mirror of
https://github.com/garrytan/gstack.git
synced 2026-08-11 16:50:20 +02:00
* fix(careful): warn on chained rm even when the last target is safe The safe-exception block whitelisted rm -rf of build artifacts by extracting targets with a single greedy match (.*rm ...), which only ever inspects the LAST rm in the command. A chain like 'rm -rf /; rm -rf node_modules' was therefore judged solely by its trailing safe target and allowed without warning, waving through the destructive 'rm -rf /'. Gate the shortcut to single rm invocations: when any shell separator (; | & newline, incl. JSON-escaped \n/\r from the grep extraction path) is present, fall through to the destructive-pattern check, which warns on any recursive rm. Single-command artifact cleanups still allow. Adds 3 regression tests covering semicolon and && chains in both orders. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * harden(careful): substitution separators + capital -R recursive flag (#2039) Two residual fail-opens in the same guard PR #2040 hardened, both verified by executing the script pre-fix: - rm -rf $(./wipe-all)/node_modules silently allowed: the substitution token ends in a whitelisted suffix and the safe-exception early exit skipped ALL downstream checks. $( and backtick now count as chain separators; plain $VAR expansion stays allowed. - rm -R / silently allowed: both greps required a lowercase r in the flag cluster; capital -R is the documented BSD/macOS recursive flag. Both greps now match -[a-zA-Z]*[rR]. Six new tests: substitution x2 -> ask, capital-R x2 -> ask, rm -Rf node_modules single-command -> still allowed, escaped-newline branch (existing code, previously untested), and a pinned deliberate FP (cd app && rm -rf node_modules -> ask) documenting the fail-closed direction on chains. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(context-restore): prefer the current branch's own checkpoint (#2052) All worktrees of a repo share one origin-derived slug, so they share one `~/.gstack/projects/<slug>/checkpoints/` dir. `/context-restore` loaded the newest checkpoint across the whole dir, so in one worktree it could silently restore a *sibling worktree's* newer checkpoint. Step 1 now orders candidates current-branch-first (read from each file's `branch:` frontmatter), keeping other branches as a fallback. A branch is checked out in at most one worktree, so this stops cross-worktree contamination while preserving Conductor cross-branch handoff: when the current branch has no checkpoint of its own, the full newest-first set is still used. - scan the 200 newest before partitioning so a current-branch checkpoint sitting below a burst of sibling saves is still found; output still capped at 20 - non-git / detached HEAD / branchless legacy saves fall back to the old newest-first behavior (back-compat) - +5 regression tests in context-save-hardening.test.ts (the #2052 bug case fails on the old pipeline); regenerated SKILL.md + proactive-suggestions.json Fixes #2052 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(gbrain): pass --confirm-destructive on drift re-register (#1985) ensureSourceRegistered() handles match-but-different-path by removing the old source then re-adding it at the new path. The remove was issued as `gbrain sources remove <id> --yes`, but gbrain >= 0.42 gates `sources remove` behind `--confirm-destructive` (`--yes` alone no longer suppresses the data-loss prompt). The remove therefore fails with "To proceed, pass --confirm-destructive", which ensureSourceRegistered surfaces as "source registration failed" — aborting the entire /sync-gbrain code stage for any already-registered source whose path has drifted. The memory and brain-sync stages still pass, so the code index silently stops refreshing. The orchestrator's own safeSourcesRemove() already passes --confirm-destructive; this brings the lib helper in line with that convention. Keeps --yes for older gbrain. Tests: extend the fake gbrain shim in gbrain-sources.test.ts to simulate the gbrain >= 0.42 guard (remove without --confirm-destructive exits 1), update the drift re-register assertion, and add a regression test that proves the drift path no longer throws. Both fail on main with the exact "To proceed, pass --confirm-destructive" error and pass with the fix. Fixes #1985 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * harden(gbrain-sources): route drift remove through #1734 guards + realpath drift check Absorbing #2031 un-blocked a destructive remove that bypassed the #1734 data-loss guards: ensureSourceRegistered's drift path issued `gbrain sources remove` directly, without the detectAutopilot + decideSourceRemove checks every other remove routes through via safeSourcesRemove. gbrain >= 0.42's own prompt was accidentally blocking that path; with --confirm-destructive passed it is live again. - Drift remove now refuses LOUDLY (throws, actionable message) while an autopilot is active or when decideSourceRemove disallows; a silent changed=false would hide the drifted registration. - decideSourceRemove's extraArgs (--keep-storage when supported) propagate to the remove call, matching safeSourcesRemove. - Drift is realpath-normalized before being declared: a symlink alias of the same directory (macOS /tmp -> /private/tmp) is a match, not drift — the probable cause of #1985's reporter hitting the remove on an unmoved repo. - Drift fires a loud stderr line (old -> new path); perpetual drift in logs is the trigger for promoting #1985's reindex-in-place design. Tests: autopilot-active refusal (no remove in call log), fail-closed refusal on unreadable sources list, --keep-storage propagation, symlink-alias no-drift; existing drift tests pin the guard probes so a live autopilot on the dev machine can't flip them. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(developer-profile): exclude mode:resources rows from SESSION_COUNT, TIER, NUDGE_ELIGIBLE (#2067) Every /office-hours run appends a mode:"resources" bookkeeping row alongside the real session row, so --read double-counted sessions (~2x): tiers promoted early and the builder-to-founder nudge armed prematurely. The file already filtered resources rows for LAST_*/CROSS_PROJECT; the same realSessions filter now feeds SESSION_COUNT/TIER, and the nudge predicate is the faithful allowlist (mode === 'builder') so a future mode #4 fails closed instead of re-opening this bug. 8 regression tests: count vs resources noise, tier boundaries both sides, nudge false-with-noise / true-at-3-builders, cross-project trailing row. Absorbed from PR #1991 by @mvann (fix + tests commits; the PR's version-bump commit is superseded by this wave's consolidated release commit). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(hooks): passThrough() two-branch contract — never emit permissionDecision:'defer' (#2035, #2006) Every AskUserQuestion died with "Tool result missing due to internal error" on current Claude Code builds (Desktop 1.14271.0, CC 2.1.177). Root cause: the question-preference-hook emitted permissionDecision:'defer' on every pass-through path. 'defer' is a real PreToolUse value, but since CC v2.1.89 its semantics are "pause this tool call for external resumption" (headless resume) — never "abstain". Interactive sessions have nothing to resume the paused call, so the tool orphaned. Pre-2.1.89 builds ignored the unknown value, which is why the hook worked when it shipped and broke later. The fix is the two-branch pass-through contract: - no context -> exit 0 with EXACTLY empty stdout - memory nuggets present -> hookSpecificOutput with hookEventName + additionalContext ONLY (the documented shape; plan-tune Layer 8 memory injection ships through this branch and keeps working) defer() is renamed passThrough() so the function says what it does, and docs/spikes/claude-code-hook-mutation.md's protocol contract (cited by the hook header) is corrected in the same commit — it taught '"defer" — let permission flow continue' and was the reintroduction vector. Test contract rewritten in the same commit (13 assertions across 3 files, verified fail-first against the unfixed hook): pass-through paths assert exact-empty stdout (a garbage/partial write cannot slip past an optional-chained parse), the nugget path asserts permissionDecision is ABSENT while additionalContext survives, and a new tripwire asserts no non-deny path ever puts the string "permissionDecision" on stdout. The deny (auto-decide) and Conductor prose-redirect paths are unchanged. Deployment: no migration needed — settings.json points at the absolute bash shim which execs the .ts live; /gstack-upgrade delivers the fix. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(one-way-doors): unify credential noun net + wire it into the runtime (#2024) Library fix: revoke/reset/rotate now share ONE noun alternation (api key, token, secret, credential, access key, password) with optional plural s?. Pre-fix leaks: "reset my secret", "reset my access key", "revoke my secret" (mismatched per-verb lists) and every plural form ("rotate the credentials", "revoke all tokens" — \b(...)\b cannot match a trailing s). Runtime wiring — the regexes could never fire in production before: - gstack-question-preference --check gains --summary-stdin: the question text pipes via stdin (never argv — summaries carry quotes/newlines/shell metacharacters) and feeds isOneWayDoor alongside the id, so an ad-hoc destructive question with a stored never-ask preference now forces ASK_NORMALLY. Empty/absent stdin keeps exact id-only semantics. - question-preference-hook falls back to classifyQuestion(question text) when the registry lookup misses, so unregistered destructive questions pass through to a human instead of auto-deciding. - question-tuning resolver prose shows the piped form (SKILL.md regen lands in the wave's release commit). Tripwires (verified fail-first): full verbs x nouns x singular/plural matrix with the #2024 repro rows, benign-summary no-over-match rows, stdin transport survival (quotes/newlines), empty-stdin fail-safe, and hook fallback both directions (destructive -> pass-through, benign -> deny). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(design): loud integer-flag contract for --count/--retry/--timeout (#2032) design variants --count abc silently generated ZERO variants and exited 0: parseInt(NaN) flowed through Math.min into the generation loop bound. The same NaN class was live on the two sibling flags in the same file: --retry abc made generate() a silent no-op (attempt <= NaN never true, null output, exit 0) and --timeout abc killed the serve board ~immediately (setTimeout(NaN)). New design/src/flag-utils.ts: parseIntFlag (pure, unit-testable) + normalizeIntFlag (CLI wrapper). Contract matches the --viewports precedent (error loudly on nonsense — these commands spend real image-API money, a silent fixup hides typos from calling agents): undefined -> default; bare flag/empty/non-integer ("3.7" rejected, not truncated)/below-min -> exit 1 with usage hint; above-max -> clamp with stderr warning. --count normalizes at the variants() consumption site so programmatic callers are covered, with the ceiling derived from STYLE_VARIATIONS.length instead of a magic 7; the CLI passes the raw flag through (a pre-parseInt would truncate "3.7"). Tripwires live in test/design-flag-utils.test.ts — deliberately under test/, not design/test/, which is invisible to the bun test glob, TEST_ROOTS, and every workflow (wiring design/test/ into CI is a captured TODO). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(gbrain): thin-client state — remote-MCP brains no longer classify as broken-config (#2051) A thin client (remote-HTTP MCP brain, no local engine by design) probed `gbrain sources list`, which gbrain's dispatch guard REFUSES on thin clients (exit 1, no recognized error string), so the classifier fell to its defensive broken-config default and every suppression gate silently hid brain-aware blocks from exactly the users on a shared team brain. New 'thin-client' state, detected PRE-probe from gbrain's own remote_mcp config marker via the existing gbrainConfigPath() helper (mirrors gbrain's isThinClient(); honors GBRAIN_HOME; zero network, immune to error-string drift), with a /thin[- ]client/ stderr backstop in the probe catch. Remote reachability is deliberately NOT probed by the classifier — that is the #1964 pathology; gbrain calls degrade gracefully at use time, and the detect JSON says so honestly (gbrain_thin_client: {probed: false}). The state is admitted at every suppression gate — gstack-gbrain-detect --is-ok (drives setup + gbrain-refresh), gen-skill-docs' detection override, gstack-config gbrain-refresh — while the sync stages (code/memory/dream) SKIP with an accurate reason: code indexing runs on the brain server, memory syncs via the remote brain's artifacts pull. The two consumer classes need opposite answers, which is why this is a distinct state and not a skip-the-probe special case. sync-gbrain Step 1.5 and setup-gbrain prose route thin-client to proceed, never into broken-config remediation. detectMcpMode secondary generalization: url-match against the config's remote_mcp.mcp_url (deterministic — gbrain mounts at the generic /mcp path) -> name pattern gbrain[-_]* -> stdio command token; gbrain_mcp_mode stays a 3-value enum. Tripwires: end-to-end --is-ok exits 0 on a thin-client fixture AND still exits 1 on broken-config (the gate didn't widen); pre-probe + stderr-fallback classifier paths; 4 detectMcpMode identification cases incl. a non-matching url that must NOT false-positive. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * release: v1.60.0.0 — regen SKILL.md, VERSION, CHANGELOG, TODOS follow-ups - Regenerate all SKILL.md from templates (question-tuning --summary-stdin prose from #2024, context-restore branch preference from PR #2054, sync-gbrain/setup-gbrain thin-client prose from #2051) + llms.txt. - VERSION + package.json -> 1.60.0.0 (bin/gstack-next-version, queue-aware: #1815 claims 1.59.0.0, #2213 claims 1.59.1.0). - CHANGELOG release summary + itemized entry crediting @jbetala7 (x3) and @mvann. - TODOS.md: three eng-review follow-ups (design/test CI wiring + documented pre-existing retry-after flake, /context-save worktree identity, gbrain reindex-in-place conditional on the new drift log). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(resolvers): compress --summary-stdin preamble prose to fit parity budget; re-bless ship goldens The v1.57.7.0 parity suite caps investigate's generated size at 1.09x baseline; the #2024 question-tuning prose (duplicated into every tier->=2 skill) tipped it to 1.092. Compressed to a single inline command + short pointer (the full rationale lives in bin/gstack-question-preference's header and the one-way-doors module docs). Ship goldens re-blessed against the final resolver text (conscious template-change acknowledgment, per the golden-file regression contract). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(e2e): office-hours-spec-review turn budget fits the carved skill layout (#2473) The test failed deterministically with error_max_turns at 9 turns on main and this branch alike (CI attempt logs + local main repro). Root cause from the failing transcript: the Spec Review Loop content is carved out of office-hours/SKILL.md into office-hours/sections/, so the agent needs discovery hops (grep SKILL.md -> ls sections/ -> read the section) before it can write — 8 tool turns + the closing text turn = 9 > the 8-turn budget, which predates the carve. Observed failures wrote a CORRECT summary on tool turn 8 and died on the closing turn. maxTurns 8 -> 12. Verified: PASS locally post-fix (7 turns this run — the extra headroom absorbs discovery-path nondeterminism). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(e2e): review-dashboard-via session budget survives runner contention (#2473) The test failed on CI (and its baseline run) with the timeout signature: 0 turns, $0.00, exactly 183s, 3/3 attempts — the spawned claude -p session never emitted a single stream event before the 180s inner timeout. The file's tests run concurrently on one runner; session startup queues behind sibling sessions, and this test had the tightest budget in the file (the 240s-budget tests in the same job passed). A clean local run takes 270s wall for 4 turns, confirming 180s was too tight even without contention. Inner timeout 180s -> 300s; outer bun timeout 240s -> 360s to keep headroom over the inner budget. Verified: PASS locally post-fix (4 turns, 270s). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(e2e): retro-base-branch session budget survives runner contention (#2473) Same class as review-dashboard-via, one test over in the same file: /retro is a long multi-step flow whose clean pass measures 225-239s — a coin flip against the 240s inner budget. First CI run passed at 225s; the rerun timed out at the 240s line on all 3 attempts (exitReason "timeout"); the local verification run passed at 239s, ONE second under the old cap. Inner timeout 240s -> 360s; outer bun timeout 300s -> 480s for headroom. Verified: PASS locally post-fix (17 turns, 239s). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Jayesh Betala <jayesh.betala7@gmail.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: Michael Vann <9221873+mvann@users.noreply.github.com>
167 lines
6.0 KiB
TypeScript
167 lines
6.0 KiB
TypeScript
/**
|
|
* One-Way Door Classifier — belt-and-suspenders safety layer.
|
|
*
|
|
* Primary safety gate is the `door_type` field in scripts/question-registry.ts.
|
|
* Every registered AskUserQuestion declares whether it is one-way (always ask,
|
|
* never auto-decide) or two-way (can be suppressed by explicit user preference).
|
|
*
|
|
* This file is a SECONDARY keyword-pattern check for questions that fire
|
|
* WITHOUT a registry id (ad-hoc question_ids generated at runtime). If the
|
|
* question_summary contains any of the destructive keyword patterns, treat
|
|
* it as one-way regardless of what the (absent or unknown) registry entry says.
|
|
*
|
|
* Codex correctly pointed out (design doc Decision C) that prose-parsing is
|
|
* too weak to be the PRIMARY safety gate — wording can change. The registry
|
|
* is primary. This is the fallback for questions not yet catalogued, and it
|
|
* errs on the side of asking the user even when tuning preferences say skip.
|
|
*
|
|
* Ordering
|
|
* --------
|
|
* isOneWayDoor() is called by gstack-question-sensitivity --check in this
|
|
* order:
|
|
* 1. Look up registry by id → use registry.door_type if found
|
|
* 2. If not in registry: apply keyword patterns below
|
|
* 3. Default to ASK_NORMALLY (safer than AUTO_DECIDE)
|
|
*/
|
|
|
|
import { getQuestion } from './question-registry';
|
|
|
|
/**
|
|
* Keyword patterns that identify one-way-door questions when the registry
|
|
* doesn't have an entry for the question_id. Case-insensitive substring match
|
|
* against the question_summary passed into AskUserQuestion.
|
|
*
|
|
* Additions here should be conservative — a false positive means the user
|
|
* gets asked an extra question they might have preferred to auto-decide.
|
|
* A false negative could mean auto-approving a destructive operation.
|
|
*/
|
|
const DESTRUCTIVE_PATTERNS: RegExp[] = [
|
|
// File system destruction
|
|
/\brm\s+-rf\b/i,
|
|
/\bdelete\b/i,
|
|
/\bremove\s+(directory|folder|files?)\b/i,
|
|
/\bwipe\b/i,
|
|
/\bpurge\b/i,
|
|
/\btruncate\b/i,
|
|
|
|
// Database destruction
|
|
/\bdrop\s+(table|database|schema|index|column)\b/i,
|
|
/\bdelete\s+from\b/i,
|
|
|
|
// Git / VCS destruction
|
|
/\bforce[- ]push\b/i,
|
|
/\bpush\s+--force\b/i,
|
|
/\bgit\s+reset\s+--hard\b/i,
|
|
/\bcheckout\s+--\b/i,
|
|
/\brestore\s+\.\b/i,
|
|
/\bclean\s+-f\b/i,
|
|
/\bbranch\s+-D\b/i,
|
|
|
|
// Deploy / infra destruction
|
|
/\bkubectl\s+delete\b/i,
|
|
/\bterraform\s+destroy\b/i,
|
|
/\brollback\b/i,
|
|
|
|
// Credentials / auth — allow filler words ("the", "my") between verb and noun.
|
|
// Keep the noun alternation IDENTICAL across revoke/reset/rotate — a noun in
|
|
// one but not the others is a false-negative safety hole (#2024: "reset my
|
|
// secret" / "reset my access key" / "revoke my secret" leaked as two-way).
|
|
// Optional plural `s?` on the noun: \b(...)\b alone cannot match
|
|
// "credentials" / "tokens" / "passwords".
|
|
/\brevoke\s+[\w\s]*\b(api key|token|secret|credential|access key|password)s?\b/i,
|
|
/\breset\s+[\w\s]*\b(api key|token|secret|credential|access key|password)s?\b/i,
|
|
/\brotate\s+[\w\s]*\b(api key|token|secret|credential|access key|password)s?\b/i,
|
|
|
|
// Scope / architecture forks (reversible with effort — still deserve confirmation)
|
|
/\barchitectur(e|al)\s+(change|fork|shift|decision)\b/i,
|
|
/\bdata\s+model\s+change\b/i,
|
|
/\bschema\s+migration\b/i,
|
|
/\bbreaking\s+change\b/i,
|
|
];
|
|
|
|
/**
|
|
* Skill-category combinations that are always one-way even when the question
|
|
* body looks benign. Matches the ownership model: certain skill actions are
|
|
* inherently high-stakes.
|
|
*/
|
|
const ONE_WAY_SKILL_CATEGORIES = new Set<string>([
|
|
'cso:approval', // security-audit findings
|
|
'land-and-deploy:approval', // anything /land-and-deploy asks
|
|
]);
|
|
|
|
export interface ClassifyInput {
|
|
/** Registry id OR ad-hoc id; looked up first */
|
|
question_id?: string;
|
|
/** Skill firing the question (for skill-category fallback) */
|
|
skill?: string;
|
|
/** Question category (approval | clarification | routing | cherry-pick | feedback-loop) */
|
|
category?: string;
|
|
/** Free-form question summary — pattern-matched against destructive keywords */
|
|
summary?: string;
|
|
}
|
|
|
|
export interface ClassifyResult {
|
|
/** true = treat as one-way door (always ask, never auto-decide) */
|
|
oneWay: boolean;
|
|
/** Which check triggered the classification (for audit/debug) */
|
|
reason: 'registry' | 'skill-category' | 'keyword' | 'default-safe' | 'default-two-way';
|
|
/** Matched pattern if reason is 'keyword' */
|
|
matched?: string;
|
|
}
|
|
|
|
/**
|
|
* Classify a question as one-way (always ask) or two-way (can be suppressed).
|
|
* Returns {oneWay: false, reason: 'default-two-way'} only when no evidence of
|
|
* one-way nature is found. Errs conservatively otherwise.
|
|
*/
|
|
export function classifyQuestion(input: ClassifyInput): ClassifyResult {
|
|
// 1. Registry lookup (primary)
|
|
if (input.question_id) {
|
|
const registered = getQuestion(input.question_id);
|
|
if (registered) {
|
|
return {
|
|
oneWay: registered.door_type === 'one-way',
|
|
reason: 'registry',
|
|
};
|
|
}
|
|
}
|
|
|
|
// 2. Skill-category fallback (certain combos are always one-way)
|
|
if (input.skill && input.category) {
|
|
const key = `${input.skill}:${input.category}`;
|
|
if (ONE_WAY_SKILL_CATEGORIES.has(key)) {
|
|
return { oneWay: true, reason: 'skill-category' };
|
|
}
|
|
}
|
|
|
|
// 3. Keyword pattern match (catch destructive questions without registry entry)
|
|
if (input.summary) {
|
|
for (const pattern of DESTRUCTIVE_PATTERNS) {
|
|
if (pattern.test(input.summary)) {
|
|
return {
|
|
oneWay: true,
|
|
reason: 'keyword',
|
|
matched: pattern.toString(),
|
|
};
|
|
}
|
|
}
|
|
}
|
|
|
|
// 4. No evidence either way — treat as two-way (can be preference-suppressed).
|
|
return { oneWay: false, reason: 'default-two-way' };
|
|
}
|
|
|
|
/**
|
|
* Convenience wrapper for the sensitivity check binary.
|
|
* Returns true if the question must be asked regardless of user preferences.
|
|
*/
|
|
export function isOneWayDoor(input: ClassifyInput): boolean {
|
|
return classifyQuestion(input).oneWay;
|
|
}
|
|
|
|
/**
|
|
* Export patterns for tests and audit tooling.
|
|
*/
|
|
export const DESTRUCTIVE_PATTERN_LIST = DESTRUCTIVE_PATTERNS;
|
|
export const ONE_WAY_SKILL_CATEGORY_SET = ONE_WAY_SKILL_CATEGORIES;
|