CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-06-02 00:01:37 +02:00
Code Issues Packages Projects Releases Wiki Activity

v1.53.1.0 fix: non-interactive-safe plan-tune hook install (flags + smart defaults) (#1805)

Browse Source 
* feat(config): add plan_tune_hooks setting (prompt|yes|no)

Registers a new gstack-config key controlling whether ./setup installs the
plan-tune Claude Code hooks. Default "prompt". Documented in the config
header and surfaced in `gstack-config defaults` / `list`.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(setup): make plan-tune hook install non-interactive-safe

The plan-tune consent prompt used a blocking `read -r` with no timeout. Under
a forwarded/automated TTY (conductor workspace setup, CI with a pty) it hung
setup forever.

Move the decision into flags + env + saved config with a smart default:
  --plan-tune-hooks / --no-plan-tune-hooks / --plan-tune-hooks=yes|no|prompt
  > GSTACK_PLAN_TUNE_HOOKS env > plan_tune_hooks config > prompt-on-real-TTY.

Explicit yes/no act non-interactively. The remaining interactive branch is
gated on a real (non-quiet) TTY and uses a time-bounded `read -t 10 </dev/tty`
that defaults to skip, so it can never hang. A timeout no longer persists a
decline marker, so a later hands-on run can still offer the install.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(dev-setup): run setup non-interactively in dev/workspace mode

Conductor runs bin/dev-setup under a forwarded pty, so any setup prompt
(skill-prefix, plan-tune consent) would hang the workspace. Detach stdin
(`setup </dev/null`) so every prompt takes its smart non-interactive default:
flat skill names, skip the global plan-tune hook install without writing a
decline marker. Saved prefix/config preferences are still honored, and a dev
workspace no longer silently mutates ~/.claude/settings.json.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(setup): guard plan-tune hooks stay non-interactive

Static + binary-level regression test (free, <1s): asserts the flags are
wired, the plan-tune read is time-bounded (no bare blocking read), explicit
yes/no decisions short-circuit before the prompt, and gstack-config knows the
plan_tune_hooks key.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(setup,config): harden plan-tune decision against bad input

Review follow-ups to the non-interactive plan-tune work:
- setup now lowercases + whitespace-strips the resolved decision before the
  case match, so an explicit opt-in via flag/env ("YES", "Yes", " yes") is
  honored instead of silently falling through to "prompt"/skip. Also accepts
  on/off and 1/0.
- gstack-config rejects out-of-domain plan_tune_hooks values (anything but
  prompt|yes|no) with a warning + fallback to prompt, matching the existing
  value-whitelist pattern for explain_level / artifacts_sync_mode.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(dev-setup): never mutate global hooks during workspace setup

Closing stdin alone only suppresses the prompt branch; a saved
`plan_tune_hooks: yes` or exported GSTACK_PLAN_TUNE_HOOKS=yes would still
resolve to "install" and rewrite the user's global ~/.claude/settings.json to
point at THIS ephemeral worktree — which breaks once the workspace is deleted.

Pass --plan-tune-hooks=prompt (highest precedence) so dev-setup pins resolution
to prompt-mode; with stdin closed that is a guaranteed no-op skip (no install,
no decline marker). To install the hooks, run ./setup --plan-tune-hooks directly.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(setup): isolate config tests from host + cover new guards

- Point gstack-config tests at a temp GSTACK_HOME so `get plan_tune_hooks`
  reads the built-in default, not whatever the host machine has in
  ~/.gstack/config.yaml (the prior test was non-deterministic).
- Add behavioral coverage: yes/no/prompt round-trip, out-of-domain rejection.
- Add a normalization guard (decision input is lowercased/trimmed) and a
  dev-setup guard (runs setup with --plan-tune-hooks=prompt + stdin detached).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test: rebaseline parity-suite v1.44.1 -> v1.53.0.0

The frozen v1.44.1 anchor went stale: five planning skills (plan-ceo-review,
plan-eng-review, plan-design-review, investigate, office-hours) crept past the
1.05x ceiling via legitimate v1.49-v1.53 growth (brain-aware planning + the
v1.53 redaction guard), so `bun test` was red on a clean checkout of main.

Capture a fresh baseline at HEAD (bun run scripts/capture-baseline.ts --tag
v1.53.0.0) and re-point the test at it. The per-skill 1.05 ratio is kept, so
future bloat is still caught; only the anchor moved. Mirrors the earlier
skill-size-budget rebase (v1.44.1 -> v1.47.0.0). Historical v1.44.1 / v1.46.0.0
/ v1.47.0.0 baselines are retained for the v1->v2 audit trail. The captured
skill bytes equal origin/main exactly (this branch left every SKILL.md
untouched). Clears the pre-existing failures noted in the v1.53.0.0 CHANGELOG.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(plan-tune): de-flake "derive pushes scope_appetite up"

The test was ~25-50% flaky (worse on main). gstack-question-log fires a
fire-and-forget background `--derive` after every write; the 5 rapid log writes
spawned 5 racing background derives that collided with the test's explicit
--derive — a late one that only saw 3 entries could clobber
developer-profile.json after the explicit one wrote sample_size=5.

Set GSTACK_QUESTION_LOG_NO_DERIVE=1 (the flag the binary documents for exactly
this case) so the writes don't spawn background derives. The explicit --derive
still runs, so real derive behavior is still asserted. 20/20 green after.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* chore: bump version and changelog (v1.53.1.0)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs: document non-interactive dev-setup + plan-tune hook flags (v1.53.1.0)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-05-30 11:42:13 -07:00
committed by GitHub
parent dedfe42ef0
commit 9562ad4e70
12 changed files with 937 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+27
View File
@@ -1,5 +1,32 @@
# Changelog # Changelog
## [1.53.1.0] - 2026-05-30
## **Workspace and scripted setup never hang on a hidden prompt again. Installing the plan-tune hooks is now flag-driven with safe defaults.**
`./setup` asked "Install both hooks now? [y/N]" with a blocking read. Run under a Conductor workspace or any forwarded terminal, that prompt had nobody to answer it, so setup hung forever. Now the decision comes from a flag, an env var, or saved config, and when nobody is there to answer it takes a safe default instead of waiting. A real terminal still gets the prompt, but it is time-bounded (auto-skips after 10s) so it can never stall a pipeline.
### What this means for you
- Spinning up a new workspace just works. `bin/dev-setup` runs fully non-interactively and never rewrites your global Claude settings behind your back.
- Want the plan-tune hooks installed without a prompt? `./setup --plan-tune-hooks` (or `GSTACK_PLAN_TUNE_HOOKS=yes`, or `gstack-config set plan_tune_hooks yes`). Don't want them? `--no-plan-tune-hooks`. Leave it unset and a real terminal still asks once, then remembers.
### Added
- `--plan-tune-hooks` / `--no-plan-tune-hooks` / `--plan-tune-hooks=yes|no|prompt` flags on `./setup`, plus the `GSTACK_PLAN_TUNE_HOOKS` env var and a `plan_tune_hooks` config key (default `prompt`). Precedence: flag > env > saved config > prompt on a real terminal.
### Fixed
- `./setup` no longer hangs in non-interactive or forwarded-TTY contexts (Conductor workspaces, CI). The plan-tune consent prompt is time-bounded and defaults to skip.
- `bin/dev-setup` runs setup non-interactively and can no longer silently rewrite your global `~/.claude/settings.json` to point at an ephemeral workspace path that breaks when the workspace is deleted.
- Opt-in values like `YES`, `Yes`, or ` yes` are honored instead of being silently downgraded to skip, and `gstack-config` now rejects out-of-domain `plan_tune_hooks` values.
### For contributors
- New regression suite `test/setup-plan-tune-hooks-noninteractive.test.ts` (flag wiring, no-blocking-read guard, decision normalization, config round-trip + domain rejection, dev-setup pin) with host-config isolation via a temp `GSTACK_HOME`.
- Rebaselined `test/parity-suite.test.ts` from the stale v1.44.1 anchor to v1.53.0.0. The 1.05 per-skill ratio is kept (only the anchor moved), absorbing legitimate v1.49–v1.53 planning-skill growth and clearing the 5 pre-existing parity failures noted in the v1.53.0.0 entry. Historical baselines retained for the v1→v2 audit trail.
- De-flaked `test/plan-tune.test.ts` "derive pushes scope_appetite up" (was ~25–50% flaky, worse on main): it now sets `GSTACK_QUESTION_LOG_NO_DERIVE=1` so gstack-question-log's fire-and-forget background `--derive` can't race the test's explicit one.
## [1.53.0.0] - 2026-05-29 ## [1.53.0.0] - 2026-05-29
## **Secrets, PII, and legal landmines get caught before they reach a public sink. One redaction engine now guards /spec, /ship, /cso, and the /document-* skills.** ## **Secrets, PII, and legal landmines get caught before they reach a public sink. One redaction engine now guards /spec, /ship, /cso, and the /document-* skills.**
CONTRIBUTING.md
+3 -1
View File
@@ -326,11 +326,13 @@ If you're using [Conductor](https://conductor.build) to run multiple Claude Code
| Hook | Script | What it does | | Hook | Script | What it does |
|------|--------|-------------| |------|--------|-------------|
| `setup` | `bin/dev-setup` | Copies `.env` from main worktree, installs deps, symlinks skills | | `setup` | `bin/dev-setup` | Copies `.env` from main worktree, installs deps, symlinks skills, runs `./setup` non-interactively |
| `archive` | `bin/dev-teardown` | Removes skill symlinks, cleans up `.claude/` directory | | `archive` | `bin/dev-teardown` | Removes skill symlinks, cleans up `.claude/` directory |
When Conductor creates a new workspace, `bin/dev-setup` runs automatically. It detects the main worktree (via `git worktree list`), copies your `.env` so API keys carry over, and sets up dev mode — no manual steps needed. When Conductor creates a new workspace, `bin/dev-setup` runs automatically. It detects the main worktree (via `git worktree list`), copies your `.env` so API keys carry over, and sets up dev mode — no manual steps needed.
`bin/dev-setup` runs `./setup` fully non-interactively (it passes `--plan-tune-hooks=prompt` and closes stdin), so a forwarded Conductor TTY can never hang on a hidden setup prompt. It also never installs the plan-tune Claude Code hooks, which means a throwaway workspace can't rewrite your global `~/.claude/settings.json` to point at an ephemeral worktree path. To install the plan-tune hooks deliberately, run `./setup --plan-tune-hooks` outside dev-setup (or `gstack-config set plan_tune_hooks yes`).
**First-time setup:** Put your `ANTHROPIC_API_KEY` in `.env` in the main repo (see `.env.example`). Every Conductor workspace inherits it automatically. **First-time setup:** Put your `ANTHROPIC_API_KEY` in `.env` in the main repo (see `.env.example`). Every Conductor workspace inherits it automatically.
**`GSTACK_*` env prefix (Conductor-injected keys).** Conductor explicitly strips `ANTHROPIC_API_KEY` and `OPENAI_API_KEY` from every workspace's process env. The `.env` copy path doesn't restore them either — the strip happens after env inheritance. Users who want paid evals, `/sync-gbrain` embeddings, or `claude-agent-sdk` calls to work in a Conductor workspace must set `GSTACK_ANTHROPIC_API_KEY` and `GSTACK_OPENAI_API_KEY` in Conductor's workspace env config; Conductor passes those through untouched. On the gstack side, TS entry points import `lib/conductor-env-shim.ts` as a side effect, which promotes `GSTACK_FOO_API_KEY` to `FOO_API_KEY` when the canonical name is empty. If you add a new TS entry point that hits a paid API, add `import "../lib/conductor-env-shim";` to the top of the file. Today the shim is imported from `bin/gstack-gbrain-sync.ts`, `bin/gstack-model-benchmark`, `scripts/preflight-agent-sdk.ts`, and `test/helpers/e2e-helpers.ts`. **`GSTACK_*` env prefix (Conductor-injected keys).** Conductor explicitly strips `ANTHROPIC_API_KEY` and `OPENAI_API_KEY` from every workspace's process env. The `.env` copy path doesn't restore them either — the strip happens after env inheritance. Users who want paid evals, `/sync-gbrain` embeddings, or `claude-agent-sdk` calls to work in a Conductor workspace must set `GSTACK_ANTHROPIC_API_KEY` and `GSTACK_OPENAI_API_KEY` in Conductor's workspace env config; Conductor passes those through untouched. On the gstack side, TS entry points import `lib/conductor-env-shim.ts` as a side effect, which promotes `GSTACK_FOO_API_KEY` to `FOO_API_KEY` when the canonical name is empty. If you add a new TS entry point that hits a paid API, add `import "../lib/conductor-env-shim";` to the top of the file. Today the shim is imported from `bin/gstack-gbrain-sync.ts`, `bin/gstack-model-benchmark`, `scripts/preflight-agent-sdk.ts`, and `test/helpers/e2e-helpers.ts`.
TODOS.md
+14 -19
View File
@@ -2,27 +2,22 @@
## Test infrastructure ## Test infrastructure
### P0: Rebaseline parity-suite (v1.44.1) — stale, 5 pre-existing failures ### ✅ DONE (v1.53.1.0): Rebaseline parity-suite (v1.44.1 → v1.53.0.0)
**What:** `test/parity-suite.test.ts` checks every skill's SKILL.md size against **What:** `test/parity-suite.test.ts` checked every skill's SKILL.md size against
the frozen `test/fixtures/parity-baseline-v1.44.1.json`. Five planning skills now the frozen `test/fixtures/parity-baseline-v1.44.1.json`. Five planning skills had
exceed the 1.05x ceiling: `plan-ceo-review` (1.052), `plan-eng-review` (1.062), crept past the 1.05x ceiling: `plan-ceo-review` (1.052), `plan-eng-review` (1.062),
`plan-design-review` (1.068), `investigate` (1.053), `office-hours` (1.065). `plan-design-review` (1.068), `investigate` (1.053), `office-hours` (1.065) — growth
from the brain-aware-planning releases (v1.49–v1.52) plus the v1.53 redaction guard.
**Why:** These grew during the brain-aware-planning releases (v1.49–v1.52) which **Resolved:** Captured a fresh baseline at HEAD via
added the `BRAIN_PREFLIGHT`/`BRAIN_CACHE_REFRESH`/`BRAIN_WRITE_BACK` resolvers to `bun run scripts/capture-baseline.ts --tag v1.53.0.0` and re-pointed the test at
those skills. The v1.44.1 baseline was never regenerated, so it's four releases `test/fixtures/parity-baseline-v1.53.0.0.json`. The per-skill 1.05 ratio is kept, so
stale. The failures are pre-existing on `origin/main` (proven: they fail with the future bloat is still caught — only the stale anchor moved. Mirrors the earlier
redaction branch absent). The active size gate (`skill-size-budget`, v1.47 baseline) `skill-size-budget` rebase (v1.44.1 → v1.47.0.0). Historical v1.44.1 / v1.46.0.0 /
passes, and parity-suite is not in CI's `test:gate`, so nothing is blocked — but the v1.47.0.0 baselines retained in `test/fixtures/` for the v1→v2 audit trail. The
local `bun test` shows red until rebaselined. captured skill bytes match `origin/main` exactly (the rebasing branch left every
SKILL.md untouched). `bun test` is green again.
**How to start:** Either regenerate the fixture to a current baseline
(`bun run scripts/capture-baseline.ts <tag>` and point the test at it), or bump the
per-skill ratio for the planning skills. Decide whether v1.44.1 should be retired in
favor of the v1.47 baseline the size-budget test already uses.
**Depends on:** nothing. Standalone.
## gbrowser memory follow-ups (filed via /plan-eng-review + /codex on the v1.49 leak-fix PR) ## gbrowser memory follow-ups (filed via /plan-eng-review + /codex on the v1.49 leak-fix PR)
VERSION
+1 -1
View File
@@ -1 +1 @@
1.53.0.0 1.53.1.0
bin/dev-setup
+17 -2
View File
@@ -56,8 +56,23 @@ if [ ! -e "$AGENTS_LINK" ]; then
ln -s "$REPO_ROOT" "$AGENTS_LINK" ln -s "$REPO_ROOT" "$AGENTS_LINK"
fi fi
# 6. Run setup via the symlink so it detects .claude/skills/ as its parent # 6. Run setup via the symlink so it detects .claude/skills/ as its parent.
"$GSTACK_LINK/setup" #
# Workspace/dev setup MUST be non-interactive: Conductor runs this under a
# forwarded pty, so any `read` in setup (skill-prefix prompt, plan-tune hook
# consent) would hang the workspace forever. Detaching stdin makes every setup
# prompt take its smart non-interactive default (flat skill names, etc.).
#
# `--plan-tune-hooks=prompt` is load-bearing, not redundant: stdin alone only
# suppresses the *prompt* branch. A saved `plan_tune_hooks: yes` or an exported
# GSTACK_PLAN_TUNE_HOOKS=yes would still resolve to "install" and rewrite the
# user's global ~/.claude/settings.json to point at THIS ephemeral worktree —
# which breaks once the workspace is deleted. The flag has highest precedence,
# so it pins resolution to "prompt", and closed stdin then makes prompt-mode a
# no-op skip (no install, no decline marker). A dev workspace must never mutate
# global settings.json. To install the hooks, run `./setup --plan-tune-hooks`
# directly (outside dev-setup). Saved prefix/other config preferences still apply.
"$GSTACK_LINK/setup" --plan-tune-hooks=prompt </dev/null
echo "" echo ""
echo "Dev mode active. Skills resolve from this working tree." echo "Dev mode active. Skills resolve from this working tree."
bin/gstack-config
+18 -2
View File
@@ -75,6 +75,16 @@ CONFIG_HEADER='# gstack configuration — edit freely, changes take effect on ne
# # Set to true once the privacy gate has asked the user. # # Set to true once the privacy gate has asked the user.
# # Flip back to false to be re-prompted. # # Flip back to false to be re-prompted.
# #
# ─── Plan-tune hooks ─────────────────────────────────────────────────
# plan_tune_hooks: prompt # Controls whether ./setup installs the plan-tune
# # Claude Code hooks (PostToolUse capture +
# # PreToolUse preference enforcement).
# # prompt — ask on a real TTY, skip otherwise (default)
# # yes — install non-interactively
# # no — skip non-interactively
# # Override per-run: ./setup --plan-tune-hooks /
# # --no-plan-tune-hooks, or env GSTACK_PLAN_TUNE_HOOKS.
#
# ─── Advanced ──────────────────────────────────────────────────────── # ─── Advanced ────────────────────────────────────────────────────────
# codex_reviews: enabled # disabled = skip Codex adversarial reviews in /ship # codex_reviews: enabled # disabled = skip Codex adversarial reviews in /ship
# gstack_contributor: false # true = file field reports when gstack misbehaves # gstack_contributor: false # true = file field reports when gstack misbehaves
@@ -110,6 +120,8 @@ lookup_default() {
cross_project_learnings) echo "" ;; # intentionally empty → unset triggers first-time prompt cross_project_learnings) echo "" ;; # intentionally empty → unset triggers first-time prompt
artifacts_sync_mode) echo "off" ;; artifacts_sync_mode) echo "off" ;;
artifacts_sync_mode_prompted) echo "false" ;; artifacts_sync_mode_prompted) echo "false" ;;
plan_tune_hooks) echo "prompt" ;; # prompt | yes | no — controls ./setup plan-tune hook install
redact_repo_visibility) echo "" ;; # empty → fall through to gh/glab detection redact_repo_visibility) echo "" ;; # empty → fall through to gh/glab detection
redact_prepush_hook) echo "false" ;; redact_prepush_hook) echo "false" ;;
# Brain-aware planning (v1.48 / T5+T10+T16). Defaults documented inline: # Brain-aware planning (v1.48 / T5+T10+T16). Defaults documented inline:
@@ -286,6 +298,10 @@ case "${1:-}" in
echo "Warning: redact_prepush_hook '$VALUE' not recognized. Valid values: true, false. Using false." >&2 echo "Warning: redact_prepush_hook '$VALUE' not recognized. Valid values: true, false. Using false." >&2
VALUE="false" VALUE="false"
fi fi
if [ "$KEY" = "plan_tune_hooks" ] && [ "$VALUE" != "prompt" ] && [ "$VALUE" != "yes" ] && [ "$VALUE" != "no" ]; then
echo "Warning: plan_tune_hooks '$VALUE' not recognized. Valid values: prompt, yes, no. Using prompt." >&2
VALUE="prompt"
fi
mkdir -p "$STATE_DIR" mkdir -p "$STATE_DIR"
# Write annotated header on first creation # Write annotated header on first creation
if [ ! -f "$CONFIG_FILE" ]; then if [ ! -f "$CONFIG_FILE" ]; then
@@ -315,7 +331,7 @@ case "${1:-}" in
for KEY in proactive routing_declined telemetry auto_upgrade update_check \ for KEY in proactive routing_declined telemetry auto_upgrade update_check \
skill_prefix checkpoint_mode checkpoint_push explain_level \ skill_prefix checkpoint_mode checkpoint_push explain_level \
codex_reviews gstack_contributor skip_eng_review workspace_root \ codex_reviews gstack_contributor skip_eng_review workspace_root \
artifacts_sync_mode artifacts_sync_mode_prompted; do artifacts_sync_mode artifacts_sync_mode_prompted plan_tune_hooks; do
VALUE=$(grep -E "^${KEY}:" "$CONFIG_FILE" 2>/dev/null | tail -1 | awk '{print $2}' | tr -d '[:space:]' || true) VALUE=$(grep -E "^${KEY}:" "$CONFIG_FILE" 2>/dev/null | tail -1 | awk '{print $2}' | tr -d '[:space:]' || true)
SOURCE="default" SOURCE="default"
if [ -n "$VALUE" ]; then if [ -n "$VALUE" ]; then
@@ -331,7 +347,7 @@ case "${1:-}" in
for KEY in proactive routing_declined telemetry auto_upgrade update_check \ for KEY in proactive routing_declined telemetry auto_upgrade update_check \
skill_prefix checkpoint_mode checkpoint_push explain_level \ skill_prefix checkpoint_mode checkpoint_push explain_level \
codex_reviews gstack_contributor skip_eng_review workspace_root \ codex_reviews gstack_contributor skip_eng_review workspace_root \
artifacts_sync_mode artifacts_sync_mode_prompted; do artifacts_sync_mode artifacts_sync_mode_prompted plan_tune_hooks; do
printf ' %-24s %s\n' "$KEY:" "$(lookup_default "$KEY")" printf ' %-24s %s\n' "$KEY:" "$(lookup_default "$KEY")"
done done
;; ;;
package.json
+1 -1
View File
@@ -1,6 +1,6 @@
{ {
"name": "gstack", "name": "gstack",
"version": "1.53.0.0", "version": "1.53.1.0",
"description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.", "description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.",
"license": "MIT", "license": "MIT",
"type": "module", "type": "module",
setup
+80 -26
View File
@@ -82,6 +82,7 @@ SKILL_PREFIX=1
SKILL_PREFIX_FLAG=0 SKILL_PREFIX_FLAG=0
TEAM_MODE=0 TEAM_MODE=0
NO_TEAM_MODE=0 NO_TEAM_MODE=0
PLAN_TUNE_HOOKS_MODE="" # "" = resolve from env/config/prompt; "yes"/"no" = explicit
while [ $# -gt 0 ]; do while [ $# -gt 0 ]; do
case "$1" in case "$1" in
--host) [ -z "$2" ] && echo "Missing value for --host (expected claude, codex, kiro, factory, opencode, openclaw, hermes, gbrain, or auto)" >&2 && exit 1; HOST="$2"; shift 2 ;; --host) [ -z "$2" ] && echo "Missing value for --host (expected claude, codex, kiro, factory, opencode, openclaw, hermes, gbrain, or auto)" >&2 && exit 1; HOST="$2"; shift 2 ;;
@@ -91,6 +92,9 @@ while [ $# -gt 0 ]; do
--no-prefix) SKILL_PREFIX=0; SKILL_PREFIX_FLAG=1; shift ;; --no-prefix) SKILL_PREFIX=0; SKILL_PREFIX_FLAG=1; shift ;;
--team) TEAM_MODE=1; shift ;; --team) TEAM_MODE=1; shift ;;
--no-team) NO_TEAM_MODE=1; shift ;; --no-team) NO_TEAM_MODE=1; shift ;;
--plan-tune-hooks) PLAN_TUNE_HOOKS_MODE="yes"; shift ;;
--no-plan-tune-hooks) PLAN_TUNE_HOOKS_MODE="no"; shift ;;
--plan-tune-hooks=*) PLAN_TUNE_HOOKS_MODE="${1#--plan-tune-hooks=}"; shift ;;
-q|--quiet) QUIET=1; shift ;; -q|--quiet) QUIET=1; shift ;;
*) shift ;; *) shift ;;
esac esac
@@ -1304,14 +1308,65 @@ if [ "$NO_TEAM_MODE" -ne 1 ] \
ALREADY_INSTALLED=1 ALREADY_INSTALLED=1
fi fi
# Resolve the desired action without ever blocking.
# Priority: CLI flag (--plan-tune-hooks / --no-plan-tune-hooks)
# > env (GSTACK_PLAN_TUNE_HOOKS=yes|no)
# > saved config (plan_tune_hooks)
# > smart default ("prompt" → timed prompt on a real TTY, else skip).
# This guarantees scripted/workspace setups (conductor, CI) are never
# interactive: pass --no-plan-tune-hooks (or --plan-tune-hooks) and the
# block runs to completion with no `read`.
PT_DECISION="$PLAN_TUNE_HOOKS_MODE"
[ -z "$PT_DECISION" ] && PT_DECISION="${GSTACK_PLAN_TUNE_HOOKS:-}"
[ -z "$PT_DECISION" ] && PT_DECISION="$("$GSTACK_CONFIG" get plan_tune_hooks 2>/dev/null || true)"
# Normalize: strip whitespace + lowercase so "YES", "Yes", " yes" from a flag
# or env var all resolve correctly (an unrecognized opt-in must NOT silently
# downgrade to skip). Unknown values fall through to "prompt".
PT_DECISION=$(printf '%s' "$PT_DECISION" | tr '[:upper:]' '[:lower:]' | tr -d '[:space:]')
case "$PT_DECISION" in
y|yes|true|install|on|1) PT_DECISION="yes" ;;
n|no|false|skip|off|0) PT_DECISION="no" ;;
*) PT_DECISION="prompt" ;;
esac
_install_plan_tune_hooks() {
"$SETTINGS_HOOK" add-event \
--event PostToolUse \
--matcher '(AskUserQuestion|mcp__.*__AskUserQuestion)' \
--command "$PLAN_TUNE_LOG_HOOK" \
--source plan-tune-cathedral \
--timeout 5
"$SETTINGS_HOOK" add-event \
--event PreToolUse \
--matcher '(AskUserQuestion|mcp__.*__AskUserQuestion)' \
--command "$PLAN_TUNE_PREF_HOOK" \
--source plan-tune-cathedral \
--timeout 5
}
if [ "$ALREADY_INSTALLED" -eq 1 ]; then if [ "$ALREADY_INSTALLED" -eq 1 ]; then
log "" log ""
log "Plan-tune hooks already installed. Run \`$SETTINGS_HOOK list-sources\` to inspect." log "Plan-tune hooks already installed. Run \`$SETTINGS_HOOK list-sources\` to inspect."
elif [ "$PT_DECISION" = "yes" ]; then
# Explicit opt-in (flag / env / config). Non-interactive.
_install_plan_tune_hooks
log ""
log "Plan-tune hooks installed. Run /plan-tune anytime to inspect."
touch "$PLAN_TUNE_INSTALL_MARKER"
elif [ "$PT_DECISION" = "no" ]; then
# Explicit opt-out (flag / env / config). Non-interactive.
log ""
log "Plan-tune cathedral hooks not installed (opted out)."
log "Install later with: ./setup --plan-tune-hooks (or /update-config)."
touch "$PLAN_TUNE_INSTALL_MARKER"
elif [ -f "$PLAN_TUNE_INSTALL_MARKER" ]; then elif [ -f "$PLAN_TUNE_INSTALL_MARKER" ]; then
# Previously declined. Don't re-ask. User can re-enable via /update-config. # Previously declined. Don't re-ask. User can re-enable via /update-config.
: :
elif [ -t 0 ] && [ -t 1 ]; then elif [ "$QUIET" -ne 1 ] && [ -t 0 ] && [ -t 1 ]; then
# Interactive install with explicit consent + diff preview. # Real interactive terminal with no recorded preference: ask, with explicit
# consent + diff preview. The read is time-bounded and defaults to "skip" so
# it can never hang an automated/forwarded TTY (the conductor failure mode).
_PT_PROMPT_TIMEOUT=10 # single source of truth for the read + the countdown text
log "" log ""
log "──────────────────────────────────────────────────────────" log "──────────────────────────────────────────────────────────"
log "Plan-tune cathedral: install Claude Code hooks?" log "Plan-tune cathedral: install Claude Code hooks?"
@@ -1336,33 +1391,32 @@ if [ "$NO_TEAM_MODE" -ne 1 ] \
log "Backup: settings.json.bak.<ts> written before any mutation." log "Backup: settings.json.bak.<ts> written before any mutation."
log "Rollback: $SETTINGS_HOOK rollback" log "Rollback: $SETTINGS_HOOK rollback"
log "" log ""
printf "Install both hooks now? [y/N] " printf "Install both hooks now? [y/N] (default: N, auto-skips in %ss): " "$_PT_PROMPT_TIMEOUT"
read -r PLAN_TUNE_INSTALL_REPLY read -t "$_PT_PROMPT_TIMEOUT" -r PLAN_TUNE_INSTALL_REPLY </dev/tty 2>/dev/null || PLAN_TUNE_INSTALL_REPLY=""
if [ "$PLAN_TUNE_INSTALL_REPLY" = "y" ] || [ "$PLAN_TUNE_INSTALL_REPLY" = "Y" ]; then case "$PLAN_TUNE_INSTALL_REPLY" in
"$SETTINGS_HOOK" add-event \ y|Y)
--event PostToolUse \ _install_plan_tune_hooks
--matcher '(AskUserQuestion|mcp__.*__AskUserQuestion)' \ log ""
--command "$PLAN_TUNE_LOG_HOOK" \ log "Plan-tune hooks installed. Run /plan-tune anytime to inspect."
--source plan-tune-cathedral \ touch "$PLAN_TUNE_INSTALL_MARKER"
--timeout 5 ;;
"$SETTINGS_HOOK" add-event \ n|N)
--event PreToolUse \ log ""
--matcher '(AskUserQuestion|mcp__.*__AskUserQuestion)' \ log "Skipped. Re-run ./setup --plan-tune-hooks or use /update-config to install later."
--command "$PLAN_TUNE_PREF_HOOK" \ touch "$PLAN_TUNE_INSTALL_MARKER"
--source plan-tune-cathedral \ ;;
--timeout 5 *)
log "" # Empty / timed out — treat as "ask me again" (don't persist a decline).
log "Plan-tune hooks installed. Run /plan-tune anytime to inspect." log ""
else log "No response — skipped for now. Re-run ./setup --plan-tune-hooks to install."
log "" ;;
log "Skipped. Re-run ./setup or use /update-config to install later." esac
fi
touch "$PLAN_TUNE_INSTALL_MARKER"
else else
# Non-interactive (CI, scripted setup). Don't prompt; print one-liner. # Non-interactive (CI, scripted/workspace setup, quiet). Never prompt.
log "" log ""
log "Plan-tune cathedral hooks not installed (non-interactive setup)." log "Plan-tune cathedral hooks not installed (non-interactive setup)."
log "Install with:" log "Install with: ./setup --plan-tune-hooks"
log " (or set GSTACK_PLAN_TUNE_HOOKS=yes, or run the commands below)"
log " $SETTINGS_HOOK add-event --event PostToolUse \\" log " $SETTINGS_HOOK add-event --event PostToolUse \\"
log " --matcher '(AskUserQuestion|mcp__.*__AskUserQuestion)' \\" log " --matcher '(AskUserQuestion|mcp__.*__AskUserQuestion)' \\"
log " --command $PLAN_TUNE_LOG_HOOK --source plan-tune-cathedral --timeout 5" log " --command $PLAN_TUNE_LOG_HOOK --source plan-tune-cathedral --timeout 5"
test/fixtures/parity-baseline-v1.53.0.0.json
Vendored
+633
View File
@@ -0,0 +1,633 @@
{
"tag": "v1.53.0.0",
"capturedAt": "2026-05-30T18:00:56.209Z",
"capturedFromCommit": "352f6a57",
"capturedFromBranch": "garrytan/setup-plan-tune-hooks-flags",
"totalSkills": 52,
"totalCorpusBytes": 3179282,
"estTotalCatalogTokens": 4116,
"topHeaviest": [
{
"skill": "ship",
"skillMdBytes": 170491,
"skillMdLines": 3153,
"estTokens": 42623,
"tmplBytes": 53240,
"descriptionLen": 291,
"hasGateEval": true,
"hasPeriodicEval": true
},
{
"skill": "plan-ceo-review",
"skillMdBytes": 137751,
"skillMdLines": 2290,
"estTokens": 34438,
"tmplBytes": 63461,
"descriptionLen": 794,
"hasGateEval": true,
"hasPeriodicEval": true
},
{
"skill": "office-hours",
"skillMdBytes": 118280,
"skillMdLines": 2161,
"estTokens": 29570,
"tmplBytes": 55534,
"descriptionLen": 860,
"hasGateEval": true,
"hasPeriodicEval": false
},
{
"skill": "plan-design-review",
"skillMdBytes": 112728,
"skillMdLines": 2019,
"estTokens": 28182,
"tmplBytes": 28717,
"descriptionLen": 218,
"hasGateEval": true,
"hasPeriodicEval": true
},
{
"skill": "plan-devex-review",
"skillMdBytes": 111292,
"skillMdLines": 2212,
"estTokens": 27823,
"tmplBytes": 35773,
"descriptionLen": 250,
"hasGateEval": true,
"hasPeriodicEval": true
},
{
"skill": "spec",
"skillMdBytes": 109688,
"skillMdLines": 2239,
"estTokens": 27422,
"tmplBytes": 30590,
"descriptionLen": 282,
"hasGateEval": true,
"hasPeriodicEval": false
},
{
"skill": "plan-eng-review",
"skillMdBytes": 107655,
"skillMdLines": 1849,
"estTokens": 26914,
"tmplBytes": 26302,
"descriptionLen": 231,
"hasGateEval": true,
"hasPeriodicEval": true
},
{
"skill": "design-review",
"skillMdBytes": 96618,
"skillMdLines": 1936,
"estTokens": 24155,
"tmplBytes": 11674,
"descriptionLen": 304,
"hasGateEval": true,
"hasPeriodicEval": false
},
{
"skill": "review",
"skillMdBytes": 95012,
"skillMdLines": 1766,
"estTokens": 23753,
"tmplBytes": 14099,
"descriptionLen": 205,
"hasGateEval": true,
"hasPeriodicEval": false
},
{
"skill": "land-and-deploy",
"skillMdBytes": 92850,
"skillMdLines": 1860,
"estTokens": 23213,
"tmplBytes": 48624,
"descriptionLen": 160,
"hasGateEval": true,
"hasPeriodicEval": false
}
],
"skills": {
"autoplan": {
"skill": "autoplan",
"skillMdBytes": 91834,
"skillMdLines": 1788,
"estTokens": 22959,
"tmplBytes": 45271,
"descriptionLen": 366,
"hasGateEval": true,
"hasPeriodicEval": true
},
"benchmark": {
"skill": "benchmark",
"skillMdBytes": 33266,
"skillMdLines": 747,
"estTokens": 8317,
"tmplBytes": 9378,
"descriptionLen": 213,
"hasGateEval": true,
"hasPeriodicEval": false
},
"benchmark-models": {
"skill": "benchmark-models",
"skillMdBytes": 29333,
"skillMdLines": 622,
"estTokens": 7333,
"tmplBytes": 6631,
"descriptionLen": 217,
"hasGateEval": false,
"hasPeriodicEval": false
},
"browse": {
"skill": "browse",
"skillMdBytes": 48151,
"skillMdLines": 930,
"estTokens": 12038,
"tmplBytes": 10805,
"descriptionLen": 181,
"hasGateEval": true,
"hasPeriodicEval": false
},
"canary": {
"skill": "canary",
"skillMdBytes": 48069,
"skillMdLines": 994,
"estTokens": 12017,
"tmplBytes": 8033,
"descriptionLen": 180,
"hasGateEval": true,
"hasPeriodicEval": false
},
"careful": {
"skill": "careful",
"skillMdBytes": 2551,
"skillMdLines": 68,
"estTokens": 638,
"tmplBytes": 2435,
"descriptionLen": 315,
"hasGateEval": false,
"hasPeriodicEval": false
},
"codex": {
"skill": "codex",
"skillMdBytes": 80584,
"skillMdLines": 1523,
"estTokens": 20146,
"tmplBytes": 34143,
"descriptionLen": 187,
"hasGateEval": true,
"hasPeriodicEval": false
},
"context-restore": {
"skill": "context-restore",
"skillMdBytes": 42457,
"skillMdLines": 852,
"estTokens": 10614,
"tmplBytes": 5255,
"descriptionLen": 238,
"hasGateEval": true,
"hasPeriodicEval": false
},
"context-save": {
"skill": "context-save",
"skillMdBytes": 46654,
"skillMdLines": 970,
"estTokens": 11664,
"tmplBytes": 9293,
"descriptionLen": 168,
"hasGateEval": true,
"hasPeriodicEval": false
},
"cso": {
"skill": "cso",
"skillMdBytes": 78849,
"skillMdLines": 1462,
"estTokens": 19712,
"tmplBytes": 35646,
"descriptionLen": 196,
"hasGateEval": true,
"hasPeriodicEval": false
},
"design-consultation": {
"skill": "design-consultation",
"skillMdBytes": 80186,
"skillMdLines": 1565,
"estTokens": 20047,
"tmplBytes": 25899,
"descriptionLen": 888,
"hasGateEval": true,
"hasPeriodicEval": false
},
"design-html": {
"skill": "design-html",
"skillMdBytes": 67511,
"skillMdLines": 1453,
"estTokens": 16878,
"tmplBytes": 22567,
"descriptionLen": 233,
"hasGateEval": false,
"hasPeriodicEval": false
},
"design-review": {
"skill": "design-review",
"skillMdBytes": 96618,
"skillMdLines": 1936,
"estTokens": 24155,
"tmplBytes": 11674,
"descriptionLen": 304,
"hasGateEval": true,
"hasPeriodicEval": false
},
"design-shotgun": {
"skill": "design-shotgun",
"skillMdBytes": 63800,
"skillMdLines": 1315,
"estTokens": 15950,
"tmplBytes": 13331,
"descriptionLen": 786,
"hasGateEval": false,
"hasPeriodicEval": false
},
"devex-review": {
"skill": "devex-review",
"skillMdBytes": 65377,
"skillMdLines": 1237,
"estTokens": 16344,
"tmplBytes": 7984,
"descriptionLen": 201,
"hasGateEval": false,
"hasPeriodicEval": false
},
"document-generate": {
"skill": "document-generate",
"skillMdBytes": 54797,
"skillMdLines": 1194,
"estTokens": 13699,
"tmplBytes": 15939,
"descriptionLen": 334,
"hasGateEval": false,
"hasPeriodicEval": false
},
"document-release": {
"skill": "document-release",
"skillMdBytes": 59827,
"skillMdLines": 1248,
"estTokens": 14957,
"tmplBytes": 20974,
"descriptionLen": 192,
"hasGateEval": true,
"hasPeriodicEval": false
},
"freeze": {
"skill": "freeze",
"skillMdBytes": 3154,
"skillMdLines": 92,
"estTokens": 789,
"tmplBytes": 3038,
"descriptionLen": 503,
"hasGateEval": false,
"hasPeriodicEval": false
},
"gstack-upgrade": {
"skill": "gstack-upgrade",
"skillMdBytes": 10817,
"skillMdLines": 285,
"estTokens": 2704,
"tmplBytes": 10667,
"descriptionLen": 163,
"hasGateEval": true,
"hasPeriodicEval": false
},
"guard": {
"skill": "guard",
"skillMdBytes": 3297,
"skillMdLines": 91,
"estTokens": 824,
"tmplBytes": 3181,
"descriptionLen": 686,
"hasGateEval": false,
"hasPeriodicEval": false
},
"health": {
"skill": "health",
"skillMdBytes": 48880,
"skillMdLines": 1018,
"estTokens": 12220,
"tmplBytes": 11617,
"descriptionLen": 184,
"hasGateEval": true,
"hasPeriodicEval": false
},
"investigate": {
"skill": "investigate",
"skillMdBytes": 51373,
"skillMdLines": 1016,
"estTokens": 12843,
"tmplBytes": 11561,
"descriptionLen": 1379,
"hasGateEval": true,
"hasPeriodicEval": false
},
"ios-clean": {
"skill": "ios-clean",
"skillMdBytes": 42009,
"skillMdLines": 817,
"estTokens": 10502,
"tmplBytes": 3851,
"descriptionLen": 252,
"hasGateEval": false,
"hasPeriodicEval": false
},
"ios-design-review": {
"skill": "ios-design-review",
"skillMdBytes": 42595,
"skillMdLines": 819,
"estTokens": 10649,
"tmplBytes": 4417,
"descriptionLen": 209,
"hasGateEval": false,
"hasPeriodicEval": false
},
"ios-fix": {
"skill": "ios-fix",
"skillMdBytes": 41724,
"skillMdLines": 815,
"estTokens": 10431,
"tmplBytes": 3574,
"descriptionLen": 187,
"hasGateEval": false,
"hasPeriodicEval": false
},
"ios-qa": {
"skill": "ios-qa",
"skillMdBytes": 48235,
"skillMdLines": 935,
"estTokens": 12059,
"tmplBytes": 10090,
"descriptionLen": 223,
"hasGateEval": true,
"hasPeriodicEval": false
},
"ios-sync": {
"skill": "ios-sync",
"skillMdBytes": 41701,
"skillMdLines": 808,
"estTokens": 10425,
"tmplBytes": 3544,
"descriptionLen": 269,
"hasGateEval": false,
"hasPeriodicEval": false
},
"land-and-deploy": {
"skill": "land-and-deploy",
"skillMdBytes": 92850,
"skillMdLines": 1860,
"estTokens": 23213,
"tmplBytes": 48624,
"descriptionLen": 160,
"hasGateEval": true,
"hasPeriodicEval": false
},
"landing-report": {
"skill": "landing-report",
"skillMdBytes": 44949,
"skillMdLines": 878,
"estTokens": 11237,
"tmplBytes": 6806,
"descriptionLen": 195,
"hasGateEval": false,
"hasPeriodicEval": false
},
"learn": {
"skill": "learn",
"skillMdBytes": 42686,
"skillMdLines": 895,
"estTokens": 10672,
"tmplBytes": 5594,
"descriptionLen": 178,
"hasGateEval": true,
"hasPeriodicEval": false
},
"make-pdf": {
"skill": "make-pdf",
"skillMdBytes": 29890,
"skillMdLines": 670,
"estTokens": 7473,
"tmplBytes": 5546,
"descriptionLen": 177,
"hasGateEval": false,
"hasPeriodicEval": false
},
"office-hours": {
"skill": "office-hours",
"skillMdBytes": 118280,
"skillMdLines": 2161,
"estTokens": 29570,
"tmplBytes": 55534,
"descriptionLen": 860,
"hasGateEval": true,
"hasPeriodicEval": false
},
"open-gstack-browser": {
"skill": "open-gstack-browser",
"skillMdBytes": 47095,
"skillMdLines": 958,
"estTokens": 11774,
"tmplBytes": 7702,
"descriptionLen": 204,
"hasGateEval": false,
"hasPeriodicEval": false
},
"pair-agent": {
"skill": "pair-agent",
"skillMdBytes": 47903,
"skillMdLines": 1014,
"estTokens": 11976,
"tmplBytes": 8548,
"descriptionLen": 167,
"hasGateEval": false,
"hasPeriodicEval": false
},
"plan-ceo-review": {
"skill": "plan-ceo-review",
"skillMdBytes": 137751,
"skillMdLines": 2290,
"estTokens": 34438,
"tmplBytes": 63461,
"descriptionLen": 794,
"hasGateEval": true,
"hasPeriodicEval": true
},
"plan-design-review": {
"skill": "plan-design-review",
"skillMdBytes": 112728,
"skillMdLines": 2019,
"estTokens": 28182,
"tmplBytes": 28717,
"descriptionLen": 218,
"hasGateEval": true,
"hasPeriodicEval": true
},
"plan-devex-review": {
"skill": "plan-devex-review",
"skillMdBytes": 111292,
"skillMdLines": 2212,
"estTokens": 27823,
"tmplBytes": 35773,
"descriptionLen": 250,
"hasGateEval": true,
"hasPeriodicEval": true
},
"plan-eng-review": {
"skill": "plan-eng-review",
"skillMdBytes": 107655,
"skillMdLines": 1849,
"estTokens": 26914,
"tmplBytes": 26302,
"descriptionLen": 231,
"hasGateEval": true,
"hasPeriodicEval": true
},
"plan-tune": {
"skill": "plan-tune",
"skillMdBytes": 64017,
"skillMdLines": 1355,
"estTokens": 16004,
"tmplBytes": 26922,
"descriptionLen": 325,
"hasGateEval": true,
"hasPeriodicEval": false
},
"qa": {
"skill": "qa",
"skillMdBytes": 74827,
"skillMdLines": 1626,
"estTokens": 18707,
"tmplBytes": 12701,
"descriptionLen": 218,
"hasGateEval": true,
"hasPeriodicEval": false
},
"qa-only": {
"skill": "qa-only",
"skillMdBytes": 57385,
"skillMdLines": 1198,
"estTokens": 14346,
"tmplBytes": 3851,
"descriptionLen": 165,
"hasGateEval": true,
"hasPeriodicEval": false
},
"retro": {
"skill": "retro",
"skillMdBytes": 83853,
"skillMdLines": 1754,
"estTokens": 20963,
"tmplBytes": 42427,
"descriptionLen": 648,
"hasGateEval": true,
"hasPeriodicEval": false
},
"review": {
"skill": "review",
"skillMdBytes": 95012,
"skillMdLines": 1766,
"estTokens": 23753,
"tmplBytes": 14099,
"descriptionLen": 205,
"hasGateEval": true,
"hasPeriodicEval": false
},
"scrape": {
"skill": "scrape",
"skillMdBytes": 44605,
"skillMdLines": 891,
"estTokens": 11151,
"tmplBytes": 5220,
"descriptionLen": 167,
"hasGateEval": true,
"hasPeriodicEval": false
},
"setup-browser-cookies": {
"skill": "setup-browser-cookies",
"skillMdBytes": 26618,
"skillMdLines": 594,
"estTokens": 6655,
"tmplBytes": 2724,
"descriptionLen": 222,
"hasGateEval": false,
"hasPeriodicEval": false
},
"setup-deploy": {
"skill": "setup-deploy",
"skillMdBytes": 44891,
"skillMdLines": 923,
"estTokens": 11223,
"tmplBytes": 7780,
"descriptionLen": 197,
"hasGateEval": true,
"hasPeriodicEval": false
},
"setup-gbrain": {
"skill": "setup-gbrain",
"skillMdBytes": 81964,
"skillMdLines": 1777,
"estTokens": 20491,
"tmplBytes": 44851,
"descriptionLen": 323,
"hasGateEval": true,
"hasPeriodicEval": false
},
"ship": {
"skill": "ship",
"skillMdBytes": 170491,
"skillMdLines": 3153,
"estTokens": 42623,
"tmplBytes": 53240,
"descriptionLen": 291,
"hasGateEval": true,
"hasPeriodicEval": true
},
"skillify": {
"skill": "skillify",
"skillMdBytes": 54498,
"skillMdLines": 1172,
"estTokens": 13625,
"tmplBytes": 15107,
"descriptionLen": 233,
"hasGateEval": true,
"hasPeriodicEval": false
},
"spec": {
"skill": "spec",
"skillMdBytes": 109688,
"skillMdLines": 2239,
"estTokens": 27422,
"tmplBytes": 30590,
"descriptionLen": 282,
"hasGateEval": true,
"hasPeriodicEval": false
},
"sync-gbrain": {
"skill": "sync-gbrain",
"skillMdBytes": 53201,
"skillMdLines": 1070,
"estTokens": 13300,
"tmplBytes": 16077,
"descriptionLen": 299,
"hasGateEval": false,
"hasPeriodicEval": false
},
"unfreeze": {
"skill": "unfreeze",
"skillMdBytes": 1504,
"skillMdLines": 49,
"estTokens": 376,
"tmplBytes": 1386,
"descriptionLen": 199,
"hasGateEval": false,
"hasPeriodicEval": false
}
}
}
test/parity-suite.test.ts
+11 -4
View File
@@ -2,9 +2,16 @@
* Cathedral parity suite — gate-tier (free, structural + content checks). * Cathedral parity suite — gate-tier (free, structural + content checks).
* *
* Runs every PARITY_INVARIANTS check against the current SKILL.md output * Runs every PARITY_INVARIANTS check against the current SKILL.md output
* vs the v1.44.1 baseline. Failures get an actionable, per-skill report * vs the v1.53.0.0 baseline. Failures get an actionable, per-skill report
* showing missing phrases, missing headings, and size ratios. * showing missing phrases, missing headings, and size ratios.
* *
* Baseline rebased v1.44.1 → v1.53.0.0: the brain-aware-planning releases
* (v1.49–v1.52) plus the v1.53 redaction guard pushed five planning skills
* past the 5% ratchet on the frozen v1.44.1 anchor. Rebasing absorbs that
* legitimate growth at HEAD while keeping the per-skill 1.05 ratio so future
* bloat is still caught. Historical v1.44.1 / v1.46.0.0 / v1.47.0.0 baselines
* are retained in test/fixtures/ for the v1→v2 audit trail.
*
* Periodic-tier LLM-judge parity (paid) lands in Phase B (v2.0.0.0) * Periodic-tier LLM-judge parity (paid) lands in Phase B (v2.0.0.0)
* alongside the sections/ extraction. Plumbing is in parity-harness.ts. * alongside the sections/ extraction. Plumbing is in parity-harness.ts.
*/ */
@@ -16,9 +23,9 @@ import { runParityChecks, PARITY_INVARIANTS } from './helpers/parity-harness';
import type { ParityBaseline } from './helpers/capture-parity-baseline'; import type { ParityBaseline } from './helpers/capture-parity-baseline';
const REPO_ROOT = path.resolve(import.meta.dir, '..'); const REPO_ROOT = path.resolve(import.meta.dir, '..');
const BASELINE_PATH = path.join(REPO_ROOT, 'test', 'fixtures', 'parity-baseline-v1.44.1.json'); const BASELINE_PATH = path.join(REPO_ROOT, 'test', 'fixtures', 'parity-baseline-v1.53.0.0.json');
describe('parity suite vs v1.44.1 baseline (gate, free)', () => { describe('parity suite vs v1.53.0.0 baseline (gate, free)', () => {
test('baseline exists', () => { test('baseline exists', () => {
expect(fs.existsSync(BASELINE_PATH)).toBe(true); expect(fs.existsSync(BASELINE_PATH)).toBe(true);
}); });
@@ -43,7 +50,7 @@ describe('parity suite vs v1.44.1 baseline (gate, free)', () => {
.map(d => ` ${d.skill}:\n - ${d.failures.join('\n - ')}`) .map(d => ` ${d.skill}:\n - ${d.failures.join('\n - ')}`)
.join('\n'); .join('\n');
throw new Error( throw new Error(
`${report.failed} skill(s) failed parity checks vs v1.44.1:\n${failureMessages}`, `${report.failed} skill(s) failed parity checks vs ${baseline.tag}:\n${failureMessages}`,
); );
}); });
}); });
test/plan-tune.test.ts
+9 -1
View File
@@ -535,7 +535,15 @@ describe('end-to-end pipeline (binaries working together)', () => {
test('log many expand choices → derive pushes scope_appetite up', () => { test('log many expand choices → derive pushes scope_appetite up', () => {
const tmpHome = fs.mkdtempSync(path.join(require('os').tmpdir(), 'gstack-e2e-')); const tmpHome = fs.mkdtempSync(path.join(require('os').tmpdir(), 'gstack-e2e-'));
try { try {
const env = { ...process.env, GSTACK_HOME: tmpHome }; // GSTACK_QUESTION_LOG_NO_DERIVE=1 suppresses gstack-question-log's
// fire-and-forget background `--derive` (it nohups one per write). Without
// it, the 5 rapid log writes spawn 5 racing background derives that collide
// with this test's explicit --derive below — a late background derive that
// only saw 3 entries can clobber developer-profile.json after the explicit
// one wrote sample_size=5, making the test flaky (~25-50% fail). The binary
// documents this flag for exactly this case. The explicit --derive still
// runs (it ignores the flag), so real derive behavior is still asserted.
const env = { ...process.env, GSTACK_HOME: tmpHome, GSTACK_QUESTION_LOG_NO_DERIVE: '1' };
const { spawnSync } = require('child_process'); const { spawnSync } = require('child_process');
const logBin = path.join(ROOT, 'bin', 'gstack-question-log'); const logBin = path.join(ROOT, 'bin', 'gstack-question-log');
const devBin = path.join(ROOT, 'bin', 'gstack-developer-profile'); const devBin = path.join(ROOT, 'bin', 'gstack-developer-profile');
test/setup-plan-tune-hooks-noninteractive.test.ts
+123
View File
@@ -0,0 +1,123 @@
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
import * as fs from 'fs';
import * as os from 'os';
import * as path from 'path';
import { execSync } from 'child_process';
// Regression guard for the conductor/workspace setup hang:
// `./setup` used a blocking `read -r` to ask "Install both hooks now? [y/N]".
// When setup runs under a forwarded/automated TTY (conductor workspace setup,
// CI with a pty) the read blocked forever. The fix moves the decision into
// flags + env + saved config with a non-blocking, time-bounded prompt fallback.
//
// These are static + binary-level assertions (free, <1s) — they lock in the
// contract without running the full (environment-mutating) setup script.
const ROOT = path.resolve(import.meta.dir, '..');
const SETUP = path.join(ROOT, 'setup');
const GSTACK_CONFIG = path.join(ROOT, 'bin', 'gstack-config');
const setupSrc = fs.readFileSync(SETUP, 'utf-8');
describe('setup: plan-tune hooks are non-interactive-safe', () => {
test('exposes --plan-tune-hooks / --no-plan-tune-hooks / =value flags', () => {
expect(setupSrc).toContain('--plan-tune-hooks)');
expect(setupSrc).toContain('--no-plan-tune-hooks)');
expect(setupSrc).toContain('--plan-tune-hooks=*)');
});
test('resolution falls through env then saved config', () => {
expect(setupSrc).toContain('GSTACK_PLAN_TUNE_HOOKS');
expect(setupSrc).toContain('get plan_tune_hooks');
});
test('explicit yes/no decisions never reach a prompt', () => {
// The yes/no branches must short-circuit before the interactive branch.
const yesIdx = setupSrc.indexOf('PT_DECISION" = "yes"');
const noIdx = setupSrc.indexOf('PT_DECISION" = "no"');
const promptIdx = setupSrc.indexOf('Install both hooks now?');
expect(yesIdx).toBeGreaterThan(-1);
expect(noIdx).toBeGreaterThan(-1);
expect(yesIdx).toBeLessThan(promptIdx);
expect(noIdx).toBeLessThan(promptIdx);
});
test('the interactive prompt is time-bounded (cannot hang)', () => {
// No bare blocking read for the plan-tune reply.
expect(setupSrc).not.toMatch(/read -r PLAN_TUNE_INSTALL_REPLY\b/);
// It must use a timed read from the controlling tty with an empty fallback.
// The timeout may be a literal or a named variable (e.g. "$_PT_PROMPT_TIMEOUT").
expect(setupSrc).toMatch(/read -t (?:\d+|"?\$\{?\w+\}?"?) -r PLAN_TUNE_INSTALL_REPLY <\/dev\/tty/);
});
test('interactive prompt is gated on a real TTY and non-quiet', () => {
// The prompt branch requires both stdin+stdout TTYs and not --quiet.
expect(setupSrc).toMatch(/\[ "\$QUIET" -ne 1 \] && \[ -t 0 \] && \[ -t 1 \]/);
});
test('decision input is normalized (lowercase + whitespace-stripped)', () => {
// "YES" / " yes" from a flag/env must not silently downgrade to skip.
expect(setupSrc).toMatch(/tr '\[:upper:\]' '\[:lower:\]'/);
expect(setupSrc).toMatch(/PT_DECISION=\$\(printf .* tr/);
});
});
describe('dev-setup: never silently mutates global settings.json', () => {
const DEV_SETUP = path.join(ROOT, 'bin', 'dev-setup');
const devSetupSrc = fs.readFileSync(DEV_SETUP, 'utf-8');
test('runs setup with stdin detached AND --plan-tune-hooks=prompt pin', () => {
// stdin alone only suppresses the prompt branch; the flag (highest
// precedence) is what stops a saved `plan_tune_hooks: yes` / env opt-in
// from rewriting global hooks to the ephemeral worktree path.
expect(devSetupSrc).toMatch(/setup" --plan-tune-hooks=prompt <\/dev\/null/);
});
});
describe('gstack-config: plan_tune_hooks key', () => {
// Isolate state: gstack-config reads $GSTACK_HOME/config.yaml. Point it at a
// fresh temp dir so `get` returns the built-in default rather than whatever
// the host machine has in ~/.gstack/config.yaml (which would make the
// default-value assertion non-deterministic).
let tmpHome: string;
let env: NodeJS.ProcessEnv;
beforeAll(() => {
tmpHome = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-cfg-test-'));
env = { ...process.env, GSTACK_HOME: tmpHome };
});
afterAll(() => {
fs.rmSync(tmpHome, { recursive: true, force: true });
});
test('default is "prompt"', () => {
const out = execSync(`${GSTACK_CONFIG} get plan_tune_hooks`, {
encoding: 'utf-8',
env,
}).trim();
expect(out).toBe('prompt');
});
test('appears in defaults and list output', () => {
const defaults = execSync(`${GSTACK_CONFIG} defaults`, { encoding: 'utf-8', env });
expect(defaults).toContain('plan_tune_hooks');
const list = execSync(`${GSTACK_CONFIG} list`, { encoding: 'utf-8', env });
expect(list).toContain('plan_tune_hooks');
});
test('accepts valid values (round-trips yes/no/prompt)', () => {
for (const v of ['yes', 'no', 'prompt']) {
execSync(`${GSTACK_CONFIG} set plan_tune_hooks ${v}`, { encoding: 'utf-8', env });
const got = execSync(`${GSTACK_CONFIG} get plan_tune_hooks`, { encoding: 'utf-8', env }).trim();
expect(got).toBe(v);
}
});
test('rejects out-of-domain values (warns + falls back to prompt)', () => {
const res = execSync(`${GSTACK_CONFIG} set plan_tune_hooks maybe 2>&1`, { encoding: 'utf-8', env });
expect(res.toLowerCase()).toContain('not recognized');
const got = execSync(`${GSTACK_CONFIG} get plan_tune_hooks`, { encoding: 'utf-8', env }).trim();
expect(got).toBe('prompt');
});
});