mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-02 15:04:37 +01:00
* docs: Oct 7 follow-up wave plan (pre-review) * docs: Oct 7 follow-up wave plan, reviewed through /autoplan * docs: Oct 7 wave plan, record final gate decisions (UC1 accepted, UC2 rejected) * docs: credit #1822 to @Mike-E-Log and #1743 to @habassa5 (v1.64.0.0) The v1.64.0.0 CHANGELOG entry credited the extension token fix (#1822) and the polyfill exited promise (#1743) to the wrong handle, and the extension-sender-auth test header repeated the first slip. Commit history is not rewritten. Fixes #3054. Co-authored-by: Mike Ilog <48659643+Mike-E-Log@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(context-restore): offer newer checkpoints from nested repos and task worktrees /context-restore could present an older checkpoint as the latest with no error in two layouts: 1. A session started in a non-git parent saved from a nested repo, so the checkpoint went to the nested repo's bucket. Restore in the parent now lists checkpoints of other buckets whose project_root lies below the cwd (BELOW_CWD; the 200 newest are read, and from $HOME only each project's newest). /context-save also leaves a JSON pointer (checkpoint path, bucket, project_root) in the starting directory's bucket when $CLAUDE_PROJECT_DIR is set and files elsewhere; restore lists those as POINTER, in or out of git. 2. A plan checkpoint on the main tree's branch shadowed a newer checkpoint saved in a ticket worktree. When another branch holds a newer checkpoint for the same task (a worktree below the main tree, read from the new worktree: stamp; equal normalized titles; or a shared #123 / ABC-123 token in titles or branch names), restore prints NEWER_TASK and the skill shows both and proposes the newer one. Generic titles (wip, checkpoint, save, notes, todo) never match on title alone, and the worktree rule applies only when restoring from the main tree, so sibling worktrees still never shadow each other. The branch-first ordering itself is unchanged. Refs #3065. Co-authored-by: Thomas Gernhardt <t.gernhardt@softwareprojekt.net> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(redact-prepush): list each MEDIUM finding with rule, file line and fix The pre-push hook printed only a MEDIUM count, which nobody could review without re-running the engine by hand. It now prints one line per finding: rule id, file and file line, and a fix, never the matched value. Line numbers come from the hunk headers (combined --cc headers included), so a finding in a later hunk or past a scan-chunk boundary points at the real file line. Findings from the per-commit catch-up path name the commit whose file line it is, so content removed before the pushed tip is still locatable. Plan items: CEO-7 (summary half), DX-9 (fix lines), ENG-8 (line mapping). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(redact-prepush): stop flagging your own email and already-public authors (#3060) The hook never passed the engine's selfEmail / repoPublicEmails, so every push that added the pusher's address, or a commit author's, raised a MEDIUM pii.email warning for an address the destination already shows. The hook now reads `git config user.email` and one bounded `git log` of author and committer addresses, raw and mailmapped (%ae %aE %ce %cE): the history of every pushed tip (those commits become public with the push), each remote tip being replaced, and, for a new branch or an unknown remote tip pushed to a configured remote, that remote's own tracking refs. A URL or unknown destination never borrows tracking refs, and another remote's history never counts. The read stops at 50,000 commits (the newest authors are used) and 5 seconds. An error or the timeout passes no history and, when an email finding is listed, prints one line saying suppression was limited for this push. The two inputs fail independently. HIGH findings and every other rule are untouched. Controls: a stranger's address, an address only another remote knows, a URL push next to a matching remote, and a first push of a repo with no history all still report. Plan items: A3, CEO-7, CEO-23 (A3 half), DX-9 (partial history), ENG-8 (history scope, mailmap). Co-authored-by: akmandhania <143462686+akmandhania@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(redact-prepush): per-address allowlist for pii.email (gstack.redact.allowEmail) `git config --add gstack.redact.allowEmail <address>` allows that address for MEDIUM pii.email findings only, so a team alias or support address that has to be in the repo stops warning without reaching for --no-verify. It never affects HIGH findings or any other rule, and the pii.email fix line names it. Controls: a different address still reports, and a HIGH secret next to an allowed address still blocks. Plan item: DX-17. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(troubleshooting): pre-push pii.email findings, exemptions and allowlist Plan item: DX-12 (pre-push touchpoint). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(redact-prepush): assemble fixture addresses at runtime The email fixtures were literals, so this branch's own push listed 47 pii.email findings in its test file. Build them from a helper instead, the way the neighbouring tests build credential and IP fixtures. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(browse): offer the user's signed-in tab, name silent aside repl failures Rules (rendered into every browsing skill, kept short): - Rule 1: before the first openTab, offer the user's tabs on the target origin (title and origin only; the rest of listBrowserTabs() stays private) and attach only after the user confirms one. - Rule 4: a second sign-in wall after a confirmed sign-in means the session is bound to the tab or URL; offer that tab instead of another sign-in. - Rule 6 no longer suggests an early return; rule 7 says a fast [ok without GSTACK_STEP_OK is an abort. Cookbook (browse, devex-review): a "Silent failures" list (evaluate returns only serializable values, no top-level return, locator(sel).press(key), an empty DOM read is about the selector until the screenshot and the request's response say otherwise, read toggle state before clicking) and a signed-in tab recipe that prints only target-origin tabs and never closes the user's tab. Parity caps for design-consultation, land-and-deploy, qa and the browse skeleton are raised to the measured sizes, with notes. Refs #3063, #3064. Co-authored-by: Thomas Gernhardt <t.gernhardt@softwareprojekt.net> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(codex): run gstack-codex-probe as a command, one subcommand per probe Generated skills now execute bin/gstack-codex-probe (select-model, check-auth, show-sandbox, check-sandbox, probe-model, check-version, show-first-use-notice, run-with-timeout, log-event, log-hang, help) and capture its KEY: value lines, so no helper state crosses into the calling shell and the preflight works from bash, zsh or sh. select-model keeps --model > GSTACK_CODEX_MODEL > config.toml precedence; run-with-timeout supervises with the existing gtimeout/timeout/ watchdog chain and returns 124 on a deadline; an unknown subcommand exits 64. Sourcing keeps working for skills rendered before the upgrade and prints one deprecation line naming /gstack-upgrade; it and the zsh self-locate block are removed in a release on or after 2026-10-21 (DX-18). Parity caps raised with measured notes for the longer capture lines. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(gstack-post): one argv-only, redaction-scanned write path for PR and issue text bin/gstack-post posts a PR/MR or issue comment, a review-comment reply, a PR title or body, a new PR/MR or a new issue from agent-written files. Every value reaches gh/glab as its own argv element in --flag=<value> form or on stdin, never through a shell string, and a target is a number or a URL of this repository on the same host. The helper owns the redaction scan: it reads each file once, scans those exact bytes (visibility from config, then gh/glab; the pusher's own email suppressed) and sends the same bytes. HIGH is refused with exit 1 and no confirmation can post it. MEDIUM exits 2 with RULE:/LINE:/PART: lines and a TOKEN: digest of the bytes, destination, operation and findings; only --confirm <token> for those exact bytes posts, so any edit needs a new confirmation. gh/glab failures exit 3, usage errors 64. It also carries the projectCards REST fallback and the title read-back that /ship did by hand. The logic lives in lib/gstack-post.ts behind an injectable runner, so its tests run in the Windows free lane; the stub-gh executable test is POSIX. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): guard verifies dispatches on Claude Code 2.1.29x (schema strip, unflushed call, named causes) Cause A: Claude Code journals the model's raw Agent input but hands PreToolUse the schema-parsed input; with the fork-subagent gate on (the interactive default in 2.1.292) run_in_background is dropped, so the journal record never deep-equaled the payload. nativeToolInput now drops only that documented strip for Agent. Agent input is bound on both paths: keys limited to prompt, description, subagent_type (general-purpose) and run_in_background; a model override or any other key is denied. Cause B: when a ready journal lacks the current call, the guard evaluates the payload placed after the last journaled record instead of polling for a record that may arrive only with the tool result. A phase transition counts a report only when a later journaled record follows it (and, on the journal path, it is not in the current call's message). One batch rule covers both paths; a background reviewer keeps the invocation armed until its completion notice. Every outcome now has a stable reason code, disposition and anchor (autoplan/bin/guard-reasons.ts). UC1: Claude-Code-caused states (unrecognized shape, journal lag, rewritten journal, oversized record, unchecked-version schema strip) allow with a visible warning; integrity failures stay denials. No denial advises a bare retry. Every guarded decision appends one content-free line to analytics/autoplan-guard.jsonl, trimmed to 1,000 lines past 256 KiB. Co-authored-by: Jared <182125291+yolo-jared@users.noreply.github.com> Co-authored-by: crblabs <293123359+crblabs@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): publish each phase report with a no-op call; foreground requests are conditional Phase-close step 6 sends the report in a message whose only tool call is the Bash no-op ': autoplan-published <phase>', and step 7 makes the next guarded call in a later message, so the guard sees the report flushed before the next phase entry regardless of Claude Code's journal timing. Every site that asked for run_in_background: false now asks for it only when the Agent schema offers it and says how to recover when a dispatch runs in the background anyway (wait for its completion notice). Parity caps rise by the measured bytes. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(ship,spec,review): PR and issue text goes out only through gstack-post /ship: Step 18 writes the title into an agent-written file. An existing PR's title is piped from gh/glab through gstack-pr-title-rewrite.sh --stdin (new), so neither the agent nor a shell string carries it; a new title is written with the file tool and its version prefix checked in the file. Step 19 composes the body as before and publishes with gstack-post pr-create, or pr-body then pr-title, which scan the exact bytes they send. The separate title and body scans, the hand-rolled REST fallback and the title self-check are gone (the helper does all three). Title preparation moved into the pr-body section, so the skeleton shrinks. /spec files its issue with gstack-post issue-create and drops the pre-issue re-scan; Greptile replies use gstack-post reply and pr-comment. scripts/resolvers/redact-doc.ts loses its PR and issue sinks, and a test keeps any template from rendering one again. Tests that pinned the old scan-then-gh wiring now pin the gstack-post wiring; the publication tests run the real compose and publish blocks against a stub gh with the real helper (HIGH in title or body refused, MEDIUM token flow). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci: pin Claude Code 2.1.292 in the CI image 2.1.292 is the npm latest users run. Its interactive default turns on the fork-subagent gate, which strips run_in_background from the Agent schema and backgrounds reviewers; CI on 2.1.284 never saw the /autoplan guard break. The image tag is a content hash, so every eval workflow picks up the new image without a workflow edit. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(brain-sync): one drain lock for every writer to the artifacts repo gstack-artifacts-init, gstack-brain-restore, gstack-gbrain-source-wireup and the skill-start merge ran git in $GSTACK_HOME without the drain's lock, so the drain could never tell an abandoned .git/index.lock from a live one. They now take the same mkdir lock (bin/gstack-brain-lock.sh): the drain and the skill-start merge skip when it is held, user-run writers wait for it (GSTACK_BRAIN_LOCK_WAIT, default 120 s), and a child of the holder (the drain's daily worktree advance, restore's wireup) inherits it by token. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(brain-sync): hold back only the flagged file, keep coupled artifacts whole One file with secret-shaped text used to block every push, silently. The drain now attributes scanner hits to files in one pass over the staged diff (split on its diff --git headers), holds back each flagged file with the rest of its coupled group, unstages it, and requires the remaining staged diff to re-scan clean; anything short of that falls back to a full unstage and status blocked. Held files stay queued and are re-scanned every drain. - Status file gains held_count, drainable, last_drain_at, last_push_at and held[] (path, scanner rule, dependents, both fixes); new status held. - Coupled groups come from an explicit map (decisions.jsonl and decisions.active.json): a queued member stages the whole group, a group stages only when its snapshot matches its log in the index, a skipped member stops the whole group. - --unskip-file undoes --skip-file and queues the path again. - An index lock older than 10 minutes is removed under the drain lock; a younger one, a failed git add, a failed commit (hooks included) keep the queue and report status error. A verified empty staged diff is the only "nothing to commit". git add runs once, batched. - The scanner reads bytes, so undecodable content no longer crashes it into a false clean; matched text never reaches the status file. - An empty-queue run with unpushed sync commits stays push_failed. - Privacy-held duplicate records collapse to one per path; --status counts a spool too deep for a shell glob. - --attention prints skill start's fixed attention lines from the sync status table in the usage header. Co-authored-by: v639dragoon <matthewsbrickley@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(skill-start): ARTIFACTS_SYNC attention lines for a stuck sync Skill start now prints one fixed attention line per sync-status-table row that applies (held, blocked, push_failed, error, unknown, stale-push, stale-drain), each naming gstack-brain-sync by absolute path. Values from the status file are clamped (status code to the table, counts to digits, timestamps to their shape), so the status message, file paths and scanner output never reach the line. The preamble tells the model to surface the line in one sentence and continue. Skill-start tests are generated from the table in bin/gstack-brain-sync, and docs/gbrain-sync-errors.md carries the same table. Co-authored-by: v639dragoon <matthewsbrickley@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(outside-review): severity words in label position count as findings The Oct 7 /autoplan run's Codex CEO and DX reviews labeled seven and eight findings High/Medium without [Pn] tags, and the classifier printed VERDICT: clean / FINDINGS: none for both. lib/outside-review-result.ts now reads severity words in label position (Severity: High, a leading High: / High — / [High], **High**, a table cell): critical/high block like P0/P1, medium/low are advisory. Words in prose (high-level, low-risk, no critical findings) never count. A review or structured response with neither tags, labels nor an explicit no-findings statement is unverified, never clean (DX-11, ENG-10). Design-direction proposals move to a new proposal gate so they keep needing only their Recommendation line, and review prompts ask for a severity per finding. Fixtures reproduce the CEO/DX label shapes, the eng [P1] output, a table and prose negative controls; the stored Codex panel keeps its verdicts. docs/troubleshooting.md explains how the verdict is read. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat: gstack-doctor readiness report and setup --status Codex row (B5) bin/gstack-doctor prints one row per check without starting a skill: install root (the registry rows behind ./setup --status), state root, Bun against the floor, hook parse check, Codex mode and self-locate via gstack-codex-probe subcommands, the cached model probe with its age (--live runs the paid probe-model), artifacts-sync health from the status file with the status code clamped, the browse bundle, Claude Code version, the largest session journal and the last five schema-1 guard reason codes. Rows are ok, warn, not configured or fail; only fail exits non-zero; fix lines name helpers by absolute install-root path. ./setup --status gains a read-only Codex row (bin/gstack-codex-status.sh, shared with the doctor) and ends with the doctor's absolute path. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: bug-report template asks for doctor output; README troubleshooting entry; doctor test in the Windows lane The template gives the Claude Code doctor path and a lookup for other hosts and names no bare gstack- command (asserted in test/gstack-doctor.test.ts). The doctor test runs every script through explicit bash argv, so it joins the curated Windows free subset. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(troubleshooting): readiness check section points at gstack-doctor Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(question-tuning,plan-tune,gbrain): free text reaches helpers only through agent-written files Question tuning no longer pipes the question summary through printf: a registered id needs no summary, and for an unregistered id the agent writes the summary to .gstack/tmp/qt.txt and passes --summary-file (new). The helper resolves a relative path against the git top level, removes scratch files under .gstack/tmp, and asks normally when the file is missing. /plan-tune tune events carry the user's own words again: they go into a file the agent writes and reach gstack-question-preference --write through --free-text-file (new), still behind the injection filter and the user-origin gate. docs/gbrain-write-surfaces.md drops its heredoc templates for the agent-written page file on stdin, matching the per-skill save block, and the generic save block stops showing a quoted --content argument. The tuning prose was tightened so every preamble stays within its size cap. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(evals): daily autoplan-schema-canary on the latest Claude Code A periodic rule case installs the latest published Claude Code with install scripts off, verifies registry signatures, and runs one headless session with the fork-subagent gate on whose PreToolUse hook records an Agent and a Read payload. Each payload must match its journal record under the guard's own comparison, keep the journal's key set apart from the documented run_in_background strip, and stay inside the Agent allowlist; a background Agent's completion notice must keep the shape the guard reads. evals-periodic.yml runs it daily on its own schedule and concurrency group (read-only token); the weekly census also includes it. A free test proves the comparison fails on an injected strip. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(doctor): read the artifacts sync held count from held_count, the field the drain writes * fix(artifacts sync): the init and restore pre-commit hooks catch Bearer/Basic/Token-prefixed JSON auth headers like the drain does * feat(greptile-early): detect Greptile, ask once on public repos, open the early draft, wait for the review bin/gstack-greptile-early backs /ship's early Greptile PR: - detect: a root .greptile/ folder (which takes precedence), greptile.json, or a Greptile comment on the repo in the last 90 days; triggerOnDrafts from the effective root config; repo visibility; public-repo consent. It prints the signal, that /ship will push and open a draft now, the 10-minute wait cap and the absolute gstack-config command that turns it off. - consent yes|no: the public-repo answer, remembered per repo in the project's state. - open: opens the draft through gstack-post with a body saying /ship opened it early, and posts one @greptileai comment through gstack-post when the config does not set triggerOnDrafts: true. An open PR is left alone. - wait: polls every 30 s for a completed Greptile check run, a Greptile review of the head commit or a summary naming it; each call returns within about 90 s and reports timeout 10 minutes after the PR opened. gstack-config gains ship_greptile_early (default true, invalid values rejected): on automatically whenever the repo uses Greptile, off per user. The logic is in lib/greptile-early.ts behind an injectable runner, so its fixture-repo tests run in the Windows lane; an end-to-end test drives the real helper and gstack-post against a stub gh. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(ship): early Greptile PR at Step 6.5, bounded wait at Step 10 (#3020) When the repo uses Greptile, /ship pushes and opens a draft PR right after its free tests pass (new lazy section greptile-early, Step 6.5), so Greptile reviews while Steps 7-9 run. A public repo asks once, remembered per repo; declining keeps today's order. Step 10 waits for that review with gstack-greptile-early wait and takes the existing unavailable route on a timeout, never a claim of zero comments. Step 18 replaces the provisional title, Step 19 marks the draft ready unless a draft was requested, and a /ship that stops after Step 6.5 leaves the draft open with one comment saying why. ship's union cap rises to 1.5275 with the measured note (B4 +836 bytes, B2 +4,732 bytes); the step-numbering guard allows 6.5; ship goldens are refreshed for B4 and B2. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): the publication no-op is 'true autoplan-published <phase>' Measured on Claude Code 2.1.292 in a default-settings interactive session: a bare ':' Bash command asks for approval ('This command requires approval'), and after a background reviewer's completion notice starts a new turn the skill's allowed tools no longer cover it, so the phase-close no-op prompted the user. 'true' with arguments runs without approval and prints nothing. The guard only needs a later journaled record, so the command changes everywhere it is named. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(evals): live autoplan-guard-pty case on the pinned Claude Code A gate-tier rule case (one trial, haiku) drives an interactive PTY session with default settings through a project skill that carries /autoplan's own hook block: init, Phase 1 entry, a CEO reviewer dispatch that sends run_in_background, a prepared close packet, the report published with the no-op, and the Phase 2 entry in a later message. It reads outcomes from the guard decision log (three verified allows) and fails if the no-op raises a permission card; other cards are approved and printed. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): bounded, append-tolerant owned-journal read (A2) The publication guard no longer reads the whole parent journal or refuses it at 32 MiB. lib/claude-owned-journal.ts streams the bytes present at open to the last complete line (pass one), keeps a content-free index per record and decides ownership, ancestry and causal order on it with the same checks and reason codes as before. Pass two reloads in full only what the evaluation reads (autoplan/bin/guard-journal.ts): every literal init and its result, the current call, and inside the invocation window (from the latest human turn at or before the bound chain's first init) guarded and close-packet Read results, structured Bash results, error results, assistant text after the first close Read and active-plan mutations, plus the earlier Read a dedup reply cites even before the window (ENG-4). - lib/claude-journal-records.ts: per-record event extraction, record metadata and the causal-order checks, shared by readPlanCountTranscript and the bounded reader. The batch reader keeps its whole-file read and cap. - Appends after open never fail a read; same device and inode and no shrink are required (identity). A second read in one hook invocation must hash bytes [0, first size) the same, or it is `rewritten` (UC1 unverified); the unrecognized-shape double read uses that prefix hash. `changing` is removed (REMOVED_CODES; its anchor stays). - OWNED_RECORD_MAX_BYTES (32 MiB): only one record over it is too_large. OWNED_RETAINED_MAX_BYTES (32 MiB): over it is the new oversized_invocation fallback denial. GSTACK_TRANSCRIPT_TEST_MAX_BYTES and GSTACK_TRANSCRIPT_TEST_RETAINED_BYTES can only lower them. - ENG-5: evaluation groups uses and results by tool id once (no per-tool rescans). CEO-25 / ENG-5 spike (120 MiB synthetic, 31,242 records, 4 vCPU Linux, Bun 1.4.2): a full streaming rescan (parse every line, small index, sha256) took 254-326 ms at 147-161 MiB peak RSS; a pass-one index cache under the state root (load cached index, verify a 64 KiB tail hash, parse the tail) took 26-29 ms at 47 MiB. The rescan meets the 1 s budget, so the cache is not adopted: it would add trusted persistent state and invalidation for no budget need. A backward tail read cannot prove competing_root or cycle, so it was not a candidate. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(autoplan): journal-read benchmark and its dispatch-only workflow (CEO-2, CEO-6) scripts/measure-journal-read.ts builds two synthetic 120 MiB parent journals around a real /autoplan invocation (mixed: ~28k records, most bytes inside the invocation; large-invocation: ~89k records with a current invocation of many small records), keeps appending while the guard reads, and measures one hook call in a fresh process (wall ms, peak RSS). The workflow runs it on ubuntu-latest and macos-latest on workflow_dispatch only. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(evals): autoplan-long-session, a resumed >100 MiB session enters Phase 1 CEO-15 with ENG-6's observer: a real session is compacted, its journal padded past 100 MiB with owned records before the compact boundary, and the resumed interactive session runs the scripted phase boundary; the guard decision log must show a verified Phase 1 allow. A free test proves that observer on a padded journal through the lower-only bound seams (the PTY counting reader refuses the same journal), with a sidechain control that must deny. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * v1.91.34.0: CHANGELOG, TODOS, version; harness decision for test-pr-profile; ship title-step test reads its new section * docs(changelog): use an example.com address in the allowEmail example * test: assemble GitHub-token fixtures at runtime in the new brain-sync and skill-start tests (CI credential scan) * fix: integration repairs across the wave (Step 6.5 fence, printed helper paths on Windows, probe usage without a heredoc) and tests pinned to the moved title and gstack-post contracts * test(doctor): the healthy fixture builds browse.exe on Windows, the name setup uses there * test(shared-libs): recognize Claude Code 2.1.292's internal git probe prefix (format.pretty and per-hook disables), with its CI receipt * fix(ship-measure): report lists v1 measurements as an older format instead of crashing --------- Co-authored-by: Mike Ilog <48659643+Mike-E-Log@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> Co-authored-by: Thomas Gernhardt <t.gernhardt@softwareprojekt.net> Co-authored-by: akmandhania <143462686+akmandhania@users.noreply.github.com> Co-authored-by: Jared <182125291+yolo-jared@users.noreply.github.com> Co-authored-by: crblabs <293123359+crblabs@users.noreply.github.com> Co-authored-by: v639dragoon <matthewsbrickley@gmail.com>
308 lines
12 KiB
Cheetah
308 lines
12 KiB
Cheetah
---
|
|
name: context-save
|
|
preamble-tier: 2
|
|
version: 1.0.0
|
|
description: |
|
|
Save working context. Captures git state, decisions made, and remaining work
|
|
so any future session can pick up without losing a beat.
|
|
Use when asked to "save progress", "save state", "context save", or
|
|
"save my work". Pair with /context-restore to resume later.
|
|
(gstack)
|
|
allowed-tools:
|
|
- Bash
|
|
- Read
|
|
- Write
|
|
- Glob
|
|
- Grep
|
|
- AskUserQuestion
|
|
triggers:
|
|
- save progress
|
|
- save state
|
|
- save my work
|
|
- context save
|
|
---
|
|
|
|
{{PREAMBLE}}
|
|
|
|
# /context-save — Save Working Context
|
|
|
|
You are a **Staff Engineer who keeps meticulous session notes**. Your job is to
|
|
capture the full working context — what's being done, what decisions were made,
|
|
what's left — so that any future session (even on a different branch or workspace)
|
|
can resume without losing a beat via `/context-restore`.
|
|
|
|
**HARD GATE:** Do NOT implement code changes. This skill captures state only.
|
|
|
|
---
|
|
|
|
## Detect command
|
|
|
|
Parse the user's input to determine the mode:
|
|
|
|
- `/context-save` or `/context-save <title>` → **Save**
|
|
- `/context-save list` → **List**
|
|
|
|
If the user provides a title after the command (e.g., `/context-save auth refactor`),
|
|
use it as the title. Otherwise, infer a title from the current work.
|
|
|
|
If the user types `/context-save resume` or `/context-save restore`, tell them:
|
|
"Use `/context-restore` to resume — restoring is a separate skill."
|
|
|
|
---
|
|
|
|
## Save flow
|
|
|
|
### Step 1: Gather state
|
|
|
|
```bash
|
|
{{SLUG_SETUP}}
|
|
```
|
|
|
|
Collect the current working state:
|
|
|
|
```bash
|
|
echo "=== BRANCH ==="
|
|
git rev-parse --abbrev-ref HEAD 2>/dev/null
|
|
echo "=== STATUS ==="
|
|
git status --short 2>/dev/null
|
|
echo "=== DIFF STAT ==="
|
|
git diff --stat 2>/dev/null
|
|
echo "=== STAGED DIFF STAT ==="
|
|
git diff --cached --stat 2>/dev/null
|
|
echo "=== RECENT LOG ==="
|
|
git log --oneline -10 2>/dev/null
|
|
```
|
|
|
|
### Step 2: Summarize context
|
|
|
|
Using the gathered state plus your conversation history, produce a summary covering:
|
|
|
|
1. **What's being worked on** — the high-level goal or feature
|
|
2. **Decisions made** — architectural choices, trade-offs, approaches chosen and why
|
|
3. **Remaining work** — concrete next steps, in priority order, each marked with
|
|
how this session knows it (see the provenance table below)
|
|
4. **Notes** — anything a future session needs to know (gotchas, blocked items,
|
|
open questions, things that were tried and didn't work)
|
|
|
|
**Remaining Work provenance.** Every item starts with the status `Open.` and never
|
|
with a completion token such as `[done]` or `[executed]`. Then pick its trailing
|
|
marker by the first rule that applies:
|
|
|
|
| # | The item is... | Marker | Use when this session... |
|
|
|---|----------------|--------|--------------------------|
|
|
| 1 | a writing step (migration, sync, insert, import, a dialog that writes), with or without a concrete path | `(target state checked)` | inspected the target's schema or state (for example the unique key) |
|
|
| | | `(code read)` | read the writer but not the target |
|
|
| | | `(path assumed)` | inferred the write without reading either |
|
|
| 2 | otherwise, names a concrete path: a runnable command, CLI flag or switch, config key or value, or file or directory path | `(path run)` | executed it and observed the outcome; state the outcome in the item (`exit 0`, `failed: <reason>`) |
|
|
| | | `(path read)` | read the code or file but did not execute it |
|
|
| | | `(path assumed)` | inferred it without running or reading it, however confident |
|
|
| 3 | anything else | none | (`Open.` alone) |
|
|
|
|
Writing steps have their own markers because whether a write is safe to repeat
|
|
depends on the target's state, not on the code that writes. Examples:
|
|
`Open. Run the suite with CONFIG=staging. (path run) exit 0` and
|
|
`Open. Switch B reads config Y. (path assumed)`.
|
|
|
|
If the user provided a title, use it. Otherwise, infer a concise title (3-6 words)
|
|
from the work being done.
|
|
|
|
### Step 3: Compute session duration
|
|
|
|
Try to determine how long this session has been active:
|
|
|
|
```bash
|
|
if [ -n "$_TEL_START" ]; then
|
|
START_EPOCH="$_TEL_START"
|
|
elif [ -n "$PPID" ]; then
|
|
_LSTART=$(ps -o lstart= -p "$PPID" 2>/dev/null)
|
|
# BSD date (macOS) parses with -jf; GNU date (Linux) with -d. Never parse an
|
|
# empty start: GNU date -d "" means today at midnight.
|
|
[ -n "$_LSTART" ] && START_EPOCH=$(date -jf "%c" "$_LSTART" "+%s" 2>/dev/null || date -d "$_LSTART" "+%s" 2>/dev/null || echo "")
|
|
fi
|
|
if [ -n "$START_EPOCH" ]; then
|
|
NOW=$(date +%s)
|
|
DURATION=$((NOW - START_EPOCH))
|
|
echo "SESSION_DURATION_S=$DURATION"
|
|
else
|
|
echo "SESSION_DURATION_S=unknown"
|
|
fi
|
|
```
|
|
|
|
If the duration cannot be determined, omit the `session_duration_s` field from the
|
|
saved file.
|
|
|
|
### Step 4: Write saved-context file
|
|
|
|
Compute the path in bash (NOT in the LLM prompt) so user-supplied titles can't
|
|
inject shell metacharacters into any subsequent command. The sanitizer is an
|
|
allowlist: only `a-z 0-9 - .` survive.
|
|
|
|
```bash
|
|
{{SLUG_SETUP}}
|
|
GSTACK_STATE_ROOT=$(~/.claude/skills/gstack/bin/gstack-paths --get GSTACK_STATE_ROOT); : "${GSTACK_STATE_ROOT:?gstack-paths failed; reinstall with ./setup or /gstack-upgrade}"
|
|
CHECKPOINT_DIR="$GSTACK_STATE_ROOT/projects/$SLUG/checkpoints"
|
|
mkdir -p "$CHECKPOINT_DIR"
|
|
TIMESTAMP=$(date +%Y%m%d-%H%M%S)
|
|
# Bash-side title sanitize. Pass the raw title via TITLE_RAW when running this block.
|
|
# Example: TITLE_RAW="wintermute progress" bash -c '...'
|
|
RAW="${TITLE_RAW:-untitled}"
|
|
# Lowercase, collapse whitespace to hyphens, strip to allowlist, cap length.
|
|
TITLE_SLUG=$(printf '%s' "$RAW" | tr '[:upper:]' '[:lower:]' | tr -s ' \t' '-' | tr -cd 'a-z0-9.-' | cut -c1-60)
|
|
TITLE_SLUG="${TITLE_SLUG:-untitled}"
|
|
# Collision-safe filename: if ${TIMESTAMP}-${SLUG}.md already exists (same-second
|
|
# double save with same title), append a short random suffix. Filenames are
|
|
# append-only — never overwrite.
|
|
FILE="${CHECKPOINT_DIR}/${TIMESTAMP}-${TITLE_SLUG}.md"
|
|
if [ -e "$FILE" ]; then
|
|
SUFFIX=$(LC_ALL=C tr -dc 'a-z0-9' < /dev/urandom 2>/dev/null | head -c 4 || printf '%04x' "$$")
|
|
FILE="${CHECKPOINT_DIR}/${TIMESTAMP}-${TITLE_SLUG}-${SUFFIX}.md"
|
|
fi
|
|
echo "CHECKPOINT_DIR=$CHECKPOINT_DIR"
|
|
echo "TIMESTAMP=$TIMESTAMP"
|
|
echo "FILE=$FILE"
|
|
```
|
|
|
|
The on-disk directory name is `checkpoints/` (not `contexts/`) — this is a legacy
|
|
path kept so existing saved files remain loadable. Users never see it.
|
|
|
|
Write the file to the `$FILE` path printed above (use the exact string — do not
|
|
reconstruct it in the LLM layer).
|
|
|
|
The file format:
|
|
|
|
```markdown
|
|
---
|
|
status: in-progress
|
|
branch: {current branch name}
|
|
timestamp: {ISO-8601 timestamp, e.g. 2026-04-18T14:30:00-07:00}
|
|
session_duration_s: {computed duration, omit if unknown}
|
|
files_modified:
|
|
- path/to/file1
|
|
- path/to/file2
|
|
---
|
|
|
|
## Working on: {title}
|
|
|
|
### Summary
|
|
|
|
{1-3 sentences describing the high-level goal and current progress}
|
|
|
|
### Decisions Made
|
|
|
|
{Bulleted list of architectural choices, trade-offs, and reasoning}
|
|
|
|
### Remaining Work
|
|
|
|
{Numbered list of concrete next steps, in priority order. Each item starts with `Open.` and ends with its provenance marker from Step 2, or no marker under rule 3.}
|
|
|
|
### Notes
|
|
|
|
{Gotchas, blocked items, open questions, things tried that didn't work}
|
|
```
|
|
|
|
The `files_modified` list comes from `git status --short` (both staged and unstaged
|
|
modified files). Use relative paths from the repo root. Do not write `remote:`,
|
|
`project_root:` or `worktree:` yourself; the stamp step below adds them.
|
|
|
|
Then stamp the project identity. Several projects can share one checkpoints
|
|
directory, so `/context-restore` needs to know which project wrote each file. The helper adds `remote:` (canonical origin:
|
|
lowercased host, no credentials, port or `.git`), `project_root:` and, in a
|
|
linked worktree, `worktree:` to the frontmatter. When the session started in
|
|
another directory that files elsewhere (a non-git parent of this repo), it also
|
|
leaves a pointer there so `/context-restore` in that directory finds this save:
|
|
|
|
```bash
|
|
FILE="<the FILE path printed above>"
|
|
~/.claude/skills/gstack/bin/gstack-slug --stamp-checkpoint "$FILE" && echo "STAMPED"
|
|
[ -z "${CLAUDE_PROJECT_DIR:-}" ] || ~/.claude/skills/gstack/bin/gstack-slug --point-from "$CLAUDE_PROJECT_DIR" "$FILE" 2>/dev/null || true
|
|
```
|
|
|
|
After writing, confirm to the user:
|
|
|
|
```
|
|
CONTEXT SAVED
|
|
════════════════════════════════════════
|
|
Title: {title}
|
|
Branch: {branch}
|
|
File: {path to saved file}
|
|
Modified: {N} files
|
|
Duration: {duration or "unknown"}
|
|
════════════════════════════════════════
|
|
|
|
Restore later with /context-restore.
|
|
```
|
|
|
|
---
|
|
|
|
## List flow
|
|
|
|
### Step 1: Gather saved contexts
|
|
|
|
```bash
|
|
{{SLUG_SETUP}}
|
|
GSTACK_STATE_ROOT=$(~/.claude/skills/gstack/bin/gstack-paths --get GSTACK_STATE_ROOT); : "${GSTACK_STATE_ROOT:?gstack-paths failed; reinstall with ./setup or /gstack-upgrade}"
|
|
CHECKPOINT_DIR="$GSTACK_STATE_ROOT/projects/$SLUG/checkpoints"
|
|
if [ -d "$CHECKPOINT_DIR" ]; then
|
|
echo "CHECKPOINT_DIR=$CHECKPOINT_DIR"
|
|
# Use find + sort instead of ls -1t: filename YYYYMMDD-HHMMSS prefix is the
|
|
# canonical order (stable across copies/rsync; mtime is not), and empty-result
|
|
# behavior is clean (no files → no output, no "lists cwd" fallback).
|
|
find "$CHECKPOINT_DIR" -maxdepth 1 -name "*.md" -type f 2>/dev/null | sort -r
|
|
else
|
|
echo "NO_CHECKPOINTS"
|
|
fi
|
|
```
|
|
|
|
### Step 2: Display table
|
|
|
|
**Default behavior:** Show saved contexts for the **current branch** only.
|
|
|
|
If the user passes `--all` (e.g., `/context-save list --all`), show contexts
|
|
from **all branches**.
|
|
|
|
Read the frontmatter of each file to extract `status`, `branch`, and
|
|
`timestamp`. Parse the title from the filename (the part after the timestamp).
|
|
|
|
Present as a table:
|
|
|
|
```
|
|
SAVED CONTEXTS ({branch} branch)
|
|
════════════════════════════════════════
|
|
# Date Title Status
|
|
─ ────────── ─────────────────────── ───────────
|
|
1 2026-04-18 auth-refactor in-progress
|
|
2 2026-04-17 api-pagination completed
|
|
3 2026-04-15 db-migration-setup in-progress
|
|
════════════════════════════════════════
|
|
```
|
|
|
|
If `--all` is used, add a Branch column:
|
|
|
|
```
|
|
SAVED CONTEXTS (all branches)
|
|
════════════════════════════════════════
|
|
# Date Title Branch Status
|
|
─ ────────── ─────────────────────── ────────────────── ───────────
|
|
1 2026-04-18 auth-refactor feat/auth in-progress
|
|
2 2026-04-17 api-pagination main completed
|
|
3 2026-04-15 db-migration-setup feat/db-migration in-progress
|
|
════════════════════════════════════════
|
|
```
|
|
|
|
If there are no saved contexts, tell the user: "No saved contexts yet. Run
|
|
`/context-save` to save your current working state."
|
|
|
|
---
|
|
|
|
## Important Rules
|
|
|
|
- **Never modify code.** This skill only reads state and writes the context file.
|
|
- **Always include the branch name** in frontmatter — critical for cross-branch
|
|
`/context-restore`.
|
|
- **Saved files are append-only.** Never overwrite or delete existing files. Each
|
|
save creates a new file.
|
|
- **Infer, don't interrogate.** Use git state and conversation context to fill in
|
|
the file. Only use AskUserQuestion if the title genuinely cannot be inferred.
|
|
- **This is a gstack skill, not a Claude Code built-in.** When the user types
|
|
`/context-save`, invoke this skill via the Skill tool.
|