mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-02 11:45:20 +02:00
garrytan/plan-tune-skill
269 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Garry Tan
|
43a01fd3b5 |
docs: move full-clone footnote from README to CONTRIBUTING
The "Contributing or need full history?" note is for contributors, not for someone following the README install flow. Moved into CONTRIBUTING's Quick start section where it fits next to the existing clone command, with a tip to upgrade an existing shallow clone via \`git fetch --unshallow\`. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
f8129a9476 |
docs: collapse team-mode setup into one paste-and-go command
Step 2 was three separate code blocks: setup --team, then team-init, then git add/commit. Mirrors Step 1's style now — one shell one-liner that does all three. Subshell (cd && ./setup --team) keeps the user in their repo pwd so team-init + git commit land in the right place. "Swap required for optional" moved to a one-liner below. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
df9ee5c1d3 |
docs: drop Writing style section from README
Was sitting in prime real estate between Quick start and Install — internal implementation detail, not something users need up-front. Existing coverage is enough: - Upgrade migration prompt notifies users on first post-upgrade run - CLAUDE.md has the contributor note - docs/designs/PLAN_TUNING_V1.md has the full design Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
e385721c25 |
docs: tighten four LOC post citations to match primary sources
1. Bill Gates quote: flagged as folklore-grade. Was "Bill Gates put it more memorably" (firm attribution). Now "The old line (widely attributed to Bill Gates, sourcing murky) puts it more memorably." The quote stands; honesty about attribution avoids the same misattribution trap we just fixed for Kernighan. 2. Capers Jones: "15-50 across thousands of projects" → "roughly 16-38 LOC/day across thousands of projects" — matches his actual published measurements (which also report as 325-750 LOC/month). 3. Steve McConnell: "10-50 for finished, tested, delivered code" was folklore. Replaced with his actual project-size-dependent range from Code Complete: "20-125 LOC/day for small projects (10K LOC) down to 1.5-25 for large projects (10M LOC) — it's size-dependent, not a single number." 4. Revert rate comparison: "Kubernetes, Rails, and Django historically run 1.5-3%" was unsourced. Replaced with "mature OSS codebases typically run 1-3%" + "run the same command on whatever you consider the bar and compare." No false specificity about which repos. Net: every quantitative citation in the post now matches primary-source figures or is explicitly flagged as folklore. Neckbeards can verify. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
73f15ca76e |
Merge remote-tracking branch 'origin/main' into garrytan/plan-tune-skill
Conflicts resolved:
- VERSION / package.json: keep 1.0.0.0 (our v1 milestone bump from
commit
|
||
|
Garry Tan
|
dc6c114b7e |
docs: four precision fixes on LOC controversy post
1. Citation fix. Kernighan didn't say anything about LOC-as-metric
(that's the famous "aircraft building by weight" quote, commonly
misattributed but actually Bill Gates). Replaced "Kernighan implied
it before that" with the real Dijkstra quote ("lines produced" vs
"lines spent" from EWD1036, with direct link) + the Gates quote.
Verified via web search.
2. Slop-scan direction clarified. "(highest on his benchmark)" was
ambiguous — could read as a brag. Now: "Higher score = more slop.
He ran it on gstack and we scored 5.24, the worst he'd measured
at the time." Then the 62% cut lands as an actual win.
3. Prose/chart skill-usage ordering now matches. Added /plan-eng-review
(28,014) to the prose list so it doesn't conflict with the chart
below it.
4. Cut the "David — I owe you one / GUnit" insider joke. Most readers
won't connect Cramer → Sentry → GUnit naming. Ends the slop-scan
paragraph on the stronger line: "Run `bun test` and watch 2,000+
tests pass."
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
root
|
f545c908a7 |
Rewrite LOC controversy post
- Lead with concession (LOC is garbage, do the math anyway) - Preempt 14 lines/day meme with historical baselines (Brooks, Jones, McConnell) - Remove 'neckbeard' language throughout - Add slop-scan story (Ben Vinegar, 5.24 → 1.96, 62% cut) - David Cramer GUnit joke - Add testing philosophy section (the real unlock) - ASCII weekly distribution chart - gstack telemetry section with real numbers (15K installs, 305K invocations, 95.2% success) - Top skills usage chart - Pick-your-priors paragraph moved earlier (the killer) - Sharper close: run the script, show me your numbers |
||
|
Garry Tan
|
8e2129a8d9 |
docs: reframe reproducibility note as OSS breakout flex
"You'd need access to my private repos" → "Bookface and Posthaven are private, but gstack and gbrain are open-sourced with tens of thousands of GitHub stars and tens of thousands of confirmed regular users, among the most-used OSS projects in the world that didn't exist three months ago." Keeps the `gh repo list` command at the end for the actual reproducibility instruction. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
71254636ac |
docs: update gstack/gbrain adoption numbers in LOC controversy post
gstack: "1,000+ distinct project installations" → "tens of thousands of daily active users" (telemetry-reported, community tier, opt-in). gbrain: "small set of beta testers" → "hundreds of beta testers running it live." Both are the accurate current numbers. The concession paragraph below (about shipped != adopted at scale for the long-tail repos) still reads correctly since it's about the corpus as a whole, not gstack/gbrain specifically. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
dc140fe8ce |
docs: harden ON_THE_LOC_CONTROVERSY against Cramer + neckbeard critiques
Reframes the thesis as "engineers can fly now" (amplification, not replacement) and fortifies the soft spots critics will attack. Added: - Flight-thesis opener: pilot vs walker, leverage not replacement. - Second deflation layer for AI verbosity (on top of NCLOC). Headline moves from 810x to 408x after generous 2x AI-boilerplate cut, with explicit sensitivity analysis showing the number is still large under pessimistic priors (5x → 162x, 10x → 81x, 100x impossible). - Weekly distribution check (kills "you had one burst week" attack). - Revert rate (2.0%) and post-merge fix rate (6.3%) with OSS comparables (K8s/Rails/Django band). Addresses "where are your error rates" directly. - Named production adoption signals (gstack 1000+ installs, gbrain beta, resend_robot paying API) with explicit concession that "shipped != used at scale" for most of the corpus. - Harder steelman: 5 specific concessions with quantified pivot points (e.g., "if 2013 baseline was 3.5x higher, 810x → 228x, still high"). Removed factual error: Posterous acquisition paragraph (Garry had already left Posterous by 2011, so the "Twitter bought our private repos" excuse for the 2013 corpus gap doesn't apply). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
9ec4ab7eb9 |
codex + Apple Silicon hardening wave (v0.18.4.0) (#1056)
* fix: ad-hoc codesign compiled binaries on Apple Silicon after build On some Apple Silicon machines, Bun's --compile produces a corrupt or linker-only code signature. macOS kills these binaries with SIGKILL (exit 137, zsh: killed) before they execute a single instruction. Add a post-build codesign step to setup that runs only on Darwin arm64: 1. Remove the corrupt/linker-only signature (required — a direct re-sign fails with 'invalid or unsupported format for signature') 2. Apply a fresh ad-hoc signature The step is idempotent, costs <1s, and is what Bun's own docs recommend for distributed standalone executables. All four compiled binaries are covered: browse, find-browse, design, and gstack-global-discover. Failure is a non-fatal warning so Intel/CI builds are unaffected. Fixes #997 * fix: prevent codex exec stdin deadlock with </dev/null redirect codex CLI 0.120.0+ blocks indefinitely when stdin is a non-TTY pipe (Claude Code Bash tool, background bash, CI). The CLI sees a non-TTY stdin and waits for EOF to append it as a <stdin> block, even when the prompt is passed as a positional argument. Fix: add < /dev/null to every codex exec and codex review invocation in the source-of-truth files (scripts/resolvers/*.ts and *.md.tmpl). Generated SKILL.md files will be produced by bun run gen:skill-docs in a subsequent commit (Tension D: template+resolver only, generator is authoritative, not cherry-picked artifacts). Affected source files (16 total invocations): - scripts/resolvers/review.ts (4) - scripts/resolvers/design.ts (3) - codex/SKILL.md.tmpl (5) - autoplan/SKILL.md.tmpl (4) Fixes #971 Co-Authored-By: loning <loning@users.noreply.github.com> Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat: codex/autoplan hardening + Apple Silicon coreutils auto-install Hardens /codex and /autoplan against silent failures surfaced by the #972 stdin fix and #1003 Apple Silicon codesign. Six-layer defense: 1. **Multi-signal auth probe** (new Step 0.5 / Phase 0.5): env-based auth ($CODEX_API_KEY, $OPENAI_API_KEY) OR file-based auth (${CODEX_HOME:-~/.codex}/auth.json). Rejects false negatives that the old file-only check produced for CI / platform-engineer users. 2. **Timeout wrapper** around every codex exec / codex review invocation: gtimeout → timeout → unwrapped fallback chain. On exit 124, surfaces common causes + actionable next step. Guards against model-API stalls not covered by the #972 stdin fix. 3. **Stderr capture in Challenge mode** (codex/SKILL.md.tmpl:208): 2>/dev/null → 2>$TMPERR. Post-invocation grep for auth/login/unauthorized surfaces errors that were previously dropped silently. 4. **Completeness check** in the Python JSON parser: tracks turn.completed events and warns on zero (possible mid-stream disconnect). 5. **Version warning** for known-bad Codex CLI (0.120.0-0.120.2, the range that introduced the stdin deadlock #972 fixes). Anchored regex `(^|[^0-9.])0\.120\.(0|1|2)([^0-9.]|$)` prevents 0.120.10 / 0.120.20 false positives. 6. **Failure telemetry + operational learnings**: codex_timeout, codex_auth_failed, codex_cli_missing, codex_version_warning events land in ~/.gstack/analytics/skill-usage.jsonl behind the existing telemetry opt-in. On timeout (exit 124), auto-logs an operational learning via gstack-learnings-log so future /investigate sessions surface prior hang patterns automatically. **Shared helper** (bin/gstack-codex-probe): consolidates all four pieces (auth probe, version check, timeout wrapper, telemetry logger) into one bash file that /codex and /autoplan source. Namespace-prefixed (_gstack_codex_*) with a unit test that verifies sourcing does not leak shell options into the caller. pathRewrites in host configs rewrite ~/.claude/skills/gstack → $GSTACK_ROOT for Codex, $GSTACK_BIN for Factory/Cursor/etc. **Apple Silicon coreutils auto-install** (setup:264): macOS lacks GNU timeout by default; Homebrew's coreutils installs it as gtimeout to avoid shadowing BSD utilities. ./setup now auto-installs coreutils on Darwin (arch-agnostic — applies to Intel + Apple Silicon) when neither gtimeout nor timeout is present. Opt-out via GSTACK_SKIP_COREUTILS=1 for CI, managed machines, or offline envs. **25 deterministic unit tests** (test/codex-hardening.test.ts): - 8 auth probe combinations (env precedence, whitespace, alternate $CODEX_HOME, corrupt file paths) - 10 version regex cases including 0.120.10 false-positive guards and v-prefixed / multiline output - 4 timeout wrapper + namespace hygiene (bash -n, gtimeout preference, set-option leak check) - 3 telemetry payload schema checks (confirms env values + auth tokens never leak into emitted events) **1 periodic-tier E2E** (test/skill-e2e-autoplan-dual-voice.test.ts): gates the /autoplan dual-voice path — asserts both Claude subagent and Codex voices produce output in Phase 1, OR that [codex-unavailable] is logged when Codex is absent. ~\$1/run, not a CI gate. Golden baseline + gen-skill-docs exclusion list updated for the new codex path references and the 16 < /dev/null redirects from #972. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: plan-review right-sized diff counterbalance (not minimal-diff default) /plan-ceo-review and /plan-eng-review listed "minimal diff" as an engineering preference without counterbalancing language. Reviewers picked up on that and rejected rewrites that should have been approved. The preference is now framed as "right-sized diff" with explicit permission to recommend a rewrite when the existing foundation is broken. Implementation alternatives section in CEO review gets an equal-weight clarification: don't default to minimal viable just because it is smaller. Recommend whichever best serves the user's goal; if the right answer is a rewrite, say so. Three-line tone edit per template, no voice / ETHOS / YC / promotional content change. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * release: v0.18.4.0 — codex + Apple Silicon hardening wave - Apple Silicon codesign fix (#1003 @voidborne-d) - Codex stdin deadlock fix (#972 @loning) - Codex timeout wrapper (gtimeout → timeout → unwrapped fallback) - Multi-signal auth gate for /codex + /autoplan - Codex version warning for known-bad CLI (0.120.0-0.120.2) - Challenge mode stderr capture + completeness check - Plan-review right-sized diff counterbalance - Failure telemetry + auto-log timeout as operational learning - 25 deterministic unit tests + dual-voice periodic E2E Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: voidborne-d <voidborne-d@users.noreply.github.com> Co-authored-by: loning <loning@users.noreply.github.com> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
58e6a94e7c |
fix: correct tax-app exclusion rationale
tax-app is a demo app I built for an upcoming YC channel video,
not an "import-dominated history" as the previous commit claimed.
Excluded because it's not production shipping work, not because
of an import commit.
Updated rationale in scripts/garry-output-comparison.ts's
EXCLUDED_REPOS constant, in docs/ON_THE_LOC_CONTROVERSY.md's
method section + conclusion, and in the README hero wording
("one demo repo" vs the earlier "repos dominated by imported code").
Numbers unchanged — the exclusion itself is the same, just the
reason.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Garry Tan
|
28f7876ea5 |
exclude: tax-app from throughput analysis (import-dominated history)
tax-app's history is one commit of 104K logical lines — an initial import of a codebase, not authored work. Removing it to keep the comparison honest. Changes: - scripts/garry-output-comparison.ts: added EXCLUDED_REPOS constant with tax-app + a one-line rationale. The script now skips excluded repos with a stderr note and deletes any stale output JSON so aggregation loops don't pick up pre-exclusion numbers. - README hero: updated to 810× run rate + 240× YTD (were 880×/260×). Wording updated to "40 public + private repos ... after excluding repos dominated by imported code." - docs/ON_THE_LOC_CONTROVERSY.md: updated all numbers, added an "Exclusions" paragraph explaining tax-app, removed tax-app from the "shipped not WIP" example list. New numbers (2026 through day 108, without tax-app): - To-date: 240× logical SLOC (1,233,062 vs 5,143) - Run rate: 810× per-day pace (11,417 vs 14 logical/day) - Annualized: ~4.2M logical lines projected Future re-runs automatically skip tax-app. Add more exclusions to EXCLUDED_REPOS at the top of the script with a one-line rationale. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
c5e2e1bf66 |
docs: ON_THE_LOC_CONTROVERSY methodology post + README link
Long-form response to the "LOC is a meaningless vanity metric" critique. Covers: - The three branches of the LOC critique and which are right - Why logical SLOC (NCLOC) beats raw LOC as the honest measurement - Full method: author-scoped git diff, regex-classified added lines, aggregated across 41 public + private garrytan/* repos - Both calculations: to-date (260x) and run-rate (879x) - Steelman of the critics (greenfield-vs-maintenance, survivorship bias, quality-adjusted productivity, time-to-first-user) - Reproduction instructions Linked from README hero via a blockquote directly below the number. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
629bb53e97 |
feat(throughput): script natively computes to-date + run-rate multiples
Enhanced scripts/garry-output-comparison.ts so both calculations come out of a single run instead of being reassembled ad-hoc in bash: PerYearResult now includes: - days_elapsed — 365 for past years, day-of-year for current - is_partial — flags the current (in-progress) year - per_day_rate — logical/raw/commits normalized by calendar day - annualized_projection — per_day_rate × 365 Output JSON's `multiples` now has two sibling blocks: - multiples.to_date — raw volume ratios (2026-YTD / 2013-full-year) - multiples.run_rate — per-day pace ratios (apples-to-apples) Back-compat: multiples.logical_lines_added still aliases to_date for older consumers reading the JSON. Updated README hero to cite both (picking up brain/* repo that was missed in the earlier aggregation pass): 2026 run rate: ~880× my 2013 pace (12,382 vs 14 logical lines/day) 2026 YTD: 260× the entire 2013 year Stderr summary now prints both multiples at the end of each run. Full analysis at ~/throughput-analysis-2026-04-18.md (local-only). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
d0645830ca |
docs: run rate vs year-to-date throughput comparison
Two separate numbers in the README hero: - Run rate: ~700× (9,859 logical lines/day in 2026 vs 14/day in 2013) - Year-to-date: 207× (2026 through April 18 already exceeds 2013 full year by 207×) Previous "207× pro-rata" framing mixed full-year 2013 vs partial-year 2026. Run rate is the apples-to-apples normalization; YTD is the "already produced" total. Both are honest; both are compelling; they measure different things. Analysis at ~/throughput-analysis-2026-04-18.md (local-only). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
b37c811ade |
feat: 207× throughput multiple (with private repos + Bookface)
Re-ran scripts/garry-output-comparison.ts across all 41 repos under garrytan/* (15 public + 26 private), including Bookface (YC's internal social network, 2013-era work). 2013 activity: 71 commits, 5,143 logical lines, 4 active repos (bookface, delicounter, tandong, zurb-foundation-wysihtml5) 2026 activity: 350 commits, 1,064,818 logical lines, 15 active repos (gbrain, gstack, gbrowser, tax-app, kumo, tenjin, autoemail, kitsune, easy-chromium-compiles, conductor-playground, garryslist-agent, baku, gstack-website, resend_robot, garryslist-brain) Multiples: - Logical SLOC: 207× (up from 130.2× when including private work) - Raw lines: 223× - Commits/active-week: 3.4× Stopped committing docs/throughput-2013-vs-2026.json — analysis is a local artifact, not repo state. Added docs/throughput-*.json to .gitignore. Full markdown analysis at ~/throughput-analysis-2026-04-18.md (local-only). README multiple is now hardcoded; re-run the script and edit manually when you want to refresh it. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
cd59590c34 |
feat: compute real 2013-vs-2026 throughput multiple (130.2×)
Ran scripts/garry-output-comparison.ts across all 15 public garrytan/* repos. Aggregated results into docs/throughput-2013-vs-2026.json and ran scripts/update-readme-throughput.ts to replace the README placeholder. 2013 public activity: 2 commits, 2,384 logical lines added across 1 week, in 1 repo (zurb-foundation-wysihtml5 upstream contribution). 2026 public activity: 279 commits, 310,484 logical lines added across 17 active weeks, in 3 repos (gbrain, gstack, resend_robot). Multiples (public repos only, apples-to-apples): - Logical SLOC: 130.2× - Commits per active week: 8.2× - Raw lines added: 134.4× Private work at both eras (2013 Bookface at YC, Posterous-era code, 2026 internal tools) is excluded from this comparison. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
00a7a65026 |
test: V1 gate coverage — writing-style resolver + config + jargon + migration + dormancy
Six new gate-tier test files: - test/writing-style-resolver.test.ts — asserts Writing Style section is injected into tier-≥2 preamble, all 6 rules present, jargon list inlined, terse-mode gate condition present, Codex output uses \$GSTACK_BIN (not ~/.claude/), tier-1 does NOT get the section, migration-prompt block present. - test/explain-level-config.test.ts — gstack-config set/get round-trip for default + terse, unknown-value warns + defaults to default, header documents the key, round-trip across set→set→get. - test/jargon-list.test.ts — shape + ~50 terms + no duplicates (case-insensitive) + includes canonical high-signal terms. - test/v0-dormancy.test.ts — 5D dimension names + archetype names forbidden in default-mode tier-≥2 SKILL.md output, except for plan-tune and office-hours where they're load-bearing. - test/readme-throughput.test.ts — script replaces anchor with number on happy path, writes PENDING marker when JSON missing, CI gate asserts committed README contains no PENDING string. - test/upgrade-migration-v1.test.ts — fresh run writes pending flag, idempotent after user-answered, pre-existing explain_level counts as answered. All 95 V1 test-expect() calls pass. Full suite: 0 failures. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
dfc091fca1 |
chore: regenerate SKILL.md files + golden fixtures for V1
Mechanical regeneration from the updated templates in prior commits: - Writing Style section now appears in tier-≥2 skill output. - EXPLAIN_LEVEL + WRITING_STYLE_PENDING echoes in preamble bash. - V1 migration-prompt block fires conditionally on first upgrade. - Jargon list inlined into preamble prose at gen time. - Retro template's logical SLOC + weighted commits order applied. Regenerated for all 8 hosts via bun run gen:skill-docs --host all. Golden ship-skill fixtures refreshed from regenerated outputs. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
18fc95c0a0 |
docs(v1): README hero reframe + writing-style + CHANGELOG + version bump to 1.0.0.0
README.md: - Hero removes "600,000+ lines of production code" framing; replaces with the computed 2013-vs-2026 pro-rata multiple (via <!-- GSTACK-THROUGHPUT-PLACEHOLDER --> anchor, filled by the update-readme-throughput build step). - Hiring callout: "ship real products at AI-coding speed" instead of "10K+ LOC/day." - New Writing Style section (~80 words) between Quick start and Install: "v1 prompts = simpler" framing, outcome-language example, terse-mode opt-out, pointer to /plan-tune. CLAUDE.md: one-paragraph Writing style (V1) note under project conventions, linking to preamble resolver + V1 design docs. CHANGELOG.md: V1 entry on top of v0.19.0.0 with user-facing narrative (what changes, how to opt out, for-contributors notes). Mentions scope reduction — pacing overhaul ships in V1.1. CONTRIBUTING.md: one-paragraph note on jargon-list.json maintenance (PR to add/remove terms; regenerate via gen:skill-docs). VERSION + package.json: bump to 1.0.0.0. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
2c404f9bd0 |
feat(retro): surface logical SLOC + weighted commits above raw LOC
V1 reorders the /retro summary table to lead with features shipped, then commits + weighted commits (commits × files-touched capped at 20), then PRs merged, then logical SLOC added as the primary code-volume metric. Raw LOC stays present but is demoted to context. Rationale inline in the template: ten lines of a good fix is not less shipping than ten thousand lines of scaffold. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
d840ab67f4 |
feat: LOC reframe tooling — throughput comparison + README updater + scc installer
Three new scripts: - scripts/garry-output-comparison.ts — enumerates Garry-authored commits in 2013 + 2026 on public repos, extracts ADDED lines from git diff, classifies as logical SLOC via scc --stdin (regex fallback if scc missing). Writes docs/throughput-2013-vs-2026.json with per-language breakdown + explicit caveats (public repos only, commit-style drift, private-work exclusion). - scripts/update-readme-throughput.ts — reads the JSON if present, replaces the README's <!-- GSTACK-THROUGHPUT-PLACEHOLDER --> anchor with the computed multiple (preserving the anchor for future runs). If JSON missing, writes GSTACK-THROUGHPUT-PENDING marker that CI rejects — forcing the build to run before commit. - scripts/setup-scc.sh — standalone OS-detecting installer for scc. Not a package.json dependency (95% of users never run throughput). Brew on macOS, apt on Linux, GitHub releases link on Windows. Two-string anchor pattern (PLACEHOLDER vs PENDING) prevents the pipeline from destroying its own update path. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
6c4f72a426 |
feat: V1 upgrade migration — writing-style opt-out prompt
New migration script following existing v0.15.2.0.sh / v0.16.2.0.sh pattern. Writes a .writing-style-prompt-pending flag file on first run post-upgrade. The preamble's migration-prompt block reads the flag and fires a one-time AskUserQuestion offering the user a choice between the new default writing style and restoring V0 prose via \`gstack-config set explain_level terse\`. Idempotent via flag files; if the user has already set explain_level explicitly, counts as answered and skips. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
34eb39285d |
feat(gstack-config): validate explain_level + document in header
Adds explain_level: default|terse to the annotated config header with
a one-line description. Whitelists valid values; on set of an unknown
value, prints a specific warning ("explain_level '\$VALUE' not
recognized. Valid values: default, terse. Using default.") and writes
the default value. Matches V1 preamble's EXPLAIN_LEVEL echo expectation.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Garry Tan
|
ada1a2a925 |
feat(preamble): V1 Writing Style section + EXPLAIN_LEVEL echo + migration prompt
Adds a new Writing Style section to tier-≥2 preamble output composing with
the existing AskUserQuestion Format section. Six rules: jargon glossed on
first use per skill invocation (from scripts/jargon-list.json), outcome-
framed questions, short sentences, decisions close with user impact,
gloss-on-first-use even if user pasted term, user-turn override for "be
terse" requests. Baked conditionally (skip if EXPLAIN_LEVEL: terse).
Adds EXPLAIN_LEVEL preamble echo using \${binDir} (host-portable matching
V0 QUESTION_TUNING pattern). Adds WRITING_STYLE_PENDING echo reading a
flag file written by the V0→V1 upgrade migration; on first post-upgrade
skill run, the agent fires a one-time AskUserQuestion offering terse mode.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Garry Tan
|
5b2790dc5b |
feat: curated jargon list for V1 writing-style glossing
Repo-owned list of ~50 high-frequency technical terms (idempotent, race condition, N+1, backpressure, etc.) that gstack glosses on first use in tier-≥2 skill output. Baked into generated SKILL.md prose at gen-skill-docs time. Terms not on this list are assumed plain-English enough. Contributions via PR. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
83c0d0aac3 |
docs: add PLAN_TUNING_V1 + PACING_UPDATES_V0 design docs
Captures the V1 design (ELI10 writing + LOC reframe) in docs/designs/PLAN_TUNING_V1.md and the extracted V1.1 pacing-overhaul plan in docs/designs/PACING_UPDATES_V0.md. V1 scope was reduced from the original bundled pacing + writing-style plan after three engineering-review passes revealed structural gaps in the pacing workstream that couldn't be closed via plan-text editing. TODOS.md P0 entry links to V1.1. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
a699018ec6 |
Merge remote-tracking branch 'origin/main' into garrytan/plan-tune-skill
Conflicts resolved: - VERSION / package.json: keep 0.19.0.0 (our MINOR bump stays above main's new 0.18.3.0 — community wave v0.18.3.0 + our plan-tune v0.19.0.0 both ship, ours on top). - CHANGELOG.md: preserved both entries in order — v0.19.0.0 (plan-tune) above v0.18.3.0 (community wave). No version gaps. - .github/docker/Dockerfile.ci: main's Hetzner-mirror swap is a better root cause fix than my retry-only patch (route-local for Ubicloud runners, avoids archive.ubuntu.com entirely). Combined: main's mirror swap PLUS my defense-in-depth layers on top (apt retries config, --retry-connrefused on curl, and outer shell-loop retries for apt-get update). Mirror swap solves the root cause; retries handle the rare case where even Hetzner blips. Main added: - v0.18.3.0 (#1028): community wave — Windows cookie import, OpenCode install, permission-prompt cleanup, $B server persistence across Bash calls, cookie picker fix, OpenClaw frontmatter fix. - Dockerfile.ci Hetzner mirror swap (from the same wave). Regenerated all SKILL.md files after merge so they reflect main's design-* template changes AND our question-tuning preamble additions. Full free test suite: 1162 pass, 0 fail, 113 skip across 29 files, 7903 expect() calls. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
1211b6b40b |
community wave: 6 PRs + hardening (v0.18.1.0) (#1028)
* fix: extend tilde-in-assignment fix to design resolver + 4 skill templates PR #993 fixed the Claude Code permission prompt for `scripts/resolvers/browse.ts` and `gstack-upgrade/SKILL.md.tmpl`. Same bug lives in three more places that weren't on the contributor's branch: - `scripts/resolvers/design.ts` (3 spots: D=, B=, and _DESIGN_DIR=) - `design-shotgun/SKILL.md.tmpl` (_DESIGN_DIR=) - `plan-design-review/SKILL.md.tmpl` (_DESIGN_DIR=) - `design-consultation/SKILL.md.tmpl` (_DESIGN_DIR=) - `design-review/SKILL.md.tmpl` (REPORT_DIR=) Replaces bare `~/` with quoted `"$HOME/..."` in the source-of-truth files, then regenerates. `grep -rEn '^[A-Za-z_]+=~/' --include="SKILL.md" .` now returns zero hits across all hosts (claude, codex, cursor, gbrain, hermes). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(openclaw): make native skills codex-friendly (#864) Normalizes YAML frontmatter on the 4 hand-authored OpenClaw skills so stricter parsers like Codex can load them. Codex CLI was rejecting these files with "mapping values are not allowed in this context" on colons inside unquoted description scalars. - Drops non-standard `version` and `metadata` fields - Rewrites descriptions into simple "Use when..." form (no inline colons) - Adds a regression test enforcing strict frontmatter (name + description only) Verified live: Codex CLI now loads the skills without errors. Observed during /codex outside-voice run on the eval-community-prs plan review — Codex stderr tripped on these exact files, which was real-world confirmation the fix is needed. Dropped the connect-chrome changes from the original PR (the symlink removal is out of scope for this fix; keeping connect-chrome -> open-gstack-browser). Co-Authored-By: Cathryn Lavery <cathrynlavery@users.noreply.github.com> Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(browse): server persists across Claude Code Bash calls The browse server was dying between Bash tool invocations in Claude Code because: 1. SIGTERM: The Claude Code sandbox sends SIGTERM to all child processes when a Bash command completes. The server received this and called shutdown(), deleting the state file and exiting. 2. Parent watchdog: The server polls BROWSE_PARENT_PID every 15s. When the parent Bash shell exits (killed by sandbox), the watchdog detected it and called shutdown(). Both mechanisms made it impossible to use the browse tool across multiple Bash calls — every new `$B` invocation started a fresh server with no cookies, no page state, and no tabs. Fix: - SIGTERM handler: log and ignore instead of shutdown. Explicit shutdown is still available via the /stop command or SIGINT (Ctrl+C). - Parent watchdog: log once and continue instead of shutdown. The existing idle timeout (30 min) handles eventual cleanup. The /stop command and SIGINT still work for intentional shutdown. Windows behavior is unchanged (uses taskkill /F which bypasses signal handlers). Tested: browse server survives across 5+ separate Bash tool calls in Claude Code, maintaining cookies, page state, and navigation. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(browse): gate #994 SIGTERM-ignore to normal mode only PR #994 made browse persist across Claude Code Bash calls by ignoring SIGTERM and parent-PID death, relying on the 30-min idle timeout for eventual cleanup. Codex outside-voice review caught that the idle timeout doesn't apply in two modes: headed mode (/open-gstack-browser) and tunnel mode (/pair-agent). Both early-return from idleCheckInterval. Combined with #994's ignore-SIGTERM, those sessions would leak forever after the user disconnects — a real resource leak on shared machines where multiple /pair-agent sessions come and go. Fix: gate SIGTERM-ignore and parent-PID-watchdog-ignore to normal (headless) mode only. Headed + tunnel modes respect both signals and shutdown cleanly. Idle timeout behavior unchanged. Also documents the deliberate contract change for future contributors — don't re-add global SIGTERM shutdown thinking it's missing; it's intentionally scoped. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: keep cookie picker alive after cli exits Fixes garrytan/gstack#985 * fix: add opencode setup support * feat(browse): add Windows browser path detection and DPAPI cookie decryption - Extend BrowserPlatform to include win32 - Add windowsDataDir to BrowserInfo; populate for Chrome, Edge, Brave, Chromium - getBaseDir('win32') → ~/AppData/Local - findBrowserMatch checks Network/Cookies first on Windows (Chrome 80+) - Add getWindowsAesKey() reading os_crypt.encrypted_key from Local State JSON - Add dpapiDecrypt() via PowerShell ProtectedData.Unprotect (stdin/stdout) - decryptCookieValue branches on platform: AES-256-GCM (Windows) vs AES-128-CBC (mac/linux) - Fix hardcoded /tmp → TEMP_DIR from platform.ts in openDbFromCopy Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(browse): Windows cookie import — profile discovery, v20 detection, CDP fallback Three bugs fixed in cookie-import-browser.ts: - listProfiles() and findInstalledBrowsers() now check Network/Cookies on Windows (Chrome 80+ moved cookies from profile/Cookies to profile/Network/Cookies) - openDb() always uses copy-then-read on Windows (Chrome holds exclusive locks) - decryptCookieValue() detects v20 App-Bound Encryption with specific error code Added CDP-based extraction fallback (importCookiesViaCdp) for v20 cookies: - Launches Chrome headless with --remote-debugging-port on the real profile - Extracts cookies via Network.getAllCookies over CDP WebSocket - Requires Chrome to be closed (v20 keys are path-bound to user-data-dir) - Both cookie picker UI and CLI direct-import paths auto-fall back to CDP Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(browse): document CDP debug port security + log Chrome version on v20 fallback Follow-up to #892 per Codex outside-voice review. Two small additions to the Windows v20 App-Bound Encryption CDP fallback: 1. Inline comment documenting the deliberate security posture of the --remote-debugging-port. Chrome binds it to 127.0.0.1 by default, so the threat model is local-user-only (which is no worse than baseline — local attackers can already read the cookie DB). Random port 9222-9321 is for collision avoidance, not security. Chrome is always killed in finally. 2. One-time Chrome version log on CDP entry via /json/version. When Chrome inevitably changes v20 key format or /json/list shape in a future major version, logs will show exactly which version users are hitting. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: v0.18.1.0 — community wave (6 PRs + hardening) VERSION bump + users-first CHANGELOG entry for the wave: - #993 tilde-in-assignment fix (byliu-labs) - #994 browse server persists across Bash calls (joelgreen) - #996 cookie picker alive after cli exits (voidborne-d) - #864 OpenClaw skills codex-friendly (cathrynlavery) - #982 OpenCode native setup (breakneo) - #892 Windows cookie import + DPAPI + v20 CDP fallback (msr-hickory) Plus 3 follow-up hardening commits we own: - Extended tilde fix to design resolver + 4 more skill templates - Gated #994 SIGTERM-ignore to normal mode only (headed/tunnel preserve shutdown) - Documented CDP debug port security + log Chrome version on v20 fallback Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: review pass — package.json version, import dedup, error context, stale help Findings from /review on the wave PR: - [P1] package.json version was 0.18.0.1 but VERSION is 0.18.1.0, failing test/gen-skill-docs.test.ts:177 "package.json version matches VERSION file". Bumped package.json to 0.18.1.0. - [P2] Duplicate import of cookie-picker-routes in browse/src/server.ts (handleCookiePickerRoute at line 20 + hasActivePicker at line 792). Merged into single import at top. - [P2] cookie-import-browser.ts:494 generic rethrow loses underlying error. Now preserves the message so "ENOENT" vs "JSON parse error" vs "permission denied" are distinguishable in user output. - [P3] setup:46 "Missing value for --host" error message listed an incomplete set of hosts (missing factory, openclaw, hermes, gbrain). Aligned with the "Unknown value" error on line 94. Kept as-is (not real issues): - cookie-import-browser.ts:869 empty catch on Chrome version fetch is the correct pattern for best-effort diagnostics (per slop-scan philosophy in CLAUDE.md — fire-and-forget failures shouldn't throw). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * test(watchdog): invert test 3 to match merged #994 behavior main #1025 added browse/test/watchdog.test.ts with test 3 expecting the old "watchdog kills server when parent dies" behavior. The merge with this branch's #994 inverted that semantic — the server now STAYS ALIVE on parent death in normal headless mode (multi-step QA across Claude Code Bash calls depends on this). Changes: - Renamed test 3 from "watchdog fires when parent dies" to "server STAYS ALIVE when parent dies (#994)". - Replaced 25s shutdown poll with 20s observation window asserting the server remains alive after the watchdog tick. - Updated docstring to document all 3 watchdog invariants (env-var disable, headed-mode disable, headless persists) and note tunnel-mode coverage gap. Verification: bun test browse/test/watchdog.test.ts → 3 pass, 0 fail (22.7s). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(ci): switch apt mirror to Hetzner to bypass Ubicloud → archive.ubuntu.com timeouts Both build attempts of `.github/docker/Dockerfile.ci` failed at `apt-get update` with persistent connection timeouts to archive.ubuntu.com:80 and security.ubuntu.com:80 — 90+ seconds of "connection timed out" against every Ubuntu IP. Not a transient blip; this PR doesn't touch the Dockerfile, and a re-run reproduced the same failure across all 9 mirror IPs. Root cause: Ubicloud runners (Hetzner FSN1-DC21 per runner output) have unreliable HTTP-port-80 routing to Ubuntu's official archive endpoints. Fix: - Rewrite /etc/apt/sources.list.d/ubuntu.sources (deb822 format in 24.04) to use https://mirror.hetzner.com/ubuntu/packages instead. Hetzner's mirror is publicly accessible from any cloud (not Hetzner-only despite the name) and route-local for Ubicloud's actual host. Solves both reliability and latency. - Add a 3-attempt retry loop around both `apt-get update` calls as belt-and-suspenders. Even Hetzner's mirror can have brief blips, and the retry costs nothing when the first attempt succeeds. Verification: the workflow will rebuild on push. Local `docker build` not practical for a 12-step image with bun + claude + playwright deps + a 10-min cold install. Trusting CI. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(ci): use HTTP for Hetzner apt mirror (base image lacks ca-certificates) Previous commit switched to https://mirror.hetzner.com/... which proved the mirror is reachable and routes correctly (no more 90s timeouts), but exposed a chicken-and-egg: ubuntu:24.04 ships without ca-certificates, and that's exactly the package we're installing. Result: "No system certificates available. Try installing ca-certificates." Fix: use http:// for the Hetzner mirror. Apt's security model verifies package integrity via GPG-signed Release files, not TLS, so HTTP here is no weaker than the upstream defaults (Ubuntu's official sources also default to HTTP for the same reason). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> Co-authored-by: Cathryn Lavery <cathrynlavery@users.noreply.github.com> Co-authored-by: Joel Green <thejoelgreen@gmail.com> Co-authored-by: d 🔹 <258577966+voidborne-d@users.noreply.github.com> Co-authored-by: Break <breakneo@gmail.com> Co-authored-by: Michael Spitzer-Rubenstein <msr.ext@hickory.ai> |
||
|
Garry Tan
|
c26d5fac78 |
fix(ci): harden Dockerfile.ci against transient Ubuntu mirror failures
The CI image build failed with: E: Failed to fetch http://archive.ubuntu.com/ubuntu/pool/main/... Connection failed [IP: 91.189.92.22 80] ERROR: process "/bin/sh -c apt-get update && apt-get install ..." did not complete successfully: exit code: 100 archive.ubuntu.com periodically returns "connection refused" on individual regional mirrors. Without retry logic a single failed fetch nukes the whole Docker build. Three defenses, layered: 1. /etc/apt/apt.conf.d/80-retries — apt fetches each package up to 5 times with a 30s timeout. Handles per-package flakes. 2. Shell-loop retry around the whole apt-get step (x3, 10s sleep) — handles the case where apt-get update itself can't reach any mirror. 3. --retry 5 --retry-delay 5 --retry-connrefused on all curl fetches (bun install script, GitHub CLI keyring, NodeSource setup script). Applied to every apt-get and curl call in the Dockerfile. No behavior change on happy path — only kicks in when mirrors blip. Fixes the build-image job that was blocking CI on the /plan-tune PR. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
bab052e10a |
Merge remote-tracking branch 'origin/main' into garrytan/plan-tune-skill
Conflicts resolved: - VERSION: keep 0.19.0.0 (our MINOR bump stays above main's new 0.18.2.0) - package.json: bumped to 0.19.0.0 to match VERSION (test/gen-skill-docs.test.ts asserts they match) - CHANGELOG.md: keep both entries — our v0.19.0.0 on top, main's v0.18.2.0 below it, preserving the full version history Main added v0.18.2.0 (#1030): context-rot defense for /ship (subagent isolation for coverage/plan-completion/greptile/docs steps + clean integer step numbering). Regenerated all SKILL.md files after merge so they reflect both main's ship template changes AND our preamble additions (question-tuning section). Full free test suite: 1158 pass, 0 fail, 113 skip across 28 files, 7855 expect() calls. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
b3eaffce07 |
feat: context rot defense for /ship — subagent isolation + clean step numbering (v0.18.1.0) (#1030)
* refactor: renumber /ship steps to clean integers (1-20)
Replaces fractional step numbers (1.5, 2.5, 3.25, 3.4, 3.45, 3.47, 3.48,
3.5, 3.55, 3.56, 3.57, 3.75, 3.8, 5.5, 6.5, 8.5, 8.75) with clean
integers 1 through 20, plus allowed resolver sub-steps 8.1, 8.2,
9.1, 9.2, 9.3. Fractional numbering signaled "optional appendix" and
contributed to /ship's habit of skipping late-stage steps.
Affects:
- ship/SKILL.md.tmpl (all headings + ~30 cross-references)
- scripts/resolvers/review.ts (ship-side 3.47/3.48/3.57/3.8 conditionals)
- scripts/resolvers/review-army.ts (ship-side 3.55/3.56 conditionals)
- scripts/resolvers/testing.ts (ship-side 2.5/3.4 references, 5 sites)
- scripts/resolvers/utility.ts (CHANGELOG heading gets Step 13 prefix)
- test/gen-skill-docs.test.ts (5 step-number assertions updated)
- test/skill-validation.test.ts (3 step-number assertions updated)
/review step numbering (1.5, 2.5, 4.5, 5.5-5.8) intentionally unchanged —
only the ship-side of each isShip conditional was updated.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat: subagent isolation for /ship's 4 context-heaviest sub-workflows
Fights context rot. By late /ship, the parent context is bloated with
500-1,750 lines of intermediate tool output from tests, coverage audits,
reviews, adversarial checks, and PR body construction. The model is
at its least intelligent when it reaches doc-sync — which is why
/document-release was being skipped ~80% of the time.
Applies subagent dispatch (proven pattern from Review Army at Step 9.1
and Adversarial at Step 11) to four sub-workflows where the parent
only needs the conclusion, not the intermediate output:
- Step 7 (Test Coverage Audit) — subagent returns coverage_pct, gaps,
diagram, tests_added
- Step 8 (Plan Completion Audit) — subagent returns total_items, done,
changed, deferred, summary
- Step 10 (Greptile Triage) — subagent fetches + classifies, parent
handles user interaction and commits fixes (AskUserQuestion + Edit
can't run in subagents)
- Step 18 (Documentation Sync) — subagent invokes full /document-release
skill in fresh context; parent embeds documentation_section in PR body
Sequencing fix for Step 18: runs AFTER Step 17 (Push) and BEFORE Step 19
(Create PR). The PR is created once from final HEAD with the
## Documentation section baked into the initial body — no create-then-
re-edit dance, no race conditions with document-release's own PR body
editor.
Adds "You are NOT done" guardrail after Step 17 (Push) to break the
natural stopping point that currently causes doc-release skips.
Each subagent falls back to inline execution if it fails or returns
invalid JSON. /ship never blocks on subagent failure.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* test: regression guard for /ship step numbering
Three regression guards in skill-validation.test.ts to prevent future
drift back to fractional step numbering:
1. ship/SKILL.md.tmpl contains no fractional step numbers except the
allowed resolver sub-steps (8.1, 8.2, 9.1, 9.2, 9.3). A contributor
adding "Step 3.75" next month will fail this test with a clear error.
2. ship/SKILL.md main headings use clean integer step numbers. If a
renumber accidentally leaves a decimal heading, this catches it.
3. review/SKILL.md step numbers unchanged — regression guard for the
resolver conditionals in review.ts/review-army.ts. If a future edit
accidentally touches the review-side of an isShip ternary, /review's
fractional numbering (1.5, 4.5, 5.7) would vanish. This test catches
that cross-contamination.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* docs: sync ship step references after renumber
CLAUDE.md: "At /ship time (Step 5)" → "(Step 13)" — CHANGELOG is now
explicitly Step 13 after the renumber (was implicit between old
Step 4 and Step 5.5).
TODOS.md: "Step 3.4 coverage audit" → "Step 7" — references the open
TODO for auto-upgrading ★-rated tests, which hooks into the coverage
audit step.
Both are historical references to ship's step numbering that became
stale when clean integer renumbering landed in
|
||
|
Garry Tan
|
bd44c27a18 |
chore: bump version and changelog (v0.19.0.0) — /plan-tune v1
Ships /plan-tune as observational substrate: typed question registry, dual-track developer profile (declared + inferred), explicit per-question preferences with user-origin gate, inline tune: feedback across every tier >= 2 skill, unified developer-profile.json with migration from builder-profile.jsonl. Scope rolled back from initial CEO EXPANSION plan after outside-voice review (Codex). 6 deferrals tracked as P0 TODOs with explicit acceptance criteria: E1 substrate wiring, E3 narrative/vibe, E4 blind-spot coach, E5 LANDED celebration, E6 auto-adjustment, E7 psychographic auto-decide. See docs/designs/PLAN_TUNING_V0.md for the full design record. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
da190c2ccd | Merge remote-tracking branch 'origin/main' into garrytan/plan-tune-skill | ||
|
Garry Tan
|
2b3f9676f2 |
test: E2E test for /plan-tune plain-English inspection flow (gate tier)
test/skill-e2e-plan-tune.test.ts — verifies /plan-tune correctly routes
plain-English intent ("review the questions I've been asked") to the
Review question log section without requiring CLI subcommand syntax.
Seeds a synthetic question-log.jsonl with 3 entries exercising:
- override behavior (user chose expand over recommended selective)
- one-way door respect (user followed ship-test-failure-triage recommendation)
- two-way override (user skipped recommended changelog polish)
Invokes the skill via `claude -p` and asserts:
- Agent surfaces >= 2 of 3 logged question_ids in output
- Agent notices override/skip behavior from the log
- Exit reason is success or error_max_turns (not agent-crash)
Gate-tier because the core v1 DX promise is plain-English intent routing.
If it requires memorized subcommands or breaks on natural language, that's
a regression of the defining feature.
Registered in test/helpers/touchfiles.ts with dependencies:
- plan-tune/** (skill template + generated md)
- scripts/question-registry.ts (required for log lookup)
- scripts/psychographic-signals.ts, scripts/one-way-doors.ts (derive path)
- bin/gstack-question-log, gstack-question-preference, gstack-developer-profile
Skipped when EVALS_ENABLED is not set; runs on `bun run test:evals`.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Garry Tan
|
0427c957f2 |
test: end-to-end pipeline + preamble injection coverage
Added 6 tests to test/plan-tune.test.ts:
Preamble injection (3 tests):
- tier 2+ includes Question Tuning section with preference check, log,
and user-origin gate language ('profile-poisoning defense', 'inline-user')
- tier 1 does NOT include the prose section (QUESTION_TUNING bash echo
still fires since it's in the bash block all tiers share)
- codex host swaps binDir references to $GSTACK_BIN
End-to-end pipeline (3 tests) — real binaries working together, not mocks:
- Log 5 expand choices → --derive → profile shows scope_appetite > 0.5
(full log → registry lookup → signal map → normalization round-trip)
- --write source: inline-tool-output rejected; --read confirms no pref
was persisted (the profile-poisoning defense actually works end-to-end)
- Migrate a 3-session legacy file; confirm legacy gstack-builder-profile
shim still returns SESSION_COUNT: 3, TIER: welcome_back, CROSS_PROJECT: true
test/plan-tune.test.ts now has 47 tests total.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Garry Tan
|
b7c6150b6f |
feat: /plan-tune skill — conversational inspection + preferences
plan-tune/SKILL.md.tmpl: the user-facing skill for /plan-tune v1. Routes
plain-English intent to one of 8 flows:
- Enable + setup (first-time): 5 declaration questions mapping to the
5 psychographic dimensions (scope_appetite, risk_tolerance,
detail_preference, autonomy, architecture_care). Writes to
developer-profile.json declared.*.
- Inspect profile: plain-English rendering of declared + inferred + gap.
Uses word bands (low/balanced/high) not raw floats. Shows vibe archetype
when calibration gate is met.
- Review question log: top-20 question frequencies with follow/override
counts. Highlights override-heavy questions as candidates for never-ask.
- Set a preference: normalizes "stop asking me about X" → never-ask, etc.
Confirms ambiguous phrasings before writing via gstack-question-preference.
- Edit declared profile: interprets free-form ("more boil-the-ocean") and
CONFIRMS before mutating declared.* (trust boundary per Codex #15).
- Show gap: declared vs inferred diff with plain-English severity bands
(close / drift / mismatch). Never auto-updates declared from the gap.
- Stats: preference counts + diversity/calibration status.
- Enable / disable: gstack-config set question_tuning true|false.
Design constraints enforced:
- Plain English everywhere. No CLI subcommand syntax required. Shortcuts
(`profile`, `vibe`, `stats`, `setup`) exist but optional.
- user-origin gate on tune: writes. source: "plan-tune" for user-invoked
/plan-tune; source: "inline-user" for inline tune: from other skills.
- One-way doors override never-ask (safety, surfaced to user).
- No behavior adaptation in v1 — this skill inspects and configures only.
Generates plan-tune/SKILL.md at ~11.6k tokens, well under the 100KB ceiling.
Generated for all hosts via `bun run gen:skill-docs --host all`.
Full free test suite: 1149 pass, 0 fail, 113 skip across 28 files.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Garry Tan
|
822e843a60 |
fix: headed browser auto-shutdown + disconnect cleanup (v0.18.1.0) (#1025)
* fix: headed browser no longer auto-shuts down after 15 seconds The parent-process watchdog in server.ts polls the spawning CLI's PID every 15s and self-terminates if it is gone. The connect command in cli.ts exits with process.exit(0) immediately after launching the server, so the watchdog would reliably kill the headed browser within ~15s. This contradicted the idle timer's own design: server.ts:745 explicitly skips headed mode because "the user is looking at the browser. Never auto-die." The watchdog had no such exemption. Two-layer fix: 1. CLI layer: connect handler always sets BROWSE_PARENT_PID=0 (was only pass-through for pair-agent subprocesses). The user owns the headed browser lifecycle; cleanup happens via browser disconnect event or $B disconnect. 2. CLI layer: startServer() honors caller's BROWSE_PARENT_PID=0 in the headless spawn path too. Lets CI, non-interactive shells, and Claude Code Bash calls opt into persistent servers across short-lived CLI invocations. 3. Server layer: defense-in-depth. Watchdog now also skips when BROWSE_HEADED=1, so even if a future launcher forgets PID=0, headed browsers won't die. Adds log lines when the watchdog is disabled so lifecycle debugging is easier. Four community contributors diagnosed variants of this bug independently. Thanks for the clear analyses and reproductions. Closes #1020 (rocke2020) Closes #1018 (sanghyuk-seo-nexcube) Closes #1012 (rodbland2021) Closes #986 (jbetala7) Closes #1006 Closes #943 Co-Authored-By: rocke2020 <noreply@github.com> Co-Authored-By: sanghyuk-seo-nexcube <noreply@github.com> Co-Authored-By: rodbland2021 <noreply@github.com> Co-Authored-By: jbetala7 <noreply@github.com> Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: disconnect handler runs full cleanup before exiting When the user closed the headed browser window, the disconnect handler in browser-manager.ts called process.exit(2) directly, bypassing the server's shutdown() function entirely. That meant: - sidebar-agent daemon kept polling a dead server - session state wasn't saved - Chromium profile locks (SingletonLock, SingletonSocket, SingletonCookie) weren't cleaned — causing "profile in use" errors on next $B connect - state file at .gstack/browse.json was left stale Now the disconnect handler calls onDisconnect(), which server.ts wires up to shutdown(2). Full cleanup runs first, then the process exits with code 2 — preserving the existing semantic that distinguishes user-close (exit 2) from crashes (exit 1). shutdown() now accepts an optional exitCode parameter (default 0) so the SIGTERM/SIGINT paths and the disconnect path can share cleanup code while preserving their distinct exit codes. Surfaced by Codex during /plan-eng-review of the watchdog fix. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: pre-existing test flakiness in relink.test.ts The 23 tests in this file all shell out to gstack-config + gstack-relink (bash scripts doing subprocess work). Under parallel bun test load, those subprocess spawns contend with other test suites and each test can drift ~200ms past Bun's 5s default timeout, causing 5+ flaky timeouts per run in the gate-tier ship gate. Wrap the `test` import to default the per-test timeout to 15s. Explicit per-test timeouts (third arg) still win, so individual tests can lower it if needed. No behavior change — only gives subprocess-heavy tests more headroom under parallel load. Noticed by /ship pre-flight test run. Unrelated to the main PR fix but blocking the gate, so fixing as a separate commit per the test ownership protocol. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: SIGTERM/SIGINT shutdown exit code regression Node's signal listeners receive the signal name ('SIGTERM' / 'SIGINT') as the first argument. When shutdown() started accepting an optional exitCode parameter in the prior disconnect-cleanup commit, the bare `process.on('SIGTERM', shutdown)` registration started silently calling shutdown('SIGTERM'). The string passed through to process.exit(), Node coerced it to NaN, and the process exited with code 1 instead of 0. Wrap both listeners so they call shutdown() with no args — signal name never leaks into the exitCode slot. Surfaced by /ship's adversarial subagent. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: onDisconnect async rejection leaves process running The disconnect handler calls this.onDisconnect() without awaiting it, but server.ts wires the callback to shutdown(2) — which is async. If that promise rejects, the rejection drops on the floor as an unhandled rejection, the browser is already disconnected, and the server keeps running indefinitely with no browser attached. Add a sync try/catch for throws and a .catch() chain for promise rejections. Both fall back to process.exit(2) so a dead browser never leaves a live server. Also widen the callback type from `() => void` to `() => void | Promise<void>` to match the actual runtime shape of the wired shutdown(2) call. Surfaced by /ship's adversarial subagent. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: honor BROWSE_PARENT_PID=0 with trailing whitespace The strict string compare `process.env.BROWSE_PARENT_PID === '0'` meant any stray newline or whitespace (common from shell `export` in a pipe or heredoc) would fail the check and re-enable the watchdog against the caller's intent. Switch to parseInt + === 0, matching the server's own parseInt at server.ts:760. Handles '0', '0\n', ' 0 ', and unset correctly; non-numeric values (parseInt returns NaN, NaN === 0 is false) fail safe — watchdog stays active, which is the safe default for unexpected input. Surfaced by /ship's adversarial subagent. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: preserve bun:test sub-APIs in relink test wrapper The previous commit wrapped bun:test's `test` to bump the per-test timeout default to 15s but cast the wrapper `as typeof _bunTest` without copying the sub-properties (`.only`, `.skip`, `.each`, `.todo`, `.failing`, `.if`) from the original. The cast was a lie: the wrapper was a plain function, not the full callable with those chained properties attached. The file doesn't use any of them today, but a future test.only or test.skip would fail with a cryptic "undefined is not a function." Object.assign the original _bunTest's properties onto the wrapper so sub-APIs chain correctly forever. Surfaced by /ship's adversarial subagent. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: bump version and changelog (v0.18.1.0) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * test: regression tests for parent-process watchdog End-to-end tests in browse/test/watchdog.test.ts that prove the three invariants v0.18.1.0 depends on. Each test spawns the real server.ts (not a mock), so any future change that breaks the watchdog logic fails here — the thing /ship's adversarial review flagged as missing. 1. BROWSE_PARENT_PID=0 disables the watchdog Spawns server with PID=0, reads stdout, confirms the "watchdog disabled (BROWSE_PARENT_PID=0)" log line appears and "Parent process ... exited" does NOT. ~2s. 2. BROWSE_HEADED=1 disables the watchdog (server-side guard) Spawns server with BROWSE_HEADED=1 and a bogus parent PID (999999). Proves BROWSE_HEADED takes precedence over a present PID — if the server-side defense-in-depth regresses, the watchdog would try to poll 999999 and fire on the "dead parent." ~2s. 3. Default headless mode: watchdog fires when parent dies The regression guard for the original orphan-prevention behavior. Spawns a real `sleep 60` parent and a server watching its PID, then kills the parent and waits up to 25s for the server to exit. The watchdog polls every 15s so first tick is 0-15s after death, plus shutdown() cleanup. ~18s. Total runtime: ~21s for all 3 tests. They catch the class of bug this branch exists to fix: "does the process live or die when it should?" Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: rocke2020 <noreply@github.com> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
c837e2403e |
chore: regenerate SKILL.md files with question-tuning section
bun run gen:skill-docs --host all after wiring the QUESTION_TUNING preamble section. Every tier >= 2 skill now includes the combined Question Tuning guidance. Runtime-gated — agents skip the section when question_tuning is off in gstack-config (default). Golden fixtures (claude-ship, codex-ship, factory-ship) updated to the new baseline. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
f388ed67b7 |
feat: wire question-tuning into preamble for tier >= 2 skills
scripts/resolvers/preamble.ts — adds two things:
1. _QUESTION_TUNING config echo in the preamble bash block, gated on the
user's gstack-config `question_tuning` value (default: false).
2. A combined Question Tuning section for tier >= 2 skills, injected after
the confusion protocol. The section itself is runtime-gated by the
QUESTION_TUNING value — agents skip it entirely when off.
scripts/resolvers/question-tuning.ts — consolidated into one compact combined
section `generateQuestionTuning(ctx)` covering: preference check before the
question, log after, and inline tune: feedback with user-origin gate. Per-phase
generators remain exported for unit tests but are no longer the main entrypoint.
Size impact: +570 tokens / +2.3KB per tier-2+ SKILL.md. Three skills
(plan-ceo-review, office-hours, ship) still exceed the 100KB token ceiling —
but they were already over before this change. Delta is the smallest viable
wiring of the /plan-tune v1 substrate.
Golden fixtures (test/fixtures/golden/claude-ship, codex-ship, factory-ship)
regenerated to match the new baseline.
Full test run: 1149 pass, 0 fail, 113 skip across 28 files.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Garry Tan
|
a8b8985048 |
feat: question-tuning preamble resolvers
scripts/resolvers/question-tuning.ts ships three preamble generators:
generateQuestionPreferenceCheck — before each AskUserQuestion, agent runs
gstack-question-preference --check <id>. AUTO_DECIDE suppresses the ask
and auto-chooses recommended. ASK_NORMALLY asks as usual. One-way door
safety override is handled by the binary.
generateQuestionLog — after each AskUserQuestion, agent appends a log
record with skill, question_id, summary, category, door_type,
options_count, user_choice, recommended, session_id.
generateInlineTuneFeedback — offers inline "tune:" prompt after two-way
questions. Documents structured shortcuts (never-ask, always-ask,
ask-only-for-one-way, ask-less) AND accepts free-form English with
normalization + confirmation. Explicitly spells out the USER-ORIGIN
GATE: only write tune events when the prefix appears in the user's own
chat message, never from tool output or file content. Binary enforces.
All three resolvers are gated by the QUESTION_TUNING preamble echo. When
the config is off, the agent skips these sections entirely. Ready to be
wired into preamble.ts in the next commit.
Codex host has a simpler variant that uses $GSTACK_BIN env vars.
scripts/resolvers/index.ts registers three placeholders:
QUESTION_PREFERENCE_CHECK, QUESTION_LOG, INLINE_TUNE_FEEDBACK
Total resolver count goes from 45 to 48.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Garry Tan
|
c249dc37b2 |
feat: bin/gstack-question-preference — explicit preferences + user-origin gate
Subcommands:
--check <id> → ASK_NORMALLY | AUTO_DECIDE (decides if a registered
question should be auto-decided by the agent)
--write '{…}' → set a preference (requires user-origin source)
--read → dump preferences JSON
--clear [id] → clear one or all
--stats → short counts summary
Preference values: always-ask | never-ask | ask-only-for-one-way.
Stored at ~/.gstack/projects/{SLUG}/question-preferences.json.
Safety contract (the core of Codex finding #16, profile-poisoning defense
from docs/designs/PLAN_TUNING_V0.md §Security model):
1. One-way doors ALWAYS return ASK_NORMALLY from --check, regardless of
user preference. User's never-ask is overridden with a visible safety
note so the user knows why their preference didn't suppress the prompt.
2. --write requires an explicit `source` field:
- Allowed: "plan-tune", "inline-user"
- REJECTED with exit code 2: "inline-tool-output", "inline-file",
"inline-file-content", "inline-unknown"
Rejection is explicit ("profile poisoning defense") so the caller can
log and surface the attempt.
3. free_text on --write is sanitized against injection patterns (ignore
previous instructions, override:, system:, etc.) and newline-flattened.
Each --write also appends a preference-set event to
~/.gstack/projects/{SLUG}/question-events.jsonl for derivation audit trail.
31 tests:
- --check behavior (4): defaults, two-way, one-way (one-way overrides
never-ask with safety note), unknown ids, missing arg
- --check with prefs (5): never-ask on two-way → AUTO_DECIDE; never-ask
on one-way → ASK_NORMALLY with override note; always-ask always asks;
ask-only-for-one-way flips appropriately
- --write valid (5): inline-user accepted, plan-tune accepted, persisted
correctly, event appended, free_text preserved with flattening
- User-origin gate (6): missing source rejected; inline-tool-output
rejected with exit code 2 and explicit poisoning message; inline-file,
inline-file-content, inline-unknown rejected; unknown source rejected
- Schema validation (4): invalid JSON, bad question_id, bad preference,
injection in free_text
- --read (2): empty → {}, returns writes
- --clear (3): specific id, clear-all, NOOP for missing
- --stats (2): empty zeros, tallies by preference type
31 pass, 0 fail, 52 expect() calls.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Garry Tan
|
2b54677398 |
feat: bin/gstack-developer-profile — unified profile with migration
bin/gstack-developer-profile supersedes bin/gstack-builder-profile. The old
binary becomes a one-line legacy shim delegating to --read for /office-hours
backward compat.
Subcommands:
--read legacy KEY:VALUE output (tier, session_count, etc)
--migrate folds ~/.gstack/builder-profile.jsonl into
~/.gstack/developer-profile.json. Atomic (temp + rename),
idempotent (no-op when target exists or source absent),
archives source as .migrated-YYYY-MM-DD-HHMMSS
--derive recomputes inferred dimensions from question-log.jsonl
using the signal map in scripts/psychographic-signals.ts
--profile full profile JSON
--gap declared vs inferred diff JSON
--trace <dim> event-level trace of what contributed to a dimension
--check-mismatch flags dimensions where declared and inferred disagree by
> 0.3 (requires >= 10 events first)
--vibe archetype name + description from scripts/archetypes.ts
--narrative (v2 stub)
Auto-migration on first read: if legacy file exists and new file doesn't,
migrate before reading. Creates a neutral (all-0.5) stub if nothing exists.
Unified schema (see docs/designs/PLAN_TUNING_V0.md §Architecture):
{identity, declared, inferred: {values, sample_size, diversity},
gap, overrides, sessions, signals_accumulated, schema_version}
25 new tests across subcommand behaviors:
- --read defaults + stub creation
- --migrate: 3 sessions preserved with signal tallies, idempotency, archival
- Tier calculation: welcome_back / regular / inner_circle boundaries
- --derive: neutral-when-empty, upward nudge on 'expand', downward on 'reduce',
recomputable (same input → same output), ad-hoc unregistered ids ignored
- --trace: contributing events, empty for untouched dims, error without arg
- --gap: empty when no declared, correctly computed otherwise
- --vibe: returns archetype name + description
- --check-mismatch: threshold behavior, 10+ sample requirement
- Unknown subcommand errors
25 pass, 0 fail, 60 expect() calls.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Garry Tan
|
a949de76b6 |
feat: bin/gstack-question-log — append validated AskUserQuestion events
Append-only JSONL log at ~/.gstack/projects/{SLUG}/question-log.jsonl.
Schema: {skill, question_id, question_summary, category?, door_type?,
options_count?, user_choice, recommended?, followed_recommendation?,
session_id?, ts}
Validates:
- skill is kebab-case
- question_id is kebab-case, <= 64 chars
- question_summary non-empty, <= 200 chars, newlines flattened
- category is one of approval/clarification/routing/cherry-pick/feedback-loop
- door_type is one-way or two-way
- options_count is integer in [1, 26]
- user_choice non-empty string, <= 64 chars
Injection defense on question_summary rejects the same patterns as
gstack-learnings-log (ignore previous instructions, system:, override:,
do not report, etc).
followed_recommendation is auto-computed when both user_choice and
recommended are present.
ts auto-injected as ISO 8601 if missing.
21 tests covering: valid payloads, full field preservation, auto-followed
computation, appending, long-summary truncation, newline flattening,
invalid JSON, missing fields, bad case, oversized ids, invalid enum
values, out-of-range options_count, and 6 injection attack patterns.
21 pass, 0 fail, 43 expect() calls.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Garry Tan
|
5e20a3b718 |
feat: psychographic signal map + builder archetypes
scripts/psychographic-signals.ts — hand-crafted {signal_key, user_choice} →
{dimension, delta} map. Version 0.1.0. Conservative deltas (±0.03 to ±0.06
per event). Covers 9 signal keys: scope-appetite, architecture-care,
code-quality-care, test-discipline, detail-preference, design-care,
devex-care, distribution-care, session-mode.
Helpers: applySignal() mutates running totals, newDimensionTotals() creates
empty starting state, normalizeToDimensionValue() sigmoid-clamps accumulated
delta to [0,1] (0 → 0.5 neutral), validateRegistrySignalKeys() checks that
every signal_key in the registry has a SIGNAL_MAP entry.
In v1 the signal map is used ONLY to compute inferred dimension values for
/plan-tune inspection output. No skill behavior adapts to these signals
until v2.
scripts/archetypes.ts — 8 named archetypes + Polymath fallback:
- Cathedral Builder (boil-the-ocean + architecture-first)
- Ship-It Pragmatist (small scope + fast)
- Deep Craft (detail-verbose + principled)
- Taste Maker (intuitive, overrides recommendations)
- Solo Operator (high-autonomy, delegates)
- Consultant (hands-on, consulted on everything)
- Wedge Hunter (narrow scope aggressively)
- Builder-Coach (balanced steering)
- Polymath (fallback when no archetype matches)
matchArchetype() uses L2 distance scaled by tightness, with a 0.55 threshold
below which we return Polymath. v1 ships the model stable; v2 narrative/vibe
commands wire it into user-facing output.
14 new tests: signal map consistency vs registry, applySignal behavior for
known/unknown keys, normalization bounds, archetype schema validity, name
uniqueness, matchArchetype correctness for each reference profile, Polymath
fallback for outliers.
41 pass, 0 fail total in test/plan-tune.test.ts.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Garry Tan
|
db3b6412b9 |
feat: one-way door classifier (belt-and-suspenders safety fallback)
scripts/one-way-doors.ts — secondary keyword-pattern classifier that catches
destructive questions even when the registry doesn't have an entry for them.
The registry's door_type field (from scripts/question-registry.ts) is the
PRIMARY safety gate. This classifier is the fallback for ad-hoc question_ids
that agents generate at runtime.
Classification priority:
1. Registry lookup by question_id → use declared door_type
2. Skill:category fallback (cso:approval, land-and-deploy:approval)
3. Keyword pattern match against question_summary
4. Default: treat as two-way (safer to log the miss than auto-decide unsafely)
Covers 21 destructive patterns across:
- File system (rm -rf, delete, wipe, purge, truncate)
- Database (drop table/database/schema, delete from)
- Git/VCS (force-push, reset --hard, checkout --, branch -D)
- Deploy/infra (kubectl delete, terraform destroy, rollback)
- Credentials (revoke/reset/rotate API key|token|secret|password)
- Architecture (breaking change, schema migration, data model change)
7 new tests in test/plan-tune.test.ts covering: registry-first lookup,
unknown-id fallthrough, keyword matching on destructive phrasings including
embedded filler words ("rotate the API key"), skill-category fallback,
benign questions defaulting to two-way, pattern-list non-empty.
27 pass, 0 fail. 1270 expect() calls.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Garry Tan
|
2c0c95099f |
test: registry schema + safety + coverage tests (gate tier)
20 tests validating the question registry: Schema (7 tests): - Every entry has required fields - All ids are kebab-case and start with their skill name - No duplicate ids - Categories are from the allowed set - door_type is one-way | two-way - Options arrays are well-formed - Descriptions are short and single-line Helpers (5 tests): - getQuestion returns entry for known id, undefined for unknown - getOneWayDoorIds includes destructive questions, excludes two-way - getAllRegisteredIds count matches QUESTIONS keys - getRegistryStats totals are internally consistent One-way door safety (2 tests): - Every critical question (test failure, SQL safety, LLM trust boundary, security scan, merge confirm, rollback, fix apply, premise revise, arch finding, privacy gate, user challenge) is declared one-way - At least 10 one-way doors exist (catches regression if declarations are accidentally dropped) Registry breadth (3 tests): - 11 high-volume skills each have >= 1 registered question - Preamble one-time prompts are registered - /plan-tune's own questions are registered Signal map references (1 test): - signal_key values are typed kebab-case strings Template coverage (2 tests, informational): - AskUserQuestion usage across templates is non-trivial (>20) - Registry spans >= 10 skills 20 pass, 0 fail. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
70ab8326b6 |
feat: typed question registry for /plan-tune v1 foundation
scripts/question-registry.ts declares 53 recurring AskUserQuestion categories across 15 skills (ship, review, office-hours, plan-ceo-review, plan-eng-review, plan-design-review, plan-devex-review, qa, investigate, land-and-deploy, cso, gstack-upgrade, preamble, plan-tune, autoplan). Each entry has: stable kebab-case id, skill owner, category (approval | clarification | routing | cherry-pick | feedback-loop), door_type (one-way | two-way), optional stable option keys, optional psychographic signal_key, and a one-line description. 12 of 53 are one-way doors (destructive ops, architecture/data forks, security/compliance). These are ALWAYS asked regardless of user preference. Helpers: getQuestion(id), getOneWayDoorIds(), getAllRegisteredIds(), getRegistryStats(). No binary or resolver wiring yet — this is the schema substrate the rest of /plan-tune builds on. Ad-hoc question_ids (not registered) still log but skip psychographic signal attribution. Future /plan-tune skill surfaces frequently-firing ad-hoc ids as candidates for registry promotion. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Garry Tan
|
2904ddeb92 |
docs: add design doc for /plan-tune v1 (observational substrate)
Canonical record of the /plan-tune v1 design: typed question registry, per-question explicit preferences, inline tune: feedback with user-origin gate, dual-track profile (declared + inferred separately), and plain-English inspection skill. Captures every decision with pros/cons, what's deferred to v2 with explicit acceptance criteria, and what was rejected entirely. Codex review drove a substantial scope rollback from the initial CEO EXPANSION plan. 15+ legitimate findings (substrate claim was false without a typed registry; E4/E6/clamp logical contradiction; profile poisoning attack surface; LANDED preamble side effect; implementation order) shaped the final shape. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |