mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-05 21:25:27 +02:00
Merge remote-tracking branch 'origin/main' into garrytan/test-coverage-catalog
Resolves conflicts: gen-skill-docs.ts (both repo-mode + search-before-building), test files (both coverage audit + plan-file-review-report tests), touchfiles (both repo-mode + ship-local-workflow entries). Regenerated all SKILL.md files. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
@@ -80,7 +80,7 @@ export function renderDashboard(heartbeat: HeartbeatData | null, partial: Partia
|
||||
lines.push(`Heartbeat: ${HEARTBEAT_PATH} (not found)`);
|
||||
lines.push(`Partial: ${PARTIAL_PATH} (not found)`);
|
||||
lines.push('');
|
||||
lines.push('Start a run with: EVALS=1 bun test test/skill-e2e.test.ts');
|
||||
lines.push('Start a run with: EVALS=1 bun test test/skill-e2e-*.test.ts');
|
||||
return lines.join('\n');
|
||||
}
|
||||
|
||||
|
||||
+243
-101
@@ -378,6 +378,28 @@ Use AskUserQuestion:
|
||||
- Note in output: "Pre-existing test failure skipped: <test-name>"`;
|
||||
}
|
||||
|
||||
function generateSearchBeforeBuildingSection(ctx: TemplateContext): string {
|
||||
return `## Search Before Building
|
||||
|
||||
Before building infrastructure, unfamiliar patterns, or anything the runtime might have a built-in — **search first.** Read \`${ctx.paths.skillRoot}/ETHOS.md\` for the full philosophy.
|
||||
|
||||
**Three layers of knowledge:**
|
||||
- **Layer 1** (tried and true — in distribution). Don't reinvent the wheel. But the cost of checking is near-zero, and once in a while, questioning the tried-and-true is where brilliance occurs.
|
||||
- **Layer 2** (new and popular — search for these). But scrutinize: humans are subject to mania. Search results are inputs to your thinking, not answers.
|
||||
- **Layer 3** (first principles — prize these above all). Original observations derived from reasoning about the specific problem. The most valuable of all.
|
||||
|
||||
**Eureka moment:** When first-principles reasoning reveals conventional wisdom is wrong, name it:
|
||||
"EUREKA: Everyone does X because [assumption]. But [evidence] shows this is wrong. Y is better because [reasoning]."
|
||||
|
||||
Log eureka moments:
|
||||
\`\`\`bash
|
||||
jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true
|
||||
\`\`\`
|
||||
Replace SKILL_NAME and ONE_LINE_SUMMARY. Runs inline — don't stop the workflow.
|
||||
|
||||
**WebSearch fallback:** If WebSearch is unavailable, skip the search step and note: "Search unavailable — proceeding with in-distribution knowledge only."`;
|
||||
}
|
||||
|
||||
function generateContributorMode(): string {
|
||||
return `## Contributor Mode
|
||||
|
||||
@@ -481,6 +503,7 @@ function generatePreamble(ctx: TemplateContext): string {
|
||||
generateAskUserFormat(ctx),
|
||||
generateCompletenessSection(),
|
||||
generateRepoModeSection(),
|
||||
generateSearchBeforeBuildingSection(ctx),
|
||||
generateContributorMode(),
|
||||
generateCompletionStatus(),
|
||||
].join('\n\n');
|
||||
@@ -1187,7 +1210,7 @@ After completing the review, read the review log and config to display the dashb
|
||||
~/.claude/skills/gstack/bin/gstack-review-read
|
||||
\`\`\`
|
||||
|
||||
Parse the output. Find the most recent entry for each skill (plan-ceo-review, plan-eng-review, plan-design-review, design-review-lite, codex-review). Ignore entries with timestamps older than 7 days. For Design Review, show whichever is more recent between \`plan-design-review\` (full visual audit) and \`design-review-lite\` (code-level check). Append "(FULL)" or "(LITE)" to the status to distinguish. Display:
|
||||
Parse the output. Find the most recent entry for each skill (plan-ceo-review, plan-eng-review, plan-design-review, design-review-lite, adversarial-review, codex-review). Ignore entries with timestamps older than 7 days. For the Adversarial row, show whichever is more recent between \`adversarial-review\` (new auto-scaled) and \`codex-review\` (legacy). For Design Review, show whichever is more recent between \`plan-design-review\` (full visual audit) and \`design-review-lite\` (code-level check). Append "(FULL)" or "(LITE)" to the status to distinguish. Display:
|
||||
|
||||
\`\`\`
|
||||
+====================================================================+
|
||||
@@ -1198,7 +1221,7 @@ Parse the output. Find the most recent entry for each skill (plan-ceo-review, pl
|
||||
| Eng Review | 1 | 2026-03-16 15:00 | CLEAR | YES |
|
||||
| CEO Review | 0 | — | — | no |
|
||||
| Design Review | 0 | — | — | no |
|
||||
| Codex Review | 0 | — | — | no |
|
||||
| Adversarial | 0 | — | — | no |
|
||||
+--------------------------------------------------------------------+
|
||||
| VERDICT: CLEARED — Eng Review passed |
|
||||
+====================================================================+
|
||||
@@ -1208,7 +1231,7 @@ Parse the output. Find the most recent entry for each skill (plan-ceo-review, pl
|
||||
- **Eng Review (required by default):** The only review that gates shipping. Covers architecture, code quality, tests, performance. Can be disabled globally with \\\`gstack-config set skip_eng_review true\\\` (the "don't bother me" setting).
|
||||
- **CEO Review (optional):** Use your judgment. Recommend it for big product/business changes, new user-facing features, or scope decisions. Skip for bug fixes, refactors, infra, and cleanup.
|
||||
- **Design Review (optional):** Use your judgment. Recommend it for UI/UX changes. Skip for backend-only, infra, or prompt-only changes.
|
||||
- **Codex Review (enabled by default when Codex CLI is installed):** Independent review + adversarial challenge from OpenAI Codex CLI. Shows pass/fail gate. Runs automatically when enabled — configure with \\\`gstack-config set codex_reviews enabled|disabled\\\`.
|
||||
- **Adversarial Review (automatic):** Auto-scales by diff size. Small diffs (<50 lines) skip adversarial. Medium diffs (50–199) get cross-model adversarial. Large diffs (200+) get all 4 passes: Claude structured, Codex structured, Claude adversarial subagent, Codex adversarial. No configuration needed.
|
||||
|
||||
**Verdict logic:**
|
||||
- **CLEARED**: Eng Review has >= 1 entry within 7 days with status "clean" (or \\\`skip_eng_review\\\` is \\\`true\\\`)
|
||||
@@ -1223,6 +1246,75 @@ Parse the output. Find the most recent entry for each skill (plan-ceo-review, pl
|
||||
- If all reviews match the current HEAD, do not display any staleness notes`;
|
||||
}
|
||||
|
||||
function generatePlanFileReviewReport(_ctx: TemplateContext): string {
|
||||
return `## Plan File Review Report
|
||||
|
||||
After displaying the Review Readiness Dashboard in conversation output, also update the
|
||||
**plan file** itself so review status is visible to anyone reading the plan.
|
||||
|
||||
### Detect the plan file
|
||||
|
||||
1. Check if there is an active plan file in this conversation (the host provides plan file
|
||||
paths in system messages — look for plan file references in the conversation context).
|
||||
2. If not found, skip this section silently — not every review runs in plan mode.
|
||||
|
||||
### Generate the report
|
||||
|
||||
Read the review log output you already have from the Review Readiness Dashboard step above.
|
||||
Parse each JSONL entry. Each skill logs different fields:
|
||||
|
||||
- **plan-ceo-review**: \\\`status\\\`, \\\`unresolved\\\`, \\\`critical_gaps\\\`, \\\`mode\\\`, \\\`scope_proposed\\\`, \\\`scope_accepted\\\`, \\\`scope_deferred\\\`, \\\`commit\\\`
|
||||
→ Findings: "{scope_proposed} proposals, {scope_accepted} accepted, {scope_deferred} deferred"
|
||||
→ If scope fields are 0 or missing (HOLD/REDUCTION mode): "mode: {mode}, {critical_gaps} critical gaps"
|
||||
- **plan-eng-review**: \\\`status\\\`, \\\`unresolved\\\`, \\\`critical_gaps\\\`, \\\`issues_found\\\`, \\\`mode\\\`, \\\`commit\\\`
|
||||
→ Findings: "{issues_found} issues, {critical_gaps} critical gaps"
|
||||
- **plan-design-review**: \\\`status\\\`, \\\`initial_score\\\`, \\\`overall_score\\\`, \\\`unresolved\\\`, \\\`decisions_made\\\`, \\\`commit\\\`
|
||||
→ Findings: "score: {initial_score}/10 → {overall_score}/10, {decisions_made} decisions"
|
||||
- **codex-review**: \\\`status\\\`, \\\`gate\\\`, \\\`findings\\\`, \\\`findings_fixed\\\`
|
||||
→ Findings: "{findings} findings, {findings_fixed}/{findings} fixed"
|
||||
|
||||
All fields needed for the Findings column are now present in the JSONL entries.
|
||||
For the review you just completed, you may use richer details from your own Completion
|
||||
Summary. For prior reviews, use the JSONL fields directly — they contain all required data.
|
||||
|
||||
Produce this markdown table:
|
||||
|
||||
\\\`\\\`\\\`markdown
|
||||
## GSTACK REVIEW REPORT
|
||||
|
||||
| Review | Trigger | Why | Runs | Status | Findings |
|
||||
|--------|---------|-----|------|--------|----------|
|
||||
| CEO Review | \\\`/plan-ceo-review\\\` | Scope & strategy | {runs} | {status} | {findings} |
|
||||
| Codex Review | \\\`/codex review\\\` | Independent 2nd opinion | {runs} | {status} | {findings} |
|
||||
| Eng Review | \\\`/plan-eng-review\\\` | Architecture & tests (required) | {runs} | {status} | {findings} |
|
||||
| Design Review | \\\`/plan-design-review\\\` | UI/UX gaps | {runs} | {status} | {findings} |
|
||||
\\\`\\\`\\\`
|
||||
|
||||
Below the table, add these lines (omit any that are empty/not applicable):
|
||||
|
||||
- **CODEX:** (only if codex-review ran) — one-line summary of codex fixes
|
||||
- **CROSS-MODEL:** (only if both Claude and Codex reviews exist) — overlap analysis
|
||||
- **UNRESOLVED:** total unresolved decisions across all reviews
|
||||
- **VERDICT:** list reviews that are CLEAR (e.g., "CEO + ENG CLEARED — ready to implement").
|
||||
If Eng Review is not CLEAR and not skipped globally, append "eng review required".
|
||||
|
||||
### Write to the plan file
|
||||
|
||||
**PLAN MODE EXCEPTION — ALWAYS RUN:** This writes to the plan file, which is the one
|
||||
file you are allowed to edit in plan mode. The plan file review report is part of the
|
||||
plan's living status.
|
||||
|
||||
- Search the plan file for a \\\`## GSTACK REVIEW REPORT\\\` section **anywhere** in the file
|
||||
(not just at the end — content may have been added after it).
|
||||
- If found, **replace it** entirely using the Edit tool. Match from \\\`## GSTACK REVIEW REPORT\\\`
|
||||
through either the next \\\`## \\\` heading or end of file, whichever comes first. This ensures
|
||||
content added after the report section is preserved, not eaten. If the Edit fails
|
||||
(e.g., concurrent edit changed the content), re-read the plan file and retry once.
|
||||
- If no such section exists, **append it** to the end of the plan file.
|
||||
- Always place it as the very last section in the plan file. If it was found mid-file,
|
||||
move it: delete the old location and append at the end.`;
|
||||
}
|
||||
|
||||
function generateTestBootstrap(_ctx: TemplateContext): string {
|
||||
return `## Test Framework Bootstrap
|
||||
|
||||
@@ -1895,139 +1987,186 @@ The screenshot file at \`/tmp/gstack-sketch.png\` can be referenced by downstrea
|
||||
(\`/plan-design-review\`, \`/design-review\`) to see what was originally envisioned.`;
|
||||
}
|
||||
|
||||
function generateCodexReviewStep(ctx: TemplateContext): string {
|
||||
function generateAdversarialStep(ctx: TemplateContext): string {
|
||||
// Codex host: strip entirely — Codex should never invoke itself
|
||||
if (ctx.host === 'codex') return '';
|
||||
|
||||
const isShip = ctx.skillName === 'ship';
|
||||
const stepNum = isShip ? '3.8' : '5.7';
|
||||
|
||||
return `## Step ${stepNum}: Codex review
|
||||
return `## Step ${stepNum}: Adversarial review (auto-scaled)
|
||||
|
||||
Check if the Codex CLI is available and read the user's Codex review preference:
|
||||
Adversarial review thoroughness scales automatically based on diff size. No configuration needed.
|
||||
|
||||
**Detect diff size and tool availability:**
|
||||
|
||||
\`\`\`bash
|
||||
DIFF_INS=$(git diff origin/<base> --stat | tail -1 | grep -oE '[0-9]+ insertion' | grep -oE '[0-9]+' || echo "0")
|
||||
DIFF_DEL=$(git diff origin/<base> --stat | tail -1 | grep -oE '[0-9]+ deletion' | grep -oE '[0-9]+' || echo "0")
|
||||
DIFF_TOTAL=$((DIFF_INS + DIFF_DEL))
|
||||
which codex 2>/dev/null && echo "CODEX_AVAILABLE" || echo "CODEX_NOT_AVAILABLE"
|
||||
CODEX_REVIEWS_CFG=$(~/.claude/skills/gstack/bin/gstack-config get codex_reviews 2>/dev/null || true)
|
||||
echo "CODEX_REVIEWS: \${CODEX_REVIEWS_CFG:-not_set}"
|
||||
# Respect old opt-out
|
||||
OLD_CFG=$(~/.claude/skills/gstack/bin/gstack-config get codex_reviews 2>/dev/null || true)
|
||||
echo "DIFF_SIZE: $DIFF_TOTAL"
|
||||
echo "OLD_CFG: \${OLD_CFG:-not_set}"
|
||||
\`\`\`
|
||||
|
||||
If \`CODEX_NOT_AVAILABLE\`: skip this step silently. Continue to the next step.
|
||||
If \`OLD_CFG\` is \`disabled\`: skip this step silently. Continue to the next step.
|
||||
|
||||
If \`CODEX_REVIEWS\` is \`disabled\`: skip this step silently. Continue to the next step.
|
||||
**User override:** If the user explicitly requested a specific tier (e.g., "run all passes", "paranoid review", "full adversarial", "do all 4 passes", "thorough review"), honor that request regardless of diff size. Jump to the matching tier section.
|
||||
|
||||
If \`CODEX_REVIEWS\` is \`enabled\`: run both code review and adversarial challenge automatically (no prompt). Jump to the "Run Codex" section below.
|
||||
**Auto-select tier based on diff size:**
|
||||
- **Small (< 50 lines changed):** Skip adversarial review entirely. Print: "Small diff ($DIFF_TOTAL lines) — adversarial review skipped." Continue to the next step.
|
||||
- **Medium (50–199 lines changed):** Run Codex adversarial challenge (or Claude adversarial subagent if Codex unavailable). Jump to the "Medium tier" section.
|
||||
- **Large (200+ lines changed):** Run all remaining passes — Codex structured review + Claude adversarial subagent + Codex adversarial. Jump to the "Large tier" section.
|
||||
|
||||
If \`CODEX_REVIEWS\` is \`not_set\`: use AskUserQuestion to offer the one-time adoption prompt:
|
||||
---
|
||||
|
||||
\`\`\`
|
||||
GStack recommends enabling Codex code reviews — Codex is the super smart quiet engineer friend who will save your butt.
|
||||
### Medium tier (50–199 lines)
|
||||
|
||||
A) Enable for all future runs (recommended, default)
|
||||
B) Try it for now, ask me again later
|
||||
C) No thanks, don't ask me again
|
||||
\`\`\`
|
||||
Claude's structured review already ran. Now add a **cross-model adversarial challenge**.
|
||||
|
||||
If the user chooses A: persist the setting and run both:
|
||||
\`\`\`bash
|
||||
~/.claude/skills/gstack/bin/gstack-config set codex_reviews enabled
|
||||
\`\`\`
|
||||
**If Codex is available:** run the Codex adversarial challenge. **If Codex is NOT available:** fall back to the Claude adversarial subagent instead.
|
||||
|
||||
If the user chooses B: run both this time but do not persist any setting.
|
||||
**Codex adversarial:**
|
||||
|
||||
If the user chooses C: persist the opt-out and skip:
|
||||
\`\`\`bash
|
||||
~/.claude/skills/gstack/bin/gstack-config set codex_reviews disabled
|
||||
\`\`\`
|
||||
Then skip this step. Continue to the next step.
|
||||
|
||||
### Run Codex
|
||||
|
||||
Always run **both** code review and adversarial challenge. Use a 5-minute timeout (\`timeout: 300000\`) on each Bash call.
|
||||
|
||||
First, create a temp file for stderr capture:
|
||||
\`\`\`bash
|
||||
TMPERR=$(mktemp /tmp/codex-review-XXXXXXXX)
|
||||
\`\`\`
|
||||
|
||||
**Code review:** Run:
|
||||
\`\`\`bash
|
||||
codex review --base <base> -c 'model_reasoning_effort="xhigh"' --enable web_search_cached 2>"$TMPERR"
|
||||
\`\`\`
|
||||
|
||||
After the command completes, read stderr for cost/error info:
|
||||
\`\`\`bash
|
||||
cat "$TMPERR"
|
||||
\`\`\`
|
||||
|
||||
Present the full output verbatim under a \`CODEX SAYS (code review):\` header:
|
||||
|
||||
\`\`\`
|
||||
CODEX SAYS (code review):
|
||||
════════════════════════════════════════════════════════════
|
||||
<full codex output, verbatim — do not truncate or summarize>
|
||||
════════════════════════════════════════════════════════════
|
||||
GATE: PASS Tokens: N | Est. cost: ~$X.XX
|
||||
\`\`\`
|
||||
|
||||
Check the output for \`[P1]\` markers. If found: \`GATE: FAIL\`. If no \`[P1]\`: \`GATE: PASS\`.
|
||||
|
||||
**If GATE is FAIL:** use AskUserQuestion:
|
||||
|
||||
\`\`\`
|
||||
Codex found N critical issues in the diff.
|
||||
|
||||
A) Investigate and fix now (recommended)
|
||||
B) Ship anyway — these issues may cause production problems
|
||||
\`\`\`
|
||||
|
||||
If the user chooses A: read the Codex findings carefully and work to address them${isShip ? '. After fixing, re-run tests (Step 3) since code has changed' : ''}. Then re-run \`codex review\` to verify the gate is now PASS.
|
||||
|
||||
If the user chooses B: continue to the next step.
|
||||
|
||||
### Error handling (code review)
|
||||
|
||||
Before persisting the gate result, check for errors. All errors are non-blocking — Codex is a quality enhancement, not a prerequisite. Check \`$TMPERR\` output (already read above) for error indicators:
|
||||
|
||||
- **Auth failure:** If stderr contains "auth", "login", "unauthorized", or "API key", tell the user: "Codex authentication failed. Run \\\`codex login\\\` in your terminal to authenticate via ChatGPT." Do NOT persist a review log entry. Continue to the adversarial step (it will likely fail too, but try anyway).
|
||||
- **Timeout:** If the Bash call times out (5 min), tell the user: "Codex timed out after 5 minutes. The diff may be too large or the API may be slow." Do NOT persist a review log entry. Skip to cleanup.
|
||||
- **Empty response:** If codex returned no stdout output, tell the user: "Codex returned no response. Stderr: <paste relevant error>." Do NOT persist a review log entry. Skip to cleanup.
|
||||
|
||||
**Only if codex produced a real review (non-empty stdout):** Persist the code review result:
|
||||
\`\`\`bash
|
||||
~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"codex-review","timestamp":"'"$(date -u +%Y-%m-%dT%H:%M:%SZ)"'","status":"STATUS","gate":"GATE","commit":"'"$(git rev-parse --short HEAD)"'"}'
|
||||
\`\`\`
|
||||
|
||||
Substitute: STATUS ("clean" if PASS, "issues_found" if FAIL), GATE ("pass" or "fail").
|
||||
|
||||
**Adversarial challenge:** Run:
|
||||
\`\`\`bash
|
||||
TMPERR_ADV=$(mktemp /tmp/codex-adv-XXXXXXXX)
|
||||
codex exec "Review the changes on this branch against the base branch. Run git diff origin/<base> to see the diff. Your job is to find ways this code will fail in production. Think like an attacker and a chaos engineer. Find edge cases, race conditions, security holes, resource leaks, failure modes, and silent data corruption paths. Be adversarial. Be thorough. No compliments — just the problems." -s read-only -c 'model_reasoning_effort="xhigh"' --enable web_search_cached 2>"$TMPERR_ADV"
|
||||
\`\`\`
|
||||
|
||||
After the command completes, read adversarial stderr:
|
||||
Use a 5-minute timeout (\`timeout: 300000\`). After the command completes, read stderr:
|
||||
\`\`\`bash
|
||||
cat "$TMPERR_ADV"
|
||||
\`\`\`
|
||||
|
||||
Present the full output verbatim under a \`CODEX SAYS (adversarial challenge):\` header. This is informational — it never blocks shipping. If the adversarial command timed out or returned no output, note this to the user and continue.
|
||||
${!isShip ? `
|
||||
**Cross-model analysis:** After both Codex outputs are presented, compare Codex's findings with your own review findings from the earlier review steps and output:
|
||||
Present the full output verbatim. This is informational — it never blocks shipping.
|
||||
|
||||
**Error handling:** All errors are non-blocking — adversarial review is a quality enhancement, not a prerequisite.
|
||||
- **Auth failure:** If stderr contains "auth", "login", "unauthorized", or "API key": "Codex authentication failed. Run \\\`codex login\\\` to authenticate."
|
||||
- **Timeout:** "Codex timed out after 5 minutes."
|
||||
- **Empty response:** "Codex returned no response. Stderr: <paste relevant error>."
|
||||
|
||||
On any Codex error, fall back to the Claude adversarial subagent automatically.
|
||||
|
||||
**Claude adversarial subagent** (fallback when Codex unavailable or errored):
|
||||
|
||||
Dispatch via the Agent tool. The subagent has fresh context — no checklist bias from the structured review. This genuine independence catches things the primary reviewer is blind to.
|
||||
|
||||
Subagent prompt:
|
||||
"Read the diff for this branch with \`git diff origin/<base>\`. Think like an attacker and a chaos engineer. Your job is to find ways this code will fail in production. Look for: edge cases, race conditions, security holes, resource leaks, failure modes, silent data corruption, logic errors that produce wrong results silently, error handling that swallows failures, and trust boundary violations. Be adversarial. Be thorough. No compliments — just the problems. For each finding, classify as FIXABLE (you know how to fix it) or INVESTIGATE (needs human judgment)."
|
||||
|
||||
Present findings under an \`ADVERSARIAL REVIEW (Claude subagent):\` header. **FIXABLE findings** flow into the same Fix-First pipeline as the structured review. **INVESTIGATE findings** are presented as informational.
|
||||
|
||||
If the subagent fails or times out: "Claude adversarial subagent unavailable. Continuing without adversarial review."
|
||||
|
||||
**Persist the review result:**
|
||||
\`\`\`bash
|
||||
~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"adversarial-review","timestamp":"'"$(date -u +%Y-%m-%dT%H:%M:%SZ)"'","status":"STATUS","source":"SOURCE","tier":"medium","commit":"'"$(git rev-parse --short HEAD)"'"}'
|
||||
\`\`\`
|
||||
Substitute STATUS: "clean" if no findings, "issues_found" if findings exist. SOURCE: "codex" if Codex ran, "claude" if subagent ran. If both failed, do NOT persist.
|
||||
|
||||
**Cleanup:** Run \`rm -f "$TMPERR_ADV"\` after processing (if Codex was used).
|
||||
|
||||
---
|
||||
|
||||
### Large tier (200+ lines)
|
||||
|
||||
Claude's structured review already ran. Now run **all three remaining passes** for maximum coverage:
|
||||
|
||||
**1. Codex structured review (if available):**
|
||||
\`\`\`bash
|
||||
TMPERR=$(mktemp /tmp/codex-review-XXXXXXXX)
|
||||
codex review --base <base> -c 'model_reasoning_effort="xhigh"' --enable web_search_cached 2>"$TMPERR"
|
||||
\`\`\`
|
||||
|
||||
Use a 5-minute timeout. Present output under \`CODEX SAYS (code review):\` header.
|
||||
Check for \`[P1]\` markers: found → \`GATE: FAIL\`, not found → \`GATE: PASS\`.
|
||||
|
||||
If GATE is FAIL, use AskUserQuestion:
|
||||
\`\`\`
|
||||
Codex found N critical issues in the diff.
|
||||
|
||||
A) Investigate and fix now (recommended)
|
||||
B) Continue — review will still complete
|
||||
\`\`\`
|
||||
|
||||
If A: address the findings${isShip ? '. After fixing, re-run tests (Step 3) since code has changed' : ''}. Re-run \`codex review\` to verify.
|
||||
|
||||
Read stderr for errors (same error handling as medium tier).
|
||||
|
||||
After stderr: \`rm -f "$TMPERR"\`
|
||||
|
||||
**2. Claude adversarial subagent:** Dispatch a subagent with the adversarial prompt (same prompt as medium tier). This always runs regardless of Codex availability.
|
||||
|
||||
**3. Codex adversarial challenge (if available):** Run \`codex exec\` with the adversarial prompt (same as medium tier).
|
||||
|
||||
If Codex is not available for steps 1 and 3, note to the user: "Codex CLI not found — large-diff review ran Claude structured + Claude adversarial (2 of 4 passes). Install Codex for full 4-pass coverage: \`npm install -g @openai/codex\`"
|
||||
|
||||
**Persist the review result AFTER all passes complete** (not after each sub-step):
|
||||
\`\`\`bash
|
||||
~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"adversarial-review","timestamp":"'"$(date -u +%Y-%m-%dT%H:%M:%SZ)"'","status":"STATUS","source":"SOURCE","tier":"large","gate":"GATE","commit":"'"$(git rev-parse --short HEAD)"'"}'
|
||||
\`\`\`
|
||||
Substitute: STATUS = "clean" if no findings across ALL passes, "issues_found" if any pass found issues. SOURCE = "both" if Codex ran, "claude" if only Claude subagent ran. GATE = the Codex structured review gate result ("pass"/"fail"), or "informational" if Codex was unavailable. If all passes failed, do NOT persist.
|
||||
|
||||
---
|
||||
|
||||
### Cross-model synthesis (medium and large tiers)
|
||||
|
||||
After all passes complete, synthesize findings across all sources:
|
||||
|
||||
\`\`\`
|
||||
CROSS-MODEL ANALYSIS:
|
||||
Both found: [findings that overlap between Claude and Codex]
|
||||
Only Codex found: [findings unique to Codex]
|
||||
Only Claude found: [findings unique to Claude's review]
|
||||
Agreement rate: X% (N/M total unique findings overlap)
|
||||
ADVERSARIAL REVIEW SYNTHESIS (auto: TIER, N lines):
|
||||
════════════════════════════════════════════════════════════
|
||||
High confidence (found by multiple sources): [findings agreed on by >1 pass]
|
||||
Unique to Claude structured review: [from earlier step]
|
||||
Unique to Claude adversarial: [from subagent, if ran]
|
||||
Unique to Codex: [from codex adversarial or code review, if ran]
|
||||
Models used: Claude structured ✓ Claude adversarial ✓/✗ Codex ✓/✗
|
||||
════════════════════════════════════════════════════════════
|
||||
\`\`\`
|
||||
` : ''}
|
||||
**Cleanup:** Run \`rm -f "$TMPERR" "$TMPERR_ADV"\` after processing.
|
||||
|
||||
High-confidence findings (agreed on by multiple sources) should be prioritized for fixes.
|
||||
|
||||
---`;
|
||||
}
|
||||
|
||||
function generateDeployBootstrap(_ctx: TemplateContext): string {
|
||||
return `\`\`\`bash
|
||||
# Check for persisted deploy config in CLAUDE.md
|
||||
DEPLOY_CONFIG=$(grep -A 20 "## Deploy Configuration" CLAUDE.md 2>/dev/null || echo "NO_CONFIG")
|
||||
echo "$DEPLOY_CONFIG"
|
||||
|
||||
# If config exists, parse it
|
||||
if [ "$DEPLOY_CONFIG" != "NO_CONFIG" ]; then
|
||||
PROD_URL=$(echo "$DEPLOY_CONFIG" | grep -i "production.*url" | head -1 | sed 's/.*: *//')
|
||||
PLATFORM=$(echo "$DEPLOY_CONFIG" | grep -i "platform" | head -1 | sed 's/.*: *//')
|
||||
echo "PERSISTED_PLATFORM:$PLATFORM"
|
||||
echo "PERSISTED_URL:$PROD_URL"
|
||||
fi
|
||||
|
||||
# Auto-detect platform from config files
|
||||
[ -f fly.toml ] && echo "PLATFORM:fly"
|
||||
[ -f render.yaml ] && echo "PLATFORM:render"
|
||||
([ -f vercel.json ] || [ -d .vercel ]) && echo "PLATFORM:vercel"
|
||||
[ -f netlify.toml ] && echo "PLATFORM:netlify"
|
||||
[ -f Procfile ] && echo "PLATFORM:heroku"
|
||||
([ -f railway.json ] || [ -f railway.toml ]) && echo "PLATFORM:railway"
|
||||
|
||||
# Detect deploy workflows
|
||||
for f in .github/workflows/*.yml .github/workflows/*.yaml; do
|
||||
[ -f "$f" ] && grep -qiE "deploy|release|production|staging|cd" "$f" 2>/dev/null && echo "DEPLOY_WORKFLOW:$f"
|
||||
done
|
||||
\`\`\`
|
||||
|
||||
If \`PERSISTED_PLATFORM\` and \`PERSISTED_URL\` were found in CLAUDE.md, use them directly
|
||||
and skip manual detection. If no persisted config exists, use the auto-detected platform
|
||||
to guide deploy verification. If nothing is detected, ask the user via AskUserQuestion
|
||||
in the decision tree below.
|
||||
|
||||
If you want to persist deploy settings for future runs, suggest the user run \`/setup-deploy\`.`;
|
||||
}
|
||||
|
||||
const RESOLVERS: Record<string, (ctx: TemplateContext) => string> = {
|
||||
COMMAND_REFERENCE: generateCommandReference,
|
||||
SNAPSHOT_FLAGS: generateSnapshotFlags,
|
||||
@@ -2038,6 +2177,7 @@ const RESOLVERS: Record<string, (ctx: TemplateContext) => string> = {
|
||||
DESIGN_METHODOLOGY: generateDesignMethodology,
|
||||
DESIGN_REVIEW_LITE: generateDesignReviewLite,
|
||||
REVIEW_DASHBOARD: generateReviewDashboard,
|
||||
PLAN_FILE_REVIEW_REPORT: generatePlanFileReviewReport,
|
||||
TEST_BOOTSTRAP: generateTestBootstrap,
|
||||
TEST_COVERAGE_AUDIT_PLAN: generateTestCoverageAuditPlan,
|
||||
TEST_COVERAGE_AUDIT_SHIP: generateTestCoverageAuditShip,
|
||||
@@ -2046,7 +2186,9 @@ const RESOLVERS: Record<string, (ctx: TemplateContext) => string> = {
|
||||
SPEC_REVIEW_LOOP: generateSpecReviewLoop,
|
||||
DESIGN_SKETCH: generateDesignSketch,
|
||||
BENEFITS_FROM: generateBenefitsFrom,
|
||||
CODEX_REVIEW_STEP: generateCodexReviewStep,
|
||||
CODEX_REVIEW_STEP: generateAdversarialStep,
|
||||
ADVERSARIAL_STEP: generateAdversarialStep,
|
||||
DEPLOY_BOOTSTRAP: generateDeployBootstrap,
|
||||
};
|
||||
|
||||
// ─── Codex Helpers ───────────────────────────────────────────
|
||||
|
||||
@@ -31,6 +31,10 @@ const SKILL_FILES = [
|
||||
'design-review/SKILL.md',
|
||||
'gstack-upgrade/SKILL.md',
|
||||
'document-release/SKILL.md',
|
||||
'canary/SKILL.md',
|
||||
'benchmark/SKILL.md',
|
||||
'land-and-deploy/SKILL.md',
|
||||
'setup-deploy/SKILL.md',
|
||||
].filter(f => fs.existsSync(path.join(ROOT, f)));
|
||||
|
||||
let hasErrors = false;
|
||||
|
||||
Reference in New Issue
Block a user