Files
gstack/setup
T
Garry Tan 070722ace3 v1.52.1.0 feat: brain-aware planning — 5 skills read structured gbrain context before asking (#1742)
* feat(brain): brain-cache-spec.ts — single source of truth for cache layer

Foundation for the brain-aware planning skills work (v1.48 plan / D2).
One TS const file consolidates BRAIN_CACHE_ENTITIES (8 entities × TTL +
budget + invalidation rules), SKILL_DIGEST_SUBSETS (per-skill which
files to load), SALIENCE_DEFAULT_ALLOWLIST (D9 privacy gate),
SKILL_CALIBRATION_WEIGHTS (Phase 2 E5), and policy / identity / schema
constants.

Drift between docs and runtime becomes impossible by construction:
resolver, cache CLI, and test/skill-preflight-budget.test.ts all import
from the same module.

test/brain-cache-spec.test.ts: 19 invariant assertions (subset/entity
consistency, per-skill achievability, allowlist sanity, transport
defaults, user-slug fallback chain, lock timeout, retention policy).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(brain): gstack-core@1.0.0 schema pack (T1 / Phase 0)

Defines 8 typed page kinds for the brain entity model:
  gstack/user-profile, gstack/product, gstack/goal,
  gstack/developer-persona, gstack/brand, gstack/competitive-intel,
  gstack/skill-run, gstack/take

Each declares frontmatter shape (typed fields with required/optional flags),
retention policy (immutable / archive-after-90d / never-archive), and
emits_links graph for mcp__gbrain__schema_graph rendering.

getSchemaPackMutationPayload() returns JSON in the shape accepted by
mcp__gbrain__schema_apply_mutations. Idempotent registration: gbrain
skips when pack+version already installed.

test/gstack-schema-pack.test.ts: 16 invariants on pack shape, retention
policies, link verb consistency, JSON serializability.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(brain): gstack-brain-cache CLI (T2a) — core subcommands

bin/gstack-brain-cache: TS CLI with five subcommands:
  get <entity-name> [--project <slug>]
  refresh [--full] [--entity X] [--project <slug>]
  invalidate <entity-name> [--project <slug>]
  digest <entity-slug>
  meta [--project <slug>]

Cache layout per Phase 0.5 design:
  ~/.gstack/brain-cache/                 ← cross-project (user-profile)
  ~/.gstack/projects/<slug>/brain-cache/ ← per-project (everything else)

Per-entity TTL drives staleness; per-entity byte budgets enforce
compression at write time. Atomic writes via tmp+rename. Stale-but-usable
fallback when brain unreachable (returns cached digest with diagnostic
prefix instead of failing). Schema-version mismatch + endpoint switch
both trigger full rebuild for the affected scope (D4 A4).

Fetch+compress paths wired for the 7 entities (user-profile, product,
goals, developer-persona, brand, competitive-intel, recent-decisions,
salience) via gbrain CLI shell-out — works for local PGLite and
local-stdio MCP, transparent over the existing spawnGbrain helper.

Concurrent-refresh dedup (D3 / T15) is a follow-up commit. Salience
allowlist gate (D9 / T17) is a follow-up commit. Bootstrap + lifecycle
subcommands (T2b / T18) are follow-up commits.

test/brain-cache-roundtrip.test.ts: 11 tests covering path resolution,
meta lifecycle, endpoint detection, schema mismatch behavior, and the
four cache states (warm / cold-refreshed / stale-fallback / missing).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(brain): concurrent-refresh lockfile dedup (T15 / D3)

When autoplan dispatches 4 planning skills back-to-back and they all hit
a cold-miss on the same digest, only ONE actually fetches from the brain.
The rest dedup via the project-scoped lockfile at
~/.gstack/projects/<slug>/brain-cache/.refresh.lock.

Reuses the 5-min stale-takeover convention from /sync-gbrain. Lock is
taken over when:
  - File is older than CACHE_REFRESH_LOCK_TIMEOUT_MS
  - PID is on the same host and dead (process.kill(pid, 0) fails)
  - Lock file is corrupt (defensive)

withRefreshLock(projectSlug, fn) returns either the callback's value or
the literal 'dedup'. The CLI emits exit code 3 + diagnostic stderr on
dedup, so callers can choose to wait + retry (resolver does this) or
fall through to stale-but-usable behavior.

test/cache-concurrent-refresh.test.ts: 7 tests covering acquire/release,
stale-takeover, dead-PID takeover, corrupt-lock recovery, error-path
release, and cross-project lock location.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(brain): salience privacy allowlist gate (T17 / D9)

D9 cross-model finding from codex outside voice: salience-sourced digests
can include emotionally-weighted personal pages (family, therapy,
reflection). Pulling those into a coding-review prompt leaks sensitive
context into work-flow reasoning.

fetchSalience now strips entries whose slugs don't match an allowlist
prefix BEFORE writing to the cache file. Default allowlist is
SALIENCE_DEFAULT_ALLOWLIST = ['projects/', 'concepts/', 'gstack/'].
User can extend via:
  gstack-config set salience_allowlist 'projects/,gstack/,concepts/,custom/'
or override with GSTACK_SALIENCE_ALLOWLIST env var.

Digest still records the strip count for transparency. Empty result
emits 'all N entries stripped' note rather than silent absence.

test/salience-allowlist.test.ts: 9 tests covering default permits,
default blocks, empty allowlist, env override, whitespace trimming,
and the invariant that defaults contain nothing sensitive (personal,
family, therapy, reflection, private, medical, health).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(brain): bootstrap + list + purge subcommands (T2b / T18)

T2b — bootstrap synthesizes draft entity content from CLAUDE.md + README
+ recent learnings.jsonl and emits as JSON for the caller. Skill template
is responsible for the AUQ-confirm-before-write flow (D10 T4 extraction-
review requirement). Cli stays pure (no AUQ logic); agent owns user
interaction.

T18 — list/purge subcommands close the lifecycle loop:
  list [--project <slug>] — enumerate gstack-owned pages in brain
                            (probe all 8 gstack/* page types)
  purge <slug>           — delete one gstack page, refuses non-gstack/
                            slugs (defensive)

list defaults to all-projects (cross-project user-profile included).
With --project, filters to per-project pages plus the cross-project
user-profile. --json flag emits machine-readable output for the agent.

Retention sweep + audit subcommand are deferred to a follow-up commit
(they need the lifecycle scheduling design, not just CLI plumbing).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(brain): brain-aware planning resolvers + 3 new placeholders (T4)

scripts/resolvers/gbrain.ts adds:
  - generateBrainPreflight(ctx)       — emits per-skill ## Brain Context
                                        block + bash that loads digests via
                                        gstack-brain-cache get (one call per
                                        digest). Per-skill subset comes from
                                        SKILL_DIGEST_SUBSETS (single source).
  - generateBrainCacheRefresh(ctx)    — at-skill-end background refresh hook;
                                        non-blocking; warms cache for next run.
  - generateBrainWriteBack(ctx)       — Phase 2 / E5 calibration write-back
                                        with per-skill weight. Gated on
                                        personal trust policy + the
                                        BRAIN_CALIBRATION_WRITEBACK flag.
                                        Includes invalidation bash that busts
                                        affected digests after the write.

scripts/resolvers/index.ts registers three new placeholders:
  {{BRAIN_PREFLIGHT}}, {{BRAIN_CACHE_REFRESH}}, {{BRAIN_WRITE_BACK}}

All three resolvers return empty string for skills not in
SKILL_DIGEST_SUBSETS (defensive — skill template authors can drop the
placeholders into non-preflight skills with zero effect).

D9 privacy is mentioned in the rendered preflight prose so the agent
knows to expect filtered salience.
D11 codex tension: write-back gates on brain_trust_policy@<hash> being
personal — shared brains skip write-back to avoid polluting team
calibration profile.

test/brain-preflight.test.ts: 19 tests covering subset rendering,
non-preflight skill gating, cross-project vs per-project --project flag
emission, weight injection per skill, BRAIN_CALIBRATION_WRITEBACK flag
mention, and registration in RESOLVERS map.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(brain): gstack-config brain integration helpers (T5+T10+T16)

Extends bin/gstack-config to support the brain-aware planning layer:

KEY VALIDATION (T5):
  Plain alphanumeric/underscore now extended to allow @<hex-hash> suffix.
  Required for per-endpoint namespaced keys (brain_trust_policy@<sha8>,
  user_slug_at_<sha8>). Keys without the suffix still validate as before.

VALUE WHITELISTING (D4 / D11):
  brain_trust_policy@* values gated to personal | shared | unset.
  Unknown values warn + default to unset (defense against typos).

NEW DEFAULTS (lookup_default):
  brain_trust_policy@*  -> unset
  salience_allowlist    -> '' (resolver uses SALIENCE_DEFAULT_ALLOWLIST)
  user_slug_at_*        -> '' (resolve-user-slug fills + persists on demand)

NEW SUBCOMMANDS:
  endpoint-hash      — print sha8 of active gbrain MCP URL from
                       ~/.claude.json. Collision check escalates to sha16
                       when a prior endpoint stored at the same sha8
                       would conflict (T10 defensive default).
  resolve-user-slug  — walks D4 A3 identity chain:
                         1. mcp__gbrain__whoami.client_name
                         2. $USER env var
                         3. sha8(git config user.email)
                         4. anonymous-<sha8(hostname)>
                       Persists result on first call so subsequent
                       calls are stable across sessions.

test/user-slug-fallback.test.ts: 14 tests covering endpoint-hash output
shape, fallback chain ordering, persistence, brain_trust_policy
namespace value validation + per-endpoint isolation, and key validator
extension for @-suffixed keys.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(brain): wire 5 planning skill templates with BRAIN_* placeholders (T6)

Adds three placeholders to each of the 5 planning SKILL.md.tmpl files:
  {{BRAIN_PREFLIGHT}}     — top of skill body, before first interactive
                            section. Loads the per-skill digest subset
                            (5 files for office-hours, 2 for plan-eng-
                            review, etc.) into the prompt context before
                            any AskUserQuestion fires.
  {{BRAIN_WRITE_BACK}}    — end of skill, before refresh hook. Phase 2
                            calibration write path; gated on personal
                            policy + BRAIN_CALIBRATION_WRITEBACK flag.
  {{BRAIN_CACHE_REFRESH}} — end of skill, after write-back. Non-blocking
                            background refresh so next invocation gets
                            warm cache.

Files touched (templates + regenerated SKILL.md):
  office-hours/SKILL.md.tmpl
  plan-ceo-review/SKILL.md.tmpl
  plan-eng-review/SKILL.md.tmpl
  plan-design-review/SKILL.md.tmpl
  plan-devex-review/SKILL.md.tmpl
  (matching .md files regenerated via bun run gen:skill-docs)

All 5 generated SKILL.md files now contain the rendered ## Brain Context
(preflight) section + write-back guidance + background-refresh hook. The
resolver renders only for skills in SKILL_DIGEST_SUBSETS — these 5 + an
empty string for any other skill that drops in the placeholders.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(brain): setup-gbrain trust-policy step + sync-gbrain flags (T5b / T13+T5c)

T5b — setup-gbrain Step 9.5:
  Inserts the brain trust policy AskUserQuestion before the verdict block.
  Detects active endpoint hash via gstack-config endpoint-hash. Branches
  per transport:
    * Local (sha == "local"): auto-set personal, one-line notice
    * Remote-MCP, unset: AskUserQuestion (personal vs shared)
    * Already-set: skip, just print current policy
  Personal default flips artifacts_sync_mode=full when still off.

T13+T5c — sync-gbrain:
  Adds two flag short-circuits:
    --refresh-cache : route to gstack-brain-cache refresh --project <slug>;
                       skip code + memory + brain-sync stages. Replaces
                       the planned /brain-refresh-context skill per D1
                       fold (one fewer always-loaded skill in catalog).
    --audit          : emit gstack-owned page summary + sensitive-content
                       leak check via gstack-brain-cache list. Read-only.
  Step 1 trust policy gate: fires the same AskUserQuestion as setup-gbrain
  Step 9.5 when policy is unset for a remote endpoint. Local engines
  auto-set personal silently. Idempotent for already-set policies.

Both templates re-rendered via bun run gen:skill-docs. Trust policy
question wording centralized in setup-gbrain Step 9.5; sync-gbrain
Step 1 references it to avoid prompt drift.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test(brain): schema migration + fence-block fallback + preflight budget (T19+T21)

3 new gate-tier test files closing the most important coverage gaps in
the brain-aware planning layer:

test/schema-version-migration.test.ts (D4 A4):
  - Cache file with mismatched schema_version triggers wipe-and-rebuild
  - Matching version + fresh TTL stays warm-hit (no unnecessary rebuild)
  - Rebuild wipes ALL files in scope, not just the one being read

test/takes-fence-fallback.test.ts:
  - Every preflight skill mentions both takes_add (preferred) and
    put_page fence-block (fallback for pre-T8 gbrain versions)
  - All 5 skills gate on BRAIN_CALIBRATION_WRITEBACK flag + personal
    trust policy
  - Per-skill weight matches SKILL_CALIBRATION_WEIGHTS (E5)
  - Write-back emits the kind=bet frontmatter shape and invalidates
    affected cache digests

test/skill-preflight-budget.test.ts (T21 / D7):
  - Per-skill BRAIN_* instruction bytes stay under 3x the runtime
    digest budget (resolver bloat catch)
  - Autoplan total instruction bytes stay under 75 KB (3x of 25 KB
    runtime cap)
  - Non-preflight skills emit zero brain bytes
  - Per-skill subset references are present in the preflight bash

Note on the 3x multiplier: SKILL_PREFLIGHT_BUDGET_BYTES governs runtime
digest data (enforced by cache CLI truncateToBudget). Instruction text
emitted by the resolver gets a separate 3x headroom — anything beyond
that signals the instructions themselves are bloated and need a trim.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* docs(todos): brain-aware planning follow-ups (T11)

Adds five deferred items from the v1.48.0.0 brain-aware planning plan:

  - P2: /gstack-reflect nightly synthesis skill (E2, deferred D4)
  - P3: cross-machine brain-cache sync (E3, deferred D5)
  - P3: /gstack-onboarding dedicated skill (E4, deferred D6)
  - P2: upstream gbrain takes_add + takes_resolve MCP ops (T8 wrap-up)
  - P3: background-refresh hook supervision (codex outside-voice T3)

Each entry follows the TODOS.md format: What / Why / Pros / Cons /
Context / Effort / Depends on. Each cross-references the v1.48.0.0
review decision (D-numbers from /plan-ceo-review and /plan-eng-review)
that deferred it.

The plan itself is at ~/.claude/plans/hm-interesting-well-why-dapper-eagle.md
and is NOT a TODO entry (it's a one-shot design doc, not ongoing work).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test(brain): bump schema-migration test timeout to 60s

Rebuild path fans out to 7 per-project entity refreshes, each shelling
gbrain with 10s internal timeout. Worst case ~70s. Default bun test
5s was timing out on slow brain unreachable cases.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore: bump version and changelog (v1.50.0.0)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(test): tighten put_page regression pin to CLI subcommand

The test asserted no substring 'put_page' anywhere in the resolver,
but the BRAIN_WRITE_BACK resolver legitimately references the MCP op
`mcp__gbrain__put_page` as the fallback path for calibration takes
when gbrain v0.42+'s `takes_add` op isn't available. The check
conflated the deprecated `gbrain put_page` CLI subcommand (renamed in
v0.18+ to `gbrain put`) with the still-valid MCP op of the same name.

Narrow the assertion to `gbrain put_page` (with the space) so the
fallback prose stays legal while the CLI rename regression stays caught.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(brain): gstack-config gbrain-refresh subcommand

Adds a new subcommand that re-detects gbrain installation state and
persists the result to ~/.gstack/gbrain-detection.json. The detection
file is consumed by gen-skill-docs --respect-detection (next commit)
to decide whether to render the GBRAIN_CONTEXT_LOAD and
GBRAIN_SAVE_RESULTS resolver blocks in user-local SKILL.md generation.

Reuses the existing bin/gstack-gbrain-detect helper for the actual
probe; this subcommand just persists + summarizes. Users run it after
installing or uninstalling gbrain so their locally generated SKILL.md
files match their installation state.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(brain): gen-skill-docs respects gbrain-detection override

Adds --respect-detection flag (and bun run gen:skill-docs:user script).
When the flag is set, gen-skill-docs reads ~/.gstack/gbrain-detection.json
and filters GBRAIN_CONTEXT_LOAD + GBRAIN_SAVE_RESULTS out of each host's
suppressedResolvers when gbrain_local_status is "ok". When absent or
gbrain isn't detected, suppression behaves as before.

The default `bun run gen:skill-docs` (CI canonical) ignores the
detection file so the committed SKILL.md stays reproducible regardless
of any developer's local gbrain installation state. Use
gen:skill-docs:user for user-local installs (./setup invokes it).

No host config files modified — the static suppressedResolvers stay
correct for the no-gbrain case; the override happens at gen-time.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(brain): setup runs gbrain detection + conditional SKILL.md regen

At the end of install, ./setup now:
  1. Runs bin/gstack-gbrain-detect, persists the result to
     ~/.gstack/gbrain-detection.json
  2. If gbrain_local_status == "ok", regenerates Claude-host SKILL.md
     via `bun run gen:skill-docs:user --host claude` so the user's
     local install picks up the compressed brain-aware blocks
  3. If gbrain isn't detected, leaves the canonical no-gbrain SKILL.md
     files in place (zero token overhead) and surfaces the
     gstack-config gbrain-refresh path for users who install gbrain
     later

Together with the prior two commits, this completes the setup-time
conditional un-suppression: brain-aware blocks render iff the user
has gbrain installed, regardless of which CLI host they're on.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* refactor(brain): compress GBRAIN_* resolvers, move template prose to docs/

generateGBrainContextLoad: 80 -> 115 tokens with explicit skip-header.
generateGBrainSaveResults: 500-700 -> 161 tokens per skill with the
skill metadata extracted into a typed skillSaveMap (slugPrefix + title
+ tag). Verbose prose (heredoc body, entity-stub instructions, throttle
handling, backlink protocol) moved into a new doc:
docs/gbrain-write-surfaces.md (Sections: §Context Load, §Save Template).
The agent reads the doc on-demand only when actually saving — one Read
call, cached by Claude's context.

Net per-planning-skill overhead under un-suppression drops from ~1000
tokens (naive un-suppression) to ~275 tokens (compressed). Combined
with the setup-time detection from prior commits, users WITHOUT gbrain
pay zero overhead (block suppressed at gen-time) and users WITH gbrain
pay ~275 tokens.

The /investigate special-case (data-research routing in CONTEXT_LOAD)
stays inline since it's skill-specific.

docs/gbrain-write-surfaces.md also serves as the manual-probe reference
for humans verifying live persistence + a topology summary covering
trust-policy + .gbrain-source reads-only semantics.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(brain): wire SAVE_RESULTS for plan-design-review + plan-devex-review

Adds {{GBRAIN_SAVE_RESULTS}} placeholder to the two planning skills
that were missing it, immediately before {{BRAIN_WRITE_BACK}} (mirrors
plan-eng-review:324 + office-hours:650). The corresponding skillSaveMap
entries (design-reviews/<feature-slug> + devex-reviews/<feature-slug>)
landed with the resolver compression in the prior commit.

Regenerated SKILL.md reflects the new placeholder position. The
default no-gbrain generation (CI canonical) still suppresses the
block — zero diff in the rendered output for non-gbrain users.

All five planning skills now write a retrievable review page to gbrain
when gbrain is detected at setup time, instead of three of five.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test(brain): resolver compression + detection-override regression pins

test/resolvers-gbrain-save-results.test.ts (140 LOC, 10 tests):
  - Per-skill assertions for all 5 planning skills: emits gbrain put +
    correct slug prefix + tag + title.
  - Skip-header present so agent can short-circuit when gbrain isn't
    on PATH.
  - Compression pin: each per-skill block stays under 750 chars
    (~190 tokens) — guards against a future "let me add one more
    line" refactor silently re-inflating toward the ~1000-token naive
    un-suppression baseline.
  - Generic fallback for unmapped skill names still works.
  - /investigate gets the data-research routing suffix; non-investigate
    skills do not.
  - generateGBrainContextLoad stays under 500 chars (~125 tokens).

test/gbrain-detection-override.test.ts (120 LOC, 4 tests):
  - End-to-end through gen-skill-docs subprocess against an isolated
    temp GSTACK_HOME. Asserts:
    * detected:true un-suppresses GBRAIN_* → SKILL.md gains the block
    * detected:false (status != "ok") suppresses → no block
    * no detection file suppresses → no block (graceful default)
    * no --respect-detection flag IGNORES the detection file → no
      block (CI canonical path stays reproducible)

Each detection-override test restores the canonical SKILL.md in a
finally block so the working tree stays clean.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test(brain): fake-CLI agent-obedience E2E for /office-hours writeback

test/skill-e2e-office-hours-brain-writeback.test.ts (~210 LOC,
periodic-tier, ~$0.50-1/run):

Drives /office-hours via runSkillTest against a deterministic fixture
brief (pixel.fund founder pitch). The workdir has:
  - A regenerated office-hours/SKILL.md with the compressed brain blocks
    (generated via gen-skill-docs --respect-detection against a temp
    GSTACK_HOME, then restored to canonical post-snapshot)
  - A fake gbrain shell script on PATH that uses printf %q quoting to
    preserve --content "$(cat <<'EOF' ... EOF)" heredoc payloads
    intact (naive `echo "$@"` would lose argv boundaries)
  - The docs/gbrain-write-surfaces.md the resolver points to

Asserts:
  - gbrain-calls.log contains `gbrain put office-hours/pixel-fund`
  - Payload file at gbrain-payloads/office-hours/pixel-fund.md exists
    with valid YAML frontmatter (title: + tags: + design-doc tag)
  - At least one gbrain put entities/<name> call (entity stub
    enrichment is best-effort, soft warning if absent)

Covers agent obedience to the SAVE_RESULTS instruction. Out of scope:
gbrain CLI persistence contract (T11 covers that with real PGLite).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test(brain): real PGLite round-trip E2E (matched-pair persistence)

test/skill-e2e-gbrain-roundtrip-local.test.ts (~145 LOC, periodic-tier,
~$0.001/run on Voyage):

Real gbrain CLI round-trip against an isolated temp HOME:
  1. gbrain init --pglite --embedding-model voyage:voyage-code-3
  2. gbrain put office-hours/<unique-slug> --content <markdown>
  3. gbrain get <slug>
  4. Assert every body line survives + title + tags + non-empty

This is the matched-pair check for the v1.50.0.0 question "is the data
we hope to save actually being saved?" — proves the gbrain CLI
persistence contract gstack relies on, against a real engine.

Does NOT involve the agent — pure CLI integration test. The agent
obedience side is covered by the fake-CLI E2E in the prior commit.

Skips cleanly when VOYAGE_API_KEY is unset OR gbrain CLI is missing
from PATH, so CI without secrets degrades gracefully.

Remote/Supabase routing is gbrain's contract — the same CLI shape
works against every engine. gstack stops at local round-trip coverage
to avoid re-testing gbrain's MCP client implementation.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore(brain): touchfiles + TODOS + CHANGELOG for v1.50.0.0

test/helpers/touchfiles.ts: register the two new E2Es in
E2E_TOUCHFILES + E2E_TIERS (both periodic):
  - office-hours-brain-writeback: triggered by resolver / gen-pipeline /
    detection helper / refresh subcommand / office-hours template /
    docs / fixture / test file changes
  - gbrain-roundtrip-local: triggered by resolver / test file changes

TODOS.md: append two P2 follow-ups carried over from the v1.50 plan:
  - Re-verify calibration takes when gbrain v0.42+ ships takes_add and
    BRAIN_CALIBRATION_WRITEBACK flips TRUE
  - Extend brain-writeback E2E to the other 4 planning skills (extract
    makeFakeGbrain to test/helpers/fake-gbrain.ts when second consumer
    arrives)

CHANGELOG.md v1.50.0.0: add a "Save-results path: works under any CLI
when gbrain is on PATH" section that documents the headline:
  - Conditional inclusion at setup-time (zero overhead for non-gbrain
    users, ~250 tokens with gbrain)
  - Wiring symmetry fix (5 of 5 planning skills now write a page)
  - Token cost table comparing detection states
  - Test coverage map (resolver unit + override mechanism + fake-CLI
    agent obedience + real PGLite round-trip)
  - Why remote routing isn't tested here (gbrain's contract)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* test(brain): tighten prompt + relax slug assertion in writeback E2E

Two fixes:

1. Prompt: "Slug it 'pixel-fund'" was ambiguous — agent could read it
   as "use pixel-fund as the FULL slug" instead of "substitute
   pixel-fund for <feature-slug>". Replaced with explicit guidance:
   "The feature-slug value to substitute into the SAVE_RESULTS
   template's <feature-slug> placeholder is exactly 'pixel-fund' (no
   path prefix — the template already provides the prefix). Apply the
   SAVE_RESULTS template literally." Also added "Do NOT explore gbrain
   --help" to short-circuit the discovery loop the agent fell into.

2. Slug assertion: was a strict /gbrain put .*office-hours\/pixel-fund/
   regex. This conflated two concerns — agent obedience (does the
   agent actually invoke gbrain put?) vs resolver output shape (does
   the template emit the right prefix?). The latter is already pinned
   by test/resolvers-gbrain-save-results.test.ts at the resolver level
   (free, hermetic). The E2E now asserts /gbrain put .*pixel-fund/
   (slug contains pixel-fund somewhere) plus a recursive payload-file
   search that accepts either office-hours/pixel-fund.md (template-
   faithful) or pixel-fund.md (agent dropped prefix). The YAML
   frontmatter + tag assertions on the payload remain strict — those
   are the real agent-obedience contract.

3. Entity-stub regex: was looking for entities/<name>; agent
   variability uses entity/<name>, people/<name>, companies/<name>.
   Loosened to match entit(y|ies) only. The soft-warning path stays
   (no hard fail) because entity extraction is best-effort prose, not
   a CLI contract.

Verified passing locally: 7 expect() calls, 268s, ~$0.50.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore: bump version to 1.51.1.0

main advanced to 1.51.0.0 while this branch was in development. Bump
to 1.51.1.0 (PATCH above main) so the branch lands cleanly above the
current main version per the monotonic-ordered-release invariant.

Renames the branch-internal [1.50.0.0] CHANGELOG entry to [1.51.1.0] —
1.50.0.0 never landed on main (main skipped to 1.51.0.0), so this
consolidates the branch's brain-aware planning + save-results work
under a single shipping version with no orphaned entry.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-29 08:35:00 -07:00

1288 lines
52 KiB
Bash
Executable File

#!/usr/bin/env bash
# gstack setup — build browser binary + register skills with Claude Code / Codex
set -e
umask 077 # Restrict new files to owner-only (0o600 files, 0o700 dirs)
if ! command -v bun >/dev/null 2>&1; then
echo "Error: bun is required but not installed." >&2
echo "Install with checksum verification:" >&2
echo ' BUN_VERSION="1.3.10"' >&2
echo ' tmpfile=$(mktemp)' >&2
echo ' curl -fsSL "https://bun.sh/install" -o "$tmpfile"' >&2
echo ' echo "Verify checksum before running: shasum -a 256 $tmpfile"' >&2
echo ' BUN_VERSION="$BUN_VERSION" bash "$tmpfile" && rm "$tmpfile"' >&2
exit 1
fi
INSTALL_GSTACK_DIR="$(cd "$(dirname "$0")" && pwd)"
SOURCE_GSTACK_DIR="$(cd "$(dirname "$0")" && pwd -P)"
INSTALL_SKILLS_DIR="$(dirname "$INSTALL_GSTACK_DIR")"
BROWSE_BIN="$SOURCE_GSTACK_DIR/browse/dist/browse"
CODEX_SKILLS="$HOME/.codex/skills"
CODEX_GSTACK="$CODEX_SKILLS/gstack"
FACTORY_SKILLS="$HOME/.factory/skills"
FACTORY_GSTACK="$FACTORY_SKILLS/gstack"
OPENCODE_SKILLS="$HOME/.config/opencode/skills"
OPENCODE_GSTACK="$OPENCODE_SKILLS/gstack"
IS_WINDOWS=0
case "$(uname -s)" in
MINGW*|MSYS*|CYGWIN*|Windows_NT) IS_WINDOWS=1 ;;
esac
# ─── Symlink-or-copy helper ───────────────────────────────────
# On macOS/Linux: create a symlink (existing behavior).
# On Windows without Developer Mode (MSYS2/Git Bash): plain ln -snf silently
# creates a frozen file copy that doesn't refresh after `git pull`. We use
# explicit `cp -R` / `cp -f` so the user gets a real copy and the staleness
# is reportable (re-run ./setup after pull). Auto-detects file vs dir.
#
# INVARIANT: every symlink in this script MUST route through this helper.
# A raw ln call here will be caught by test/setup-windows-fallback.test.ts
# (the static-invariant assertion D7).
_link_or_copy() {
local src="$1"
local dst="$2"
if [ "$IS_WINDOWS" -eq 1 ]; then
rm -rf "$dst"
# Unix `ln -snf` accepts a name-only or relative-path source even when the
# target doesn't resolve from CWD (e.g. the connect-chrome alias points at
# the sibling-relative "gstack/open-gstack-browser"). On Windows the
# equivalent semantics don't exist — we'd need a real source on disk to
# copy. Skip the alias quietly rather than aborting setup under `set -e`.
if [ ! -e "$src" ]; then
return 0
fi
if [ -d "$src" ]; then
cp -R "$src" "$dst"
else
cp -f "$src" "$dst"
fi
else
ln -snf "$src" "$dst"
fi
}
_WINDOWS_COPY_NOTE_PRINTED=0
_print_windows_copy_note_once() {
if [ "$IS_WINDOWS" -eq 1 ] && [ "$_WINDOWS_COPY_NOTE_PRINTED" -eq 0 ]; then
echo " note: Windows install uses file copies (no Developer Mode required). Re-run ./setup after every 'git pull' to refresh skill files."
_WINDOWS_COPY_NOTE_PRINTED=1
fi
}
# ─── Quiet mode helper ────────────────────────────────────────
QUIET=0
log() { [ "$QUIET" -eq 0 ] && echo "$@" || true; }
# ─── Parse flags ──────────────────────────────────────────────
HOST="claude"
LOCAL_INSTALL=0
SKILL_PREFIX=1
SKILL_PREFIX_FLAG=0
TEAM_MODE=0
NO_TEAM_MODE=0
while [ $# -gt 0 ]; do
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="$2"; shift 2 ;;
--host=*) HOST="${1#--host=}"; shift ;;
--local) LOCAL_INSTALL=1; shift ;;
--prefix) SKILL_PREFIX=1; SKILL_PREFIX_FLAG=1; shift ;;
--no-prefix) SKILL_PREFIX=0; SKILL_PREFIX_FLAG=1; shift ;;
--team) TEAM_MODE=1; shift ;;
--no-team) NO_TEAM_MODE=1; shift ;;
-q|--quiet) QUIET=1; shift ;;
*) shift ;;
esac
done
case "$HOST" in
claude|codex|kiro|factory|opencode|auto) ;;
openclaw)
echo ""
echo "OpenClaw integration uses a different model — OpenClaw spawns Claude Code"
echo "sessions natively via ACP. gstack provides methodology artifacts, not a"
echo "full skill installation."
echo ""
echo "To integrate gstack with OpenClaw:"
echo " 1. Tell your OpenClaw agent: 'install gstack for openclaw'"
echo " 2. Or generate artifacts: bun run gen:skill-docs --host openclaw"
echo " 3. See docs/OPENCLAW.md for the full architecture"
echo ""
exit 0 ;;
hermes)
echo ""
echo "Hermes integration uses the same model as OpenClaw — Hermes spawns"
echo "Claude Code sessions, and gstack provides methodology artifacts."
echo ""
echo "To integrate gstack with Hermes:"
echo " 1. Tell your Hermes agent: 'install gstack for hermes'"
echo " 2. Or generate artifacts: bun run gen:skill-docs --host hermes"
echo ""
exit 0 ;;
gbrain)
echo ""
echo "GBrain is a mod for gstack — it makes coding skills brain-aware."
echo "GBrain generates brain-enhanced skill variants that search your brain"
echo "for context before starting and save results after finishing."
echo ""
echo "To generate brain-aware skills:"
echo " bun run gen:skill-docs --host gbrain"
echo ""
echo "GBrain setup and brain skills ship from the GBrain repo."
echo ""
exit 0 ;;
*) echo "Unknown --host value: $HOST (expected claude, codex, kiro, factory, opencode, openclaw, hermes, gbrain, or auto)" >&2; exit 1 ;;
esac
# ─── Resolve skill prefix preference ─────────────────────────
# Priority: CLI flag > saved config > interactive prompt (or flat default for non-TTY)
GSTACK_CONFIG="$SOURCE_GSTACK_DIR/bin/gstack-config"
export GSTACK_SETUP_RUNNING=1 # Prevent gstack-config post-set hook from triggering relink mid-setup
if [ "$SKILL_PREFIX_FLAG" -eq 0 ]; then
_saved_prefix="$("$GSTACK_CONFIG" get skill_prefix 2>/dev/null || true)"
if [ "$_saved_prefix" = "true" ]; then
SKILL_PREFIX=1
elif [ "$_saved_prefix" = "false" ]; then
SKILL_PREFIX=0
else
# No saved preference — prompt interactively (or default flat for non-TTY/quiet)
if [ "$QUIET" -eq 1 ]; then
SKILL_PREFIX=0
elif [ -t 0 ]; then
echo ""
echo "Skill naming: how should gstack skills appear?"
echo ""
echo " 1) Short names: /qa, /ship, /review"
echo " Recommended. Clean and fast to type."
echo ""
echo " 2) Namespaced: /gstack-qa, /gstack-ship, /gstack-review"
echo " Use this if you run other skill packs alongside gstack to avoid conflicts."
echo ""
printf "Choice [1/2] (default: 1, auto-selects in 10s): "
read -t 10 -r _prefix_choice </dev/tty 2>/dev/null || _prefix_choice=""
case "$_prefix_choice" in
2) SKILL_PREFIX=1 ;;
*) SKILL_PREFIX=0 ;;
esac
else
SKILL_PREFIX=0
fi
# Save the choice for future runs
"$GSTACK_CONFIG" set skill_prefix "$([ "$SKILL_PREFIX" -eq 1 ] && echo true || echo false)" 2>/dev/null || true
fi
else
# Flag was passed explicitly — persist the choice
"$GSTACK_CONFIG" set skill_prefix "$([ "$SKILL_PREFIX" -eq 1 ] && echo true || echo false)" 2>/dev/null || true
fi
# --local: install to .claude/skills/ in the current working directory (deprecated)
if [ "$LOCAL_INSTALL" -eq 1 ]; then
echo "Warning: --local is deprecated. Use global install + --team instead." >&2
echo " See: https://github.com/garrytan/gstack#team-mode" >&2
if [ "$HOST" = "codex" ]; then
echo "Error: --local is only supported for Claude Code (not Codex)." >&2
exit 1
fi
INSTALL_SKILLS_DIR="$(pwd)/.claude/skills"
mkdir -p "$INSTALL_SKILLS_DIR"
HOST="claude"
INSTALL_CODEX=0
fi
# For auto: detect which agents are installed
INSTALL_CLAUDE=0
INSTALL_CODEX=0
INSTALL_KIRO=0
INSTALL_FACTORY=0
INSTALL_OPENCODE=0
if [ "$HOST" = "auto" ]; then
command -v claude >/dev/null 2>&1 && INSTALL_CLAUDE=1
command -v codex >/dev/null 2>&1 && INSTALL_CODEX=1
command -v kiro-cli >/dev/null 2>&1 && INSTALL_KIRO=1
command -v droid >/dev/null 2>&1 && INSTALL_FACTORY=1
command -v opencode >/dev/null 2>&1 && INSTALL_OPENCODE=1
# If none found, default to claude
if [ "$INSTALL_CLAUDE" -eq 0 ] && [ "$INSTALL_CODEX" -eq 0 ] && [ "$INSTALL_KIRO" -eq 0 ] && [ "$INSTALL_FACTORY" -eq 0 ] && [ "$INSTALL_OPENCODE" -eq 0 ]; then
INSTALL_CLAUDE=1
fi
elif [ "$HOST" = "claude" ]; then
INSTALL_CLAUDE=1
elif [ "$HOST" = "codex" ]; then
INSTALL_CODEX=1
elif [ "$HOST" = "kiro" ]; then
INSTALL_KIRO=1
elif [ "$HOST" = "factory" ]; then
INSTALL_FACTORY=1
elif [ "$HOST" = "opencode" ]; then
INSTALL_OPENCODE=1
fi
migrate_direct_codex_install() {
local gstack_dir="$1"
local codex_gstack="$2"
local migrated_dir="$HOME/.gstack/repos/gstack"
[ "$gstack_dir" = "$codex_gstack" ] || return 0
[ -L "$gstack_dir" ] && return 0
mkdir -p "$(dirname "$migrated_dir")"
if [ -e "$migrated_dir" ] && [ "$migrated_dir" != "$gstack_dir" ]; then
echo "gstack setup failed: direct Codex install detected at $gstack_dir" >&2
echo "A migrated repo already exists at $migrated_dir; move one of them aside and rerun setup." >&2
exit 1
fi
log "Migrating direct Codex install to $migrated_dir to avoid duplicate skill discovery..."
mv "$gstack_dir" "$migrated_dir"
SOURCE_GSTACK_DIR="$migrated_dir"
INSTALL_GSTACK_DIR="$migrated_dir"
INSTALL_SKILLS_DIR="$(dirname "$INSTALL_GSTACK_DIR")"
BROWSE_BIN="$SOURCE_GSTACK_DIR/browse/dist/browse"
}
if [ "$INSTALL_CODEX" -eq 1 ]; then
migrate_direct_codex_install "$SOURCE_GSTACK_DIR" "$CODEX_GSTACK"
fi
ensure_playwright_browser() {
if [ "$IS_WINDOWS" -eq 1 ]; then
# On Windows, Bun can't launch Chromium due to broken pipe handling
# (oven-sh/bun#4253). Use Node.js to verify Chromium works instead.
(
cd "$SOURCE_GSTACK_DIR"
node -e "const { chromium } = require('playwright'); (async () => { const b = await chromium.launch(); await b.close(); })()" 2>/dev/null
)
else
(
cd "$SOURCE_GSTACK_DIR"
bun --eval 'import { chromium } from "playwright"; const browser = await chromium.launch(); await browser.close();'
) >/dev/null 2>&1
fi
}
prepare_bun_for_windows_compile() {
BUN_CMD="bun"
BUN_CMD_WAS_COPIED=0
[ "$IS_WINDOWS" -eq 1 ] || return 0
local bun_path
bun_path="$(command -v bun 2>/dev/null || true)"
case "$bun_path" in
*[![:ascii:]]*)
local bun_copy_dir="$SOURCE_GSTACK_DIR/.tmp-bun-bin"
mkdir -p "$bun_copy_dir"
cp -f "$bun_path" "$bun_copy_dir/bun.exe"
BUN_CMD="$bun_copy_dir/bun.exe"
BUN_CMD_WAS_COPIED=1
;;
esac
}
bun_cmd() {
"$BUN_CMD" "$@"
}
cleanup_copied_bun() {
if [ "${BUN_CMD_WAS_COPIED:-0}" -eq 1 ]; then
rm -rf "$SOURCE_GSTACK_DIR/.tmp-bun-bin"
fi
}
prepare_bun_for_windows_compile
trap cleanup_copied_bun EXIT
# 1. Build browse binary if needed (smart rebuild: stale sources, package.json, lock)
NEEDS_BUILD=0
if [ ! -x "$BROWSE_BIN" ]; then
NEEDS_BUILD=1
elif [ -n "$(find "$SOURCE_GSTACK_DIR/browse/src" -type f -newer "$BROWSE_BIN" -print -quit 2>/dev/null)" ]; then
NEEDS_BUILD=1
elif [ "$SOURCE_GSTACK_DIR/package.json" -nt "$BROWSE_BIN" ]; then
NEEDS_BUILD=1
elif [ -f "$SOURCE_GSTACK_DIR/bun.lock" ] && [ "$SOURCE_GSTACK_DIR/bun.lock" -nt "$BROWSE_BIN" ]; then
NEEDS_BUILD=1
fi
if [ "$NEEDS_BUILD" -eq 1 ]; then
log "Building browse binary..."
(
cd "$SOURCE_GSTACK_DIR"
bun_cmd install --frozen-lockfile 2>/dev/null || bun_cmd install
bun_cmd run build
)
# Safety net: write .version if build script didn't (e.g., git not available during build)
if [ ! -f "$SOURCE_GSTACK_DIR/browse/dist/.version" ]; then
git -C "$SOURCE_GSTACK_DIR" rev-parse HEAD > "$SOURCE_GSTACK_DIR/browse/dist/.version" 2>/dev/null || true
fi
# macOS Apple Silicon: ad-hoc codesign compiled binaries.
# Bun's --compile can produce a corrupt or linker-only code signature that
# macOS kills with SIGKILL (exit 137). The two-step remove+re-sign is
# required because a naive `codesign -s - -f` fails when the existing
# signature block is corrupt. This is idempotent and costs <1s.
# See: https://github.com/garrytan/gstack/issues/997
if [ "$(uname -s)" = "Darwin" ] && [ "$(uname -m)" = "arm64" ]; then
for _bin in browse/dist/browse browse/dist/find-browse design/dist/design make-pdf/dist/pdf bin/gstack-global-discover; do
_bin_path="$SOURCE_GSTACK_DIR/$_bin"
[ -f "$_bin_path" ] && [ -x "$_bin_path" ] || continue
codesign --remove-signature "$_bin_path" 2>/dev/null || true
if ! codesign -s - -f "$_bin_path" 2>/dev/null; then
log "warning: codesign failed for $_bin (binary may not run on Apple Silicon)"
fi
done
fi
# macOS: install coreutils for `gtimeout` (Codex hang protection in /codex + /autoplan).
# macOS ships BSD `timeout`-less; Homebrew's coreutils installs GNU timeout as
# `gtimeout` to avoid shadowing BSD utilities. The /codex and /autoplan skills
# fall back to unwrapped codex invocations when neither is available — this
# auto-install upgrades them to hang-protected where possible.
# Skip entirely with GSTACK_SKIP_COREUTILS=1 (CI, managed machines, offline envs).
if [ "$(uname -s)" = "Darwin" ] && [ "${GSTACK_SKIP_COREUTILS:-0}" != "1" ]; then
if ! command -v gtimeout >/dev/null 2>&1 && ! command -v timeout >/dev/null 2>&1; then
if command -v brew >/dev/null 2>&1; then
log "Installing coreutils for Codex hang protection (set GSTACK_SKIP_COREUTILS=1 to skip)..."
brew install coreutils >/dev/null 2>&1 || log "warning: brew install coreutils failed; /codex will run without hang protection"
else
log "warning: Homebrew not found. /codex will run without hang protection. Install coreutils manually or set GSTACK_SKIP_COREUTILS=1."
fi
fi
fi
fi
if [ ! -x "$BROWSE_BIN" ]; then
echo "gstack setup failed: browse binary missing at $BROWSE_BIN" >&2
exit 1
fi
# 1b. Generate .agents/ Codex skill docs — always regenerate to prevent stale descriptions.
# .agents/ is no longer committed — generated at setup time from .tmpl templates.
# bun run build already does this, but we need it when NEEDS_BUILD=0 (binary is fresh).
# Always regenerate: generation is fast (<2s) and mtime-based staleness checks are fragile
# (miss stale files when timestamps match after clone/checkout/upgrade).
AGENTS_DIR="$SOURCE_GSTACK_DIR/.agents/skills"
NEEDS_AGENTS_GEN=1
if [ "$NEEDS_AGENTS_GEN" -eq 1 ] && [ "$NEEDS_BUILD" -eq 0 ]; then
log "Generating .agents/ skill docs..."
(
cd "$SOURCE_GSTACK_DIR"
bun_cmd install --frozen-lockfile 2>/dev/null || bun_cmd install
bun_cmd run gen:skill-docs --host codex
)
fi
# 1c. Generate .factory/ Factory Droid skill docs
if [ "$INSTALL_FACTORY" -eq 1 ] && [ "$NEEDS_BUILD" -eq 0 ]; then
log "Generating .factory/ skill docs..."
(
cd "$SOURCE_GSTACK_DIR"
bun_cmd install --frozen-lockfile 2>/dev/null || bun_cmd install
bun_cmd run gen:skill-docs --host factory
)
fi
# 1d. Generate .opencode/ OpenCode skill docs
if [ "$INSTALL_OPENCODE" -eq 1 ] && [ "$NEEDS_BUILD" -eq 0 ]; then
log "Generating .opencode/ skill docs..."
(
cd "$SOURCE_GSTACK_DIR"
bun_cmd install --frozen-lockfile 2>/dev/null || bun_cmd install
bun_cmd run gen:skill-docs --host opencode
)
fi
# 2. Ensure Playwright's Chromium is available
if ! ensure_playwright_browser; then
echo "Installing Playwright Chromium..."
(
cd "$SOURCE_GSTACK_DIR"
bunx playwright install chromium
)
if [ "$IS_WINDOWS" -eq 1 ]; then
# On Windows, Node.js launches Chromium (not Bun — see oven-sh/bun#4253).
# Ensure playwright is importable by Node from the gstack directory.
if ! command -v node >/dev/null 2>&1; then
echo "gstack setup failed: Node.js is required on Windows (Bun cannot launch Chromium due to a pipe bug)" >&2
echo " Install Node.js: https://nodejs.org/" >&2
exit 1
fi
echo "Windows detected — verifying Node.js can load Playwright..."
(
cd "$SOURCE_GSTACK_DIR"
# Bun's node_modules already has playwright; verify Node can require it
node -e "require('playwright')" 2>/dev/null || npm install --no-save playwright
# @ngrok/ngrok is externalized in server-node.mjs and resolved at runtime.
# Verify the platform-specific native binary is installed so /pair-agent
# tunnels don't fail later with a cryptic module-not-found error.
node -e "require('@ngrok/ngrok')" 2>/dev/null || npm install --no-save @ngrok/ngrok
)
fi
fi
if ! ensure_playwright_browser; then
if [ "$IS_WINDOWS" -eq 1 ]; then
echo "gstack setup failed: Playwright Chromium could not be launched via Node.js" >&2
echo " This is a known issue with Bun on Windows (oven-sh/bun#4253)." >&2
echo " Ensure Node.js is installed and 'node -e \"require('playwright')\"' works." >&2
else
echo "gstack setup failed: Playwright Chromium could not be launched" >&2
fi
exit 1
fi
# 3. Ensure ~/.gstack global state directory exists
mkdir -p "$HOME/.gstack/projects"
# ─── Helper: link Claude skill subdirectories into a skills parent directory ──
# Creates real directories (not symlinks) at the top level with a SKILL.md symlink
# inside. This ensures Claude discovers them as top-level skills, not nested under
# gstack/ (which would auto-prefix them as gstack-*).
# When SKILL_PREFIX=1, directories are prefixed with "gstack-".
# Use --no-prefix to restore flat names.
link_claude_skill_dirs() {
local gstack_dir="$1"
local skills_dir="$2"
local linked=()
for skill_dir in "$gstack_dir"/*/; do
if [ -f "$skill_dir/SKILL.md" ]; then
dir_name="$(basename "$skill_dir")"
# Skip node_modules
[ "$dir_name" = "node_modules" ] && continue
# Use frontmatter name: if present (e.g., run-tests/ with name: test → symlink as "test")
skill_name=$(grep -m1 '^name:' "$skill_dir/SKILL.md" 2>/dev/null | sed 's/^name:[[:space:]]*//' | tr -d '[:space:]')
[ -z "$skill_name" ] && skill_name="$dir_name"
# Apply gstack- prefix unless --no-prefix or already prefixed
if [ "$SKILL_PREFIX" -eq 1 ]; then
case "$skill_name" in
gstack-*) link_name="$skill_name" ;;
*) link_name="gstack-$skill_name" ;;
esac
else
link_name="$skill_name"
fi
target="$skills_dir/$link_name"
# Upgrade old directory symlinks to real directories
if [ -L "$target" ]; then
rm -f "$target"
fi
# Create real directory with symlinked SKILL.md (absolute path)
# Use mkdir -p unconditionally (idempotent) to avoid TOCTOU race
mkdir -p "$target"
# Validate target isn't a symlink before creating the link
if [ -L "$target/SKILL.md" ]; then rm "$target/SKILL.md"; fi
_link_or_copy "$gstack_dir/$dir_name/SKILL.md" "$target/SKILL.md"
linked+=("$link_name")
fi
done
if [ ${#linked[@]} -gt 0 ]; then
echo " linked skills: ${linked[*]}"
_print_windows_copy_note_once
fi
}
# Claude Code skips the repo-shaped ~/.claude/skills/gstack directory when
# building the user-facing slash-command list. Keep the repo path for runtime
# assets, and add a separate thin wrapper whose frontmatter name remains
# `gstack` so `/gstack` can autocomplete.
link_claude_root_skill_alias() {
local gstack_dir="$1"
local skills_dir="$2"
local target="$skills_dir/_gstack-command"
[ -f "$gstack_dir/SKILL.md" ] || return 0
if [ -L "$target" ]; then
rm -f "$target"
fi
mkdir -p "$target"
if [ -L "$target/SKILL.md" ]; then rm "$target/SKILL.md"; fi
_link_or_copy "$gstack_dir/SKILL.md" "$target/SKILL.md"
echo " linked root skill alias: gstack"
_print_windows_copy_note_once
}
# ─── Helper: remove old unprefixed Claude skill entries ───────────────────────
# Migration: when switching from flat names to gstack- prefixed names,
# clean up stale symlinks or directories that point into the gstack directory.
cleanup_old_claude_symlinks() {
local gstack_dir="$1"
local skills_dir="$2"
local removed=()
for skill_dir in "$gstack_dir"/*/; do
if [ -f "$skill_dir/SKILL.md" ]; then
skill_name="$(basename "$skill_dir")"
[ "$skill_name" = "node_modules" ] && continue
# Skip already-prefixed dirs (gstack-upgrade) — no old symlink to clean
case "$skill_name" in gstack-*) continue ;; esac
old_target="$skills_dir/$skill_name"
# Remove directory symlinks pointing into gstack/
if [ -L "$old_target" ]; then
link_dest="$(readlink "$old_target" 2>/dev/null || true)"
case "$link_dest" in
gstack/*|*/gstack/*)
rm -f "$old_target"
removed+=("$skill_name")
;;
esac
# Remove real directories with symlinked SKILL.md pointing into gstack/
elif [ -d "$old_target" ] && [ -L "$old_target/SKILL.md" ]; then
link_dest="$(readlink "$old_target/SKILL.md" 2>/dev/null || true)"
case "$link_dest" in
*gstack*)
rm -rf "$old_target"
removed+=("$skill_name")
;;
esac
# Windows install pattern: real dir with real-file SKILL.md (no symlink
# available, so we can't readlink to verify provenance). The outer loop
# iterates known gstack skill names from "$gstack_dir"/*, so a name match
# plus IS_WINDOWS is safe to treat as gstack-managed during a mode flip.
elif [ "$IS_WINDOWS" -eq 1 ] && [ -d "$old_target" ] && [ -f "$old_target/SKILL.md" ]; then
rm -rf "$old_target"
removed+=("$skill_name")
fi
fi
done
if [ ${#removed[@]} -gt 0 ]; then
echo " cleaned up old entries: ${removed[*]}"
fi
}
# ─── Helper: remove old prefixed Claude skill entries ─────────────────────────
# Reverse migration: when switching from gstack- prefixed names to flat names,
# clean up stale gstack-* symlinks or directories that point into the gstack directory.
cleanup_prefixed_claude_symlinks() {
local gstack_dir="$1"
local skills_dir="$2"
local removed=()
for skill_dir in "$gstack_dir"/*/; do
if [ -f "$skill_dir/SKILL.md" ]; then
skill_name="$(basename "$skill_dir")"
[ "$skill_name" = "node_modules" ] && continue
# Only clean up prefixed entries for dirs that AREN'T already prefixed
# (e.g., remove gstack-qa but NOT gstack-upgrade which is the real dir name)
case "$skill_name" in gstack-*) continue ;; esac
prefixed_target="$skills_dir/gstack-$skill_name"
# Remove directory symlinks pointing into gstack/
if [ -L "$prefixed_target" ]; then
link_dest="$(readlink "$prefixed_target" 2>/dev/null || true)"
case "$link_dest" in
gstack/*|*/gstack/*)
rm -f "$prefixed_target"
removed+=("gstack-$skill_name")
;;
esac
# Remove real directories with symlinked SKILL.md pointing into gstack/
elif [ -d "$prefixed_target" ] && [ -L "$prefixed_target/SKILL.md" ]; then
link_dest="$(readlink "$prefixed_target/SKILL.md" 2>/dev/null || true)"
case "$link_dest" in
*gstack*)
rm -rf "$prefixed_target"
removed+=("gstack-$skill_name")
;;
esac
# Windows install pattern: real dir with real-file SKILL.md. Same
# reasoning as cleanup_old_claude_symlinks — directory name match plus
# IS_WINDOWS is safe during a mode flip.
elif [ "$IS_WINDOWS" -eq 1 ] && [ -d "$prefixed_target" ] && [ -f "$prefixed_target/SKILL.md" ]; then
rm -rf "$prefixed_target"
removed+=("gstack-$skill_name")
fi
fi
done
if [ ${#removed[@]} -gt 0 ]; then
echo " cleaned up prefixed entries: ${removed[*]}"
fi
}
# ─── Helper: link generated Codex skills into a skills parent directory ──
# Installs from .agents/skills/gstack-* (the generated Codex-format skills)
# instead of source dirs (which have Claude paths).
link_codex_skill_dirs() {
local gstack_dir="$1"
local skills_dir="$2"
local agents_dir="$gstack_dir/.agents/skills"
local linked=()
if [ ! -d "$agents_dir" ]; then
echo " Generating .agents/ skill docs..."
( cd "$gstack_dir" && bun run gen:skill-docs --host codex )
fi
if [ ! -d "$agents_dir" ]; then
echo " warning: .agents/skills/ generation failed — run 'bun run gen:skill-docs --host codex' manually" >&2
return 1
fi
for skill_dir in "$agents_dir"/gstack*/; do
if [ -f "$skill_dir/SKILL.md" ]; then
skill_name="$(basename "$skill_dir")"
# Skip the sidecar directory — it contains runtime asset symlinks (bin/,
# browse/), not a skill. Linking it would overwrite the root gstack
# symlink that Step 5 already pointed at the repo root.
[ "$skill_name" = "gstack" ] && continue
target="$skills_dir/$skill_name"
# Create or update symlink
if [ -L "$target" ] || [ ! -e "$target" ]; then
_link_or_copy "$skill_dir" "$target"
linked+=("$skill_name")
fi
fi
done
if [ ${#linked[@]} -gt 0 ]; then
echo " linked skills: ${linked[*]}"
fi
}
# ─── Helper: create .agents/skills/gstack/ sidecar symlinks ──────────
# Codex/Gemini/Cursor read skills from .agents/skills/. We link runtime
# assets (bin/, browse/dist/, review/, qa/, etc.) so skill templates can
# resolve paths like $SKILL_ROOT/review/design-checklist.md.
create_agents_sidecar() {
local repo_root="$1"
local agents_gstack="$repo_root/.agents/skills/gstack"
mkdir -p "$agents_gstack"
# Sidecar directories that skills reference at runtime
for asset in bin browse review qa; do
local src="$SOURCE_GSTACK_DIR/$asset"
local dst="$agents_gstack/$asset"
if [ -d "$src" ] || [ -f "$src" ]; then
if [ -L "$dst" ] || [ ! -e "$dst" ]; then
_link_or_copy "$src" "$dst"
fi
fi
done
# Sidecar files that skills reference at runtime
for file in ETHOS.md; do
local src="$SOURCE_GSTACK_DIR/$file"
local dst="$agents_gstack/$file"
if [ -f "$src" ]; then
if [ -L "$dst" ] || [ ! -e "$dst" ]; then
_link_or_copy "$src" "$dst"
fi
fi
done
}
# ─── Helper: create a minimal ~/.codex/skills/gstack runtime root ───────────
# Codex scans ~/.codex/skills recursively. Exposing the whole repo here causes
# duplicate skills because source SKILL.md files and generated Codex skills are
# both discoverable. Keep this directory limited to runtime assets + root skill.
create_codex_runtime_root() {
local gstack_dir="$1"
local codex_gstack="$2"
local agents_dir="$gstack_dir/.agents/skills"
if [ -L "$codex_gstack" ]; then
rm -f "$codex_gstack"
elif [ -d "$codex_gstack" ] && [ "$codex_gstack" != "$gstack_dir" ]; then
# Old direct installs left a real directory here with stale source skills.
# Remove it so we start fresh with only the minimal runtime assets.
rm -rf "$codex_gstack"
fi
mkdir -p "$codex_gstack" "$codex_gstack/browse" "$codex_gstack/gstack-upgrade" "$codex_gstack/review"
if [ -f "$agents_dir/gstack/SKILL.md" ]; then
_link_or_copy "$agents_dir/gstack/SKILL.md" "$codex_gstack/SKILL.md"
fi
if [ -d "$gstack_dir/bin" ]; then
_link_or_copy "$gstack_dir/bin" "$codex_gstack/bin"
fi
if [ -d "$gstack_dir/browse/dist" ]; then
_link_or_copy "$gstack_dir/browse/dist" "$codex_gstack/browse/dist"
fi
if [ -d "$gstack_dir/browse/bin" ]; then
_link_or_copy "$gstack_dir/browse/bin" "$codex_gstack/browse/bin"
fi
if [ -f "$agents_dir/gstack-upgrade/SKILL.md" ]; then
_link_or_copy "$agents_dir/gstack-upgrade/SKILL.md" "$codex_gstack/gstack-upgrade/SKILL.md"
fi
# Review runtime assets (individual files, NOT the whole review/ dir which has SKILL.md)
for f in checklist.md design-checklist.md greptile-triage.md TODOS-format.md; do
if [ -f "$gstack_dir/review/$f" ]; then
_link_or_copy "$gstack_dir/review/$f" "$codex_gstack/review/$f"
fi
done
# ETHOS.md — referenced by "Search Before Building" in all skill preambles
if [ -f "$gstack_dir/ETHOS.md" ]; then
_link_or_copy "$gstack_dir/ETHOS.md" "$codex_gstack/ETHOS.md"
fi
}
create_factory_runtime_root() {
local gstack_dir="$1"
local factory_gstack="$2"
local factory_dir="$gstack_dir/.factory/skills"
if [ -L "$factory_gstack" ]; then
rm -f "$factory_gstack"
elif [ -d "$factory_gstack" ] && [ "$factory_gstack" != "$gstack_dir" ]; then
rm -rf "$factory_gstack"
fi
mkdir -p "$factory_gstack" "$factory_gstack/browse" "$factory_gstack/gstack-upgrade" "$factory_gstack/review"
if [ -f "$factory_dir/gstack/SKILL.md" ]; then
_link_or_copy "$factory_dir/gstack/SKILL.md" "$factory_gstack/SKILL.md"
fi
if [ -d "$gstack_dir/bin" ]; then
_link_or_copy "$gstack_dir/bin" "$factory_gstack/bin"
fi
if [ -d "$gstack_dir/browse/dist" ]; then
_link_or_copy "$gstack_dir/browse/dist" "$factory_gstack/browse/dist"
fi
if [ -d "$gstack_dir/browse/bin" ]; then
_link_or_copy "$gstack_dir/browse/bin" "$factory_gstack/browse/bin"
fi
if [ -f "$factory_dir/gstack-upgrade/SKILL.md" ]; then
_link_or_copy "$factory_dir/gstack-upgrade/SKILL.md" "$factory_gstack/gstack-upgrade/SKILL.md"
fi
for f in checklist.md design-checklist.md greptile-triage.md TODOS-format.md; do
if [ -f "$gstack_dir/review/$f" ]; then
_link_or_copy "$gstack_dir/review/$f" "$factory_gstack/review/$f"
fi
done
if [ -f "$gstack_dir/ETHOS.md" ]; then
_link_or_copy "$gstack_dir/ETHOS.md" "$factory_gstack/ETHOS.md"
fi
}
create_opencode_runtime_root() {
local gstack_dir="$1"
local opencode_gstack="$2"
local opencode_dir="$gstack_dir/.opencode/skills"
if [ -L "$opencode_gstack" ]; then
rm -f "$opencode_gstack"
elif [ -d "$opencode_gstack" ] && [ "$opencode_gstack" != "$gstack_dir" ]; then
rm -rf "$opencode_gstack"
fi
mkdir -p "$opencode_gstack" "$opencode_gstack/browse" "$opencode_gstack/design" "$opencode_gstack/gstack-upgrade" "$opencode_gstack/review" "$opencode_gstack/qa" "$opencode_gstack/plan-devex-review"
if [ -f "$opencode_dir/gstack/SKILL.md" ]; then
_link_or_copy "$opencode_dir/gstack/SKILL.md" "$opencode_gstack/SKILL.md"
fi
if [ -d "$gstack_dir/bin" ]; then
_link_or_copy "$gstack_dir/bin" "$opencode_gstack/bin"
fi
if [ -d "$gstack_dir/browse/dist" ]; then
_link_or_copy "$gstack_dir/browse/dist" "$opencode_gstack/browse/dist"
fi
if [ -d "$gstack_dir/browse/bin" ]; then
_link_or_copy "$gstack_dir/browse/bin" "$opencode_gstack/browse/bin"
fi
if [ -d "$gstack_dir/design/dist" ]; then
_link_or_copy "$gstack_dir/design/dist" "$opencode_gstack/design/dist"
fi
if [ -f "$opencode_dir/gstack-upgrade/SKILL.md" ]; then
_link_or_copy "$opencode_dir/gstack-upgrade/SKILL.md" "$opencode_gstack/gstack-upgrade/SKILL.md"
fi
for f in checklist.md design-checklist.md greptile-triage.md TODOS-format.md; do
if [ -f "$gstack_dir/review/$f" ]; then
_link_or_copy "$gstack_dir/review/$f" "$opencode_gstack/review/$f"
fi
done
if [ -d "$gstack_dir/review/specialists" ]; then
_link_or_copy "$gstack_dir/review/specialists" "$opencode_gstack/review/specialists"
fi
if [ -d "$gstack_dir/qa/templates" ]; then
_link_or_copy "$gstack_dir/qa/templates" "$opencode_gstack/qa/templates"
fi
if [ -d "$gstack_dir/qa/references" ]; then
_link_or_copy "$gstack_dir/qa/references" "$opencode_gstack/qa/references"
fi
if [ -f "$gstack_dir/plan-devex-review/dx-hall-of-fame.md" ]; then
_link_or_copy "$gstack_dir/plan-devex-review/dx-hall-of-fame.md" "$opencode_gstack/plan-devex-review/dx-hall-of-fame.md"
fi
if [ -f "$gstack_dir/ETHOS.md" ]; then
_link_or_copy "$gstack_dir/ETHOS.md" "$opencode_gstack/ETHOS.md"
fi
}
link_factory_skill_dirs() {
local gstack_dir="$1"
local skills_dir="$2"
local factory_dir="$gstack_dir/.factory/skills"
local linked=()
if [ ! -d "$factory_dir" ]; then
echo " Generating .factory/ skill docs..."
( cd "$gstack_dir" && bun run gen:skill-docs --host factory )
fi
if [ ! -d "$factory_dir" ]; then
echo " warning: .factory/skills/ generation failed — run 'bun run gen:skill-docs --host factory' manually" >&2
return 1
fi
for skill_dir in "$factory_dir"/gstack*/; do
if [ -f "$skill_dir/SKILL.md" ]; then
skill_name="$(basename "$skill_dir")"
[ "$skill_name" = "gstack" ] && continue
target="$skills_dir/$skill_name"
if [ -L "$target" ] || [ ! -e "$target" ]; then
_link_or_copy "$skill_dir" "$target"
linked+=("$skill_name")
fi
fi
done
if [ ${#linked[@]} -gt 0 ]; then
echo " linked skills: ${linked[*]}"
fi
}
link_opencode_skill_dirs() {
local gstack_dir="$1"
local skills_dir="$2"
local opencode_dir="$gstack_dir/.opencode/skills"
local linked=()
if [ ! -d "$opencode_dir" ]; then
echo " Generating .opencode/ skill docs..."
( cd "$gstack_dir" && bun run gen:skill-docs --host opencode )
fi
if [ ! -d "$opencode_dir" ]; then
echo " warning: .opencode/skills/ generation failed — run 'bun run gen:skill-docs --host opencode' manually" >&2
return 1
fi
for skill_dir in "$opencode_dir"/gstack*/; do
if [ -f "$skill_dir/SKILL.md" ]; then
skill_name="$(basename "$skill_dir")"
[ "$skill_name" = "gstack" ] && continue
target="$skills_dir/$skill_name"
if [ -L "$target" ] || [ ! -e "$target" ]; then
_link_or_copy "$skill_dir" "$target"
linked+=("$skill_name")
fi
fi
done
if [ ${#linked[@]} -gt 0 ]; then
echo " linked skills: ${linked[*]}"
fi
}
# 4. Install for Claude (default)
SKILLS_BASENAME="$(basename "$INSTALL_SKILLS_DIR")"
SKILLS_PARENT_BASENAME="$(basename "$(dirname "$INSTALL_SKILLS_DIR")")"
CODEX_REPO_LOCAL=0
if [ "$SKILLS_BASENAME" = "skills" ] && [ "$SKILLS_PARENT_BASENAME" = ".agents" ]; then
CODEX_REPO_LOCAL=1
fi
if [ "$INSTALL_CLAUDE" -eq 1 ]; then
if [ "$SKILLS_BASENAME" = "skills" ]; then
# Clean up stale symlinks from the opposite prefix mode
if [ "$SKILL_PREFIX" -eq 1 ]; then
cleanup_old_claude_symlinks "$SOURCE_GSTACK_DIR" "$INSTALL_SKILLS_DIR"
else
cleanup_prefixed_claude_symlinks "$SOURCE_GSTACK_DIR" "$INSTALL_SKILLS_DIR"
fi
# Patch name: fields BEFORE creating symlinks so link_claude_skill_dirs
# reads the correct (patched) name: values for symlink naming
"$SOURCE_GSTACK_DIR/bin/gstack-patch-names" "$SOURCE_GSTACK_DIR" "$SKILL_PREFIX"
link_claude_skill_dirs "$SOURCE_GSTACK_DIR" "$INSTALL_SKILLS_DIR"
link_claude_root_skill_alias "$SOURCE_GSTACK_DIR" "$INSTALL_SKILLS_DIR"
# Self-healing: re-run gstack-relink to ensure name: fields and directory
# names are consistent with the config. This catches cases where an interrupted
# setup, stale git state, or gen:skill-docs left name: fields out of sync.
GSTACK_RELINK="$SOURCE_GSTACK_DIR/bin/gstack-relink"
if [ -x "$GSTACK_RELINK" ]; then
GSTACK_SKILLS_DIR="$INSTALL_SKILLS_DIR" GSTACK_INSTALL_DIR="$SOURCE_GSTACK_DIR" "$GSTACK_RELINK" >/dev/null 2>&1 || true
fi
# Backwards-compat alias: /connect-chrome → /open-gstack-browser
_OGB_LINK="$INSTALL_SKILLS_DIR/connect-chrome"
if [ "$SKILL_PREFIX" -eq 1 ]; then
_OGB_LINK="$INSTALL_SKILLS_DIR/gstack-connect-chrome"
fi
if [ -L "$_OGB_LINK" ] || [ ! -e "$_OGB_LINK" ]; then
_link_or_copy "gstack/open-gstack-browser" "$_OGB_LINK"
fi
if [ "$LOCAL_INSTALL" -eq 1 ]; then
log "gstack ready (project-local)."
log " skills: $INSTALL_SKILLS_DIR"
else
log "gstack ready (claude)."
fi
log " browse: $BROWSE_BIN"
else
# Not inside a skills/ directory — would symlink the source into
# ~/.claude/skills/gstack/ and register from there.
CLAUDE_SKILLS_DIR="$HOME/.claude/skills"
CLAUDE_GSTACK_LINK="$CLAUDE_SKILLS_DIR/gstack"
# Conductor worktree guard: if ~/.claude/skills/gstack is already a real
# (non-symlink) directory pointing to a *different* install, refuse to plant
# a symlink there. On macOS/BSD, `ln -snf SRC DST` won't replace a real DST;
# it creates DST/$(basename SRC) → SRC inside it. The result is per-worktree
# symlinks leaking into the global install that Claude Code picks up as
# separate top-level skills (dublin-v1, lincoln-v2, ...). Typical trigger:
# running ./setup from a Conductor worktree of the gstack repo itself.
_SKIP_CLAUDE_REGISTER=0
if [ -d "$CLAUDE_GSTACK_LINK" ] && [ ! -L "$CLAUDE_GSTACK_LINK" ]; then
_EXISTING_REAL=$(cd "$CLAUDE_GSTACK_LINK" 2>/dev/null && pwd -P || echo "")
if [ -n "$_EXISTING_REAL" ] && [ "$_EXISTING_REAL" != "$SOURCE_GSTACK_DIR" ]; then
_SKIP_CLAUDE_REGISTER=1
fi
fi
if [ "$_SKIP_CLAUDE_REGISTER" -eq 1 ]; then
log ""
log " $CLAUDE_GSTACK_LINK already exists as a separate global install."
log " Skipping Claude skill registration to avoid polluting it with"
log " per-worktree symlinks. (Binaries still built locally for dev.)"
log ""
log " Global install: $CLAUDE_GSTACK_LINK"
log " This worktree: $SOURCE_GSTACK_DIR"
log ""
log " To register this worktree as the active gstack, remove the global"
log " install first: rm -rf $CLAUDE_GSTACK_LINK"
log ""
log "gstack built (claude registration skipped)."
log " browse: $BROWSE_BIN"
else
mkdir -p "$CLAUDE_SKILLS_DIR"
_link_or_copy "$SOURCE_GSTACK_DIR" "$CLAUDE_GSTACK_LINK"
log " symlinked $CLAUDE_GSTACK_LINK -> $SOURCE_GSTACK_DIR"
INSTALL_SKILLS_DIR="$CLAUDE_SKILLS_DIR"
INSTALL_GSTACK_DIR="$CLAUDE_GSTACK_LINK"
# Clean up stale symlinks from the opposite prefix mode
if [ "$SKILL_PREFIX" -eq 1 ]; then
cleanup_old_claude_symlinks "$SOURCE_GSTACK_DIR" "$INSTALL_SKILLS_DIR"
else
cleanup_prefixed_claude_symlinks "$SOURCE_GSTACK_DIR" "$INSTALL_SKILLS_DIR"
fi
"$SOURCE_GSTACK_DIR/bin/gstack-patch-names" "$SOURCE_GSTACK_DIR" "$SKILL_PREFIX"
link_claude_skill_dirs "$SOURCE_GSTACK_DIR" "$INSTALL_SKILLS_DIR"
link_claude_root_skill_alias "$SOURCE_GSTACK_DIR" "$INSTALL_SKILLS_DIR"
GSTACK_RELINK="$SOURCE_GSTACK_DIR/bin/gstack-relink"
if [ -x "$GSTACK_RELINK" ]; then
GSTACK_SKILLS_DIR="$INSTALL_SKILLS_DIR" GSTACK_INSTALL_DIR="$SOURCE_GSTACK_DIR" "$GSTACK_RELINK" >/dev/null 2>&1 || true
fi
_OGB_LINK="$INSTALL_SKILLS_DIR/connect-chrome"
if [ "$SKILL_PREFIX" -eq 1 ]; then
_OGB_LINK="$INSTALL_SKILLS_DIR/gstack-connect-chrome"
fi
if [ -L "$_OGB_LINK" ] || [ ! -e "$_OGB_LINK" ]; then
_link_or_copy "gstack/open-gstack-browser" "$_OGB_LINK"
fi
log "gstack ready (claude)."
log " browse: $BROWSE_BIN"
fi
fi
fi
# 5. Install for Codex
if [ "$INSTALL_CODEX" -eq 1 ]; then
if [ "$CODEX_REPO_LOCAL" -eq 1 ]; then
CODEX_SKILLS="$INSTALL_SKILLS_DIR"
CODEX_GSTACK="$INSTALL_GSTACK_DIR"
fi
mkdir -p "$CODEX_SKILLS"
# Skip runtime root creation for repo-local installs — the checkout IS the runtime root.
# create_codex_runtime_root would create self-referential symlinks (bin → bin, etc.).
if [ "$CODEX_REPO_LOCAL" -eq 0 ]; then
create_codex_runtime_root "$SOURCE_GSTACK_DIR" "$CODEX_GSTACK"
fi
# Install generated Codex-format skills (not Claude source dirs)
link_codex_skill_dirs "$SOURCE_GSTACK_DIR" "$CODEX_SKILLS"
log "gstack ready (codex)."
log " browse: $BROWSE_BIN"
log " codex skills: $CODEX_SKILLS"
fi
# 6. Install for Kiro CLI (copy from .agents/skills, rewrite paths)
if [ "$INSTALL_KIRO" -eq 1 ]; then
KIRO_SKILLS="$HOME/.kiro/skills"
AGENTS_DIR="$SOURCE_GSTACK_DIR/.agents/skills"
mkdir -p "$KIRO_SKILLS"
# Create gstack dir with symlinks for runtime assets, copy+sed for SKILL.md
KIRO_GSTACK="$KIRO_SKILLS/gstack"
# Remove old whole-dir symlink from previous installs
[ -L "$KIRO_GSTACK" ] && rm -f "$KIRO_GSTACK"
mkdir -p "$KIRO_GSTACK" "$KIRO_GSTACK/browse" "$KIRO_GSTACK/gstack-upgrade" "$KIRO_GSTACK/review"
_link_or_copy "$SOURCE_GSTACK_DIR/bin" "$KIRO_GSTACK/bin"
_link_or_copy "$SOURCE_GSTACK_DIR/browse/dist" "$KIRO_GSTACK/browse/dist"
_link_or_copy "$SOURCE_GSTACK_DIR/browse/bin" "$KIRO_GSTACK/browse/bin"
# ETHOS.md — referenced by "Search Before Building" in all skill preambles
if [ -f "$SOURCE_GSTACK_DIR/ETHOS.md" ]; then
_link_or_copy "$SOURCE_GSTACK_DIR/ETHOS.md" "$KIRO_GSTACK/ETHOS.md"
fi
# gstack-upgrade skill
if [ -f "$AGENTS_DIR/gstack-upgrade/SKILL.md" ]; then
_link_or_copy "$AGENTS_DIR/gstack-upgrade/SKILL.md" "$KIRO_GSTACK/gstack-upgrade/SKILL.md"
fi
# Review runtime assets (individual files, not whole dir)
for f in checklist.md design-checklist.md greptile-triage.md TODOS-format.md; do
if [ -f "$SOURCE_GSTACK_DIR/review/$f" ]; then
_link_or_copy "$SOURCE_GSTACK_DIR/review/$f" "$KIRO_GSTACK/review/$f"
fi
done
# Rewrite root SKILL.md paths for Kiro
sed -e "s|~/.claude/skills/gstack|~/.kiro/skills/gstack|g" \
-e "s|\.claude/skills/gstack|.kiro/skills/gstack|g" \
-e "s|\.claude/skills|.kiro/skills|g" \
"$SOURCE_GSTACK_DIR/SKILL.md" > "$KIRO_GSTACK/SKILL.md"
if [ ! -d "$AGENTS_DIR" ]; then
echo " warning: no .agents/skills/ directory found — run 'bun run build' first" >&2
else
for skill_dir in "$AGENTS_DIR"/gstack*/; do
[ -f "$skill_dir/SKILL.md" ] || continue
skill_name="$(basename "$skill_dir")"
target_dir="$KIRO_SKILLS/$skill_name"
mkdir -p "$target_dir"
# Generated Codex skills use $HOME/.codex (not ~/), plus $GSTACK_ROOT variables.
# Rewrite the default GSTACK_ROOT value and any remaining literal paths.
sed -e 's|\$HOME/.codex/skills/gstack|$HOME/.kiro/skills/gstack|g' \
-e "s|~/.codex/skills/gstack|~/.kiro/skills/gstack|g" \
-e "s|~/.claude/skills/gstack|~/.kiro/skills/gstack|g" \
"$skill_dir/SKILL.md" > "$target_dir/SKILL.md"
done
echo "gstack ready (kiro)."
echo " browse: $BROWSE_BIN"
echo " kiro skills: $KIRO_SKILLS"
fi
fi
# 6b. Install for Factory Droid
if [ "$INSTALL_FACTORY" -eq 1 ]; then
mkdir -p "$FACTORY_SKILLS"
create_factory_runtime_root "$SOURCE_GSTACK_DIR" "$FACTORY_GSTACK"
link_factory_skill_dirs "$SOURCE_GSTACK_DIR" "$FACTORY_SKILLS"
echo "gstack ready (factory)."
echo " browse: $BROWSE_BIN"
echo " factory skills: $FACTORY_SKILLS"
fi
# 6c. Install for OpenCode
if [ "$INSTALL_OPENCODE" -eq 1 ]; then
mkdir -p "$OPENCODE_SKILLS"
create_opencode_runtime_root "$SOURCE_GSTACK_DIR" "$OPENCODE_GSTACK"
link_opencode_skill_dirs "$SOURCE_GSTACK_DIR" "$OPENCODE_SKILLS"
echo "gstack ready (opencode)."
echo " browse: $BROWSE_BIN"
echo " opencode skills: $OPENCODE_SKILLS"
fi
# 7. Create .agents/ sidecar symlinks for the real Codex skill target.
# The root Codex skill ends up pointing at $SOURCE_GSTACK_DIR/.agents/skills/gstack,
# so the runtime assets must live there for both global and repo-local installs.
if [ "$INSTALL_CODEX" -eq 1 ]; then
create_agents_sidecar "$SOURCE_GSTACK_DIR"
fi
# 8. Run pending version migrations
# Migrations handle state fixes that ./setup alone can't cover (stale config,
# orphaned files, directory structure changes). Each migration is idempotent.
MIGRATIONS_DIR="$SOURCE_GSTACK_DIR/gstack-upgrade/migrations"
CURRENT_VERSION=$(cat "$SOURCE_GSTACK_DIR/VERSION" 2>/dev/null || echo "unknown")
LAST_SETUP_VERSION=$(cat "$HOME/.gstack/.last-setup-version" 2>/dev/null || echo "0.0.0.0")
if [ -d "$MIGRATIONS_DIR" ] && [ "$CURRENT_VERSION" != "unknown" ] && [ "$LAST_SETUP_VERSION" != "$CURRENT_VERSION" ]; then
# Fresh install (no marker file) — skip migrations, just write marker
if [ ! -f "$HOME/.gstack/.last-setup-version" ]; then
: # fall through to marker write below
else
find "$MIGRATIONS_DIR" -maxdepth 1 -name 'v*.sh' -type f 2>/dev/null | sort -V | while IFS= read -r migration; do
m_ver="$(basename "$migration" .sh | sed 's/^v//')"
# Run if migration is newer than last setup version AND not newer than current version
if [ "$(printf '%s\n%s' "$LAST_SETUP_VERSION" "$m_ver" | sort -V | head -1)" = "$LAST_SETUP_VERSION" ] && [ "$LAST_SETUP_VERSION" != "$m_ver" ] \
&& [ "$(printf '%s\n%s' "$m_ver" "$CURRENT_VERSION" | sort -V | tail -1)" = "$CURRENT_VERSION" ]; then
echo " running migration $m_ver..."
bash "$migration" || echo " warning: migration $m_ver had errors (non-fatal)"
fi
done
fi
fi
mkdir -p "$HOME/.gstack"
if [ "$CURRENT_VERSION" != "unknown" ]; then
echo "$CURRENT_VERSION" > "$HOME/.gstack/.last-setup-version"
fi
# 9. First-time welcome + legacy cleanup
if [ ! -f "$HOME/.gstack/.welcome-seen" ]; then
log " Welcome! Run /gstack-upgrade anytime to stay current."
touch "$HOME/.gstack/.welcome-seen"
fi
rm -f /tmp/gstack-latest-version
# 10. Team mode: register/unregister SessionStart hook
SETTINGS_HOOK="$SOURCE_GSTACK_DIR/bin/gstack-settings-hook"
HOOK_CMD="$SOURCE_GSTACK_DIR/bin/gstack-session-update"
if [ "$TEAM_MODE" -eq 1 ]; then
"$GSTACK_CONFIG" set auto_upgrade true 2>/dev/null || true
"$GSTACK_CONFIG" set team_mode true 2>/dev/null || true
# Register SessionStart hook in Claude Code settings
if [ -x "$SETTINGS_HOOK" ]; then
"$SETTINGS_HOOK" add "$HOOK_CMD" 2>/dev/null || true
fi
log ""
log "Team mode enabled: gstack will auto-update at the start of each Claude Code session."
log " Hook: $HOOK_CMD"
log " To disable: ./setup --no-team"
log ""
log "Bootstrap your repo:"
log " cd <your-repo> && $SOURCE_GSTACK_DIR/bin/gstack-team-init required"
fi
if [ "$NO_TEAM_MODE" -eq 1 ]; then
"$GSTACK_CONFIG" set auto_upgrade false 2>/dev/null || true
"$GSTACK_CONFIG" set team_mode false 2>/dev/null || true
# Remove SessionStart hook from Claude Code settings
if [ -x "$SETTINGS_HOOK" ]; then
"$SETTINGS_HOOK" remove "$HOOK_CMD" 2>/dev/null || true
fi
log "Team mode disabled: auto-update hook removed."
fi
# ─── GBrain detection + conditional SKILL.md regen ──────────────────────
#
# Detect whether gbrain is installed and persist the result to
# ~/.gstack/gbrain-detection.json so gen-skill-docs can decide whether to
# render GBRAIN_CONTEXT_LOAD and GBRAIN_SAVE_RESULTS blocks. If detected,
# regenerate the Claude-host SKILL.md files with the un-suppressed
# (compressed) brain-aware blocks via `bun run gen:skill-docs:user`.
#
# If gbrain is not detected, the canonical no-gbrain SKILL.md files
# (which were just generated above by `gen:skill-docs --host claude` if
# applicable, or which are checked in) stay as-is. Zero token overhead
# for non-gbrain users.
#
# Users who install gbrain after running ./setup should re-run setup OR
# call `gstack-config gbrain-refresh` + `bun run gen:skill-docs:user`.
DETECT_BIN="$SOURCE_GSTACK_DIR/bin/gstack-gbrain-detect"
GBRAIN_STATE_DIR="${GSTACK_HOME:-$HOME/.gstack}"
DETECTION_FILE="$GBRAIN_STATE_DIR/gbrain-detection.json"
mkdir -p "$GBRAIN_STATE_DIR"
if [ -x "$DETECT_BIN" ]; then
if "$DETECT_BIN" > "$DETECTION_FILE.tmp" 2>/dev/null; then
mv "$DETECTION_FILE.tmp" "$DETECTION_FILE"
if grep -q '"gbrain_local_status": "ok"' "$DETECTION_FILE" 2>/dev/null; then
log "gbrain detected — regenerating Claude SKILL.md with brain-aware blocks (~250 token overhead per planning skill)..."
(
cd "$SOURCE_GSTACK_DIR"
bun_cmd run gen:skill-docs:user --host claude 2>&1 | tail -3
) || log " warning: gen:skill-docs:user failed — run 'bun run gen:skill-docs:user' manually if you want brain-aware blocks"
else
log "gbrain not detected — brain-aware blocks suppressed in planning-skill SKILL.md files (zero token overhead)."
log " To enable: install gbrain via /setup-gbrain, then re-run ./setup or 'gstack-config gbrain-refresh'."
fi
else
rm -f "$DETECTION_FILE.tmp"
log " warning: gstack-gbrain-detect failed — brain-aware blocks will stay suppressed"
fi
fi
# 11. Plan-tune cathedral hook install (T8).
#
# Registers PostToolUse (deterministic AUQ capture) + PreToolUse (preference
# enforcement) hooks in ~/.claude/settings.json so /plan-tune actually does
# something at runtime instead of being agent-convention. Explicit consent UX
# per D4 + Codex: never mutate settings.json silently.
#
# Idempotent via _gstack_source tag = 'plan-tune-cathedral'. If both hooks
# already registered under that tag, the install is a no-op (no prompt).
PLAN_TUNE_LOG_HOOK="$SOURCE_GSTACK_DIR/hosts/claude/hooks/question-log-hook"
PLAN_TUNE_PREF_HOOK="$SOURCE_GSTACK_DIR/hosts/claude/hooks/question-preference-hook"
PLAN_TUNE_INSTALL_MARKER="$HOME/.gstack/.plan-tune-hooks-prompted"
if [ "$NO_TEAM_MODE" -ne 1 ] \
&& [ -x "$SETTINGS_HOOK" ] \
&& [ -x "$PLAN_TUNE_LOG_HOOK" ] \
&& [ -x "$PLAN_TUNE_PREF_HOOK" ]; then
# Already installed? Check the settings.json for our source tag.
ALREADY_INSTALLED=0
if "$SETTINGS_HOOK" list-sources 2>/dev/null | grep -q "plan-tune-cathedral"; then
ALREADY_INSTALLED=1
fi
if [ "$ALREADY_INSTALLED" -eq 1 ]; then
log ""
log "Plan-tune hooks already installed. Run \`$SETTINGS_HOOK list-sources\` to inspect."
elif [ -f "$PLAN_TUNE_INSTALL_MARKER" ]; then
# Previously declined. Don't re-ask. User can re-enable via /update-config.
:
elif [ -t 0 ] && [ -t 1 ]; then
# Interactive install with explicit consent + diff preview.
log ""
log "──────────────────────────────────────────────────────────"
log "Plan-tune cathedral: install Claude Code hooks?"
log "──────────────────────────────────────────────────────────"
log ""
log "These hooks make /plan-tune settings actually bind at runtime:"
log " • PostToolUse hook captures every AskUserQuestion fire (no agent"
log " compliance required). Today it's agent-convention and the log"
log " is empty in dogfood."
log " • PreToolUse hook enforces 'never-ask' preferences via Claude Code's"
log " permissionDecision protocol. Today preferences are agent-honored"
log " convention; this makes them binding."
log ""
log "Diff preview (PostToolUse capture hook):"
"$SETTINGS_HOOK" diff-event \
--event PostToolUse \
--matcher '(AskUserQuestion|mcp__.*__AskUserQuestion)' \
--command "$PLAN_TUNE_LOG_HOOK" \
--source plan-tune-cathedral \
--timeout 5 2>/dev/null || true
log ""
log "Backup: settings.json.bak.<ts> written before any mutation."
log "Rollback: $SETTINGS_HOOK rollback"
log ""
printf "Install both hooks now? [y/N] "
read -r PLAN_TUNE_INSTALL_REPLY
if [ "$PLAN_TUNE_INSTALL_REPLY" = "y" ] || [ "$PLAN_TUNE_INSTALL_REPLY" = "Y" ]; then
"$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 "$PLAN_TUNE_PREF_HOOK" \
--source plan-tune-cathedral \
--timeout 5
log ""
log "Plan-tune hooks installed. Run /plan-tune anytime to inspect."
else
log ""
log "Skipped. Re-run ./setup or use /update-config to install later."
fi
touch "$PLAN_TUNE_INSTALL_MARKER"
else
# Non-interactive (CI, scripted setup). Don't prompt; print one-liner.
log ""
log "Plan-tune cathedral hooks not installed (non-interactive setup)."
log "Install with:"
log " $SETTINGS_HOOK add-event --event PostToolUse \\"
log " --matcher '(AskUserQuestion|mcp__.*__AskUserQuestion)' \\"
log " --command $PLAN_TUNE_LOG_HOOK --source plan-tune-cathedral --timeout 5"
log " $SETTINGS_HOOK add-event --event PreToolUse \\"
log " --matcher '(AskUserQuestion|mcp__.*__AskUserQuestion)' \\"
log " --command $PLAN_TUNE_PREF_HOOK --source plan-tune-cathedral --timeout 5"
fi
fi
# Also tear down plan-tune hooks on --no-team (matches the existing pattern).
if [ "$NO_TEAM_MODE" -eq 1 ] && [ -x "$SETTINGS_HOOK" ]; then
"$SETTINGS_HOOK" remove-source --source plan-tune-cathedral 2>/dev/null || true
fi