6 Commits

Include renames

Author	SHA1	Message	Date
+717 people	3e8b34d892	v1.91.106.0 fix: the 2026-10-15 issue wave (#3209) ... * docs(designs): add fix wave 2026-10-15 plan (revision 3, approved) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(cso): invoke docker as argv0 docker so OrbStack's multicall binary dispatches executable() returns the canonical path, and OrbStack installs docker as a symlink to docker-tools, which dispatches on argv[0] and exits 127 with 'unsupported argv0 "docker-tools"'. Every Docker call failed, so doctor reported local-docker-isolation and every scanner missing and setup could not preload the qualified images. runProcess takes an argv0 option; docker.ts routes every Docker call through runDocker, which passes 'docker'. The native watchdog's execve calls pass "docker" as argv[0] too, so its container cleanup works on the same installs. The executed file is still the verified canonical path. Fixes #3187 * test(cso): cover Docker and watchdog invocation through a multicall binary A compiled fake that refuses any argv[0] but docker stands in for OrbStack's docker-tools. Both behavior tests fail on the previous code. Refs #3187 * fix(cso): bound the argv0 test's socket helper and probe images through OrbStack's multicall docker (#3187) Follow-up to #3188 by Bryan Stone (@aegixx): - the python3 spawnSync that binds the fake daemon socket gets a 30 s timeout; without it test/spawnsync-timeout-tripwire.test.ts fails. - reviewer test: dockerExactImagePresent, a production probe, admits an image when the endpoint's canonical executable is a multicall binary that refuses any argv0 other than "docker". It fails on 47d639a (returns false) and passes with #3188. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): own the conversation after a Claude Code 2.1.300 compaction Claude Code 2.1.300 keeps a compaction's last records in place and lists them in compactMetadata.preservedMessages. The segment's tail, which is also the boundary's logicalParentUuid, is written after the boundary under the compact summary, so the parent links form a cycle that the owned causal order never reaches. Every record after the compaction was dropped, and the publication guard denied each later phase entry with close_incomplete. Such a boundary now continues from the last preserved record that is a node of the file and not its own descendant. Boundaries without that metadata, with a foreign preserved uuid, or with nothing kept in place still supply no ownership. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(autoplan): report a compaction-explained unreachable component as unrecognized_shape (#3194) Follow-up to #3196 by vilano93. After the ownership walk, an owned node the walk never reached was silently dropped, and the phase guard answered the next phase entry with close_incomplete, which the user cannot satisfy. When the unreachable node's ancestry ends in a cycle through a compact boundary's logical parent, ownedCausalOrder now returns unrecognized_shape:compaction_unreachable, the guard's existing unverified disposition (allow with a visible warning and a guard-log row). Orphans whose ancestor is missing (not flushed yet) and other roots keep today's behaviour, so the fail-open surface does not widen beyond compaction. Each node is walked once. Gate-integrity edit: a close_incomplete denial becomes an unverified allow for that shape only. Negative controls kept: the existing guard, hook, guard-reasons and captured-fixture tests still deny (356 pass), and a new case with the boundary not yet flushed still denies close_incomplete. Intentional pin changes in #3196's own test file: the three "fails closed" cases (tail-only segment, missing preserved metadata, foreign preserved uuid) and the "without compactMetadata" case now expect unrecognized_shape:compaction_unreachable instead of close_incomplete or a silently cut transcript. Reviewer tests: three compactions in one session stay owned and pass the next phase entry; a 50k-record history with three compactions is decided in ~300 ms (budget 1000 ms), so descends needs no memo. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(lib): one echo sanitizer for external strings, with a Bash twin lib/sanitize-echo.ts and bin/gstack-sanitize-echo.sh flatten CR/LF/TAB to spaces, remove every other ASCII control byte (ESC included) and DEL, collapse runs of spaces, and cap the result at 200 bytes of valid UTF-8 with no leading or trailing space. Every external string gstack echoes into a message, a log line or a key=value state file goes through it (fix wave 2026-10-15, plan rev 3 DX F8). test/sanitize-echo.test.ts runs both twins on one table under bash, bash --posix and zsh, including a "\nstages=" injection, ESC sequences and UTF-8 characters cut by the cap. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(bun-version): judge the Bun floor under zsh and hold on an unreadable version (#3195) Reported by mochafreddo. _gstack_bun_below word-split $_gb_core, which zsh does not do: `[ -ne ]` errored and every error path read as "not below", so /gstack-upgrade Step 4 accepted Bun 1.3.2 in a zsh tool shell. - _gstack_bun_below copies the release's parsed fields into quoted positional parameters and compares with $((10#...)); no new _gb_* globals. It returns 2 when either side cannot be parsed. - gstack_bun_status prints malformed for an unparseable version or floor (never ok); gstack_bun_incoming_hold holds on it with bun-version-unreadable: ... (BUN_VERSION_UNREADABLE), the bun path and its output passed through gstack_sanitize_echo. setup's own malformed warning is unchanged. - /gstack-upgrade Step 4 runs the check through `bash -c` and stops on BUN_VERSION_UNREADABLE with a reinstall fix (never "bun upgrade"). - New result code BUN_VERSION_UNREADABLE with its troubleshooting entry; bin/gstack-doctor-components.sh regenerated from the table. test/bun-version-shells.test.ts: one version table (1.3.2, 1.3.3-canary.1, 1.3.3, 1.3.14, 1.4.2, 1.10.0, 01.04.02, 2.0.0, garbage) drives bash, bash --posix, zsh and the TypeScript twin's below(); `zsh -c '. bin/gstack-bun-version.sh; gstack_bun_status 1.3.2'` printed ok on 47d639a and prints too-old now. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * style(cso): format #3188's runDocker call so format:cso:check passes (#3187) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(cso): keep scanner JSON reports parseable after redaction (#3185) Reported in #3185. The scanner path splices redactions into raw JSON, and redactFindingSpans replaced a bare 10+ digit number ("max_memory_bytes":1145427776, an epoch) with an unquoted marker, so JSON.parse failed and every non-trivial Semgrep run was INVALID_OUTPUT. - lib/redact-engine.ts: redactJsonFindingSpans, a string- and escape-aware lexical tokenizer over one or more top-level values (NDJSON included). A span inside a number replaces that whole token (-, fraction, exponent) with the quoted marker, number by number; a span inside a string keeps the in-string marker, widened to whole escapes; a span touching several tokens, whitespace, a literal or a structural character returns null (withhold). Non-JSON text gets the plain splice. redactFindingSpans is unchanged for every other caller. - The scan operation's declared format rides the real capture path: scanner-executor (scan stdout, or the report file read for outputPath plans) -> DockerGroup.execCapture -> runProcess -> spliceRedaction, which redacts the concatenated stdout once and maps each interleaved run onto it. Version probes and stderr stay plain; marker-only withholding and the cross-stream views check are kept, and the output is a fixpoint of that check. Behavior change: a redacted number in a scanner report is now the string "<REDACTED-...>" instead of an unquoted marker; non-JSON streams keep the unquoted form (test/cso-eval.test.ts unchanged). Intentional pin change: test/cso-scanner-release.test.ts pinned the report read as capture(['/bin/cat', plan.outputPath]); it now pins capture(['/bin/cat', plan.outputPath], plan.format), so the read also carries the declared JSON format (stricter, not weaker). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(browse): recover when the last tab is closed outside the CLI Closing the last tab outside browse (for example, closing the headed Chromium window) left the daemon wedged: the page 'close' handler removed the tab and set activeTabId to 0, and executeCommand called getActiveSession() first, so every later command (goto, status, even stop) failed with "No active page" until the daemon PID was killed by hand. closeTab() already opens a blank tab when the last tab closes; the external close path never did. Add BrowserManager.ensureActiveTab(), which reselects a remaining tab or opens one blank tab (concurrent callers share one recovery), and call it before resolving the active session in executeCommand. Fixes #3167 * fix(browse): status and stop answer after an external close; recovery says what it did (#3167) Follow-up to #3179 by aftabkh4n, which reopens a tab on demand. - BrowserManager.ensureCommandTab runs before every command: status, stop and restart never open a tab, so a daemon whose browser or context is gone can still report and be stopped; any other command gets an active tab. A failed recovery is BROWSE_TAB_UNRECOVERABLE carrying the restart command (cause passed through sanitizeEcho), and a command that ran on a newly opened tab prints a one-line warning first. - server.ts reads the session inside the read and write branches instead of before dispatch (2223 lines, cap 2224) and exposes browserManager and handleCommandInternal on __testInternals__ for the dispatch test. - meta-commands.ts: handleMetaCommand no longer reads the active session before its switch (only snapshot and resume used it), and status prints getCurrentUrl() so it works with zero tabs. This file is outside the lane's listed ownership; no other lane or #3190 touches browse/. - New result code BROWSE_TAB_UNRECOVERABLE and troubleshooting entries for it and for the old "No active page" wedge. Reviewer test browse/test/tab-external-close-dispatch.test.ts drives the real dispatch in a child process: status, text, goto and stop after an external close, and the closed-context case. On 47d639a (with only the test seam added) all five fail with "No active page". Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(troubleshooting): /cso INVALID_OUTPUT on Semgrep reports and OrbStack's argv0 refusal (#3185, #3187) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(session-update): name the reinstall fix when an unreadable Bun holds the auto-update (#3195) Item 11 makes every caller of gstack_bun_incoming_hold treat a Bun version it cannot read as a hold (bun-version-unreadable, BUN_VERSION_UNREADABLE). The session-start banner only knew bun-too-old, so the new reason fell through to "git pull did not finish ... gstack is not updating" with a pull-and-setup fix that does not help. - bin/gstack-session-update: a bun-version-unreadable banner case with the reinstall fix and the troubleshooting anchor; the comment that said a malformed version passes is corrected. Intentional pin change: test/session-update-stages.test.ts "supported or unparseable Bun (bun-dev (local build)) proceeds: setup decides" is split. 1.3.14 still proceeds; bun-dev (local build) now holds with BUN_VERSION_UNREADABLE, leaves the checkout and setup untouched, and the banner names the reinstall fix. The fixture installs bin/gstack-sanitize-echo.sh beside the floor helper, as a real install of this release does. The new case fails on 47d639a. Ownership exception granted by the coordinator for Lane A (bin/gstack-session-update is Lane B's file; PR 1b stacks on 1a). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(session-update): recover a conflicting autostash by its unmerged files The auto-updater fast-forwards with `merge --ff-only --autostash`. When the carried-over local edits conflict with the incoming revision, git 2.56 still exits 0 from that merge, pops the edits with conflict markers into the live checkout, and keeps the stash entry. The recovery only ran on a non-zero exit with "autostash" in stderr, so on git 2.56 it never ran: the updater logged UPDATED and ran setup over a half-merged tree, in the directory Claude Code runs hooks from. When it did run, it had two more problems: - `git checkout -- .` refuses unmerged paths ("error: path 'f' is unmerged", exit 1), so it left the markers in place anyway. - `git stash drop` dropped stash@{0}, whatever that was. refs/stash is shared with every worktree of the repository, and when refs/stash.lock is held git cannot store the autostash at all, so the top entry can be someone else's. Now the merge is judged by `git ls-files -u`, whatever its exit code. On unmerged files after the fast-forward, autostash_recover finds the autostash commit by the id git prints ("cannot store <id>" first, then "Created autostash: <id>", with the merge run under LC_ALL=C and core.abbrev=40). A moved refs/stash is only the fallback. When that id is not a stash entry, it is anchored under refs/gstack-autostash/<UTC>. The tree is reset to the fast-forwarded revision, which the hook check already passed, and the stash is kept. The log line is AUTOSTASH_CONFLICT_RECOVERED tree_reset=1 kept_stash=<id> kept_ref=<ref>. The update then continues, so the regenerable patches are re-rendered and setup runs as for any other move. If the commit cannot be found, nothing is reset: the markers stay for a person, the run logs PULL_FAILED, and setup does not run. Files that are already unmerged before the update, from someone's own merge, rebase or stash pop, now hold the update with PULL_FAILED "unmerged files ...". Without that check, the recovery would take them for its own and reset them away. core.abbrev=40, not "no": "no" is accepted from git 2.31.0 (its release notes), and `merge --autostash` exists from 2.27.0, so "no" would fail every update on git 2.27-2.30. Files: - bin/gstack-session-update: autostash_recover, the unmerged-files check before the merge, the C-locale merge with its stdout kept for the id, and removal of the old grep-and-drop block. - test/session-update-autostash.test.ts: 7 cases in a new describe block. A conflicting pop leaves no markers, keeps the edits and still runs setup. A user's own stash entry survives. A held refs/stash.lock gets the edits anchored. With a git whose merge prints nothing, a moved refs/stash still finds the edits; with the lock held as well, nothing is reset. Pre-existing unmerged files hold the checkout. A non-conflicting edit rides over the update (control). Tests, on upstream 15ebd85cd: - 5 of the 7 new cases fail against the previous session-update; the unmerged-files guard and the control pass on both. - Two mutants are each caught by one new case: dropping the refs/stash fallback, and resetting when the edits cannot be found. - session-update-autostash, session-update-stages, session-update-hook-hold and team-mode pass 63/0 with `--timeout 60000`. At bun's 5 s default under heavy load (one reading: load average 169), the three shared files timed out 8 tests on this branch and 17 with the previous script. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(session-update): trust only git's autostash id; owe setup on a stop An independent review of the autostash recovery (Codex gpt-6-astra, high effort, verdict BLOCK high=1 med=2) found three defects on its rare paths. All three are fixed here, each with a case that failed first. - [high] The refs/stash fallback could erase local edits. When git's messages were unavailable, recovery took any change to refs/stash as its own autostash. refs/stash is shared with every worktree: if a sibling pushed a stash while refs/stash.lock kept git from storing this one, recovery took the sibling's entry and reset the checkout, erasing edits nothing held. Now only git's own printed id counts. A missing id resets nothing: the markers stay, the run logs PULL_FAILED. Recovery needs git's messages, so when the temp file for them cannot be created the update is held before the merge (HELD temp-file-unavailable), not merged blind. - [med] A stop after the checkout moved lost the setup it owed. The failure recorded only the pull reason. Once the person resolved the conflict, the next check saw an unchanged HEAD and no pending stage, logged UP_TO_DATE, and never set up the new revision. Now a failure after HEAD moved records `setup` as a pending stage, retried at once. The unmerged-files check holds it until the conflict is resolved, and the pull reason is the stage's reason, so the session-start line says what to resolve. - [med] An unreadable index read as "no conflicts". Both `git ls-files -u` checks discarded the exit status, so a failed read after a conflicting pop (which git exits 0 for) let setup run over the markers. Now a failed read stops the update with PULL_FAILED "cannot read the index", before the merge or after it. Files: - bin/gstack-session-update: autostash_recover drops the refs/stash fallback (and STASH_BEFORE). The temp-file hold. The ls-files exit status checked at both points. The pending setup stage on a failure after HEAD moved. - test/session-update-autostash.test.ts: a shim(fx, name, tool, body) helper; the fallback case now expects a refusal; the refusal case runs on through resolution to setup; three new cases (unreadable index before and after the merge, no temp file for git's messages). Tests, on upstream 15ebd85cd: - The 5 changed or new cases failed on the previous commit, each on its defect: refs/stash trusted and recovered; UP_TO_DATE with no setup after resolution; UPDATED over an unreadable index, before and after the merge; a blind merge with no temp file. - Against upstream's own session-update, 8 of the block's 10 cases fail. - session-update-autostash, session-update-stages, session-update-hook-hold and team-mode pass 66/0 with `--timeout 90000`. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(session-update): reap heartbeat and its sleeper on exit The lock heartbeat subshell left its sleep 300 child orphaned when the updater exited, so heartbeats accumulated across sessions. Track and reap the heartbeat job (with a job-table fallback for signals between fork and $!), give the subshell its own exit trap that kills and waits its sleeper, and map HUP/INT/TERM to exits so the EXIT trap always runs. Adds a fixture-driven regression test. * test(session-update): repin the lock trap and heartbeat to #3191's cleanup shape Intentional pin change: test/session-update-autostash.test.ts 'reclaim is TOCTOU-safe' and 'EXIT trap is ownership-checked' pinned the one-line EXIT trap and the 'while :; do sleep 300; ...' loop that #3191 (Jess Sullivan) replaces with cleanup_session_update and a 'sleep 300 & wait' heartbeat. The pins still assert the ownership-checked rm -rf, the EXIT trap, MYPID, and that the heartbeat is killed. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(session-update): move installs only through gstack-ff-update; extract hooks without tar (#3184) Item 2 (#3189, #3191 adopted in the previous commits) and item 3 of the fix-wave plan. bin/gstack-ff-update <dir> <rev> is now the only code that moves an install's tree. Inside an install-scoped lock (absolute git common dir, the updater's TTL and mv-aside reap, a heartbeat reaped on exit) it captures the working tree and the staged state through private indexes, carries edits that merge cleanly (as an autostash pop would), lets the regenerable SKILL.md/sections footprint take the target when it conflicts, and shelves any other conflicting edit, staged change or unmerged file into refs/gstack/rescue/<oid> (first parent the pre-update HEAD, second the staged state; compare-and-create; gstack rescue identity). The move is a two-way read-tree on the private index, so a late edit or an untracked file in the way refuses with autostash-unrecoverable and changes nothing. It sources nothing so the held-install recovery can fetch it from the new revision. gstack-session-update calls it instead of merge --autostash, holds a checkout with unmerged files (unmerged-files:), and names shelved edits at session start at most once a day with inspect, export-the-delta and delete commands. The incoming revision is extracted for the hook check through a private index and checkout-index with core.symlinks=false, never tar (MSYS tar cannot create connect-chrome before its target), and the held reason carries the failing command's flattened, control-free stderr. Held lines print before the stage line, one case per reason with its anchor, every path shell-quoted, no setup fix while unmerged files exist. docs/troubleshooting.md gains the held-install recovery forms (Git Bash, PowerShell 5.1, trial and go-back) and entries for each new line. design: kept_ref is refs/gstack/rescue/<oid>, refs/stash is never touched, the quiet-merge cases become a pre-existing-ref refusal and its recovery, pre-existing unmerged files are a HELD unmerged-files, and the git shim pins the real binary through git --exec-path. Intentional pin changes in existing tests: - test/session-update-stages.test.ts: printed paths are shell-quoted; the bun-too-old fix runs gstack-ff-update instead of git pull. - test/session-update-hook-hold.test.ts: the order pin looks for 'bash "$FF_UPDATE"' instead of 'merge --ff-only'; the hook-check-unavailable fix no longer recommends git pull --autostash; installedUpdater copies gstack-ff-update beside the updater. Reported by wengweiling (#3184). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(gstack-upgrade): Step 4 fast-forwards through gstack-ff-update (#3189) Item 2 of the fix-wave plan, kept in its own commit so PR 1b can be rebased onto PR 1a (which edits only Step 4's Bun floor-check line). Step 4's `git pull --ff-only --autostash` had the same hole the auto-updater had: a conflicting autostash exits 0 and leaves conflict markers in the install, and the skill printed FF_OK. It now runs bin/gstack-ff-update . origin/main after the fetch and the floor check: exit 0 runs setup (a rescued line is relayed with its inspect, export and delete commands), exit 4 (not a fast-forward) is the only way into the gated reset fallback, and any other refusal stops with nothing changed. The footprint discard moves to the reset fallback, ahead of its stash, where the warning text already promised it. Intentional pin changes: - test/upgrade-template-pins.test.ts: the ff-before-reset pin looks for 'bash bin/gstack-ff-update . origin/main'. - test/gstack-upgrade-fresh-shell.test.ts: the C9 fence marker is 'bash bin/gstack-ff-update'; the gstack-like fixture ships the bin. - test/upgrade-setup-recovery.test.ts: the git-path fixtures ship gstack-ff-update (a stub where git itself is a stub). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(setup.ps1): run under Windows PowerShell 5.1's legacy argument passing (#3130) Item 4 of the fix-wave plan. Windows PowerShell 5.1 strips the double quotes inside native arguments, so the bash -c script setup.ps1 handed Git Bash arrived broken ("unexpected EOF while looking for matching"). The script now holds no double quote: `set -f; IFS=; mapfile -d '' -t argv < $1; rm -f -- $1; exec ./setup ${argv[@]}` (empty IFS and no globbing keep $1 and each argv entry whole). That form drops an empty argument, so setup.ps1 refuses one before anything runs (SETUP_PS1_EMPTY_ARGUMENT, with its troubleshooting entry). test/setup-ps1.test.ts runs the adversarial arguments under legacy passing (pwsh with $PSNativeCommandArgumentPassing = 'Legacy', and powershell.exe itself on Windows) with a space in TMPDIR, plus the empty-argument refusal. Intentional pin change: the pinned bash -c line in "passes arguments NUL-separated through a private file to a constant bash script" now names the quote-free script and asserts it holds no double quote. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(setup): register hooks at the $HOME path when CLAUDE_CONFIG_DIR links back to it A per-session CLAUDE_CONFIG_DIR whose skills symlink to ~/.claude/skills passed the split-brain guard, so its temporary path was written into the global settings.json and the hooks broke once the session directory was removed. Fall back to $HOME/.claude/skills/gstack whenever both spellings resolve to the same tree. Fixes #3180 * fix(setup): one sourced helper picks the hook root for setup and gstack-memorable (#3180) bin/gstack-memorable carried a verbatim copy of setup's old canonical-root block, so `gstack-memorable enable` under a per-session CLAUDE_CONFIG_DIR still baked the session path into settings.json after #3181 fixed setup. The choice now lives in bin/gstack-claude-root.sh (gstack_canonical_claude_root), sourced by both. Intentional test changes: - test/setup-hook-canonical-paths.test.ts: #3181's source-slicing block test is rewritten to source the helper (with a spawnSync timeout, which the sliced version lacked and the tripwire flags); the "honors CLAUDE_CONFIG_DIR" pin moves from setup to the helper, and a new pin requires both callers to source it. Adds a no-$HOME-install case. - test/setup-hook-syntax-gate.test.ts: the hook-section slice starts at the new assignment and the harness sources the helper. - test/setup-claude-code-migration.test.ts, test/team-mode.test.ts: the partial-checkout fixtures copy the new helper setup sources. Reviewer test: gstack-memorable enable under a per-session config dir that links back to ~/.claude registers the $HOME path (fails on main). Builds on #3181 by NetrioGit. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(setup): remove 1.31-era unprefixed Cursor skill folders (#3133) A 1.31 setup run from a checkout under ~/.cursor/skills linked unprefixed <skill>/ folders there, each holding a SKILL.md symlink into the checkout. Current setup links gstack-<skill>/ folders, and the retired-skill prune only looks at gstack-* names, so the old folders stayed: Cursor loaded autoplan, review and the rest twice, or kept dangling links once the checkout moved. Run the Claude flat-name cleanup on ~/.cursor/skills as well. Cursor installs only gstack-* names, so no prefix gate is needed, and the helper removes only entries proven to link into gstack (#2119), so user-owned folders stay. It runs after linking, so a run that fails before the new links exist keeps the old folders. Reported by @andrewkjankowski in #3084. Fixes #3133 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(setup): name the skills dir in the flat-name cleanup line (#3133) `./setup --host cursor` now runs the flat-name cleanup on ~/.cursor/skills as well as ~/.claude/skills, so the "cleaned up old entries" line says which directory the folders were removed from. Reviewer test for #3152 (szsunyuan): a real dir whose SKILL.md links into gstack loses only that link and keeps the user's file; SKILL.md links into a sibling repo named gstack-fork, a relative link, and a dangling link outside any gstack checkout are all kept; the printed line names the removed folders and the Cursor skills dir. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(setup): install Chromium with `bun x`, and name exit 127 for what it is (#3131) A Bun installed with winget ships no `bunx`, so setup's `bunx playwright install chromium` exited 127 and was reported as "offline, proxy, or blocked download?". setup now runs `bun_cmd x playwright install chromium` through its existing bun resolver ($BUN_CMD), and bin/gstack-browser-ensure runs the bun it found on PATH with `x`. Exit 127 gets its own text naming the resolved bun, Bun from bun.sh, and the skip commands for Git Bash and PowerShell; other codes keep the network hint. New troubleshooting entry: #chromium-install-exit-127. Intentional test changes: - test/setup-playwright-best-effort.test.ts: the installer stub is now a `bun_cmd()` stub (was `bunx()`), its mark renamed bun-x-called and now records the args; the block under test calls bun_cmd. New winget-shaped cases (bun on PATH, no bunx anywhere) run setup's real bun_cmd. - test/gstack-browser-ensure.test.ts: the fixture is winget-shaped (the `bun` stub handles `x`, no `bunx` on PATH); the exit-7 pin now reads `<stub>/bun x playwright install chromium exited 7 (...)`. --help in gstack-browser-ensure prints the comment header only (3,24p). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci(windows): prove setup.ps1 on PowerShell 5.1 and the held-install recovery natively (#3130, #3184) windows-setup job: - setup.ps1 joins the path filter (with bin/gstack-ff-update, bin/gstack-claude-root.sh, bin/gstack-browser-ensure, docs/troubleshooting.md and test/setup-ps1.test.ts). - powershell.exe must be Windows PowerShell 5; test/setup-ps1.test.ts runs with a space in TEMP and must report exactly 4 pass, 0 fail, 1 skip (the Linux-only missing-prerequisite case). - A copy of the built checkout under a path with a space installs through `powershell.exe -File setup.ps1 --host codex`. held-install-journey job (new, parallel): - origin's main is this PR's tree on top of the v1.91.101.0 tree (47d639abf); fix-branch adds one file. - A prefix-mode v1.91.101.0 install at the runner's ~/.claude path in three states (clean, dirty-conflicting, already-unmerged), with auto_upgrade=true and the throttle cleared: the old updater must log `HELD hook-check-unavailable`; the PowerShell recovery form, read verbatim from docs/troubleshooting.md and run under powershell.exe, must reach main with every local edit (only those) in one rescue ref. The dirty state runs it with its .\setup.ps1; the others replace that step with a marker. - The trial and go-back forms move the install to fix-branch (detached) and back to main. - Only then a later release whose symlink sorts before its target is pushed, and the new updater must log UPDATED and reach it. - Both jobs assert the exact list of cases that ran. The journey steps ran locally on Linux with pwsh in Legacy argument mode as powershell.exe, a git exec-path whose ../../../bin/bash.exe is bash, and a failing tar standing in for MSYS tar (all 9 cases passed); the windows-latest run itself happens on the PR. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(ff-update): a killed step-4 run fails the status check instead of the type check Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci(windows): the held-install job runs without the bun cache step The cache key line is a secret-scanner false positive on added lines (env.kv); the fixture's own setup installs its packages either way. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(fixtures): register #3191's heartbeat fixture as free test/free-fixtures.test.ts failed on the frozen-branch Ubicloud run: test/fixtures/session-update-heartbeat.sh (adopted with #3191) was in no paid touchfile and not in FREE_FIXTURES. Its only consumer is test/session-update-heartbeat.test.ts. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(session-update): leave the bun-version-unreadable banner case to item 11 (PR 1a) PR 1a owns the bun-version-unreadable hold (BUN_VERSION_UNREADABLE), its banner case and its troubleshooting entry; this branch is rebased onto 1a. Drops the case, the docs entry and the banner test this branch had added. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(setup.ps1): resolve Git Bash in the shared order, with GSTACK_BASH as an alias and a BASH_UNAVAILABLE refusal Follows lib/script-invocation.ts (Lane C, PR 2): GSTACK_GIT_BASH is the override and GSTACK_BASH its deprecated alias at the same precedence; when both are set and differ GSTACK_GIT_BASH wins and one warning prints. An override that does not exist is refused, never skipped. Without one: the install git --exec-path belongs to (behind a scoop shim, or a portable Git), the folders around git.exe, %LOCALAPPDATA%\Programs\Git, %ProgramFiles%\Git, and last a bash on PATH whose uname -s reports MSYS; WSL's bash (System32, WindowsApps) is rejected. A miss lists every candidate with its rejection, then the PowerShell user-variable and ~/.claude/settings.json env recipes (BASH_UNAVAILABLE, #bash-unavailable). test/setup-ps1.test.ts gains a 14-row pwsh-on-Linux table with every location injected (override, alias, both set, missing override and alias, scoop shim, per-user, portable and machine-wide Git, MSYS PATH bash, WSL and non-MSYS rejections, missing); 11 rows fail on main. The rows mirror Lane C's table in test/script-invocation.test.ts; they are not wired to it, since that branch is not available here. The Windows job's expected skip count for this file moves from 1 to 15 (the table is Linux-only). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(setup.ps1): give the empty-argument refusal its result code (SETUP_PS1_EMPTY_ARGUMENT) Adds the row to lib/result-codes.ts (anchor #setup-ps1-empty-argument, which setup.ps1 already prints). bin/gstack-doctor-components.sh is regenerated from the table (generated; resolved by regeneration at merge). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci(windows): silence SC2016 on the PowerShell version probe (the $ is PowerShell's, not bash's) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci(windows-setup): give tar a POSIX path for the spaced checkout MSYS tar reads `D:\a\_temp/...` as host:path (rsh syntax) and fails with 'Cannot open: No such file or directory' before setup.ps1 runs. The copy target now goes through cygpath -u; setup.ps1 still gets the Windows form. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci(windows-setup): dereference symlinks when copying the spaced checkout MSYS tar cannot extract connect-chrome, a symlink that precedes its target (the #3184 failure mode), so the copy died before setup.ps1 ran. tar -h stores the target instead. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(windows): one Git Bash resolver for gstack's shebang bins (#3197) Windows has no shebangs, and gstack had three conflicting bash lookups: the hooks fell back to a bare PATH `bash` (often WSL's launcher), the gbrain sync checked three fixed paths, and setup.ps1 walked up from git.exe. lib/script-invocation.ts is now the only TypeScript resolver: GSTACK_GIT_BASH (GSTACK_BASH as a deprecated alias, same precedence, warning when they differ, a missing value refused), bash next to `git --exec-path` (scoop, per-user, portable Git), the known install paths, then a PATH bash only when `uname -s` reports MSYS/MINGW. WSL launchers are rejected unprobed. A miss is BASH_UNAVAILABLE, listing every candidate with its rejection reason. Bun-shebang bins run under Bun (process.execPath, or the PATH bun inside a compiled binary). Hooks' runBin resolves through a state-root cache keyed by git.exe path and mtime, written by temp file plus rename, so the hot path spawns nothing extra; the override is never cached. wtreeFingerprint({cwd, timeoutMs}) returns {tree} | {error, kind} with GIT_OPTIONAL_LOCKS=0 and 40-64 hex ids; the consumers move next. Intentional pin change: test/gbrain-spawn-windows-shell.test.ts expects forward-slashed bash paths (WIN_BASH and the GSTACK_BASH override), the form the shared resolver returns because Bun's spawnSync on Windows returns ENOENT for a backslash exe path containing spaces. The copied-tree adapters in test/timeline-stop-hook-slug.test.ts and test/plan-tune-cathedral.test.ts list the two modules spawn-bin.ts now imports; the new fixture is registered in test/helpers/free-fixtures-data.ts. bin/gstack-doctor-components.sh is regenerated for the new result-code row. Reported by @exGeni. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(windows): fingerprint and gstack bins through the shared invocation (#3197) bin/gstack-wtree was spawned by path in lib/regen.ts, lib/gate-diff/git.ts, lib/restamp.ts and bin/gstack-evidence; gstack-slug in restamp, gate-diff and evidence; gstack-redact in the pregate secrets check; and a bare `bash -c` in regen, the lane selection manifest and gstack-evidence run. On Windows each one failed to launch. All now go through lib/script-invocation.ts, and each fingerprint consumer keeps its fail direction while saying why: - gstack-regen check: incomplete, `cannot fingerprint the working tree (gstack-wtree exited 1: <helper's own repair>)` instead of `(gstack-wtree failed)`; write keeps the registry label as its run id. - gstack-gate-diff: `+nowtree` candidate, with the cause. - gstack-restamp: RESTAMP_CONFLICT carrying the launch or exit detail (Windows printed `()` before). - gstack-evidence: records without wtree (grades STALE) and warns once; SHA-256 repositories now get a 64-hex fingerprint. lib/regen.ts keeps a string-returning wtreeFingerprint(repoRoot) wrapper for lib/pregate/context.ts and lib/pregate/index.ts (files #3190 changes); item 10b migrates them. test/script-invocation-tripwire.test.ts fails on a new by-path or bare-bash spawn under lib/, hosts/ or a Bun bin; five sites outside this change are listed with their owners and may only shrink. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(pregate): keep framework route paths from a selection manifest (#3176) laneFileSet parsed manifest output with `[\w.-]+` path segments, so `app/(shop)/[id]/page.test.ts` came back as `page.test.ts`. The selected test then matched no platform lane, its remote receipt obligation vanished and it fell back to a local run. manifestTestPaths keeps route segments whole (`(group)`, `[id]`, `[...slug]`, `[[lang]]`, `@slot`, `$param`, `+page`), reads every path-shaped token on a line (JSON arrays, quoted, `path:line`, parenthesized), and decides what is a test file with the import graph's own isTestFile, so a test-file rule change there (bats, #3177) reaches manifests without a second regex. A manifest that cannot start is "unknown" (widens), like a non-zero exit. This is the manifest-parser half of #3176 by @vocodestudios; the import-graph half (tsconfig aliases, Next.js route mapping) ships in a separate PR. test/pregate-manifest-paths.test.ts drives the CLI with a bracketed route test in the fixture's Windows-only lane and asserts its requires-remote obligation; it failed on main (requires_remote was []). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci(windows): windows-pregate-e2e drives the #3197 paths natively A windows-latest job (Bun 1.4.2) builds a fixture repository and runs gstack-restamp --dry-run, gstack-regen check and write, gstack-evidence run and gstack-gate-diff from their TypeScript entry points, asserting a real tree fingerprint each time; times a question-log hook cold and warm and checks it cached its Git Bash resolution; and checks that a missing GSTACK_GIT_BASH refuses with BASH_UNAVAILABLE and lists the candidate. The journey runs twice: under the runner's Git for Windows and under a pinned PortableGit 2.56.0.2 (SHA-256 verified), found only through `git --exec-path`. gstack-pregate run joins it with item 10b. The workflow is registered in scripts/test-pr-profile.ts FREE_ONLY_PR_FILES (no paid case reads it), recorded as a non-behavioral HARNESS_VERSION decision in scripts/harness-version.json. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(setup.ps1): resolve Git Bash by the shared fixture table (#3197) test/setup-ps1.test.ts now drives setup.ps1 through every row of test/fixtures/windows-bash-resolution.json, the table that pins lib/script-invocation.ts, instead of a hand-mirrored copy. Two rows failed and are fixed here: - an override and alias that differ only in slash direction no longer print the differ warning; - the root git --exec-path names is also searched for usr\bin\bash.exe (Git for Windows on arm64). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(windows): isolate the no-bash case and launch pregate as the product does (#3197, #3176) windows-free-tests run 38813751242 failed two tests this layer added. Both were fixture defects on a real Windows host, not product defects: - gbrain-spawn-windows-shell "returns null when Windows has no bash" stubbed only `exists`. The resolver's PATH step asks the real Bun.which and found the runner's MSYS bash, which is correct. The case now also stubs `which` and `gitExecPath`, so it really means "no bash anywhere". - pregate-manifest-paths spawned the extensionless bin/gstack-pregate directly. CreateProcess cannot exec a shebang, so nothing ran and stdout was "". It now launches through lib/script-invocation's runScriptSync, gstack's own Windows invocation, so the case runs the manifest lane end to end on Windows instead of being excluded. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci(windows): the missing-bash step survives the refusal it expects (#3197) GitHub runs `shell: bash` as `bash -eo pipefail`, and the step's own `set -uo pipefail` does not turn -e off. So when gstack-restamp refused, as the step expects, `OUT=$(...)` aborted the script before `CODE=$?` and before any output was printed: exit 1 after 0.5 s with nothing in the log (PR #3209, job 116729693492). The capture is now `OUT=$(...) && CODE=0 || CODE=$?`. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(pregate): the manifest-lane case expects the host's own remote lanes (#3176) Once 8b2f297cc made the case run on Windows, windows-free-tests run 38824886195 (shard 4) showed the expectation itself was Linux-only. pregate owes a lane remotely when its runner platform is not the host's (lib/pregate/workflows.ts). On a Windows host the fixture's Windows lane runs locally, and the Ubuntu `free-tests.yml/unit` lane is the remote obligation; that is the record Windows produced. The case now derives the owed lanes from the host the same way. On Windows it also requires `ran: node --test 'app/(shop)/[id]/page.test.js'`: there the route reaches the local run only through the manifest's whole path. With a cut manifest path (page.test.js) the local set is empty, checked through buildContext({ platform: 'win32' }) + selectLanes. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci(windows-setup): expect 31 skipped setup.ps1 cases now that the shared table drives it Layer 2 drives setup.ps1 through the 16 shared rows of test/fixtures/windows-bash-resolution.json; like the 14 existing resolution rows they run under pwsh on Linux and skip on Windows. The case list is still asserted exactly (4 pass, 0 fail, 31 skip). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(ship-measure): give the CLI tests a private HOME (#3162) Every bun run test left ~/.gstack/projects/ship-measure-cli-*/evals and sweep-cli-fake-*/evals in the developer's real home, and the free-suite runner flagged them ("real home changed ... Give the writer a private HOME/GSTACK_HOME"). ship-measure's diagnostic-dir check calls getProjectEvalDir(), which builds the eval dir from os.homedir(), and these two CLI tests passed the real HOME while overriding only the state root. Both now set HOME and USERPROFILE to the test's own state dir. The sweep test also runs on the Windows lane, where os.homedir() reads USERPROFILE. test/ship-measure.test.ts:79 already gives its config test a private HOME the same way. getProjectEvalDir() itself is unchanged: whether eval history should follow GSTACK_HOME is left open in #3162. Fixes #3162 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * test(ship-measure): prove the sweep CLI never writes under the parent HOME (#3162) Reviewer test for #3163 (adopted from y$un_, forrest.sun527): points the parent HOME at a sentinel with a stub global gstack-slug and asserts no .gstack dir appears there. Fails on 47d639a (the sentinel gets .gstack/projects/leaked-slug/evals); passes with #3163. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(redact): isolate fixture git from inherited hooks Fixture git was spawned with the parent environment, so a developer's core.hooksPath ran on the local push and rejected it (#2967). The helper blanks the global and system files and drops GIT_CONFIG_COUNT and GIT_CONFIG_PARAMETERS. A hooksPath set in the fixture repo still runs. * test(redact): blank GIT_CONFIG_GLOBAL with /dev/null on every platform (#2967) Follow-up to #3156 (adopted from Lockyer228): Git for Windows rejects GIT_CONFIG_GLOBAL=NUL (the repo convention is EMPTY_GLOBAL_GIT_CONFIG = '/dev/null' in lib/cso/process.ts), so both fixture helpers use /dev/null everywhere. Reviewer test: a hooksPath in the default global files under HOME/.gitconfig and XDG_CONFIG_HOME/git/config cannot reject the fixture push; it fails with the inherited environment (the 47d639a behavior) and passes with the isolated env. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: gstack-config compares whole root paths and prints a runnable recovery command - report_root_disagreement compared word-split values, so two variables naming the same directory with a space were reported as disagreeing. Compare each complete value instead. - The privacy-key recovery hint single-quoted the root and left the script path bare; an apostrophe or space made it unrunnable. Quote with printf %q. - On Bash 3.2 (macOS /bin/bash) a failed `.` under set -e exits before the `||` fallback, so a missing gstack-state-root.sh exited 1 silently and test/state-root-resolver-failure.test.ts failed there. Check readability first. - The merge fixture now lives under a path with a space and an apostrophe, executes the printed command, and asserts same-directory variables agree. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * test(config): pin the %q-quoted recovery command and run it from a spaced install path Follow-up to #3186 (adopted from davidfragnoli-lang). Intentional pin change: the fix line's GSTACK_STATE_ROOT='<legacy>' pin becomes the exact bash printf %q form of the legacy root (the PR loosened it to a prefix check; this restores an exact pin) and the original test name is kept. Reviewer test: copy bin/ to a path containing a space and an apostrophe; the printed fix: command runs cleanly and flips the merged value. Fails on 47d639a (unquoted $_SELF), passes with #3186. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(gstack-gbrain-sync): fail when a star gitignore already ignores the pin ensureGbrainSourceGitignored appends .gbrain-source even when git check-ignore already excludes that path. The extra line dirties a tracked ignore-everything gitignore. * fix(gstack-gbrain-sync): skip the pin line when git already ignores it ensureGbrainSourceGitignored asked only for a literal .gbrain-source line. An ignore-everything star already excludes the pin, and the extra line left the tracked gitignore dirty. * fix(gbrain-sync): only a tracked .gitignore can stand in for the pin line Follow-up to #3178 (adopted from KuroChen). The skip now requires `git -c core.excludesFile= check-ignore -v` to name a tracked .gitignore (not global excludes, not .git/info/exclude, not a negation), so a pin ignored only on this machine still gets the shared line teammates need (#1384). Tests: the two git init spawns get timeouts (they failed the spawnSync tripwire), fixtures isolate HOME/XDG_CONFIG_HOME, and the PR's star-gitignore fixture stages its .gitignore (intentional fixture change: the contract is a tracked file). Reviewer tests: global excludes only, info/exclude only, an untracked star .gitignore, and a re-include each still append; all three fail on the PR head. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(skill-end): log the completion event before the final drain (#3198) gstack-skill-end drained and pushed before it appended its own completed timeline event, and gstack-timeline-log backgrounded its enqueue, so a full-tier end boundary returned with its latest event unpushed. The completion log now runs before the drain and the logger waits for its enqueue (one config read and a spool write; it exits early when sync is off or the session is unattended). Every consent, secret-scan and queue-lock gate is unchanged; the stale "local-only, never sent anywhere" comment is replaced. Patch and regression test from Kkkkkuro (#3198): 2 pass / 5 fail on 47d639a, 8/8 with the fix. Reviewer test: with artifacts_sync_mode off the completion is written locally with no queue entry and no push. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(pregate): map Next.js route paths and tsconfig path aliases to their tests QUOTED excluded ( ) [ ] +, so a test naming app/(app)/page.tsx in a string never matched. resolveRef never read tsconfig compilerOptions.paths, so an import through @/ resolved to nothing. Both were PREGATE_NO_LANE false negatives in a Next.js App Router repo whose tests did name the files. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(pregate): TypeScript alias precedence, relative extends and a no-lane explanation Follow-up to #3176 (adopted from vocodestudios). Path aliases now follow TypeScript's choice: an exact pattern, else the wildcard with the longest prefix, targets tried in order. When the chosen pattern resolves nothing, every plausible reading (other matching patterns, baseUrl, the repo root) gains the edge, so uncertainty selects more tests, never fewer. Relative extends chains are followed up to MAX_TSCONFIG_EXTENDS (4) hops, with baseUrl and paths resolved against the config that declares them. Trailing commas are dropped by the JSONC tokenizer (never inside a string) instead of a whole-text regex. A touched file with no lane now gets explain lines naming the import specifiers in test files that resolved to no repo file, any extends hop that was not followed (with the limit), and the hint to declare the file under dependencies or report the resolver gap. The lines ride testsFor's provenance, which lanes already pushes to --explain. Reviewer tests: overlapping aliases in both key orders, exact vs wildcard, target fallback, the union case, a two-hop extends chain, a string containing ',]', and the depth-limit explanation. Five fail on the PR head; all 12 pass. The manifest-parser half of #3176's follow-up (lane-selection.ts) ships in PR 2. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(browse): reap PTY children on agent shutdown * fix(browse): reap a terminal-agent PTY's whole process group at shutdown (#3147) Follow-up to #3148 (adopted from Y4NN777). The PTY child leads its own session and process group; its identity (pgid, sid, leader start time) is recorded at spawn and stays checkable after the leader exits. Disposal schedules a group reap after PTY_SHUTDOWN_GRACE_MS that, unlike the direct-child SIGKILL fallback, is not cancelled when the leader exits, and shutdown reaps every pending group before exiting, so descendants that ignore SIGHUP no longer outlive the agent. Only proven members are signalled: same pgid and sid, started no earlier than the leader, and nothing at all when the leader's PID is held by a process with another start time. Linux only (/proc); other platforms keep the direct-child behavior. During the shutdown grace the server answers 503 and no new PTY is spawned. Test changes to the PR's own test (intentional): the agent is spawned with process.execPath and the PTY child traps INT TERM HUP, so the case proves the SIGKILL fallback instead of passing on the kernel hangup. Reviewer tests: a HUP-immune grandchild is dead within the grace plus 1 s; an early-exiting leader's surviving descendant is reaped; a session that completed before shutdown still has its group reaped; unit cases for a foreign group and a reused leader PID. All four integration cases fail on 47d639a; three fail on the PR head. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * build(deps): bump the github-actions group with 5 updates Bumps the github-actions group with 5 updates: | Package | From | To | | --- | --- | --- | | [actions/upload-artifact](https://github.com/actions/upload-artifact) | `7.0.1` | `7.0.2` | | [actions/download-artifact](https://github.com/actions/download-artifact) | `8.0.1` | `8.0.2` | | [actions/setup-node](https://github.com/actions/setup-node) | `7.0.0` | `7.1.0` | | [ossf/scorecard-action](https://github.com/ossf/scorecard-action) | `2.4.4` | `2.5.0` | | [github/codeql-action/upload-sarif](https://github.com/github/codeql-action) | `4.38.2` | `4.38.3` | Updates `actions/upload-artifact` from 7.0.1 to 7.0.2 - [Release notes](https://github.com/actions/upload-artifact/releases) - [Commits](https://github.com/actions/upload-artifact/compare/043fb46d1a93c77aae656e7c1c64a875d1fc6a0a...cf430e030ddbb5b0abf93d22962f4752f3646cd9) Updates `actions/download-artifact` from 8.0.1 to 8.0.2 - [Release notes](https://github.com/actions/download-artifact/releases) - [Commits](https://github.com/actions/download-artifact/compare/3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c...9000827ccba6bdab643e8b6fd33ac0654aef8333) Updates `actions/setup-node` from 7.0.0 to 7.1.0 - [Release notes](https://github.com/actions/setup-node/releases) - [Commits](https://github.com/actions/setup-node/compare/820762786026740c76f36085b0efc47a31fe5020...949feb2413d6458794dcd2491c4babbbce0c15c1) Updates `ossf/scorecard-action` from 2.4.4 to 2.5.0 - [Release notes](https://github.com/ossf/scorecard-action/releases) - [Changelog](https://github.com/ossf/scorecard-action/blob/main/RELEASE.md) - [Commits](https://github.com/ossf/scorecard-action/compare/2d1146689b8cda280b9bc96326124645441f03bc...fa7117db83c52d787ae5a89f350999701505d78e) Updates `github/codeql-action/upload-sarif` from 4.38.2 to 4.38.3 - [Release notes](https://github.com/github/codeql-action/releases) - [Changelog](https://github.com/github/codeql-action/blob/main/CHANGELOG.md) - [Commits](https://github.com/github/codeql-action/compare/2892aa5e19bbd11bc0cff5427e3b750a04d9e3c2...24c54180a607b1449ed407dd24f251e4e9147c8d) --- updated-dependencies: - dependency-name: actions/upload-artifact dependency-version: 7.0.2 dependency-type: direct:production update-type: version-update:semver-patch dependency-group: github-actions - dependency-name: actions/download-artifact dependency-version: 8.0.2 dependency-type: direct:production update-type: version-update:semver-patch dependency-group: github-actions - dependency-name: actions/setup-node dependency-version: 7.1.0 dependency-type: direct:production update-type: version-update:semver-minor dependency-group: github-actions - dependency-name: ossf/scorecard-action dependency-version: 2.5.0 dependency-type: direct:production update-type: version-update:semver-minor dependency-group: github-actions - dependency-name: github/codeql-action/upload-sarif dependency-version: 4.38.3 dependency-type: direct:production update-type: version-update:semver-patch dependency-group: github-actions ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(model-policy): track the upload-artifact v7.0.2 pin from #3175 Intentional pin change: test/model-policy-workflow.test.ts asserted actions/upload-artifact@043fb46d…; dependabot #3175 moves the workflow to cf430e03… (v7.0.2, verified against the upstream tag). The pin tracks the workflow. #3175's free-tests.yml hunk is left out of this PR (free-tests.yml is a #3190 file; it is re-bumped in PR 5). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(model-policy): its upload-artifact pin matches the eval workflows' pin Reviewer test for dependabot #3175: the model-policy workflow's single upload-artifact pin equals the pin evals.yml, evals-periodic.yml and windows-free-tests.yml use, so a group bump that misses one workflow (or the hard-coded pin above) is caught here. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * build(deps): hold Playwright minor/major bumps behind the windowsHide patch (#2923) Dependabot #2923 bumped playwright to ^1.64.0 and dropped the patchedDependencies entry keyed to playwright-core@1.62.1, which keeps windowsHide on Windows (#2160, #1989). The bun ecosystem now ignores only semver-minor and semver-major updates for playwright and playwright-core; patch updates still flow. The 1.64 migration (re-key the patch, the Dia/cookie qualification pins, the arm64 artifact name) is filed with owner Garry, revisit 2026-11-15. Test fails on 47d639a (no ignore rule). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(readme): drop the stale skill lists users pasted into CLAUDE.md (#3169) README's install prompt and troubleshooting block each carried a skill list for CLAUDE.md; both were stale (18 shipped skills missing) and they disagreed. Claude Code lists installed skills itself, so both now keep only the /browse rule, and the troubleshooting entry says to delete an old pasted list. New free test: any comma-separated skill list in README.md or CLAUDE.md must name exactly the shipped skills (with a negative control for the detector). Fails on 47d639a; passes now. Reported by the #3169 issue author. The matching doctor warning for pasted lists ships in PR 5. Intentional pin change: test/test-value-bar.test.ts no longer expects the README skill list to name /test-audit twice; it now expects that list to be gone (0 occurrences), the registration this commit removes on purpose. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore(osv): image-size has a fix; html-to-docx's ^1.0.0 pin blocks it (#2753) The image-size ledger said no fixed release exists. OSV lists 2.0.3 as fixed for GHSA-5p2g-fcmc-qvqq and GHSA-w3rx-r6r6-pgpr (checked against api.osv.dev), but html-to-docx@1.8.0 pins image-size ^1.0.0 and there is no fixed 1.x, so the fix is a cross-major override. Both entries now say so and name the upgrade trigger; the 2026-11-30 expiry is kept. New test checks the wording and that bun.lock still shows the stated pin (it fails on 47d639a). Correction first raised on #2753 by sonukapoor. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(ios-qa): forward GSTACK_IOS_LAUNCH_ENV to devicectl launches (#1796) Reimplements only the launch-environment half of #1796 (credit Bmathews721; the session-cache half is superseded by #3132's design and had state-root and symlink-write problems). devicectl.ts parses GSTACK_IOS_LAUNCH_ENV as a JSON object of string to string; launchEnvArgs() returns the --environment-variables argv (empty when unset or {}) and launchApp passes it before the bundle id. Invalid JSON, a non-object, a non-string value, a bad name or a key in the debug bridge's reserved GSTACK_ namespace refuses before any launch with the new result code IOS_LAUNCH_ENV_INVALID (the detail names keys and types, never values). launchEnvArgs is exported for the forced-relaunch path in tunnel-bootstrap.ts. Adds the result-code row (bin/gstack-doctor-components.sh regenerated by gen:skill-docs), a troubleshooting entry under its exact text, the pregate-no-lane entry's explain note, and the how-to section with an example. New test fails on 47d639a (module load: no parseLaunchEnv). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(deps): declare sharp and clear two transitive advisories sharp is imported in four files, including browse/src/screenshot-size-guard.ts, and test/dependency-security.test.ts asserts a >=0.35.4 floor on it and loads it. It was declared in no dependency field, reaching the tree only through @huggingface/transformers with the overrides pin forcing the version. Declare it at ^0.35.4, matching the floor that test already asserts. Upgrade @huggingface/transformers to ^4.3.0, which clears sprintf-js@1.1.3 and aligns the sharp override with what the parent declares: 4.2.0 declared sharp ^0.34.5 while the override pins 0.35.5, which is outside that range, and 4.3.0 declares ^0.35.4. Upgrade @anthropic-ai/claude-agent-sdk to 0.2.141, which clears @anthropic-ai/sdk@0.81.0. The existing overrides entry for sharp is left in place. * test(deps): sharp is declared and its override satisfies every asking range Reviewer test for #3145 (adopted from sonukapoor): sharp must be a declared dependency, and the pinned overrides.sharp must satisfy both that declaration and every lockfile package that depends on sharp (@huggingface/transformers included). Fails on 47d639a (sharp not declared; transformers 4.2.0 asked for ^0.34.5 against a 0.35.5 pin). Classifier smoke on the changed tree (transformers 4.3.0, onnxruntime-node 1.30.0, sharp 0.35.5, claude-agent-sdk 0.2.141): the real sidecar entry bundled for Node with a private state root, and the classifier in-process under Bun, each downloaded the TestSavantAI model fresh, reported testsavant: ok, and returned scores identical to 47d639a's tree on five inputs, including a >512-token input that exercises the truncation override. dependency-security, deps-smoke, overlay-sdk-cancel-eof, security-classifier and screenshot-size-guard pass; typecheck:test reports no new diagnostics. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(gbrain-sync): the no-bash skip names GSTACK_GIT_BASH and how to set it (#3197) The brain-sync stage's Windows skip line told users to set GSTACK_BASH. After the fix wave the canonical override is GSTACK_GIT_BASH, with GSTACK_BASH as a deprecated alias (plan correction 9). The summary is now the exported NO_BASH_SUMMARY: it names GSTACK_GIT_BASH first and GSTACK_BASH as the old name, and gives the two recipes that reach Claude Code (a PowerShell user environment variable plus a Claude Code restart, or the "env" block of ~/.claude/settings.json). Minimal on purpose: once PR 2 lands, this switches to lib/script-invocation.ts noBashMessage(). Until then lib/gbrain-exec.ts still reads only GSTACK_BASH, so this line is accurate only with PR 2 merged first. New test test/gbrain-sync-no-bash-message.test.ts fails on the previous commit (NO_BASH_SUMMARY not exported) and passes now. Handoff from Lane C (PR 2). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(ios-qa): the forced relaunch carries GSTACK_IOS_LAUNCH_ENV too (#1796) bootstrapTunnel's relaunchApp (an app whose boot token an earlier daemon consumed is relaunched once with --terminate-existing) built its own devicectl argv and dropped GSTACK_IOS_LAUNCH_ENV, so an env-gated debug bridge vanished after the one relaunch the howto says carries it. It now uses launchEnvArgs(); an invalid value refuses the relaunch with launch_failed and the IOS_LAUNCH_ENV_INVALID detail before anything is terminated. Two new tests in ios-qa/daemon/test/devicectl-launch-env.test.ts drive bootstrapTunnel through a consumed-token device: both fail on the previous commit (relaunch argv lacks --environment-variables; the invalid value still terminates and relaunches) and pass now. ios-qa daemon: 167 pass. tunnel-bootstrap.ts was assigned to Lane D by the coordinator for this fix. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci(version-gate): check the version queue only on PRs into main Stacked layer PRs carry no VERSION stamp by design (the release layer stamps once), so the queue check failed on any layer touching package.json. The queue and its collision rule only describe main; a PR into main is still checked exactly as before. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(browse): scope the SIGTERM PTY-reap case to POSIX signals (#3147) windows-free-tests run 38813751242 (shard 6) failed "SIGTERM reaps every active PTY child before terminal-agent exits" with "timed out waiting for pty-child.pid", serially and on retry. Diagnosis: invalid test expectation on Windows, not an agent defect the test can observe. The contract under test is the agent's graceful shutdown, its process.on('SIGTERM'/'SIGINT') cleanup in terminal-agent.ts. On Windows, Bun's subprocess.kill('SIGTERM') is libuv's TerminateProcess, so that handler never runs there; and the PTY fixture is an extension-less `#!/bin/bash` script, which CreateProcess cannot launch, so the child never starts (the timeout is at the pid file, after the port, token, grant and WebSocket all succeeded). The file's other integration cases were already Linux-scoped; this one now skips only on win32 and still runs on Linux and macOS. The pure ownership unit tests in the file keep running on Windows. Open, not covered by any test: whether a ConPTY child outlives a hard-terminated agent on Windows. Testing it needs a Windows-launchable terminal fixture, which BROWSE_TERMINAL_BINARY (one executable, fixed argv) cannot express without a product change. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(plan-review): bound the native outside voice without TaskOutput (#3182) Claude Code 2.1.277 removed TaskOutput, so the plan-review native fallback's preflight always failed and users without the Codex CLI never got a second voice. The fallback now uses primitives the host still enforces: a background `sleep 300` Bash timer (its exit re-invokes the parent; the 2.1.300 sleep block applies only to foreground commands), a background Plan dispatch whose completion arrives as a <task-notification>, and TaskStop for whichever task loses. Only a matching completed notification that beats the timer counts; interim ("is waiting on its own background work"), turn-limit, foreground and late results get no credit. The "[Subagent hand-back]" header (2.1.277) is treated as framing. The unavailable line now names its cause and fix, ends with OUTSIDE_VOICE_UNAVAILABLE (new result code + troubleshooting entry), and the review-log row carries unavailable_reason. The bounded-wait prose was tightened so plan-ceo-review and plan-eng-review stay under their existing size ceilings (no ratchet raise for this item). Intentional pin change: test/run-in-background-guidance.test.ts hasBoundedOutsideVoiceWait and the dispatch-contract cases now pin the timer/notification/TaskStop contract instead of TaskOutput's envelope. bin/gstack-doctor-components.sh is regenerated from lib/result-codes.ts. Reported by HuellintonMota in #3182. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(bin): gstack-ceo-plan-find locates the CEO plan for a branch (#280) /plan-ceo-review saves its scope decisions under the state root's ceo-plans/, but no plan review can find them: only /design-html reads that directory, newest file first. This helper is the CEO-plan sibling of gstack-design-doc-find, so /plan-eng-review can call one command instead of a glob in prose. It prints the newest top-level plan whose "Branch:" header names the branch, compared the way gstack-slug writes BRANCH (feat/x matches feat-x), else the newest plan, else nothing. Subdirectories are not read. A usage error exits 2. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(plan-eng-review): read the CEO plan in the Design Doc Check (#280) /plan-eng-review never looked in ceo-plans/, so an eng review after /plan-ceo-review ran without the scope that review accepted, deferred or skipped. capy-ai closed #414 asking for this focused fix, and TODOS.md scopes it as a gstack-ceo-plan-find sibling of gstack-design-doc-find. The Design Doc Check now prints "CEO plan found: <path>" or "No CEO plan found" after the design doc line, and the prose says what to read the plan for. The data-not-instructions rule names the CEO plan too, since another agent may have written it. Only plan-eng-review changes: the shared {{DESIGN_DOC_DISCOVERY}} block and the branch-scoped review log are untouched. Reported by @chancheuklap in #280. main left plan-eng-review 4 bytes under its parity cap, so the +325 bytes raise maxSizeRatio to the measured 1.2196, noted the way earlier growth was. Fixes #280 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(plan-eng-review): disclose a CEO plan borrowed from another branch (#280) Review changes on top of #3159 (szsunyuan / y$un_): - gstack-ceo-plan-find keeps stdout a bare path or empty; when it falls back to another branch's plan it prints one stderr line, "CEO plan found (from branch <b>, not <current>): <path>", with control characters stripped from the plan header ("unknown" when it has none). - The Design Doc Check tells an interactive reviewer to ask before using such a plan, and a spawned session to use it and quote the disclosure. - The Design Doc Check prose is tightened so plan-eng-review fits the owner-approved 1.2196 ceiling (measured 151,950 / 124,597 = 1.2195). Reviewer tests: test/ceo-plan-find-cross-branch.test.ts (5 of 7 fail on the Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> #3159 head). The design-doc finder's matching disclosure stays deferred. * fix(test): credit abutting section chunks whose edge bytes repeat (#3182) detectSectionReads trims the longest suffix/prefix overlap between consecutive Bash outputs. Two chunks that abut exactly (tail -c +N after a chunk ending at N-1) can share an edge byte by chance; the trim then drops a real byte and a fully printed section reads as incomplete. #3182's review-sections edit moved plan-ceo-review's 66,999-byte boundary onto "cur|rent", which turned the existing byte-range test red. The detector now also checks the plain concatenation; a gap still refuses. Detector/fixture defect, not a product change. New regression case in test/section-capture-native-tools.test.ts fails without the fix. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(changelog): fix wave 2026-10-15 release notes Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * v1.91.104.0 fix: the 2026-10-15 issue wave Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(qa): probe each documented input rule, not only its boundary values The paid gate's qa-functional-cli-report run (38829994639) probed zero and an unsafe integer but never a non-digit amount, so it missed the planted parseInt defect ("Amounts contain only ASCII digits") and reported no defect. The functional contract map's invalid-input row now asks for one probe per documented input rule (allowed characters, format, sign, range, arity). test/qa-functional-prompt.test.ts replays a captured CI Read of system-functional.md; its completed-method variant now feeds the current section bytes, so the validator check keeps its omitted/pending negative controls without pinning the old wording. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * v1.91.106.0: restamp the fix wave above v1.91.105.0 Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(release): keep the wave's dependency bumps through the main merge Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> Co-authored-by: Bryan Stone <aegixx@gmail.com> Co-authored-by: vilano93 <244097767+vilano93@users.noreply.github.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> Co-authored-by: aftabkh4n <akobkz@gmail.com> Co-authored-by: Benjamin D. Smith <benjamin.smith@binarysword.com> Co-authored-by: Jess Sullivan <jess@sulliwood.org> Co-authored-by: NetrioGit <5wngh@naver.com> Co-authored-by: y$un_ <forrest.sun527@gmail.com> Co-authored-by: Lockyer <135391289+Lockyer228@users.noreply.github.com> Co-authored-by: davidfragnoli-lang <249433777+davidfragnoli-lang@users.noreply.github.com> Co-authored-by: KuroChen <kurochen_macmini@KuroChendeMac-mini.local> Co-authored-by: AV <vo.quanganh@gmail.com> Co-authored-by: Y4NN777 <171065166+Y4NN777@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Sonu Kapoor <sonukapoor@gmail.com>	2026-10-16 22:00:32 +00:00
+2232 people	8bb6d65270	v1.91.66.0 fix: /autoplan without permission prompts after background reviewers, 34 contributor PRs from the backlog triage (#3087) ... * docs: fix CONTRIBUTING.md test-tiers link in TESTING_INTERNALS 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> * ci: refresh GitHub Actions SHA pins (setup-buildx 4.4.1, build-push 7.4.0, attest 4.2.2, setup-node 7.0.0) 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> * docs(openclaw): stop advising a per-spawn env for spawned sessions 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> * fix(benchmark): scope /benchmark routing to web page performance /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> * fix(llms.txt): link skills by generated path, drop host-skipped skills 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> * fix(ci): install Bun from the SHA-256-verified release archive in GitLab CI and Ubicloud setup 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> * fix(browse): viewport auto unpins a pinned viewport without a restart `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> * fix(browse): screenshot accepts --clip=x,y,w,h and --selector=<css> 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> * fix(benchmark): price Codex cached input at the cache rate, stop calling Gemini OAuth ready 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> * fix(review): catch loosened-input consumers and stale user-facing strings 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> * fix(global-discover): bucket Codex sessions by originator 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> * fix(hook-check): cover skill frontmatter hooks, sourced helpers, conflict markers and the caller's tsconfig 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> * fix(review): extend defensive-security framing to the security specialist and Red Team 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> * fix(team-init): make the required-mode hook shell-neutral (node CommonJS, no shell variables) 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> * fix(setup-gbrain): register the gbrain MCP through bun.exe on Windows so no console window opens 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> * fix(hosts): rewrite every "Agent tool" phrasing for agent-runtime hosts 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> * fix(setup-deploy): Vercel auto-deploys only when connected to the Git repo /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> * fix(retro): persist recommendations so the next retro detects follow-through /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> * fix(global-discover): count the interactive Codex CLI (codex_cli_rs) in its own cli bucket * feat(developer-profile): --reconcile backfills office-hours tenure from timeline.jsonl 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> * fix(autoplan): the publication hook approves /autoplan's own Reads after the skill turn 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> * fix(autoplan): restore point and phase artifacts live in the project's .gstack/tmp/autoplan/ 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> * test(evals): autoplan-guard-pty fails on any permission card after the reviewer's notice turn 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> * docs(autoplan): permission cards after a background reviewer, and where /autoplan keeps its files Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(outside-review): read a trailing '— Medium.' or '(High)' severity on a finding line, the shape Codex now writes * feat(design): honor OPENAI_BASE_URL for every design API call 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> * review: testing specialist treats negative assertions as decisions 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> * review: security specialist checks authorization a route-guard read misses 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> * review: zero findings is valid; suppress six common false positives 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> * docs(todos): parked contributor ideas by theme; /autoplan permission follow-ups * design-review: capture code tokens before universal principles /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> * feat(sidebar): add a terminal text-size picker to the toolbar 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> * feat(design-shotgun): generate with Codex's built-in $imagegen on Codex 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> * voice: ban the "load-bearing" stock phrase 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> * voice: reply in the language of the user's latest message 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> * feat(redact-prepush): committed exact-span allowlist at .gstack-redact-allowlist The pre-push hook never fed the engine's allowlist option, so a reviewed, known-benign value (a public dev-compose URL, a documented sample key) warned or blocked every push, and the only ways out were a bypass or reshaping code until the detector stopped matching. The hook now reads the repo-root .gstack-redact-allowlist from each pushed commit (never the working tree), one exact matched span per line with # comments. Only a finding whose matched text equals an entry is suppressed: a password alone, a substring, or a different key still reports and still blocks, and engine.* unscanned findings are untouched. Every push that carries entries prints the entry count and each suppressed finding's rule and file line. Oversized files (over 64 KiB) are ignored. gstack.redact.allowEmail keeps working as before. Co-authored-by: Boyard Engels <boyard.engels@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(brain-sync): opt-in removal publishing with a bulk-removal valve gstack-brain-sync never published a removal: a deleted synced file, or the old directory after a project slug migration, stayed on the remote forever and gbrain indexed both copies. New setting artifacts_sync_removals (off by default). When on, each drain commits and pushes, receipted like every push, the removal of tracked files that are gone from disk and match the sync allowlist. Transcript pages are never removed here, and a decision log goes only together with its active snapshot. One valve: a drain that would remove more than 20 files at once publishes none and says so. `gstack-brain-sync --publish-removals` lists the pending removals and `--publish-removals --yes` publishes them on demand, whatever the setting. Co-authored-by: Jey2311 <5177215+Jey2311@users.noreply.github.com> * feat(windows): setup.ps1 checks prerequisites and runs ./setup in Git Bash A PowerShell entry point for Windows users. It checks that Git for Windows, Bun and Node.js are on PATH (printing the winget command for each missing one and changing nothing), finds Git Bash from git.exe rather than a PATH bash that may be WSL's, and runs ./setup from the checkout with every argument passed as its own argv entry to a constant bash script. No argument is interpolated into shell source. ./setup itself is unchanged. Co-authored-by: Jim McKeeth <jim@mckeeth.org> * v1.91.63.0: CHANGELOG, version * fix(ci): link bunx after the SHA-verified Bun install in GitLab CI and the Ubicloud setup * fix(redact-prepush): strip every parent column from combined-diff lines, so a merged release bump is exempt like any other * fix(hook-check): treat a Windows drive path as absolute (cygpath when present), so --list finds the skill hooks from a native caller * fix(windows): owned-read requires the read-only attribute on Windows; setup.ps1 passes arguments NUL-separated through a private file; Windows-only tests expect the owned-read approval * perf(hook-check): bundle every hook's TypeScript entries in one bun process instead of two bun starts per entry (seconds each on Windows) * perf(hook-check): read all skill frontmatter in one awk and scan conflict markers with one grep per hook (half the process starts) --------- Co-authored-by: thearbajonart <334330110+thearbajonart@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: DanCanadian <211164803+DanCanadian@users.noreply.github.com> Co-authored-by: Nader Helmy <31414549+creatornader@users.noreply.github.com> Co-authored-by: Nader Helmy <creator.nader@gmail.com> Co-authored-by: Zee Zheng <228040220+spacegeologist@users.noreply.github.com> Co-authored-by: Jack Thomas <17882510+loulanyue@users.noreply.github.com> Co-authored-by: Jayesh Betala <jayesh.betala7@gmail.com> Co-authored-by: techcenter68 <75930234+techcenter68@users.noreply.github.com> Co-authored-by: Mattias Petersson <mattias.petersson@gmail.com> Co-authored-by: Arno V <38716+aversini@users.noreply.github.com> Co-authored-by: 0xDevNinja <manmit0x@gmail.com> Co-authored-by: Benjamin D. Smith <7134745+BenjaminDSmithy@users.noreply.github.com> Co-authored-by: Brian Majewski <1693720+bmajewski@users.noreply.github.com> Co-authored-by: neallee2012 <1499497+neallee2012@users.noreply.github.com> Co-authored-by: Max Hogan <max@maxhogan.dev> Co-authored-by: maxpetrusenkoagent <280464918+maxpetrusenkoagent@users.noreply.github.com> Co-authored-by: katlun-lgtm <264247399+katlun-lgtm@users.noreply.github.com> Co-authored-by: mikehasa <91774998+mikehasa@users.noreply.github.com> Co-authored-by: Briac <137724549+briacSck@users.noreply.github.com> Co-authored-by: JackJin <1037461232@qq.com> Co-authored-by: EmilianoU26 <314541067+EmilianoU26@users.noreply.github.com> Co-authored-by: frosimanuel <frosimanuel@gmail.com> Co-authored-by: Tom Lam <tomlam0811@berkeley.edu> Co-authored-by: Yotam <yotsurfing@gmail.com> Co-authored-by: Jinzhe <hwang.phy@gmail.com> Co-authored-by: Xianying Tan <shrektan@126.com> Co-authored-by: Boyard Engels <boyard.engels@gmail.com> Co-authored-by: Jey2311 <5177215+Jey2311@users.noreply.github.com> Co-authored-by: Jim McKeeth <jim@mckeeth.org>	2026-10-08 17:40:06 +00:00
Garry Tan	55f8151fbe	v1.91.30.0 fix: honest eval failure reports, Bun floor with safe auto-update, make-pdf and /review on Codex (#3033) ... * docs: approved reliability follow-ups plan (Oct 2026) * D1: score overlay wrong answers as comparison results (contract v4) A completed answer that fails the fixture's output check is now a valid measurement with taskCorrect false and answerError set, in either arm. Only execution, scope and metric failures invalidate a trial. ON correctness still gates the case, so an OFF wrong answer stays in the comparison. OVERLAY_CONTRACT moves to v4; v3 verdicts are not reinterpreted. Replays the 37198445662 sonnet trials (OFF-0 wrong). * C4: score auq-matrix substance with a 3-sample judge panel Each skill keeps one native capture in the same execution; the recommendation-substance grader now runs as a JUDGE_PANEL_SAMPLES panel on that capture and gates on the mean against the unchanged minimum of 4. A failed sample fails the panel without resampling. Approved at the gate 2026-10-04 for censuses after this change. * E1: one Bun version source; setup refuses below the 1.3.3 floor, updater checks before advancing bin/gstack-bun-version.sh holds the security floor (1.3.3) and the tested version (1.4.0, the CI pin and engines.bun). setup refuses Bun below the floor before writing anything, warns between floor and tested, warns and continues on an unparseable version, and prints a 1.4.0 install hint. Prereleases sort below their release (semver). gstack-session-update now fetches, reads the incoming release's floor and checks the bun setup will run before fast-forwarding to that exact revision; below it the update is held with reason bun-too-old and a resume command, leaving the revision and installs untouched. Fixture copies of setup (team-mode, claude-code migration) now include the sourced file; the slow-git lock test sleeps on fetch, the updater's network step. * E3: record the owned Chromium's PID over CDP so the #2709 reap runs on Playwright 1.62 Playwright 1.62's Browser has no process(), so chromiumProcInfo was always null and browse stop never reaped a surviving headless Chromium. The owned headless launch now reads the browser PID from CDP SystemInfo.getProcessInfo (bounded at 2s; a hung or failed call logs once and records nothing). The reaper's start-time and cmdline identity checks are unchanged, so a recycled PID or an externally owned browser is never signalled. * A1: ship docs gate records post-child hashes with gstack-docs-candidate, saves each record once Stored transcripts (37198445662 gate-census-2) show the parent's reads of release files take ~1 s; the parent's own model time dominates (completion 268 s of 392 s, store ~270 s of 387 s), and 45-78 s of it is retyping hash maps, child output and records into several artifacts after the child returns. The child contract is unchanged. * A2: /plan-ceo-review sends the mode handoff line before any other tool call plan-ceo-mode-routing's HOLD SCOPE session spends its 240 s post-selection window on model work: 37176837432 skipped the handoff helper and paraphrased the mode, 37198445662 ran it, then wrote the plan, loaded sections and probed Codex for 114 s before the posture chat. The handoff line is the posture. * B3: accept wrapped unchanged rows in the cropped Edit preview PR run 37176835584 timed out with the floor's owned Edit menu on screen: unchanged diff rows soft-wrap under their gutter with a blank marker column, and a trimmed empty unchanged row keeps only its number. The parser accepted wrapped +/- rows only, so it never verified the owned edit. Both forms are now parsed and still compared with the exact source lines; the captured viewport is replayed with negative controls. * A3: record per-phase headroom diagnosis for docsync, plan-mode-no-op, mode-routing and gate slice 11 * E4: /review Step 1 keeps going when the base fetch fails and reports stale base coverage Under Codex's read-only .git, 'git fetch && merge-base && diff --stat' stopped at the fetch, so the empty output read as 'Nothing to review'. The fetch is now separate, prints BASE_REFRESH fresh or stale with the local base revision, and the review states stale coverage. * D2: reword the format-approach question prompt Both plan-ceo-review-format-approach refusals in census 37195203538 (Fable 5.1 model_refusal_no_fallback, category reasoning_extraction: "duplicating model outputs") were anchored on the session prompt, whose capture instruction asked for the "verbatim" question and "the exact prose you would have shown" in a "format-capture test". The approach case now asks for the same question in the same file as the step's output, without that wording. The other three plan-format cases keep their unchanged prompt (no refusals in 72 trials). * C2: /qa defines its outcome filename fields; QA report templates name the measured timing fields Low judge samples in failing panels named both: qa workflow (37186854666) 'an undefined {user} in the outcome filename', and qa-only workflow (37198445662) 'template asks for Duration / durationMs totals while reporting.md mandates Probe budget and Guarded command time'. The qa union stays under its 1.11 size ratio (93292 of 93294 bytes). * 0.1: session ledger written by the claude -p, Agent SDK, PTY and Codex runners Each armed model session appends one best-effort line to $GSTACK_EVAL_DIR/session-ledger.jsonl: a stable session key, the timeout it armed, monotonic elapsed time, its end reason (completed, session_timeout, observer_timeout, api_error, refusal, aborted, error), one sanitized evidence line and, for stream-JSON runners, a compact liveness summary (longest in-request silence with nothing outstanding, last event kind, tool open at end). Partial messages now stream for every claude -p session and for SDK sessions without a custom query provider (runSharedInteractive opts in); their rows feed only the summary, so transcripts keep their size unless publicStreamDiagnostics is set. Structured refusal and API-error signals win over phrases, and tool results are never read for them. * 0.2: failure_cause beside failure_class, from runner facts and the session ledger One pure failureCauseOf() beside failureClassOf() sets failure_cause (contract > pre_turn_infra > api_error > refusal > provider_stall > session_timeout > observer_timeout > assertion > unknown; no machine-set 'detector') with one bounded evidence line, and failureDetailOf() keeps a Bun matcher's Expected/Received or a judge's failing dimensions in failure_detail. Both record builders (classifyTrialShard, junitCensus) call them and attach the trial's ledger sessions. failure_class, error and TRIAL_ERROR_MAX are computed exactly as before; the new fields are optional, bounded and validated only when present, and a frozen copy of the v1 reader accepts every new record. A provider stall needs partial messages and STALL_WINDOW_MS (120 s, eval-budgets.ts beside HEADROOM_WARN/FAIL) of in-request silence with nothing outstanding; it stays a failure under EVAL_POLICY v1. * E4: fingerprint under a read-only .git via a private object dir owned by review-log Codex's sandbox mounts .git read-only, so gstack-wtree's git add -A could not write blobs and /review lost its start capture. gstack-review-log now creates a private 0700 object directory under TMPDIR, passes it to gstack-wtree (which writes new objects there with the common-dir object store, resolved before exporting, as an alternate, so linked worktrees work), exposes it to the bindReview/checkSharedLibsReuse consumers that read the tree and blobs, and removes it on EXIT/INT/TERM after they finish. gstack-wtree prints one stderr line and exits 1 on a failed write or unwritable TMPDIR instead of printing a partial hash; review-log no longer swallows that line. Standalone gstack-wtree keeps writing to the repository store so git diff between saved snapshots (/ship) still works. * 0.3: red lines name their values, evidence and an after-a-repair command; one published-text sanitizer Each red line in the census report keeps its stored error and adds the machine cause with its evidence, the failure_detail values (Expected/Received, or each failing judge dimension with its mean, sample count and the sample sentence naming it), the slice artifact and shard directory that hold the transcript, a fetch command (eval:pass-rates --run <id> --case <id>), and 'after a repair:' with a command that selects only that case (E2E ids via --case, judges via their selection and an exact test-name filter). A session that completed and failed a check says so instead of 'assertion (success)'. Report text that reaches a PR comment, issue or committed file goes through scripts/lib/published-text.ts: control and bidi characters stripped, credential-scan patterns redacted, mentions neutralized, HTML and link brackets escaped inline, blocks in a fence longer than any backtick run, length capped. Verdicts and collector verdict objects are unchanged. * E2: one make-pdf resolver for readiness and every $P block on env-var hosts make-pdf exported $P from its readiness block, which Codex and the other env-var hosts lose between blocks. binaryAssignment gains 'make-pdf': the MAKE-PDF SETUP readiness check and the runtime prelude both use it, so every block that runs $P derives the same make-pdf/dist/pdf binary, with MAKE_PDF_BIN (dev builds) winning when it is executable. Claude output keeps its repo-local-first probe; only the false 'subsequent blocks' comment changed. Root plus P=... fits the 400-byte prelude budget; the fixed MAKE_PDF_OVERRIDE segment is the one exemption, named in runtime-root.ts and the conformance test. * 0.1: eval:pass-rates --headroom, --reds and --run report views; 85% headroom alarm in --gate A new pure module, scripts/lib/eval-history.ts, reports per case the slowest armed session against the timeout it armed (censored when it timed out, insufficient below 3 samples, unknown without a session ledger, with the case wall shown separately as an upper bound), the census critical path from the slice jobs' timings, the verdict red ledger per census by failure class and machine cause with shrunk per-case rates, and the all-green probability (an approximation: the product of 1 - p_i, with an interval). --run <id> lists one census's reds with their values and history and downloads only the slice artifacts those reds name, reporting any over 64 MB instead of skipping them. eval-flake-rank.ts only routes flags: --help works offline, an unknown flag or case id exits 2 before any fetch, --case narrows the JSON and the alarms, every view prints its run/branch scope, and --gate also alarms on a session above HEADROOM_FAIL (85%) of its budget. * E5: GSTACK_DESIGN_IMAGE_MODEL override; the live model check always tests the defaults The image_generation tool model gains an env override validated against a conservative gpt-image-<version> pattern; a bad value fails before any request and the error names the variable. Pairing and rejection hints name the tool model actually requested. design/scripts/live-model-check.ts now ignores GSTACK_DESIGN_MODEL and GSTACK_DESIGN_IMAGE_MODEL (and says so), so an override cannot mask a retirement of a default, and its exit 2 (no key) says nothing was checked. * C3: /deslop-shared-libs names a concrete risk for each recommendation, never 'none' Both shared-libs-opportunity-judgment reds (37193478719 t3, 37195203538 t1) failed adoption_and_risk because the top recommendation said 'Main risk: none found inside the repo' / 'none in behavior'. The skill asked to 'name the main risk or uncertainty' without saying what counts. * B4: --case selects loop-registered cases; an unknown id exits before any process caseSelection() resolves the one paid file that registers a case and how a trial selects it: by its literal Bun test name, by the id a registration loop names its test at runtime (coverage audits, TPA, journeys), or by running the whole file when it registers no other case (plan-mode-no-op, whose test names are not the id, so the old name pattern ran nothing). A whole-file case runs one file shard per trial and is judged by shard status, as CI judges it. --list prints the selection. Every E2E_TIERS id now resolves except carve-section-loading, which fifteen files register (CI runs each as its own shard) and which still fails with the owning files named. * 0.3: after-a-repair runs the shard file when --case cannot resolve a case A case that several files register (carve-section-loading) cannot be selected by --case; its red line now prints the bun test command for the shard file that went red, so every printed command selects exactly one case. * C1: pre-register workflow-judge control bundles for qa, qa-only, review and setup-deploy Positive (production bundle), negative (headings only) and one targeted execution-blocking defect per judge, one 3-sample panel each, built with the eval's own reader, prompt builder, options and floors. * F: cost_known: a trial whose harness captured no billing says so; totals never hide it cost_usd stays a finite number. Trial and eval records gain an optional cost_known boolean (absent means known, so old records still parse; the validator accepts only a boolean). Session-ledger rows record whether the session's terminal result carried total_cost_usd; PTY and Codex sessions never do, and SDK captures without a terminal result do not. A trial is cost-known only when it has eval records and every record and session captured billing, so JUnit-only PTY cases (125 of 298 trials in run 37198445662 recorded 0) now read cost unknown. The census headline prints the known sum plus the unknown count, never a bare total over unknown costs, and no total when every cost is unknown; the history import keeps the flag. PTY transcripts are not priced: test/helpers/pricing.ts estimates exclude cache writes, so they cannot give the billed cost. * B1: replay corpora for the five repeat-offender cases shared-libs-plan-callers, plan-ceo-section-loading, auto-decide-preserved, plan-design-review-plan-mode and ship-docsync-late-result each get an inventory of every wave census in scope (all artifacts still available) and minimal, redacted detector or actor inputs replayed through the real detector in the free suite: census passes, every distinct census red, and derived negative controls labelled as derived. Fixed false reds stay as expected passes with their history; the two genuine auto-decide product failures (37176837432, 37179171083) stay refused. A contract test bounds each entry at 64 KB, scans it for HIGH credentials, requires a pass and a refusal per case, and reports entries whose series identity is stale. Building the auto-decide corpus exposed a latent native detector misread: a bold 'Mode application and rationale.' heading was parsed as a withdrawn Mode field (37186854666). A field status now ends at its sentence. * B2: read approved stale-fill decisions from more valid ledger records The structured ledger reader is authoritative before the prose fallback, but it missed two valid approved records in passing censuses (37186854666: a camelCase writeProfile subject; 37195203538: a slash-joined 'D1 / STALE-FILL' row id), which then rested on the prose detector that caused both historical reds. Both forms are accepted; an unresolved row, an unrelated decision, the copied fixture plan and non-write camelCase words stay refused. * C1: record workflow-judge control results (negatives separated; qa and review miss a removed step) * C2: record every low workflow-judge sample in the wave censuses with its disposition * 0.3: published lines cannot break a fixed fence evals.yml wraps collector-outcomes failures in a fixed three-backtick fence for the PR comment, so those lines (and eval:pass-rates output meant for the tracking issue) go through sanitizeFixedFenceLine: cleaned like every published line, with backticks turned into quotes. Inline published text also neutralizes backticks. * A1: fit the post-child record wording under ship's 1.428 parity size cap * E4: inline the Step 1 base refresh to fit review's 1.199 parity size cap * B2: inventory of gate and periodic phrase-only detector checks docs/evals/detector-inventory.md lists every pass/fail decision in gate and periodic E2E cases that rests on phrases in model free text, with its structured source (if any), whether the contract is user-visible, and a disposition: already structured-first, convert candidate, phrase witness required, or no structured source. Convert candidates are ordered by census red history. * 0.2: failureCauseOf takes the stall window instead of importing it; the PTY ledger never throws eval-store.ts imported STALL_WINDOW_MS from eval-budgets.ts, which free tests replace with mock.module stubs (review-finalization-budget, office-hours, qa-fix-loop, qa-only), so loading eval-store failed there. failureCauseOf is now dependency-free: the record builders pass STALL_WINDOW_MS. A PTY session whose handle cannot show its text (test doubles) records no panel instead of throwing from runPtySession's cleanup. The 37186854666 replay also runs through classifyTrialShard. * A2/auto-decide: the CEO handoff chat repeats the helper's printed line verbatim Claude Code 2.1.284 collapses the helper's Bash output ('Ran 1 shell command'), so the 'Auto-decided review mode → …' line reaches the user only through chat. In lane D's auto-decide-preserved corpus every passing capture's chat starts with that line, and the reds paraphrased it ('HOLD SCOPE was auto-selected…', 'Mode decision done…', "I'm defaulting to HOLD SCOPE…"). The template now says verbatim and why. * C2: record the judge panels rerun on the final ship and review wording * integrate: touchfiles and module-size ratchet entries for the wave's new modules GLOBAL_TOUCHFILES gains session-ledger.ts, published-text.ts and auq-substance-panel.ts; bin/gstack-bun-version.sh joins every entry that lists setup or the updater; auq-matrix stays a rule case with its C4 evidence beside E2E_KINDS; eval-history, published-text and session-ledger are registered new modules. * E1: BROWSE SETUP install hint pins the tested Bun (1.4.0) * E2: quote "$P" in make-pdf commands so install paths with spaces work * E1: /gstack-upgrade checks the incoming Bun floor before pulling gstack_bun_incoming_hold (bin/gstack-bun-version.sh) is now the one pre-advance check: the auto-updater calls it before its fast-forward and /gstack-upgrade's git path calls it after fetching. Below the incoming release's floor the upgrade stops with BUN_TOO_OLD and the checkout, VERSION and installs stay untouched. Vendored installs were already safe: setup refuses before writing and the swap restores the previous install. * 0.3: only main posts or closes tracking issues; reports carry alarms, red ledger, headroom and all-green A branch-dispatched periodic or marathon run writes its report to the step summary and a report artifact; the upsert and close steps run only on refs/heads/main. The periodic body now keeps every pass-rate alarm line (the old grep kept only the header), adds the red ledger and session headroom read with an explicit --branch, the all-green estimate and the triage guide link, and routes report text through scripts/lib/published-text.ts. The marathon lane gains the matching close-on-green step. Migrated: evals-workflow-wiring pinned report-summary.md in the upsert step; the body is now written by 'Write the census report'. * C3: prosons neutral-posture detector ignores a negated "taste call" Both plan-review-prosons-neutral-neg reds (37179171083 t3, 37193478719 t3) recommended A and closed with "a coverage call, not a taste call"; the old /taste call/i matched the negation. The detector moves to a helper so the two census captures replay free as negatives, with positive controls. * B2: credit the CEO mode handoff only when the chat shows its line Claude Code 2.1.284 collapses the gstack-ceo-mode-handoff Bash result, so the printed AUTO_DECIDE line is user-visible only when a later chat message of the session begins with it. The native detector now requires that witness; the helper's tool result locates it but no longer replaces it, and a generic mode statement cannot stand in once a handoff ran. Census 37182865432 is relabelled a genuine miss (expected: refused): the chat said "I'm defaulting to HOLD SCOPE…" and "Mode decided: HOLD SCOPE". Corpus replay: 5 credited, 3 refused. ceo-mode-handoff tests migrated to the witness rule (deliberate behavior change). * test: baseline the wave's approved detector and harness replay tests B1 corpora, B3, C3, C4 and D2 replay captures through paid-case detectors, actors or fixtures (test code by design); each entry carries its reason. * E6: live Codex multi-block periodic case in the host-run Codex job test/codex-e2e-multiblock-live.test.ts runs ./setup --host codex once from the job's checkout into a fresh HOME and CODEX_HOME (auth.json copied from the CI login home), asserts codex debug prompt-input lists the gstack router as a real file, seeds one learning, and runs /learn's Show recent block through codex exec: that later block must root itself through its prelude, run the installed gstack-learnings-search and print the seeded learning; no block may report a missing install or an unresolved gstack helper path. The file joins CODEX_CI_FILES so the planner gives it to the host-run Codex job. paid-test-durations.json carries a 180 s packing estimate (refreshed by --write-durations after the first census) so the plan keeps every slice within max-parallel. Oracles live in test/helpers/codex-multiblock.ts with free replays in test/codex-multiblock.test.ts. Registration (E2E_TOUCHFILES, E2E_TIERS periodic, E2E_KINDS rule) is the integrator's. * E5: design live-model check as a periodic case test/skill-e2e-design-model-smoke.test.ts runs design/scripts/live-model-check.ts (default models only) under a temp HOME. Without OPENAI_API_KEY the case is a Bun skip that the census lists as SKIPPED with no coverage credit; with a key, exit 0 passes and any other exit fails with the script output (exit 2 under a present key fails as 'nothing was checked'). paid-test-durations.json carries a 90 s packing estimate. Registration (E2E_TOUCHFILES, E2E_TIERS periodic, E2E_KINDS rule) is the integrator's. * A1: docsync parent points children at a saved interface file The /ship docsync fixture saved its observation interface only in the parent prompt and told the parent to copy it into every child prompt, about 30-40 s of parent generation per session (lane S, 37198445662). docsSessionOptions now writes it to <home>/fixture-interface.md (0600) and the parent tells each child to Read that file first. Fault-actor prompts, which prepare already writes to a file, are unchanged. Fixture-only. * A3: a JUnit case's recorded wall is capped by its shard's wall junitCensus summed a case's JUnit test times as duration_ms; for plan-mode-no-op's concurrent PTY tests that is 346 s inside a 176 s shard (the "432-613 s" history). The case wall headroom shows is now min(sum, shard elapsed), a true upper bound. Session headroom already used the ledger's per-session clocks. * A3: refresh paid-test durations from census 37198445662 Recorded 2026-09-29 estimates under-packed gate slice 11 (17 files estimated 1078 s ran 1353 s; plan-review-report 76 s -> 198 s, plan-ceo-plan-mode 37 s -> 112 s, safety-codex-consult 83 s -> 150 s). Refreshed both tiers with --report --write-durations from the latest census's slice walls. Old plan re-costed with observed walls: worst slice ~677 s (slice 11); refreshed plan: every slice estimated <= 539 s. * C2: Browser Quick gets a feasible budget; QA loop names its directory and stop path Judge rationales on the qa-only panels (2 of the last 3) cited the 30 s Browser Quick budget: homepage + 5 targets, each a checkpoint write and a guarded command, left ~5 s per probe. Quick is now 180 s (method text: 3 minutes); the qa-only-no-fix paid check expects the same native deadline. PROBE_DIR points at its source line, a stopped loop goes to the final report steps (annotations, materialize, Markdown), and /review and /ship say that after smoke expiry only plan checks rerun in revalidation. * C2: name the flows judges found implicit in review resolvers Structured outside review: MISSING COVERAGE asks no fix question and is never reported clean (was "preserve the existing user decision flow"). /review's HIGH-impact plan gate: spawned or non-interactive runs report REQUIREMENTS MISSING and continue, writing no TODOs. Value cards: the byte clamp applies to card lines; JSON records you write keep full values. * C1: a free test catches a removed workflow step, which the judges missed C1 controls showed the qa workflow judge passing /qa without Phase 10 and the review judge passing /review without Step 3. The new test pins every step/phase heading of qa, qa-only, review, ship, plan-ceo-review, plan-eng-review and setup-deploy (derived from the templates' step headings) and names any that goes missing or out of order; new step headings must be pinned. The judge rubric is unchanged (EVAL_POLICY). * size: fit the wave's wording under ship, review and qa parity caps Measured after all lane merges: ship -79, review -210, qa -68 bytes over. Trimmed the added wording first (post-expiry rule, MISSING COVERAGE, plan-gate default, value-card JSON, stop line) and folded /review's redundant INFORMATIONAL sentence and findings bullet. ship 268,036 (room 8), review 130,118 (room 1). qa needed 11 more bytes: cap 1.11 -> 1.1102 with the measured 93,305 / 84,049 = 1.11013 and its reason beside it. * docs: troubleshooting sections for the wave's new messages Bun floor (setup, auto-update, /gstack-upgrade), /review stale base and fingerprint temp-dir errors, the design image model override, the unrecorded Chromium PID, and a contributor section for census report lines (pass-rates flags, failure causes, headroom, cost unknown, overlay v4, stale corpora, auq substance). A free test checks every troubleshooting.md#anchor printed by setup or bin scripts exists. * TODOS: reliability follow-ups deferrals; close the Bun floor, make-pdf $P and #2709 reap * 0.4: 'A census went red' guide; docs for causes, session ledger, headroom and new messages docs/evals/census-red.md walks one red line to a diagnosis: prerequisites, the report fields, eval:pass-rates --run/--reds/--headroom with expected output, what unknown/insufficient/unrecorded data means, free replay, and the single 'after a repair' paid run allowed by TESTING_INTERNALS. Linked from CONTRIBUTING, TESTING_INTERNALS and both census reports. TESTING_INTERNALS documents the failure_cause glossary (one row per FAILURE_CAUSES value, diagnostic only under EVAL_POLICY v1), failure_detail, sessions[], cost_known, the session ledger, the pass-rates views and the 85% headroom alarm, main-only tracking issues, overlay contract v4, auq-matrix's 3-sample substance panel and the E5/E6 periodic cases. troubleshooting.md gains #bun-too-old and an anchor per new user-facing message from lanes P, D and F. README names GSTACK_DESIGN_IMAGE_MODEL. test/census-red-docs.test.ts pins the glossary to FAILURE_CAUSES, parses every guide command and checks the links. * v1.91.20.0: CHANGELOG and version for the reliability follow-ups * regen: SKILL.md and sections for all hosts, digest, context-budget fixture bun run gen:skill-docs --host all; goldens and llms.txt re-rendered unchanged; bun test/helpers/capture-context-budget.ts. * integrate: register codex-multiblock-live and design-model-smoke (periodic, rule) * 0.4: census report and eval:pass-rates views link the census-red guide * test: cookie approval fixture reverses the Bun install-hint pin (E1) The historical approved cookie-workflow prompt carried BUN_VERSION=1.3.10; the regenerated install hint now pins 1.4.0, so the fixture's reversal list gains that edit like the earlier waves' entries. * test: release floor counts the two new periodic cases (E5, E6) * fix: /freeze, /guard, /unfreeze and /investigate work on Codex and other env-var hosts Templates quoted "$HOME/.claude/skills/gstack/...", which the env-var hosts' rewrites turned into "$HOME/.agents/skills/gstack/..." on Codex (a path a global install never has; same class on the other hosts), and setup's runtime roots had no freeze/bin. Quoted runtime paths now use {{RUNTIME_ROOT}}: $GSTACK_ROOT on env-var hosts (the fence gets the runtime prelude), the unchanged $HOME path on Claude. _link_runtime_dists links freeze/bin and the careful/bin helper it sources into every env-var host's root. Also fixes the same guess in /benchmark-models, /retro and /diagram. test/env-host-runtime-assets.test.ts fails on the previous code: no fence guesses a $HOME/<dir>/skills/gstack path, every $GSTACK_ROOT path a fence uses is in the host's runtime root, and the installed Codex /freeze and /unfreeze fences run from a fresh shell. Template-reading tests now read the Claude render or expect the placeholder (deliberate change). * CHANGELOG/TODOS: lane W's workflow, cases and guide; the env-var host freeze fix * E6: a block that reads a SKILL.md is not a missing install The first live codex-multiblock-live run passed its real check (the /learn block found the install and printed the seeded learning) but the oracle flagged a sed of the learn SKILL.md, whose prelude source quotes the 'gstack: no install found (tried $_r)' text. Only an emitted line that starts with the message and names a real root counts now; free replay negative added. * test: qa-only fixture keeps its caller-set 30 s deadline The qa-only-no-fix fixture tells the model to start the guard with 30 s (a caller limit), so its deadline assertion's default stays 30 000 ms; the product's Browser Quick default (180 s) does not apply to it. Reverts the helper and its test to their base. * C2: keep PROBE_DIR 'owned' (qa-functional-prompt pins it); qa measured 93,311 * test: paid file count and periodic floor include the two new periodic cases * test: ship docs freshness pin checks meaning after A1's wording trim The snapshot still hashes selected release paths (--select narrows them), generated outputs and docs; the pin now checks that instead of the pre-trim sentence. * E3: reap the recorded Chromium only after the daemon has exited With the PID now recorded (E3), browse stop reaped Chromium while the daemon was still shutting down; the daemon read that as a crash, exited 1 and left its state file (chromium-profile-isolation's headless stop test failed 3/3 locally, passes on base). The CLI waits up to 5 s for the daemon to exit before reaping a survivor. * regen: qa and qa-only exploratory sections (PROBE_DIR wording) * B1: batching counter reads a target declared mid-line; replay corpus GSTA-23's census 37228573062 failed plan-eng-multi-finding-batching with reviewCount=0 after 975 s although D1-D10 were asked one per finding, each with its saved decision-ledger record. The report wrote 'Report destination requested by the user. Review target (fixed): `PLAN.md` ...' and the counter read target fields only at a line start, so no brief inherited the plan identity. A target field may now open any sentence of its line; a mid-sentence mention or another file still gives no identity. Floor (3), budget and kind unchanged. Corpus: 9 earlier passing censuses, the red (now credited at D5), and a derived batching refusal; 975 s noted in the headroom diagnosis. * B1: shared-libs corpus labels its git path and covers the supported shape Every census entry was recorded in CI's eval image (git 2.43), where gstack-safe-git falls back because --no-lazy-fetch is rejected; each entry now says so (git_path: fallback). Two synthetic supported-path entries (HEAD and a history citation in the brief, as git >= 2.44 produces) keep the 37193478719 pass and the 37195203538 refusal, and a test asserts both shapes are covered and the actor reads no git-path-specific text. * v1.91.21.0: move off v1.91.20.0 (claimed by #3031) * test: settle nav-guard commands before asserting; make two new tests Windows-safe navigation-guard: Bun's expect(promise).rejects slows each Playwright round-trip to ~1s while it waits (50 page.evaluate: 43ms plain vs 46.6s inside the matcher), so the click's 5s timeout expired before the guard saw the link-local request (CI: 'click: Timeout 5000ms exceeded ... waiting for scheduled navigations'). Settle the command first, then assert on the refusal; a source check keeps it so. env-host-runtime-assets: PROBE_FILES now matches either path separator. detector-corpus ship-docsync-late-result: JSON-escape the <ROOT> substitution so a Windows temp path's backslashes do not break JSON.parse. * fix: CI run/job ids are not phone numbers; context-recovery fixture gets the full runtime bin pii.phone.e164 redacted the run id in the published eval report's fetch command (--run 37235771700), breaking the command it prints. Digit-only spans in a run/job flag, gh run argument, actions/runs/ or /job/ URL segment, or run_id/job_id key are now exempt; the same digits elsewhere still report. context-recovery-artifacts: the fixture's ./bin/ lacked gstack-skill-start and gstack-context-recovery (the preamble's runtime scripts since v1.71), so the agent spent its 10 turns hunting for them and hit error_max_turns with no final message (run 37235771700, 11 turns). Link the whole runtime bin; diagnostic rerun passed in 6 turns. * test: replay run 37237194905's late-result capture through the docs authority detector The only failure was call 20's write to a mistyped shard root (3GanyY for 3GanyU), which the model disclosed; the detector is correct and the A1 post-snapshot --out under the fixture home stays permitted. Named red recorded in TODOS. * test: keep docsync-authority in the Windows profile The replay test's literal helper path tripped the Windows curator's shebang-spawn pattern, dropping the whole file from the Windows profile (test-free-shards invariant). The snapshot --out case is already covered by docsync-command-grammar, so it is removed here, and the Linux-path replay skips on win32. * fix: gstack-docs-candidate --help works; docs gate red lines name the denying tool failure PR run 37239016858 ship-docsync-completion: the parent ran 'gstack-docs-candidate --help' (the helper's usage error points at --help, which failed). That undeclared command made docsToolFailures non-empty, which denied the atomic-replacement proof of the child's legitimate native Edit, so the red line blamed the Edit's temp file. A replay of the capture proves the atomic replace once --help is declared. - the helper prints its usage for --help/-h and exits 0 - the fixture interface and command grammar admit the helper's bare --help - the atomic-proof denial names its check and the tool failures behind it (deny labels renumbered to their lines) - replay with negative controls (undeclared command, temp left behind, renamed elsewhere); diagnostic rerun of ship-docsync-completion passed * test: retro-base-branch fixture uses main and a shallow report path PR run 37241493377: the agent wrote retro-output.md one directory above the requested <tmp>/retro-base/retro-output.md (it dropped the retro-base segment), so the report check found nothing. The fixture also ran plain git init, which makes master on CI's git while the prompt says the repo is on main; the agent logged that mismatch as a learning. Init on main and use the temp dir itself as the repo. Diagnostic rerun passed (18 turns, 203s). * test: qa-quick sets a caller probe limit and drains past its session budget C2 raised Browser Quick's native budget to 180 s. qa-quick is the only gate case on the native budget, and its wall went 194 s (main periodic, pre-C2) -> 254 s and 274 s (this PR's runs) -> 300 s session timeout (run 37242691913): the agent now probes every navigation target with a checkpoint, then needs ~80 s to report. Like qa-only-no-fix, the eval now sets a caller probe limit (30 s), scopes the fixture, and gives bun's outer timeout the session drain margin instead of racing the 300 s session. The product's 180 s budget and the session budget are unchanged. Diagnostic rerun passed in 195 s. * review/ship: use main's post-expiry smoke sentence; v1.91.24.0 GSTA-23's measurement on the review workflow judge: main's 'Post-expiry smoke rechecks are not-run.' passed 10/10; the C2 wording passed 6/10 and the '..., even in 4c.' variant failed in PR run 37248650879. qa-probe-gates pins main's sentence before step 4c. * test: record the plan-design corpus test in the test-of-test baseline #3031's ratchet now counts tests that slice a paid test file's source; the B1 plan-design-review-plan-mode replay corpus reads test/skill-e2e-design.test.ts like its sibling corpora already listed. * fix: --case no longer deadlocks importing the running CLI runCaseDiagnosis loaded runPaidShards with a dynamic import of scripts/test-paid-shards.ts; when that file is the entry it is still in its top-level await, so the import never resolved and `--case` hung after its first line (on main since #3031, found by the per-case measurement runs). The CLI now passes its runner in; library callers keep the lazy import. * test: name the in-flight file and the native error when bun dies before its summary (#3037) * Bun 1.4.2 everywhere CI and setup pin the tested version Bun 1.4.0 on Windows aborts about 3% of free-suite shards with native bad-handle errors (main too; #3037); the same head on 1.4.2 had none in 180 shard runs. Every current 1.4.0 pin moves together, as bun-version-drift requires: setup-bun in every workflow (CSO orchestration included), the eval image (sha256 from bun-v1.4.2's SHASUMS256.txt, re-hashed locally), GitLab, the Ubicloud free-suite setup, gstack-bun-version.sh's tested version, engines.bun and @types/bun, the install hint in generated skills, the Dia and cookie native-qualification pins, and docs and tests that state the current pin. Recorded 1.4.0 observations, fixtures, CHANGELOG history and the CSO images' oven/bun:1.3.10 base stay. * fix: --case runs a single-case file whole A session option naming the case (testName: 'office-hours-section-loading') made caseSelection pick test-name mode, whose filter matched no Bun test, so every trial would run hollow. A file that registers only this case now runs whole before any name match is tried. * fix(office-hours): reviewer returns a hash-bound receipt instead of echoing its verdict The spec reviewer now Writes its verdict once, seals it with gstack-office-hours-review seal (validates the saved JSON and prints OFFICE_HOURS_VERDICT round=N sha256=<hash> path=<verdict>), and returns only that line. check --receipt recomputes the hash and fails closed on a missing, malformed, stale-round, wrong-path or mismatched receipt. The saved file stays the sole findings inventory; validators bind the receipt to the saved bytes and the judge reads those bytes. * fix(office-hours): only blocking findings send a design back for another review round Review findings carry severity blocking|minor (verdict schema v2). PASS when no blocking findings remain; minor findings are recorded in Reviewer Concerns and the Spec Review table, never a reason for another round. CONVERGENCE needs a persisting blocking prior. A persisting or unverified blocking prior cannot be relabeled minor. The 3-round cap is unchanged. * fix(office-hours): rounds 2 and 3 are delta re-reviews of the captured design diff prepare saves each reviewed design as round-N.design.md and gives later reviewers the exact line diff since the previous round. A new later-round blocking finding must cite (changed_text) an excerpt of a changed line; seal, check and the validators verify it against the snapshots and fail closed when a citation or snapshot is missing. Other new observations are minor. Severity, anti-downgrade and CONVERGENCE rules are unchanged. * test(office-hours): preservation judge accepts COMPLETED with recorded minor findings * fix(office-hours): parent fixes only blocking findings; callers may set --max-rounds Between rounds the parent edits for blocking findings only; minor findings stay recorded. gstack-office-hours-review takes --max-rounds 1|2|3 (default 3) on every command; reaching it stops at MAX_ITERATIONS. The marathon fixture sets 2 rounds so round 1 (full) and round 2 (delta) run live. * docs(changelog): office-hours review loop changes in v1.91.28.0 * fix(cso): helper JSON keeps run URLs only in the validated workflow slot The shared redactor now treats GitHub Actions run ids as CI metadata (c245d1bc2), so main's #3041 invariant that the same run digits stay redacted outside qualification.workflow held only through the phone false positive. Make it explicit in the CSO sanitizer. * test(plan-ceo): split-overflow progress detector accepts the skill's candidate wording Collection never ended when the model wrote 'E1 Slack:' / 'E1-SLACK:' or labels like 'Include in this quarter' / 'Defer with flip trigger', so the session ran the whole review (930-1464 s) and failed on its extra findings or the case deadline (6 of 21 runs). The candidate check now accepts a platform-bound E-id and the action is the bucket's leading verb, as the skill names them (Include/Defer/Cut/Hold). The semantic judge, call floor and include/defer/cut validation are unchanged. Replays the captured CI 37374526437, t2, t9 and t15 menus with negative controls. * test(plan-ceo): split-overflow candidate identity is the one E1-E5 token The skill fixes no header or question wording, and shape-matching kept missing new forms (header 'D1.1 Slack' with 'SCOPE-E1:', 'D1.1 E1 Slack', 'E1 Slack DM bot ...:', a misspelled 'Mattermst'). Identity is now exactly one E1-E5 token across the header and the question's first line, with no other candidate's platform named. Options rules, judge, call floor and include/defer/cut validation are unchanged. Replays all 31 measured runs; the quoted-row controls now quote a second ledger id. * v1.91.30.0: move past #3044's claimed 1.91.29.0 * test: register the split-overflow wording replay as a free fixture * fix(skills): resolve judge-cited ambiguities in /qa and /plan-eng-review - tasks JSONL keeps the raw branch as GIT_BRANCH instead of overwriting gstack-slug's sanitized BRANCH used for artifact names - the Codex outside-voice block runs for ready or unverified, matching its routing rule - plan-eng startup names the preamble's own setup prompts; the cross-project question waits for Step 0 - /qa 8c: a fix that applies but leaves the finding reproducing gets one revised fix, else it is reverted; browser verification names its before screenshot; the exploratory loop drops its duplicate 3-step summary * fix(plan-eng): keep the startup steps in their pinned order * fix(plan-eng): explicit spawned sessions follow the spawned rule at the scope gate; one announcement rule A missing tool still sends the prose menu whatever the session type, but a session the caller or host explicitly marks spawned selects the menu's Recommendation without prose or BLOCKED. The pre-load announcement sentence now states Step 0's single check. * eval policy v3: judge panels gate on the per-dimension median of 3 samples A judge dimension now passes when at least 2 of its 3 samples meet the unchanged threshold (judgePanelMedian); any other sample count or a non-numeric sample fails closed. Thresholds, sample count, judge model and prompts are unchanged; panel logs show every sample and the mean, and name the median as the gate. Applies to the skill-llm-eval panels, the workflow-judge cache, the auq-matrix substance panel and the calibration replicas. EVAL_POLICY 2 -> 3 and HARNESS_VERSION 1 -> 2 (verdicts change), so every case starts a new pass-rate series. Replays the captured panels from jobs 112032744416 and 112049856586 as replayed evidence.	2026-10-06 18:07:50 +00:00
Garry Tan	55fbe77195	v1.91.24.0 test: audit wave — PR evals keep finished work, honest ceilings, EVAL_POLICY v2, faster free suite (#3031) ... * chore(scripts): retire hollow and legacy paid package scripts behind one-release stubs (W8a, DX-4, CEO-31) test:codex*, test:evals*, test:e2e*, test:gate, test:periodic, eval:bg, eval:bg:all, eval:flake-rank, eval:watch and test:audit now print their replacement and exit 1 via scripts/retired-command.ts. CONTRIBUTING.md carries the same table; test/retired-commands.test.ts pins both. Eval CLI empty-state hints point at eval:bg:pr. * chore: delete dead update-readme-throughput, eval-watch, orphan fixtures and QA_FUNCTIONAL_INPUTS (W8b, CEO-24) Retired with named behavior: - update-readme-throughput.ts + readme-throughput test: replaced a README anchor that no longer exists from a JSON file that was never produced; the script was a no-op. Guarantee withdrawn (nothing to protect). - eval-watch.ts + its dashboard tests: rendered ~/.gstack-dev/e2e-live.json and _partial-e2e.json, written only by unsharded runs, so it showed nothing for every supported (sharded) entry point. Guarantee withdrawn; live progress is the gstack-detach log or gh run watch. Manual-review rendering stays covered by eval-list and eval-summary tests. - Orphan fixtures (autoplan-pending-artifact-ae.json, autoplan-existing-app/, autoplan-sign-in-ui/, parity baselines v1.47.0.0/v1.57.7.0/v1.69.1.0): no test, touchfile or script reads them; superseded baselines stay in git history. - QA_FUNCTIONAL_INPUTS: exported, never imported. * refactor(test-free): delete dead WORKER_HOSTILE list and buildShardArgs parallel mode Neither had a production caller: full-suite mode runs shard processes, so the worker quarantine was inert and --parallel was never passed (W8b). * docs(test-value): narrow prompt-byte contract to machine-read tokens (D2) Define prompt-byte contract as machine-read tokens (markers, field names, command lines, enum values, file paths, security-boundary strings) and add a sentence-pin glossary entry: convert to structural checks or delete when a behavioral eval covers the behavior. * test(ratchet): count free tests that slice a paid test's source A free test that binds readFileSync(<paid test file>) and cuts it with .slice() tests the paid harness's code out of context even when it imports a lib/ symbol. Record the 15 existing files with reasons; new ones fail with fix text. Self-test covers positive and negative shapes. * test(browse): un-quarantine compare-board; all 16 board tests pass headless (W8d, CEO-24) The GSTACK_COMPARE_BOARD_TESTS opt-in hid a headless mismatch that no longer reproduces: all 16 tests pass on Bun 1.4.0 with the bundled headless Chromium, solo, repeated, and beside other in-process browser files. Protected behavior (the comparison-board DOM contract the plan-design-review/office-hours/design-consultation feedback loop polls) is checked on every free run again. * test: replace silent existsSync early returns with explicit skips or assertions (W8d) - browse/test/build.test.ts: server-node.mjs checks skip only when the bundle is absent and GSTACK_EXPECT_BINARIES is unset; the free CI lane and test:ubicloud build it and set the flag, so a dropped build step fails with the build command instead of passing with no assertions. - gstack-update-check: VERSION is tracked; the guard could only hide a bug. - gen-skill-docs host leakage/frontmatter checks assert the host tree exists (the module-level render always produces it). - cso-docker staged-runtime test uses test.skipIf so reports show it as skipped, not passed. * test(ship): convert ship-workflow-clarity sentence pins to structural checks Add test/helpers/prompt-structure.ts (between, expectTokens, expectAbsent, expectOrdered, expectMentions) with fix text on failure. ship-workflow-clarity now pins headings, step order and machine-read tokens (commands, fields, enum and status strings); safety rules are meaning-level keyword checks. Wording is judged by the 'ship/SKILL.md workflow' judge in skill-llm-eval. Sentence pins: 90 -> 0. * ci: add platform-qualification lane for opt-in ML, gitleaks and Swift tests (W8d, CEO-24) security-bench + security-live-playwright L4 (SECURITY_BENCH), the real gitleaks 8.30.1 memory-ingest cases (GSTACK_TEST_GITLEAKS) and the DebugBridge Swift build invariants (GSTACK_TEST_SWIFT) self-skip in every lane today. No scheduled lane has their prerequisites, so per CEO-24 they move to an owned dispatch + quarterly workflow instead of being deleted. Each job was run locally (ML 10 pass, gitleaks 130 pass; Swift needs macOS). test/platform-qualification-workflow.test.ts pins gate variable, job and file together. * fix(scripts): capture-baseline and preflight-agent-sdk no longer act on --help or typos (W8e) capture-baseline parses its flags strictly: --help prints usage, an unknown or valueless flag exits 2, and only a valid invocation writes a fixture (--help used to write test/fixtures/parity-baseline-current.json). preflight-agent-sdk gains --help, rejects unknown flags, and runs the live SDK query (API spend) only with --live. * test(evals): register the three keyless periodic paid files with case ids (W1b) skill-e2e-auq-consistency, skill-e2e-auq-verbose-vs-carved-ab and codex-e2e-recommendation-substance now carry touchfiles, a periodic tier and kind rule (one trial, unchanged), so editing one selects its own case instead of restoring the full PR gate. The verbose A/B case also registers the vendored pre-cut fixture it reads, and review-army-migration-safety registers the SQL fixture it reads. * feat(evals): narrow PR fallback for free-only inputs (W1a, CEO-13/20, ENG-13) The PR profile now exempts the duration seeds, every free-lane workflow (explicit list; inventory test fails on an unclassified workflow, .yaml and workflow_call included), scripts/ubicloud/** and fixtures declared in the explicit FREE_FIXTURES map. Each remaining unknown file carries a label and fix (needs touchfile entry / add to FREE_ONLY_PR_FILES / real unknown dependency). evals.yml itself still restores the full gate. * ci: delete ci-image.yml; the eval workflows already build and push the same content-hash tag (W8f) evals.yml, evals-periodic.yml and evals-marathon.yml each compute the identical hashFiles() tag and build/push it (with :buildcache and :latest) when missing, so ci-image's push trigger and weekly cron were no-ops (30-day median 0.5 min, 36/36 success). ci-image-tag-binding now pins the three eval workflows. * ci(evals): key periodic/marathon concurrency on ref+event; branch periodic dispatch skips the gate census (W2a, ENG-9, CEO-04) * refactor(paid): drop ~160 unused imports; leaf paid-types/paid-select modules break the paid-* import cycle (W8c) * ci(quality-gate): per-PR concurrency, free runner, drop unscoped bun audit (W2a, W8f) - Concurrency keys on pull_request.number || run_id, so back-to-back main pushes no longer cancel each other's credential scan. - ubuntu-24.04 instead of a billed 8-vCPU Ubicloud runner for a ~1 min job. - bun audit --audit-level=critical ran on every PR regardless of diff, so a newly published advisory turned unrelated PRs red, with its own ignore policy. dependency-review (lockfile PRs, fail >= high) and the weekly OSV sweep remain the dependency gates. * chore(test-free): refresh the free duration seed from the audit's Ubicloud recording Adds the 19 files merged after the last refresh, including the 115 s claude-overlay-setup that packed as ~1 s and doubled a shard (W6a). The seed is re-recorded on the final tree at the end of this wave. * ci: move tiny ubicloud-standard-2 jobs to free ubuntu-24.04 runners (W8f) actionlint, skill-docs, dependency-review, version-gate and pr-title-sync are sub-minute jobs; GitHub-hosted runners are free for this public repo. * feat(test-free): pessimistic unseeded packing, seed growth ratchet and CI health summary - Unseeded files pack at the seed's p99 instead of p75 (W6a). - --ci-plan warns in the job summary past 5 unseeded files; --ci-verify lists shards that outran their prediction by 1.5x (and 30 s) plus every flaky pass absorbed by the serial retry (W6a, W7a job summary). - test/free-seed-ratchet.test.ts fails when a seeded file over 60 s is not on scripts/free-test-seed-allowlist.json, when an entry is stale, and when the allowlist grows versus its merge-base copy unless the new entry is an annotated exception with a todo (CEO-10, DX-7). free-plan runs it with full history so the shrink check is real in the required lane. - Every message names the fix command and docs anchor (DX-6). * feat(evals): state PR coverage mode, counts, reuse and fallback files in the summary and comment (CEO-13) * test: make the tracked-tree skill-doc freshness check local-only; tidy skill-docs header (W8f) Every free CI shard regenerates the tracked SKILL.md files before running tests, so the --dry-run freshness assertion compared the regenerated tree with itself and could not fail there. It now skips under GitHub Actions; skill-docs.yml's git diff --exit-code is CI's freshness gate. Removes a stale concurrency comment in skill-docs.yml. * ci(free-tests): install zsh so the bash+zsh portability arms run (W6f) ~42 zsh-arm tests (aside-probe-shell, qa-browser-preservation, generated-docs-fences) skipped in CI because zsh is not in the runner image. All 141 tests in those files pass with zsh present. * feat(evals): executors write negative receipts at the execution boundary (CEO-25, ENG-6) A completed single-trial rule/judge shard that did not pass now writes its negative receipt beside the pass receipts in the slice artifact, so a cancelled run's FAIL still blocks an older PASS when its report never runs. Receipts merge negatives first and order by (run attempt, completedAt); a same-second FAIL/PASS tie resolves to FAIL. The runner call site is a one-line hunk in scripts/test-paid-shards.ts. * docs(cso): state that contained runtime/scanner execution is unavailable today The scanner catalog is empty while its build inputs await review and the runtime catalog holds no qualified profile until the private evaluator exists, so /cso runs static assessment only. AGENTS.md, README and docs/cso-release-qualification.md now say so; docs/cso-scanners.md already did. * test(helpers): expectMentions splits on sentence ends only Clauses joined by ';' or ':' are one rule; splitting there made a reworded rule fail for punctuation. * test(plan-ceo): convert skill-ceo-section-ordering sentence pins Safety and authority rules (never/do not/stop/only/without/wait/approval) are meaning-level expectMentions checks; other sentence pins are dropped. Headings, labels, option rows, placeholders and machine-read lines (auto-decide annotation, Mode:/approved decisions format, STATUS/SOURCE fields, CROSS-MODEL marker, gstack-ceo-mode-handoff) stay as tokens; ordering checks unchanged. Behavior is covered by the periodic PTY case in skill-e2e-plan-ceo-review-section-loading.test.ts. Sentence pins: 210 -> 23. * test(helpers): expectMentions treats wrapped lines as one sentence Templates hard-wrap prose; only sentence ends and blank lines separate rules. * test(gen-skill-docs): convert sentence pins to meaning checks or drop them Safety/authority sentences become expectMentions keyword checks; other English sentences are dropped (wording is judged by the per-skill workflow judges in skill-llm-eval and the E2E cases in touchfiles-data). Commands, config keys, markers (PLAN MODE EXCEPTION, NO UNRESOLVED DECISIONS, Gate outcome), field names and alternation-based meaning regexes stay. Removed the now-empty 'contains opt-in AskUserQuestion text' test (only pinned a sentence; the resolver's AskUserQuestion wiring is covered by the codex second-opinion tests in the same describe). Lane E's existsSync hunks are untouched. Sentence pins: 216 -> 65 (remaining lines carry machine tokens). * ci(windows): shard the Windows lane via --ci-plan/--ci-run/--ci-verify; move native campaigns to native-qualification.yml - windows-free-tests.yml: a Linux plan job curates and packs the Windows-safe files into 6 shards, one strict serial shard per windows-latest job, and a Linux aggregate verifies exact coverage and every result (8.1 min on one runner today). --windows-only now combines with the CI modes; the plan binds the curated file set (W6e). - Every Windows plan and --list run prints the curated count with its top exclusion reasons in the job summary; a free ratchet fails when the curated subset drops below its floor, with the fix (W6e). - The four Dia/cookie diagnostic dispatch campaigns move to the dispatch-only native-qualification.yml with one exclusive `mode` choice input, so their red dispatch runs no longer read as a red PR lane (W8f). Their workflow pins move to test/windows-native-workflows.test.ts; the boolean-exclusivity guard is replaced by the choice input. * feat(paid): per-slice CI job ceilings and an in-process slice deadline with not_run/hung outcomes and checkpoints (W2c, ENG-2) * fix(pass-rates): segment trial history strictly by EVAL_POLICY version Reader-compatibility floor for EVAL_POLICY v2 (ENG-14/CEO-35/DX-12). Only trials under the reader's own policy version feed labels and alarms; older policy trials stay visible but are never scored or used as a drift baseline; trials from a newer policy are ignored with a printed count and fix text. Reverting the later v2 writer commits leaves a reader that cannot pool v2 records into v1 series (the pre-PR reader at 2db0b3a does: it reports a mixed fixture as FAILING with drift alarms). * docs: one contributor command table; retired commands, seed sources and current workflows (W8g, DX-5, DX-13, CEO-12) - CONTRIBUTING.md gains 'Which command do I run?' (task -> command -> cost/time -> needs, including branch validation via gh workflow run); CLAUDE.md, AGENTS.md and TESTING_INTERNALS.md link to it instead of repeating command lists. Tier tables drop retired commands and stale per-run dollar estimates. - Retired names (test:evals, test:e2e, eval:bg, eval:flake-rank, eval:watch, ...) are gone from CLAUDE.md, CONTRIBUTING.md, TESTING_INTERNALS.md, ARCHITECTURE.md and USING_GBRAIN_WITH_GSTACK.md. - The flake-ledger claim now says what happens: CI uploads flake-ledger-* artifacts; eval:pass-rates reads only the local ledger. - TESTING_INTERNALS states that only test:ubicloud --record-durations produces an acceptable duration seed (DX-13). - CI section: quality gate no longer runs bun audit; dependency-review's real trigger; the platform-qualification lane. - docs/test-audit-2026-09.md gets a corrections section for its stale claims. - TODOS.md: audit follow-ups (post-merge metrics, stub removal, name reclaim, diff-aware planner); eval-watch shard-awareness and the image freshness tripwire closed as won't-do. * feat(evals): recover receipts of cancelled PR runs (W1c, CEO-14/34, ENG-4/5/7) A new recover-receipts job runs base-ref code with actions: read, restores the PR's store, merges the receipts of completed cancelled evals.yml runs for this PR (provenance-checked, at most 5, oldest first, negatives first), reconstructs completed panel negatives with panelVerdict() (partial panels get no credit) and keeps a recovery.json checkpoint that never advances past an unresolved run. plan-slices keeps contents: read, takes the store as an artifact, turns reuse off when recovery degraded or a run is unresolved, and carries the whole store to slices-report so nothing is lost. Any gh problem degrades to no recovered receipts with a named reason. * feat(evals): classify this wave's free-only tools and workflows for PR selection platform-qualification.yml, retired-command.ts, test-health-report.ts, bump-harness-version.ts and eval-bg.ts never run inside a paid case. * feat(evals): debounce PR push bursts before planning paid slices (W1d, CEO-15, ENG-11, DX-7) A tiny ubuntu-24.04 job waits 90 s only on synchronize when another run for the PR started in the last 15 minutes; cancel-in-progress supersedes, and a run that outlives the wait reports "superseded by <sha>" and plans nothing. Labels: evals-no-debounce skips the wait, evals-fresh disables receipt reuse. * perf(test): move the real-process browser settlement cases out of test-free-shards.test.ts (W6b) The 19 owned-browser settlement modes were 85 s of the file's 95 s and could not be packed apart from the fast runner unit cases. They move to a shared fixture with two files (lifecycle 47 s, ownership 39 s); the unit file drops to 10 s. Same modes, same assertions. * chore(evals): delete the finished validation_phase dispatch and its inline planner (W8f) Retirement (CEO-24): the protected behavior was a one-off cookie-repair validation subset (eight dependent cases) and a quality/behavior split of the census; that validation is complete, so the guarantee is withdrawn. Branch validation dispatches evals.yml with evals_all. * perf(test): inject the office-hours record grace in non-cooperative deadline tests * perf(test): shrink aside-render process slack via GSTACK_RENDER_SLACK_MS in timeout tests * perf(test): make the memorable lock give-up configurable for lock-contention tests * perf(test): check install-timeout knob normalization through its own setup lines * perf(test): inject a 2 s storage-reset deadline in the late isolated dispatch test * perf(test): shorten the slow gbrain fake to 1 s, still past the 300 ms probe timeout * ci(free-tests): run only cso-docker-integration in the free CSO Docker job (F16) cso-node-lifecycle-integration and cso-stack-cold-integration need GSTACK_CSO_TEST_STACK images and always skipped there; they stay in the CSO runtime workflows through test:cso:docker. * test(gen-skill-docs,plan-ceo): split mixed sentence pins into tokens and rules Sentences that wrap a backticked or bold token keep the token (expectTokens) and, when they state a safety rule, a keyword check; short safety sentences (25-39 chars) get the same treatment. * test(plan-ceo): convert ceo-workflow-clarity.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: periodic PTY case skill-e2e-plan-ceo-review-section-loading and the plan-ceo workflow judges. Sentence pins: 13 -> 1. * test(plan-eng): convert eng-review-routing.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: plan-eng E2E cases (skill-e2e-plan-eng-*) and the plan-eng workflow judge. Sentence pins: 28 -> 6. * test(plan-eng): convert eng-scope-entry-ap.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: plan-eng E2E cases (skill-e2e-plan-eng-*) and the plan-eng workflow judge. Sentence pins: 16 -> 5. * test(plan): convert plan-scope-selection.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: plan-review E2E cases and workflow judges in skill-llm-eval. Sentence pins: 19 -> 2. * test(qa): convert qa-lazy-sections.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: qa/qa-only E2E cases (skill-e2e-qa-*) and the qa workflow judge. Sentence pins: 71 -> 11. * test(qa): convert qa-browser-preservation.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: qa/qa-only E2E cases (skill-e2e-qa-*) and the qa workflow judge. Sentence pins: 25 -> 11. * test(qa): convert qa-probe-gates.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: qa/qa-only E2E cases (skill-e2e-qa-*) and the qa workflow judge. Sentence pins: 20 -> 5. * test(qa): convert qa-checkpoint-evidence.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: qa/qa-only E2E cases (skill-e2e-qa-*) and the qa workflow judge. Sentence pins: 7 -> 5. * test(qa): convert qa-evidence.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: qa/qa-only E2E cases (skill-e2e-qa-*) and the qa workflow judge. Sentence pins: 4 -> 3. * test(design): convert design-consultation-contract.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: design-consultation E2E/judge cases in touchfiles-data. Sentence pins: 44 -> 11. * test(outside-voice): convert run-in-background-guidance.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: outside-voice E2E cases and plan-review workflow judges. Sentence pins: 35 -> 5. * test(spec): convert spec-template-invariants.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: spec E2E/judge cases in touchfiles-data. Sentence pins: 36 -> 21. * perf(evals): 420 s census slice budget; case-shard skill-e2e-qa-workflow; seed its case walls (W5c) * feat(evals): evals.yml dispatch contract for eval:bg (CEO-17/29, DX-1, ENG-8/12) workflow_dispatch gains base_ref, base_sha, expected_sha, nonce and pr_receipts. The nonce appears in run-name so the dispatcher resolves its own run; evals_all=false runs the PR profile against base_sha/base_ref; a checkout that differs from expected_sha fails before any paid work with a named fix; pr_receipts reads that PR's receipts read-only through the recover-receipts artifact path (never the cache) and never saves. * ci(windows): pack the Windows lane with Windows-measured durations (W6e) The first sharded run (37221451711) finished in 6.0 min: the Linux seed has browse/test/cookie-import-native-job.test.ts at ~0 s (its cases skip on Linux) but it takes 122 s on Windows, so one shard ran 242 s against an 84 s prediction. The plan now reads scripts/free-test-durations-windows.json; a record_durations dispatch times every Windows-safe file alone and uploads it. * test(free): settlement case files import the runner rule they exercise Keeps the split files out of the test-of-test ratchet: the retry-eligibility rule is a direct runner import passed to the shared fixture. * fix(marathon): no hollow plan-decision-classification shard; office-hours marathon scenario scoped to the pilot (W2f) * test(free): satisfy the typecheck:test ratchet in the seed ratchet test * refactor(ci-history): one shared GitHub history reader with the CI flake-ledger reader Extract pass-rates' gh fetch layer into scripts/lib/ci-history.ts (CEO-09) and add the W7a reader: paged run listings that fail whole on any page error, per-run artifact downloads (cached, size-capped, data only), flake-ledger parsing, the pre-registered flaky-file rule (> 5% of main free-tests runs over a window of at least 20 runs, widened to the newest 20 runs when the window is thinner), a job-summary table, and named unavailable reasons with next steps. * feat(test-health): test:health report of the audit success metrics scripts/test-health-report.ts (CEO-09/06/22/32, DX-8/9/12/13) prints every success metric with its counting rule from CI history: PR full-fallback rate, reused PR trial records, PR-lane spend per merged PR and per validated revision, cancelled slice-minutes per week, push-to-verdict p50/p95, census expected failed trials per run with raw failure rate per kind/class and P(lane red) under the recorded panels vs single-trial aggregation, INFRA re-dispatches, quarantine evidence (insufficient evidence distinct from healthy), free flaky-pass rate, free/Windows wall, free serial time and the net-complexity line. An unreadable input prints 'unavailable: <reason>; next: <step>', never 0. --enforce fails on a flaky file (W7a) or > 5 unseeded free files (CEO-10); unavailable checks never fail and keep the issue open. * test(review): convert review-workflow-clarity.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: review E2E cases (skill-e2e-review*) and the review workflow judge in skill-llm-eval. Sentence pins: 85 -> 17. * test(review): convert review-entry-and-design-clarity-au.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: review E2E cases (skill-e2e-review*) and the review workflow judge in skill-llm-eval. Sentence pins: 15 -> 4. * test(review): convert review-enum-lifecycle.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: review E2E cases (skill-e2e-review*) and the review workflow judge in skill-llm-eval. Sentence pins: 8 -> 0. * test(ship): convert ship-control-flow.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: ship E2E cases (skill-e2e-ship*, skill-e2e-workflow) and the 'ship/SKILL.md workflow' judge. Sentence pins: 74 -> 9. * test(ship): convert ship-skip-requeue.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: ship E2E cases (skill-e2e-ship*, skill-e2e-workflow) and the 'ship/SKILL.md workflow' judge. Sentence pins: 28 -> 3. * test(ship): convert ship-plan-completion-invariants.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: ship E2E cases (skill-e2e-ship*, skill-e2e-workflow) and the 'ship/SKILL.md workflow' judge. Sentence pins: 28 -> 12. * test(ship): convert ship-reentry-gates.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: ship E2E cases (skill-e2e-ship*, skill-e2e-workflow) and the 'ship/SKILL.md workflow' judge. Sentence pins: 16 -> 4. * test(ship): convert ship-document-release-dispatch.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: ship E2E cases (skill-e2e-ship*, skill-e2e-workflow) and the 'ship/SKILL.md workflow' judge. Sentence pins: 11 -> 4. * test(ship): convert ship-apple-gate.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: ship E2E cases (skill-e2e-ship*, skill-e2e-workflow) and the 'ship/SKILL.md workflow' judge. Sentence pins: 7 -> 0. * test(ship): convert ship-skip-actor.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: ship E2E cases (skill-e2e-ship*, skill-e2e-workflow) and the 'ship/SKILL.md workflow' judge. Sentence pins: 6 -> 1. * test(ship): convert ship-template-redaction.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: ship E2E cases (skill-e2e-ship*, skill-e2e-workflow) and the 'ship/SKILL.md workflow' judge. Sentence pins: 5 -> 4. * test(ship): convert ship-publication-gates.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: ship E2E cases (skill-e2e-ship*, skill-e2e-workflow) and the 'ship/SKILL.md workflow' judge. Sentence pins: 5 -> 2. * test(ship): convert ship-review-loop.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: ship E2E cases (skill-e2e-ship*, skill-e2e-workflow) and the 'ship/SKILL.md workflow' judge. Sentence pins: 3 -> 1. * test(ship): convert ship-version-sync.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: ship E2E cases (skill-e2e-ship*, skill-e2e-workflow) and the 'ship/SKILL.md workflow' judge. Sentence pins: 5 -> 2. * test(ship): convert ship-pr-liveness-policy.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: ship E2E cases (skill-e2e-ship*, skill-e2e-workflow) and the 'ship/SKILL.md workflow' judge. Sentence pins: 4 -> 0. * test(plan-review): convert plan-review-cases.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: plan-review E2E cases and workflow judges in skill-llm-eval. Sentence pins: 58 -> 15. * test(autoplan): convert autoplan-phase-order.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: autoplan E2E cases (skill-e2e-autoplan-*) and the autoplan workflow judge. Sentence pins: 42 -> 11. * test(autoplan): convert autoplan-phase-handoff.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: autoplan E2E cases (skill-e2e-autoplan-*) and the autoplan workflow judge. Sentence pins: 20 -> 4. * test(autoplan): convert autoplan-snapshot.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: autoplan E2E cases (skill-e2e-autoplan-*) and the autoplan workflow judge. Sentence pins: 21 -> 5. * test(outside-voice): convert outside-voice-preflight.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: outside-voice E2E cases and plan-review workflow judges. Sentence pins: 26 -> 9. * test(ask-format): convert resolver-ask-user-format.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: AUQ E2E cases (skill-e2e-auq-*); prompt-injection rule kept as a meaning check. Sentence pins: 32 -> 15. * test(skills): convert binding-template-drift.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: workflow judges in skill-llm-eval. Sentence pins: 19 -> 13. * test(skills): convert carve-plan-fixture.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: workflow judges in skill-llm-eval. Sentence pins: 20 -> 6. * test(land-and-deploy): convert land-and-deploy-postfail.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: land-and-deploy E2E cases and its workflow judge. Sentence pins: 21 -> 14. * test(land-and-deploy): convert land-and-deploy-ci-gate.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: land-and-deploy E2E cases and its workflow judge. Sentence pins: 5 -> 4. * test(land-and-deploy): convert land-and-deploy-flow.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: land-and-deploy E2E cases and its workflow judge. Sentence pins: 5 -> 3. * test(office-hours): convert office-hours-completion.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: office-hours E2E cases (skill-e2e-office-hours*). Sentence pins: 16 -> 1. * test(plan-ceo): restore the stale closing-route guard The negative check for 'Closing hooks' / 'return to section' guards a retired route token, not a sentence; the first conversion pass dropped it. * ci(test-health): weekly test-health workflow with an honest tracking issue New test-health.yml (CEO-18/DX-9): Monday 10:00 UTC after the periodic census plus dispatch, free ubuntu-24.04 runner, permissions contents:read + actions:read + issues:write only. Runs bun run test:health --since-days 7 --enforce; an enforced failure upserts one tracking issue, a run with unavailable inputs keeps it open and lists them, and it closes only when every enforced check has evidence and passes. Only main runs touch the issue. * feat(evals): an edited paid test file runs its own gate cases in the PR lane (DX-11) A gate case outside the audited fast profile is selected when its single owning paid test file changed and the runner can select it by name (its Bun test is named by the case id). The manifest records directCases and validation accepts only recorded, name-addressable ones; the runner and planner read the file->cases map from test-pr-profile. Cases the runner cannot address stay deferred with the fix. An inventory test covers every owned gate case. Touches one hunk each in test-paid-shards.ts and lib/paid-plan.ts, and pr-shared-input-selection.test.ts's ship-skip pin. * ci(osv): tracking issue for scheduled reds and a 14-day suppression expiry test F11/W8f: a failed main OSV scan now upserts one tracking issue and a clean scan closes it (scheduled reds notified no one during the August backlog). A free test fails 14 days before any .osv-scanner.toml ignoreUntil (all four expire 2026-11-30), with the fix: upgrade and delete, or re-justify and move the date. * test(ship,review): keep guards against retired fail-open instructions 'skip silently' on reviewer failure and 'do not block /ship on subagent failure' were harmful instructions, not prose style; keep them absent with the shortest distinctive phrase. * feat(eval-select): default to the pr profile DX-10: eval:select previews the PR lane's selection by default, matching test:pr and eval:bg:pr; --profile full (or EVALS_PROFILE=full) keeps the plain touchfile selection. * test(evals): type-clean the recovery gh fake (typecheck:test ratchet) * chore(windows): record the Windows duration seed (run 37221963236) 573 Windows-safe files timed alone on windows-latest; cookie-import-native-job is 102 s there. Six shards now predict 154 s each. * feat(evals): eval:bg dispatches the pushed ref to CI or runs locally under a 1.5x-planned cap (W5d, CEO-17/29, DX-1/2/3/7, ENG-12/19) * feat(runners): --help on both shard runners via the shared flag loop; paid runner header describes today's planner/executor/report (W8e) * test(windows): drop the stale Playwright exclusion and force-include probe-proven files (W6e) A temporary windows-latest probe (run 37221995077) ran each of the 97 files excluded for 'launches Playwright browser' or 'raw /tmp/ path' alone: all 17 Playwright files pass (Chromium is installed and Bun drives it there), and 41 of the /tmp files pass with executed cases. The Playwright pattern is removed and the 41 files are force-included with the probe as their reason; the 36 real failures stay excluded. The curated subset grows from 573 to 631 files and the ratchet floor follows. Windows curation moves to scripts/lib/windows-curation.ts (the runner drops to 2000 lines). * test(free): one install fixture cloned from a read-only seed (W6c, ENG-1) Merge test/helpers/setup-codex-scope-fixture.ts into install-fixture.ts. The checkout is built once per test file into a read-only seed and cloned per fixture with copy-on-write where the filesystem has it (full copy otherwise), restoring each file's own mode; clones never hard-link the seed because put() and tests write in place. Callers register afterAll(cleanupSeed); Bun's runner fires no exit event, so seeds of killed runs are swept by pid. test/install-fixture.test.ts is the ENG-1 tripwire: put/setVersion/chmod in one clone leave the seed and a sibling unchanged, and clones share no inodes with the read-only seed. * test(free): split claude-overlay-setup by describe (W6b) The 115 s serial file becomes default/lifecycle/installs files (5/4/3 tests, unchanged bodies) sharing test/helpers/claude-overlay-fixture.ts, so the shard packer can balance them. * test(cso): convert cso-contracts.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: cso E2E/judge cases (skill-e2e-cso*, cso-eval). Sentence pins: 16 -> 8. * test(cso): convert cso-preserved.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: cso E2E/judge cases (skill-e2e-cso*, cso-eval). Sentence pins: 10 -> 3. * test(cso): convert cso-eval.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: cso E2E/judge cases (skill-e2e-cso*, cso-eval). Sentence pins: 7 -> 4. * test(browser): convert aside-driver.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: Aside/browse E2E cases; the installer ban stays a meaning check. Sentence pins: 27 -> 9. * test(browser): convert third-party-actions.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: Aside/browse E2E cases; the installer ban stays a meaning check. Sentence pins: 17 -> 2. * test(skills): convert skill-validation.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: workflow judges in skill-llm-eval. Sentence pins: 19 -> 6. * test(skills): convert workflow-excerpt.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: workflow judges in skill-llm-eval. Sentence pins: 37 -> 10. * test(skills): convert question-tuning-registry-path.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: workflow judges in skill-llm-eval. Sentence pins: 4 -> 0. * test(skills): convert host-conformance.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: workflow judges in skill-llm-eval. Sentence pins: 4 -> 4. * test(memory): convert memory-ingest-landing.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: memory-ingest free tests that run the binary. Sentence pins: 11 -> 9. * test(windows): exclude the skip-only claude-overlay setup files from the Windows subset Their real-setup cases are describe.skipIf(win32); after the split their bin/ spawns live in the shared helper, so the source scan stopped seeing them. * test(skills): convert agents-digest.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: the owning skills' E2E cases and workflow judges; CLI/hook output and fixture-data pins in the tail were left alone. Sentence pins: 1 -> 0. * test(skills): convert brain-preflight.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: the owning skills' E2E cases and workflow judges; CLI/hook output and fixture-data pins in the tail were left alone. Sentence pins: 2 -> 1. * test(skills): convert codex-skill-isolation.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: the owning skills' E2E cases and workflow judges; CLI/hook output and fixture-data pins in the tail were left alone. Sentence pins: 1 -> 0. * test(skills): convert office-hours-review.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: the owning skills' E2E cases and workflow judges; CLI/hook output and fixture-data pins in the tail were left alone. Sentence pins: 2 -> 1. * test(skills): convert onboarding-moved-literals.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: the owning skills' E2E cases and workflow judges; CLI/hook output and fixture-data pins in the tail were left alone. Sentence pins: 2 -> 2. * test(skills): convert open-gstack-browser-liveness.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: the owning skills' E2E cases and workflow judges; CLI/hook output and fixture-data pins in the tail were left alone. Sentence pins: 3 -> 2. * test(skills): convert plan-floor-review.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: the owning skills' E2E cases and workflow judges; CLI/hook output and fixture-data pins in the tail were left alone. Sentence pins: 3 -> 2. * test(skills): convert plan-review-report-recording.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: the owning skills' E2E cases and workflow judges; CLI/hook output and fixture-data pins in the tail were left alone. Sentence pins: 4 -> 2. * test(skills): convert regression-1539-review-self-verify.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: the owning skills' E2E cases and workflow judges; CLI/hook output and fixture-data pins in the tail were left alone. Sentence pins: 4 -> 0. * test(skills): convert skill-fixture.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: the owning skills' E2E cases and workflow judges; CLI/hook output and fixture-data pins in the tail were left alone. Sentence pins: 6 -> 3. * test(skills): convert template-context-parity.test.ts sentence pins Safety and authority sentences become expectMentions keyword checks (reword freely, keep the rule); other English sentence pins are dropped. Headings, labels, placeholders, commands, field names, enum/status tokens and ordering checks stay. Behavior and wording: the owning skills' E2E cases and workflow judges; CLI/hook output and fixture-data pins in the tail were left alone. Sentence pins: 1 -> 0. * test: restore pins on renderer output and paid-fixture inputs cso-contracts (the report renderer's required empty phrase), memory-ingest (binary output), carve-plan-fixture, ship-skip-actor and cso-eval (inputs the paid harness builds) assert product or fixture output, not skill prose, so the value-bar narrowing does not apply to them. * feat(eval-policy): v2 series identity, HARNESS_VERSION guard and identity backtest W4a (CEO-27/ENG-3/DX-6), not yet wired to the writer: caseSeriesIdentitiesV2 keys a case by the bytes it owns (paid test file, fixtures, its skills' prompt files including the generated SKILL.md) plus HARNESS_VERSION, and records the full consumed-input fingerprint as provenance. scripts/harness-version.json pins the blob of every shared-harness file (GLOBAL_TOUCHFILES plus the session runners, PTY harness, e2e gate and LLM judge), one line per file; test/harness-version.test.ts fails on drift with both fixes, and scripts/bump-harness-version.ts records the decision: --bump (new series for every case) or --non-behavioral (compatibility entry, no reset). eval-trial-series --backtest replays identities over weekly main revisions and recorded trials (ENG-3/DX-12). * feat(pass-rates): weekly history is main's scheduled runs plus main dispatches W4b: pass-rates reads evals-periodic history from main only, keeping scheduled runs and main dispatches and never a branch dispatch, so back-to-back branch validation runs neither feed pass rates nor count as weeks for quarantine expiry or drift. --branch <name> still reads one branch's runs for inspection. * docs(test-audit): EVAL_POLICY v2 decision memo with the identity backtest D1 memo (CEO-33, ENG-3, DX-12, CEO-27): P(green) arithmetic, false-blocking targets, the v2 identity rule and harness guard, weekly history, W4c evidence (the named 'stochastic' cases pass 26/27 to 34/34, so they stay rule), the backtest over 29 weekly main revisions and 14,898 recorded trials, what it means for quarantine reachability, alternatives (gating vs trended, adaptive panels not adopted, buy vs build), and the rollback proof on the pre-PR reader. * feat(eval-policy): EVAL_POLICY v2 writer: case-owned series identity The v2 writer, last commit of the W4 block (DX-12/ENG-14/ENG-21): the report job's stamp now writes caseSeriesIdentitiesV2 (case-owned bytes plus HARNESS_VERSION) as series_identity, the full consumed-input fingerprint as series_fingerprint and harness_version as provenance, and EVAL_POLICY.version is 2 (approved 2026-10-04, D1). The v1 touchfile identity is removed. Rollback = revert this commit (and the W4 commits above the reader-compat floor); readers then ignore the v2 records with a printed count. * test: restore pins on paid-harness prompt inputs review-enum-lifecycle and plan-review-report-recording assert the prompt a paid case's harness builds (opts.prompt / call.prompt), a fixture contract, not skill prose. * test(security): check injected safety lines on meaning, not capitals content-security, the canary instruction and the arm judge prompt still must carry their never-follow / never-output / exact-"none" rules; the checks are case-insensitive keyword checks so emphasis can change. The UNTRUSTED envelope markers and "none" value stay exact tokens. (Hidden element stripping fails locally only because Playwright Chromium is not installed; same at base.) * test(plan-ceo): keep the outside-voice scope-summary rule as a meaning check The first codemod pass left an empty if body (TS1313). * chore(windows): re-record the Windows duration seed for the 631-file subset (run 37222668939) * ci(free-tests): summarize every shard's flake ledger in the aggregate job (W7a) The aggregate downloads flake-ledger-* (one subdirectory per shard) and appends lane C's `scripts/test-health-report.ts flake-summary` output to the job summary before strict verification. The runner's own flaky table is dropped so the ledger reader stays the single source; --ci-verify keeps the shard-overrun warning. * feat(evals): free test files anywhere and the stored-zip helper never restore the full PR gate (W1a) The CEO-23 replay found design/test free tests forcing fallback (36485436963). * feat(evals): replay recorded PR pushes through today's selector (CEO-23, ENG-18) scripts/replay-pr-selection.ts reports per push the recorded vs replayed mode and case count, dropped gate cases, retired failed cases and every miss (a failed case that depends on the diff but is no longer selected). * refactor(evals): one case-sharded carve-section-loading file with a case id and touchfiles per skill (W5a) * test(free): hold qa-deadline's full-pipe case on a FIFO, not a paused Bun stream Bun gives a child 'pipe' stdio a unix socketpair, so whether the 2 MB fill actually blocks depends on the parent's reader and the host's socket buffer sizes. CI (run 36761671811, both attempts) saw exit 0 after ~130 ms; with net.core.{w,r}mem_default=4 MiB locally the old case fails 3/3 the same way. A FIFO the test never reads is bounded by the kernel pipe buffer, so the receipt write genuinely blocks and the 5 s settlement deadline must fire. The 7 s bound now starts once the preload has queued the write. * test(free): event-driven waits in pty-output-wake close-releases-observers: the 500 ms wall race becomes an ordering check (the waiter is released while only SIGINT has been sent, before close's escalation finishes), and the Bun.spawn spy fakes only the PTY launch so a shard neighbor's in-process spawn cannot add a stray SIGTERM (CI runs 36015568981, 36036582721, 36074636848). continuous-redraws: the fixture spinner stops once the observer has made five coalesced reads, so the run reaches its work deadline with no redraw in flight. Streaming right up to the deadline raced the helper's screen drain and failed as 'PTY screen parse failed; viewport is incomplete' (5 CI runs 09-30..10-03; 4/40 locally under 8 busy loops, 0/40 after). * test(free): session-runner long-capture handshake waits for the collected Read event The fake CLI's init line arms the runner's work-phase timer, so the worker's handshake (work-ready + a >200 s timer) could pass before the runner's read loop had collected the Read event printed just before work-ready. Advancing the clock then killed the run with the Read lost: readSection false (CI run 37194511124). The worker now also waits for the runner's own progress line for that Read. Forcing the observed ordering (work-ready 200 ms before the Read line) fails the old test deterministically and passes the new one. * test(free): budget-override restores the CI variables it rewrites Its provenance cases set and then deleted CI, GITHUB_ACTIONS, GITHUB_REF_NAME, GITHUB_SHA and the GitLab CI_* names without restoring them, so in a CI shard every later file ran with CI unset. qa-only-cleanup's real browse daemons then launched Chromium without --no-sandbox, the sandbox failed on the runner, and both real-Chromium cases timed out with 'QA cleanup fixture did not become ready' (shard 12 attempt 1 of six runs on 10-04, retry alone green). Retained startup log: 'Chromium sandboxing failed!', child env with no CI. Reproduced 3/3 with CI=true, userns denied and budget-override ahead of qa-only-cleanup in one process; 0/3 after. * test(free): pr-shared-input-selection names its base and package history Every selection now passes EVALS_BASE and packageVersionOnly explicitly, so no case reads the checkout's git state. Before, 12 calls ran detectBaseBranch and the cumulative case diffed package.json against merge-base(origin/main, HEAD) — the ambient input that turned main red in runs 36572856858 and 36594314027. A PATH git spy counts 14 git calls in the old file and 0 now. * feat(evals): derive PR-lane dependents for unmapped files instead of restoring the full gate scripts/pr-dependencies.ts derives, from the checked-out tree, which paid cases consume each repository file: test import closures, repo paths and path.join segments in code/shell/skill text (whole-line comments and selection data excluded), bin script names, compiled binaries by outfile path (scripts/build.sh), package scripts, template placeholders through RESOLVERS, and host configs by host id. The global touchfiles' import closure is global. PR selection: an unmapped file with derived consumers puts the run in the new 'dependents' mode (every dependent gate case and judge, no profile cut); a tracked file under a derivable directory that nothing reaches is exempt; periodic/marathon workflows, .gitignore and tsconfig.test.json never run the PR gate. PR_FULL_GATE_FILES is the fail-closed list (deps, CI image, setup, build, evals.yml and its actions, test preload, tsconfig.json, .gitattributes, the skill generator and preamble resolvers, the eval policy). Untracked or underivable files restore the full gate with fix text. The summary and PR comment list derived dependents. * feat(evals): replay misses count derived dependents; report wave vs ordinary pushes (CEO-23) * test: drop FREE_FIXTURES entries for fixtures deleted in W8b * test: re-shape the census attribution fixture to qa-workflow and carve case shards * test: census fixture case order * ci: 420 s PR-lane slices with per-slice ceilings; periodic tracking issue only on main evals.yml joins the census lanes at the 420 s slice budget (W5c/CEO-15) and indexes each eval slice's job timeout from .plan.sliceCiTimeoutMinutes with the slice-deadline clock as its first step (W2c/ENG-2). evals-periodic.yml's tracking-issue upsert and close run only on refs/heads/main, so a branch dispatch whose gate census is skipped (CEO-04) never opens or closes #2755. * docs: integrate lane docs for the audit wave (eval-bg backends, PR fallback, policy v2, ceilings, evidence) - CLAUDE.md: 'Running evals as an agent' describes scripts/eval-bg.ts's dispatch and local backends, forcing flags, the sentinel and status; eval:select's PR-profile default; prompt-structure helper and value-bar terms. instruction-facts now requires scripts/eval-bg.ts in that section. - CONTRIBUTING.md: decision table gains test:health, eval:select default, eval:bg backends and the include_gate_census / evals_all dispatch lines; 420 s runners and per-runner ceilings; flake ledger, OSV tracking issue and expiry test, weekly test health; prompt-structure guidance. - AGENTS.md: build commands name the eval:bg backend choice and test:health. - docs/TESTING_INTERNALS.md: anchors the fix texts point to (#pr-paid-lane-fallback, #pass-rate-policy-versions, #harness-version, #flake-ledger, #duration-seed), receipts/recovery/debounce, per-slice ceilings, the slice deadline with not_run/hung and checkpoints, the eval-bg cap formula in place of the detach floors, EVAL_POLICY v2 history, carve case shards via --case. - docs/test-audit-2026-10.md: CEO-23 replay (165/168 -> 164/168 full-fallback, 0 misses), ENG-17 slice table (re-measured on this tree), D2 prose-pin metric. - TODOS.md: progress note on 'Let pass-rate history decide the rest'. - test/testing-internals-anchors.test.ts: every TESTING_INTERNALS.md#anchor named in code must match a heading. * test(free): hold qa-deadline's blocked-output-pipe receipts on a FIFO The five 'guard %s receipts survive a blocked output pipe' cases filled a paused Bun child pipe with 2 MiB. That pipe is a unix socketpair, so the fill only blocks while the host's socket buffers are smaller than the write: with net.core.{w,r}mem_default=4 MiB the old cases fail 13 of 15 case runs (the guard finishes before the test resumes the stream). The held stream is now a FIFO the test drains only after resume(), bounded by the kernel pipe buffer; Windows keeps the paused pipe. Bounds and assertions are unchanged. * test(free): qa-deadline waits for a written pid, not just the pid file DRIVER and LEAF write their pid with writeFileSync, so under load ready() can see the file before its digits and fail 'expected > 0, received 0' (seen once in 150 loaded runs). After any early failure the finally SIGKILLs the CLI, which orphans the detached command group; a leaf whose pid file is not yet readable then keeps the output stream open and the case hangs to its 15 s timeout (2/80 old-file runs and 3/310 FIFO-only runs under 8 busy loops; the instrumented hang showed the CLI already SIGKILLed by the finally). ready() now polls within the same 3 s bound until the file holds a positive pid. * fix(evals): a deleted file selects the dependents of the live files that still reference it PR selection treated every path absent from the head tree as an unknown dependency, so any PR that deleted a file forced the full gate. A deleted path is now placed like a live one, against the head tree: a matching touchfile selects its cases; live code, skill text or a full-gate input that still references it (path, extensionless import target, relative import, bin name, ancestor directory, compiled-binary outfile; whole-line comments and data files excluded) contributes its dependents, a full-gate referencer restores the full gate with a 'deleted but still referenced' fix, and an unreferenced deleted path has no dependents. Deleted PR_FULL_GATE_FILES entries still force the full gate. Tests that used absent paths as stand-ins for new unmapped files now use tracked root files (or an explicit tracked set); the CEO-23 replay counts misses through those references too. * docs: integrate free-suite lane docs (seed anchor, Windows lane, native qualification, install fixture, flake rules) - docs/TESTING_INTERNALS.md: '### Free suite duration seed' (the anchor the seed messages link) with DX-13, the 99th-percentile packing, --ci-plan warning, --ci-verify overruns and the CEO-10 seed ratchet; the Windows 6-job lane, its Windows-measured seed and refresh dispatch, curation and WINDOWS_CURATED_FLOOR; native-qualification.yml modes; the merged install fixture; test-only timing knobs; the flake-ledger job summary, Windows ledger names and three free-suite flake rules; zsh in the Ubicloud mirror. - scripts/test-health-report.ts links #free-suite-duration-seed, so the two seed messages share one heading (the anchor test caught the split). - CONTRIBUTING.md: Windows seed refresh and native qualification rows; seed-source pointer. AGENTS.md: Windows six-job lane. - docs/cso-release-qualification.md: the free CSO Docker job runs only cso-docker-integration.test.ts. - docs/test-audit-2026-10.md: free-suite evidence lines. - TODOS.md: CEO-11b progress note on the pre-push hook hang. * test: final duration seeds on the integrated tree; retire the emptied cookie-validation-phases file Linux seed re-recorded on Ubicloud standard-16 and the Windows seed from dispatch run 37227140871, both at c903310. The seed allowlist drops the three entries that are no longer over the ceiling. cookie-validation-phases lost its validation-phase pins with W8f and its Windows/Dia pins moved to windows-native-workflows with native-qualification.yml, so the file is deleted and the curated Windows floor rises to 638. The Windows recorder writes the seed at its default path so GSTACK_FREE_TEST_DURATIONS never leaks into timed tests. * test: re-express stale PR-lane pins against the new evals.yml contract - ci-eval-cache: the profile/fresh expressions now include evals_all=false dispatches and pr_receipts/evals-fresh; the PR store is restored only by recover-receipts (still scoped to repository_id + PR, PR events only), plan-slices takes it as an artifact and never touches the cache, saves stay PR-only, EVALS_CACHE_PR binds pr_receipts dispatches, and the report verdict artifact carries report receipts. - ci-paid-coordination: plan-slices needs only the two ubuntu coordination jobs (never the image); the fork/Dependabot clause is unchanged on plan-slices and also gates debounce and recover-receipts; only recovery holds actions: read. - qa-supervision-selection: auq-consistency and auq-verbose-vs-carved-ab (W1b) reach claude-pty-runner and pty-screen through auq-sdk-capture, exactly as auq-format-gate does. - paid-retry-supervision: the full-validation plan uses a tracked full-gate input (setup); an absent path is now a deletion placed by its references. * ci(windows): record the Windows seed at the default path * chore: HARNESS_VERSION non-behavioral decision for the audit-wave integration * v1.91.20.0 release metadata: test, eval and CI audit wave * test(compare-board): wait for the post-submit state the feedback POST settles The two post-submit assertions read the board once, but the board disables the submit button and shows the message only after its feedback POST resolves. On a loaded Ubicloud shard the read beat the round trip (FLAKY-PASS in the final free-suite run). Delaying the POST by 400 ms reproduces both failures at HEAD; polling for the settled state passes. * test(plan-eng plan-mode): run the seeded STOP-gate smoke in its own fixture project The seeded plan proposes a custom test runner, so the review's Step 0 reads the working tree's test setup. In the gstack checkout that is gstack's own sharded runner, and the case timed out at 300 s in census 37228573062 after this wave reshaped the runner. It now runs in a four-file Bun project with git history, with the product-notice suppression auto-decide-preserved's standalone fixture already uses. Local pass on Bun 1.4.0 + Claude Code 2.1.284: asked in 121 s, seed tokens observed. * test(plan-mode evidence): pin the seeded eng smoke's isolated fixture cwd and env * ci(image): Git >= 2.44 so paid shared-libs cases run the supported safe-git path bin/gstack-safe-git prefixes every /deslop-shared-libs Git read with --no-lazy-fetch, which noble's git 2.43 rejects (exit 129). The eval image therefore ran every paid shared-libs case on the unsupported-Git fallback: local history unavailable, branch HEAD unknown. shared-libs-read-only failed on exactly that in PR run 37230639146 ("Current branch HEAD: unknown. The safe-git probe failed (unknown option: --no-lazy-fetch, git 2.43.0)") and in 2 of 74 earlier PR runs. The image installs current Git from the Ubuntu Git Maintainers PPA and fails its build if --no-lazy-fetch is missing; the deliberate unsupported-Git case keeps its fake Git. * eval: pool matching branch census trials into main's pass-rate series (D1 option b) Approved 2026-10-05. eval:pass-rates also reads completed branch census runs in the weekly window. A branch trial counts only toward a series a main run also has (same case-owned bytes, HARNESS_VERSION, model and CLI), so a branch extends main's history but never starts or becomes a case's current series; weeks for quarantine expiry still count main runs only. The D1 backtest put this at 67 of 210 cases with enough trials for the entry rule, against 0 of 195 on main alone. * C2: /qa defines its outcome filename fields; QA report templates name the measured timing fields Low judge samples in failing panels named both: qa workflow (37186854666) 'an undefined {user} in the outcome filename', and qa-only workflow (37198445662) 'template asks for Duration / durationMs totals while reporting.md mandates Probe budget and Guarded command time'. The qa union stays under its 1.11 size ratio (93292 of 93294 bytes). (cherry picked from commit e14c0c1de1) * C2: Browser Quick gets a feasible budget; QA loop names its directory and stop path Judge rationales on the qa-only panels (2 of the last 3) cited the 30 s Browser Quick budget: homepage + 5 targets, each a checkpoint write and a guarded command, left ~5 s per probe. Quick is now 180 s (method text: 3 minutes); the qa-only-no-fix paid check expects the same native deadline. PROBE_DIR points at its source line, a stopped loop goes to the final report steps (annotations, materialize, Markdown), and /review and /ship say that after smoke expiry only plan checks rerun in revalidation. (cherry picked from commit 78d4a2a343) * qa: fit the C2 judge fixes under the qa and review size caps Brings GSTA-21's qa.ts trims (3bd625d, ce73af0) for the cherry-picked C2 wording: PROBE_DIR keeps 'owned', the stop line points at §4, and the post-expiry rule is one sentence, so /review fits its cap. qa measures 93,303 / 84,049 = 1.11010 against the same 1.1102 cap GSTA-21 set. The qa-only workflow judge passed 10 of 10 local trials on this wording (7 of 10 before the C2 fixes). * test: qa-only fixture keeps its caller-set 30 s deadline The qa-only-no-fix fixture tells the model to start the guard with 30 s (a caller limit), so its deadline assertion's default stays 30 000 ms; the product's Browser Quick default (180 s) does not apply to it. Reverts the helper and its test to their base. (cherry picked from commit e36e622add) * test: qa-quick sets a caller probe limit and drains past its session budget C2 raised Browser Quick's native budget to 180 s. qa-quick is the only gate case on the native budget, and its wall went 194 s (main periodic, pre-C2) -> 254 s and 274 s (this PR's runs) -> 300 s session timeout (run 37242691913): the agent now probes every navigation target with a checkpoint, then needs ~80 s to report. Like qa-only-no-fix, the eval now sets a caller probe limit (30 s), scopes the fixture, and gives bun's outer timeout the session drain margin instead of racing the 300 s session. The product's 180 s budget and the session budget are unchanged. Diagnostic rerun passed in 195 s. (cherry picked from commit f8dc64031e) * chore: restore the audit wave's package scripts after the main merge (version 1.91.23) * qa: keep main's one-sentence post-expiry rule for /review and /ship The C2 variants ("step 4c reruns plan checks only" and "even in 4c") read to the review workflow judge as conflicting with Step 5.8's repeat-pass reruns: 6 of 10 local trials passed with the longer sentence and PR run 37248650879 failed on the shorter one. Main's "Post-expiry smoke rechecks are not-run." passed 10 of 10. qa (9/10), qa-only (10/10) and ship-managed-hook-refresh (10/10) were measured on the same tree. * v1.91.24.0: move off the slot #3036 claims	2026-10-05 01:29:54 +00:00
4 people	ac20ef1e13	v1.91.16.0 fix: safe installs and upgrades, skills start everywhere, truthful completion (parallel wave) (#3014) ... * fix(make-pdf,design): real TOC page numbers and anchors; design models move to gpt-5.5 + gpt-image-2 (#2903, #2807) * ci: pin every action to a SHA, Scorecard, checksummed Bun, scoped Codex CLI in the CI image, macOS named-regressions job (#1948, #1706, #1997) * fix(cso,browse): Windows/macOS lease identity, retention skips bad runs, truthful 'not assessed' reports, env.kv false positive, Windows browse spawn fixes (#2894, #2912, #2048, #2637, #2805) * fix(outside-voice): one Codex model precedence for probe and dispatch, bounded timeouts with KILL escalation, probe cache identity, guarded mktemp, skills hidden in nested Codex (#2776, #2914, #2787, #2881, #2847) * feat(setup): install registry, ./setup --status, staged activation, per-scope migrations, host tiers and conformance kit, OpenCode/Hermes fixes, Copilot CLI (experimental), disabled_skills, slimmer CLAUDE.md (#1925, #2879, #2347, #2338, #2626, #2629, #2825, #2015, #393, #1206, #2096) Co-authored-by: Andrey Esipov <61357035+andrey-esipov@users.noreply.github.com> Co-authored-by: Matthew Williams <5863886+ridermw@users.noreply.github.com> Co-authored-by: Rocky Wu <92764750+lolisaigao1234@users.noreply.github.com> * fix(preamble): skills start in worktree-isolated Claude Code sessions — one literal skill-start line, context-recovery helper, no eval in skill blocks, $N token tripwire, honest plan-mode precedence (#2763, #2896, #2851) * fix(setup): per-install renders for renamed, vendored and custom-config installs, space-safe alias roots, per-host /cso launcher path (#1882, #2906) * test: free tests never write the real HOME (home-write tripwire), no orphaned browse daemons, symlinked-TMPDIR (macOS) fixes, gbrain-on-PATH isolation (#2895, #2816, #2829, #2841, #2982, #2911, #2909, #2908, #2910) * chore: integrate wave follow-ups — regenerate all hosts, README model docs, TODOS, touchfiles, duration seeds, Bun 1.3 telemetry test fix, replay fixtures pinned to their recorded bytes * v1.91.14.0: release metadata * test(browse): group-kill cleanup falls back to the leader when macOS returns EPERM for a live group * ci: Codex login steps run under bash (the CI container's default sh rejects pipefail) * fix: full-suite repairs — private state roots for 7 real-HOME writers, truthful home-guard attribution with --attribute-home, gstack-paths shim in ship-hook fixtures, Copilot in team-init probes, test-of-test detector, cookie review fixture pinned to the approved excerpt * fix(windows): LF for Dockerfiles, normalized home-guard exclusions, path.relative fixture containment, ship push test spawn timeouts * test(design-detect): widen the whole-scan budget test's timing margins so a loaded macOS runner can't time out the single-batch call * fix(evals): qa protocol names defined for the judge, async PTY judge so overlapping sessions keep their cleanup deadline, bws setup cases use the standard JUDGE_MS tier * test(pty): the non-blocking judge case is POSIX-only (its fake judge is a shebang script, like the PTY harness it covers) * test(evals): ship-coverage-audit names absolute skill paths, uses Read, and skips the Step 7 artifact nothing consumes (removes the mechanism behind 3 of 4 historical timeouts) * test: deflake terminal-agent concurrent startup (write the placeholder record before spawning, like the product) and qa-evidence resumed pipe (barrier on a full high-water mark instead of a sleep) * fix(design): daemon log stream handles open errors instead of crashing the daemon; shutdown test awaits the stubbed exit * test(evals): skillify checks the product's resolved state root (no GSTACK_HOME bypass), negative cases check every root; tpa shims live outside the agent's cwd and answer consistently * test(evals): coverage-audit detector splits parallel columns at │ rails and [+] groups; coverage prompts name absolute skill paths; TODOs from the gate eval census * fix(plan-eng-review): scope gate always sends the menu (no headless 'Scope pending' exit); PTY harness ends idle turn-ends and API-error panels promptly with a precise diagnostic * test(evals): one position-bound coverage-read rule credits read-only && chains (labels, context ranges, git displays in either order) and still rejects forged output * fix(ship): documentation section has one saved source inserted by cat (never retyped); spawned-marker evidence is the child output; refreshed codex/factory ship goldens * test(docsync): the byte-exact insert positive is POSIX-only (the bash-command observer refuses backslash paths by design) * test(evals): plan-design-with-ui focus-title rule accepts the comma-less 'dimensions or focus' wording (replayed on the captured CI run, negative controls kept) * fix(qa-callers): exploratory preflight says the scope/method Reads come after exploratory.md; design-review scan check credits an executed scan proven by one engine run over the changed files --------- Co-authored-by: Andrey Esipov <61357035+andrey-esipov@users.noreply.github.com> Co-authored-by: Matthew Williams <5863886+ridermw@users.noreply.github.com> Co-authored-by: Rocky Wu <92764750+lolisaigao1234@users.noreply.github.com>	2026-10-03 07:54:09 -07:00
Garry Tan	7fca42ad8b	v1.91.12.0 v1.91.12.0: audit fix wave, ~11-minute paid eval lanes, eval reliability policy (#2999) ... * test: delete test-infrastructure dead code (G) - exit-propagation drives the runner's real strict verdict (BunTestOutputClassifier + strictTestExitCode); delete the unused shardRunLooksTruncated predicate. - delete skill-coverage-matrix registry + its gate (nothing reads it; the floor already iterates skillCensus()). - delete touchfiles-facade export-parity tests (Bun fails missing imports at link time) and the duplicated E2E_TIERS tier-value test. - delete brain-cache-spec TRANSPORT_DEFAULT_POLICY, SKILL_RUN_RETENTION_DAYS and the now-unused BrainTrustPolicy type with their literal tests. AUTOPLAN_PREFLIGHT_BUDGET_BYTES stays: skill-preflight-budget enforces it against real resolver output. - delete audit-compliance's JSDoc-comment grep. * test: replace product tests that fake the product with real-boundary tests (F) - design: serve.test.ts drove an inline mirror server; now two tests run the real serve() on an ephemeral port (reload confinement, submit exit 0). - setup-gbrain: rollback + voyage tests execute the template-extracted init blocks (3 sites) instead of drifted local bash copies. - terminal-agent: internalHandler source greps replaced by a behavioral /internal/grant + /internal/revoke auth matrix (no/wrong/valid token). - /health: server-security-surface and the server-auth / security-audit-r2 / sidebar-tabs source greps fold into one liveness-only check on the real body; the L4 sidecar wiring gets a behavioral /pty-inject-scan test. - delete tautologies (browser-manager onDisconnect, memory-command #12), ios swiftui tap fixture self-check, memory-ingest put_page grep, detach source greps, sidebar-agent absence pins, dead-CSS pins + the dead CSS, security-audit-r2 Task 1 + the test-only meta-commands re-export, duplicate generated-SKILL.md checks. - make-pdf coverage-gaps cases move into their owner test files. * test: delete tests of dead eval code (A) - A1: the retired Eng lexical oracle (evaluateEngSeedCoverage, isEngSeedDecisionAUQ), the completion-handoff detector and the retained corpus had no paid caller since v1.87.6; delete their 26 replay files, ~2.6k helper LOC and fixtures, and the dead blocks in 8 mixed files (live hasNativePlanTerminal / batching assertions stay). - A2: dead viewport approvers in autoplan-artifact-permission and their 11 replay files + fixtures; recorder/launcher cases stay. - A3: never-wired oracles and seeders (autoplan-phase-order, eng-finding-fixture, ceo-paired-fixture, design-ui-scope, plan-skill-completion, pty-current-screen, required-reads, transcript-section-logger); plan-seed-submission now decodes through the production createPtyScreen; section manifests name their actual guard. - A4: zero-reference helper exports, plus execGit and invokeAndObserve found by the reachability pass. - 52 fixtures orphaned by the deletions; touchfile and selection-table entries for every deleted path. * test: clean up the paid eval lane (B1-B4, B6, B7) - B1: delete paid files that assert nothing or cannot pass meaningfully: skill-llm-eval-spec and skill-e2e-spec-execute (test.todo), gemini-e2e (+ gemini-session-runner; no gemini CLI in CI), ship-idempotency (red since v1.63), the two opus-4-7 *-sonnet overlay wrappers, conductor-prose (+ its source-evaluation replay), codex-e2e-plan-format; drop their keys, scripts and census rows. - B2: skill-llm-eval grades browse/sections/command-list.md with one union judge that also carries the baseline score pin; regression-vs-baseline deleted (paid run: pass, c4/c4/a4). - B3: memory-pipeline, ios-qa, ios-qa-swift-build and plan-tune-cathedral make no model calls; renamed out of the paid glob so they run on every PR. Swift builds need GSTACK_TEST_SWIFT=1; device stub deleted. - B4: codex-e2e*, outside-voice, aside and ios-device cannot run in the CI image; excluded from the weekly lane with a tracked re-entry condition. - B6: fold opus-47's negative routing controls into skill-routing-e2e journey-negatives (paid run: 3/3 unrouted) and delete the file. - B7: delete the never-green brain-privacy-gate eval; a free gstack-skill-start test now proves consent precedes artifacts egress. * test: retire the finding-count cluster and trim its helpers (C) - C0/C1: the five never-green evals (skill-e2e-autoplan-chain and skill-e2e-plan-{ceo,eng,design,devex}-finding-count) failed on harness and budget, never on skill behavior; delete them, their touchfile/tier ids, AUTOPLAN_CHAIN_BUDGET and the dedicated eighth periodic slice (--slices 7). - C2: delete the helper groups whose only paid consumers were those files (11 modules), trim claude-pty-runner and eng-seeded-coverage to the paid closure, and delete the free replay tests whose assertions exercised only that dead code (89 files, 135 orphaned fixtures). Blocks that used dead code only as input for a live subject keep their assertions: the multiSelect default moved to plan-review-decisions, runner PTY tests use inline caller policies, and the timer-safe budget checks moved to eng-finding-retry-budget. - The eight production-touching files stay except ceo-current-decision-record (its template read only feeds the retired counter). - CARVE_GUARDS.autoplan is behavioral 'none'; TODOS records the lost chain and per-finding cadence coverage with their re-entry tests. * test: fold per-incident replay series into their detector owners (D) Twelve detector families move into one owner test each: 73 incident files become describe blocks in ceo-section-loading-fixture (stale-fill race), model-overlays, coverage-audit-evidence, autoplan-phase-observer, native-auto-decide, outside-voice-evidence, eng-first-review, plan-count-completion, plan-count-file-permission, ceo-mode-option, plan-scope-selection and plan-count-prerequisite. Each block keeps its original code and fixture, so every case still runs; only tests asserting the incident file's own touchfile registration are dropped (41). Touchfile lists that named an incident now name its owner. * test: start the plan-count history PTY on its readiness marker (H) The fake CLI prints a startup marker and the runner waits for it instead of the fixed 8 s startup sleep (8.6 s -> 0.9 s locally). eng-semantic-terminal's sleeping registration cases went with C; plan-count-timeout keeps the fixed wait because it asserts deadline behavior. * test: derive paid touchfiles from each eval's static closure (E) touchfiles.test.ts now checks, per key, that the paid file's static test/helpers and test/fixtures closure (plus fixture paths it names in string literals) is covered, and names the file, path, chain and key to fix when it is not. Free *.test.ts files are no longer touchfiles, so editing a free replay test stops selecting paid evals: 950 entries removed, 653 real closure paths added. The hand-copied inventories go: periodic-fixture-selection, fake-impeccable-touchfiles and 45 per-file selection examples. Selection for the sample edits (plan-eng-review template, claude-pty-runner, plan-count-fixture, gstack-config) loses no case under either profile. CONTRIBUTING documents the rule and its lower bound. * test: skip hollow tier shards and census judges in the paid planner (B5) A paid file is now skipped for a tier lane only when every E2E id it registers is known statically and none has that tier; ids come from the touchfile registrations and literal testName/*IfSelected arguments, so a comment or skill path that quotes another id cannot unschedule it, and computed names keep today's scheduling. --list and the manifest show each skip as "skipped: no E2E_TIERS id has tier <tier>". The weekly gate census drops the LLM judges (--skip-judges); they still run in the periodic census and PR gate lanes. Gate lane 52 -> 42 files, census 41; periodic 77 -> 69. * test: run seven paid evals on the current default capture model (B8) skill-e2e-{auq-matrix,plan-format,qa-bugs,retro,workflow} pinned claude-opus-4-7 and skill-e2e-office-hours plus -brain-writeback pinned claude-sonnet-4-6; none tests a historical model, so they now capture with resolveEvalModel('capture'), and the free harness tests that execute these registrations receive the same resolver. The paid re-pin run passed all of them. skill-e2e-{design,office-hours-phase4,plan-prosons,plan} keep claude-opus-4-7: six of their cases failed on the default model (three timeouts, a missing report file, a format miss and a posture score of 3), so per the plan's fallback they keep their pins with a TODOS entry. The pre-spend estimate and drop threshold are in docs/test-audit-2026-09.md. * test: guard the reduced suite against new test-of-test files - test/test-of-test-ratchet.test.ts records the 228 free tests that import only test/ code and fails on a new one, naming the owner test to extend instead; a stale baseline entry fails with the remove instruction. - test/helpers/resolve-repo-path.ts is the one specifier/literal resolver for the ratchet and the touchfile closure invariant, with its own unit tests. - CONTRIBUTING "Test tiers" describes the paid-failure workflow (fix, then one row in the detector's owner test) and the ratchet; TEST_PORTFOLIO gains the detector -> owner-test table and no longer claims an Autoplan chain eval. - TODOS: automatic exclusion policy for chronically red periodic files (P3), the deferred native-completion table collapse, the unused CEO payment seeder; the PTY readiness item is narrowed to the paid runner. - docs/test-audit-2026-09.md collects the triage, security mapping, inventories, selection proof, behavior-commit decisions and retained false positives. * v1.91.8.0 test: smaller suite, derived paid selection, retired never-green evals Release metadata for the test-reduction branch: VERSION 1.91.8.0 (1.91.7.0 is claimed by #2983), CHANGELOG with the measured before/after table and a contributor section, durations re-recorded on Ubicloud standard-16 (857 files, 0 failures), the agents digest, CONTRIBUTING's after-measurement row, the B8 fallback TODOS entry, and the after metrics, kept-vs-plan notes, B8 run and census estimate in docs/test-audit-2026-09.md. * fix(ubicloud): skip retrieval globs that match nothing instead of reporting a failed pull * test: pin DISABLE_AUTOUPDATER in hermetic env and capture corrupt-seed warning Both EVALS_HERMETIC branches of buildHermeticEnv now carry DISABLE_AUTOUPDATER=1 (the allowlist scrubbed the workflow's copy, so every PTY screen showed the updater's npm-prefix failure). Per-test overrides still win. The corrupt durations-seed test now captures its expected warning and restores the console spy. * style(cso): format lib/cso TypeScript with pinned Prettier Mechanical reformat only. Minified transpile output is byte-identical for 21 of 22 files; witness.ts differs only in three regex flag orders (/mi -> /im), which JavaScript canonicalizes. Source-text assertions over lib/cso now compare whitespace-insensitively with the same tokens. * fix(cso): import join for compiled-launcher assertion witnesses Compiled installs always take the non-Bun branch, which called an unimported join and threw before any runtime-tested assertion could be witnessed. The child command selection is now a pure, platform-aware function; a missing sibling launcher fails with its expected path. * fix(browse): make connect --supervise actually respawn a crashed server The supervisor respawned with a block-scoped env that no longer existed, so every attempt threw and the loop gave up after five tries. The headed env is now one pure helper used by connect and respawn, the loop is an injectable runHeadedSupervisor with behavioral tests, failures name the daemon log and relaunch command, and connect's usage advertises --supervise. * test: one finite PR world for the shared-libs fixture; name dual-voice probe evidence The shared-libs shim served 2 PRs for pulls?state=all and endless full pages for state=open. gh pr list, pulls?state=open|all|closed (per_page/page, short last page, direction) and search/issues now page one deterministic table: PR 7, 600 older open PRs, PR 42 and 3 closed PRs, so five 100-item open-metadata pages still leave older open PRs unchecked. The Contents API lists pinned directories (the captured attempt got 404 for contents/ and contents/src while files resolved, then fell back to a raw host), unknown endpoints return 404 instead of repo metadata, and the read-only detector is unchanged. Free tests cover view agreement, the budget bound, gh/curl agreement and the empty world. Dual-voice outside-voice failures now report probeToolUseId, probeMode and the canonical-match result with the reason the probe output was rejected. * feat: require a zero-error product typecheck and a test type-debt ratchet Adds tsconfig.json (strict) over product code, fixes its remaining 90 diagnostics (type-only, interface corrections, and explicit narrowing), and adds a typecheck job to the required free-tests aggregate running bun run typecheck, the test-code ratchet (identity -> count baseline, fails on new, repeated, or unlocked fixed diagnostics), and the lib/cso format check. Reuses fixes from #2447 where they still applied. * test: follow the headed env helper and the typecheck gate in source-shape checks * fix(test): pin the package.json change kind in shared-input selection tests computePaidCaseSelection read the version-only exemption from git even when changed files were injected, so the shared-input test failed on main and on version-only branches. The exemption is now an optional input; the test pins a real package.json change and covers the version-only case. * test: judge plan-count completion on structured evidence, not wording Replaying run 36385945043's two Design attempts showed the existing routes rejected correct endings: attempt 1 at the typed-completion path field ('- Reviewed plan written to …' is not a 'Plan written to' line), attempt 2 at the leading-fence veto (its final message opens with the dashboard). nativePlanTerminalPreconditions is the structural prefix of hasNativePlanTerminal (behavior unchanged). structuredPlanCompletion adds, inside the existing nativeSummary branch: a complete report (Design binding for Design), a completed review-log row for the expected skill appended during this attempt under the child's GSTACK_HOME/project slug (resolved with bin/gstack-slug) and stamped with the fixture commit, timed between the report/last answer (second resolution) and the final native message, a final message with stop_reason end_turn (now carried on public transcript messages), and no visible question or permission prompt. Timeout summaries add idleFor and lastTerminalCandidate. Terminal and throw captures copy the plan file and review-log rows into the artifact directory; copies are best-effort and recorded in evidence-copy.json. Free regressions: both captured Design endings (trimmed fixture with provenance; report, row and end_turn reconstructed and labelled), the negative controls, and real-PTY completion/timeout runs through the real review logger. * test: structural Design count boundary; TODO proposals are not findings Replaying run 36385945043 through the Design count predicates: routing, focus and learnings setup was not recognized as setup, Issue 1 was counted pre-review in both attempts (the boundary fired on it), and attempt 2 counted the Font TODO proposal as a finding (review=4 and review=5 for five issues). The paid caller now starts review at the first answered native decision that is not setup (recognized packet, or setup header/question ID), a completion handoff, artifact rendering or a TODO proposal (the review's Add to TODOS.md / Skip / Build it now menu). TODO proposals are recorded as administrative extra decisions. The replay asserts each counted call: both attempts review=5 (Issues 1-5). isDesignCountFirstReview and its controls are unchanged. * test: CEO classifier throws name the question and matched predicates Replaying run 36385945043's FAN-1 and ERR-1 throws (ledger rows reconstructed from rendered diffs) through ceoPaymentFinding: the email obligation's row, subject, option and proposal predicates pass and the ELI10 explanation-defect predicate fails first ('lets that exception fly out', 'the error bubbles up'). Binding the defect to the named ledger row instead (the planned fix) was tried and reverted: scoped to the email seed it flips 30+ existing cf74 still-rejects replays, which require a vocabulary-free, ledger-bound email question to earn credit only through a complete saved comparison. With FAN-1's rendered currentDecision payload reconstructed, the recorded- decision path counts it, so the real saved plan (not uploaded) must have differed; failure artifacts now retain it. The classifier stays fail-closed and unchanged. Its throw now prints the header, the first 200 question characters and each obligation's predicate results. Free regressions with provenance and negative controls: an unrelated question, an email question whose row says it is already rescued, and a ledger ID whose row belongs to another seed. * chore: regenerate the test type-debt baseline on top of #2994 * fix(typecheck): strip the checkout root from ratchet diagnostic identities * fix(test): recognize ledger row-ID split candidates so collection stops at the last ACK Run 36385945043's split-overflow case asked all five candidate decisions by 8m55s, but the live candidate check required the question to open with "E1:" and every option to be a known disposition. The skill cited ledger row IDs ("D2.1 — R-E1: …") and offered "Hold, discuss first", so no candidate was recognized and the attempt ran the whole review (1302s). Identity now comes from the native header; the question must open with that candidate's ledger reference, name only that candidate, and offer exactly one include, defer and cut disposition. The selected answer must still be one of those three. The semantic evaluator and every existing negative control are unchanged; a trimmed capture from the run adds the positive case and four row-ID negative controls. * fix(test): stop the eng batching eval once its floor is proven The case's only verdict is reviewCount >= FLOOR (3). Run 36385945043 had three distinct acknowledged review decisions at 6m41s but kept answering until the ceiling (7) at 12m13s. The registration now passes the runner's existing isCollectionComplete stop once FLOOR non-setup, non-administrative review decisions are acknowledged; the floor check, ceiling, budget and counter are unchanged. A child-process registration test proves the stop predicate and that below-floor and timeout outcomes still fail. * test: add the non-blocking 'marathon' E2E tier Full start-to-finish flows move out of the blocking lanes. E2E_TIERS and E2ETier gain 'marathon'; describeE2ETier('marathon') is enabled only when EVALS_TIER=marathon, so the gate/PR and periodic lanes (and the gate census) never run those cases. The PR profile accepts marathon ids as scheduled elsewhere and defers them with their own reason, even on full fallback. * test: move the full office-hours workflow to marathon; add a periodic design-draft checkpoint The full startup workflow runs 1–3 real spec-review rounds (~280s each) and hit its 1200s capture in run 36385945043 at finalize. Review depth is the product's loop, so the case cannot fit a blocking lane without cutting rounds. It is now marathon tier with every assertion unchanged. skill-e2e-office-hours-design-draft.test.ts (periodic) runs the same fixed interview only through the Write that creates the design (269s in that run) and applies the full validator's design-draft checks, the required section reads and the launch/foreign-skill-read guards. validateOfficeHoursDesignDraft is extracted from validateOfficeHoursCompletion, which still applies it. Selection: office-hours-design-draft is registered periodic; the marathon-only file is already excluded from the gate and periodic plans by the B5 planner rule. Tier-alignment regexes and the valid-tier check accept 'marathon'. A type-only cast in plan-scope-selection.test.ts removes a diagnostic whose union print order made the ratchet identity unstable; baseline tightened. * test: supply the split-overflow fixture's HOLD SCOPE mode as a prerequisite The split actor always answered 0E's mode question with HOLD SCOPE. The skill skips that question on an explicit choice, so the fixture now states it and the attempt starts at the five candidate decisions (about 1.5 min earlier in run 36385945043). Candidates, actor policy, floor and semantic evaluation are unchanged; the fixture test pins the supplied choice. * test: start the eng batching eval with its setup prerequisites supplied Routing setup and cross-project learnings (D1/D2 in run 36385945043) are never counted and are not what the case measures. The registration now uses the runner's existing preconfiguredReviewActor so the attempt starts at the review; engSetupAUQ still vetoes any late setup question. The registration test pins the option. * test: count the design-draft paid file and defer marathon ids in PR selection pins The discovered paid-file census grows by one (skill-e2e-office-hours-design-draft). Full-fallback PR selection defers every non-gate id; the shared-input pins now expect periodic and marathon ids there. * fix(review): resolve the judged revalidation, setup-authority, plan-gate and findings-record ambiguities The census review workflow judge scored clarity/actionability 3 on both attempts: smoke-clock limits appeared to forbid post-repair revalidation, the caller deadline was undefined, 'ask for setup' conflicted with the report-only browser rule, fallback-sourced HIGH discrepancies had no gate decision, and the Step 5.8 record omitted adversarial findings. * fix(office-hours): load the builder section for every builder-mode reply Both census builder-wildness attempts answered a direct request for adjacent unlocks without reading phase-2b-builder-brainstorm.md, whose trigger read as applying only to the generative questions. * fix(sync-gbrain): define Step 4 helper args and one atomic write path Both census read-ready attempts spent turns reading the helper source to resolve <user-args>, inspecting fixture internals kept inside the repo, and reconciling 'Read + Edit' with the tmp+mv atomic write, then hit max turns before the verdict. * refactor(evals): share the import-closure walker and add the E2E shard reuse identity sourceDependencyClosure moves from the workflow-judge adapter into scripts/eval-input-cache.ts unchanged, so judge keys stay byte-identical. scripts/e2e-shard-reuse.ts builds the consumed-input identity of one PR-lane E2E shard (test import closure, every registered case's touchfiles, globals, runner/workflow/setup actions, child env pins, CI image, Claude CLI) and fails closed on anything unknown. Marathon joins the always-fresh purposes. * feat(evals): ~12-minute blocking paid lanes and a non-blocking marathon lane - Planner budget mode (--slice-budget S --jobs J): recorded per-tier wall times pack into as many ~9-minute executors as the work needs; the plan records per-slice estimates and the CI job timeout (supervised worst case + 20 min). evals.yml and evals-periodic.yml derive matrix size and timeout-minutes from it; max-parallel covers every slice at once. - Case shards: plan/design/review-army/shared-libs(-paths) run one registered case per process (<file>#<case id>, exact name pattern, exactly one case). - Retry rule: a timed-out attempt is a verdict. Only files whose every case budget is CAPTURE tier or shorter keep one retry; walls shrink to match. - Marathon tier: positive selection, excluded from gate/periodic planners, run by the new evals-marathon.yml (weekly + dispatch, fresh, own report). - PR-lane E2E reuse of verified first-attempt passes on identical inputs; the report rejects reuse outside the fast PR profile. - Duration seed from census run 36385945043, per tier and per case shard. * docs: blocking lane budget, marathon lane, retry policy and E2E reuse * chore(typecheck): lock in two fixed test diagnostics * fix(ci): drop a duplicated env/jobs block in evals-marathon.yml * test(ship-docsync): shard the doc-sync lifecycle by case and drop the duplicate dispatch-only case ship-docsync ran the same fixture and prompt as ship-docsync-completion and asserted a subset of it. The file now runs one case per process, so its lane wall is its longest case instead of half the sum of thirteen. * fix(evals): plan CI-unrunnable cases as excluded entries, not empty case shards design-review-fix drives the Aside browser and registers test.skip on Linux runners, so its case shard executed zero cases and failed the exact-one-case check in proof census 36597762183 (eval-slices 6). CASE_CI_EXCLUDE (reason + tracking, beside PERIODIC_CI_EXCLUDE) now turns such cases into excluded manifest entries that --list and the manifest surface; every planned case shard still must execute exactly its case. * docs(todos): list the case-level Aside exclusion with the CI-unrunnable evals * fix(plan-ceo-review): restore experience-first expansion framing, require the mode handoff, skip pacing menus Census 36597762183: both mode-routing runs logged provenance and moved on without the mandated handoff chat; the EXPANSION run asked an unauthorized batch/narrow pacing menu instead of the first per-addition question; the expansion-energy proposals led with the spec because v1.87.6.0 dropped 'lead with the felt experience'. The HOLD review detector also rejected a decision whose grounding line named no plan file although the owned source Read binds it. * test(outside-plan-disabled): bind quoted prior-record values by their sentence, not phrase order The parent obeyed the off switch and twice named the seeded completed record as pre-existing, once with the quotation after its owner and once with slash separators; the order-specific stripper counted both as current completion. Timestamp, location, current-claim and value-match controls still reject. * test(outside-plan-disabled): compare named record timestamps as instants; negated authorship is not a current claim The repair rerun named the seeded record by its ISO second (2026-09-29T16:58:52Z vs .727Z) and said 'I did not write'; both were misread as a foreign timestamp and a current write. * test(ceo-section-loading): recognize an arrow-ordered stale-fill execution by event roles The census review traced the seeded race as 'R1 miss -> R1 store read (v1) -> W commit v2 -> W cache.delete -> W fulfills -> R1 cache.set(v1) -> R2 (begun after W) hits v1', but the in-flight gate only accepted race vocabulary or fixed sentence shapes. Order, actor, version and dismissal mutations still fail. * test(design-floor): answer the seed-declared all-seven 0D focus menu while it is pending The actor declares 'Design: review all seven dimensions', but its picker reused designReviewSetupAUQ, which only matches already-answered calls (and a narrower header/label set), so the pending D1 focus menu was never answered and the case waited out its 609 s deadline. The skill's Step 0D requires asking; the fixture now answers it. * test(ceo-mode-routing): accept the skill-mandated Note form and Recommendation reason as HOLD posture HOLD Defer/Keep briefs must use 'Note: options differ in kind' (preamble), but the answered-HOLD path demanded a Completeness score, rejected a one-line Net with a semicolon, and read posture only from ELI10. The rerun's brief applied HOLD SCOPE in its Recommendation reason. Revert the ineffective 'always'/'handoff chat' wording: two runs still skipped the mode handoff. * test(qa-bugs): keep claude-opus-4-7 after qa-b6-static stalled on the default model qa-b6-static timed out on claude-fable-5-1 in census 36597762183 and in one of two targeted reruns. Both times the stream stopped mid-message with no pending tool, right after the model found the disabled submit button, and stayed silent until the 300 s deadline. Per the B8 fallback, re-pin with a TODOS entry; budgets and retries are unchanged. A rerun on opus-4-7 passed (125 s, 5/5 detected). * test(evals): add E2E_KINDS, BEHAVIOR_WHY, EVAL_POLICY and CASE_QUARANTINE skeletons Every E2E_TIERS and LLM_JUDGE_TOUCHFILES key starts as 'rule'; BEHAVIOR_WHY and CASE_QUARANTINE start empty. EVAL_POLICY pre-registers the approved panel (3, majority 2), quarantine entry 0.95/10 and exit 0.97/10, 10% cap, 8-weekly-run expiry, Fisher drift alarm and one INFRA re-dispatch. * test(evals): add trial records, panelVerdict, expectContract and trial-outcomes JSONL EvalTestEntry gains case_id, kind, trial, panel, failure_class and policy_version, stamped from the runner's TRIAL_ENV on isolated trial shards. panelVerdict() is the single verdict function (INCOMPLETE on missing or duplicate trials, contract veto at any count, quarantine hard-break rule, INFRA/INCOMPLETE machine classification). expectContract() records failure_class 'contract' on the collector entry and a sidecar before throwing. trial-outcomes JSONL has a fail-closed writer and a data-only reader. * test(evals): pin the fail-closed rule-shard gate through the real --report path Synthetic slice artifacts for rule fail, timeout, missing slice, unreported entry, hollow, never-started, collector failure and wrong-slice reports all exit red before the panel-verdict gate change lands. * test(evals): retire every paid automatic retry Paid evals never retry (approved 2026-09-29): delete SHORT_CASE_RETRY_FILES and retriesWithinCaseCap, drop the retry fields from the registered wall rows (walls now cover one run plus reserve), make retriesForFiles return 0, pass --retry 0 explicitly, and drop --retry 1 from the package.json paid scripts. Add the eval:pass-rates alias. Tests that pinned the old retry allowance are updated as a policy change; review-finalization-budget now proves late-result recording under the production zero-retry arguments. * test(llm-judge): sample every judge as a pre-registered 3-sample panel Each of the 24 skill-llm-eval judges now draws EVAL_POLICY.judge.samples independent samples of the same prompt concurrently inside the unchanged JUDGE_MS budget. Numeric dimensions gate on the per-dimension panel mean against the unchanged threshold; booleans (would_browse, consistent) on a strict majority. An erroring sample fails the whole panel and is never resampled; a refusal is an unscored panel only when every sample refused. callJudge's 429 backoff stays: it is transport before any model output. The workflow-judge cache stores and validates only complete panels, and its identity now records the panel and zero file retries. Harness tests that pinned one provider call per case now pin the panel size. * test(evals): classify every live case and re-select a case when its kind changes E2E_KINDS: rule by default (191 E2E ids), 22 behavior cases whose verdict is a live model choice with an acceptable sub-100% per-trial rate, each with a BEHAVIOR_WHY tolerance, and 25 judge entries (the 24 workflow judges plus the fixed-fixture llm-judge-recommendation rubric check). Contract-shaped cases (ask-before-decide, plan-mode no-writes, mandated steps, secrets, the batching floor) stay rule. Behavior requires a known literal registration and an exact Bun test name so the case runs as its own trial shard. Map-diff selection now diffs E2E_KINDS and BEHAVIOR_WHY per key, and a base revision without them selects every key, so a kind flip runs the panel it introduces. test/eval-kinds.test.ts enforces coverage, tolerances, isolatability and the reviewed counts, printing the literal to add. * feat(evals): per-case pass rates with Wilson intervals, identity series and quarantine policy scripts/eval-flake-rank.ts becomes eval:pass-rates (eval:flake-rank stays an alias, and the legacy aggregate stays exported). It reads eval-store's trial-outcomes JSONL from the last N completed evals-periodic runs on this branch and main (gh, downloading only the trial-outcomes artifact, cached and size-capped, parsed as data), plus local eval dirs, and prints per-case per-trial pass rates with 95% Wilson intervals. A series is a case's own touchfiles minus GLOBAL_TOUCHFILES (caseSeriesIdentities, for the report job to stamp), per model, CLI version and policy version. Labels: INCONCLUSIVE, BROKEN, FLAKY, FAILING, PASSING. --backfill imports legacy slice artifacts as pre-policy trials (first attempt only, attributed by registry id, never guessed) for display only. --gate fails with ACTION REQUIRED on post-policy evidence only: drift below the quarantine entry rule, a rule case behaving like behavior, a one-sided Fisher drop against the previous identity (Holm-controlled), and quarantine entries that met their exit rule, expired after 8 weekly runs, broke the 10% tier cap or are invalid. CASE_QUARANTINE entries now carry a failureClass (detector, harness or model-latency); a product defect has no class and is never quarantined. The policy test pins EVAL_POLICY's approved constants. * feat(eval-pass-rates): attribute legacy records by the exact slug of their display name * ci(image): pin Claude Code 2.1.284 so the eval model is recognized 2.1.251 logs [claude-code:unrecognized_model] for claude-fable-5-1, the eval capture/judge default. 2.1.284 does not. The gate PTY smoke subset (plan-ceo/plan-devex plan-mode, plan-mode-no-op) parses on the new TUI; plan-design-review-plan-mode passed at 293 s on 2.1.284 and timed out at 300 s on 2.1.251 on the same tree. * test(eng-batching): grade the floor once the review report is complete A completed GSTACK REVIEW REPORT ends the review, so the review-question count is final there. Run 36606688266 wrote its report at 1,248 s and closed the session at 1,318 s; the case now stops collection and applies the unchanged floor at the report instead of waiting out the session. No budget changes. * test(eng-batching): bind unsourced native briefs through the report's target Run 36606688266 asked ten separate native review questions (D1-D9 bound to ledger records R1-R9) and failed reviewCount=0 < FLOOR=3: its briefs named the plan by title instead of citing PLAN.md, its report declared 'Review target (fixed): PLAN.md' under '# Engineering review: <plan>', and it kept an unfenced copy of the plan's own H1. The named-source route now accepts those spellings and non-inline ledger briefs. The same replay rejects a foreign, mixed, duplicate or missing target, another plan's title or copied H1, a brief naming another plan or file, a mismatched saved brief, and re-asks. The run-36597762183 capture still counts 3. * fix(plan-design-review): treat a designer with no API key as unavailable Both proof runs (36597762183, 36606688266) printed DESIGN_READY, hit 'No OpenAI API key found' on the first $D variants call, then hand-built HTML/CSS wireframes, screenshots and a comparison board for ~195-245 s before the first review question; the second run timed out at 600 s. A failed first generation now takes the existing text-only path, and the skill forbids substituting hand-built mockups. * fix(deslop-shared-libs): read related sources together within the turn limit Run 36606688266's opportunity audit read sixteen sources one per turn and stopped at error_max_turns; the passing run 36597762183 read the same files in three batched commands. The skill now says turns are bounded and asks for parallel reads or one read-only command per step. * test(ceo-mode-routing): submit a mode review that scrolled past the viewport Run 36606688266 bundled routing, learnings and the mode choice into one native call. Its review panel was taller than the terminal, so the tab bar scrolled off, ceoModeSubmissionInput returned null for 240 s and HOLD SCOPE was never submitted ('no posture match'). With no bar on screen the viewport must still end at the focused Submit prompt, and the accumulated screen text supplies the one complete panel, authenticated exactly as before. Replay controls reject another mode, an unoffered answer, an altered question, a quoted panel, trailing output, a moved cursor and an answered or changed call. * docs(evals): document the pre-registered verdict policy, quarantine, pass-rate history and arithmetic AGENTS.md replaces the retry rule with the approved policy text (no retries; kind fixes trials; no added trials, samples or dispatches after a result; quarantine by CASE_QUARANTINE only; one INFRA/INCOMPLETE re-dispatch) and notes that a pre-registered fixed panel is not rejudging. CONTRIBUTING gains the kind rules, the judge panel, eval:pass-rates and an 'Add a paid eval' checklist. TESTING_INTERNALS describes verdicts, quarantine, history and the arithmetic, including the rule term: 1 trial vs 2-of-3 red rates at p = 0.99/0.95/0.90/0.70/0.30 and lane all-green probabilities for the current 191 rule / 22 behavior / 25 judge registry. * feat(evals): trial planner, slice exit split and panel-verdict report Planner: behavior and quarantined cases become panels of isolated trial shards (<file>#<id>~t<N>) bound by EVALS_SELECTION_JSON=[id] and the exact test name; the file shard excludes them by name. Trials of one case never share a slice, result slugs are unique, panels are validated whole, unknown registrations throw, and the planner prints a capacity preflight. Executor: each trial shard gets its TRIAL_ENV identity and a trial record (outcome, failure class, cause, cost); every shard writes a JUnit report. The slice exit now means execution completeness: a failed rule shard or a trial without a record reds the runner, a failed trial does not. Report: panelVerdict() decides every panel of the first run attempt (later attempts are reported, never replacing it); rule shards keep the unchanged fail-closed checks; collector records all count (no last-attempt wins); census runs enforce the quarantine cap and expiry. It writes collector-outcomes v2, trial-outcomes.jsonl (trials plus JUnit rule/judge cases), report-summary.md, and one headline + failure block with rerun commands, and flags INFRA/INCOMPLETE-only reds for the one re-dispatch. The fail-open suite gains the panel cases: behavior 1/3 red, 2/3 green with its failed trial shown, missing trial INCOMPLETE, contract at 2/3 red, quarantined 1/3 green, 0/3 and contract red, missing slice red, and a later attempt never replacing the first. * chore(evals): refresh paid duration seeds from proof runs 36597762183 and 36606688266 Both tiers, merged in run order (the later run wins). Notable: split-overflow 1332s -> 504s, section-loading 604s -> 342s, mode-routing 575s -> 444s; multi-finding-batching 734s -> 1318s (its red path in run 36606688266). * feat(evals): stamp trial series identities and fit panels to the live registry - scripts/eval-trial-series.ts stamps series_identity (eval-flake-rank's caseSeriesIdentities) on a report's trial-outcomes JSONL as its own step, keeping the history tool out of the paid runner's closure; TrialOutcomeRecord gains the optional series_identity field. - Slice-count plans let a registered trial spill into an ordinary lane when its siblings hold every long lane, so panels never share a runner. - Re-audited test-selection.ts (Stream B added the E2E_KINDS/BEHAVIOR_WHY map-diff; no new module loading) and repinned its hash. - Detach and release floors now count trial shards (66 periodic trials in 22 panels): periodic floor 33,821s, still under eval:bg:periodic's 67,380s. - Coordination fixtures supply the executor's trial records. * ci(evals): attempt-scoped artifacts, verdict-v2 PR comment, weekly pass-rate gate and one INFRA re-dispatch - Slice, census and marathon artifacts carry -a<run_attempt>; reports download them per artifact (no merge), so records never overwrite and a re-run never replaces the first attempt's verdict. - Planners pass --max-parallel for the capacity preflight (24/16 unchanged: the refreshed periodic plan needs 24 slices, the gate census 12). - PR comment: jq-only job reads collector-outcomes v2 (headline, sanitized failure block); the group_by(.name)|last recomputation is gone. - Reports stamp series identities, upload trial-outcomes-* for history, and shard logs upload always (a failed trial no longer reds its runner). - Weekly report: headline + failure block of both lanes in the issue body, the eval:pass-rates --gate step (fails closed without history), close the issue on a green run, and UC-E1: when every red is machine-classified INFRA/INCOMPLETE, one re-dispatch as a new run in its own concurrency group (redispatch_of), both runs reported. * feat(evals): planner-side whole-panel reuse and negative receipts The planner job restores this PR's receipt store once and ships a single filtered set with the plan: a pass or panel receipt with a same-or-newer FAIL for its input identity is dropped, and a panel receipt ships only as a whole PASS panel (re-verified with panelVerdict) from one run. Executors read only that set (no per-slice cache restore or save), so every trial of a panel sees the same receipts; a trial reuses its own record from the panel receipt, keeping a split PASS's failed trial. Trial identities drop the trial index (run-scoped) and bind the panel policy. Executed shards carry their input identity; the report turns a whole fresh PASS panel into a panel receipt and a FAIL panel or failed rule shard into a negative receipt, and marks a panel that mixes reused and fresh trials INCOMPLETE. The report job merges plan, slice and report receipts (newest per file) and saves one store per run. Also fixes two TS2352 casts in browse/test/dia-macos-qualification.test.ts whose diagnostic text drifted with program order (baseline locked, fix only). * feat(evals): --case/--trials local diagnosis and panels in local sharded runs bun run scripts/test-paid-shards.ts --case <id> [--trials N] runs N independent trials of one case through the CI panel runner (trial shards, TRIAL_ENV identity, name-pattern isolation) and prints its panelVerdict(); N defaults to the case's policy panel and CI never reads it. The local sharded path (test:gate:sharded, test:periodic:sharded) now plans the same trial shards and exclusions as CI and exits on execution completeness plus panel verdicts. * test(pty): grant an owned Create pane whose title row is cropped The targeted batching rerun on Claude Code 2.1.284 left its first report Write unanswered for 1,372 s and timed out: the viewport began at the pane's relative file row and rule, with the 'Create file' title cropped above, so the preview parser rejected the file row as foreign. That row must now resolve to the owned path and is skipped before the unchanged line-by-line preview match. Replay controls reject another file, another directory and an edited preview row. * fix(evals): tsx-safe generics in eval-flake-rank, legacy artifact names, no-retry wall docs * test(evals): record the read-only and detector-row invariants as contracts shared-libs-opportunity-judgment and review-design-lite are behavior cases: their recommendation and checklist judgments may vary, but the read-only invariant (commands, provider requests, fixture bytes, hooks, state) and the deterministic fake-engine detector rows are contracts. Both now go through expectContract, so any failure vetoes the panel. * test(judges): sample the recommendation rubric as a panel; never re-ask armJudge llm-judge-recommendation is a judge case: each fixture now draws a 3-sample judgePanel, gates reason_substance on the panel mean and the present/commits/has_because checks on a 2-of-3 majority, thresholds unchanged. armJudge no longer re-asks on a malformed verdict; it is a failed sample, as the judge policy requires. * test(evals): record a pre-turn API or CLI failure as infra recordE2E sets failure_class 'infra' on a failed session whose runner reports error_api, timeout_startup, error_output_stream or a non-zero CLI exit with zero turns and no assistant event. A model refusal, a timeout after model work, max turns, or an explicit caller pass/class keeps its ordinary classification. * test: pin every-record outcome counts and the twelve doc-sync callbacks * test(eng-batching): read the report target as a field, not a spelling The next targeted rerun (Claude Code 2.1.284) again asked eleven separate native questions and again counted zero: its briefs named no plan and its report declared '- **Review target (fixed):** `/abs/PLAN.md`' under '# Eng Review — PLAN.md: <plan>'. An unsourced brief now inherits the one current target field that names a PLAN.md file, whatever its list or emphasis markup; its ledger record still supplies the cited finding and must reproduce the brief exactly. A brief that names its plan must still match the report title. Replays of all three captures count 9, 9 and 3; controls reject a foreign, duplicate or missing target and an archived title. * fix(evals): --case list mode and name precheck; case-shard qa-callers; refresh batching and design-with-ui seeds * chore(release): v1.91.9.0 * test: settle the post-response composer before seeding; give the TPA recorder adapter its infra helper submitPlanSeed accepted a stale empty composer when the transcript recorded end_turn before the CLI repainted (late-repaint-typed-current fails 5/5 on the old helper, passes 5/5 now). The TPA recording fixture extracted recordE2E without isPreTurnInfraFailure, so every failed case threw before recording. * test(autoplan-dual-voice): unwrap Claude Code 2.1.284 subagent hand-back frames; accept read-only probe diagnostics; record before asserting Census run 36626737820: the native CEO report arrived framed and indented, so its INPUT line never matched, and the model's exact probe plus two variable echoes was not canonical. A column-zero line inside a frame, command substitution, backticks, redirects, assignments, CODEX_MODE echoes and output line-count mismatches stay rejected. The failure now records before asserting. * ci(image): keep Claude Code 2.1.251; test(ceo-mode-routing): keep HOLD's own deferrals in scope before assessing its rigor decision 2.1.284 enables per-turn effort for claude-fable-5-1: in gate census 36626737820, 66 of 84 sessions ran longer than on 2.1.251 (+20% session time, +32% thinking tokens) and 11 cases timed out on unchanged budgets. HOLD SCOPE's 0G step asks its own defer/keep menu; the actor answered it Defer and the assessment then judged that scope question as the rigor decision. The actor now answers that menu Keep and assesses the next one. * test: attribute quoted prior-record field lists, state the judge reason bound in its schema, move split-overflow to marathon Census 36629958451 reds: - outside-plan-disabled-no-fallback: the model quoted the pre-existing record as a parenthesized field list with its exact timestamp; attribution now requires that exact timestamp and the record's own field values. - plan-devex-peer-comparison-classification: the judge correctly returned missing but wrote a 1069-character reason, voiding the judgment; structured outputs cannot enforce maxLength, so the bound is stated on the field. - plan-ceo-split-overflow ran 504-1188 s as one PTY flow and set the periodic lane's wall clock; it now runs weekly in the marathon lane. * test: supply holdDeferKeepIndex to the CEO routing mocks and follow split-overflow into the marathon lane The registered-callback fixtures mock ceo-mode-option and lacked the new export; the split fixtures asserted the periodic tier; the registered-budget check looked for split-overflow only in the periodic manifest. * fix(qa): checkpoint receipts print the report link for their exploration file qa-functional-webhook-report failed in two of three censuses because the report linked .qa-evidence/NNN capture folders as "checkpoints" and never linked exploration-NNN.json. The checkpoint receipt now prints link: [checkpoint NNN](exploration-NNN.json), and the functional report template says capture folders are not checkpoints. * docs: final census numbers in the v1.91.9.0 entry; file the paid-eval follow-ups * ci(evals): name the PR-comment loop's unused fields so shellcheck passes (SC2034) * fix(plan-ceo-review): tighten expansion pacing wording to fit the skeleton cap after the main merge The merged skeleton measured 80,166 bytes against its unchanged 80,150 cap. Same instructions: ask separately for each addition, in turn, with no pacing menu; lead each proposal with the felt experience, then shape, effort and impact. * fix(eval-pass-rates): match trial-outcome files by basename so Windows backslash paths are read * fix(evals): repair proof-run reds in design-consultation, document-release, design and QA fixtures - design-consultation Phase 1 asks one brief that confirms context and decides research; the confirm-only first question scored substance 2. - document-release defines ship-owned inputs, exact steps and the JSON result, and drops stale spawned-from-/ship text (judge actionability 3.67 -> 4/4/4). - plan-design-with-ui accepts the Step 0D focus menu the same way the shared picker does ("focus on specific ones?"). - plan-design-review plan-mode saves in three Edits instead of one final Write. - QA functional annotations ask for the full 40-character revision. - Outside-disabled attribution judges quoted prior-record data by its exact timestamp or a dated, pre-existing-record sentence; four captured phrasings replay clean and current claims still fail. - --case can select autoplan-dual-voice by its literal test name. * test(design): revert the three-Edit plan-mode flow A focused paid run still timed out at 300 s: the first three passes alone took 150 s of thinking. The case stays a named timeout red rather than cutting review depth. * test: accept 'review mode = X' auto-decide declarations and parenthetical scope exclusions in the shared-libs actor auto-decide-preserved: the product auto-decided HOLD SCOPE and said "Decision: review mode = HOLD SCOPE"; the grammar knew only "is" and ":". shared-libs-plan-callers: the recommended option said "(no hardening)" and the actor read "hardening" as an expansion. Both replay the captured text, keep negative controls, and passed focused paid runs. * fix(review): pass Review Army checklists by path, run research alongside dispatch, always probe the design detector; state review-log invocation and statuses in the caller fixture - review-army-perf-n-plus-one: the parent copied full checklists into agent prompts and ran web research before dispatch (290 s on a 12-line diff); 212 s now. - review-design-lite: 5 of 6 captured trials reported the detector absent without probing; the probe is mandatory and its first line is reported, and the contract credits only fake-engine rule ids the checklist never names. - review-exploratory-small-cli: the fixture never gave review-log's direct invocation or status vocabulary; the model ran it through bun and wrote status "blocked". The prompt states both and the validator rejects out-of-vocabulary review statuses. Each case passed a focused paid run after repair. * docs(changelog): proof-run product fixes * fix(ship): always run the design-lite detector probe; test(shared-libs): credit a failed first file view and deferred-reuse Skip wording - /ship design-lite: the probe is mandatory and any non-ready first line is stated, matching /review (5 of 6 captured /review trials had skipped it). - shared-libs-pr-coverage: the first PR 42 page-1 read printed only a jq error, so the one refetch is a legitimate recovery, charged to the same budget. - shared-libs-review-prior-coverage: the Skip option said a future review can "reuse it once snapshot coverage holds"; a conditional tail on the recorded decision is not product work. Captured-text regressions and negative controls. * fix(ship,qa,document-release): repair proof-run regressions and fixture gaps - ship-docsync-completion: yesterday's audit-scope result dropped the section's status, so /ship spliced one in; the section now opens with **Status:**. - ship-docsync-missing-asset: a missing section or old Ship-owned mode blocks before launch. - ship-docsync-late-result: the invocation record says prepare already saves the candidate selection (no extra Read; budget unchanged). - qa exploratory: await the method Reads before the first probe. - qa-callers fixture: quote the real review-log record template; allow the git log command plan-completion prescribes. - qa functional observer: a receipt caught mid-link(2) is checked at stop instead of failing with ENOENT (reproduced from CI). Each repaired case passed a focused paid run. * ci(image): pin Claude Code 2.1.284, the version users run Request-body capture shows both 2.1.251 and 2.1.284 send effort "high" to claude-fable-5-1; 2.1.284 adds the model's own profile. The slower 2.1.284 census was mostly API latency: its SDK-only judges were 25% slower too. Nine previously slow cases pass on 2.1.284 within unchanged budgets. * test: one owner per case id, a structural devex 0B setup rule, and correct design/gbrain actors - plan-design-review-plan-mode was registered by two files; the PTY smoke is now plan-design-review-plan-mode-smoke, and a registry test requires one owner per case in case-sharded files. - plan-devex-finding-floor: the template's 0B narrative-confirmation question is classified as setup structurally instead of timing out a Haiku assessor. - setup-gbrain-remote: the actor accepted 'skip' on the MCP-registration question the test asserts; it now accepts that question and declines others. - design-review-plugin-handoff: the fake engine cited a file absent from the fixture repo and index.html linked a missing styles.css. Captured-question regressions with negative controls; each case passed a focused paid run. * test: PTY harness handles clipped reviews and bundled setup tabs; AUQ judge uses structured output; design-consultation carve declines optional outside voices - ceo mode routing: a Submit review taller than the viewport, a setup tab bundled after the mode tab, and a clip through the mode question each hung or misread the run; the native answer is still verified after Submit. - judgeRecommendation requests a 1-5 enum schema; a malformed Haiku reply had scored substance 0 for a 4/5 brief. Judge failures now propagate. - carve section-loading for design-consultation declines the optional outside voices (a supported path) and treats DESIGN.md as the report; timeout unchanged. The Step 0E handoff defect is not fixed (0/15 samples across four wordings, none shipped) and is filed in TODOS. * test: fold the design-consultation completion replay into carve-section-sharding (test-of-test ratchet) * docs(todos): record the pre-push hook shard-order hang * test(qa-callers): disable git auto maintenance in the fixture repo (same guard as shared-libs; from #3002) * test(office-hours-attempt): the fake judge SDK response carries stop_reason like the real API (structured judge requires end_turn) * fix(qa): the caller STOP line says to await the method Reads before any probe ship-exploratory-plan-checks: the model read exploratory.md and sent a capture in the same response, before seeing the section's own await rule. * fix(qa): number the qa value-bar questions from 1 and say reproduced bugs already answer the first two * fix(qa): define evidence.json where it is built, point the preparation gate at the next section, name measured command durations in the report template Recurring qa/qa-only workflow-judge complaints in CI (clarity/actionability 3.33). * fix(plan-eng-review,review): a disallowed question tool is not headless; report kept tests only when some were skipped * fix(plan-eng-review): keep the headless-rule contract phrases adjacent * fix(evals): cut path variance at its measured sources - gstack-qa-evidence capture prints startedAt/completedAt/durationMs and, for --deadline captures, remainingMs; the functional report takes durations from them. The section clock notice asks for one clock read up front instead of one after every checkpoint (QA runs spent 7-14% of tool calls on date -u). - ship plan-completion: skip the audit dispatch when discovery already found no plan (the dispatch-vs-skip conflict produced an optional 60-100 s subagent). - materialize/checkpoint validation errors state the expected schema, so a rejected annotations file is fixable in one call instead of blocking the phase. - session-runner counts turns from the transcript when a run times out, so timeouts stop reporting 'turn 0'. * fix(evals): count timeout turns only from object transcript events * test(qa-callers): deterministic child transport, completion-time handoff reads, compact phase report The exploratory caller cases exist to prove the caller starts and bounds exploratory QA. Their native adversarial reviewer (review) and plan audit (ship plan-checks) now come from recorded child outputs instead of a live subagent, handoff freshness reads are required before completion records rather than every bookkeeping log, and the phase report is compact. Measured: 194-257 s per case against 208-284 s before, no subagent calls. * test(ship-docsync): seed fault cases at their gate instead of replaying attempt 1 The post-dispatch fault cases (missing-marker, launch-failure, timeout-unsettled, late-result, stale-before, stale-after, recovery) now start from a fixture-owned attempt 1: the real actor prepares and dispatches it, its verbatim output is saved once, and the invocation journal carries its pre-dispatch entry with the child asset hashes. The model resumes at Parent processing with a trimmed read list, inspect named as the authoritative repository observation, and recovery's intermediate checkpoint folded into the next attempt's pre-dispatch entry. Assertions count only parent-issued transport events and require a read of the saved attempt-1 output; missing-asset and the legacy failure case keep the full model-driven first attempt, and their prompts are byte-identical. * test(ship-docsync): name the seeded read list and cap journal/report length The first seeded stale-before run spent calls locating documentation.md (two ls sweeps), reading through cat and re-Reading the record before Edit, and ~40 s composing 1.5-2.2 KB entries and report. Name every seeded read path, ask for native Read, and bound entry/report length. * test(ship-docsync): trim the seeded parent's measured model time Measured on the seeded runs: one read the 78 KB ship/SKILL.md, the post-child freshness comparison spent 18-32 s of thinking over full inspect contents, and the final response restated the report (~1.1 KB). Say the phase excerpt stands in for ship/SKILL.md, compare hashes first and read content only for changed paths, and end with one status line. * feat(qa-evidence): enforce the checkpoint sequence and fill report bookkeeping in code - capture refuses to run another probe until a checkpoint anchored on the latest complete capture names this capture as its next command, and every complete capture prints that requirement. - materialize fills revision, runtime, cwd and learning (checkpoints whose next native command differs) when omitted and prints the reportLinks the report must include; the QA section shrinks accordingly. * test(qa-callers): hand the caller phase its invocation-start observations and review token; fix(next-version): fetch without auto maintenance - Every caller case receives the diff, status, log, untracked list, HEAD and an already-captured review start token, so the phase spends its budget on the contract under test instead of re-running setup reads. - gstack-next-version's fetches pass --no-auto-maintenance. On git 2.55 a completed fetch forks detached maintenance in the caller's repository; the free suite's live smoke test ran it inside the CI checkout, and every shard-12 pre-push hook hang so far followed a completed smoke fetch. * feat(deslop-shared-libs): route every Git read through bin/gstack-safe-git The skill made the model retype a long safe-Git prefix on each call and a dropped flag failed shared-libs-read-only. bin/gstack-safe-git applies the fixed env + flag prefix, adds --no-ext-diff --no-textconv to log/show/diff, allows diff only between two explicit object IDs and ls-files only in the NUL-delimited overlay form, and refuses every other shape with one line naming the allowed forms. The template now points at the installed helper (host global runtime via {{SAFE_GIT}}) and drops the prose it enforces. Fixtures resolve the helper to this checkout, the git shim records the safety environment, and isGuardedGitRequest requires the complete prefix (env included) for every repository read. * test(shared-libs): tee to a discard device is not a file write Paid shared-libs-opportunity-judgment t1 on 1213b01 failed read-only on '... | tee /dev/null | sha256sum'. The detector flagged any tee operand while the same devices are allowed for redirection. tee now fails only when an operand is a real file; tee to a file, -a file and -- -a stay violations. * fix(qa-evidence,observer): reject placeholder metadata and replay-only learning; declare the docs atomic-write target - materialize measures revision, runtime and cwd itself and rejects supplied values that differ (CI run wrote revision "HEAD" and runtime "bun"), and refuses learning checkpoints that replay the same probe, naming the fix. - The docs write observer treats Claude Code's atomic temp for the authorized doc target as transient, so a temp renamed before its per-file watch no longer marks the observation incomplete (ship-docsync-completion flake). Per-file monitoring outside declared targets stays fail-closed. * test(qa-functional): fix mode requires only the happy scenario from the model (carried byte-identical from #3002 183b01f4..3e6074b4) verifyQANativeRegression already reruns all eight webhook scenarios on the repaired source, so the model-side eight-scenario requirement in fix mode duplicated harness coverage and pushed qa-functional-webhook-fix past its budget. qa-only still requires every scenario. * fix(deslop-shared-libs): probe the audited repository with -C <repo> A CI run probed safe-git from the session directory above the target repo, so the capability probe never touched the repository and the run fell back to the API without a local attempt. The probe (and any call from elsewhere) now names the audited repository. * test(qa-deadline): never attach a reader to the full-pipe fixture's stdout The full-pipe receipt test attached a 'data' listener (flowing mode) and then paused; on CI the reader could drain the 2 MB write before the pause, so the receipt write never blocked and the helper exited 0 in ~126 ms. The stdout pipe now stays unread until the assertion, which is what the test means to model. * feat(qa): helpers answer --help, and the QA eval interfaces declare it Approved by Garry: asking gstack-qa-evidence or gstack-qa-deadline for usage is read-only, so both helpers print usage and exit 0 on --help (the evidence usage now names the annotation shape), and the functional and caller command allowlists accept exactly 'bun <path>/bin/gstack-qa-{evidence,deadline} --help'. Two CI runs failed only on that call. * fix(qa): after an input change, a probe is affected unless shown otherwise CI late-input run finished in time but revalidated only the happy probe after the locale input changed and reported the stale adverse probe green. The revalidation step now treats any probe not shown to be unaffected as affected. * test(shared-libs): seed the lifecycle replay's first Step 3 pass instead of replaying it shared-libs-review-lifecycle ran ~88% of its 300 s session budget (12-run census median 265 s, 4/24 sessions timed out). The fixture now executes pass 1's Step 3 once with the real logger and Git: a real unused REVIEW_START, then the diff, inventories, attributes/config/index flags, gstack-review-read output and every file's bytes and sha256, saved to one observation. The model resumes at Step 4 with an exact four-file first read, the observation named as the authoritative pass-1 repository read, one post-fix verification, an explicit pass-2 read list and a twelve-line summary. Pass 2 still runs its own --start, diff, reads, fingerprint and stage actor before --finish. The actor scope now states that a current settled final-pass actor result supplies the replaced QA/adversarial prerequisites and that the no-credit disclosure is a reporting label: one r1 session persisted completed:false from that ambiguity. New assertions: the final binding never uses the seeded token's start or tree, and the observation was read; free controls finish the seeded token (binding changed) and omit the observation read, and both fail. * test(shared-libs): trim the resumed review replays' setup and report Every sibling review session (revalidation, path-eligibility, index-flags, prior-coverage) loaded qa/sections/exploratory.md and often scope.md although its QA and native adversarial results are supplied synthetic inputs, then spent a second request on shared-code-reuse.md and base metadata. The resumed scope now states that the supplied results replace Step 4's QA method loading; the revalidation contract names one first response (workflow, checklist, finding, prerequisites, shared-code-reuse.md, base metadata) and caps the summary at twelve lines. Receipt order, direct source reads, the checker, the question and final persistence are unchanged. * fix(review): define what a Step 5c Skip option says Step 5c named "B) Skip" without saying what its description may claim. Two CI captures (path-eligibility on 131d43be, index-flags on 4643cb85) offered a Skip whose description added effects beyond declining: "The extraction can be applied in a later editing review pass" and "replacing the invalidated prior Skip". Those read as change commitments, so the no-change actor refused both. Step 5c now says to describe Skip only as no code/index change with the Skip recorded; adjacent lines are compacted so the review parity caps hold unchanged. Both exact packets are kept as a free regression: still refused, and accepted once Skip follows the rule. The actor's classifier is unchanged. * fix(qa-evidence): every complete capture needs an evidence row; test(tpa): accept the hyphenated app-specific-password spelling - materialize refuses when a complete capture has no evidence row and is not named in limits (CI cli-report omitted capture 004), naming the missing IDs. - tpa-apple-ban's detector required 'app-specific password' with a space; the CI answer said 'app-specific-password path' and was otherwise correct. * test(qa-observer): fix mode treats atomic temps of authorized src/test writes as transient CI webhook-fix failed with 'Could not watch test/worker.regression-1.test.ts.tmp...': Claude Code's Write renamed its temp before the per-file watch was added. The functional eval now tells the observer its mode, and a temp whose target that mode may write is observed through its directory watch. Report-only mode and undeclared paths keep failing closed. * feat(qa-evidence): refuse evidence observed on an older input snapshot than the latest capture When native probe output declares a top-level input snapshot, materialize compares each evidence row with the latest capture's snapshot and refuses stale rows unless they are classified superseded, naming the captures to rerun. ship-exploratory-late-input kept reporting a pre-change adverse probe green after the input changed. * test(qa-functional): point the fixture at the helper's --help instead of its source A CI webhook-fix run spent three turns reading lib/qa-evidence.ts to learn the interface and timed out just before materialize (agreed with #3002's owner). * feat(qa-evidence): captures list the caller's declared-but-unrun required probes GSTACK_QA_REQUIRED_PROBES (a JSON array of native child commands) makes every capture print requiredRemaining; it never judges pass or fail. The functional eval passes the webhook list from QA_WEBHOOK_REQUIRED_SCENARIOS, which the verdict now reads too, so the nudge and the verdict share one source (agreed with #3002's owner). CI webhook-report kept stopping with scenarios unrun. * test(review-army): record N+1's pre-dispatch stages and scope the session to Step 4.5 review-army-perf-n-plus-one timed out in 7 of 13 CI runs on this branch (passing 245-280 s of 300). Each session spent ~95 s on setup (the full extracted SKILL, checklist, section greps, exploratory.md, diff-scope/stats/learnings, tooling checks), ran Step 4's core pass, a search-before-recommending WebSearch, and wrote a 10-16 KB report (~100 s after the Red Team returned). The fixture now stages only review/sections/review-army.md plus the performance and red-team checklists, and hands the session the recorded detect-scope, specialist-stats and learnings outputs and the diff. The caller passes --performance (every CI parent already treated the prompt as that force flag against the <50-line skip), declares the core pass, QA, adversarial review, web research, Fix-First and persistence out of scope, and caps the report at the selection line, the SPECIALIST REVIEW block and the Red Team result (30 lines). The Performance specialist and the conditional Red Team are still real foreground subagents, and the report still has to surface the N+1. New assertion: a foreground Performance specialist dispatch precedes the Red Team dispatch. Free controls omit the Performance dispatch or background it, and both fail; the budget lifecycle adapter supplies the current result shape. Touchfiles now include the .rb fixture the case reads. * test(review-army): share the recorded Step 4.5 staging with consensus and supply its Red Team review-army-consensus (periodic) timed out in 2 of 13 census sessions; passing runs took 213-297 s of 300. Like N+1 it spent ~30-50 s reading the whole extracted SKILL, checklist and every specialist file, sometimes dispatched an unrequested Maintainability specialist, then ran a Red Team (60-70 s) and a second merge before writing a 9-15 KB report. The N+1 staging and scope text move into stageReviewArmySession / reviewArmyScope / reviewArmyChecklists (the N+1 prompt renders byte-identical). Consensus now records its detect-scope, stats, learnings and diff, stages the Review Army section with the security and testing checklists, forces --security --testing, and caps the report like N+1. Its Red Team is outside the multi-specialist contract, so the fixture supplies a labeled synthetic NO FINDINGS result instead of a dispatch. The existing SQL-finding and browser-error assertions are unchanged; the lifecycle adapter's spawnSync now returns the git output the staging reads. * docs(changelog): v1.91.10.0 records the flake census and its repairs * test(strict-output): give the spool-prefix child time to finish before the pending stream times out windows-free-tests failed on 9a7a7e54: the 150 ms shared deadline raced Bun startup on Windows, so the child was killed mid-write and the spool held a partial payload. Only the never-released extra stream should time out; the child now has 3 s. * fix(qa-evidence): accept a single limits string; test(qa-callers): read the handoff first when a probe snapshot changes CI late-input spent a turn rewriting limits as an array after materialize refused a string, and a ten-read sweep hunting for the changed input before it read reports/HANDOFF.md, then timed out at 300 s. * test(autoplan-dual-voice): unwrap the framed native report before Claude Code 2.1.284's agentId/usage trailer * test(section-loading): credit a Bash print that contains every line of the carved section * test(auto-decide): ask for the selected mode in the skill's mode handoff line, not a separate public decision * test(plan-ceo floor): scope preservation approves no premise, approach or remedy * test(autoplan-dual-voice): the fixture declares that delivered bash blocks run alone, diagnostics separately * test(coverage-audit): a fenced plain-word caption in a successful && read chain is display only Census 36776104571 plan-eng capture read both owned files with cat -n in one successful && chain; the caption 'echo "=== git diff main --stat ==="' fell outside the two-token caption grammar, so both reads lost credit. Accept a fenced caption of plain words; unfenced command strings, expansions, redirection, -e escapes and ; / || tails stay rejected. * test(office-hours): a fork whose outer options are the seeded shapes is the Phase 4 question Census trials 1-2 captured complete Phase 4 forks (A) Server-side B) Client-side C) Hybrid, recommendation with because) whose prose used none of the vocabulary words. Accept two seeded shapes as outer options as Phase 4 specificity; the earlier-phase, nested, fenced and single-shape controls still fail. * fix(review): design-lite rows keep the detector's [rule-id]; the e2e detector rows point at the diff The output template had no rule-id slot, so rows merged with checklist items dropped the detector id (census t2, local t1). Rows now carry [rule-id]. The fake engine's sample rows named a foreign fixture path at line 0; the e2e remaps them to landing.html/styles.css so trials stop spending turns reconciling it. * test(shared-libs): the plan actor reads scheduler parity and unchanged-scope lists Census 36776104571's question preserved the contract ('behaving exactly like the scheduler', 'scheduler parity holds by construction') and excluded work with 'Existing copies and helper hardening stay unchanged'. Accept exactly/parity as preservation (negated forms refuse) and a bare noun list that stays unchanged as an exclusion for the expansion scan only; verb-led clauses still refuse. * fix(qa-only,qa): name the exploratory read point and finalization order; judge qa with its browser assets qa-only judges cited 'next section' pointing at the wrong heading, an exploratory trigger that contradicted its read point, clock ownership in mixed runs and the unstated order of exploratory section 4 vs reporting. The qa judge penalized the absent qa-report-template and issue-taxonomy that qa-patterns loads; with them in, it found issue-taxonomy's dangling 'rule 13' (the consent rule is browser rule 3). * test(ship-docsync): seeded attempt 1 counts toward the limit; transport counts ignore calls that never reached the state file - CI launch-failure retried after the seeded attempt 1 as if that attempt were the fixture's; the seeded prompt now says attempt 1 is this invocation's and a further attempt needs what Blocked recovery requires. - A late-result run typo'd the state path once (ENOENT, the actor never ran), then repeated the call correctly; the per-action count compared both calls with one actor event. Only calls naming the real state file are counted. * fix(plan-eng-review): show the accepted dedicated read form for coverage-diagram sources CI plan-eng-coverage-audit mixed package/config and git diff into the source read; the review variant, whose prompt shows the && display form, does not. The plan trace step now shows it too, within the unchanged size cap. * test(sync-gbrain-readiness): a negation earlier in the claim clause is not a search/write readiness claim The census unknown actor wrote 'nothing about read, search, or write capability is confirmed either way' after a YELLOW/WARN verdict. The claim window started at 'write', so the leading 'nothing' was outside it. Check the clause subject for nothing/neither/none/no; keep the original in-claim negations. Replay of the captured output passes; positive controls still flag an unnegated claim. * fix(office-hours): a forcing question's recommendation takes the position the founder's words support auq-matrix office-hours asked D1 Demand as options about the founder's own evidence and, with no rule for that shape, recommended 'answer whichever is TRUE — A is marked recommended only because it is the strongest position' (substance 2). Say what such a recommendation is: the option the founder's own words support, why it matters for the next step, and what would change it. * fix(plan-ceo-review): name the mode preference command and the exact handoff line auto-decide-preserved at 6fcb0981: the model never ran the preference check, read 'check ... through the preamble' as already done, auto-selected 'per your preference setting', and wrote 'Selected mode: HOLD SCOPE, auto-decided from your tuned preference' instead of the AUTO_DECIDE handoff line. At 9a7a7e54 it ran the check but wrote 'Decision: HOLD SCOPE is the review mode for ...'. Neither matched the handoff template the observer recognizes. Name gstack-question-preference --check at the point of use and say the handoff begins with the exact matching line. Collapse the audit block's comment padding to stay within the unchanged 80150-byte skeleton cap. * test(section-loading): record the CEO capture's report and transcript The 6fcb0981 census failed hasStaleFillRaceFinding (line 98), but the case records nothing beyond junit, so the report the detector judged is gone. Return the SkillTestResult from captureSectionReads and record it, with the full saved report, through the eval collector on pass and fail. * test(design): plan-mode names its read list and caps its additions and summary At 6fcb0981 plan-design-review-plan-mode timed out at 300 s (9 turns): 22 cat/sed chunk reads (~50 s), then a 28 KB plan Write (~150 s), before the read-back finished. The 9a7a7e54 pass took 240 s with a 24.6 KB Write. Read SKILL.md, review-sections.md and plan.md natively in one response, keep additions under 14,000 characters and the summary within ten lines. Budgets unchanged. * test(plan-mode-no-op): require prose evidence before a waiting verdict ends eng/design runs (carried byte-identical from #3002) With the prose fallback forced, the gate renders as a lettered menu; a judge 'waiting' verdict on a spinner-only frame ended the run as 'asked' before the menu rendered, so the scope-gate check failed on unchanged behavior. * feat(qa-evidence): materialize computes the phase verdict; callers must report it Approved by Garry: the helper, not the model, decides whether evidence can pass. materialize writes verdict {status, open} into evidence.json and prints it: fail or blocked from row classifications, inconclusive while any row is superseded, a complete capture is withheld, a declared required probe is unrun or there is no evidence, else pass. The caller fixture requires receipt.status to equal that verdict. CI late-input kept reporting pass with a superseded happy probe. * test(qa-callers): compare the receipt with the helper verdict only when evidence.json was materialized The producer free tests run captures without materialize; evidence.json is optional for callers, so its absence is not a verdict mismatch. * test(llm-judge): run the ship workflow judge at medium effort so its panel fits JUDGE_MS claude-fable-5-1 accepts only adaptive thinking (thinking.type.enabled with budget_tokens returns 400), so effort is the available thinking control. Measured on the exact ship judge request (105,301 input tokens): - default effort, 18 samples: thinking 5,086-10,881 tokens, 75.9-144.7 s; 3 of 18 passed the 120 s deadline (about 42% of 3-sample panels). - medium effort, 18 samples: thinking 2,749-5,762, output at most 6,144 tokens, 43.1-77.9 s; scores 4/4/4 in 16 of 18 (clarity 3 in two), versus 14 of 18 at default. callJudge gains an effort option sent as output_config.effort; only the ship judge sets it. Rubric, floors, panel size, deadline, model and max_tokens are unchanged. The cache identity records effort. * test(llm-judge): ask frontier workflow judges for 120-word reasoning under the unchanged 150-word check Told "under 150 words", the ship judge's reasoning landed at 130-156 words (3 of 18 probe samples at 152-156), so the structured-response check failed about one panel in three independent of effort. The prompt's frontier block and the response schema description now say under 120 words; the validator still rejects 150 words or more. The changed prompt bytes reach only the two frontier judges: ship/SKILL.md workflow (prompt and schema) and review/SKILL.md workflow (prompt). * test(llm-judge): type the stream transport mock call * test(plan-ceo floor): the request answers only the questions it names PR lane 36794871032 (head 20d6e98f): the CEO floor ran 608 s without a question. Its Step 0 recorded the premise gap and approach choice as unresolved ledger rows, then said "this session supplies all answers up front, so no decision brief was dispatched" and wrote Sections 1-11. 2734e203 stopped scope preservation from approving the premise; this time the actor block (declined setup, recall, outside voices, HOLD SCOPE) and the fixture's "complete user request is available from the start" were read as pre-answering every review question. The CEO actor now states that the request answers only the routing, recall, outside-reviewer and review-mode questions it names. * test(plan-devex floor): a 'Partly wrong' 0B answer is the narrative confirmation PR lane 36794871032: the DX floor asked its D1 narrative confirmation (Accurate, proceed / Partly wrong, correct it / Way off, actual is...). The deterministic setup rule accepted only 'Some ... wrong', so the question went to the LLM assessor, which hit its 30 s spawnSync cap (ETIMEDOUT) and ended the case as assessment_error at 141 s, the same failure as census 36641820398. The rule now accepts 'partly' beside 'some'; the captured question is a free regression and the remedy-option controls still go to the assessor. * test(design-review plugin handoff): quoted report text is not an install command PR lane 36794871032: every behavioral check passed except noInstallOrOverride, which matched "no `npx impeccable`" inside the quoted heredoc that wrote detector-output.md. Nothing was installed or downloaded. The check now drops quoted-delimiter heredoc bodies (literal data) before matching; unquoted bodies, which can expand $(...), and unterminated bodies stay checked. Free controls cover the captured write, bare npx, an IMPECCABLE_BIN override, an unquoted $(npx ...), npx after the delimiter and an unterminated body. * test(review-army delivery audit): stage only the plan-completion section and record its git reads PR lane 36794871032: the case timed out at its 120 s budget after 7 turns (previous lane passed in 45 s). The session read the 46 KB extracted SKILL in three passes (cat to persisted output, grep, sed), ran its own git reads, wrote a 74-line report, then inspected and ran gstack-learnings-log and rewrote the report's Learnings section. As in the Step 4.5 cases (17ee2e54/2bd4651c), the fixture now stages only review/sections/plan-completion.md, hands the session the recorded git log and diff, declares the HIGH-impact question, its Scope Check, learnings logging and later steps outside the capture, and caps the report at the audit block and its DISCREPANCY entries (30 lines). The NOT DONE and email assertions are unchanged. * feat(qa-evidence): one capture call records the causal note for the previous capture capture R NNN [--public] (--deadline D|--timeout-ms MS) --after PREV --hypothesis 'TEXT' -- CMD publishes exploration-NNN.json {observationCapture, observationArgv, observed, hypothesis, nextCapture, nextArgv} before running CMD, refusing unless PREV is the latest complete capture. The receipt carries checkpoint/checkpointSha256; validators bind the note to the transcript's capture calls by capture ID and receipt hash instead of exact command strings. The separate checkpoint command and the capture guard keep working; materialize learning accepts both note shapes and still rejects same-probe replays. Prose and eval fixture prompts teach the merged form. * fix(qa-evidence): a superseded row stops holding the verdict open once its probe is rerun on current inputs materialize requires an old-snapshot row to be classified superseded, and its verdict kept every superseded row open, so rerunning the probe (what its own error tells the model to do) could never reach pass; late-input reran 3 and 9 on the new snapshot and still got inconclusive. A superseded row now closes only when a non-superseded row with the same captured argv observed the current snapshot. Re-materializing an already-published evidence.json names the cause instead of failing generically. * test(plan-eng batching): count saved decisions whose label drops the (recommended) marker or whose report is titled 'Eng Review Report — <plan>' * fix(qa): browser-only runs skip annotations/materialize; only Q captures can anchor evidence rows * test(design): plan-mode length is a drafting target, not a check to measure and trim * test(llm-judge): structured output for doc, outcome and posture judges so reasoning quotes cannot break JSON * test(ship-docsync): steer skill file reads to Read; large cat output becomes an unpageable preview * docs(changelog): browser-only QA evidence and structured judge output * test(qa-only cleanup): refusal scenarios get a 1 s budget and an absolute worker deadline; 300 ms starved under parallel load * fix(office-hours, design-consultation): ask the goal question and read the mode section first; ask the memorable-thing question on its own * test(outside-disabled): a record named by the retained record's own clock and then disowned owns its completed status * test(context-skills): install gstack-paths in the fixture bin; without it the model guessed the checkpoint root * test(ceo mode routing): SCOPE EXPANSION posture credits plural 'expansions' * test(ship-docsync): name the unmet atomic-replacement check on a forbidden temp-file write * fix(qa): browser-only runs materialize an empty evidence list with checkpoints in limits, matching /qa-only * test(qa callers): an accepted review-log record may cite checkpoints as finding evidence * fix(plan-eng-review): state that a disallowed question tool never qualifies as headless before the headless action * merge follow-up: re-record paid CLI parity for #2999's flags; trim merged review, qa-only and plan-eng wording toward the size caps * test(golden): refresh codex/factory ship goldens for the trimmed caller QA wording * test(coverage-audit fixture): disable git auto maintenance so cleanup is not racing a detached git writer * test(parity): raise review, qa and plan-eng caps to the measured merged size of #2999 and #3002 (each fit alone), documented per cap * fix(qa-evidence): materialize rejects an unrecognized classification before publishing, so the one-shot verdict cannot be locked inconclusive by a descriptive label	2026-10-01 13:55:16 -07:00