Files
gstack/test/codex-model-probe.test.ts
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

651 lines
33 KiB
TypeScript

/**
* _gstack_codex_model_probe — round-trip model readiness (#2477).
*
* The auth probe accepts "auth exists" as readiness, but a ChatGPT account
* with a model it cannot use passes auth and then dies with an HTTP 400 on
* every invocation. The model probe does one short `codex exec "reply OK"`
* round trip with gstack's selected model.
*
* Contract pinned here (all runs use a STUBBED codex binary):
* - exit 0 -> MODEL_OK, result cached (1h TTL + config/auth
* mtime signature), second call does NOT re-invoke
* - model 400 output -> MODEL_UNUSABLE (exit 1) + config.toml HINT lines,
* negative-cached 15 min (same exit-1 + hints from
* cache; re-probing every preflight charged the
* affected user 30s + real tokens per section)
* - transient failure -> MODEL_PROBE_INCONCLUSIVE, FAIL-OPEN (exit 0),
* never cached
* - usage limit / insufficient_quota on a failed call -> MODEL_QUOTA_EXHAUSTED
* (exit 4), cached 15 min; GSTACK_CODEX_PROBE_RETRY=1
* skips the cache. A plain 429 -> MODEL_PROBE_RATE_LIMITED
* (exit 0, state rate_limited), never cached. Only
* Codex's trailing ERROR / stream error lines count.
* - config.toml mtime change invalidates a cached MODEL_OK and a cached
* MODEL_UNUSABLE (editing the pin IS the fix)
* - the probed model is the runtime selection (#2914): explicit request,
* GSTACK_CODEX_MODEL, config.toml (review_model first for native review),
* then gpt-6-astra; an invalid choice never falls back to the default
* - the cache key also covers the resolved codex binary, its mtime and the
* auth mode (#2787), and never stores a credential
*/
import { describe, test, expect } from 'bun:test';
import { spawnSync } from 'child_process';
import * as fs from 'fs';
import * as os from 'os';
import * as path from 'path';
import { codexPreflight } from '../scripts/resolvers/constants';
import { withoutDeprecation } from './helpers/codex-probe-sourcing';
const ROOT = path.resolve(import.meta.dir, '..');
const PROBE = path.join(ROOT, 'bin', 'gstack-codex-probe');
const SANDBOX_FIXTURES = path.join(ROOT, 'test', 'fixtures', 'codex-sandbox');
const STUB = `#!/usr/bin/env bash
if [ "$1" = sandbox ]; then
echo "$*" >> "$STUB_LOG.sandbox"
case "\${STUB_SANDBOX:-ok}" in
ok) exit 0 ;;
userns) cat "$SANDBOX_FIXTURES/sandbox-userns-denied.stderr" >&2; exit 1 ;;
missing) cat "$SANDBOX_FIXTURES/sandbox-bwrap-missing.stderr" >&2; exit 101 ;;
unknown) echo "error: unrecognized subcommand 'sandbox'" >&2; exit 2 ;;
esac
fi
echo "invoked" >> "$STUB_LOG"
printf '%s\\n' "$*" >> "$STUB_ARGS_LOG"
case "\${STUB_MODE:-ok}" in
ok) echo "OK"; exit 0 ;;
model400)
echo 'warning: Model metadata for \`gpt-6-astra\` not found.' >&2
echo 'ERROR: {"type":"error","status":400,"error":{"type":"invalid_request_error","message":"The '"'"'gpt-6-astra'"'"' model is not supported when using Codex with a ChatGPT account."}}' >&2
exit 1 ;;
transient) echo "stream error: network unreachable" >&2; exit 7 ;;
quota)
echo "ERROR: You've hit your usage limit. Upgrade to Pro (https://chatgpt.com/explore/pro), visit https://chatgpt.com/codex/settings/usage to purchase more credits or try again at Oct 10th, 2026 2:55 AM." >&2
exit 1 ;;
ratelimit429) echo 'ERROR: {"type":"error","status":429,"error":{"type":"rate_limit_exceeded","message":"Rate limit reached"}}' >&2; exit 1 ;;
insufficientquota) echo 'ERROR: Quota exceeded. Check your plan and billing details. (insufficient_quota)' >&2; exit 1 ;;
quota429)
echo 'stream error: exceeded retry limit, last status: 429 Too Many Requests; retrying 1/5' >&2
echo 'ERROR: {"type":"error","status":429,"error":{"type":"insufficient_quota","message":"You exceeded your current quota"}}' >&2
exit 1 ;;
echoedquota)
printf 'user\nexplain why the usage limit and insufficient_quota (429) paths differ\n' >&2
echo 'ERROR: unexpected status 500 Internal Server Error' >&2
exit 1 ;;
quotaok) echo "OK (note: you are close to your usage limit)"; exit 0 ;;
ratelimitok) echo "OK"; echo "ERROR: rate limit warning from a retried request" >&2; exit 0 ;;
quotatimeout) echo "ERROR: You've hit your usage limit. Try again at 3 AM." >&2; exit 124 ;;
retired404)
echo 'ERROR: unexpected status 404 Not Found: The model \`gpt-5.2-codex\` does not exist or you do not have access to it., url: https://chatgpt.com/backend-api/codex/responses' >&2
exit 1 ;;
baseurl404) echo 'ERROR: unexpected status 404 Not Found: <html><body>Not Found</body></html>, url: http://localhost:9999/v1/responses' >&2; exit 1 ;;
outdated400)
echo 'ERROR: {"type":"error","status":400,"error":{"type":"invalid_request_error","message":"The '"'"'gpt-6-astra'"'"' model requires a newer version of Codex. Please upgrade to the latest app or CLI and try again."}}' >&2
exit 1 ;;
esac
`;
interface Fixture {
home: string;
stubDir: string;
codexHome: string;
gstackHome: string;
stubLog: string;
stubArgsLog: string;
}
function makeFixture(): Fixture {
const home = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-model-probe-'));
const stubDir = path.join(home, 'stub-bin');
const codexHome = path.join(home, '.codex');
const gstackHome = path.join(home, '.gstack');
fs.mkdirSync(stubDir, { recursive: true });
fs.mkdirSync(codexHome, { recursive: true });
fs.mkdirSync(gstackHome, { recursive: true });
fs.writeFileSync(path.join(stubDir, 'codex'), STUB, { mode: 0o755 });
fs.writeFileSync(path.join(codexHome, 'config.toml'), 'model = "gpt-5.4"\n');
fs.writeFileSync(path.join(codexHome, 'auth.json'), '{}');
const stubLog = path.join(home, 'stub.log');
const stubArgsLog = path.join(home, 'stub-args.log');
return { home, stubDir, codexHome, gstackHome, stubLog, stubArgsLog };
}
function runProbe(f: Fixture, stubMode: string, extraEnv: Record<string, string> = {}, call = '_gstack_codex_model_probe'): { stdout: string; stderr: string; status: number } {
const result = spawnSync(
'bash',
['-c', `set +e\nsource "${PROBE}"\n${call}`],
{
env: {
PATH: `${f.stubDir}:${process.env.PATH ?? ''}`,
HOME: f.home,
CODEX_HOME: f.codexHome,
GSTACK_HOME: f.gstackHome,
STUB_MODE: stubMode,
STUB_LOG: f.stubLog,
STUB_ARGS_LOG: f.stubArgsLog,
SANDBOX_FIXTURES,
_TEL: 'off',
...extraEnv,
},
timeout: 10000,
},
);
return { stdout: (result.stdout ?? '').toString(), stderr: withoutDeprecation((result.stderr ?? '').toString()), status: result.status ?? -1 };
}
function lastArgs(f: Fixture): string {
try {
const lines = fs.readFileSync(f.stubArgsLog, 'utf-8').trim().split('\n').filter(Boolean);
return lines.at(-1) ?? '';
} catch {
return '';
}
}
function invocations(f: Fixture): number {
try {
return fs.readFileSync(f.stubLog, 'utf-8').split('\n').filter(Boolean).length;
} catch {
return 0;
}
}
describe('codex model probe (#2477)', () => {
test('successful round trip -> MODEL_OK, cached, no re-invocation', () => {
const f = makeFixture();
try {
const first = runProbe(f, 'ok');
expect(first.stdout.trim()).toBe('MODEL_OK');
expect(first.status).toBe(0);
expect(invocations(f)).toBe(1);
// #2914: the fixture's config.toml chooses gpt-5.4; gstack must not override it.
expect(lastArgs(f)).toContain('-c model="gpt-5.4"');
expect(lastArgs(f)).toContain("-c skills.include_instructions=false");
expect(first.stderr).toContain(`CODEX_MODEL: gpt-5.4 (exec; source: ${path.join(f.codexHome, 'config.toml')} model)`);
expect(fs.existsSync(path.join(f.gstackHome, '.codex-model-probe'))).toBe(true);
const second = runProbe(f, 'ok');
expect(second.stdout.trim()).toBe('MODEL_OK (cached)');
expect(second.status).toBe(0);
expect(invocations(f)).toBe(1); // cache hit: stub not re-invoked
} finally {
fs.rmSync(f.home, { recursive: true, force: true });
}
});
test('model 400 -> MODEL_UNUSABLE with selected-model hints, exit 1, negative-cached', () => {
const f = makeFixture();
try {
const r = runProbe(f, 'model400');
expect(r.stdout).toContain('MODEL_UNUSABLE');
expect(r.stdout).toContain('gstack requested model');
expect(r.stdout).toContain('GSTACK_CODEX_MODEL');
// Surfaces the actual rejection so the user sees WHICH model and why it was chosen.
expect(r.stdout).toContain("gstack requested model 'gpt-5.4'");
expect(r.stdout).toContain('config.toml model');
expect(r.status).toBe(1);
// The deterministic 400 is config-driven: re-probing every preflight
// charged the user a 30s round trip + real tokens per review section.
// A second run within the 15-min TTL must NOT re-invoke codex, and must
// keep the exit-1 + hints contract so callers can't tell the difference.
expect(invocations(f)).toBe(1);
const second = runProbe(f, 'model400');
expect(second.stdout).toContain('MODEL_UNUSABLE (cached)');
expect(second.stdout).toContain('GSTACK_CODEX_MODEL');
expect(second.status).toBe(1);
expect(invocations(f)).toBe(1);
} finally {
fs.rmSync(f.home, { recursive: true, force: true });
}
});
test('GSTACK_CODEX_MODEL change re-probes past a cached MODEL_UNUSABLE (the recovery path)', () => {
const f = makeFixture();
try {
runProbe(f, 'model400');
expect(invocations(f)).toBe(1);
// Fixing the gstack model override changes the cache signature — the
// negative cache must not outlive the model it condemned.
const r = runProbe(f, 'ok', { GSTACK_CODEX_MODEL: 'gpt-5.6-sol' });
expect(r.stdout.trim()).toBe('MODEL_OK');
expect(r.status).toBe(0);
expect(invocations(f)).toBe(2);
expect(lastArgs(f)).toContain('-c model="gpt-5.6-sol"');
} finally {
fs.rmSync(f.home, { recursive: true, force: true });
}
});
test('transient failure -> inconclusive, FAIL-OPEN exit 0', () => {
const f = makeFixture();
try {
const r = runProbe(f, 'transient');
expect(r.stdout).toContain('MODEL_PROBE_INCONCLUSIVE');
expect(r.status).toBe(0);
} finally {
fs.rmSync(f.home, { recursive: true, force: true });
}
});
test('TTL expiry: a cached MODEL_OK older than 3600s re-probes (T5)', () => {
const f = makeFixture();
try {
runProbe(f, 'ok');
expect(invocations(f)).toBe(1);
// Backdate the cache line's timestamp past the 1h TTL, keeping the
// signature valid — TTL alone must force the re-probe.
const cachePath = path.join(f.gstackHome, '.codex-model-probe');
const [status, ts, sig] = fs.readFileSync(cachePath, 'utf-8').trim().split(' ');
expect(status).toBe('MODEL_OK');
fs.writeFileSync(cachePath, `MODEL_OK ${Number(ts) - 3700} ${sig}\n`);
const r = runProbe(f, 'ok');
expect(r.stdout.trim()).toBe('MODEL_OK'); // not "(cached)"
expect(invocations(f)).toBe(2); // re-probed
} finally {
fs.rmSync(f.home, { recursive: true, force: true });
}
});
test('auth.json mtime change invalidates the cached MODEL_OK (T5: re-login re-probes)', () => {
const f = makeFixture();
try {
runProbe(f, 'ok');
expect(invocations(f)).toBe(1);
// A re-login rewrites auth.json; the mtime signature must invalidate
// the cache even though config.toml is untouched.
const future = Date.now() / 1000 + 10;
fs.utimesSync(path.join(f.codexHome, 'auth.json'), future, future);
const r = runProbe(f, 'ok');
expect(r.stdout.trim()).toBe('MODEL_OK');
expect(invocations(f)).toBe(2); // re-probed
} finally {
fs.rmSync(f.home, { recursive: true, force: true });
}
});
test('config.toml change invalidates the cached MODEL_OK', () => {
const f = makeFixture();
try {
runProbe(f, 'ok');
expect(invocations(f)).toBe(1);
// Change the model pin; mtime signature must invalidate the cache.
fs.writeFileSync(path.join(f.codexHome, 'config.toml'), 'model = "gpt-5.5"\n');
const future = Date.now() / 1000 + 10;
fs.utimesSync(path.join(f.codexHome, 'config.toml'), future, future);
const r = runProbe(f, 'ok');
expect(r.stdout.trim()).toBe('MODEL_OK');
expect(invocations(f)).toBe(2); // re-probed
} finally {
fs.rmSync(f.home, { recursive: true, force: true });
}
});
test('#2914: precedence is explicit request, GSTACK_CODEX_MODEL, config.toml, then gpt-6-astra', () => {
const f = makeFixture();
try {
fs.writeFileSync(path.join(f.codexHome, 'config.toml'), 'model = "gpt-5.6-terra"\nreview_model = "gpt-5.6-luna"\n');
const sel = (env: Record<string, string>, call: string) =>
runProbe(f, 'ok', env, `${call}; printf '%s|%s\\n' "$_GSTACK_CODEX_SEL" "$_GSTACK_CODEX_SEL_SRC"`).stdout.trim();
const config = path.join(f.codexHome, 'config.toml');
expect(sel({}, '_gstack_codex_select_model exec')).toBe(`gpt-5.6-terra|${config} model`);
expect(sel({}, '_gstack_codex_select_model review')).toBe(`gpt-5.6-luna|${config} review_model`);
expect(sel({ GSTACK_CODEX_MODEL: 'gpt-6-sol' }, '_gstack_codex_select_model review')).toBe('gpt-6-sol|GSTACK_CODEX_MODEL');
expect(sel({ GSTACK_CODEX_MODEL: 'gpt-6-sol' }, "_gstack_codex_select_model exec 'gpt-6-luna'")).toBe('gpt-6-luna|explicit request');
// An id with no dedicated prompt overlay is still passed through unchanged.
fs.writeFileSync(config, 'model = "acme/custom-model:2026-09"\n');
expect(sel({}, '_gstack_codex_select_model review')).toBe(`acme/custom-model:2026-09|${config} model`);
fs.rmSync(config);
expect(sel({}, '_gstack_codex_select_model exec')).toBe(`gpt-6-astra|gstack default (no ${config})`);
expect(invocations(f)).toBe(0); // selection alone never spends a call
} finally {
fs.rmSync(f.home, { recursive: true, force: true });
}
});
test('#2914: native review probes its own review_model selection', () => {
const f = makeFixture();
try {
fs.writeFileSync(path.join(f.codexHome, 'config.toml'), 'model = "gpt-5.6-terra"\nreview_model = "gpt-5.6-luna"\n');
const r = runProbe(f, 'ok', {}, '_gstack_codex_model_probe review');
expect(r.status).toBe(0);
expect(lastArgs(f)).toContain('-c model="gpt-5.6-luna"');
expect(r.stderr).toContain('CODEX_MODEL: gpt-5.6-luna (review; source:');
} finally {
fs.rmSync(f.home, { recursive: true, force: true });
}
});
for (const [label, env, config] of [
['an injection-shaped GSTACK_CODEX_MODEL', { GSTACK_CODEX_MODEL: 'gpt"; touch PWNED; "' }, 'model = "gpt-5.4"\n'],
['an invalid config.toml model', {}, 'model = "has space"\n'],
['an unparseable config.toml', {}, 'model = \n'],
] as const) {
test(`#2914: ${label} is a repair message, never a silent frontier fallback`, () => {
const f = makeFixture();
try {
fs.writeFileSync(path.join(f.codexHome, 'config.toml'), config);
const r = runProbe(f, 'ok', { ...env });
expect(r.status).toBe(1);
expect(r.stdout).toContain('MODEL_UNUSABLE');
expect(r.stderr).toContain('GSTACK_CODEX_MODEL=<model>');
expect(r.stderr).toContain('No Codex call was made');
expect(r.stderr).not.toContain('CODEX_MODEL: gpt-6-astra');
expect(invocations(f)).toBe(0);
expect(fs.existsSync(path.join(f.home, 'PWNED'))).toBe(false);
} finally {
fs.rmSync(f.home, { recursive: true, force: true });
}
});
}
test('#2787: swapping the codex binary or its mtime invalidates a cached MODEL_OK', () => {
const f = makeFixture();
try {
runProbe(f, 'ok');
expect(runProbe(f, 'ok').stdout.trim()).toBe('MODEL_OK (cached)');
// A different codex earlier on PATH (an upgrade or a second install).
const other = path.join(f.home, 'other-bin');
fs.mkdirSync(other);
fs.writeFileSync(path.join(other, 'codex'), STUB, { mode: 0o755 });
const swapped = runProbe(f, 'ok', { PATH: `${other}:${f.stubDir}:${process.env.PATH ?? ''}` });
expect(swapped.stdout.trim()).toBe('MODEL_OK');
expect(invocations(f)).toBe(2);
// Reinstalling in place keeps the path but moves the mtime.
const future = Date.now() / 1000 + 10;
fs.utimesSync(path.join(f.stubDir, 'codex'), future, future);
expect(runProbe(f, 'ok').stdout.trim()).toBe('MODEL_OK');
expect(invocations(f)).toBe(3);
} finally {
fs.rmSync(f.home, { recursive: true, force: true });
}
});
test('#2787: switching to env-var auth invalidates the cache without persisting the key', () => {
const f = makeFixture();
try {
runProbe(f, 'ok');
const secret = 'sk-test-SHOULD-NOT-PERSIST-abcdefghij';
const r = runProbe(f, 'ok', { OPENAI_API_KEY: secret });
expect(r.stdout.trim()).toBe('MODEL_OK');
expect(invocations(f)).toBe(2);
expect(runProbe(f, 'ok', { OPENAI_API_KEY: secret }).stdout.trim()).toBe('MODEL_OK (cached)');
expect(fs.readFileSync(path.join(f.gstackHome, '.codex-model-probe'), 'utf-8')).not.toContain(secret);
// A different Codex home is a different configuration identity.
const otherHome = path.join(f.home, 'codex-two');
fs.cpSync(f.codexHome, otherHome, { recursive: true, preserveTimestamps: true });
expect(runProbe(f, 'ok', { OPENAI_API_KEY: secret, CODEX_HOME: otherHome }).stdout.trim()).toBe('MODEL_OK');
expect(invocations(f)).toBe(3);
} finally {
fs.rmSync(f.home, { recursive: true, force: true });
}
});
});
describe('B1: codex sandbox preflight and unverified readiness', () => {
const unavailable = (detail: string) =>
`Codex outside review unavailable: Codex's sandbox could not start here (${detail}). 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.`;
for (const [mode, detail] of [
['userns', 'bwrap: No permissions to create new namespace, likely because the kernel does not allow non-privileged user namespaces. See <https://deb.li/bubblewrap> or <file:///usr/share/doc/bubblewrap/README.Debian.gz>.'.slice(0, 240)],
['missing', 'bubblewrap is unavailable: no system bwrap was found on PATH and no bundled codex-resources/bwrap binary was found next to the Codex executable'],
] as const) {
test(`captured ${mode} failure -> sandbox unavailable (exit 3), named like the gate outcome`, () => {
const f = makeFixture();
try {
const r = runProbe(f, 'ok', { STUB_SANDBOX: mode }, '_gstack_codex_sandbox_preflight; echo "rc=$?"');
expect(r.stdout).toBe('CODEX_SANDBOX: unavailable\nrc=3\n');
expect(r.stderr.trim()).toBe(unavailable(detail));
expect(fs.readFileSync(`${f.stubLog}.sandbox`, 'utf-8')).toBe(`sandbox -c sandbox_mode="read-only" true\n`);
expect(invocations(f)).toBe(0);
} finally { fs.rmSync(f.home, { recursive: true, force: true }); }
});
}
test('a healthy sandbox, an older CLI without the subcommand, or a timeout defers to the post-run check', () => {
const f = makeFixture();
try {
for (const mode of ['ok', 'unknown']) {
const r = runProbe(f, 'ok', { STUB_SANDBOX: mode }, '_gstack_codex_sandbox_preflight; echo "rc=$?"');
expect(r.stdout).toBe('rc=0\n');
expect(r.stderr).toBe('');
}
const timedOut = runProbe(f, 'ok', { STUB_SANDBOX: 'userns' },
'_gstack_codex_timeout_wrapper() { return 124; }; _gstack_codex_sandbox_preflight; echo "rc=$?"');
expect(timedOut.stdout).toBe('rc=0\n');
} finally { fs.rmSync(f.home, { recursive: true, force: true }); }
});
test('GSTACK_CODEX_NO_SANDBOX: exactly 1 selects full access with a warning each use; other values keep read-only', () => {
const f = makeFixture();
try {
const warning = 'WARNING: GSTACK_CODEX_NO_SANDBOX=1: Codex runs this review without a sandbox and can read and write anything your user can. Use it only inside a container you trust.';
const on = runProbe(f, 'ok', { GSTACK_CODEX_NO_SANDBOX: '1', STUB_SANDBOX: 'userns' },
'_gstack_codex_select_model exec; echo "sandbox=$_GSTACK_CODEX_SANDBOX"; _gstack_codex_select_model exec; _gstack_codex_sandbox_preflight; echo "rc=$?"');
expect(on.stdout).toBe('sandbox=danger-full-access\nrc=0\n');
expect(on.stderr.split(warning).length - 1).toBe(2);
expect(fs.existsSync(`${f.stubLog}.sandbox`)).toBe(false);
for (const value of ['', 'true', 'yes', '0', '1 ']) {
const off = runProbe(f, 'ok', { GSTACK_CODEX_NO_SANDBOX: value }, '_gstack_codex_select_model exec; echo "sandbox=$_GSTACK_CODEX_SANDBOX"');
expect(off.stdout).toBe('sandbox=read-only\n');
expect(off.stderr).not.toContain('WARNING');
}
} finally { fs.rmSync(f.home, { recursive: true, force: true }); }
});
test('the preflight runs only on Linux', () => {
const f = makeFixture();
try {
fs.writeFileSync(path.join(f.stubDir, 'uname'), '#!/usr/bin/env bash\necho Darwin\n', { mode: 0o755 });
const r = runProbe(f, 'ok', { STUB_SANDBOX: 'userns' }, '_gstack_codex_sandbox_preflight; echo "rc=$?"');
expect(r.stdout).toBe('rc=0\n');
expect(fs.existsSync(`${f.stubLog}.sandbox`)).toBe(false);
} finally { fs.rmSync(f.home, { recursive: true, force: true }); }
});
test('an inconclusive model probe marks readiness unverified without blocking stale callers', () => {
const f = makeFixture();
try {
const r = runProbe(f, 'transient', {}, '_gstack_codex_model_probe; echo "rc=$? state=${_GSTACK_CODEX_PROBE_STATE:-}"');
expect(r.stdout).toContain('CODEX_MODE: unverified');
expect(r.stdout).toContain('rc=0 state=inconclusive');
const ok = runProbe(f, 'ok', {}, '_gstack_codex_model_probe; echo "state=${_GSTACK_CODEX_PROBE_STATE:-none}"');
expect(ok.stdout).toContain('state=none');
} finally { fs.rmSync(f.home, { recursive: true, force: true }); }
});
test('the rendered preflight reports sandbox_unavailable before any paid probe, and unverified on an inconclusive probe', () => {
const block = codexPreflight({ disabledBehavior: 'codex-only' }).match(/```bash\n([\s\S]*?)\n```/)![1];
for (const [sandbox, model, mode, probed] of [
['userns', 'ok', 'sandbox_unavailable', 0],
['ok', 'transient', 'unverified', 1],
['ok', 'ok', 'ready', 1],
['ok', 'model400', 'model_unusable', 1],
['ok', 'quota', 'quota_exhausted', 1],
['ok', 'ratelimit429', 'unverified (rate_limited)', 1],
] as const) {
const f = makeFixture();
try {
fs.mkdirSync(path.join(f.home, '.claude', 'skills'), { recursive: true });
fs.symlinkSync(ROOT, path.join(f.home, '.claude', 'skills', 'gstack'));
const r = spawnSync('bash', ['-c', block], { encoding: 'utf8', timeout: 20000, env: {
PATH: `${f.stubDir}:${process.env.PATH ?? ''}`, HOME: f.home, CODEX_HOME: f.codexHome, GSTACK_HOME: f.gstackHome,
STUB_MODE: model, STUB_SANDBOX: sandbox, STUB_LOG: f.stubLog, STUB_ARGS_LOG: f.stubArgsLog, SANDBOX_FIXTURES } });
expect(r.stdout).toContain(`CODEX_MODE: ${mode}`);
const paid = fs.existsSync(f.stubArgsLog) ? fs.readFileSync(f.stubArgsLog, 'utf-8').split('\n').filter(l => l.includes('reply OK')).length : 0;
expect(paid).toBe(probed);
} finally { fs.rmSync(f.home, { recursive: true, force: true }); }
}
});
});
const QUOTA_LINE = "try again at Oct 10th, 2026 2:55 AM";
const DOCS = 'https://github.com/garrytan/gstack/blob/main/docs/troubleshooting.md';
describe('a Codex usage limit is quota_exhausted; a plain 429 is rate_limited', () => {
for (const mode of ['quota', 'insufficientquota', 'quota429'] as const) {
test(`${mode} -> MODEL_QUOTA_EXHAUSTED, exit 4, Codex's own line relayed, cached 15 min, event logged`, () => {
const f = makeFixture();
try {
const r = runProbe(f, mode, { _TEL: 'community' }, '_gstack_codex_model_probe; echo "rc=$?"');
expect(r.stdout).toContain('MODEL_QUOTA_EXHAUSTED');
expect(r.stdout).toContain('rc=4');
expect(r.stdout).not.toContain('MODEL_PROBE_INCONCLUSIVE');
expect(r.stdout).not.toContain('RATE_LIMITED');
expect(r.stdout).not.toContain('MODEL_UNUSABLE');
if (mode === 'quota') expect(r.stdout).toContain(QUOTA_LINE);
expect(r.stdout).toContain('gstack skips Codex for 15 minutes. Retry now: GSTACK_CODEX_PROBE_RETRY=1');
expect(r.stdout).toContain(`${DOCS}#codex-quota-exhausted`);
expect(fs.readFileSync(path.join(f.gstackHome, 'analytics', 'skill-usage.jsonl'), 'utf-8')).toContain('"event":"codex_quota_exhausted"');
const again = runProbe(f, 'ok', {}, '_gstack_codex_model_probe; echo "rc=$?"');
expect(again.stdout).toContain('MODEL_QUOTA_EXHAUSTED (cached)');
expect(again.stdout).toContain('rc=4');
expect(again.stdout).toMatch(/gstack skips Codex for 1[45] more minute\(s\)\. Retry now: GSTACK_CODEX_PROBE_RETRY=1, or delete \S+\.codex-model-probe\./);
if (mode === 'quota') expect(again.stdout).toContain(QUOTA_LINE);
expect(invocations(f)).toBe(1);
} finally { fs.rmSync(f.home, { recursive: true, force: true }); }
});
}
test('a plain 429 -> MODEL_PROBE_RATE_LIMITED: exit 0, state rate_limited, line relayed, never cached', () => {
const f = makeFixture();
try {
const r = runProbe(f, 'ratelimit429', { _TEL: 'community' }, '_gstack_codex_model_probe; echo "rc=$? state=${_GSTACK_CODEX_PROBE_STATE:-}"');
expect(r.stdout).toContain('MODEL_PROBE_RATE_LIMITED — CODEX_MODE: unverified (rate_limited)');
expect(r.stdout).toContain('"status":429');
expect(r.stdout).toContain(`${DOCS}#codex-rate-limited`);
expect(r.stdout).toContain('rc=0 state=rate_limited');
expect(r.stdout).not.toContain('QUOTA');
expect(fs.readFileSync(path.join(f.gstackHome, 'analytics', 'skill-usage.jsonl'), 'utf-8')).toContain('"event":"codex_rate_limited"');
const again = runProbe(f, 'ok', {}, '_gstack_codex_model_probe; echo "rc=$?"');
expect(again.stdout).toContain('MODEL_OK');
expect(again.stdout).not.toContain('cached');
expect(invocations(f)).toBe(2);
} finally { fs.rmSync(f.home, { recursive: true, force: true }); }
});
test("an echoed prompt that names usage limit, insufficient_quota and 429 is not Codex's error", () => {
const f = makeFixture();
try {
const r = runProbe(f, 'echoedquota', {}, '_gstack_codex_model_probe; echo "rc=$? state=${_GSTACK_CODEX_PROBE_STATE:-}"');
expect(r.stdout).toContain('MODEL_PROBE_INCONCLUSIVE');
expect(r.stdout).toContain('rc=0 state=inconclusive');
expect(r.stdout).not.toContain('QUOTA');
expect(r.stdout).not.toContain('RATE_LIMITED');
} finally { fs.rmSync(f.home, { recursive: true, force: true }); }
});
for (const mode of ['quotaok', 'ratelimitok'] as const) {
test(`a successful call that mentions a limit (${mode}) stays MODEL_OK`, () => {
const f = makeFixture();
try {
const r = runProbe(f, mode, {}, '_gstack_codex_model_probe; echo "rc=$?"');
expect(r.stdout).toContain('MODEL_OK');
expect(r.stdout).toContain('rc=0');
} finally { fs.rmSync(f.home, { recursive: true, force: true }); }
});
}
test('a timeout that printed a usage-limit line keeps the inconclusive contract', () => {
const f = makeFixture();
try {
const r = runProbe(f, 'quotatimeout', {}, '_gstack_codex_model_probe; echo "rc=$? state=${_GSTACK_CODEX_PROBE_STATE:-}"');
expect(r.stdout).toContain('MODEL_PROBE_INCONCLUSIVE (exit 124)');
expect(r.stdout).toContain('rc=0 state=inconclusive');
expect(r.stdout).not.toContain('QUOTA');
} finally { fs.rmSync(f.home, { recursive: true, force: true }); }
});
test('GSTACK_CODEX_PROBE_RETRY=1 re-checks past a cached quota result without touching model, config or credentials', () => {
const f = makeFixture();
try {
runProbe(f, 'quota');
const before = ['config.toml', 'auth.json'].map(name => fs.statSync(path.join(f.codexHome, name)).mtimeMs);
expect(runProbe(f, 'ok', {}, '_gstack_codex_model_probe; echo "rc=$?"').stdout).toContain('MODEL_QUOTA_EXHAUSTED (cached)');
const r = runProbe(f, 'ok', { GSTACK_CODEX_PROBE_RETRY: '1' }, '_gstack_codex_model_probe; echo "rc=$?"');
expect(r.stdout).toContain('MODEL_OK');
expect(r.stdout).toContain('rc=0');
expect(invocations(f)).toBe(2);
expect(lastArgs(f)).toContain('model="gpt-5.4"');
expect(['config.toml', 'auth.json'].map(name => fs.statSync(path.join(f.codexHome, name)).mtimeMs)).toEqual(before);
expect(runProbe(f, 'ok', {}, '_gstack_codex_model_probe').stdout).toContain('MODEL_OK (cached)');
} finally { fs.rmSync(f.home, { recursive: true, force: true }); }
});
test('re-login (auth.json change) re-probes past a cached quota result', () => {
const f = makeFixture();
try {
runProbe(f, 'quota');
const future = new Date(Date.now() + 5000);
fs.utimesSync(path.join(f.codexHome, 'auth.json'), future, future);
const r = runProbe(f, 'ok', {}, '_gstack_codex_model_probe; echo "rc=$?"');
expect(r.stdout).toContain('MODEL_OK');
expect(invocations(f)).toBe(2);
} finally { fs.rmSync(f.home, { recursive: true, force: true }); }
});
test('two fresh-shell preflight blocks in one run: the second makes no paid Codex call after a quota refusal', () => {
const block = codexPreflight({ disabledBehavior: 'skip-all' }).match(/```bash\n([\s\S]*?)\n```/)![1]!;
const f = makeFixture();
try {
fs.mkdirSync(path.join(f.home, '.claude', 'skills'), { recursive: true });
fs.symlinkSync(ROOT, path.join(f.home, '.claude', 'skills', 'gstack'));
const env = { PATH: `${f.stubDir}:${process.env.PATH ?? ''}`, HOME: f.home, CODEX_HOME: f.codexHome, GSTACK_HOME: f.gstackHome,
STUB_LOG: f.stubLog, STUB_ARGS_LOG: f.stubArgsLog, SANDBOX_FIXTURES };
const first = spawnSync('bash', ['-c', block], { encoding: 'utf8', timeout: 20000, env: { ...env, STUB_MODE: 'quota' } });
expect(first.stdout).toContain('CODEX_MODE: quota_exhausted');
expect(invocations(f)).toBe(1);
const second = spawnSync('bash', ['-c', block], { encoding: 'utf8', timeout: 20000, env: { ...env, STUB_MODE: 'ok' } });
expect(second.stdout).toContain('MODEL_QUOTA_EXHAUSTED (cached)');
expect(second.stdout).toContain(QUOTA_LINE);
expect(second.stdout).toContain('CODEX_MODE: quota_exhausted');
expect(invocations(f)).toBe(1);
} finally { fs.rmSync(f.home, { recursive: true, force: true }); }
});
});
describe('B2: a 404 model rejection is unusable, never ready (#2843)', () => {
for (const [mode, hint, event] of [
['retired404', "Codex answered 404: either the model is retired or not visible to this account, or a custom provider's base_url", 'codex_model_retired'],
['baseurl404', "a custom provider's base_url", 'codex_model_retired'],
['outdated400', 'this Codex CLI is too old', 'codex_cli_outdated'],
] as const) {
test(`${mode} -> MODEL_UNUSABLE with a hint naming the cause and a ${event} event`, () => {
const f = makeFixture();
try {
const r = runProbe(f, mode, { _TEL: 'community' }, '_gstack_codex_model_probe; echo "rc=$?"');
expect(r.stdout).toContain('MODEL_UNUSABLE');
expect(r.stdout).toContain('rc=1');
expect(r.stdout).not.toContain('MODEL_PROBE_INCONCLUSIVE');
expect(r.stdout).toContain(hint);
expect(fs.readFileSync(path.join(f.gstackHome, 'analytics', 'skill-usage.jsonl'), 'utf-8')).toContain(`"event":"${event}"`);
} finally { fs.rmSync(f.home, { recursive: true, force: true }); }
});
}
});
describe('Q2: one-time outside-review notice (#965)', () => {
test('names the account source per auth mode, never the credential, and shows once per state root', () => {
for (const [env, files, account] of [
[{ CODEX_API_KEY: 'sk-codex-secret' }, {}, 'the API key in CODEX_API_KEY'],
[{ OPENAI_API_KEY: 'sk-openai-secret' }, {}, 'the API key in OPENAI_API_KEY'],
[{}, { 'auth.json': '{"auth_mode":"chatgpt","tokens":{"id_token":"secret-token"}}' }, 'the ChatGPT account Codex is logged in with'],
[{}, { 'auth.json': '{"auth_mode":"apikey","OPENAI_API_KEY":"sk-file-secret"}' }, 'the API key saved by codex login'],
[{}, { 'config.toml': 'model_provider = "mimo"\n[model_providers.mimo]\nenv_key = "MIMO_API_KEY"\n' }, 'Codex (provider: mimo) using the credentials your Codex config.toml provider names'],
] as const) {
const f = makeFixture();
try {
fs.rmSync(path.join(f.codexHome, 'auth.json'));
fs.rmSync(path.join(f.codexHome, 'config.toml'));
for (const [name, body] of Object.entries(files)) fs.writeFileSync(path.join(f.codexHome, name), body);
const first = runProbe(f, 'ok', { ...env }, '_gstack_codex_first_use_notice; echo "rc=$?"');
expect(first.stdout).toBe('rc=0\n');
expect(first.stderr).toContain(account);
expect(first.stderr).toContain('To turn them off: gstack-config set codex_reviews disabled');
expect(first.stderr).not.toMatch(/secret/);
expect(fs.existsSync(path.join(f.gstackHome, '.codex-review-notice-shown'))).toBe(true);
expect(runProbe(f, 'ok', { ...env }, '_gstack_codex_first_use_notice').stderr).toBe('');
} finally { fs.rmSync(f.home, { recursive: true, force: true }); }
}
});
});