`
|
||||
4. **Performance** — if SCOPE_BACKEND=true OR SCOPE_FRONTEND=true. Read `~/.claude/skills/gstack/review/specialists/performance.md`
|
||||
5. **Data Migration** — if SCOPE_MIGRATIONS=true. Read `~/.claude/skills/gstack/review/specialists/data-migration.md`
|
||||
6. **API Contract** — if SCOPE_API=true. Read `~/.claude/skills/gstack/review/specialists/api-contract.md`
|
||||
7. **Design** — if SCOPE_FRONTEND=true. Use the existing design review checklist at `~/.claude/skills/gstack/review/design-checklist.md`
|
||||
|
||||
### Adaptive gating
|
||||
|
||||
After scope-based selection, apply adaptive gating based on specialist hit rates:
|
||||
|
||||
For each conditional specialist that passed scope gating, check the `gstack-specialist-stats` output above:
|
||||
- If tagged `[GATE_CANDIDATE]` (0 findings in 10+ dispatches): skip it. Print: "[specialist] auto-gated (0 findings in N reviews)."
|
||||
- If tagged `[NEVER_GATE]`: always dispatch regardless of hit rate. Security and data-migration are insurance policy specialists — they should run even when silent.
|
||||
|
||||
**Force flags:** If the user's prompt includes `--security`, `--performance`, `--testing`, `--maintainability`, `--data-migration`, `--api-contract`, `--design`, or `--all-specialists`, force-include that specialist regardless of gating.
|
||||
|
||||
Note which specialists were selected, gated, and skipped. Print the selection:
|
||||
"Dispatching N specialists: [names]. Skipped: [names] (scope not detected). Gated: [names] (0 findings in N+ reviews)."
|
||||
|
||||
---
|
||||
|
||||
### Dispatch specialists in parallel
|
||||
|
||||
For each selected specialist, launch an independent subagent via the Agent tool.
|
||||
**Launch ALL selected specialists in a single message** (multiple Agent tool calls)
|
||||
so they run in parallel. Each subagent has fresh context — no prior review bias.
|
||||
|
||||
**Each specialist subagent prompt:**
|
||||
|
||||
Construct the prompt for each specialist. The prompt includes:
|
||||
|
||||
1. The specialist's checklist content (you already read the file above)
|
||||
2. Stack context: "This is a {STACK} project."
|
||||
3. Past learnings for this domain (if any exist):
|
||||
|
||||
```bash
|
||||
~/.claude/skills/gstack/bin/gstack-learnings-search --type pitfall --query "{specialist domain}" --limit 5 2>/dev/null || true
|
||||
```
|
||||
|
||||
If learnings are found, include them: "Past learnings for this domain: {learnings}"
|
||||
|
||||
4. Instructions:
|
||||
|
||||
"You are a specialist code reviewer. Read the checklist below, then run
|
||||
`git diff origin/<base>` to get the full diff. Apply the checklist against the diff.
|
||||
|
||||
For each finding, output a JSON object on its own line:
|
||||
{\"severity\":\"CRITICAL|INFORMATIONAL\",\"confidence\":N,\"path\":\"file\",\"line\":N,\"category\":\"category\",\"summary\":\"description\",\"fix\":\"recommended fix\",\"fingerprint\":\"path:line:category\",\"specialist\":\"name\"}
|
||||
|
||||
Required fields: severity, confidence, path, category, summary, specialist.
|
||||
Optional: line, fix, fingerprint, evidence, test_stub.
|
||||
|
||||
If you can write a test that would catch this issue, include it in the `test_stub` field.
|
||||
Use the detected test framework ({TEST_FW}). Write a minimal skeleton — describe/it/test
|
||||
blocks with clear intent. Skip test_stub for architectural or design-only findings.
|
||||
|
||||
If no findings: output `NO FINDINGS` and nothing else.
|
||||
Do not output anything else — no preamble, no summary, no commentary.
|
||||
|
||||
Stack context: {STACK}
|
||||
Past learnings: {learnings or 'none'}
|
||||
|
||||
CHECKLIST:
|
||||
{checklist content}"
|
||||
|
||||
**Subagent configuration:**
|
||||
- Use `subagent_type: "general-purpose"`
|
||||
- Do NOT use `run_in_background` — all specialists must complete before merge
|
||||
- If any specialist subagent fails or times out, log the failure and continue with results from successful specialists. Specialists are additive — partial results are better than no results.
|
||||
|
||||
---
|
||||
|
||||
### Step 3.56: Collect and merge findings
|
||||
|
||||
After all specialist subagents complete, collect their outputs.
|
||||
|
||||
**Parse findings:**
|
||||
For each specialist's output:
|
||||
1. If output is "NO FINDINGS" — skip, this specialist found nothing
|
||||
2. Otherwise, parse each line as a JSON object. Skip lines that are not valid JSON.
|
||||
3. Collect all parsed findings into a single list, tagged with their specialist name.
|
||||
|
||||
**Fingerprint and deduplicate:**
|
||||
For each finding, compute its fingerprint:
|
||||
- If `fingerprint` field is present, use it
|
||||
- Otherwise: `{path}:{line}:{category}` (if line is present) or `{path}:{category}`
|
||||
|
||||
Group findings by fingerprint. For findings sharing the same fingerprint:
|
||||
- Keep the finding with the highest confidence score
|
||||
- Tag it: "MULTI-SPECIALIST CONFIRMED ({specialist1} + {specialist2})"
|
||||
- Boost confidence by +1 (cap at 10)
|
||||
- Note the confirming specialists in the output
|
||||
|
||||
**Apply confidence gates:**
|
||||
- Confidence 7+: show normally in the findings output
|
||||
- Confidence 5-6: show with caveat "Medium confidence — verify this is actually an issue"
|
||||
- Confidence 3-4: move to appendix (suppress from main findings)
|
||||
- Confidence 1-2: suppress entirely
|
||||
|
||||
**Compute PR Quality Score:**
|
||||
After merging, compute the quality score:
|
||||
`quality_score = max(0, 10 - (critical_count * 2 + informational_count * 0.5))`
|
||||
Cap at 10. Log this in the review result at the end.
|
||||
|
||||
**Output merged findings:**
|
||||
Present the merged findings in the same format as the current review:
|
||||
|
||||
```
|
||||
SPECIALIST REVIEW: N findings (X critical, Y informational) from Z specialists
|
||||
|
||||
[For each finding, in order: CRITICAL first, then INFORMATIONAL, sorted by confidence descending]
|
||||
[SEVERITY] (confidence: N/10, specialist: name) path:line — summary
|
||||
Fix: recommended fix
|
||||
[If MULTI-SPECIALIST CONFIRMED: show confirmation note]
|
||||
|
||||
PR Quality Score: X/10
|
||||
```
|
||||
|
||||
These findings flow into the Fix-First flow (item 4) alongside the checklist pass (Step 3.5).
|
||||
The Fix-First heuristic applies identically — specialist findings follow the same AUTO-FIX vs ASK classification.
|
||||
|
||||
**Compile per-specialist stats:**
|
||||
After merging findings, compile a `specialists` object for the review-log persist.
|
||||
For each specialist (testing, maintainability, security, performance, data-migration, api-contract, design, red-team):
|
||||
- If dispatched: `{"dispatched": true, "findings": N, "critical": N, "informational": N}`
|
||||
- If skipped by scope: `{"dispatched": false, "reason": "scope"}`
|
||||
- If skipped by gating: `{"dispatched": false, "reason": "gated"}`
|
||||
- If not applicable (e.g., red-team not activated): omit from the object
|
||||
|
||||
Include the Design specialist even though it uses `design-checklist.md` instead of the specialist schema files.
|
||||
Remember these stats — you will need them for the review-log entry in Step 5.8.
|
||||
|
||||
---
|
||||
|
||||
### Red Team dispatch (conditional)
|
||||
|
||||
**Activation:** Only if DIFF_LINES > 200 OR any specialist produced a CRITICAL finding.
|
||||
|
||||
If activated, dispatch one more subagent via the Agent tool (foreground, not background).
|
||||
|
||||
The Red Team subagent receives:
|
||||
1. The red-team checklist from `~/.claude/skills/gstack/review/specialists/red-team.md`
|
||||
2. The merged specialist findings from Step 3.56 (so it knows what was already caught)
|
||||
3. The git diff command
|
||||
|
||||
Prompt: "You are a red team reviewer. The code has already been reviewed by N specialists
|
||||
who found the following issues: {merged findings summary}. Your job is to find what they
|
||||
MISSED. Read the checklist, run `git diff origin/<base>`, and look for gaps.
|
||||
Output findings as JSON objects (same schema as the specialists). Focus on cross-cutting
|
||||
concerns, integration boundary issues, and failure modes that specialist checklists
|
||||
don't cover."
|
||||
|
||||
If the Red Team finds additional issues, merge them into the findings list before
|
||||
the Fix-First flow (item 4). Red Team findings are tagged with `"specialist":"red-team"`.
|
||||
|
||||
If the Red Team returns NO FINDINGS, note: "Red Team review: no additional issues found."
|
||||
If the Red Team subagent fails or times out, skip silently and continue.
|
||||
|
||||
### Step 3.57: Cross-review finding dedup
|
||||
|
||||
Before classifying findings, check if any were previously skipped by the user in a prior review on this branch.
|
||||
|
||||
```bash
|
||||
~/.claude/skills/gstack/bin/gstack-review-read
|
||||
```
|
||||
|
||||
Parse the output: only lines BEFORE `---CONFIG---` are JSONL entries (the output also contains `---CONFIG---` and `---HEAD---` footer sections that are not JSONL — ignore those).
|
||||
|
||||
For each JSONL entry that has a `findings` array:
|
||||
1. Collect all fingerprints where `action: "skipped"`
|
||||
2. Note the `commit` field from that entry
|
||||
|
||||
If skipped fingerprints exist, get the list of files changed since that review:
|
||||
|
||||
```bash
|
||||
git diff --name-only <prior-review-commit> HEAD
|
||||
```
|
||||
|
||||
For each current finding (from both the checklist pass (Step 3.5) and specialist review (Step 3.55-3.56)), check:
|
||||
- Does its fingerprint match a previously skipped finding?
|
||||
- Is the finding's file path NOT in the changed-files set?
|
||||
|
||||
If both conditions are true: suppress the finding. It was intentionally skipped and the relevant code hasn't changed.
|
||||
|
||||
Print: "Suppressed N findings from prior reviews (previously skipped by user)"
|
||||
|
||||
**Only suppress `skipped` findings — never `fixed` or `auto-fixed`** (those might regress and should be re-checked).
|
||||
|
||||
If no prior reviews exist or none have a `findings` array, skip this step silently.
|
||||
|
||||
Output a summary header: `Pre-Landing Review: N issues (X critical, Y informational)`
|
||||
|
||||
4. **Classify each finding from both the checklist pass and specialist review (Step 3.55-3.56) as AUTO-FIX or ASK** per the Fix-First Heuristic in
|
||||
checklist.md. Critical findings lean toward ASK; informational lean toward AUTO-FIX.
|
||||
|
||||
5. **Auto-fix all AUTO-FIX items.** Apply each fix. Output one line per fix:
|
||||
@@ -1671,10 +1927,13 @@ Present Codex output under a `CODEX (design):` header, merged with the checklist
|
||||
|
||||
9. Persist the review result to the review log:
|
||||
```bash
|
||||
~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"review","timestamp":"TIMESTAMP","status":"STATUS","issues_found":N,"critical":N,"informational":N,"commit":"'"$(git rev-parse --short HEAD)"'","via":"ship"}'
|
||||
~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"review","timestamp":"TIMESTAMP","status":"STATUS","issues_found":N,"critical":N,"informational":N,"quality_score":SCORE,"specialists":SPECIALISTS_JSON,"findings":FINDINGS_JSON,"commit":"'"$(git rev-parse --short HEAD)"'","via":"ship"}'
|
||||
```
|
||||
Substitute TIMESTAMP (ISO 8601), STATUS ("clean" if no issues, "issues_found" otherwise),
|
||||
and N values from the summary counts above. The `via:"ship"` distinguishes from standalone `/review` runs.
|
||||
- `quality_score` = the PR Quality Score computed in Step 3.56 (e.g., 7.5). If specialists were skipped (small diff), use `10.0`
|
||||
- `specialists` = the per-specialist stats object compiled in Step 3.56. Each specialist that was considered gets an entry: `{"dispatched":true/false,"findings":N,"critical":N,"informational":N}` if dispatched, or `{"dispatched":false,"reason":"scope|gated"}` if skipped. Example: `{"testing":{"dispatched":true,"findings":2,"critical":0,"informational":2},"security":{"dispatched":false,"reason":"scope"}}`
|
||||
- `findings` = array of per-finding records. For each finding (from checklist pass and specialists), include: `{"fingerprint":"path:line:category","severity":"CRITICAL|INFORMATIONAL","action":"ACTION"}`. ACTION is `"auto-fixed"`, `"fixed"` (user approved), or `"skipped"` (user chose Skip).
|
||||
|
||||
Save the review output — it goes into the PR body in Step 8.
|
||||
|
||||
@@ -1880,7 +2139,7 @@ echo "BASE: $BASE_VERSION HEAD: $CURRENT_VERSION"
|
||||
if [ "$CURRENT_VERSION" != "$BASE_VERSION" ]; then echo "ALREADY_BUMPED"; fi
|
||||
```
|
||||
|
||||
If output shows `ALREADY_BUMPED`, VERSION was already bumped on this branch (prior `/ship` run). Skip the rest of Step 4 and use the current VERSION. Otherwise proceed with the bump.
|
||||
If output shows `ALREADY_BUMPED`, VERSION was already bumped on this branch (prior `/ship` run). Skip the bump action (do not modify VERSION), but read the current VERSION value — it is needed for CHANGELOG and PR body. Continue to the next step. Otherwise proceed with the bump.
|
||||
|
||||
1. Read the current `VERSION` file (4-digit format: `MAJOR.MINOR.PATCH.MICRO`)
|
||||
|
||||
@@ -2071,7 +2330,7 @@ echo "LOCAL: $LOCAL REMOTE: $REMOTE"
|
||||
[ "$LOCAL" = "$REMOTE" ] && echo "ALREADY_PUSHED" || echo "PUSH_NEEDED"
|
||||
```
|
||||
|
||||
If `ALREADY_PUSHED`, skip the push. Otherwise push with upstream tracking:
|
||||
If `ALREADY_PUSHED`, skip the push but continue to Step 8. Otherwise push with upstream tracking:
|
||||
|
||||
```bash
|
||||
git push -u origin <branch-name>
|
||||
@@ -2093,7 +2352,7 @@ gh pr view --json url,number,state -q 'if .state == "OPEN" then "PR #\(.number):
|
||||
glab mr view -F json 2>/dev/null | jq -r 'if .state == "opened" then "MR_EXISTS" else "NO_MR" end' 2>/dev/null || echo "NO_MR"
|
||||
```
|
||||
|
||||
If an **open** PR/MR already exists: **update** the PR body with the latest test results, coverage, and review findings using `gh pr edit --body "..."` (GitHub) or `glab mr update -d "..."` (GitLab). Print the existing URL and continue to Step 8.5.
|
||||
If an **open** PR/MR already exists: **update** the PR body using `gh pr edit --body "..."` (GitHub) or `glab mr update -d "..."` (GitLab). Always regenerate the PR body from scratch using this run's fresh results (test output, coverage audit, review findings, adversarial review, TODOS summary). Never reuse stale PR body content from a prior run. Print the existing URL and continue to Step 8.5.
|
||||
|
||||
If no PR/MR exists: create a pull request (GitHub) or merge request (GitLab) using the platform detected in Step 0.
|
||||
|
||||
@@ -2198,6 +2457,8 @@ execute its full workflow:
|
||||
This step is automatic. Do not ask the user for confirmation. The goal is zero-friction
|
||||
doc updates — the user runs `/ship` and documentation stays current without a separate command.
|
||||
|
||||
If Step 8.5 created a docs commit, re-edit the PR/MR body to include the latest commit SHA in the summary. This ensures the PR body reflects the truly final state after document-release.
|
||||
|
||||
---
|
||||
|
||||
## Step 8.75: Persist ship metrics
|
||||
|
||||
+65
-5
@@ -80,6 +80,8 @@ fi
|
||||
_ROUTING_DECLINED=$($GSTACK_BIN/gstack-config get routing_declined 2>/dev/null || echo "false")
|
||||
echo "HAS_ROUTING: $_HAS_ROUTING"
|
||||
echo "ROUTING_DECLINED: $_ROUTING_DECLINED"
|
||||
# Detect spawned session (OpenClaw or other orchestrator)
|
||||
[ -n "$OPENCLAW_SESSION" ] && echo "SPAWNED_SESSION: true" || true
|
||||
```
|
||||
|
||||
If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
|
||||
@@ -206,6 +208,13 @@ Say "No problem. You can add routing rules later by running `gstack-config set r
|
||||
|
||||
This only happens once per project. If `HAS_ROUTING` is `yes` or `ROUTING_DECLINED` is `true`, skip this entirely.
|
||||
|
||||
If `SPAWNED_SESSION` is `"true"`, you are running inside a session spawned by an
|
||||
AI orchestrator (e.g., OpenClaw). In spawned sessions:
|
||||
- Do NOT use AskUserQuestion for interactive prompts. Auto-choose the recommended option.
|
||||
- Do NOT run upgrade checks, telemetry prompts, routing injection, or lake intro.
|
||||
- Focus on completing the task and reporting results via prose output.
|
||||
- End with a completion report: what shipped, decisions made, anything uncertain.
|
||||
|
||||
## Voice
|
||||
|
||||
You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
|
||||
@@ -565,6 +574,16 @@ You are running the `/ship` workflow. This is a **non-interactive, fully automat
|
||||
- Auto-fixable review findings (dead code, N+1, stale comments — fixed automatically)
|
||||
- Test coverage gaps within target threshold (auto-generate and commit, or flag in PR body)
|
||||
|
||||
**Re-run behavior (idempotency):**
|
||||
Re-running `/ship` means "run the whole checklist again." Every verification step
|
||||
(tests, coverage audit, plan completion, pre-landing review, adversarial review,
|
||||
VERSION/CHANGELOG check, TODOS, document-release) runs on every invocation.
|
||||
Only *actions* are idempotent:
|
||||
- Step 4: If VERSION already bumped, skip the bump but still read the version
|
||||
- Step 7: If already pushed, skip the push command
|
||||
- Step 8: If PR exists, update the body instead of creating a new PR
|
||||
Never skip a verification step because a prior `/ship` run already performed it.
|
||||
|
||||
---
|
||||
|
||||
## Step 1: Pre-flight
|
||||
@@ -1593,7 +1612,43 @@ Substitute: TIMESTAMP = ISO 8601 datetime, STATUS = "clean" if 0 findings or "is
|
||||
|
||||
Include any design findings alongside the code review findings. They follow the same Fix-First flow below.
|
||||
|
||||
4. **Classify each finding as AUTO-FIX or ASK** per the Fix-First Heuristic in
|
||||
|
||||
|
||||
### Step 3.57: Cross-review finding dedup
|
||||
|
||||
Before classifying findings, check if any were previously skipped by the user in a prior review on this branch.
|
||||
|
||||
```bash
|
||||
$GSTACK_ROOT/bin/gstack-review-read
|
||||
```
|
||||
|
||||
Parse the output: only lines BEFORE `---CONFIG---` are JSONL entries (the output also contains `---CONFIG---` and `---HEAD---` footer sections that are not JSONL — ignore those).
|
||||
|
||||
For each JSONL entry that has a `findings` array:
|
||||
1. Collect all fingerprints where `action: "skipped"`
|
||||
2. Note the `commit` field from that entry
|
||||
|
||||
If skipped fingerprints exist, get the list of files changed since that review:
|
||||
|
||||
```bash
|
||||
git diff --name-only <prior-review-commit> HEAD
|
||||
```
|
||||
|
||||
For each current finding (from both the checklist pass (Step 3.5) and specialist review (Step 3.55-3.56)), check:
|
||||
- Does its fingerprint match a previously skipped finding?
|
||||
- Is the finding's file path NOT in the changed-files set?
|
||||
|
||||
If both conditions are true: suppress the finding. It was intentionally skipped and the relevant code hasn't changed.
|
||||
|
||||
Print: "Suppressed N findings from prior reviews (previously skipped by user)"
|
||||
|
||||
**Only suppress `skipped` findings — never `fixed` or `auto-fixed`** (those might regress and should be re-checked).
|
||||
|
||||
If no prior reviews exist or none have a `findings` array, skip this step silently.
|
||||
|
||||
Output a summary header: `Pre-Landing Review: N issues (X critical, Y informational)`
|
||||
|
||||
4. **Classify each finding from both the checklist pass and specialist review (Step 3.55-3.56) as AUTO-FIX or ASK** per the Fix-First Heuristic in
|
||||
checklist.md. Critical findings lean toward ASK; informational lean toward AUTO-FIX.
|
||||
|
||||
5. **Auto-fix all AUTO-FIX items.** Apply each fix. Output one line per fix:
|
||||
@@ -1615,10 +1670,13 @@ Substitute: TIMESTAMP = ISO 8601 datetime, STATUS = "clean" if 0 findings or "is
|
||||
|
||||
9. Persist the review result to the review log:
|
||||
```bash
|
||||
$GSTACK_ROOT/bin/gstack-review-log '{"skill":"review","timestamp":"TIMESTAMP","status":"STATUS","issues_found":N,"critical":N,"informational":N,"commit":"'"$(git rev-parse --short HEAD)"'","via":"ship"}'
|
||||
$GSTACK_ROOT/bin/gstack-review-log '{"skill":"review","timestamp":"TIMESTAMP","status":"STATUS","issues_found":N,"critical":N,"informational":N,"quality_score":SCORE,"specialists":SPECIALISTS_JSON,"findings":FINDINGS_JSON,"commit":"'"$(git rev-parse --short HEAD)"'","via":"ship"}'
|
||||
```
|
||||
Substitute TIMESTAMP (ISO 8601), STATUS ("clean" if no issues, "issues_found" otherwise),
|
||||
and N values from the summary counts above. The `via:"ship"` distinguishes from standalone `/review` runs.
|
||||
- `quality_score` = the PR Quality Score computed in Step 3.56 (e.g., 7.5). If specialists were skipped (small diff), use `10.0`
|
||||
- `specialists` = the per-specialist stats object compiled in Step 3.56. Each specialist that was considered gets an entry: `{"dispatched":true/false,"findings":N,"critical":N,"informational":N}` if dispatched, or `{"dispatched":false,"reason":"scope|gated"}` if skipped. Example: `{"testing":{"dispatched":true,"findings":2,"critical":0,"informational":2},"security":{"dispatched":false,"reason":"scope"}}`
|
||||
- `findings` = array of per-finding records. For each finding (from checklist pass and specialists), include: `{"fingerprint":"path:line:category","severity":"CRITICAL|INFORMATIONAL","action":"ACTION"}`. ACTION is `"auto-fixed"`, `"fixed"` (user approved), or `"skipped"` (user chose Skip).
|
||||
|
||||
Save the review output — it goes into the PR body in Step 8.
|
||||
|
||||
@@ -1701,7 +1759,7 @@ echo "BASE: $BASE_VERSION HEAD: $CURRENT_VERSION"
|
||||
if [ "$CURRENT_VERSION" != "$BASE_VERSION" ]; then echo "ALREADY_BUMPED"; fi
|
||||
```
|
||||
|
||||
If output shows `ALREADY_BUMPED`, VERSION was already bumped on this branch (prior `/ship` run). Skip the rest of Step 4 and use the current VERSION. Otherwise proceed with the bump.
|
||||
If output shows `ALREADY_BUMPED`, VERSION was already bumped on this branch (prior `/ship` run). Skip the bump action (do not modify VERSION), but read the current VERSION value — it is needed for CHANGELOG and PR body. Continue to the next step. Otherwise proceed with the bump.
|
||||
|
||||
1. Read the current `VERSION` file (4-digit format: `MAJOR.MINOR.PATCH.MICRO`)
|
||||
|
||||
@@ -1892,7 +1950,7 @@ echo "LOCAL: $LOCAL REMOTE: $REMOTE"
|
||||
[ "$LOCAL" = "$REMOTE" ] && echo "ALREADY_PUSHED" || echo "PUSH_NEEDED"
|
||||
```
|
||||
|
||||
If `ALREADY_PUSHED`, skip the push. Otherwise push with upstream tracking:
|
||||
If `ALREADY_PUSHED`, skip the push but continue to Step 8. Otherwise push with upstream tracking:
|
||||
|
||||
```bash
|
||||
git push -u origin <branch-name>
|
||||
@@ -1914,7 +1972,7 @@ gh pr view --json url,number,state -q 'if .state == "OPEN" then "PR #\(.number):
|
||||
glab mr view -F json 2>/dev/null | jq -r 'if .state == "opened" then "MR_EXISTS" else "NO_MR" end' 2>/dev/null || echo "NO_MR"
|
||||
```
|
||||
|
||||
If an **open** PR/MR already exists: **update** the PR body with the latest test results, coverage, and review findings using `gh pr edit --body "..."` (GitHub) or `glab mr update -d "..."` (GitLab). Print the existing URL and continue to Step 8.5.
|
||||
If an **open** PR/MR already exists: **update** the PR body using `gh pr edit --body "..."` (GitHub) or `glab mr update -d "..."` (GitLab). Always regenerate the PR body from scratch using this run's fresh results (test output, coverage audit, review findings, adversarial review, TODOS summary). Never reuse stale PR body content from a prior run. Print the existing URL and continue to Step 8.5.
|
||||
|
||||
If no PR/MR exists: create a pull request (GitHub) or merge request (GitLab) using the platform detected in Step 0.
|
||||
|
||||
@@ -2019,6 +2077,8 @@ execute its full workflow:
|
||||
This step is automatic. Do not ask the user for confirmation. The goal is zero-friction
|
||||
doc updates — the user runs `/ship` and documentation stays current without a separate command.
|
||||
|
||||
If Step 8.5 created a docs commit, re-edit the PR/MR body to include the latest commit SHA in the summary. This ensures the PR body reflects the truly final state after document-release.
|
||||
|
||||
---
|
||||
|
||||
## Step 8.75: Persist ship metrics
|
||||
|
||||
+266
-5
@@ -82,6 +82,8 @@ fi
|
||||
_ROUTING_DECLINED=$($GSTACK_BIN/gstack-config get routing_declined 2>/dev/null || echo "false")
|
||||
echo "HAS_ROUTING: $_HAS_ROUTING"
|
||||
echo "ROUTING_DECLINED: $_ROUTING_DECLINED"
|
||||
# Detect spawned session (OpenClaw or other orchestrator)
|
||||
[ -n "$OPENCLAW_SESSION" ] && echo "SPAWNED_SESSION: true" || true
|
||||
```
|
||||
|
||||
If `PROACTIVE` is `"false"`, do not proactively suggest gstack skills AND do not
|
||||
@@ -208,6 +210,13 @@ Say "No problem. You can add routing rules later by running `gstack-config set r
|
||||
|
||||
This only happens once per project. If `HAS_ROUTING` is `yes` or `ROUTING_DECLINED` is `true`, skip this entirely.
|
||||
|
||||
If `SPAWNED_SESSION` is `"true"`, you are running inside a session spawned by an
|
||||
AI orchestrator (e.g., OpenClaw). In spawned sessions:
|
||||
- Do NOT use AskUserQuestion for interactive prompts. Auto-choose the recommended option.
|
||||
- Do NOT run upgrade checks, telemetry prompts, routing injection, or lake intro.
|
||||
- Focus on completing the task and reporting results via prose output.
|
||||
- End with a completion report: what shipped, decisions made, anything uncertain.
|
||||
|
||||
## Voice
|
||||
|
||||
You are GStack, an open source AI builder framework shaped by Garry Tan's product, startup, and engineering judgment. Encode how he thinks, not his biography.
|
||||
@@ -567,6 +576,16 @@ You are running the `/ship` workflow. This is a **non-interactive, fully automat
|
||||
- Auto-fixable review findings (dead code, N+1, stale comments — fixed automatically)
|
||||
- Test coverage gaps within target threshold (auto-generate and commit, or flag in PR body)
|
||||
|
||||
**Re-run behavior (idempotency):**
|
||||
Re-running `/ship` means "run the whole checklist again." Every verification step
|
||||
(tests, coverage audit, plan completion, pre-landing review, adversarial review,
|
||||
VERSION/CHANGELOG check, TODOS, document-release) runs on every invocation.
|
||||
Only *actions* are idempotent:
|
||||
- Step 4: If VERSION already bumped, skip the bump but still read the version
|
||||
- Step 7: If already pushed, skip the push command
|
||||
- Step 8: If PR exists, update the body instead of creating a new PR
|
||||
Never skip a verification step because a prior `/ship` run already performed it.
|
||||
|
||||
---
|
||||
|
||||
## Step 1: Pre-flight
|
||||
@@ -1645,7 +1664,244 @@ Present Codex output under a `CODEX (design):` header, merged with the checklist
|
||||
|
||||
Include any design findings alongside the code review findings. They follow the same Fix-First flow below.
|
||||
|
||||
4. **Classify each finding as AUTO-FIX or ASK** per the Fix-First Heuristic in
|
||||
## Step 3.55: Review Army — Specialist Dispatch
|
||||
|
||||
### Detect stack and scope
|
||||
|
||||
```bash
|
||||
source <($GSTACK_BIN/gstack-diff-scope <base> 2>/dev/null) || true
|
||||
# Detect stack for specialist context
|
||||
STACK=""
|
||||
[ -f Gemfile ] && STACK="${STACK}ruby "
|
||||
[ -f package.json ] && STACK="${STACK}node "
|
||||
[ -f requirements.txt ] || [ -f pyproject.toml ] && STACK="${STACK}python "
|
||||
[ -f go.mod ] && STACK="${STACK}go "
|
||||
[ -f Cargo.toml ] && STACK="${STACK}rust "
|
||||
echo "STACK: ${STACK:-unknown}"
|
||||
DIFF_INS=$(git diff origin/<base> --stat | tail -1 | grep -oE '[0-9]+ insertion' | grep -oE '[0-9]+' || echo "0")
|
||||
DIFF_DEL=$(git diff origin/<base> --stat | tail -1 | grep -oE '[0-9]+ deletion' | grep -oE '[0-9]+' || echo "0")
|
||||
DIFF_LINES=$((DIFF_INS + DIFF_DEL))
|
||||
echo "DIFF_LINES: $DIFF_LINES"
|
||||
# Detect test framework for specialist test stub generation
|
||||
TEST_FW=""
|
||||
{ [ -f jest.config.ts ] || [ -f jest.config.js ]; } && TEST_FW="jest"
|
||||
[ -f vitest.config.ts ] && TEST_FW="vitest"
|
||||
{ [ -f spec/spec_helper.rb ] || [ -f .rspec ]; } && TEST_FW="rspec"
|
||||
{ [ -f pytest.ini ] || [ -f conftest.py ]; } && TEST_FW="pytest"
|
||||
[ -f go.mod ] && TEST_FW="go-test"
|
||||
echo "TEST_FW: ${TEST_FW:-unknown}"
|
||||
```
|
||||
|
||||
### Read specialist hit rates (adaptive gating)
|
||||
|
||||
```bash
|
||||
$GSTACK_BIN/gstack-specialist-stats 2>/dev/null || true
|
||||
```
|
||||
|
||||
### Select specialists
|
||||
|
||||
Based on the scope signals above, select which specialists to dispatch.
|
||||
|
||||
**Always-on (dispatch on every review with 50+ changed lines):**
|
||||
1. **Testing** — read `$GSTACK_ROOT/review/specialists/testing.md`
|
||||
2. **Maintainability** — read `$GSTACK_ROOT/review/specialists/maintainability.md`
|
||||
|
||||
**If DIFF_LINES < 50:** Skip all specialists. Print: "Small diff ($DIFF_LINES lines) — specialists skipped." Continue to the Fix-First flow (item 4).
|
||||
|
||||
**Conditional (dispatch if the matching scope signal is true):**
|
||||
3. **Security** — if SCOPE_AUTH=true, OR if SCOPE_BACKEND=true AND DIFF_LINES > 100. Read `$GSTACK_ROOT/review/specialists/security.md`
|
||||
4. **Performance** — if SCOPE_BACKEND=true OR SCOPE_FRONTEND=true. Read `$GSTACK_ROOT/review/specialists/performance.md`
|
||||
5. **Data Migration** — if SCOPE_MIGRATIONS=true. Read `$GSTACK_ROOT/review/specialists/data-migration.md`
|
||||
6. **API Contract** — if SCOPE_API=true. Read `$GSTACK_ROOT/review/specialists/api-contract.md`
|
||||
7. **Design** — if SCOPE_FRONTEND=true. Use the existing design review checklist at `$GSTACK_ROOT/review/design-checklist.md`
|
||||
|
||||
### Adaptive gating
|
||||
|
||||
After scope-based selection, apply adaptive gating based on specialist hit rates:
|
||||
|
||||
For each conditional specialist that passed scope gating, check the `gstack-specialist-stats` output above:
|
||||
- If tagged `[GATE_CANDIDATE]` (0 findings in 10+ dispatches): skip it. Print: "[specialist] auto-gated (0 findings in N reviews)."
|
||||
- If tagged `[NEVER_GATE]`: always dispatch regardless of hit rate. Security and data-migration are insurance policy specialists — they should run even when silent.
|
||||
|
||||
**Force flags:** If the user's prompt includes `--security`, `--performance`, `--testing`, `--maintainability`, `--data-migration`, `--api-contract`, `--design`, or `--all-specialists`, force-include that specialist regardless of gating.
|
||||
|
||||
Note which specialists were selected, gated, and skipped. Print the selection:
|
||||
"Dispatching N specialists: [names]. Skipped: [names] (scope not detected). Gated: [names] (0 findings in N+ reviews)."
|
||||
|
||||
---
|
||||
|
||||
### Dispatch specialists in parallel
|
||||
|
||||
For each selected specialist, launch an independent subagent via the Agent tool.
|
||||
**Launch ALL selected specialists in a single message** (multiple Agent tool calls)
|
||||
so they run in parallel. Each subagent has fresh context — no prior review bias.
|
||||
|
||||
**Each specialist subagent prompt:**
|
||||
|
||||
Construct the prompt for each specialist. The prompt includes:
|
||||
|
||||
1. The specialist's checklist content (you already read the file above)
|
||||
2. Stack context: "This is a {STACK} project."
|
||||
3. Past learnings for this domain (if any exist):
|
||||
|
||||
```bash
|
||||
$GSTACK_BIN/gstack-learnings-search --type pitfall --query "{specialist domain}" --limit 5 2>/dev/null || true
|
||||
```
|
||||
|
||||
If learnings are found, include them: "Past learnings for this domain: {learnings}"
|
||||
|
||||
4. Instructions:
|
||||
|
||||
"You are a specialist code reviewer. Read the checklist below, then run
|
||||
`git diff origin/<base>` to get the full diff. Apply the checklist against the diff.
|
||||
|
||||
For each finding, output a JSON object on its own line:
|
||||
{\"severity\":\"CRITICAL|INFORMATIONAL\",\"confidence\":N,\"path\":\"file\",\"line\":N,\"category\":\"category\",\"summary\":\"description\",\"fix\":\"recommended fix\",\"fingerprint\":\"path:line:category\",\"specialist\":\"name\"}
|
||||
|
||||
Required fields: severity, confidence, path, category, summary, specialist.
|
||||
Optional: line, fix, fingerprint, evidence, test_stub.
|
||||
|
||||
If you can write a test that would catch this issue, include it in the `test_stub` field.
|
||||
Use the detected test framework ({TEST_FW}). Write a minimal skeleton — describe/it/test
|
||||
blocks with clear intent. Skip test_stub for architectural or design-only findings.
|
||||
|
||||
If no findings: output `NO FINDINGS` and nothing else.
|
||||
Do not output anything else — no preamble, no summary, no commentary.
|
||||
|
||||
Stack context: {STACK}
|
||||
Past learnings: {learnings or 'none'}
|
||||
|
||||
CHECKLIST:
|
||||
{checklist content}"
|
||||
|
||||
**Subagent configuration:**
|
||||
- Use `subagent_type: "general-purpose"`
|
||||
- Do NOT use `run_in_background` — all specialists must complete before merge
|
||||
- If any specialist subagent fails or times out, log the failure and continue with results from successful specialists. Specialists are additive — partial results are better than no results.
|
||||
|
||||
---
|
||||
|
||||
### Step 3.56: Collect and merge findings
|
||||
|
||||
After all specialist subagents complete, collect their outputs.
|
||||
|
||||
**Parse findings:**
|
||||
For each specialist's output:
|
||||
1. If output is "NO FINDINGS" — skip, this specialist found nothing
|
||||
2. Otherwise, parse each line as a JSON object. Skip lines that are not valid JSON.
|
||||
3. Collect all parsed findings into a single list, tagged with their specialist name.
|
||||
|
||||
**Fingerprint and deduplicate:**
|
||||
For each finding, compute its fingerprint:
|
||||
- If `fingerprint` field is present, use it
|
||||
- Otherwise: `{path}:{line}:{category}` (if line is present) or `{path}:{category}`
|
||||
|
||||
Group findings by fingerprint. For findings sharing the same fingerprint:
|
||||
- Keep the finding with the highest confidence score
|
||||
- Tag it: "MULTI-SPECIALIST CONFIRMED ({specialist1} + {specialist2})"
|
||||
- Boost confidence by +1 (cap at 10)
|
||||
- Note the confirming specialists in the output
|
||||
|
||||
**Apply confidence gates:**
|
||||
- Confidence 7+: show normally in the findings output
|
||||
- Confidence 5-6: show with caveat "Medium confidence — verify this is actually an issue"
|
||||
- Confidence 3-4: move to appendix (suppress from main findings)
|
||||
- Confidence 1-2: suppress entirely
|
||||
|
||||
**Compute PR Quality Score:**
|
||||
After merging, compute the quality score:
|
||||
`quality_score = max(0, 10 - (critical_count * 2 + informational_count * 0.5))`
|
||||
Cap at 10. Log this in the review result at the end.
|
||||
|
||||
**Output merged findings:**
|
||||
Present the merged findings in the same format as the current review:
|
||||
|
||||
```
|
||||
SPECIALIST REVIEW: N findings (X critical, Y informational) from Z specialists
|
||||
|
||||
[For each finding, in order: CRITICAL first, then INFORMATIONAL, sorted by confidence descending]
|
||||
[SEVERITY] (confidence: N/10, specialist: name) path:line — summary
|
||||
Fix: recommended fix
|
||||
[If MULTI-SPECIALIST CONFIRMED: show confirmation note]
|
||||
|
||||
PR Quality Score: X/10
|
||||
```
|
||||
|
||||
These findings flow into the Fix-First flow (item 4) alongside the checklist pass (Step 3.5).
|
||||
The Fix-First heuristic applies identically — specialist findings follow the same AUTO-FIX vs ASK classification.
|
||||
|
||||
**Compile per-specialist stats:**
|
||||
After merging findings, compile a `specialists` object for the review-log persist.
|
||||
For each specialist (testing, maintainability, security, performance, data-migration, api-contract, design, red-team):
|
||||
- If dispatched: `{"dispatched": true, "findings": N, "critical": N, "informational": N}`
|
||||
- If skipped by scope: `{"dispatched": false, "reason": "scope"}`
|
||||
- If skipped by gating: `{"dispatched": false, "reason": "gated"}`
|
||||
- If not applicable (e.g., red-team not activated): omit from the object
|
||||
|
||||
Include the Design specialist even though it uses `design-checklist.md` instead of the specialist schema files.
|
||||
Remember these stats — you will need them for the review-log entry in Step 5.8.
|
||||
|
||||
---
|
||||
|
||||
### Red Team dispatch (conditional)
|
||||
|
||||
**Activation:** Only if DIFF_LINES > 200 OR any specialist produced a CRITICAL finding.
|
||||
|
||||
If activated, dispatch one more subagent via the Agent tool (foreground, not background).
|
||||
|
||||
The Red Team subagent receives:
|
||||
1. The red-team checklist from `$GSTACK_ROOT/review/specialists/red-team.md`
|
||||
2. The merged specialist findings from Step 3.56 (so it knows what was already caught)
|
||||
3. The git diff command
|
||||
|
||||
Prompt: "You are a red team reviewer. The code has already been reviewed by N specialists
|
||||
who found the following issues: {merged findings summary}. Your job is to find what they
|
||||
MISSED. Read the checklist, run `git diff origin/<base>`, and look for gaps.
|
||||
Output findings as JSON objects (same schema as the specialists). Focus on cross-cutting
|
||||
concerns, integration boundary issues, and failure modes that specialist checklists
|
||||
don't cover."
|
||||
|
||||
If the Red Team finds additional issues, merge them into the findings list before
|
||||
the Fix-First flow (item 4). Red Team findings are tagged with `"specialist":"red-team"`.
|
||||
|
||||
If the Red Team returns NO FINDINGS, note: "Red Team review: no additional issues found."
|
||||
If the Red Team subagent fails or times out, skip silently and continue.
|
||||
|
||||
### Step 3.57: Cross-review finding dedup
|
||||
|
||||
Before classifying findings, check if any were previously skipped by the user in a prior review on this branch.
|
||||
|
||||
```bash
|
||||
$GSTACK_ROOT/bin/gstack-review-read
|
||||
```
|
||||
|
||||
Parse the output: only lines BEFORE `---CONFIG---` are JSONL entries (the output also contains `---CONFIG---` and `---HEAD---` footer sections that are not JSONL — ignore those).
|
||||
|
||||
For each JSONL entry that has a `findings` array:
|
||||
1. Collect all fingerprints where `action: "skipped"`
|
||||
2. Note the `commit` field from that entry
|
||||
|
||||
If skipped fingerprints exist, get the list of files changed since that review:
|
||||
|
||||
```bash
|
||||
git diff --name-only <prior-review-commit> HEAD
|
||||
```
|
||||
|
||||
For each current finding (from both the checklist pass (Step 3.5) and specialist review (Step 3.55-3.56)), check:
|
||||
- Does its fingerprint match a previously skipped finding?
|
||||
- Is the finding's file path NOT in the changed-files set?
|
||||
|
||||
If both conditions are true: suppress the finding. It was intentionally skipped and the relevant code hasn't changed.
|
||||
|
||||
Print: "Suppressed N findings from prior reviews (previously skipped by user)"
|
||||
|
||||
**Only suppress `skipped` findings — never `fixed` or `auto-fixed`** (those might regress and should be re-checked).
|
||||
|
||||
If no prior reviews exist or none have a `findings` array, skip this step silently.
|
||||
|
||||
Output a summary header: `Pre-Landing Review: N issues (X critical, Y informational)`
|
||||
|
||||
4. **Classify each finding from both the checklist pass and specialist review (Step 3.55-3.56) as AUTO-FIX or ASK** per the Fix-First Heuristic in
|
||||
checklist.md. Critical findings lean toward ASK; informational lean toward AUTO-FIX.
|
||||
|
||||
5. **Auto-fix all AUTO-FIX items.** Apply each fix. Output one line per fix:
|
||||
@@ -1667,10 +1923,13 @@ Present Codex output under a `CODEX (design):` header, merged with the checklist
|
||||
|
||||
9. Persist the review result to the review log:
|
||||
```bash
|
||||
$GSTACK_ROOT/bin/gstack-review-log '{"skill":"review","timestamp":"TIMESTAMP","status":"STATUS","issues_found":N,"critical":N,"informational":N,"commit":"'"$(git rev-parse --short HEAD)"'","via":"ship"}'
|
||||
$GSTACK_ROOT/bin/gstack-review-log '{"skill":"review","timestamp":"TIMESTAMP","status":"STATUS","issues_found":N,"critical":N,"informational":N,"quality_score":SCORE,"specialists":SPECIALISTS_JSON,"findings":FINDINGS_JSON,"commit":"'"$(git rev-parse --short HEAD)"'","via":"ship"}'
|
||||
```
|
||||
Substitute TIMESTAMP (ISO 8601), STATUS ("clean" if no issues, "issues_found" otherwise),
|
||||
and N values from the summary counts above. The `via:"ship"` distinguishes from standalone `/review` runs.
|
||||
- `quality_score` = the PR Quality Score computed in Step 3.56 (e.g., 7.5). If specialists were skipped (small diff), use `10.0`
|
||||
- `specialists` = the per-specialist stats object compiled in Step 3.56. Each specialist that was considered gets an entry: `{"dispatched":true/false,"findings":N,"critical":N,"informational":N}` if dispatched, or `{"dispatched":false,"reason":"scope|gated"}` if skipped. Example: `{"testing":{"dispatched":true,"findings":2,"critical":0,"informational":2},"security":{"dispatched":false,"reason":"scope"}}`
|
||||
- `findings` = array of per-finding records. For each finding (from checklist pass and specialists), include: `{"fingerprint":"path:line:category","severity":"CRITICAL|INFORMATIONAL","action":"ACTION"}`. ACTION is `"auto-fixed"`, `"fixed"` (user approved), or `"skipped"` (user chose Skip).
|
||||
|
||||
Save the review output — it goes into the PR body in Step 8.
|
||||
|
||||
@@ -1876,7 +2135,7 @@ echo "BASE: $BASE_VERSION HEAD: $CURRENT_VERSION"
|
||||
if [ "$CURRENT_VERSION" != "$BASE_VERSION" ]; then echo "ALREADY_BUMPED"; fi
|
||||
```
|
||||
|
||||
If output shows `ALREADY_BUMPED`, VERSION was already bumped on this branch (prior `/ship` run). Skip the rest of Step 4 and use the current VERSION. Otherwise proceed with the bump.
|
||||
If output shows `ALREADY_BUMPED`, VERSION was already bumped on this branch (prior `/ship` run). Skip the bump action (do not modify VERSION), but read the current VERSION value — it is needed for CHANGELOG and PR body. Continue to the next step. Otherwise proceed with the bump.
|
||||
|
||||
1. Read the current `VERSION` file (4-digit format: `MAJOR.MINOR.PATCH.MICRO`)
|
||||
|
||||
@@ -2067,7 +2326,7 @@ echo "LOCAL: $LOCAL REMOTE: $REMOTE"
|
||||
[ "$LOCAL" = "$REMOTE" ] && echo "ALREADY_PUSHED" || echo "PUSH_NEEDED"
|
||||
```
|
||||
|
||||
If `ALREADY_PUSHED`, skip the push. Otherwise push with upstream tracking:
|
||||
If `ALREADY_PUSHED`, skip the push but continue to Step 8. Otherwise push with upstream tracking:
|
||||
|
||||
```bash
|
||||
git push -u origin <branch-name>
|
||||
@@ -2089,7 +2348,7 @@ gh pr view --json url,number,state -q 'if .state == "OPEN" then "PR #\(.number):
|
||||
glab mr view -F json 2>/dev/null | jq -r 'if .state == "opened" then "MR_EXISTS" else "NO_MR" end' 2>/dev/null || echo "NO_MR"
|
||||
```
|
||||
|
||||
If an **open** PR/MR already exists: **update** the PR body with the latest test results, coverage, and review findings using `gh pr edit --body "..."` (GitHub) or `glab mr update -d "..."` (GitLab). Print the existing URL and continue to Step 8.5.
|
||||
If an **open** PR/MR already exists: **update** the PR body using `gh pr edit --body "..."` (GitHub) or `glab mr update -d "..."` (GitLab). Always regenerate the PR body from scratch using this run's fresh results (test output, coverage audit, review findings, adversarial review, TODOS summary). Never reuse stale PR body content from a prior run. Print the existing URL and continue to Step 8.5.
|
||||
|
||||
If no PR/MR exists: create a pull request (GitHub) or merge request (GitLab) using the platform detected in Step 0.
|
||||
|
||||
@@ -2194,6 +2453,8 @@ execute its full workflow:
|
||||
This step is automatic. Do not ask the user for confirmation. The goal is zero-friction
|
||||
doc updates — the user runs `/ship` and documentation stays current without a separate command.
|
||||
|
||||
If Step 8.5 created a docs commit, re-edit the PR/MR body to include the latest commit SHA in the summary. This ensures the PR body reflects the truly final state after document-release.
|
||||
|
||||
---
|
||||
|
||||
## Step 8.75: Persist ship metrics
|
||||
|
||||
@@ -749,6 +749,22 @@ describe('TEST_COVERAGE_AUDIT placeholders', () => {
|
||||
expect(shipSkill).toContain(phrase);
|
||||
}
|
||||
});
|
||||
|
||||
test('ship SKILL.md contains review army specialist dispatch', () => {
|
||||
expect(shipSkill).toContain('Specialist Dispatch');
|
||||
expect(shipSkill).toContain('Step 3.55');
|
||||
expect(shipSkill).toContain('Step 3.56');
|
||||
});
|
||||
|
||||
test('ship SKILL.md contains cross-review finding dedup', () => {
|
||||
expect(shipSkill).toContain('Cross-review finding dedup');
|
||||
expect(shipSkill).toContain('Step 3.57');
|
||||
});
|
||||
|
||||
test('ship SKILL.md contains re-run idempotency behavior', () => {
|
||||
expect(shipSkill).toContain('Re-run behavior (idempotency)');
|
||||
expect(shipSkill).toContain('Never skip a verification step');
|
||||
});
|
||||
});
|
||||
|
||||
// --- {{TEST_FAILURE_TRIAGE}} resolver tests ---
|
||||
|
||||
@@ -131,6 +131,165 @@ describe("gstack-global-discover", () => {
|
||||
});
|
||||
});
|
||||
|
||||
describe("codex large session_meta parsing", () => {
|
||||
let codexDir: string;
|
||||
let tmpDir: string;
|
||||
|
||||
beforeEach(() => {
|
||||
tmpDir = mkdtempSync(join(tmpdir(), "gstack-codex-test-"));
|
||||
// Build a realistic ~/.codex/sessions/YYYY/MM/DD structure
|
||||
const now = new Date();
|
||||
const y = now.getFullYear().toString();
|
||||
const m = String(now.getMonth() + 1).padStart(2, "0");
|
||||
const d = String(now.getDate()).padStart(2, "0");
|
||||
codexDir = join(tmpDir, "codex-home", "sessions", y, m, d);
|
||||
mkdirSync(codexDir, { recursive: true });
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
rmSync(tmpDir, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
function writeCodexSession(
|
||||
dir: string,
|
||||
cwd: string,
|
||||
baseInstructionsSize: number
|
||||
): string {
|
||||
const padding = "x".repeat(baseInstructionsSize);
|
||||
const line = JSON.stringify({
|
||||
timestamp: new Date().toISOString(),
|
||||
type: "session_meta",
|
||||
payload: {
|
||||
id: `test-${Date.now()}`,
|
||||
timestamp: new Date().toISOString(),
|
||||
cwd,
|
||||
originator: "codex_exec",
|
||||
cli_version: "0.118.0",
|
||||
source: "exec",
|
||||
model_provider: "openai",
|
||||
base_instructions: { text: padding },
|
||||
},
|
||||
});
|
||||
const name = `rollout-${new Date().toISOString().replace(/[:.]/g, "-")}-${Math.random().toString(36).slice(2)}.jsonl`;
|
||||
const filePath = join(dir, name);
|
||||
writeFileSync(filePath, line + "\n");
|
||||
return filePath;
|
||||
}
|
||||
|
||||
test("discovers codex sessions with >4KB session_meta via CLI", () => {
|
||||
// Create a git repo as the session target
|
||||
const repoDir = join(tmpDir, "fake-repo");
|
||||
mkdirSync(repoDir);
|
||||
spawnSync("git", ["init"], { cwd: repoDir, stdio: "pipe" });
|
||||
spawnSync("git", ["commit", "--allow-empty", "-m", "init"], {
|
||||
cwd: repoDir,
|
||||
stdio: "pipe",
|
||||
});
|
||||
|
||||
// Write a session with a 20KB first line (simulates Codex v0.117+)
|
||||
writeCodexSession(codexDir, repoDir, 20000);
|
||||
|
||||
// Run discovery with CODEX_SESSIONS_DIR override
|
||||
const result = spawnSync(
|
||||
"bun",
|
||||
["run", scriptPath, "--since", "1h", "--format", "json"],
|
||||
{
|
||||
encoding: "utf-8",
|
||||
timeout: 30000,
|
||||
env: {
|
||||
...process.env,
|
||||
CODEX_SESSIONS_DIR: join(tmpDir, "codex-home", "sessions"),
|
||||
},
|
||||
}
|
||||
);
|
||||
|
||||
expect(result.status).toBe(0);
|
||||
const json = JSON.parse(result.stdout);
|
||||
expect(json.tools.codex.total_sessions).toBeGreaterThanOrEqual(1);
|
||||
});
|
||||
|
||||
test("4KB buffer truncates session_meta, 128KB buffer parses it", () => {
|
||||
const padding = "x".repeat(20000);
|
||||
const sessionMeta = JSON.stringify({
|
||||
timestamp: new Date().toISOString(),
|
||||
type: "session_meta",
|
||||
payload: {
|
||||
id: "test-id",
|
||||
timestamp: new Date().toISOString(),
|
||||
cwd: "/tmp/test-repo",
|
||||
originator: "codex_exec",
|
||||
cli_version: "0.118.0",
|
||||
source: "exec",
|
||||
model_provider: "openai",
|
||||
base_instructions: { text: padding },
|
||||
},
|
||||
});
|
||||
|
||||
expect(sessionMeta.length).toBeGreaterThan(4096);
|
||||
|
||||
const filePath = join(codexDir, "test.jsonl");
|
||||
writeFileSync(filePath, sessionMeta + "\n");
|
||||
|
||||
// 4KB buffer: JSON.parse fails (the old bug)
|
||||
const { openSync, readSync, closeSync } = require("fs");
|
||||
const fd4k = openSync(filePath, "r");
|
||||
const buf4k = Buffer.alloc(4096);
|
||||
readSync(fd4k, buf4k, 0, 4096, 0);
|
||||
closeSync(fd4k);
|
||||
expect(() =>
|
||||
JSON.parse(buf4k.toString("utf-8").split("\n")[0])
|
||||
).toThrow();
|
||||
|
||||
// 128KB buffer: JSON.parse succeeds (the fix)
|
||||
const fd128k = openSync(filePath, "r");
|
||||
const buf128k = Buffer.alloc(131072);
|
||||
const bytesRead = readSync(fd128k, buf128k, 0, 131072, 0);
|
||||
closeSync(fd128k);
|
||||
const firstLine = buf128k.toString("utf-8", 0, bytesRead).split("\n")[0];
|
||||
const meta = JSON.parse(firstLine);
|
||||
expect(meta.type).toBe("session_meta");
|
||||
expect(meta.payload.cwd).toBe("/tmp/test-repo");
|
||||
});
|
||||
|
||||
test("regression: session_meta beyond 128KB still needs streaming parse", () => {
|
||||
// This test documents the current limitation: 128KB buffer is a heuristic.
|
||||
// If Codex ever embeds >128KB in session_meta, this test will fail,
|
||||
// signaling that the buffer needs to increase or be replaced with streaming.
|
||||
const padding = "x".repeat(140000); // ~140KB payload
|
||||
const sessionMeta = JSON.stringify({
|
||||
timestamp: new Date().toISOString(),
|
||||
type: "session_meta",
|
||||
payload: {
|
||||
id: "test-large",
|
||||
timestamp: new Date().toISOString(),
|
||||
cwd: "/tmp/large-test",
|
||||
originator: "codex_exec",
|
||||
cli_version: "0.200.0",
|
||||
source: "exec",
|
||||
model_provider: "openai",
|
||||
base_instructions: { text: padding },
|
||||
},
|
||||
});
|
||||
|
||||
expect(sessionMeta.length).toBeGreaterThan(131072);
|
||||
|
||||
const filePath = join(codexDir, "large-test.jsonl");
|
||||
writeFileSync(filePath, sessionMeta + "\n");
|
||||
|
||||
// 128KB buffer: JSON.parse FAILS for >128KB lines (current limitation)
|
||||
const { openSync, readSync, closeSync } = require("fs");
|
||||
const fd = openSync(filePath, "r");
|
||||
const buf = Buffer.alloc(131072);
|
||||
readSync(fd, buf, 0, 131072, 0);
|
||||
closeSync(fd);
|
||||
expect(() =>
|
||||
JSON.parse(buf.toString("utf-8").split("\n")[0])
|
||||
).toThrow();
|
||||
// When this test starts passing (e.g., after implementing streaming parse),
|
||||
// update it to verify correct parsing instead of documenting the limitation.
|
||||
});
|
||||
});
|
||||
|
||||
describe("discovery output structure", () => {
|
||||
test("repos have required fields", () => {
|
||||
const result = spawnSync(
|
||||
|
||||
@@ -484,9 +484,13 @@ describe('host config correctness', () => {
|
||||
expect(openclaw.adapter).toContain('openclaw-adapter');
|
||||
});
|
||||
|
||||
test('openclaw has staticFiles for SOUL.md', () => {
|
||||
expect(openclaw.staticFiles).toBeDefined();
|
||||
expect(openclaw.staticFiles!['SOUL.md']).toBeDefined();
|
||||
test('openclaw has no staticFiles (SOUL.md removed)', () => {
|
||||
expect(openclaw.staticFiles).toBeUndefined();
|
||||
});
|
||||
|
||||
test('openclaw includeSkills is empty (native skills replaced generated ones)', () => {
|
||||
expect(openclaw.generation.includeSkills).toBeDefined();
|
||||
expect(openclaw.generation.includeSkills!.length).toBe(0);
|
||||
});
|
||||
|
||||
test('every host has coAuthorTrailer or undefined', () => {
|
||||
|
||||
@@ -1522,6 +1522,26 @@ describe('Test failure triage in ship skill', () => {
|
||||
});
|
||||
});
|
||||
|
||||
describe('no compiled binaries in git', () => {
|
||||
test('git tracks no Mach-O or ELF binaries', () => {
|
||||
const result = require('child_process').execSync(
|
||||
'git ls-files -z | xargs -0 file --mime-type 2>/dev/null | grep -E "application/(x-mach-binary|x-executable|x-pie-executable|x-sharedlib)" || true',
|
||||
{ cwd: ROOT, encoding: 'utf-8' }
|
||||
).trim();
|
||||
const files = result ? result.split('\n').map((l: string) => l.split(':')[0].trim()) : [];
|
||||
expect(files).toEqual([]);
|
||||
});
|
||||
|
||||
test('git tracks no files larger than 2MB', () => {
|
||||
const result = require('child_process').execSync(
|
||||
'git ls-files -z | xargs -0 -I{} sh -c \'size=$(wc -c < "{}" 2>/dev/null | tr -d " "); [ "$size" -gt 2097152 ] 2>/dev/null && echo "{}:${size}"\' || true',
|
||||
{ cwd: ROOT, encoding: 'utf-8' }
|
||||
).trim();
|
||||
const files = result ? result.split('\n').filter(Boolean) : [];
|
||||
expect(files).toEqual([]);
|
||||
});
|
||||
});
|
||||
|
||||
describe('sidebar agent (#584)', () => {
|
||||
// #584 — Sidebar Write: sidebar-agent.ts allowedTools includes Write
|
||||
test('sidebar-agent.ts allowedTools includes Write', () => {
|
||||
|
||||
Reference in New Issue
Block a user