Files
gstack/bin/gstack-codex-probe
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

644 lines
37 KiB
Bash
Executable File

#!/usr/bin/env bash
# gstack-codex-probe: shared helper for /codex, /autoplan and every outside
# review. Run it as a command, one subcommand per probe (`gstack-codex-probe
# help`): it prints KEY: value lines on stdout, human status lines where they
# went before, and sets nothing in the caller's shell.
#
# Subcommands (each wraps one function below):
# select-model <exec|review> [--model <id>] CODEX_SEL:, CODEX_SEL_KIND:, CODEX_SANDBOX:
# check-auth exit 0 authed, 1 not
# show-sandbox CODEX_SANDBOX:
# check-sandbox exit 0, or 3 with the reason on stderr
# probe-model <exec|review> [--model <id>] CODEX_PROBE_STATE:; exit 0, 1, 2 or 4
# check-version warnings on stderr; exit 0
# show-first-use-notice notice on stderr; exit 0
# run-with-timeout <secs> <cmd...> the command's exit code; 124 on timeout
# log-event <event> [detail] silent; exit 0
# log-hang <skill> <prompt-size> silent; exit 0
# help usage; an unknown subcommand exits 64
#
# Sourcing (compatibility window): skills rendered before the executed form
# source this file and call the functions directly. That still works, prints
# one deprecation line on stderr, and is removed in a release on or after
# 2026-10-21 together with the zsh self-locate block below.
#
# Functions (all prefixed with _gstack_codex_ for namespace hygiene):
# _gstack_codex_auth_probe — multi-signal auth check (env + file)
# _gstack_codex_select_model — resolve + print the runtime model (#2914)
# _gstack_codex_sandbox_mode — read-only, or full access only for GSTACK_CODEX_NO_SANDBOX=1
# _gstack_codex_sandbox_preflight — free `codex sandbox` check before paid calls (Linux)
# _gstack_codex_first_use_notice — once per machine: provider, account, how to turn off
# _gstack_codex_model_probe — round-trip probe of the selected model (#2477);
# exit 4 = the account's Codex usage limit
# _gstack_codex_version_check — warn on known-bad Codex CLI versions
# _gstack_codex_timeout_wrapper — gtimeout -> timeout -> bash-native watchdog
# _gstack_codex_log_event — telemetry emission to ~/.gstack/analytics/
#
# Hygiene rules for the sourced form (enforced by test/codex-hardening.test.ts):
# - Never change -e / -u / traps / IFS / PATH in the caller shell.
# - All internal vars prefix with _GSTACK_CODEX_.
# - All functions prefix with _gstack_codex_.
# - No command execution at source time (only function defs, the shared
# self-location block below, which is parameter expansion only, and the
# deprecation line; its _gstack_helper* variables are the one exception to
# the prefix rule and are unset once _GSTACK_CODEX_BIN is set).
# --- Self-location (bash and zsh) -------------------------------------------
# Under zsh BASH_SOURCE is empty, so every "$dir/../scripts/..." path became
# "/..." and Codex model selection failed. The shared block below sets
# _gstack_helper_dir; inside a function zsh's %x names the function, not the
# file, so it is copied once here.
_gstack_helper=gstack-codex-probe
# === gstack self-locate (shared, byte-identical in every sourced helper) ===
# Skill blocks source helpers into the host's shell: bash, or zsh on macOS
# (Claude Code's Bash tool included). Resolved once at source time, using
# parameter expansion only: BASH_SOURCE under bash, %x under zsh (inside eval
# so bash never parses it), made absolute with $PWD; else $GSTACK_ROOT/bin
# when it holds this helper. Any other case, and any other shell, fails loudly
# instead of guessing; the message and the return come before any bash- or
# zsh-only syntax, so dash and sh print it instead of a syntax error.
_gstack_helper_dir=""
_gstack_helper_shell=""
if [ -n "${BASH_VERSION:-}" ]; then
_gstack_helper_shell=bash
_gstack_helper_dir="${BASH_SOURCE[0]}"
elif [ -n "${ZSH_VERSION:-}" ]; then
_gstack_helper_shell=zsh
eval '_gstack_helper_dir="${(%):-%x}"'
fi
case "$_gstack_helper_dir" in
/*) _gstack_helper_dir="${_gstack_helper_dir%/*}" ;;
*/*) _gstack_helper_dir="$PWD/${_gstack_helper_dir%/*}" ;;
?*) _gstack_helper_dir="$PWD" ;;
esac
if [ -n "$_gstack_helper_shell" ] && [ ! -f "$_gstack_helper_dir/$_gstack_helper" ]; then
_gstack_helper_dir=""
if [ -n "${GSTACK_ROOT:-}" ] && [ -f "$GSTACK_ROOT/bin/$_gstack_helper" ]; then
_gstack_helper_dir="$GSTACK_ROOT/bin"
fi
fi
if [ -z "$_gstack_helper_shell" ] || [ -z "$_gstack_helper_dir" ]; then
_gstack_helper_error="gstack: cannot locate $_gstack_helper (shell: ${_gstack_helper_shell:-${0##*/}}). Source it from bash or zsh, or export GSTACK_ROOT=<install dir>. https://github.com/garrytan/gstack/blob/main/docs/troubleshooting.md#sourced-helper-location"
printf '%s\n' "$_gstack_helper_error" >&2
return 1 2>/dev/null || exit 1
fi
# === end gstack self-locate ===
_GSTACK_CODEX_BIN="$_gstack_helper_dir"
unset _gstack_helper _gstack_helper_dir _gstack_helper_shell
# --- Auth probe -------------------------------------------------------------
_gstack_codex_auth_probe() {
# Multi-signal: env vars OR auth file OR a custom provider's env_key. Avoids
# false negatives for env-auth users (CI, platform engineers, self-hosted
# OpenAI-compatible providers) that a file-only check would reject.
local _codex_home="${CODEX_HOME:-$HOME/.codex}"
# Use `-n` which returns true only for non-empty non-whitespace. Bash's [ -n ]
# alone allows whitespace; pair with a whitespace strip for robustness.
local _k1 _k2
_k1=$(printf '%s' "${CODEX_API_KEY:-}" | tr -d '[:space:]')
_k2=$(printf '%s' "${OPENAI_API_KEY:-}" | tr -d '[:space:]')
if [ -n "$_k1" ] || [ -n "$_k2" ] || [ -f "$_codex_home/auth.json" ]; then
echo "AUTH_OK"
return 0
fi
# Custom OpenAI-compatible providers (#2192): a [model_providers.<id>]
# table names its credential variable in env_key. Only keys inside those
# tables count, comments are ignored, and the name must be a plain shell
# identifier before it is dereferenced.
local _env_key _resolved _missing=""
if [ -f "$_codex_home/config.toml" ]; then
while IFS= read -r _env_key; do
case "$_env_key" in ''|[0-9]*|*[!A-Za-z0-9_]*) continue ;; esac
# Indirect read through eval, not ${!name}: zsh rejects bash's
# indirection, and _env_key is a validated identifier by this point.
eval "_resolved=\${$_env_key:-}"
_resolved=$(printf '%s' "$_resolved" | tr -d '[:space:]')
if [ -n "$_resolved" ]; then
echo "AUTH_OK"
return 0
fi
_missing="${_missing:+$_missing, }$_env_key"
done < <(awk '/^[[:space:]]*#/ { next }
/^[[:space:]]*\[/ { in_provider = ($0 ~ /^[[:space:]]*\[model_providers\.[^]]+\][[:space:]]*(#.*)?$/); next }
in_provider && /^[[:space:]]*env_key[[:space:]]*=/ { v = $0; sub(/^[^=]*=[[:space:]]*/, "", v); sub(/[[:space:]]*#.*$/, "", v); gsub(/["\047[:space:]]/, "", v); print v }' "$_codex_home/config.toml" 2>/dev/null)
fi
echo "AUTH_FAILED"
[ -n "$_missing" ] && echo "HINT: $_codex_home/config.toml names a custom provider key ($_missing), but it is not set in this shell. Export it, or run codex login." >&2
return 1
}
# --- Runtime model selection (#2914) ---------------------------------------
_gstack_codex_select_model() {
# One selection record per invocation kind, shared by the probe and the
# dispatch flag in the same block: explicit request ($2), GSTACK_CODEX_MODEL,
# Codex config.toml (review_model first for native review), gstack default.
# The TOML is read by the TypeScript resolver; bash never parses it.
local _kind="${1:-exec}" _explicit="${2:-}" _line _rc
case "$_kind" in exec|review) ;; *) echo "ERROR: _gstack_codex_select_model takes exec or review" >&2; return 2 ;; esac
if ! command -v bun >/dev/null 2>&1; then
echo "CODEX_MODEL: unresolved — bun is not on PATH, so gstack cannot read the Codex model choice. Reinstall gstack with ./setup; no Codex call was made." >&2
return 1
fi
if [ -n "$_explicit" ]; then
_line=$(bun run "$_GSTACK_CODEX_BIN/../scripts/resolve-codex-generation-model.ts" --runtime "$_kind" --explicit "$_explicit")
else
_line=$(bun run "$_GSTACK_CODEX_BIN/../scripts/resolve-codex-generation-model.ts" --runtime "$_kind")
fi
_rc=$?
_GSTACK_CODEX_SEL="${_line%%$'\t'*}"
_GSTACK_CODEX_SEL_SRC="${_line#*$'\t'}"
case "$_GSTACK_CODEX_SEL" in ''|*[!A-Za-z0-9._:/-]*) _rc=1 ;; esac
if [ "$_rc" -ne 0 ] || [ "${#_GSTACK_CODEX_SEL}" -gt 100 ]; then
_GSTACK_CODEX_SEL=""
_GSTACK_CODEX_SEL_SRC=""
echo "CODEX_MODEL: invalid — Codex outside review unavailable; missing coverage. No Codex call was made. Fix the model choice above; gstack never substitutes its default for it." >&2
return 1
fi
_GSTACK_CODEX_SEL_KIND="$_kind"
echo "CODEX_MODEL: $_GSTACK_CODEX_SEL ($_kind; source: $_GSTACK_CODEX_SEL_SRC)" >&2
_gstack_codex_sandbox_mode
}
# --- Sandbox (B1) -----------------------------------------------------------
_gstack_codex_sandbox_mode() {
# Every gstack Codex command passes -s / sandbox_mode from this variable, so
# one place decides it. Codex has no read-only mode without its sandbox, so
# the escape hatch is full access: honored only for exactly 1, only from the
# shell environment (never a dotenv file or config), and announced each use.
if [ "${GSTACK_CODEX_NO_SANDBOX:-}" = "1" ]; then
_GSTACK_CODEX_SANDBOX="danger-full-access"
echo "WARNING: GSTACK_CODEX_NO_SANDBOX=1: Codex runs this review without a sandbox and can read and write anything your user can. Use it only inside a container you trust." >&2
else
_GSTACK_CODEX_SANDBOX="read-only"
fi
}
_gstack_codex_sandbox_preflight() {
# Free check before the first paid call: `codex sandbox` starts the same
# bubblewrap sandbox with no model. Only a recognized sandbox failure blocks
# (exit 3, printed as missing coverage); success, a timeout, or an older CLI
# without the subcommand defers to the post-run classifier. Linux only, and
# skipped when the user turned the sandbox off. Fixtures:
# test/fixtures/codex-sandbox/.
[ "${GSTACK_CODEX_NO_SANDBOX:-}" = "1" ] && return 0
[ "$(uname -s 2>/dev/null)" = "Linux" ] || return 0
local _out _code _line
_out=$(_gstack_codex_timeout_wrapper 10 codex sandbox -c 'sandbox_mode="read-only"' true </dev/null 2>&1)
_code=$?
{ [ "$_code" -eq 0 ] || [ "$_code" -eq 124 ]; } && return 0
_line=$(printf '%s\n' "$_out" | grep -m1 -iE '^[[:space:]]*bwrap: |bubblewrap is unavailable|landlock.{0,60}(fail|error|not supported|unsupported)|seccomp.{0,60}(fail|error)|user namespaces?.{0,80}(not (allowed|permitted|supported)|denied|disabled)' | sed 's/^[[:space:]]*//' | cut -c1-240)
[ -n "$_line" ] || return 0
echo "CODEX_SANDBOX: unavailable"
echo "Codex outside review unavailable: Codex's sandbox could not start here ($_line). No review ran; this is missing coverage, not a pass. Fix: enable unprivileged user namespaces for this container, or set GSTACK_CODEX_NO_SANDBOX=1." >&2
_gstack_codex_log_event "codex_sandbox_unavailable" 2>/dev/null || true
return 3
}
# --- First-use notice (#965) ------------------------------------------------
_gstack_codex_first_use_notice() {
# Outside reviews are on by default and use whatever Codex login exists, so
# the first one on a machine says where the code goes, with which account,
# and how to turn reviews off. Shown once per state root; never blocks and
# never prints a credential, only where it comes from.
local _root _marker _codex_home="${CODEX_HOME:-$HOME/.codex}" _account _provider
_root="$(. "$_GSTACK_CODEX_BIN/gstack-state-root.sh" 2>/dev/null && gstack_state_root)" || return 0
[ -n "$_root" ] || return 0
_marker="$_root/.codex-review-notice-shown"
[ -e "$_marker" ] && return 0
if [ -n "$(printf '%s' "${CODEX_API_KEY:-}" | tr -d '[:space:]')" ]; then _account="the API key in CODEX_API_KEY"
elif [ -n "$(printf '%s' "${OPENAI_API_KEY:-}" | tr -d '[:space:]')" ]; then _account="the API key in OPENAI_API_KEY"
elif grep -q '"auth_mode"[[:space:]]*:[[:space:]]*"chatgpt"' "$_codex_home/auth.json" 2>/dev/null; then _account="the ChatGPT account Codex is logged in with (see: codex login status)"
elif [ -f "$_codex_home/auth.json" ]; then _account="the API key saved by codex login in $_codex_home/auth.json"
else _account="the credentials your Codex config.toml provider names"
fi
_provider=$(sed -n 's/^[[:space:]]*model_provider[[:space:]]*=[[:space:]]*"\([A-Za-z0-9_.-]*\)".*/\1/p' "$_codex_home/config.toml" 2>/dev/null | head -1)
echo "NOTICE: gstack outside reviews send the review prompt and code to Codex (provider: ${_provider:-openai}) using $_account. Reviews stay on; this notice shows once per machine. To turn them off: gstack-config set codex_reviews disabled" >&2
mkdir -p "$_root" 2>/dev/null && : > "$_marker" 2>/dev/null
return 0
}
# --- Model round-trip probe (#2477) ------------------------------------------
_gstack_codex_model_probe() {
# Auth-exists is a weaker signal than the auth probe implies: a ChatGPT
# account can be valid while the model gstack will request is unavailable.
# A short real round trip with the selected model catches model rejection
# and entitlement changes in one shot (#2477). The model comes from
# _gstack_codex_select_model ($1 = exec|review, default exec), the same
# record the dispatch flag uses, so the probe never checks a different model.
#
# Contract:
# MODEL_OK (exit 0) — round trip succeeded; cached 1h.
# MODEL_UNUSABLE (exit 1) — deterministic model rejection (400, or a
# 404 from a retired model or a wrong custom-provider base_url) or an
# invalid model choice; hints name the cause. The 400 is cached 15 min: re-probing every
# preflight charged the affected user a 30s round trip + real tokens per
# review section, forever. Changing the model or config.toml changes the
# cache signature and re-probes immediately; the short TTL covers
# server-side entitlement recovery the signature can't see.
# MODEL_UNUSABLE_INSTALL (exit 2) — the CLI cannot execute at all (spawn
# ENOENT, non-executable binary, missing vendor payload). Deterministic,
# so fail-open is wrong: retrying never helps. Never cached — a reinstall
# fixes it and must be picked up on the very next probe (#2742).
# MODEL_QUOTA_EXHAUSTED (exit 4) — Codex's usage-limit or insufficient_quota
# error on a failed, non-timeout call: the account, not the model. Codex's
# own line (with its reset time) is relayed verbatim; cached 15 min under
# the same signature as MODEL_UNUSABLE, so later fresh-shell blocks in the
# run make no Codex call. GSTACK_CODEX_PROBE_RETRY=1 skips both negative
# cache entries for that probe.
# MODEL_PROBE_RATE_LIMITED (exit 0) — a plain 429 / rate-limit error: often
# gone in seconds, so the review still runs, like the inconclusive case
# (_GSTACK_CODEX_PROBE_STATE=rate_limited, CODEX_MODE: unverified
# (rate_limited)). Codex's line is relayed verbatim; never cached.
# MODEL_PROBE_INCONCLUSIVE (exit 0) — timeout/transient; the review still
# runs so a slow network never wedges codex mode, but readiness is
# unverified (_GSTACK_CODEX_PROBE_STATE=inconclusive, CODEX_MODE:
# unverified) and the review's own classification decides. Never cached.
#
# Quota and rate-limit signatures read only Codex's own trailing error lines
# (ERROR: / stream error), never the whole output: it echoes the prompt.
#
# Only call this AFTER _gstack_codex_auth_probe passes — probing without
# auth just measures the auth failure again.
local _kind="${1:-exec}"
if [ -z "${_GSTACK_CODEX_SEL:-}" ] || [ "${_GSTACK_CODEX_SEL_KIND:-}" != "$_kind" ]; then
if ! _gstack_codex_select_model "$_kind"; then
echo "MODEL_UNUSABLE"
echo "HINT: the requested Codex model is not a valid model id; fix it as described above."
return 1
fi
fi
local _model="$_GSTACK_CODEX_SEL"
local _codex_home="${CODEX_HOME:-$HOME/.codex}"
# State root from the shared twin (sourced in a subshell, so the caller's
# shell is untouched). A missing twin only disables the cache.
local _gstack_home _cache=""
_gstack_home="$(. "$_GSTACK_CODEX_BIN/gstack-state-root.sh" 2>/dev/null && gstack_state_root)" || _gstack_home=""
[ -n "$_gstack_home" ] && _cache="$_gstack_home/.codex-model-probe"
# Cache signature (#2787): everything that can change the round trip's
# outcome without the hour passing — the model, the Codex home and its
# config.toml mtime, the auth mode (which env var or auth.json, plus its
# mtime; never a credential value), and the resolved codex binary and its
# mtime (an upgrade or PATH swap re-probes). Folded through cksum so paths
# with spaces stay one field of the cache line.
# GNU-first stat order + numeric validation (the #2195 pattern): on GNU
# stat, `-f` means FILESYSTEM mode, so the BSD-first form emitted a
# multi-line filesystem block on Linux — the signature then never matched
# its own cache line and the cache missed on every read. BSD stat rejects
# `-c` cleanly, so GNU-first degrades correctly on macOS.
local _cfg_m _auth_m _auth_mode="" _bin _bin_m _sig
_cfg_m=$(stat -c %Y "$_codex_home/config.toml" 2>/dev/null || stat -f %m "$_codex_home/config.toml" 2>/dev/null || echo 0)
_auth_m=$(stat -c %Y "$_codex_home/auth.json" 2>/dev/null || stat -f %m "$_codex_home/auth.json" 2>/dev/null || echo 0)
case "$_cfg_m" in ''|*[!0-9]*) _cfg_m=0 ;; esac
case "$_auth_m" in ''|*[!0-9]*) _auth_m=0 ;; esac
[ -n "$(printf '%s' "${CODEX_API_KEY:-}" | tr -d '[:space:]')" ] && _auth_mode="${_auth_mode}env-codex,"
[ -n "$(printf '%s' "${OPENAI_API_KEY:-}" | tr -d '[:space:]')" ] && _auth_mode="${_auth_mode}env-openai,"
[ -f "$_codex_home/auth.json" ] && _auth_mode="${_auth_mode}file,"
_bin=$(command -v codex 2>/dev/null || echo none)
_bin=$(readlink -f "$_bin" 2>/dev/null || printf '%s' "$_bin")
_bin_m=$(stat -c %Y "$_bin" 2>/dev/null || stat -f %m "$_bin" 2>/dev/null || echo 0)
case "$_bin_m" in ''|*[!0-9]*) _bin_m=0 ;; esac
_sig=$(printf '%s\n' "$_model" "$_codex_home" "$_cfg_m" "$_auth_mode" "$_auth_m" "$_bin" "$_bin_m" | cksum | tr -d ' ')
local _now
_now=$(date +%s 2>/dev/null || echo 0)
local _docs="https://github.com/garrytan/gstack/blob/main/docs/troubleshooting.md"
if [ -n "$_cache" ] && [ -f "$_cache" ]; then
local _c_line _c_status _c_ts _c_sig
_c_line=$(head -1 "$_cache" 2>/dev/null)
_c_status=$(printf '%s' "$_c_line" | cut -d' ' -f1)
_c_ts=$(printf '%s' "$_c_line" | cut -d' ' -f2)
_c_sig=$(printf '%s' "$_c_line" | cut -d' ' -f3)
case "$_c_ts" in ''|*[!0-9]*) _c_ts=0 ;; esac
if [ "$_c_status" = "MODEL_OK" ] && [ "$_c_sig" = "$_sig" ] && [ $((_now - _c_ts)) -lt 3600 ]; then
echo "MODEL_OK (cached)"
return 0
fi
[ "${GSTACK_CODEX_PROBE_RETRY:-}" = "1" ] && _c_sig="retry"
if [ "$_c_status" = "MODEL_QUOTA_EXHAUSTED" ] && [ "$_c_sig" = "$_sig" ] && [ $((_now - _c_ts)) -lt 900 ]; then
echo "MODEL_QUOTA_EXHAUSTED (cached)"
sed -n '2,4p' "$_cache" 2>/dev/null
echo "HINT: Codex refused this account's calls for its usage limit (Codex's line above names the reset time); the model choice is fine. No Codex call was made: gstack skips Codex for $(( (_c_ts + 900 - _now + 59) / 60 )) more minute(s). Retry now: GSTACK_CODEX_PROBE_RETRY=1, or delete $_cache. $_docs#codex-quota-exhausted"
return 4
fi
if [ "$_c_status" = "MODEL_UNUSABLE" ] && [ "$_c_sig" = "$_sig" ] && [ $((_now - _c_ts)) -lt 900 ]; then
echo "MODEL_UNUSABLE (cached)"
echo "HINT: gstack requested model '$_model' (source: $_GSTACK_CODEX_SEL_SRC)."
echo "HINT: choose a model your account can use: set GSTACK_CODEX_MODEL=<supported-model>, set model in $_codex_home/config.toml, or name one for this request."
return 1
fi
fi
local _out _code
_out=$(_gstack_codex_timeout_wrapper 30 codex exec --skip-git-repo-check -s read-only -c "model=\"$_model\"" -c 'skills.include_instructions=false' "reply OK" </dev/null 2>&1)
_code=$?
if [ "$_code" -eq 0 ]; then
[ -n "$_cache" ] && { mkdir -p "$_gstack_home" 2>/dev/null; printf 'MODEL_OK %s %s\n' "$_now" "$_sig" > "$_cache" 2>/dev/null; }
echo "MODEL_OK"
return 0
fi
# A usage limit is the account, not the model or the network: Codex says so
# plainly ("You've hit your usage limit ... try again at <time>"), and the
# inconclusive branch used to drop that line and re-probe in every skill.
# Only a failed, non-timeout call counts, and only Codex's own trailing error
# lines are read. Quota wins over rate limit: a 429 body that names
# insufficient_quota is the quota.
local _err _q_lines
if [ "$_code" -ne 124 ]; then
_err=$(printf '%s\n' "$_out" | awk '
/^[[:space:]]*(\[[^]]*\][[:space:]]*)?(ERROR:|stream error)/ { buf = buf $0 "\n"; next }
/^[[:space:]]*$/ { next }
{ buf = "" }
END { printf "%s", buf }')
fi
_q_lines=$(printf '%s' "$_err" | grep -iE "usage limit|insufficient_quota|exceeded your current quota|quota exceeded" | head -3)
if [ -n "$_q_lines" ]; then
[ -n "$_cache" ] && { mkdir -p "$_gstack_home" 2>/dev/null; printf 'MODEL_QUOTA_EXHAUSTED %s %s\n%s\n' "$_now" "$_sig" "$_q_lines" > "$_cache" 2>/dev/null; }
echo "MODEL_QUOTA_EXHAUSTED"
printf '%s\n' "$_q_lines"
echo "HINT: Codex refused the call for this account's usage limit (Codex's line above names the reset time); the model choice is fine. Outside coverage is unavailable: gstack skips Codex for 15 minutes. Retry now: GSTACK_CODEX_PROBE_RETRY=1${_cache:+, or delete $_cache}. $_docs#codex-quota-exhausted"
_gstack_codex_log_event "codex_quota_exhausted" 2>/dev/null || true
return 4
fi
_q_lines=$(printf '%s' "$_err" | grep -iE "rate.?limit|too many requests|(^|[^0-9])429([^0-9]|$)" | head -3)
if [ -n "$_q_lines" ]; then
_GSTACK_CODEX_PROBE_STATE="rate_limited"
echo "MODEL_PROBE_RATE_LIMITED — CODEX_MODE: unverified (rate_limited); proceeding, and the review's own result still decides."
printf '%s\n' "$_q_lines"
echo "HINT: Codex rate-limited the check (Codex's line above). Not cached; if the review itself is rate-limited, it reports missing coverage. $_docs#codex-rate-limited"
_gstack_codex_log_event "codex_rate_limited" 2>/dev/null || true
return 0
fi
# A model rejection is deterministic: a 400 ("is not supported", "requires a
# newer version of Codex") or a 404. A retired model answers 404 "does not
# exist or you do not have access to it", and a custom provider with a wrong
# base_url answers a bare 404; neither is network luck, so neither may fall
# through to the inconclusive branch below and report ready (#2843).
if printf '%s' "$_out" | grep -qiE 'model.{0,40}is not supported|"status":[[:space:]]*40[04]|requires a newer version of codex|does not exist or you do not have access|model.{0,40}does not exist|404 not found|status:?[[:space:]]*404'; then
[ -n "$_cache" ] && { mkdir -p "$_gstack_home" 2>/dev/null; printf 'MODEL_UNUSABLE %s %s\n' "$_now" "$_sig" > "$_cache" 2>/dev/null; }
echo "MODEL_UNUSABLE"
printf '%s\n' "$_out" | grep -iE "model|404" | head -3
echo "HINT: gstack requested model '$_model' (source: $_GSTACK_CODEX_SEL_SRC)."
if printf '%s' "$_out" | grep -qiE 'requires a newer version of codex|upgrade to the latest (app|version|cli)'; then
echo "HINT: the server refused it because this Codex CLI is too old; no model choice fixes that. Upgrade the CLI (\`codex doctor\` prints the command; usually npm install -g @openai/codex)."
_gstack_codex_log_event "codex_cli_outdated" 2>/dev/null || true
elif printf '%s' "$_out" | grep -qiE 'does not exist|404'; then
echo "HINT: Codex answered 404: either the model is retired or not visible to this account, or a custom provider's base_url in $_codex_home/config.toml is wrong."
echo "HINT: choose a current model (GSTACK_CODEX_MODEL=<supported-model> or model in config.toml), or fix that provider's base_url."
_gstack_codex_log_event "codex_model_retired" 2>/dev/null || true
else
echo "HINT: choose a model your account can use: set GSTACK_CODEX_MODEL=<supported-model>, set model in $_codex_home/config.toml, or name one for this request."
_gstack_codex_log_event "codex_model_unusable" 2>/dev/null || true
fi
return 1
fi
# A CLI that cannot execute is deterministic, not transient: the fail-open
# below exists for network luck, and swallowing this here is what let a
# missing vendor binary report CODEX_MODE: ready while every Codex pass was
# silently skipped (#2742). 126 = found but not executable, 127 = not found.
# String signatures only count on a FAILED, NON-TIMEOUT spawn: a successful
# response that mentions "permission denied" must not classify as broken,
# and neither may a timed-out (124) probe whose partial output quotes such
# strings — 124 keeps its fail-open contract below.
_BROKEN_SIG='ENOENT|ENOEXEC|EACCES|no such file or directory|cannot execute binary file|not executable|permission denied'
if [ "$_code" -eq 126 ] || [ "$_code" -eq 127 ] || { [ "$_code" -ne 0 ] && [ "$_code" -ne 124 ] && printf '%s' "$_out" | grep -qiE "$_BROKEN_SIG"; }; then
echo "MODEL_UNUSABLE_INSTALL"
printf '%s\n' "$_out" | grep -iE "$_BROKEN_SIG" | head -3
echo "HINT: the Codex CLI is on PATH but cannot run — its binary or vendor payload is missing."
echo "HINT: reinstall with: npm install -g @openai/codex"
_gstack_codex_log_event "codex_broken_install" 2>/dev/null || true
return 2
fi
# Timeout (124) or transient failure: fail-open with a warning. The probe
# exists to catch the deterministic model 400, not to gate on network luck.
# Callers report CODEX_MODE: unverified, never ready; the exit stays 0 so
# skills rendered before this marker keep running the review.
_GSTACK_CODEX_PROBE_STATE="inconclusive"
echo "MODEL_PROBE_INCONCLUSIVE (exit $_code) — CODEX_MODE: unverified; proceeding, and the review's own result is still checked. If invocations fail with a model 400, see the codex skill's Error Handling entry."
return 0
}
# --- Version check ----------------------------------------------------------
_gstack_codex_version_check() {
# Warn on known-bad Codex CLI versions. Anchored regex prevents false
# positives like 0.120.10 or 0.120.20 from matching. 0.120.2-beta still
# matches the bad release and gets warned (it IS buggy).
# Update this list when a new Codex CLI version regresses.
local _ver _vcode
# Capture the code from codex, not from `head` — a pipeline reports the LAST
# command's status, which is why a CLI that only ever printed a spawn error
# still read as healthy here (#2742). Keep stderr: it carries the diagnosis.
_ver=$(codex --version 2>&1)
_vcode=$?
_ver=$(printf '%s' "$_ver" | head -1)
# Only a NON-ZERO exit is evidence of a broken CLI. Empty-but-successful
# output stays silent by design (a CLI may legitimately print nothing), which
# the "empty output → OK" case in this file's suite pins.
if [ "$_vcode" -ne 0 ]; then
echo "WARN: \`codex --version\` failed (exit $_vcode) — the CLI is on PATH but may not be runnable."
[ -n "$_ver" ] && echo "WARN: it said: $_ver"
echo "WARN: if Codex passes are being skipped, reinstall with: npm install -g @openai/codex"
_gstack_codex_log_event "codex_version_unreadable" 2>/dev/null || true
return 0
fi
[ -z "$_ver" ] && return 0
if echo "$_ver" | grep -Eq '(^|[^0-9.])0\.120\.(0|1|2)([^0-9.]|$)'; then
echo "WARN: Codex CLI $_ver has known stdin deadlock bugs. Run: npm install -g @openai/codex@latest"
_gstack_codex_log_event "codex_version_warning"
fi
}
# --- Timeout wrapper --------------------------------------------------------
_gstack_codex_timeout_wrapper() {
# Resolve wrapper binary: prefer gtimeout (Homebrew coreutils on macOS),
# fall back to timeout (Linux), else a bash-native watchdog. Arguments:
# $1 is the duration in seconds; rest is the command to run.
# A child that ignores TERM is KILLed after a grace period
# (_GSTACK_CODEX_KILL_AFTER seconds, default 10), so the deadline always
# ends the provider before the caller's outer tool gate (#2776). Either
# way a deadline reports timeout(1)'s exit 124; output already written stays.
local _duration="$1"
shift
local _grace="${_GSTACK_CODEX_KILL_AFTER:-10}"
local _to _rc _start
_to=$(command -v gtimeout 2>/dev/null || command -v timeout 2>/dev/null || echo "")
if [ -n "$_to" ]; then
_start=$(date +%s 2>/dev/null || echo 0)
"$_to" -k "$_grace" "$_duration" "$@"
_rc=$?
# 137 = timeout(1)'s KILL escalation; it is still the deadline firing.
if [ "$_rc" -eq 137 ] && [ $(( $(date +%s 2>/dev/null || echo 0) - _start )) -ge "${_duration%%.*}" ]; then
_rc=124
fi
return "$_rc"
else
# Stock macOS ships neither coreutils gtimeout nor timeout(1); running
# unwrapped let a hung `codex exec` block the probe — and the calling
# workflow — indefinitely. Emulate: background the command, TERM it at
# the deadline, KILL it after the grace period if it is still alive, and
# mirror timeout(1)'s exit-124 contract. The watchdog's stdout is
# detached so an early finish never blocks a caller's $(...) capture on
# the orphaned sleep.
# Without job control a background command's stdin is /dev/null; keep the
# caller's stdin so prompts fed with `codex exec -` arrive (#1674).
"$@" <&0 &
local _cmd_pid=$!
(
sleep "$_duration" && trap '' TERM && kill -TERM "$_cmd_pid" 2>/dev/null || exit 0 # best-effort: the command already exited, nothing to stop
_GSTACK_CODEX_WAITED=0
while [ "$_GSTACK_CODEX_WAITED" -lt "$_grace" ] && kill -0 "$_cmd_pid" 2>/dev/null; do
sleep 1
_GSTACK_CODEX_WAITED=$((_GSTACK_CODEX_WAITED + 1))
done
# Freeze the command first: killing its children while it runs lets it
# continue past the killed child and print output after its deadline.
kill -STOP "$_cmd_pid" 2>/dev/null
pkill -KILL -P "$_cmd_pid" 2>/dev/null
kill -KILL "$_cmd_pid" 2>/dev/null
exit 124
) >/dev/null 2>&1 &
local _watch_pid=$!
wait "$_cmd_pid"
_rc=$?
kill "$_watch_pid" 2>/dev/null
wait "$_watch_pid" 2>/dev/null
if [ "$?" -eq 124 ]; then
_rc=124
fi
return "$_rc"
fi
}
# --- Telemetry event --------------------------------------------------------
_gstack_codex_log_event() {
# Emit a telemetry event to ~/.gstack/analytics/skill-usage.jsonl.
# Gated on $_TEL != "off" (caller sets this from gstack-config).
# Event types: codex_timeout, codex_auth_failed, codex_cli_missing,
# codex_version_warning, codex_model_unusable, codex_sandbox_unavailable,
# codex_model_retired, codex_cli_outdated, codex_quota_exhausted,
# codex_rate_limited.
# Payload schema: {skill, event, duration_s, ts}. NEVER includes prompt
# content, env var values, or auth tokens.
local _event="$1"
local _duration="${2:-0}"
[ "${_TEL:-off}" = "off" ] && return 0
local _root
_root="$(. "$_GSTACK_CODEX_BIN/gstack-state-root.sh" 2>/dev/null && gstack_state_root)" || return 0
[ -n "$_root" ] || return 0
mkdir -p "$_root/analytics" 2>/dev/null || return 0
local _ts
_ts=$(date -u +%Y-%m-%dT%H:%M:%SZ 2>/dev/null || echo unknown)
printf '{"skill":"codex","event":"%s","duration_s":"%s","ts":"%s"}\n' \
"$_event" "$_duration" "$_ts" \
>> "$_root/analytics/skill-usage.jsonl" 2>/dev/null || true
}
# --- Learnings log on hang --------------------------------------------------
_gstack_codex_log_hang() {
# Invoked when a codex invocation times out (exit 124). Records an
# operational learning so future /investigate sessions surface the pattern.
# Best-effort: errors swallowed.
local _mode="${1:-unknown}"
local _prompt_size="${2:-0}"
local _log_bin="$HOME/.claude/skills/gstack/bin/gstack-learnings-log"
[ -x "$_log_bin" ] || return 0
local _key="codex-hang-$(date +%s 2>/dev/null || echo unknown)"
"$_log_bin" "$(printf '{"skill":"codex","type":"operational","key":"%s","insight":"Codex hit its timeout wrapper during [%s] invocation. Prompt size: %s. Consider splitting prompt or checking network.","confidence":8,"source":"observed","files":["codex/SKILL.md.tmpl","autoplan/SKILL.md.tmpl"]}' "$_key" "$_mode" "$_prompt_size")" \
>/dev/null 2>&1 || true
}
# --- Executed subcommands ----------------------------------------------------
_gstack_codex_usage() {
printf '%s\n' \
'Usage: gstack-codex-probe <subcommand> [args]' \
' select-model <exec|review> [--model <id>] print CODEX_SEL:, CODEX_SEL_KIND: and CODEX_SANDBOX:; exit 0 or 1' \
' check-auth exit 0 when Codex credentials exist, 1 otherwise' \
' show-sandbox print CODEX_SANDBOX: read-only (or danger-full-access)' \
' check-sandbox free sandbox check; exit 0, or 3 with the reason on stderr' \
' probe-model <exec|review> [--model <id>] paid round trip; print CODEX_PROBE_STATE:; exit 0, 1, 2 or 4' \
' check-version warn on stderr about known-bad Codex CLI versions; exit 0' \
' show-first-use-notice once per machine, say where reviews go; exit 0' \
' run-with-timeout <secs> <cmd...> run cmd under a deadline; its exit code, 124 on timeout' \
' log-event <event> [detail] record a telemetry event when telemetry is on; exit 0' \
' log-hang <skill> <prompt-size> record a timeout learning; exit 0' \
' help this text'
}
# Parses "<exec|review> [--model <id>]" into _GSTACK_CODEX_ARG_KIND and
# _GSTACK_CODEX_ARG_MODEL; returns 64 on anything else.
_gstack_codex_kind_args() {
_GSTACK_CODEX_ARG_KIND="${1:-}"
_GSTACK_CODEX_ARG_MODEL=""
case "$_GSTACK_CODEX_ARG_KIND" in exec|review) shift ;; *) return 64 ;; esac
if [ "$#" -eq 2 ] && [ "$1" = "--model" ] && [ -n "$2" ]; then
_GSTACK_CODEX_ARG_MODEL="$2"
elif [ "$#" -ne 0 ]; then
return 64
fi
}
_gstack_codex_main() {
local _cmd="${1:-}" _rc
[ "$#" -gt 0 ] && shift
case "$_cmd" in
log-event|probe-model|check-sandbox|check-version)
# Telemetry is the caller's choice when it exports _TEL, else gstack-config's.
[ -n "${_TEL+set}" ] || _TEL=$("$_GSTACK_CODEX_BIN/gstack-config" get telemetry 2>/dev/null || echo off) ;;
esac
case "$_cmd" in
help|-h|--help) _gstack_codex_usage ;;
select-model)
_gstack_codex_kind_args "$@" || { _gstack_codex_usage >&2; return 64; }
_gstack_codex_select_model "$_GSTACK_CODEX_ARG_KIND" "$_GSTACK_CODEX_ARG_MODEL" || return 1
printf 'CODEX_SEL: %s\nCODEX_SEL_KIND: %s\nCODEX_SANDBOX: %s\n' "$_GSTACK_CODEX_SEL" "$_GSTACK_CODEX_SEL_KIND" "$_GSTACK_CODEX_SANDBOX" ;;
check-auth) [ "$#" -eq 0 ] || { _gstack_codex_usage >&2; return 64; }; _gstack_codex_auth_probe ;;
show-sandbox)
[ "$#" -eq 0 ] || { _gstack_codex_usage >&2; return 64; }
_gstack_codex_sandbox_mode
printf 'CODEX_SANDBOX: %s\n' "$_GSTACK_CODEX_SANDBOX" ;;
check-sandbox) [ "$#" -eq 0 ] || { _gstack_codex_usage >&2; return 64; }; _gstack_codex_sandbox_preflight >&2 ;;
probe-model)
_gstack_codex_kind_args "$@" || { _gstack_codex_usage >&2; return 64; }
if [ -n "$_GSTACK_CODEX_ARG_MODEL" ] && ! _gstack_codex_select_model "$_GSTACK_CODEX_ARG_KIND" "$_GSTACK_CODEX_ARG_MODEL"; then
echo "MODEL_UNUSABLE"
echo "HINT: the requested Codex model is not a valid model id; fix it as described above."
echo "CODEX_PROBE_STATE: unusable"
return 1
fi
_gstack_codex_model_probe "$_GSTACK_CODEX_ARG_KIND"
_rc=$?
case "$_rc" in
0) echo "CODEX_PROBE_STATE: ${_GSTACK_CODEX_PROBE_STATE:-ok}" ;;
1) echo "CODEX_PROBE_STATE: unusable" ;;
2) echo "CODEX_PROBE_STATE: broken_install" ;;
4) echo "CODEX_PROBE_STATE: quota_exhausted" ;;
*) echo "CODEX_PROBE_STATE: error" ;;
esac
return "$_rc" ;;
check-version) [ "$#" -eq 0 ] || { _gstack_codex_usage >&2; return 64; }; _gstack_codex_version_check >&2; return 0 ;;
show-first-use-notice) [ "$#" -eq 0 ] || { _gstack_codex_usage >&2; return 64; }; _gstack_codex_first_use_notice; return 0 ;;
run-with-timeout)
case "${1:-}" in ''|*[!0-9.]*) _gstack_codex_usage >&2; return 64 ;; esac
[ "$#" -ge 2 ] || { _gstack_codex_usage >&2; return 64; }
_gstack_codex_timeout_wrapper "$@" ;;
log-event) [ "$#" -ge 1 ] && _gstack_codex_log_event "$@" >/dev/null 2>&1; return 0 ;;
log-hang) _gstack_codex_log_hang "$@" >/dev/null 2>&1; return 0 ;;
*) _gstack_codex_usage >&2; return 64 ;;
esac
}
# Executed (bash through the shebang, $0 names this file): run one subcommand.
# Sourced, including eval and zsh: keep the functions and say the form is going.
if [ -n "${BASH_VERSION:-}" ] && [ "${0##*/}" = "gstack-codex-probe" ]; then
_gstack_codex_main "$@"
exit $?
fi
printf '%s\n' "gstack: sourcing gstack-codex-probe is deprecated and stops working in a release on or after 2026-10-21. Run /gstack-upgrade so your skills run it as a command (gstack-codex-probe help)." >&2