Files
gstack/bin/gstack-skill-start
T
f67c478f05 v1.91.34.0 fix: /autoplan on current Claude Code and long sessions, quieter pre-push and sync guards, gstack-post, gstack-doctor (#3069)
* docs: Oct 7 follow-up wave plan (pre-review)

* docs: Oct 7 follow-up wave plan, reviewed through /autoplan

* docs: Oct 7 wave plan, record final gate decisions (UC1 accepted, UC2 rejected)

* docs: credit #1822 to @Mike-E-Log and #1743 to @habassa5 (v1.64.0.0)

The v1.64.0.0 CHANGELOG entry credited the extension token fix (#1822)
and the polyfill exited promise (#1743) to the wrong handle, and the
extension-sender-auth test header repeated the first slip. Commit history
is not rewritten.

Fixes #3054.

Co-authored-by: Mike Ilog <48659643+Mike-E-Log@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(context-restore): offer newer checkpoints from nested repos and task worktrees

/context-restore could present an older checkpoint as the latest with no
error in two layouts:

1. A session started in a non-git parent saved from a nested repo, so the
   checkpoint went to the nested repo's bucket. Restore in the parent now
   lists checkpoints of other buckets whose project_root lies below the cwd
   (BELOW_CWD; the 200 newest are read, and from $HOME only each project's
   newest). /context-save also leaves a JSON pointer (checkpoint path, bucket,
   project_root) in the starting directory's bucket when $CLAUDE_PROJECT_DIR
   is set and files elsewhere; restore lists those as POINTER, in or out of git.
2. A plan checkpoint on the main tree's branch shadowed a newer checkpoint
   saved in a ticket worktree. When another branch holds a newer checkpoint
   for the same task (a worktree below the main tree, read from the new
   worktree: stamp; equal normalized titles; or a shared #123 / ABC-123
   token in titles or branch names), restore prints NEWER_TASK and the skill
   shows both and proposes the newer one. Generic titles (wip, checkpoint,
   save, notes, todo) never match on title alone, and the worktree rule
   applies only when restoring from the main tree, so sibling worktrees
   still never shadow each other.

The branch-first ordering itself is unchanged.

Refs #3065.

Co-authored-by: Thomas Gernhardt <t.gernhardt@softwareprojekt.net>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(redact-prepush): list each MEDIUM finding with rule, file line and fix

The pre-push hook printed only a MEDIUM count, which nobody could review
without re-running the engine by hand. It now prints one line per finding:
rule id, file and file line, and a fix, never the matched value.

Line numbers come from the hunk headers (combined --cc headers included), so
a finding in a later hunk or past a scan-chunk boundary points at the real
file line. Findings from the per-commit catch-up path name the commit whose
file line it is, so content removed before the pushed tip is still locatable.

Plan items: CEO-7 (summary half), DX-9 (fix lines), ENG-8 (line mapping).

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(redact-prepush): stop flagging your own email and already-public authors (#3060)

The hook never passed the engine's selfEmail / repoPublicEmails, so every
push that added the pusher's address, or a commit author's, raised a MEDIUM
pii.email warning for an address the destination already shows.

The hook now reads `git config user.email` and one bounded `git log` of
author and committer addresses, raw and mailmapped (%ae %aE %ce %cE): the
history of every pushed tip (those commits become public with the push),
each remote tip being replaced, and, for a new branch or an unknown remote
tip pushed to a configured remote, that remote's own tracking refs. A URL or
unknown destination never borrows tracking refs, and another remote's
history never counts.

The read stops at 50,000 commits (the newest authors are used) and 5 seconds.
An error or the timeout passes no history and, when an email finding is
listed, prints one line saying suppression was limited for this push. The two
inputs fail independently. HIGH findings and every other rule are untouched.

Controls: a stranger's address, an address only another remote knows, a URL
push next to a matching remote, and a first push of a repo with no history
all still report.

Plan items: A3, CEO-7, CEO-23 (A3 half), DX-9 (partial history), ENG-8
(history scope, mailmap).

Co-authored-by: akmandhania <143462686+akmandhania@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* feat(redact-prepush): per-address allowlist for pii.email (gstack.redact.allowEmail)

`git config --add gstack.redact.allowEmail <address>` allows that address for
MEDIUM pii.email findings only, so a team alias or support address that has
to be in the repo stops warning without reaching for --no-verify. It never
affects HIGH findings or any other rule, and the pii.email fix line names it.

Controls: a different address still reports, and a HIGH secret next to an
allowed address still blocks.

Plan item: DX-17.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* docs(troubleshooting): pre-push pii.email findings, exemptions and allowlist

Plan item: DX-12 (pre-push touchpoint).

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test(redact-prepush): assemble fixture addresses at runtime

The email fixtures were literals, so this branch's own push listed 47
pii.email findings in its test file. Build them from a helper instead, the
way the neighbouring tests build credential and IP fixtures.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(browse): offer the user's signed-in tab, name silent aside repl failures

Rules (rendered into every browsing skill, kept short):
- Rule 1: before the first openTab, offer the user's tabs on the target
  origin (title and origin only; the rest of listBrowserTabs() stays
  private) and attach only after the user confirms one.
- Rule 4: a second sign-in wall after a confirmed sign-in means the session
  is bound to the tab or URL; offer that tab instead of another sign-in.
- Rule 6 no longer suggests an early return; rule 7 says a fast [ok without
  GSTACK_STEP_OK is an abort.

Cookbook (browse, devex-review): a "Silent failures" list (evaluate returns
only serializable values, no top-level return, locator(sel).press(key), an
empty DOM read is about the selector until the screenshot and the request's
response say otherwise, read toggle state before clicking) and a signed-in
tab recipe that prints only target-origin tabs and never closes the user's tab.

Parity caps for design-consultation, land-and-deploy, qa and the browse
skeleton are raised to the measured sizes, with notes.

Refs #3063, #3064.

Co-authored-by: Thomas Gernhardt <t.gernhardt@softwareprojekt.net>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* feat(codex): run gstack-codex-probe as a command, one subcommand per probe

Generated skills now execute bin/gstack-codex-probe (select-model, check-auth,
show-sandbox, check-sandbox, probe-model, check-version, show-first-use-notice,
run-with-timeout, log-event, log-hang, help) and capture its KEY: value lines,
so no helper state crosses into the calling shell and the preflight works from
bash, zsh or sh. select-model keeps --model > GSTACK_CODEX_MODEL > config.toml
precedence; run-with-timeout supervises with the existing gtimeout/timeout/
watchdog chain and returns 124 on a deadline; an unknown subcommand exits 64.

Sourcing keeps working for skills rendered before the upgrade and prints one
deprecation line naming /gstack-upgrade; it and the zsh self-locate block are
removed in a release on or after 2026-10-21 (DX-18). Parity caps raised with
measured notes for the longer capture lines.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* feat(gstack-post): one argv-only, redaction-scanned write path for PR and issue text

bin/gstack-post posts a PR/MR or issue comment, a review-comment reply, a
PR title or body, a new PR/MR or a new issue from agent-written files. Every
value reaches gh/glab as its own argv element in --flag=<value> form or on
stdin, never through a shell string, and a target is a number or a URL of
this repository on the same host.

The helper owns the redaction scan: it reads each file once, scans those
exact bytes (visibility from config, then gh/glab; the pusher's own email
suppressed) and sends the same bytes. HIGH is refused with exit 1 and no
confirmation can post it. MEDIUM exits 2 with RULE:/LINE:/PART: lines and a
TOKEN: digest of the bytes, destination, operation and findings; only
--confirm <token> for those exact bytes posts, so any edit needs a new
confirmation. gh/glab failures exit 3, usage errors 64. It also carries the
projectCards REST fallback and the title read-back that /ship did by hand.

The logic lives in lib/gstack-post.ts behind an injectable runner, so its
tests run in the Windows free lane; the stub-gh executable test is POSIX.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(autoplan): guard verifies dispatches on Claude Code 2.1.29x (schema strip, unflushed call, named causes)

Cause A: Claude Code journals the model's raw Agent input but hands
PreToolUse the schema-parsed input; with the fork-subagent gate on (the
interactive default in 2.1.292) run_in_background is dropped, so the journal
record never deep-equaled the payload. nativeToolInput now drops only that
documented strip for Agent. Agent input is bound on both paths: keys limited
to prompt, description, subagent_type (general-purpose) and
run_in_background; a model override or any other key is denied.

Cause B: when a ready journal lacks the current call, the guard evaluates
the payload placed after the last journaled record instead of polling for a
record that may arrive only with the tool result. A phase transition counts
a report only when a later journaled record follows it (and, on the journal
path, it is not in the current call's message). One batch rule covers both
paths; a background reviewer keeps the invocation armed until its
completion notice.

Every outcome now has a stable reason code, disposition and anchor
(autoplan/bin/guard-reasons.ts). UC1: Claude-Code-caused states
(unrecognized shape, journal lag, rewritten journal, oversized record,
unchecked-version schema strip) allow with a visible warning; integrity
failures stay denials. No denial advises a bare retry. Every guarded
decision appends one content-free line to analytics/autoplan-guard.jsonl,
trimmed to 1,000 lines past 256 KiB.

Co-authored-by: Jared <182125291+yolo-jared@users.noreply.github.com>
Co-authored-by: crblabs <293123359+crblabs@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(autoplan): publish each phase report with a no-op call; foreground requests are conditional

Phase-close step 6 sends the report in a message whose only tool call is
the Bash no-op ': autoplan-published <phase>', and step 7 makes the next
guarded call in a later message, so the guard sees the report flushed
before the next phase entry regardless of Claude Code's journal timing.

Every site that asked for run_in_background: false now asks for it only
when the Agent schema offers it and says how to recover when a dispatch
runs in the background anyway (wait for its completion notice). Parity
caps rise by the measured bytes.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* feat(ship,spec,review): PR and issue text goes out only through gstack-post

/ship: Step 18 writes the title into an agent-written file. An existing PR's
title is piped from gh/glab through gstack-pr-title-rewrite.sh --stdin (new),
so neither the agent nor a shell string carries it; a new title is written
with the file tool and its version prefix checked in the file. Step 19
composes the body as before and publishes with gstack-post pr-create, or
pr-body then pr-title, which scan the exact bytes they send. The separate
title and body scans, the hand-rolled REST fallback and the title self-check
are gone (the helper does all three). Title preparation moved into the
pr-body section, so the skeleton shrinks.

/spec files its issue with gstack-post issue-create and drops the pre-issue
re-scan; Greptile replies use gstack-post reply and pr-comment.
scripts/resolvers/redact-doc.ts loses its PR and issue sinks, and a test
keeps any template from rendering one again.

Tests that pinned the old scan-then-gh wiring now pin the gstack-post wiring;
the publication tests run the real compose and publish blocks against a stub
gh with the real helper (HIGH in title or body refused, MEDIUM token flow).

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* ci: pin Claude Code 2.1.292 in the CI image

2.1.292 is the npm latest users run. Its interactive default turns on the
fork-subagent gate, which strips run_in_background from the Agent schema
and backgrounds reviewers; CI on 2.1.284 never saw the /autoplan guard
break. The image tag is a content hash, so every eval workflow picks up
the new image without a workflow edit.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(brain-sync): one drain lock for every writer to the artifacts repo

gstack-artifacts-init, gstack-brain-restore, gstack-gbrain-source-wireup
and the skill-start merge ran git in $GSTACK_HOME without the drain's lock,
so the drain could never tell an abandoned .git/index.lock from a live one.
They now take the same mkdir lock (bin/gstack-brain-lock.sh): the drain and
the skill-start merge skip when it is held, user-run writers wait for it
(GSTACK_BRAIN_LOCK_WAIT, default 120 s), and a child of the holder (the
drain's daily worktree advance, restore's wireup) inherits it by token.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(brain-sync): hold back only the flagged file, keep coupled artifacts whole

One file with secret-shaped text used to block every push, silently. The
drain now attributes scanner hits to files in one pass over the staged diff
(split on its diff --git headers), holds back each flagged file with the
rest of its coupled group, unstages it, and requires the remaining staged
diff to re-scan clean; anything short of that falls back to a full unstage
and status blocked. Held files stay queued and are re-scanned every drain.

- Status file gains held_count, drainable, last_drain_at, last_push_at and
  held[] (path, scanner rule, dependents, both fixes); new status held.
- Coupled groups come from an explicit map (decisions.jsonl and
  decisions.active.json): a queued member stages the whole group, a group
  stages only when its snapshot matches its log in the index, a skipped
  member stops the whole group.
- --unskip-file undoes --skip-file and queues the path again.
- An index lock older than 10 minutes is removed under the drain lock; a
  younger one, a failed git add, a failed commit (hooks included) keep the
  queue and report status error. A verified empty staged diff is the only
  "nothing to commit". git add runs once, batched.
- The scanner reads bytes, so undecodable content no longer crashes it into
  a false clean; matched text never reaches the status file.
- An empty-queue run with unpushed sync commits stays push_failed.
- Privacy-held duplicate records collapse to one per path; --status counts
  a spool too deep for a shell glob.
- --attention prints skill start's fixed attention lines from the sync
  status table in the usage header.

Co-authored-by: v639dragoon <matthewsbrickley@gmail.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* feat(skill-start): ARTIFACTS_SYNC attention lines for a stuck sync

Skill start now prints one fixed attention line per sync-status-table row
that applies (held, blocked, push_failed, error, unknown, stale-push,
stale-drain), each naming gstack-brain-sync by absolute path. Values from
the status file are clamped (status code to the table, counts to digits,
timestamps to their shape), so the status message, file paths and scanner
output never reach the line. The preamble tells the model to surface the
line in one sentence and continue. Skill-start tests are generated from the
table in bin/gstack-brain-sync, and docs/gbrain-sync-errors.md carries the
same table.

Co-authored-by: v639dragoon <matthewsbrickley@gmail.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(outside-review): severity words in label position count as findings

The Oct 7 /autoplan run's Codex CEO and DX reviews labeled seven and eight
findings High/Medium without [Pn] tags, and the classifier printed
VERDICT: clean / FINDINGS: none for both. lib/outside-review-result.ts now
reads severity words in label position (Severity: High, a leading High: /
High — / [High], **High**, a table cell): critical/high block like P0/P1,
medium/low are advisory. Words in prose (high-level, low-risk, no critical
findings) never count. A review or structured response with neither tags,
labels nor an explicit no-findings statement is unverified, never clean
(DX-11, ENG-10). Design-direction proposals move to a new proposal gate so
they keep needing only their Recommendation line, and review prompts ask
for a severity per finding. Fixtures reproduce the CEO/DX label shapes, the
eng [P1] output, a table and prose negative controls; the stored Codex panel
keeps its verdicts. docs/troubleshooting.md explains how the verdict is read.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* feat: gstack-doctor readiness report and setup --status Codex row (B5)

bin/gstack-doctor prints one row per check without starting a skill:
install root (the registry rows behind ./setup --status), state root, Bun
against the floor, hook parse check, Codex mode and self-locate via
gstack-codex-probe subcommands, the cached model probe with its age
(--live runs the paid probe-model), artifacts-sync health from the status
file with the status code clamped, the browse bundle, Claude Code version,
the largest session journal and the last five schema-1 guard reason codes.
Rows are ok, warn, not configured or fail; only fail exits non-zero; fix
lines name helpers by absolute install-root path.

./setup --status gains a read-only Codex row (bin/gstack-codex-status.sh,
shared with the doctor) and ends with the doctor's absolute path.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* docs: bug-report template asks for doctor output; README troubleshooting entry; doctor test in the Windows lane

The template gives the Claude Code doctor path and a lookup for other
hosts and names no bare gstack- command (asserted in
test/gstack-doctor.test.ts). The doctor test runs every script through
explicit bash argv, so it joins the curated Windows free subset.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* docs(troubleshooting): readiness check section points at gstack-doctor

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(question-tuning,plan-tune,gbrain): free text reaches helpers only through agent-written files

Question tuning no longer pipes the question summary through printf: a
registered id needs no summary, and for an unregistered id the agent writes
the summary to .gstack/tmp/qt.txt and passes --summary-file (new). The
helper resolves a relative path against the git top level, removes scratch
files under .gstack/tmp, and asks normally when the file is missing.

/plan-tune tune events carry the user's own words again: they go into a
file the agent writes and reach gstack-question-preference --write through
--free-text-file (new), still behind the injection filter and the
user-origin gate.

docs/gbrain-write-surfaces.md drops its heredoc templates for the
agent-written page file on stdin, matching the per-skill save block, and the
generic save block stops showing a quoted --content argument.

The tuning prose was tightened so every preamble stays within its size cap.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test(evals): daily autoplan-schema-canary on the latest Claude Code

A periodic rule case installs the latest published Claude Code with
install scripts off, verifies registry signatures, and runs one headless
session with the fork-subagent gate on whose PreToolUse hook records an
Agent and a Read payload. Each payload must match its journal record under
the guard's own comparison, keep the journal's key set apart from the
documented run_in_background strip, and stay inside the Agent allowlist;
a background Agent's completion notice must keep the shape the guard reads.
evals-periodic.yml runs it daily on its own schedule and concurrency group
(read-only token); the weekly census also includes it. A free test proves
the comparison fails on an injected strip.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(doctor): read the artifacts sync held count from held_count, the field the drain writes

* fix(artifacts sync): the init and restore pre-commit hooks catch Bearer/Basic/Token-prefixed JSON auth headers like the drain does

* feat(greptile-early): detect Greptile, ask once on public repos, open the early draft, wait for the review

bin/gstack-greptile-early backs /ship's early Greptile PR:
- detect: a root .greptile/ folder (which takes precedence), greptile.json,
  or a Greptile comment on the repo in the last 90 days; triggerOnDrafts from
  the effective root config; repo visibility; public-repo consent. It prints
  the signal, that /ship will push and open a draft now, the 10-minute wait
  cap and the absolute gstack-config command that turns it off.
- consent yes|no: the public-repo answer, remembered per repo in the
  project's state.
- open: opens the draft through gstack-post with a body saying /ship opened
  it early, and posts one @greptileai comment through gstack-post when the
  config does not set triggerOnDrafts: true. An open PR is left alone.
- wait: polls every 30 s for a completed Greptile check run, a Greptile
  review of the head commit or a summary naming it; each call returns within
  about 90 s and reports timeout 10 minutes after the PR opened.

gstack-config gains ship_greptile_early (default true, invalid values
rejected): on automatically whenever the repo uses Greptile, off per user.
The logic is in lib/greptile-early.ts behind an injectable runner, so its
fixture-repo tests run in the Windows lane; an end-to-end test drives the
real helper and gstack-post against a stub gh.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* feat(ship): early Greptile PR at Step 6.5, bounded wait at Step 10 (#3020)

When the repo uses Greptile, /ship pushes and opens a draft PR right after
its free tests pass (new lazy section greptile-early, Step 6.5), so Greptile
reviews while Steps 7-9 run. A public repo asks once, remembered per repo;
declining keeps today's order. Step 10 waits for that review with
gstack-greptile-early wait and takes the existing unavailable route on a
timeout, never a claim of zero comments. Step 18 replaces the provisional
title, Step 19 marks the draft ready unless a draft was requested, and a
/ship that stops after Step 6.5 leaves the draft open with one comment
saying why.

ship's union cap rises to 1.5275 with the measured note (B4 +836 bytes,
B2 +4,732 bytes); the step-numbering guard allows 6.5; ship goldens are
refreshed for B4 and B2.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(autoplan): the publication no-op is 'true autoplan-published <phase>'

Measured on Claude Code 2.1.292 in a default-settings interactive session:
a bare ':' Bash command asks for approval ('This command requires
approval'), and after a background reviewer's completion notice starts a
new turn the skill's allowed tools no longer cover it, so the phase-close
no-op prompted the user. 'true' with arguments runs without approval and
prints nothing. The guard only needs a later journaled record, so the
command changes everywhere it is named.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test(evals): live autoplan-guard-pty case on the pinned Claude Code

A gate-tier rule case (one trial, haiku) drives an interactive PTY
session with default settings through a project skill that carries
/autoplan's own hook block: init, Phase 1 entry, a CEO reviewer dispatch
that sends run_in_background, a prepared close packet, the report
published with the no-op, and the Phase 2 entry in a later message. It
reads outcomes from the guard decision log (three verified allows) and
fails if the no-op raises a permission card; other cards are approved and
printed.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(autoplan): bounded, append-tolerant owned-journal read (A2)

The publication guard no longer reads the whole parent journal or refuses
it at 32 MiB. lib/claude-owned-journal.ts streams the bytes present at open
to the last complete line (pass one), keeps a content-free index per record
and decides ownership, ancestry and causal order on it with the same checks
and reason codes as before. Pass two reloads in full only what the
evaluation reads (autoplan/bin/guard-journal.ts): every literal init and its
result, the current call, and inside the invocation window (from the latest
human turn at or before the bound chain's first init) guarded and
close-packet Read results, structured Bash results, error results, assistant
text after the first close Read and active-plan mutations, plus the earlier
Read a dedup reply cites even before the window (ENG-4).

- lib/claude-journal-records.ts: per-record event extraction, record
  metadata and the causal-order checks, shared by readPlanCountTranscript
  and the bounded reader. The batch reader keeps its whole-file read and cap.
- Appends after open never fail a read; same device and inode and no
  shrink are required (identity). A second read in one hook invocation must
  hash bytes [0, first size) the same, or it is `rewritten` (UC1 unverified);
  the unrecognized-shape double read uses that prefix hash. `changing` is
  removed (REMOVED_CODES; its anchor stays).
- OWNED_RECORD_MAX_BYTES (32 MiB): only one record over it is too_large.
  OWNED_RETAINED_MAX_BYTES (32 MiB): over it is the new oversized_invocation
  fallback denial. GSTACK_TRANSCRIPT_TEST_MAX_BYTES and
  GSTACK_TRANSCRIPT_TEST_RETAINED_BYTES can only lower them.
- ENG-5: evaluation groups uses and results by tool id once (no per-tool
  rescans).

CEO-25 / ENG-5 spike (120 MiB synthetic, 31,242 records, 4 vCPU Linux,
Bun 1.4.2): a full streaming rescan (parse every line, small index, sha256)
took 254-326 ms at 147-161 MiB peak RSS; a pass-one index cache under the
state root (load cached index, verify a 64 KiB tail hash, parse the tail)
took 26-29 ms at 47 MiB. The rescan meets the 1 s budget, so the cache is
not adopted: it would add trusted persistent state and invalidation for no
budget need. A backward tail read cannot prove competing_root or cycle, so
it was not a candidate.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test(autoplan): journal-read benchmark and its dispatch-only workflow (CEO-2, CEO-6)

scripts/measure-journal-read.ts builds two synthetic 120 MiB parent journals
around a real /autoplan invocation (mixed: ~28k records, most bytes inside
the invocation; large-invocation: ~89k records with a current invocation of
many small records), keeps appending while the guard reads, and measures one
hook call in a fresh process (wall ms, peak RSS). The workflow runs it on
ubuntu-latest and macos-latest on workflow_dispatch only.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* test(evals): autoplan-long-session, a resumed >100 MiB session enters Phase 1

CEO-15 with ENG-6's observer: a real session is compacted, its journal
padded past 100 MiB with owned records before the compact boundary, and
the resumed interactive session runs the scripted phase boundary; the
guard decision log must show a verified Phase 1 allow. A free test proves
that observer on a padded journal through the lower-only bound seams
(the PTY counting reader refuses the same journal), with a sidechain
control that must deny.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* v1.91.34.0: CHANGELOG, TODOS, version; harness decision for test-pr-profile; ship title-step test reads its new section

* docs(changelog): use an example.com address in the allowEmail example

* test: assemble GitHub-token fixtures at runtime in the new brain-sync and skill-start tests (CI credential scan)

* fix: integration repairs across the wave (Step 6.5 fence, printed helper paths on Windows, probe usage without a heredoc) and tests pinned to the moved title and gstack-post contracts

* test(doctor): the healthy fixture builds browse.exe on Windows, the name setup uses there

* test(shared-libs): recognize Claude Code 2.1.292's internal git probe prefix (format.pretty and per-hook disables), with its CI receipt

* fix(ship-measure): report lists v1 measurements as an older format instead of crashing

---------

Co-authored-by: Mike Ilog <48659643+Mike-E-Log@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Co-authored-by: Thomas Gernhardt <t.gernhardt@softwareprojekt.net>
Co-authored-by: akmandhania <143462686+akmandhania@users.noreply.github.com>
Co-authored-by: Jared <182125291+yolo-jared@users.noreply.github.com>
Co-authored-by: crblabs <293123359+crblabs@users.noreply.github.com>
Co-authored-by: v639dragoon <matthewsbrickley@gmail.com>
2026-10-07 23:29:05 +00:00

586 lines
33 KiB
Bash
Executable File

#!/usr/bin/env bash
# gstack-skill-start — the skill preamble's runtime, consolidated (token-reduction Phase 1).
#
# Absorbs the bash that every generated SKILL.md used to inline twice over
# (the "Preamble (run first)" bootstrap fence and the "Artifacts Sync" fence,
# ~13KB per skill x 50 skills). The generated skill now carries a one-line
# invocation; this script emits the SAME `KEY: value` STATUS lines the prose
# rules interpret. The contract is pinned by test/gstack-skill-start.test.ts
# (every KEY the rendered prose references must be emitted here).
#
# Enumerated divergences from the inline original (plan EOV5):
# - Paths resolve $0-relative (works for every host + install layout) instead
# of gen-time interpolation.
# - Session identity is the HARNESS pid, derived here: the nearest non-shell
# ancestor ($PPID inside this script is the ephemeral tool-call shell —
# wrong identity). --parent-pid still overrides it. The rendered command
# passes no "$PPID" (#2763: worktree-isolated Claude Code sessions refuse
# variables and fallbacks in the start command).
# - State paths honor ${GSTACK_HOME} (EOV7); the inline original hardcoded
# ~/.gstack in the bootstrap half.
# - SESSION_ID / TEL_START are echoed (the inline shell vars never survived
# across Bash tool calls, so skill-end durations were already broken; the
# echo makes them real).
# - SKILL_START_PROTO handshake (OV5): prose treats a missing/unexpected
# proto as a degraded install and applies safe defaults.
# - Passthrough sub-command output is sanitized (OV4): GSTACK_INSTRUCTION
# markers cannot be injected into the blessed tool result by learnings,
# update-check, or first-task text.
#
# Error style (F3): per-line `|| true`, never `set -e` — a mid-script failure
# must not drop later STATUS lines.
# Heredoc bodies in the 512B-64KiB window can deadlock bash 5.1+'s pipe-backed
# heredoc path when the reader stalls; compat level 50 restores the tempfile
# path. This script is bash-3.2-clean, so the compat level costs nothing
# (same guard as bin/gstack-brain-sync; pinned by
# test/heredoc-pipe-deadlock.test.ts).
BASH_COMPAT=50
SKILL_NAME=""
MODEL_OVERLAY="none"
PARENT_PID=""
BRAIN_HEALTH="no"
while [ $# -gt 0 ]; do
case "$1" in
--skill) SKILL_NAME="$2"; shift 2 ;;
--model) MODEL_OVERLAY="$2"; shift 2 ;;
--parent-pid) PARENT_PID="$2"; shift 2 ;;
--brain-health) BRAIN_HEALTH="yes"; shift ;;
*) shift ;;
esac
done
[ -n "$SKILL_NAME" ] || SKILL_NAME="unknown"
# Harness pid: walk up from the calling shell past shell wrappers. Claude
# Code runs this under a per-call `bash -c`, whose parent is the harness; a
# host that execs the command directly is already the parent. Without a
# usable ps (some Windows shells) the immediate parent stands.
if [ -z "$PARENT_PID" ]; then
PARENT_PID="$PPID"
_hops=0
while [ "$_hops" -lt 8 ]; do
_comm=$(ps -o comm= -p "$PARENT_PID" 2>/dev/null | head -1) || break
_comm=${_comm##*/}; _comm=${_comm#-}
case "$_comm" in bash|sh|zsh|dash|ksh|mksh|ash|fish|busybox) ;; *) break ;; esac
_up=$(ps -o ppid= -p "$PARENT_PID" 2>/dev/null | tr -d ' ')
case "$_up" in ''|*[!0-9]*|0|1) break ;; esac
PARENT_PID="$_up"
_hops=$((_hops + 1))
done
fi
_SCRIPT_DIR=$(cd "$(dirname "$0")" 2>/dev/null && pwd)
_BIN="$_SCRIPT_DIR"
. "$(dirname "$0")/gstack-state-root.sh" 2>/dev/null || { echo "$0: cannot resolve the gstack state root: $(dirname "$0")/gstack-state-root.sh is missing. fix: reinstall with ./setup or /gstack-upgrade (docs/state-root.md)" >&2; exit 1; }
gstack_state_root_select
_GH="$_gstack_sr_root"
# OV4: strip instruction markers from any passthrough text before echoing it
# into the blessed tool result. Prior-session/repo content must not be able to
# mint directive blocks — nor forge a SESSION_ID: status line (the token that
# authenticates instruction blocks), so line-leading spoofs are neutralized too.
_sanitize() { sed -e 's/GSTACK_INSTRUCTION/GSTACK-INSTRUCTION-(stripped)/g' -e 's/^SESSION_ID:/SESSION-ID-(stripped):/'; }
echo "SKILL_START_PROTO: 1"
# Session kind resolves FIRST (env-only checks, cheap). Spawned sessions skip
# the network-bound update-check: its only consumer (the upgrade-flow block)
# is emission-gated on kind != spawned below, so the work would be discarded —
# and running it would consume the one-shot just-upgraded marker meant for the
# next human session (#2733 review).
_SESSION_KIND=$("$_BIN/gstack-session-kind" 2>/dev/null || echo "interactive")
case "$_SESSION_KIND" in spawned|headless|interactive) ;; *) _SESSION_KIND="interactive" ;; esac
_UPD=""
if [ "$_SESSION_KIND" != "spawned" ]; then
_UPD=$("$_BIN/gstack-update-check" 2>/dev/null || true)
[ -n "$_UPD" ] && printf '%s\n' "$_UPD" | _sanitize || true
fi
mkdir -p "$_GH/sessions" 2>/dev/null || true
touch "$_GH/sessions/$PARENT_PID" 2>/dev/null || true
find "$_GH/sessions" -mmin +120 -type f -exec rm {} + 2>/dev/null || true
_PROACTIVE=$("$_BIN/gstack-config" get proactive 2>/dev/null || echo "true")
_PROACTIVE_PROMPTED=$([ -f "$_GH/.proactive-prompted" ] && echo "yes" || echo "no")
# Branch name is embedded in concatenated JSON below; strip anything outside
# the gstack-slug BRANCH alphabet so a hostile ref name can't forge fields.
_BRANCH=$(git branch --show-current 2>/dev/null | tr -cd 'a-zA-Z0-9._/-')
_BRANCH=${_BRANCH:-unknown}
echo "BRANCH: $_BRANCH"
_SKILL_PREFIX=$("$_BIN/gstack-config" get skill_prefix 2>/dev/null || echo "false")
echo "PROACTIVE: $_PROACTIVE"
echo "PROACTIVE_PROMPTED: $_PROACTIVE_PROMPTED"
echo "SKILL_PREFIX: $_SKILL_PREFIX"
REPO_MODE=""
eval "$("$_BIN/gstack-repo-mode" 2>/dev/null)" 2>/dev/null || true
REPO_MODE=${REPO_MODE:-unknown}
echo "REPO_MODE: $REPO_MODE"
echo "SESSION_KIND: $_SESSION_KIND"
# Tamper visibility (#2733 review): a repo-provided settings env block or a CI
# wrapper could set GSTACK_SESSION_KIND or OPENCLAW_SESSION for a real human's
# session, silently flipping every gate to auto-choose. Surface the env-driven
# override loudly, naming the driver, so the transcript shows WHY this session
# is spawned. Gated on the RESOLVED kind so a broken session-kind fallback
# never prints a contradictory override line next to SESSION_KIND: interactive.
if [ "$_SESSION_KIND" = "spawned" ]; then
if [ "${GSTACK_SESSION_KIND:-}" = "spawned" ]; then
echo "SPAWNED_OVERRIDE: env (GSTACK_SESSION_KIND)"
elif [ -n "${OPENCLAW_SESSION:-}" ]; then
echo "SPAWNED_OVERRIDE: env (OPENCLAW_SESSION)"
fi
fi
# Conductor host: AskUserQuestion is unreliable there (native disabled, MCP
# variant flaky); skills render decisions as prose. Gated on !headless so an
# eval/CI run INSIDE Conductor still BLOCKs rather than rendering prose to
# nobody, and on !spawned so an orchestrator- or parent-skill-spawned session
# inside a Conductor workspace auto-chooses per its spawned-session block
# instead of rendering prose to nobody (#2733).
if [ "$_SESSION_KIND" != "headless" ] && [ "$_SESSION_KIND" != "spawned" ] && { [ -n "${CONDUCTOR_WORKSPACE_PATH:-}" ] || [ -n "${CONDUCTOR_PORT:-}" ]; }; then
echo "CONDUCTOR_SESSION: true"
fi
_ACTIVATED=$([ -f "$_GH/.activated" ] && echo "yes" || echo "no")
_FIRST_LOOP_SHOWN=$([ -f "$_GH/.first-loop-tip-shown" ] && echo "yes" || echo "no")
echo "ACTIVATED: $_ACTIVATED"
echo "FIRST_LOOP_SHOWN: $_FIRST_LOOP_SHOWN"
# First-run project detection: only on the first-ever skill run (off the hot
# path after). Spawned excluded like headless (#2733 review): spawned sessions
# never write .activated, so without the exclusion the ~17-subprocess probe
# would re-run on EVERY spawned start while its only consumers stay suppressed.
_FIRST_TASK=""
if [ "$_ACTIVATED" = "no" ] && [ "$_SESSION_KIND" != "headless" ] && [ "$_SESSION_KIND" != "spawned" ]; then
_FIRST_TASK=$("$_BIN/gstack-first-task-detect" 2>/dev/null || true)
fi
printf 'FIRST_TASK: %s\n' "$_FIRST_TASK" | _sanitize
_LAKE_SEEN=$([ -f "$_GH/.completeness-intro-seen" ] && echo "yes" || echo "no")
echo "LAKE_INTRO: $_LAKE_SEEN"
_TEL=$("$_BIN/gstack-config" get telemetry 2>/dev/null || true)
_TEL_PROMPTED=$([ -f "$_GH/.telemetry-prompted" ] && echo "yes" || echo "no")
_TEL_START=$(date +%s)
# PID+epoch alone is guessable; a random suffix makes the block-binding token
# unforgeable by content reflected into the same tool result. Falls back to
# the plain form when urandom is unavailable.
_SID_RAND=$(od -An -N4 -tx4 /dev/urandom 2>/dev/null | tr -d ' \n' || true)
_SESSION_ID="$PARENT_PID-$_TEL_START${_SID_RAND:+-$_SID_RAND}"
echo "TELEMETRY: ${_TEL:-off}"
echo "TEL_PROMPTED: $_TEL_PROMPTED"
echo "SESSION_ID: $_SESSION_ID"
echo "TEL_START: $_TEL_START"
_EXPLAIN_LEVEL=$("$_BIN/gstack-config" get explain_level 2>/dev/null || echo "default")
if [ "$_EXPLAIN_LEVEL" != "default" ] && [ "$_EXPLAIN_LEVEL" != "terse" ]; then _EXPLAIN_LEVEL="default"; fi
echo "EXPLAIN_LEVEL: $_EXPLAIN_LEVEL"
_QUESTION_TUNING=$("$_BIN/gstack-config" get question_tuning 2>/dev/null || echo "false")
echo "QUESTION_TUNING: $_QUESTION_TUNING"
_UPDATE_CHECK=$("$_BIN/gstack-config" get update_check 2>/dev/null || echo "true")
echo "UPDATE_CHECK: $_UPDATE_CHECK"
mkdir -p "$_GH/analytics" 2>/dev/null || true
if [ "$_TEL" != "off" ]; then
echo '{"skill":"'"$SKILL_NAME"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(_repo=$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null | tr -cd 'a-zA-Z0-9._-'); echo "${_repo:-unknown}")'"}' >> "$_GH/analytics/skill-usage.jsonl" 2>/dev/null || true
fi
for _PF in $(find "$_GH/analytics" -maxdepth 1 -name '.pending-*' 2>/dev/null); do
if [ -f "$_PF" ]; then
if [ "$_TEL" != "off" ] && [ -x "$_BIN/gstack-telemetry-log" ]; then
"$_BIN/gstack-telemetry-log" --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true
fi
rm -f "$_PF" 2>/dev/null || true
fi
# Deliberate throttle: drain at most ONE orphaned pending file per skill
# start so a backlog can't stall the preamble.
break
done
eval "$("$_BIN/gstack-slug" 2>/dev/null)" 2>/dev/null || true
for _former in $("$_BIN/gstack-slug" --get FORMER_SLUGS 2>/dev/null || true); do
echo "gstack: earlier data for this project is in projects/$_former (a worktree's old bucket). Merge it: gstack-slug --adopt-legacy --from $_former (or stop this reminder: gstack-slug --adopt-legacy --dismiss $_former)"
done
_LEARN_FILE="$_GH/projects/${SLUG:-unknown}/learnings.jsonl"
if [ -f "$_LEARN_FILE" ]; then
_LEARN_COUNT=$(wc -l < "$_LEARN_FILE" 2>/dev/null | tr -d ' ')
echo "LEARNINGS: $_LEARN_COUNT entries loaded"
if [ "$_LEARN_COUNT" -gt 5 ] 2>/dev/null; then
_LEARN_ERR=$(mktemp "${TMPDIR:-/tmp}/gstack-learn-err.XXXXXX" 2>/dev/null) || _LEARN_ERR=/dev/null
if ! "$_BIN/gstack-learnings-search" --limit 3 2>"$_LEARN_ERR" | _sanitize; then
echo "LEARNINGS: unavailable ($(head -n 1 "$_LEARN_ERR" 2>/dev/null))"
fi
[ "$_LEARN_ERR" = /dev/null ] || rm -f "$_LEARN_ERR"
fi
else
echo "LEARNINGS: 0"
fi
"$_BIN/gstack-timeline-log" '{"skill":"'"$SKILL_NAME"'","event":"started","branch":"'"$_BRANCH"'","session":"'"$_SESSION_ID"'"}' 2>/dev/null &
_HAS_ROUTING="no"
for _RF in CLAUDE.md AGENTS.md; do
if [ -f "$_RF" ] && grep -q "## Skill routing" "$_RF" 2>/dev/null; then
_HAS_ROUTING="yes"
fi
done
_ROUTING_DECLINED=$("$_BIN/gstack-config" get routing_declined 2>/dev/null || echo "false")
echo "HAS_ROUTING: $_HAS_ROUTING"
echo "ROUTING_DECLINED: $_ROUTING_DECLINED"
_VENDORED="no"
if [ -d ".claude/skills/gstack" ] && [ ! -L ".claude/skills/gstack" ]; then
if [ -f ".claude/skills/gstack/VERSION" ] || [ -d ".claude/skills/gstack/.git" ]; then
_VENDORED="yes"
fi
fi
echo "VENDORED_GSTACK: $_VENDORED"
echo "MODEL_OVERLAY: $MODEL_OVERLAY"
# Plan-mode hint for skills that branch on plan-mode state. Detected best-effort
# from CLAUDE_PLAN_FILE (set by the harness when plan mode is active); "inactive"
# is the safe default (file+execute pipeline).
if [ -n "${CLAUDE_PLAN_FILE:-}${GSTACK_PLAN_MODE_FORCE:-}" ]; then
GSTACK_PLAN_MODE="active"
elif [ "${GSTACK_PLAN_MODE:-}" = "active" ]; then
GSTACK_PLAN_MODE="active"
else
GSTACK_PLAN_MODE="inactive"
fi
echo "GSTACK_PLAN_MODE: $GSTACK_PLAN_MODE"
# Keyed on the resolved kind, not raw OPENCLAW_SESSION (#2733): the explicit
# GSTACK_SESSION_KIND=spawned override must light this up too.
[ "$_SESSION_KIND" = "spawned" ] && echo "SPAWNED_SESSION: true" || true
# ---------------------------------------------------------------------------
# Artifacts sync (the former "Artifacts Sync (skill start)" fence, verbatim
# modulo GSTACK_HOME + $0-relative bins).
# ---------------------------------------------------------------------------
if [ -f "$HOME/.gstack-artifacts-remote.txt" ]; then
_BRAIN_REMOTE_FILE="$HOME/.gstack-artifacts-remote.txt"
else
_BRAIN_REMOTE_FILE="$HOME/.gstack-brain-remote.txt"
fi
_BRAIN_SYNC_BIN="$_BIN/gstack-brain-sync"
_BRAIN_CONFIG_BIN="$_BIN/gstack-config"
# /sync-gbrain context-load hint. Per-worktree pin via kubectl-style
# .gbrain-source at the git toplevel; empty output when gbrain is not
# configured (zero context cost for non-gbrain users).
_GBRAIN_CONFIG="$HOME/.gbrain/config.json"
if [ -f "$_GBRAIN_CONFIG" ] && command -v gbrain >/dev/null 2>&1; then
_GBRAIN_VERSION_OK=$(gbrain --version 2>/dev/null | grep -c '^gbrain ' || true)
if [ "$_GBRAIN_VERSION_OK" -gt 0 ] 2>/dev/null; then
_GBRAIN_PIN_PATH=""
_REPO_TOP=$(git rev-parse --show-toplevel 2>/dev/null || echo "")
if [ -n "$_REPO_TOP" ] && [ -f "$_REPO_TOP/.gbrain-source" ]; then
_GBRAIN_PIN_PATH="$_REPO_TOP/.gbrain-source"
fi
if [ -n "$_GBRAIN_PIN_PATH" ]; then
echo "GBrain configured. Prefer \`gbrain search\`/\`gbrain query\` over Grep for"
echo "semantic questions; use \`gbrain code-def\`/\`code-refs\`/\`code-callers\` for"
echo "symbol-aware code lookup. See \"## GBrain Search Guidance\" in CLAUDE.md."
echo "Run /sync-gbrain to refresh."
else
echo "GBrain configured but this worktree isn't pinned yet. Run \`/sync-gbrain --full\`"
echo "before relying on \`gbrain search\` for code questions in this worktree."
echo "Falls back to Grep until pinned."
fi
fi
fi
_BRAIN_SYNC_MODE=$("$_BRAIN_CONFIG_BIN" get artifacts_sync_mode 2>/dev/null || echo off)
# Remote-MCP mode detection (Path 4 of /setup-gbrain): read claude.json
# directly (no subprocess to claude CLI on the hot path). Both registration
# scopes are read (#2499): nearest-ancestor project scope first, then user
# scope; project-local BEATS user scope; the ancestor match accepts both path
# separators (Windows project keys are backslash-formed).
_GBRAIN_MCP_MODE="none"
_GBRAIN_MCP_ENTRY=""
# Cheap substring pre-filter: ~/.claude.json can be megabytes on real installs;
# skip the full jq parse when no gbrain server is registered at all.
if command -v jq >/dev/null 2>&1 && [ -f "$HOME/.claude.json" ] && grep -q '"gbrain"' "$HOME/.claude.json" 2>/dev/null; then
_GBRAIN_MCP_ENTRY=$(jq -c --arg cwd "$PWD" '((.projects // {}) | to_entries | map(select((.key as $k | $cwd == $k or ($cwd | startswith($k + "/")) or ($cwd | startswith($k + "\\"))) and ((try .value.mcpServers.gbrain catch null) != null))) | sort_by(.key | length) | last | .value.mcpServers.gbrain) // .mcpServers.gbrain // empty' "$HOME/.claude.json" 2>/dev/null)
_GBRAIN_MCP_TYPE=$(printf '%s' "$_GBRAIN_MCP_ENTRY" | jq -r '.type // .transport // empty' 2>/dev/null)
case "$_GBRAIN_MCP_TYPE" in
url|http|sse) _GBRAIN_MCP_MODE="remote-http" ;;
stdio) _GBRAIN_MCP_MODE="local-stdio" ;;
esac
fi
if [ -f "$_BRAIN_REMOTE_FILE" ] && [ ! -d "$_GH/.git" ] && [ "$_BRAIN_SYNC_MODE" = "off" ]; then
_BRAIN_NEW_URL=$(head -1 "$_BRAIN_REMOTE_FILE" 2>/dev/null | tr -d '[:space:]')
if [ -n "$_BRAIN_NEW_URL" ]; then
printf 'ARTIFACTS_SYNC: artifacts repo detected: %s\n' "$_BRAIN_NEW_URL" | _sanitize
echo "ARTIFACTS_SYNC: run 'gstack-brain-restore' to pull your cross-machine artifacts (or 'gstack-config set artifacts_sync_mode off' to dismiss forever)"
fi
fi
if [ -d "$_GH/.git" ] && [ "$_BRAIN_SYNC_MODE" != "off" ]; then
_BRAIN_LAST_PULL_FILE="$_GH/.brain-last-pull"
_BRAIN_NOW=$(date +%s)
_BRAIN_DO_PULL=1
if [ -f "$_BRAIN_LAST_PULL_FILE" ]; then
_BRAIN_LAST=$(cat "$_BRAIN_LAST_PULL_FILE" 2>/dev/null || echo 0)
case "$_BRAIN_LAST" in ''|*[!0-9]*) _BRAIN_LAST=0 ;; esac
_BRAIN_AGE=$(( _BRAIN_NOW - _BRAIN_LAST ))
[ "$_BRAIN_AGE" -lt 86400 ] && _BRAIN_DO_PULL=0
fi
if [ "$_BRAIN_DO_PULL" = "1" ]; then
# Daily artifacts pull is a brain-sync-class sink: receipt-before-send,
# fail-closed (same wiring as bin/gstack-brain-sync's fetch/push).
. "$_BIN/gstack-egress-lib.sh" 2>/dev/null || true
_PULL_HOST=$(cd "$_GH" 2>/dev/null && git remote get-url origin 2>/dev/null | sed -E 's|^[a-z+]+://([^/@]*@)?([^/:]+).*|\2|; s|^([^@]+@)?([^:]+):.*|\2|' | head -1)
# The merge writes the artifacts repo's git state, so it takes the drain
# lock every gstack writer shares; when a drain holds it, the pull waits
# for the next start (no stamp).
. "$_BIN/gstack-brain-lock.sh" 2>/dev/null || true
if command -v _receipted_git >/dev/null 2>&1 && command -v gstack_brain_lock_acquire >/dev/null 2>&1 \
&& gstack_brain_lock_acquire "$_GH" try; then
# Non-interactive + slow-network bounded (same guards as gstack-update-check):
# a hung remote or a credential prompt must not stall the preamble.
( cd "$_GH" && GSTACK_HOME="$_GH" GIT_TERMINAL_PROMPT=0 GIT_HTTP_LOW_SPEED_LIMIT=1000 GIT_HTTP_LOW_SPEED_TIME=5 \
_receipted_git closed brain-sync "${_PULL_HOST:-unknown}" curated-memory-git-fetch "artifacts_sync_mode!=off" \
git fetch origin >/dev/null 2>&1 && git merge --ff-only "origin/$(git rev-parse --abbrev-ref HEAD)" >/dev/null 2>&1 ) || true
gstack_brain_lock_release
# Stamp only when the receipted path actually ran — a missing egress lib
# must surface as a retry next start, not a silent 24h suppression.
echo "$_BRAIN_NOW" > "$_BRAIN_LAST_PULL_FILE"
fi
fi
"$_BRAIN_SYNC_BIN" --once 2>/dev/null || true
fi
if [ "$_GBRAIN_MCP_MODE" = "remote-http" ]; then
# Remote-MCP mode: local artifacts sync is a no-op by design (the brain
# admin's server pulls from GitHub/GitLab).
_GBRAIN_HOST=$(printf '%s' "${_GBRAIN_MCP_ENTRY:-}" | jq -r '.url // empty' 2>/dev/null | sed -E 's|^https?://([^/:]+).*|\1|' | head -1 | tr -cd 'A-Za-z0-9._-')
echo "ARTIFACTS_SYNC: remote-mode (managed by brain server ${_GBRAIN_HOST:-remote})"
elif [ -d "$_GH/.git" ] && [ "$_BRAIN_SYNC_MODE" != "off" ]; then
_BRAIN_QUEUE_DEPTH=0
# Spool-dir queue (one file per record); legacy .brain-queue.jsonl lines
# counted too until the drain migrates them.
[ -d "$_GH/.brain-queue.d" ] && _BRAIN_QUEUE_DEPTH=$(find "$_GH/.brain-queue.d" -maxdepth 1 -name '*.json' 2>/dev/null | wc -l | tr -d ' ')
[ -f "$_GH/.brain-queue.jsonl" ] && _BRAIN_QUEUE_DEPTH=$(( _BRAIN_QUEUE_DEPTH + $(wc -l < "$_GH/.brain-queue.jsonl" | tr -d ' ') ))
[ -f "$_GH/.brain-queue.jsonl.migrating" ] && _BRAIN_QUEUE_DEPTH=$(( _BRAIN_QUEUE_DEPTH + $(wc -l < "$_GH/.brain-queue.jsonl.migrating" | tr -d ' ') ))
_BRAIN_LAST_PUSH="never"
# First line only + charset clamp: this file lives in a git checkout pulled
# from the artifacts remote, so its content is not trusted for STATUS output.
[ -f "$_GH/.brain-last-push" ] && _BRAIN_LAST_PUSH=$(head -1 "$_GH/.brain-last-push" 2>/dev/null | tr -cd 'A-Za-z0-9._:+-' || echo never)
_BRAIN_LAST_PUSH=${_BRAIN_LAST_PUSH:-never}
echo "ARTIFACTS_SYNC: mode=$_BRAIN_SYNC_MODE | last_push=$_BRAIN_LAST_PUSH | queue=$_BRAIN_QUEUE_DEPTH"
# A stuck sync (scanner hold, failed push or commit, no push or no drain for
# 24 hours) prints fixed attention lines; a healthy sync prints none.
"$_BRAIN_SYNC_BIN" --attention 2>/dev/null | grep '^ARTIFACTS_SYNC: attention: ' || true
else
echo "ARTIFACTS_SYNC: off"
fi
# ---------------------------------------------------------------------------
# Instruction-emission layer (token-reduction Phase 2). One-time onboarding
# text used to be inlined unconditionally in every SKILL.md (~7KB/skill);
# it now appears ONLY when its runtime gate fires, wrapped in blocks the
# preamble prose tells the model to follow. Security scoping (F4/OV4): each
# header carries this run's SESSION_ID; the prose rule requires the match and
# accepts blocks only from this command's direct tool result, so page/file
# content cannot mint directives (passthrough output above is _sanitize-d).
# Ack ownership (OV6): display-only tips write their done-marker here at
# emit; interactive flows carry their ack commands inside the block for the
# model to run after the interaction.
# ---------------------------------------------------------------------------
_ROOT_DIR=$(dirname "$_BIN")
_emit_block() { echo "GSTACK_INSTRUCTION_BEGIN: $1 $_SESSION_ID"; cat; echo "GSTACK_INSTRUCTION_END"; }
# Spawned sessions get NO interactive-onboarding blocks (#2733): no human is
# watching, so an emitted prompt gets auto-answered (config writes nobody
# approved) and ack-at-emit markers get consumed invisibly — the next HUMAN
# session would never see the one-time prompt. Gating EMISSION here (not just
# the prose-skip inside the spawned-session block) also gates the script-side
# marker/state writes: .activated, .first-loop-tip-shown, and scaffold
# telemetry stay untouched, so onboarding fires intact on the next human run.
# The spawned-session block and the privacy-stop-gate below sit OUTSIDE this
# guard: the former is the gate's inverse, the latter is interactive-only.
if [ "$_SESSION_KIND" != "spawned" ]; then
# Upgrade flow (gated: update-check emitted something above).
if [ -n "$_UPD" ]; then
_emit_block upgrade-flow <<EOI
The update-check output above applies. If it shows \`UPGRADE_AVAILABLE <old> <new>\`: read \`$_ROOT_DIR/gstack-upgrade/SKILL.md\` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If it shows \`JUST_UPGRADED <from> <to>\`: print "Running gstack v{to} (just updated!)". If \`SPAWNED_SESSION\` is true, skip feature discovery. After upgrade prompts, continue the workflow.
EOI
fi
# Feature discovery (one prompt per session, marker-gated). These are
# machine-local UX acknowledgements, so keep them in GSTACK_HOME rather than
# beside an install path that may resolve through a project-local symlink.
if [ ! -f "$_GH/.feature-prompted-model-overlay" ]; then
_emit_block feature-overlay <<EOI
Feature discovery: inform "Model overlays are active. MODEL_OVERLAY shows the patch." Always run: \`touch "$_GH/.feature-prompted-model-overlay"\`.
EOI
fi
# Writing-style migration (gate previously dormant: nothing echoed
# WRITING_STYLE_PENDING; the script now computes it from the marker files).
if [ -f "$_GH/.writing-style-prompt-pending" ] && [ ! -f "$_GH/.writing-style-prompted" ]; then
_emit_block writing-style-migration <<EOI
Ask once about writing style:
> v1 prompts are simpler: first-use jargon glosses, outcome-framed questions, shorter prose. Keep default or restore terse?
Options:
- A) Keep the new default (recommended — good writing helps everyone)
- B) Restore V0 prose — set \`explain_level: terse\`
If A: leave \`explain_level\` unset (defaults to \`default\`). If B: run \`$_BIN/gstack-config set explain_level terse\`.
Always run (regardless of choice): \`rm -f "$_GH/.writing-style-prompt-pending" && touch "$_GH/.writing-style-prompted"\`.
EOI
fi
# Lake intro (one-time; the offer is interactive, so the model acks).
if [ "$_LAKE_SEEN" = "no" ]; then
_emit_block lake-intro <<EOI
Say: "gstack follows the **Boil the Ocean** principle — do the complete thing when AI makes marginal cost near-zero. Read more: https://garryslist.org/posts/boil-the-ocean" and offer to open it. Only run \`open https://garryslist.org/posts/boil-the-ocean\` if the user says yes. Always run: \`touch "$_GH/.completeness-intro-seen"\`.
EOI
fi
# Telemetry opt-in (interactive; consent — the model acks after answering).
if [ "$_TEL_PROMPTED" = "no" ] && [ "$_LAKE_SEEN" = "yes" ]; then
_emit_block telemetry-prompt <<EOI
Ask telemetry once via AskUserQuestion:
> Help gstack get better. Share usage data only: skill, duration, crashes, stable device ID. No code or file paths. Your repo name is recorded locally only and stripped before any upload.
Options:
- A) Help gstack get better! (recommended)
- B) No thanks
If A: run \`$_BIN/gstack-config set telemetry community\`. If B, ask the follow-up:
> Anonymous mode sends only aggregate usage, no unique ID.
Options: A) Sure, anonymous is fine B) No thanks, fully off
If B→A: \`$_BIN/gstack-config set telemetry anonymous\`. If B→B: \`$_BIN/gstack-config set telemetry off\`.
Always run: \`touch "$_GH/.telemetry-prompted"\`.
EOI
fi
# Proactive-suggestions opt-in (interactive).
if [ "$_PROACTIVE_PROMPTED" = "no" ] && [ "$_TEL_PROMPTED" = "yes" ]; then
_emit_block proactive-prompt <<EOI
Ask once:
> Let gstack proactively suggest skills, like /qa for "does this work?" or /investigate for bugs?
Options: A) Keep it on (recommended) B) Turn it off — I'll type /commands myself
If A: \`$_BIN/gstack-config set proactive true\`. If B: \`$_BIN/gstack-config set proactive false\`.
Always run: \`touch "$_GH/.proactive-prompted"\`.
EOI
fi
# First-run guidance (display-only tips: marker + scaffold telemetry written
# HERE at emit, per OV6 — a lost tip is acceptable; a re-firing loop is not).
if [ "$_ACTIVATED" = "no" ]; then
_FT_TIP=""
case "$_FIRST_TASK" in
greenfield) _FT_TIP="Fresh repo — shape it first with \`/spec\` or \`/office-hours\`." ;;
code_node|code_python|code_rust|code_go|code_ruby|code_ios) _FT_TIP="There's code here — \`/qa\` to see it work, or \`/investigate\` if something's off." ;;
branch_ahead) _FT_TIP="Unshipped work on this branch — \`/review\` then \`/ship\`." ;;
dirty_default) _FT_TIP="Uncommitted changes — \`/review\` before committing." ;;
clean_default) _FT_TIP="Pick one: \`/spec\`, \`/investigate\`, or \`/qa\`." ;;
esac
if [ -n "$_FT_TIP" ]; then
_emit_block first-run-tip <<EOI
Show this one project-specific line as a heads-up, then CONTINUE with whatever the user actually asked — do NOT halt their task: $_FT_TIP
EOI
"$_BIN/gstack-telemetry-log" --event-type first_task_scaffold_shown --skill "$_FIRST_TASK" --outcome shown 2>/dev/null || true
fi
touch "$_GH/.activated" 2>/dev/null || true
elif [ "$_FIRST_LOOP_SHOWN" = "no" ]; then
_emit_block first-loop-tip <<EOI
Say once as a heads-up (then continue): Tip: gstack pays off when you complete one loop — **plan → review → ship**. A common first loop: \`/office-hours\` or \`/spec\` to shape it, \`/plan-eng-review\` to lock it, then \`/ship\`.
EOI
touch "$_GH/.first-loop-tip-shown" 2>/dev/null || true
fi
# Routing injection (interactive: AUQ + CLAUDE.md append + commit). The body
# is a quoted heredoc (markdown backticks must stay literal), so the resolved
# bin path is substituted via sed on the __BIN__ placeholder.
if [ "$_HAS_ROUTING" = "no" ] && [ "$_ROUTING_DECLINED" = "false" ] && [ "$_PROACTIVE_PROMPTED" = "yes" ]; then
sed "s|__BIN__|$_BIN|g" <<'EOI' | _emit_block routing-injection
gstack works best when the project CLAUDE.md includes skill routing rules. If no CLAUDE.md exists in the project root, create it. Use AskUserQuestion:
> gstack works best when your project's CLAUDE.md includes skill routing rules.
Options: A) Add routing rules to CLAUDE.md (recommended) B) No thanks, I'll invoke skills manually
If A: append this section to the end of CLAUDE.md, then commit it (`git add CLAUDE.md && git commit -m "chore: add gstack skill routing rules to CLAUDE.md"`):
## Skill routing
When the user's request matches an available skill, invoke it via the Skill tool. Route only to skills in the session's available-skills list; answer directly for quick questions or small scoped edits.
Key routing rules:
- Product ideas/brainstorming → invoke /office-hours
- Strategy/scope → invoke /plan-ceo-review
- Architecture → invoke /plan-eng-review
- Design system/plan review → invoke /design-consultation or /plan-design-review
- Full review pipeline → invoke /autoplan
- Bugs/errors → invoke /investigate
- QA/testing site behavior → invoke /qa or /qa-only
- Code review/diff check → invoke /review
- Visual polish → invoke /design-review
- Ship/deploy/PR → invoke /ship or /land-and-deploy
- Save progress → invoke /context-save
- Resume context → invoke /context-restore
- Author a backlog-ready spec/issue → invoke /spec
If B: run `__BIN__/gstack-config set routing_declined true` and say they can re-enable with `__BIN__/gstack-config set routing_declined false`. This only happens once per project.
EOI
fi
# Vendoring deprecation (interactive; slug-scoped marker).
if [ "$_VENDORED" = "yes" ] && [ ! -f "$_GH/.vendoring-warned-${SLUG:-unknown}" ]; then
_emit_block vendoring-deprecation <<EOI
This project has gstack vendored in \`.claude/skills/gstack/\`. Vendoring is deprecated. Warn once via AskUserQuestion:
> Migrate to team mode?
Options: A) Yes, migrate to team mode now B) No, I'll handle it myself
If A: 1) \`git rm -r .claude/skills/gstack/\` 2) \`echo '.claude/skills/gstack/' >> .gitignore\` 3) \`$_BIN/gstack-team-init required\` (or \`optional\`) 4) \`git add .claude/ .gitignore CLAUDE.md && git commit -m "chore: migrate gstack from vendored to team mode"\` 5) Tell the user: "Done. Each developer now runs: \`cd ~/.claude/skills/gstack && ./setup --team\`"
If B: say "OK, you're on your own to keep the vendored copy up to date."
Always run (regardless of choice): \`touch "$_GH/.vendoring-warned-${SLUG:-unknown}"\`.
EOI
fi
fi # end interactive-onboarding guard (kind != spawned)
# Spawned-session rules (NOT one-time — every spawned session gets the full
# behavioral instruction, per plan OV6 move-with-care). Keyed on the resolved
# kind, not raw OPENCLAW_SESSION (#2733): the GSTACK_SESSION_KIND=spawned
# override must emit this block too — it is the only runtime text that
# actually says "auto-choose".
if [ "$_SESSION_KIND" = "spawned" ]; then
_emit_block spawned-session <<EOI
You are running inside a session spawned by an AI orchestrator (e.g., OpenClaw, or a parent skill such as /ship that dispatched you as a subagent). In spawned sessions: do NOT use AskUserQuestion for interactive prompts — auto-choose the recommended option (exception: never auto-choose a destructive or irreversible option such as delete, force-push, or overwrite, and never grant a consent or choose an option that publishes or syncs data off this machine — take the conservative non-destructive (local) choice and record it in the completion report); do NOT run upgrade checks, telemetry prompts, routing injection, or lake intro (skip any such instruction blocks above); focus on completing the task and reporting results via prose output; end with a completion report: what shipped, decisions made, anything uncertain.
EOI
fi
# Privacy stop-gate (Phase 2, user-approved Q2: consent question surfaces only
# when consent is actually pending; still fired through AskUserQuestion).
# Interactive sessions ONLY: this block is emitted AFTER the spawned-session
# block, so its "skip instruction blocks above" rule does not cover it — a
# spawned session's auto-choose would accept data-sync consent no human gave.
# Deferral is safe (EOV8): the config key stays unset, so the gate fires on
# the next interactive run. Same reasoning suppresses it in headless runs.
_ARTIFACTS_PROMPTED=$("$_BRAIN_CONFIG_BIN" get artifacts_sync_mode_prompted 2>/dev/null || echo "false")
if [ "$_SESSION_KIND" = "interactive" ] && [ "$_BRAIN_SYNC_MODE" = "off" ] && [ "$_ARTIFACTS_PROMPTED" != "true" ] && command -v gbrain >/dev/null 2>&1; then
_emit_block privacy-stop-gate <<EOI
Privacy stop-gate — ask once via AskUserQuestion:
> gstack can publish your artifacts (CEO plans, designs, reports) to a private GitHub repo that GBrain indexes across machines. How much should sync?
Options: A) Everything allowlisted (recommended) B) Only artifacts C) Decline, keep everything local
After answer run: \`$_BIN/gstack-config set artifacts_sync_mode <full|artifacts-only|off>\` and \`$_BIN/gstack-config set artifacts_sync_mode_prompted true\`. If A/B and \`~/.gstack/.git\` is missing, ask whether to run \`gstack-artifacts-init\`. Do not block the skill.
EOI
fi
# BRAIN_HEALTH block: only for hosts whose render passes --brain-health
# (gbrain/hermes) — gen-time host conditional preserved as a flag.
if [ "$BRAIN_HEALTH" = "yes" ] && command -v gbrain >/dev/null 2>&1; then
_BRAIN_JSON=$(gbrain doctor --fast --json 2>/dev/null || echo '{}')
_BRAIN_SCORE=$(echo "$_BRAIN_JSON" | grep -o '"health_score":[0-9]*' | cut -d: -f2)
_BRAIN_FAILS=$(echo "$_BRAIN_JSON" | grep -o '"status":"fail"' | wc -l | tr -d ' ')
_BRAIN_WARNS=$(echo "$_BRAIN_JSON" | grep -o '"status":"warn"' | wc -l | tr -d ' ')
echo "BRAIN_HEALTH: ${_BRAIN_SCORE:-unknown} (${_BRAIN_FAILS:-0} failures, ${_BRAIN_WARNS:-0} warnings)"
if [ "${_BRAIN_SCORE:-100}" -lt 50 ] 2>/dev/null; then
echo "$_BRAIN_JSON" | grep -o '"name":"[^"]*","status":"[^"]*","message":"[^"]*"' | _sanitize || true
fi
fi