* fix(hooks): fail open on oversized stdin instead of echoing truncated JSON (#2222)
run-with-flags.js capped stdin at 1MB but every fallthrough path still
echoed the truncated string to stdout. The harness parses hook stdout as
JSON, got a document cut mid-stream, and blocked the tool call — so any
Edit/Write with a >1MB hook payload was permanently blocked by every
registered pre-write hook, before ECC_HOOK_PROFILE / ECC_DISABLED_HOOKS
gating could run.
- Exit 0 with empty stdout (no opinion) when the stdin cap trips, before
any echo or gating logic.
- Flush stdout via write callback before process.exit: exiting right
after stdout.write() dropped everything past the ~64KB pipe buffer,
cutting even sub-cap pass-through payloads mid-JSON.
Regression tests cover the enabled, disabled, and missing-arg paths for
oversized payloads plus full echo of sub-cap >64KB payloads.
* fix(codex): stop emitting invalid exa url entry, align merge with connector policy (#2224)
The Codex MCP merge declared exa with a url key, but Codex's
[mcp_servers.*] TOML schema is stdio-only — the url key makes the
entire config.toml fail to load, bricking both the codex CLI and the
desktop app. Every install/update re-injected the line because the
urlEntry branch treated the broken entry as present.
- ECC_SERVERS now emits only the current default set per
docs/MCP-CONNECTOR-POLICY.md: chrome-devtools (stdio, command/args).
Retired servers (supabase, playwright, context7, exa, github, memory,
sequential-thinking) are never re-emitted; existing user-managed
entries are untouched.
- The merge now repairs the exact ECC-emitted broken form (url-only
exa entry) on every run so re-running the installer fixes broken
configs instead of preserving them. User stdio exa entries
(command + mcp-remote) are left alone.
- check-codex-global-state.sh requires chrome-devtools instead of the
retired set, and flags url-only exa entries with a repair hint.
Tests cover repair, re-run idempotence, stdio-entry preservation, and
no-retired-server emission in add, update, dry-run, and disabled modes.
* fix(hooks): never echo truncated stdin from Stop hooks (#2090)
Stop hooks follow the ECC pass-through convention (echo stdin on
stdout), but every echoing Stop hook capped stdin and echoed the capped
string. The Stop payload carries last_assistant_message, so a long
final assistant message produced a JSON document cut mid-stream on
stdout, which the harness reports as 'Stop hook error: JSON validation
failed' across the whole Stop chain.
Reproduced: a Stop payload with a >64KB last_assistant_message run
through run-with-flags + cost-tracker emitted exactly 65536 bytes of
invalid JSON (cost-tracker capped stdin at 64KB — far below realistic
Stop payloads).
- cost-tracker: raise the cap to 1MB (matching all other hooks) and
suppress the pass-through echo when stdin was truncated.
- check-console-log, stop-format-typecheck, desktop-notify: suppress
the echo when stdin was truncated; flush stdout before process.exit
so sub-cap payloads are not cut at the ~64KB pipe buffer.
- All hooks keep exiting 0 (fail-open); diagnostics go to stderr.
New stop-hooks-stdout test asserts the contract for every registered
Stop hook: stdout is empty or valid JSON, exit code 0 — for realistic
100KB payloads and oversized >1MB payloads, via the production runner
and via direct invocation. Updated the old hooks.test.js case that
codified the truncated-echo behavior.
* fix(hooks): dampen GateGuard fact-force repetition in long sessions (#2142)
In long autonomous sessions the fact-force gate produced 10+
near-identical 'state facts -> blocked -> restate -> retry' blocks in
one context window, which measurably raises the odds of the model
collapsing into a degenerate single-token repetition loop.
- Track a per-session fact_force_denials counter in GateGuard state
(merged max across concurrent writers, reset with the session, robust
to malformed on-disk values).
- The first GATEGUARD_FACT_FORCE_FULL_DENIALS denials (default 3) keep
the full four-fact block; later denials emit a condensed single-line
message that carries the denial ordinal, so consecutive denials are
structurally different and never textually identical.
- True retries of the same target remain allowed without re-prompting
(unchanged). Destructive-Bash and routine-Bash gates are unchanged,
as are the ECC_GATEGUARD=off / ECC_DISABLED_HOOKS escape hatches.
Eight new tests cover budget counting, condensed format, ordinal
advancement, retry pass-through, env tuning, malformed state, MultiEdit
dampening, and destructive-gate exemption.
* fix(hooks): keep security hooks able to block on oversized stdin (#2222)
Refine the truncation fail-open: instead of skipping the hook entirely,
the runner now suppresses only its own raw-echo when stdin was
truncated. The hook still executes and receives the truncated flag
(run() context / ECC_HOOK_INPUT_TRUNCATED), so config-protection keeps
blocking truncated protected-config payloads (its test requires exit 2)
while pass-through hooks fail open with empty stdout as before.
* style: apply repo formatter to touched hook files
* fix(gateguard): gate force/path git checkout as destructive
The destructive-command gate's `checkout` handler only flagged
`git checkout -- <path>`. It missed `git checkout --force` / `-f <branch>`
and `git checkout .`, all of which discard uncommitted working-tree changes,
so they bypassed the gate (once the once-per-session routine-Bash gate is
satisfied, they ran with no challenge). The sibling `switch` handler already
covers these force forms; mirror it for `checkout`.
* test(gateguard): document Test 7b force-checkout case
---------
Co-authored-by: bymle <229636660+bymle@users.noreply.github.com>
* feat(gateguard): add env knobs for routine bash gate + extra destructive patterns
The JS port of gateguard-fact-force has two bash gates: a destructive
gate (rm -rf, drop table, git push --force, etc.) that operators want
to keep, and a once-per-session routine gate that fires on the very
first bash invocation regardless of intent. Operators on hosts where
the routine gate is friction without signal (Cursor, OpenCode, etc.)
have been maintaining local patches that get clobbered on every plugin
update; the Python upstream gateguard-ai already exposes equivalent
config via .gateguard.yml.
Adds two env vars, both off-by-default so existing behavior is
preserved:
- GATEGUARD_BASH_ROUTINE_DISABLED — truthy values (1, true, on, yes,
enabled) skip the routine bash gate. Destructive gate is unaffected.
- GATEGUARD_BASH_EXTRA_DESTRUCTIVE — regex source string for additional
destructive patterns. Matches against the same quote-stripped,
subshell-flattened command the built-in DESTRUCTIVE_SQL_DD regex sees,
so a custom phrase inside $(...) or backticks is also caught. A
malformed regex is logged once to stderr and treated as not configured
rather than crashing the hook (hooks must never block tool execution
unexpectedly).
Twelve new tests pin both env vars (truthy aliases, falsy values, unset
baseline, destructive-gate-still-fires, alternation members, malformed
regex degrades safely, custom phrase inside command substitution).
Existing 2619/2619 tests still pass; eslint clean.
Fixes#2078
* fix(gateguard): reset extra-destructive warn-once gate when env value changes
Both reviewers (CodeRabbit + cubic) flagged that
extraDestructiveWarnLogged was never reset when GATEGUARD_BASH_EXTRA_DESTRUCTIVE
flipped from one invalid regex to a different invalid regex. The
sticky boolean meant a long-running process saw bad-pattern-a's
warning then silently swallowed bad-pattern-b's parse failure.
Fix: clear extraDestructiveWarnLogged whenever the cache key changes
(i.e. before the regex compile attempt). The warn-once-per-distinct-
pattern invariant now matches the per-key cache invariant.
Adds a same-process regression test via loadDirectHook() that spies on
process.stderr.write and asserts: same bad pattern warns once across
multiple invocations; switching to a different bad pattern emits a
second warning; switching to a valid regex emits zero warnings.
* fix(gateguard): rewrite routineBashMsg to use fact-presentation pattern
The imperative 'Quote user's instruction verbatim. Then retry.' phrasing
triggers Claude Code's runtime anti-prompt-injection filter, deadlocking
the first Bash call of every session. The sibling gates (edit, write,
destructive) use multi-point fact-list framing that the runtime accepts.
Align routineBashMsg with that pattern to restore the gate's intended
behavior without changing run(), state schema, or any public API.
Closes#1530
* docs(gateguard): sync SKILL.md routine gate spec with new message format
CodeRabbit flagged that skills/gateguard/SKILL.md still described the
pre-fix imperative message. Update the Routine Bash Gate section to
match the numbered fact-list format used by the new routineBashMsg().
P1: Gate message asked for raw production data records — changed to
"redacted or synthetic values" to prevent sensitive data exfiltration
P2: SKILL.md description now includes MultiEdit (was missing after
MultiEdit gate was added in previous commit)
P2: Session key pruning now caps __prefixed keys at 50 to prevent
unbounded growth even in theoretical edge cases
9/9 tests pass.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- isChecked() no longer calls saveState() — read-only operation
should not write to disk (was causing 3x writes per tool call)
- Test cleanup uses fs.rmSync(recursive) instead of fs.rmdirSync
which failed with ENOTEMPTY when .tmp files remained
9/9 tests pass.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
P1 (cubic-dev-ai): Test process PID differs from spawned hook PID,
so test was seeding/clearing wrong state file. Fix: pass fixed
CLAUDE_SESSION_ID='gateguard-test-session' to spawned hooks.
P2 (cubic-dev-ai): Pruning checked array could evict __bash_session__
and other session keys, causing gates to re-fire mid-session. Fix:
preserve __prefixed keys during pruning, only evict file-path entries.
9/9 tests pass.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
P1 bug reported by greptile-apps: MultiEdit uses toolInput.edits[].file_path,
not toolInput.file_path. The gate was silently allowing all MultiEdit calls.
Fix: separate MultiEdit into its own branch that iterates edits array
and gates on the first unchecked file_path.
9/9 tests pass.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Addresses reviewer feedback from @affaan-m:
1. State keyed by CLAUDE_SESSION_ID / ECC_SESSION_ID
- Falls back to pid-based isolation when env vars absent
- State file: state-{sessionId}.json (was .session_state.json)
2. Atomic write+rename semantics
- Write to temp file, then fs.renameSync to final path
- Prevents partial reads from concurrent hooks
3. Bounded checked list (MAX_CHECKED_ENTRIES = 500)
- Prunes to last 500 entries when cap exceeded
- Stale session files auto-deleted after 1 hour
9/9 tests pass.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
MultiEdit was bypassing the fact-forcing gate because only Edit and
Write were checked. Now MultiEdit triggers the same edit gate (list
importers, public API, data schemas) before allowing file modifications.
Updated both the hook logic and hooks.json matcher pattern.
Addresses coderabbit/greptile/cubic-dev: "MultiEdit bypasses gate"
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Destructive bash gate previously denied every invocation with no
isChecked call, creating an infinite deny loop. Now gates per-command
on first attempt and allows retry after the model presents the required
facts (targets, rollback plan, user instruction).
Addresses greptile P1: "Destructive bash gate permanently blocks"
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- GATEGUARD_STATE_DIR env var for test isolation (hook + tests)
- Exit code assertions on all 9 tests (no vacuous passes)
- Non-vacuous allow-path assertions (verify pass-through preserves input)
- Robust newline-injection assertion
- clearState() now reports errors instead of swallowing
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1. Use run-with-flags.js wrapper (supports ECC_HOOK_PROFILE, ECC_DISABLED_HOOKS)
2. Add session timeout (30min inactivity = state reset, fixes "once ever" bug)
3. Add 9 integration tests (deny/allow/timeout/sanitize/disable)
Refactored hook to module.exports.run() pattern for direct require() by
run-with-flags.js (~50-100ms faster per invocation).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
A PreToolUse hook that forces Claude to investigate before editing.
Instead of self-evaluation ("are you sure?"), it demands concrete facts:
importers, public API, data schemas, user instruction.
A/B tested: +2.25 quality points (9.0 vs 6.75) across two independent tasks.
- scripts/hooks/gateguard-fact-force.js — standalone Node.js hook
- skills/gateguard/SKILL.md — skill documentation
- hooks/hooks.json — PreToolUse entries for Edit|Write and Bash
Full package with config: pip install gateguard-ai
Repo: https://github.com/zunoworks/gateguard
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
