Every skill's voice directive now tells the agent to reply in the language
of the user's latest message unless asked otherwise, so long English skill
text no longer drags a Chinese (or any non-English) session into English.
Mixed-language sessions follow the latest message. Code, commands, paths,
identifiers and quoted output stay verbatim, and at tier 2+ so do the
machine-read question markers (D<N>, option letters, (recommended)).
The rule costs 205 bytes per tier-2+ skill and 144 per tier-1 skill. A
further 25-byte cut to the bounded closer's exemption list leaves the net
for this wave at +17 bytes per tier-2+ skill and +158 per tier-1 skill.
review, qa and browse caps rise with measured notes; the ship goldens are
refreshed.
Co-authored-by: Xianying Tan <shrektan@126.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Models overuse "load-bearing"; it joins the AI-vocabulary ban line in both
voice tiers. The tier-2 voice directive is also tightened (the meta
"compressed for runtime" tag and the bounded closer's restated exemption
clause) so the shared preamble shrinks by 163 bytes per tier-2+ skill,
which also pays for the reply-language rule that follows. The ship goldens
are refreshed for the new render.
Co-authored-by: Nader Helmy <creator.nader@gmail.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
On the Codex host, /design-shotgun now generates and edits mockups with
Codex's documented $imagegen skill in its default built-in mode (the
image_gen tool), so users signed in with ChatGPT need no OPENAI_API_KEY.
The design binary stays for the local comparison board only, images are
published with gstack-design-claim as before, and screenshot evolution
loads the captured page with view_image before an $imagegen edit.
Step 3c-3d moved into a DESIGN_SHOTGUN_GENERATION resolver that returns
the existing design-binary text unchanged for every other host; the
Claude output differs only in two host-neutral rewordings of the
evolve-from-screenshot pointers. DESIGN_SETUP and the regenerate step of
the board loop gain matching Codex-only text for design-shotgun.
Co-authored-by: Jinzhe <hwang.phy@gmail.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
The sidebar terminal toolbar gets an XS-XL text-size picker beside
Restart. SM (13px) stays the default, so nothing changes until a user
picks a size; the choice persists in chrome.storage.local and applies
to the live terminal, re-fitting xterm and re-sending the PTY size two
frames later so the new character cell is measured first.
A VM test runs the real sidepanel-terminal.js through one auto-connect
and checks the creation size, the stored-size fallback, persistence and
the live resize.
Co-authored-by: Yotam <yotsurfing@gmail.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
/design-review read only DESIGN.md and otherwise fell back to universal
principles, so a project whose system lives in CSS custom properties,
tailwind.config or a theme file got audited and mocked up against an
invented aesthetic. The skill now reads code tokens before falling back,
and the target-mockup brief reuses the captured colors, fonts, radii and
spacing, changing layout only.
The contributor's optional microcopy checks (domain vocabulary, human
register) are not adopted here.
Co-authored-by: Tom Lam <tomlam0811@berkeley.edu>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
The checklist now says a clean diff may come back clean, and suppresses
framework-owned error handling, long exhaustive switches, null derefs a
type guard already narrows, N+1 on fixed-cardinality loops, hardcoded test
fixture values and non-cryptographic Math.random().
The contributor's "missing input validation on an internal function" and
"missing await on fire-and-forget" suppressions are left out: both can hide
real bugs.
Co-authored-by: frosimanuel <frosimanuel@gmail.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Four access-control classes where the guard is correct and the object still
leaks: error pages composed outside the guard, ownership surviving a role
downgrade, list/detail/download paths checked as one, and a session mutated
before the identity-switch callback is validated.
Adopted to review/specialists/security.md only; the /cso hunk targeted a
bullet list that is now an OWASP/ASVS table.
Co-authored-by: EmilianoU26 <314541067+EmilianoU26@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
A new assertion that something is absent records a behavior removal and
needs cited intent. A rename or removal in the diff can empty a standing
negative assertion so it passes forever; the specialist now greps the suite
for negative assertions naming the old value.
Adopted from the testing-specialist part of a community PR; the scope-check
hunk targeted text that no longer exists.
Co-authored-by: EmilianoU26 <314541067+EmilianoU26@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
One resolver, openaiUrl() in design/src/auth.ts, now builds every OpenAI
URL the design binary, its prototype and its live model check use. Setting
OPENAI_BASE_URL sends image generation and screenshot analysis to an
OpenAI-compatible gateway; unset or blank keeps api.openai.com. The
prototype script now goes through receiptedFetch, so its egress is
receipted like the rest, and receipts already record the gateway host.
A source scan keeps any design file outside auth.ts from hardcoding an
OpenAI API URL again, and a request-shape test proves the gateway reaches
both the vision and image endpoints.
Co-authored-by: JackJin <1037461232@qq.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(timeline): reject a missing or malformed --limit with exit 2 (#1723)
gstack-timeline-read parsed --limit with parseInt and fell back to 20, so
'--limit 1abc' became 1, 'nope', 0 and -5 silently became the default, and a
bare --limit crashed on an unbound $2. Validate the argument as a positive
integer before the no-timeline early exit and exit 2 with an example. No flag
still means 20.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(skill-start): echo SESSIONS, the live session-marker count (#1651)
The sessions directory is touched and expired at skill start, but the count
was never printed, so CLAUDE.md rules that read the preamble's session count
had nothing to read. Echo SESSIONS: N (markers fresher than 120 minutes,
this session included). Idea from @0xDevNinja's PR #1747, redone in the
consolidated skill-start script.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(office-hours): pick the closing tier from the profile read before this session is logged (#2801)
Phase 4.5 appended this session to the builder profile and Phase 6 then read
the profile to choose its closing, so every run saw itself as history: a
first-time user got welcome_back and was asked how the assignment issued
minutes earlier went. Phase 4.5 now reads the profile before --log-session and
records the prior tier, count and last-session fields in the transcript;
Phase 6 uses those values (this session is prior + 1) and re-reads only the
running totals. A failed read proceeds as a first session and says so. Tier
headers now name the session numbers each tier actually covers.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(office-hours): print the full design doc inline before asking for approval (#879)
Tool output collapses in Claude Code, so users were asked to approve a doc
they could not see. Port of @RyanAlberts's PR #1116 into the carved
design-and-handoff section.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(office-hours): report success only when this run wrote its design doc (#1049)
Before telemetry, check the design doc this run wrote, by its exact path under
the state root, never the newest file in the folder. Success needs a
non-empty doc there; otherwise the outcome is abort or error with failed step
design_doc. Rewrite of @walton-chris's PR #1049, which matched the newest
global session marker and hardcoded ~/.gstack.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(plan reviews): skip the /office-hours prerequisite offer in spawned and headless sessions (#1958)
The BENEFITS_FROM offer had no recommended option, so a spawned run had
nothing defined to auto-pick and a headless run could only block. Skip it
there and continue with the standard review.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore: regenerate SKILL.md files
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: office-hours tier order, failed-read fallback, inline doc, design-doc check and offer skip
Rendered-block tests run the Phase 4.5 read and log on a temp state root
(first session reads introduction, failed read is marked) and the
pre-telemetry check against this run's doc, an empty doc, another session's
doc and a path outside the state root. Parity caps take the measured growth.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore(release): v1.91.37.0 changelog and TODOS
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(browse): run watchdog test servers under a private HOME
The headed-mode case starts a real server with BROWSE_HEADED=1, and its
headed launch writes ~/.gstack/.auth.json for the extension. With the
caller's HOME, a slow kill let that write reach the real home and failed the
free runner's home-containment check (free-suite shard 5 on #3075). Give each
spawned server a private HOME and GSTACK_HOME, keeping Playwright's browser
cache path.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(evals): name the office-hours-auto-mode case so the PR lane can select it
The PR lane runs each short probe with a Bun name pattern ending in its case
id. The office-hours AskUserQuestion-blocked smoke had a descriptive test
name and no CASE_TEST_NAMES label, so whenever office-hours changed its shard
matched 0 tests and failed in 0 s (E2E Evals slice 6 on #3075). Name the
test after its id, keep the description on the describe, and check that
every literal-named PR probe has a test the pattern selects.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(office-hours): skip a last-session greeting clause whose value is empty
A profile backfilled from the timeline can carry a welcome_back or regular
tier with empty LAST_ASSIGNMENT and LAST_PROJECT. The welcome_back and
regular greetings now drop the "last time" clause and its question when the
value it names is empty, and say only "Welcome back."
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(qa-quick): run the fixture in a committed git repository
/qa runs inside a repository: its clean-tree check and the evidence
recorder's revision come from git. The qa-quick working directory was a
bare temp dir, so all 15 CI transcripts read (runs 37374409928 to
37744583272) hit 'revision is required when git rev-parse HEAD is
unavailable' on the first materialize and spent a retry (6-46 s) plus a
learnings-log of the pitfall. qa-only-no-fix already commits its fixture.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(qa-quick): scope Quick to the fixture page, not its 404 links
basic.html's /page1 and /page2 links 404 on the test server. With the
links in scope, the 15 CI transcripts spent 55-75 s of the 30 s caller
probe window and its wrap-up navigating, screenshotting and checkpointing
those 404s, then triaging and reporting them as issues. The case proves
/qa Quick completes end to end (fallback browser, deadline guard,
checkpoint, evidence materialize, report); link-following and defect
detection are covered by the qa-b6/b7/b8 and qa-fix-loop cases. The
links are now listed as untested coverage.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(qa): say that annotations.json limits is a non-empty string array
exploratory.md §4 gave the annotations shape as {evidence: [...], limits}
with 'checkpoints in limits', but never said what type limits is. The
materialize validator (lib/qa-evidence.ts) wants a non-empty array of
strings. In 11 of 15 qa-quick CI transcripts the agent's first
annotations.json wrote limits as an object, failed with 'need limits
(non-empty string array)', and spent a retry. The section now shows the
shape with a one-line example and says it is never an object. Shared by
/qa and /qa-only through the QA_EXPLORATORY resolver.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.52.0 fix(qa): annotations limits shape; qa-quick does less work in the same 300 s budget
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(careful): check PowerShell tool commands and nested pwsh/cmd (#3067)
/careful and /guard matched only the Bash tool, so on Windows, where
Claude Code's PowerShell tool is the primary shell, the guard never ran.
check-careful.sh also had no PowerShell or cmd patterns.
- careful/guard register a PowerShell matcher beside Bash.
- hook-extract.sh gains gstack_hook_extract_tool: one parser call reads
tool_name with the field, so dispatch adds no fork.
- check-careful.sh runs one PowerShell/cmd pattern table on PowerShell
tool commands and on the tail of any Bash command that launches
pwsh/powershell/cmd: Remove-Item and aliases with -Recurse/-Force
prefixes, rd/rmdir/del/erase /s, Format-Volume, Clear-Disk,
Clear-Content, [IO.Directory]/[IO.File]::Delete, and asks with an
explanation for -EncodedCommand, iex, Start-Process of a shell and
& $cmd. Command-position anchors keep Bash negative controls allowed.
- /careful documents the coverage as best-effort and points to Claude
Code permission deny rules.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(freeze): NotebookEdit respects the freeze boundary (#3067)
NotebookEdit was in no freeze/guard/investigate matcher, and
check-freeze.sh read only file_path, so notebook edits ignored /freeze on
every platform. NotebookEdit carries tool_input.notebook_path.
- freeze, guard and investigate register a NotebookEdit matcher beside
Edit and Write.
- check-freeze.sh reads file_path, then notebook_path, through the shared
extractor; denials name the tool, the field, the boundary and
/unfreeze. A helper without the combined reader denies as out of date.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test: run hook-scripts on the Windows lane (#3067)
The careful/freeze hooks are Windows coverage, but test/hook-scripts.test.ts
was excluded from windows-free-tests by the raw /tmp/ pattern; its /tmp/
literals are payload strings that are never opened. Admit it by name and
gate the three cases Windows runners cannot host: a symlink (no Developer
Mode), a newline in a directory name, and a POSIX ':' PATH prefix.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore(evals): check-careful.sh is free-only for PR selection
No paid fixture copies or runs careful/bin/check-careful.sh (the
investigate boundary fixture copies hook-extract.sh and check-freeze.sh
only); test/hook-scripts.test.ts covers it. As an unknown dependency it
restored the full paid gate on every /careful hook change.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(careful): pin the #3067 Invoke-Sqlcmd DROP TABLE example on the PowerShell tool
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore(evals): record the check-careful.sh selection change as non-behavioral
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: /careful covers PowerShell (best-effort), /freeze covers NotebookEdit (#3067)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore: release v1.91.37.0 (CHANGELOG, TODOS for deferred hook follow-ups)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore: re-slot release to v1.91.39.0 (v1.91.37.0 and v1.91.38.0 claimed by #3075, #3076)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore: re-slot release to v1.91.41.0 (merge-queue reservation)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(careful): hook payload reader survives Windows text-mode Python and backslash source paths
windows-free-tests (run 37739845723) showed every PowerShell-tool case
falling through: Python's text-mode stdout on Windows wrote tool_name as
"PowerShell\r", so dispatch never matched, and freeze denials carried
stray CRs. gstack_hook_extract_tool now reads and writes bytes.
hook-extract.sh also located gstack-state-root.sh with ${BASH_SOURCE%/*},
which strips nothing when the file is sourced through a C:\... path, so
gstack_hook_state_root vanished (state-root parity case on the same run).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(evals): PR lane selects office-hours-auto-mode by its real test name
The PR paid lane filters audited files with -t built from
CASE_TEST_NAMES[id] ?? id. office-hours-auto-mode's Bun test is named
'AskUserQuestion surfaces when --disallowedTools AskUserQuestion is set',
so the filter matched 0 tests and the shard failed (#3077 eval-slices (6),
run 37741434771). Map the label, and check every audited PR-profile case
is addressable by name. Recorded as non-behavioral for HARNESS_VERSION.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore: CHANGELOG notes for the Windows CRLF and PR-lane name fixes
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore: re-slot release to v1.91.47.0 (merge-queue assignment)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
The scripted boundary now mirrors Step 1's layout (restore point and artifacts
in the project's .gstack/tmp/autoplan/) and continues past the Phase 2 entry to
dispatch the Phase 2 reviewer after the CEO reviewer's completion notice. The
case asserts four verified guard allows, that the close packet Read, the Phase 2
section Read and the Phase 2 dispatch came after a task-notification turn, that
the Phase 2 reviewer read its input, and that no permission card appeared at
all. Still one trial on haiku, about 75-85 seconds.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Skill hooks do not run inside subagents, so a reviewer launched after a
background completion notice raised a card for its own input (native-prompt.md
under the state root). Step 1 now puts RESTORE_PATH in the repository's
git-excluded .gstack/tmp/autoplan/ (added to .git/info/exclude, mode 700), and
the snapshot tool writes every phase artifact beside it, so /autoplan and its
reviewers read them from the working directory without a card. The guard's
bindings are unchanged: they anchor on the restore point's directory. Step 1
still prints the slug, which the old RESTORE_PATH carried.
A free test runs the generated Step 1 block twice from a repository
subdirectory: the restore point lands in <repo>/.gstack/tmp/autoplan/, the
exclude line is written once and git status stays clean. The autoplan parity
cap rises by the measured bytes (115,270 / 101,979 = 1.1303).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Claude Code applies a skill's allowed-tools only to the turn that invoked it.
On 2.1.292 the default fork-subagent mode runs reviewers in the background, and
the completion notice starts a new turn, so later Reads outside the working
directory (the next phase's section file, the close packet) raised permission
cards. Skill hooks stay registered for the session, and a PreToolUse "allow"
skips the card (reproduced in a PTY on 2.1.292).
autoplan/bin/owned-read.ts approves a parent Read only when the guard itself
returned no output, and only for this installation's autoplan/sections/*.md
(canonical path or the gbrain :user render) or an immutable phase artifact in
<repo>/.gstack/tmp/autoplan/autoplan-<phase>-*/ whose repo is the session's
project directory or contains it. Denials, unverified allows, child calls and
every other path are unchanged. renderSectionBase and userRenderRoot move
there with it.
Tests that asserted a verified driver Read as {} now expect the approval;
autoplan-owned-read covers the shipped shim, the close packet without a
journal, verified artifacts through the guard, look-alikes (foreign install,
writable copy, symlink alias, other repository, other names) and a guard
denial staying a denial.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* feat: add configurable model tiers and advisory freshness
* fix: disclose role selections before Claude review execution
* fix: reject malformed model policies and keep model pins portable
* fix: separate readiness diagnostics and bound version checks
* fix: preserve actionable model failures and validate review inputs before probes
* fix: retry released probe locks and retain late-rejection repair context
* feat: finalize configurable model tiers and verified release repairs
* fix: preserve strict model policy reads on Windows
* fix: keep fixture probes read-only and clarify pending CEO decisions
* fix: verify native terminal closure before bounded descriptor settlement
* fix(cso): give snapshot.json its own 16 MiB cap and actionable capacity errors
/cso refused any repository with more than about 3,100 tracked files before
an audit started: the snapshot manifest was pretty-printed and both its
writer and every reader capped it at the shared 1 MiB private-state limit
(#3068, manifest half of #2993).
- snapshot.json is written compactly and capped by SNAPSHOT_MANIFEST_LIMIT
(16 MiB), a constant local to the snapshot module.
- readJson takes a per-artifact cap; readSnapshotManifest is the only
reader of snapshot.json and passes the snapshot cap through recovery and
the private-file size check. MAX_STATE_FILE and MAX_OUTPUT stay 1 MiB.
- The manifest-cap and 64 MiB source-cap errors name the bound cap, the
measured value, what counts toward it, the next step and #2993. A single
file that would cross 64 MiB now hits the same message before it is read.
- Older pretty-printed manifests still load (recheck, inspect).
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(cso): bound per-entry report and evidence lists with omitted counts
Lifting the manifest cap alone moved the failure into the audit: report.json
listed one transformation per transformed entry plus one coverage gap or
exclusion per omitted entry (1.97 MB for 5,000 nested paths), and
sensitive-evidence.json grew per scanner hit (1.68 MB), both under the
1 MiB private-state cap that saveReport and the start stdout share.
- boundedList (state.ts) keeps the leading entries that fit a byte budget,
measured as the pretty-printed JSON they add at their nesting depth, and
ends the list with one summary carrying the omitted count.
- report.json snapshot lists share one 256 KiB budget (gaps 128 KiB,
transformations 96 KiB, exclusions 32 KiB); coverage counts and status are
computed before trimming, so they stay exact.
- sensitive-evidence.json keeps 512 KiB of per-file evidence plus an
omitted-count record.
- Snapshot coverage and publicSnapshotPath no longer scan the whole manifest
per entry.
Test: 5,000 long nested paths, mostly excluded or withheld, 999 files with
scanner hits, driven through start, inspect, submit, finish and recheck.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(cso): admit Git path listings above 1 MiB during snapshot capture
With the manifest cap lifted, the next file-count wall was the shared 1 MiB
process-output cap on Git's path listings: ls-files/ls-tree --name-only
failed at roughly 15-20k files (23,749-file grafana/grafana fails there) and
the comparison-base ls-tree near 8-10k.
runProcess lets raw callers, whose output is never printed or persisted,
opt in to up to 16 MiB; git() forwards an optional cap, and the four
snapshot listings pass SNAPSHOT_MANIFEST_LIMIT. Every other caller keeps
the MAX_OUTPUT clamp.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(cso): explain the capacity refusals and file the follow-ups
docs/troubleshooting.md#cso-capacity covers the snapshot-list cap, the 64 MiB
source cap and the tracked-symlink refusal. TODOS.md records the symlink
design call, the #2993 aggregate cap, the full-manifest inspect output and
repair-bundle transformations.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore(release): v1.91.42.0 /cso lifts its file-count ceiling
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(ios-qa): allow physical iPad devices in tunnel bootstrap (#2743)
(cherry picked from commit d6d43934ef)
* fix(ios-qa): iPhone + iPad on USB names each UDID instead of picking one
With GSTACK_IOS_TARGET_UDID unset, tied default ranks used to pick the first
device devicectl listed, so a QA session could drive the wrong device. Tied
candidates now fail with multiple_devices, list each device and UDID, and
print a ready export line. Device selection moves into selectDevice() so the
route-drop recovery can re-resolve with the same rules.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(ios-qa): a dropped CoreDevice route no longer relaunches the app (#1975)
Rotation deletes the app's one-shot boot-token file, so the daemon's old
503/504 path (invalidate + full bootstrap) could only get a new token by
running devicectl launch --terminate-existing, wiping the in-app QA state at
every route blip.
A route failure now goes through recoverTunnel(): re-select the device with
the bootstrap rules, re-resolve the tunnel address for the pinned UDID, check
the unauthenticated /healthz owner, then probe /state/snapshot with the cached
bearer. Outcomes:
- bearer accepted: keep the session (new address if it moved)
- 401: full bootstrap from the fresh boot token (app was relaunched)
- app confirmed absent: bootstrap, which launches it normally once
- different device or an address devicectl cannot tie to the UDID:
bootstrap; the old bearer is never sent there
- route still down with the app running: surface the error, keep the session
Concurrent failures on one tunnel share a single refresh. Mutations whose
response was lost are still never replayed. The CLI wiring moves into
deviceTunnelSource() so tests drive it against a simulated device.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(ios-qa): a failed boot-token write is loud instead of silent (#1837)
StateServer.start() wrote the boot-token file with try?, so a failed write
left nothing on disk and no trace anywhere, and the daemon then relaunched the
app trying to mint a token that could never be written. The write is now a
do/catch that logs the path and error (never the token), logs a NOT READY
bootstrap line, and reports boot_token_error on /healthz. bootstrapTunnel
reads that field and returns boot_token_unavailable naming the device-side
cause instead of running --terminate-existing.
Also drops the stale comments claiming the token was written to os_log.
Template and fixture stay byte-identical.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(ios-qa): type the iPad acceptance test's mDNS stub
ResolveImpl returns Promise<string[]>; resolving null tripped the test-code
typecheck ratchet. A rejected lookup exercises the same resolve_failed path.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(ios-qa): iPad support, GSTACK_IOS_TARGET_UDID, route-drop recovery, known limits
- iPhone-only description, triggers, and prerequisites now cover iPads, and
say how to pick one device with GSTACK_IOS_TARGET_UDID.
- Phase 2 no longer tells you to capture a boot token from os_log (it has
not been logged for many releases); it describes the 0600 tmp/ file and
the NOT READY signal (#1837, #1735).
- Source-control guidance for the generated DebugBridge/ package (#1735).
- Failure table: route drops keep the session, multiple_devices, unwritable
token file, and the one relaunch a daemon restart still costs.
- Known limits: SwiftUI DragGesture and /swipe on iOS 26 (#1975), the
iOS 26.3.1 /elements data from PR #1755, unverified iPad Stage Manager.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs: iOS QA how-to and skill index cover iPads and route-drop recovery
The how-to still said the boot token was readable from os_log and that a
route drop re-bootstraps; both are now accurate, with iPad selection,
GSTACK_IOS_TARGET_UDID, and three new failure rows.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* v1.91.37.0 fix(ios-qa): iPads work, a route drop no longer relaunches the app, loud boot-token write
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* docs(ios-qa): keep issue numbers out of model-read skill text
The archaeology lint rejects issue references in generated SKILL.md text;
the Known limits entry keeps the iOS version and drops the number.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* chore: re-slot to v1.91.38.0 (v1.91.37.0 claimed by #3075)
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* test(ios-qa): device-change recovery test without an IPv4-mapped address
The Windows lane could not reach a fake StateServer through
::ffff:127.0.0.1, so the iPad half of the device-change test timed out. The
fake device now swaps identity on its one ::1 listener, which is also closer
to production: every StateServer answers on the same port.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: loulanyue <260355617@qq.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
sessions[] is written only at office-hours Phase 4.5, so runs that ended
earlier never counted toward tenure and the tier undercounted. Add a manual
`--reconcile` that scans projects/*/timeline.jsonl for office-hours
`completed` events and appends a count-only row ({date, mode, project_slug,
signal_count: 0, signals: [], backfilled: true}) for each run with no
sessions[] entry for the same project within 60 minutes, extended back by a
duration_s under 8h. It is idempotent, skips malformed lines, and leaves the
file untouched on a no-op. `--read` counts backfilled rows for SESSION_COUNT
and TIER but takes LAST_*, DESIGN_*, CROSS_PROJECT and the nudge from logged
sessions only. Not wired into the preamble yet; the office-hours greeting
guard for backfill-only profiles is left to the office-hours owner.
Adopts #2668 (rewritten on current main). Closes part (b) of #2657.
Co-authored-by: Briac <137724549+briacSck@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
/retro produced "3 Things to Improve" but never saved them in its JSON
snapshot, so the next retro could not tell whether last week's
recommendations were acted on. Step 13 now drafts the items before saving
and always writes a `recommendations` array ({category, text}, [] when
empty); Step 12 scores each prior recommendation addressed/partial/open
against this window's commits, files and metrics and renders a
follow-through line, skipping silently for snapshots without the key. The
report format ties the items to the saved array. Global mode is unchanged.
Adopts #1853 (rewritten on current main). Refs #1834.
Co-authored-by: Jayesh Betala <jayesh.betala7@gmail.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
/setup-deploy stated that Vercel always deploys on push, which is false for
CLI-only projects with no Git integration, and its nothing-detected path did
not say why such a project is invisible to detection. Qualify the Vercel
trigger (ask for and record the CLI deploy command otherwise) and note that
`vercel link` creates .vercel/ so a re-run detects the project.
Adopts the Vercel accuracy part of #2992 (rewritten on current main); the
third-party bring-up tool pointer is not adopted.
Co-authored-by: mikehasa <91774998+mikehasa@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
The Agent-tool rewrite for hermes, gbrain, openclaw and factory keyed only
on "use the Agent tool", but templates mostly say "via the Agent tool",
"with the Agent tool", "multiple Agent tool calls" or "Use the Agent tool",
so the Claude tool name leaked into those hosts' skills and sections. Add
ordered rules after the existing key (possessive, "the Agent tool", then
bare "Agent tool") mapping to sessions_spawn (gbrain/openclaw),
delegate_task (hermes) and delegation (factory). No goldens change.
Adopts #1935 (rewritten on current main, without the new goldens).
Co-authored-by: katlun-lgtm <264247399+katlun-lgtm@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Rewrite of #2007, folding #1963's MCP notes. On Windows the local stdio
registration stored the bun `gbrain` binstub; gbrain.exe starts bun in a new
console, so every Claude Code session opened a visible terminal for the MCP
(the contributor's process trees show it; bun.exe launched directly attaches
to Claude Code's headless ConPTY).
Under MINGW/MSYS/Cygwin the skill now resolves BUN_ROOT from BUN_INSTALL or
~/.bun and registers `$BUN_ROOT/bin/bun.exe <global node_modules
gbrain/src/cli.ts> serve`. That path also covers a `bun link`ed clone, whose
global node_modules entry links to it; gstack-gbrain-install records no other
clone location. When bun.exe or the entry is missing it registers
`$BUN_ROOT/bin/gbrain.exe` by its full name, because Claude Code does not
apply PATHEXT to a stored path (#1963). POSIX keeps the binstub line. The
skill also notes that `claude mcp list` can show "Failed to connect" while a
live session holds a local PGLite brain's single-writer lock (#1963).
test/setup-gbrain-windows-mcp.test.ts runs the generated fence under bash with
stub uname/claude and a temp HOME for MINGW64, MSYS with BUN_INSTALL, a
missing entry, and Linux. It is listed as Windows-incompatible (POSIX stubs);
the console behavior needs a manual Windows check.
Co-authored-by: Max Hogan <max@maxhogan.dev>
Co-authored-by: maxpetrusenkoagent <280464918+maxpetrusenkoagent@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Rewrite of #2217. Required team mode wrote a bash check-gstack.sh and
registered it as "$CLAUDE_PROJECT_DIR/.claude/hooks/check-gstack.sh", which
only works when the hook runner is a POSIX shell. Under cmd.exe or PowerShell
(Windows, Copilot CLI) the variable is not expanded and the .sh cannot run, so
an intended allow or deny became a hook error.
- The hook is now .claude/hooks/check-gstack.cjs: the same root search
(GSTACK_ROOT, every host's global root, the migrated repo), with the home
directory from HOME, then USERPROFILE, then os.homedir(). It prints {} when
gstack resolves and the PreToolUse deny JSON with exit 2 when not.
- The registered command is `node -e "require(require('path').resolve(
process.env.CLAUDE_PROJECT_DIR || '.', '.claude', 'hooks',
'check-gstack.cjs'))"`: no `$` or `%`, so sh, cmd.exe and PowerShell all
pass it through unchanged.
- An existing check-gstack registration (matcher Skill or Skill|skill) is
replaced in place; duplicates are dropped and unrelated hooks in the same
entry kept. The legacy .sh is deleted only after the settings write
succeeds (a tracked one joins the suggested git add), and is kept when bun
is missing or the write fails, which now reports instead of claiming success.
Tests: team-mode and the hook-schema test run the command as registered;
test/team-init-hook-shell-neutral.test.ts runs it through the platform's
default shell (cmd.exe on the Windows lane, which curates it in) and through
PowerShell when installed (verified here in the pwsh 7 container). The
routing-probe check for the bash `_GSTACK_ROOT` gate now pins the same
contract in the .cjs: every host root probed, block only when none resolves.
Co-authored-by: neallee2012 <1499497+neallee2012@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
The "authorized defensive-security review" framing and fixture summary mode
lived only in the adversarial subagent prompt. The security specialist and
the Red Team also reason adversarially over the full diff, so repos whose
test corpus is attack payloads could still get those passes refused.
Move both paragraphs into scripts/resolvers/defensive-review.ts (the
adversarial render stays byte-identical), state them once in the specialist
dispatch for the security specialist and the Red Team, and have the Red
Team prompt start from them. Testing and the other specialists keep full
fixture reads; the codex host still strips Review Army. Parity caps for
ship and review rise by the measured 1,380 bytes each (carve-guards notes).
Adopts #1921 (rewritten on current main).
Co-authored-by: Brian Majewski <1693720+bmajewski@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Rewrite of #3066. bin/gstack-hook-check only listed setup's hooks plus
/autoplan's by name, so the /careful and /freeze PreToolUse checks (also run
by /guard and /investigate), /plan-ceo-review's hand-off hook and the helpers
they source were never parse-checked before Claude Code ran them.
- The hook list is setup's _hook_command_path arguments plus every gstack path
on a `command:` line in a generated */SKILL.md frontmatter (9 hooks, up from
6). The generated files are read rather than the .tmpl sources because the
/autoplan and /plan-ceo-review commands come from resolvers.
- Each shell hook's gstack-tree helpers (`.`/`source` lines, assignments and
shellcheck source= directives, followed transitively) are parsed too:
careful/bin/hook-extract.sh and bin/gstack-state-root.sh for /careful and
/freeze.
- The shim, its helpers, each TypeScript entry and every local module the
bundle used (bun build --metafile; entry only when bun lacks it) are scanned
for conflict-marker lines, which still parse inside heredocs, strings and
template literals.
- bun build runs from the gstack root, so the caller's broken tsconfig.json or
bunfig.toml no longer fails every TypeScript hook. Lists are newline
separated, so a root with spaces works.
Tests in test/setup-hook-syntax-gate.test.ts cover each case; the gstack-doctor
fixture now copies autoplan/SKILL.md, whose frontmatter registers the hook its
hooks-row test breaks. docs/troubleshooting.md describes the wider check.
Co-authored-by: Benjamin D. Smith <7134745+BenjaminDSmithy@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Every Codex rollout counted as one undifferentiated codex bucket, so
/retro global could not tell interactive Codex Desktop work from
codex_exec runs or Claude Code-driven calls. Normalize
session_meta.payload.originator into desktop, exec, claude_code or
other (missing, unknown and non-string values), report the split per
repo as codex_originators and globally as tools.codex.originators, and
print it in the summary. Existing totals are unchanged. Adopts #1488.
Refs #1315.
Co-authored-by: 0xDevNinja <manmit0x@gmail.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
The Enum & Value Completeness check fired only on newly added values, so a
diff that widens what a validator, parser or guard accepts, and breaks an
unchanged downstream consumer outside the diff, was a blind spot. Widen the
check's trigger (heading unchanged) and add a consumer-grep bullet. Teach
the maintainability specialist to flag user-facing strings whose guarding
condition changed while the text did not.
Adopts #2141 (rewritten on current main; the section heading is kept).
Co-authored-by: Arno V <38716+aversini@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Codex reports cached_input_tokens as a subset of input_tokens, but the
adapter billed all of input_tokens at the full input rate. Split them
into disjoint uncached and cached counts (what estimateCostUsd expects)
and show new+cached input in the table and Markdown reports. A stored
Gemini OAuth file alone is now reported as not ready, with a reason
naming GEMINI_API_KEY; key-based auth stays ready. Adopts the focused
subset of #2283; the capacity error code and stdin change are left out
(no captured failure or reproduced hang).
Co-authored-by: Mattias Petersson <mattias.petersson@gmail.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Agent-generated commands often use the GNU `--flag=value` form, which threw
"Unknown screenshot flag". Both value flags now accept it, through the same
validation and conflict checks as the space-separated form. Adopts #1563.
Co-authored-by: techcenter68 <75930234+techcenter68@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
`viewport WxH` pinned the page with no way back short of `browse restart`,
which also drops a headed /connect-chrome session. `viewport auto` (aliases
`reset`, `unpin`) now undoes the pin:
- headed: the context already launches with `viewport: null`, but Playwright
cannot drop a page's emulated size (and re-applies it on new frame
sessions), so the active tab gets a fresh page in the same context at the
same URL or load-html content. Cookies and storage persist, the tab id and
ownership stay, refs reset as on navigation, and the page follows the real
window again.
- headless: back to the 1280x720 launch default, tracked viewport included.
`auto` with --scale is rejected. Fixes#1059. Adopts #2782 and #1881.
Co-authored-by: Jack Thomas <17882510+loulanyue@users.noreply.github.com>
Co-authored-by: Jayesh Betala <jayesh.betala7@gmail.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Rewrite of #1713. .gitlab-ci.yml's .setup-bun anchor and
scripts/ubicloud/setup-free-suite.sh still piped https://bun.sh/install into
bash. Both now download the bun-v$BUN_VERSION linux-x64 release zip, check it
against the same SHA-256 Dockerfile.ci uses (#1706) before unzipping, install
it to ~/.bun/bin and assert `bun --version`. test/ci-image-cli-pin.test.ts runs
curlPipedToShell over both files and binds their hash and BUN_VERSION to
Dockerfile.ci's amd64 arm and package.json's engines floor, so a Bun bump has
to move all of them together. Verified by running the GitLab anchor in
debian:stable-slim (bash and sh) and the Ubicloud block in a temp HOME.
Co-authored-by: Zee Zheng <228040220+spacegeologist@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
gen-llms-txt built every skill link as <name>/SKILL.md, so the router
pointed at a nonexistent gstack/SKILL.md (it is the root SKILL.md) and
/claude-code pointed at a SKILL.md the Claude host never generates.
Links now use the template's generated output path, and skills the
Claude host skips are left out of the index. Adopts #2279.
Co-authored-by: Nader Helmy <creator.nader@gmail.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
/benchmark claimed the bare words "benchmark" and "performance", so model
and eval benchmark requests could route to the web performance skill
instead of /benchmark-models. Narrow the description, Use-when list and
triggers to web-specific phrases, point model/skill benchmarks at
/benchmark-models, and split the root router line the same way. The
catalog lead stays within the discovery budget ("Web performance ...").
Adopts #2302 and closes duplicate #2083 (rewritten on current main).
Co-authored-by: Nader Helmy <31414549+creatornader@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
OpenClaw's sessions_spawn has no env argument (openclaw/openclaw#51654
was closed without adding one), so the documented
env: { OPENCLAW_SESSION: "1" } silently did nothing. Point users at the
ACP harness or Gateway environment instead and guard the old advice.
Adopts #2749.
Co-authored-by: DanCanadian <211164803+DanCanadian@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
Rewrite of dependabot #2988. Every bumped `uses:` stays pinned to the full
commit SHA (verified against the upstream tags) and now carries its exact
version comment, including the lines that had none. setup-node 6.5.0 -> 7.0.0
is a major bump; its notes list an ESM migration, cache outputs and removal of
a dummy NODE_AUTH_TOKEN export, none of which affect our node-version-only use.
actionlint 1.7.11 (CI image) and 1.7.12 are clean.
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
The link resolved relative to docs/, pointing at a nonexistent
docs/CONTRIBUTING.md. Adopts #3070.
Co-authored-by: thearbajonart <334330110+thearbajonart@users.noreply.github.com>
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
* fix(cso): Python and Rails repairs verify and replay; killed attempts leave no scratch
- Python offline preparation sets SOURCE_DATE_EPOCH so .pyc bytecode is reproducible.
- Prepared identity hashes skip RubyGems/mini_portile build diagnostics that name random build dirs.
- Rails verification attempts and replays get 900 s; the attempt watchdog, Docker
verification executor and assertion witness share MAX_VERIFICATION_ATTEMPT_MS.
- resume and finish reclaim a killed attempt's scratch once its watchdog recorded cleanup.
v1.91.34.0
* Format lib/cso with prettier
* Take v1.91.36.0 (1.91.35.0 is claimed by #3073)