Commit Graph
484 Commits
Author SHA1 Message Date
haelyra 75322d5bb0 Merge reviewed PR #3675 2026-11-05 23:11:08 -05:00
haelyra 5d64ad64f3 Merge reviewed PR #3672
# Conflicts:
#	scripts/hooks/pre-bash-commit-quality.js
2026-11-05 23:10:59 -05:00
haelyra 912fc63c41 Merge reviewed PR #3671 2026-11-05 23:10:45 -05:00
haelyra 632aeb4d76 Merge reviewed PR #3663 2026-11-05 23:10:32 -05:00
haelyra ab10daba18 Merge reviewed PR #3870 2026-11-05 23:10:32 -05:00
haelyra a222e0091b Merge reviewed PR #3849 2026-11-05 23:10:32 -05:00
haelyra 22596737f7 Merge reviewed PR #3829 2026-11-05 23:09:32 -05:00
haelyra 759a3ba299 Merge reviewed PR #3822 2026-11-05 23:09:32 -05:00
haelyra 44de2e5996 Merge reviewed PR #3814 2026-11-05 23:09:32 -05:00
Gaurav DubeyandClaude Opus 5.5 f0eee4b543 fix(hooks): redact JWTs joined to an underscore-prefixed label
The JWT chain scanner only accepted a header at the start of a segment or
after `-`, so `session_<JWT>` reached the audit and cost logs unredacted.
Treat `_` as a prefix boundary too and cover it in the tests.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 03:30:52 +00:00
L4XB fee3d08666 fix(hooks): drop line continuations before checking text after a commit here-document
In double quotes Bash drops a backslash-newline before it expands
anything, so a tail of `$\<newline>HOME` after the substitution's `)` is
`$HOME` and expands. The expansion check read the tail with the
continuation still in it and saw an escaped newline, so the hook
validated `fix: a$HOME` with no warning. Continuations are now dropped
first, while other escapes stay for the check: `\$\<newline>HOME` is
still the literal `$HOME`.
2026-11-05 14:36:26 +01:00
L4XB 2ff19fafa0 fix(hooks): read text after a commit here-document's substitution
In `-m "$(cat <<'EOF' … EOF\n)."` Bash drops the body's trailing newlines
and adds the period, so Git records `fix: update input.`, but the hook
checked only the here-document and missed the trailing-period warning.
Read the rest of the quoted value after the substitution's `)` and add
it to the message as double-quoted text. Commands or an expansion after
the here-document make the message unverifiable, as an expansion in an
unquoted body already does. The here-document reading moves into
readHeredocMessage, which also returns the Bash 3.2 note.
2026-11-05 13:22:57 +01:00
L4XB 34e41430b1 perf(hooks): read the dev guard's segment queue by index
Since expanded here-document segments are queued too, a long substitution puts every segment in the queue, and shift() copied it each time: 130,000 segments took about 20 s, past the hook timeout. An index keeps the walk linear (under 0.3 s).
2026-11-05 13:14:48 +01:00
L4XB 30eb570117 fix(hooks): read NUL-ended delimiters, Bash blanks before #, and long bodies
Bash ends a decoded $'...' string at its first NUL, so `cat <<$'EOF\0X'`
ends at the line EOF, but the splitter looked for EOF\0X and swallowed
the commands after the body. A carriage return or a no-break space is
not a blank to Bash, so `echo foo\r# && npm run dev` runs the dev
server, but the splitter read the # as a comment. And spreading a long
substitution's segments into push() threw RangeError, which the hook's
catch turned into an allow. Truncate the decoded part at the NUL, use
Bash's blanks for word starts, and append the segments one at a time.
2026-11-05 13:07:21 +01:00
L4XB 31866936b9 fix(hooks): keep printf arguments literal, model descriptor copies, charge expansion
printf decoded escapes in %s arguments too, so `printf '%s' 'gi\t push
--no-verify' | sh` read as `gi<tab> push` and passed, while the shell
reads `gi\t` as `git`. Escapes are now decoded in the format and in %b
arguments only. `1<&3` and the move `1>&3-` copy a descriptor like
`1>&3`, so restoring a saved stdout is followed. The format-reuse loop
charges the work budget before each piece, so a short command cannot
expand into a huge string. The bash-backed tests now run what the shell
reads with a stub git, which also sees how the shell unescapes words.
2026-11-05 12:59:29 +01:00
L4XB bf71cdfff1 fix(hooks): follow each producer's descriptors into the shell
A group or pipeline producer counted whatever its redirections said, so
`{ echo 'git push --no-verify' >/dev/null | cat; } | bash` was blocked
although bash reads nothing, and printf filled no %s, so
`printf 'git %s --no-verify\n' push | sh` got through. shell-scan now
keeps a redirection's descriptor, and a stage's output counts only when
its descriptors, the stages after it and an `exec` earlier in its group
take it to the shell; an `exec` is carried only where it adds output.
printf fills %s, %b and %c and reuses its format; other conversions are
read like an unmodeled command. The header states what the model covers.
2026-11-05 12:27:55 +01:00
L4XB ae681a2a66 Merge remote-tracking branch 'origin/main' into fix/block-no-verify-group-piped-into-shell 2026-11-05 12:18:59 +01:00
L4XB a3ced7db06 fix(hooks): keep no structured tool result in activity history
The tracker serialized any structured result with JSON.stringify before
redaction, so an encoding nested in it, such as a double-escaped JSON
token, reached tool-usage.jsonl whole, and Claude Code's Bash stdout went
in as text. Keep text only from the adapter's tool_output, as main did,
and from Claude Code's tool_response only the sizes of stdout and stderr
and its interrupted and image flags. Any other structure is left out.
2026-11-05 11:35:43 +01:00
L4XB 6b9ff09542 Merge remote-tracking branch 'origin/main' into fix/hooks-read-tool-response
# Conflicts:
#	scripts/hooks/hook-input.js
#	tests/hooks/hook-input.test.js
2026-11-05 11:33:26 +01:00
Rahul Selvaraj 846a561a7b fix(hooks): drop classifier notices from LLM summary input
The safety-classifier notice filter only covered the mechanical summary.
When generateSessionSummary runs (low context or message interval),
extractConversationText read the raw transcript and passed the notice to
the LLM as a user turn, so it could still reach saved context.

Move the check into one shared isClassifierNotice() in
scripts/lib/llm-summary.js and use it in both userMessageText() and
extractConversationText(). Add LLM-path regression tests, and split the
session-end classifier-notice tests into small functions (<50 lines).

Refs #3867

Assisted-by: Claude <noreply@anthropic.com>
2026-11-05 18:06:51 +08:00
haelyra 94d2c659ba fix(hooks): scan substitutions nested in expanded here-document bodies
The dev-guard half of 7632669d from #3735: segments that the splitter
reads from an expanded here-document body are scanned again, so a dev
command in a substitution nested inside one is still found.

(split from commit 7632669d28)
2026-11-05 11:05:56 +01:00
L4XB 4ae1f0d812 Merge remote-tracking branch 'origin/main' into fix/commit-quality-subject-line 2026-11-05 10:49:41 +01:00
L4XB 8c67067582 fix(hooks): join continued lines of a commit here-document as bash does
In an unquoted here-document, Bash removes a backslash-newline before Git
receives the message, so `fix: \` followed by `Update input.` commits
`fix: Update input.`, and a delimiter line right after a continued line
does not end the body. Read the body that way, keep `<<-` from stripping
the tabs of a continued line, and drop the backslash before $, ` and \.

A quoted body stays literal, as Bash 4 and later and zsh read it. Inside
"$(...)", Bash 3.2 joins its lines too, so the hook now notes when that
would change the subject.
2026-11-05 10:49:40 +01:00
haelyra 950f8ce0f3 fix(hooks): validate Bash commit here-document substitutions
The commit-quality half of 7632669d from #3735: a single-quoted -m
message keeps its backslashes, and an unquoted here-document whose body
Bash would expand yields an advisory that the subject cannot be validated
from the literal command.

(split from commit 7632669d28)
2026-11-05 10:43:53 +01:00
Gaurav DubeyandClaude Opus 5.5 71084e0555 fix(hooks): redact JWTs joined to a hyphenated prefix
The lookbehind added to keep the JWT scan linear also skipped tokens right
after a `-`, so `--cookie "session=jwt-<JWT>"` reached the logs unredacted.
Scan each `[A-Za-z0-9_.-]` run once instead, checking every dot segment for
a header at its start or after a `-`, decoding at most once per segment so
long `ey-ey-...` runs stay linear.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-05 03:31:50 +00:00
Rahul Selvaraj a08d5da8c9 fix(hooks): skip safety-classifier notices in session summaries
When a response is stopped by the safety classifier, the harness records
a notice ("Your response above was stopped by a safety classifier ...")
as a user entry in the transcript. session-end.js kept it as a user
message, so it was written under "### Tasks" and re-injected by
session-start.js on the next session.

userMessageText() now drops entries that start with that notice, next
to the existing HARNESS_NOISE filter. User messages that only mention
the phrase are kept, since the match is anchored to the start.

Fixes #3867

Assisted-by: Claude <noreply@anthropic.com>
2026-11-04 19:29:32 +08:00
Gaurav DubeyandClaude Opus 5.5 4d3e66e0ab fix(hooks): redact joined-fragment secret values and make JWT scan linear
- Replace the secret=/api_key= value regex with a single-pass, quote-aware
  scanner so the whole Bash word is redacted when quoted and unquoted
  fragments are joined (e.g. --secret='prefix-'suffix), while a value inside
  an enclosing quoted string stops at that string's closing quote.
- Searching for the keyword itself (grep -n "secret =" file,
  rg 'api_key:' dir) no longer redacts the rest of the command.
- Use a lookbehind instead of \b before the JWT header so long dot-free
  ey-ey-... runs are scanned in linear time instead of quadratic.
- Add regression tests for joined fragments, keyword searches, and the
  ey- performance case.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-04 03:41:05 +00:00
Gaurav Dubey 0b57406e57 fix(hooks): redact spaced-header JWTs and escaped or $'...' secret values
Match JWT headers that start with ey or ew (whitespace after the opening
brace) and keep non-eyJ matches only when the header does not decode to
an object with an alg field. Parse secret= / api_key= values with escaped
double quotes, $'...' quoting and backslash escapes, and redact an
unterminated quoted value to the end of the command.

Refs #3846
2026-11-03 04:19:37 +00:00
Gaurav Dubey 08fb3c8a1c fix(hooks): redact bare API keys, JWTs and PEM blocks in bash command logs
sanitizeCommand only redacted keyword- or flag-shaped secrets, so a bare
Anthropic/OpenAI sk- key, a JWT, a PEM private key block, or a secret= /
api_key= / x-api-key: value was written verbatim to bash-commands.log and
cost-tracker.log. Add value-shape patterns for these and keep the key name
and separator for assignments so the log stays readable.

Refs #3846
2026-11-03 04:12:32 +00:00
Muhammad Mirza 3e7b4d74b9 fix(continuous-learning): sync Stop hook and fail-closed delivery marker
Address bot review on the Stop delivery path: the stop:evaluate-session
registration no longer carries async (an async Stop registration cannot
block), so delivery is synchronous, and the metadata fingerprint for the
changed entry is regenerated with the repo's own function; the delivery
marker is now claimed atomically with exclusive create and any write
failure fails closed instead of delivering without once-per-session
protection; the skill doc now marks the shell entry as counting-only,
requires the JavaScript evaluator through the plugin hooks for delivery,
and clarifies that Stop fires whenever Claude finishes responding; test
spawn helpers no longer coerce a failed spawn to exit 0.

Test plan:
- tests/hooks/evaluate-session.test.js: 25 passed, 0 failed (2 new:
  marker write failure skips delivery, registration is synchronous);
  pristine comparison: 22 passed, 3 failed (delivery, marker, registration)
- tests/hooks/hooks.test.js: 260 passed
- tests/hooks/stop-hooks-stdout.test.js: 48 passed
- tests/hooks/cursor-hook-dispatchers.test.js: 27 passed
- tests/integration/hooks.test.js: 27 passed
- scripts/ci/check-unicode-safety.js: passed
2026-10-31 23:36:38 +07:00
Muhammad Mirza Kurniawan f82eb1414b fix(continuous-learning): deliver v1 Stop nudge via native Stop contract behind explicit opt-in
The v1 evaluator computed the learning signal but wrote it to stderr, which Claude Code never forwards to the model, so the learned-skills folder was never populated through this path.

Delivery now follows the maintainer-endorsed shape: an explicit stop_nudge_opt_in flag (default off, so existing installs are unchanged), the native Stop block contract (decision block plus reason) instead of plain stdout text, at most one delivery per session via a temp-dir marker, Stop-loop protection via stop_hook_active, and delivery only for sessions with a registered lease from SessionStart.

Tests: 7 new evaluator tests (opt-in off, no lease, one valid block then silence on repeat, stop_hook_active, short session, non-Stop event, missing session id). Evaluator suite 23/23 with the fix, failing on pristine; hooks suite 260/260; Stop stdout contract suite 48/48.

Limits stated plainly: end-to-end delivery in a live Claude Code session is not certified from this host (unit-level spawn plus parse only), and the fix ships inert by default until a user opts in.
2026-10-31 22:40:13 +07:00
Iain f914d617fd fix(hooks): accept the ! breaking-change marker in commit-quality 2026-10-30 22:46:01 +00:00
Quinn O'Donnell 00a8fe96f8 fix(hooks): skip stdin listeners on require and match exact tsc paths in post-edit-typecheck
config-protection.js and post-edit-typecheck.js attached process.stdin
listeners at module scope. tests/hooks/hook-input.test.js requires
config-protection.js, so that test never exits while stdin stays open.
Attach the listeners only when the script runs directly
(require.main === module), as stop-format-typecheck.js and quality-gate.js
already do.

post-edit-typecheck.js picked tsc diagnostics with line.includes(candidate),
so editing a root index.ts reported the errors of src/index.ts, and a
Windows relative path (src\index.ts) never matched tsc's forward-slash
output. Compare the file at the start of each diagnostic instead, the same
check diagnosticMatchesFile() does in stop-format-typecheck.js.

Refs #3821
2026-10-30 12:29:32 -04:00
rabbit-collabandClaude Opus 5.5 21d651cb8e fix: exit hook runners whose parent process is gone
On Windows, Claude Code kills an overrunning hook by killing the bash.exe
wrapper; the node.exe runner underneath survives. If another process still
holds the write end of the runner's stdin (a handle inherited by a process
spawned at the same moment), the runner never sees EOF and waits forever.
Orphaned runners were observed living 3-18 hours.

Add scripts/hooks/hook-watchdog.js and start it from the four hook entry
points (plugin-hook-bootstrap, run-with-flags, posttooluse-dispatcher,
lifecycle-hook-bootstrap). It exits the process when the parent PID is gone
(Windows) or the process was re-parented (POSIX), polled every 2s, or when a
hard deadline passes (330s, above the longest hooks.json timeout, or an
earlier inherited ECC_HOOK_DEADLINE_MS). Timers are unref'd so a finished
hook is never kept alive.

The regression test reproduces the leak with a detached runner whose stdin
write end is held by an unrelated process; it fails without the watchdog
(runner still alive after 8s) and passes with it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-30 03:08:18 -07:00
haelyra 3dca6e2e88 fix(hooks): preserve provider conversation identity under inherited environments
Restore the shipped payload-first contract from #3464/#3495 and the explicit source #3755 scope clarification. Two provider conversations must retain distinct IDs despite an inherited registered ECC parent ID. Normal and ambient producer24 tests, canonical resolver10 and independent differential review pass. Keep native importer guards; explicit provider/native correlation is queued separately.
2026-10-29 18:57:29 -07:00
haelyra 6cd41995f4 fix(hooks): attribute native activity to the registered ECC session
Verify review discussion4419348312 against actual native producer/importer behavior. Prefer the independently sanitized ECC_SESSION_ID for the ECC-owned metrics feed, retain payload then legacy fallback for standalone hooks, and leave sibling hooks unchanged.

Actual Node producer plus read-only cached native binary reproduces zero imported metrics before the fix and exactly one tool/file/log after repeated sessions/status commands. Four producer regression controls and normal/adversarial inherited-env suites pass22/22. Focused coverage96.47percent lines and91.47percent branches; parent independent source review passed.
2026-10-29 17:43:55 -07:00
haelyra fc549b6372 fix: preserve Windows rule examples and conservative summary budgets
Address #3809 review regressions for CRLF code fences and inferred context capacity. Reproduced unit and actual Stop-hook failures; verified llm-summary38, Stop14, Copilot37 and independent code/security review. Keep confirmed model/ECC context authority, native budget scheduling and unknown capacity separate.
2026-10-29 17:27:56 -07:00
haelyra 14ba1e211f maint: integrate reviewed contribution #3777 2026-10-29 11:27:40 -07:00
haelyra 291635f7f9 maint: integrate reviewed contribution #3776 2026-10-29 11:27:01 -07:00
haelyra ff9095f6f7 maint: integrate reviewed contribution #3775 2026-10-29 11:26:59 -07:00
haelyra 65d83f9290 maint: integrate reviewed contribution #3669 2026-10-29 11:25:30 -07:00
haelyra 9aed578c67 fix: integrate symlink-aware GateGuard exemptions from #3726 2026-10-29 11:20:48 -07:00
haelyra 8e00137b04 fix: integrate observer identity and lease repair with canonical root matching 2026-10-29 11:19:43 -07:00
Brian La Plume 4a76f78411 fix(gateguard): expand unique sudo long-option prefixes
getopt_long accepts a unique prefix, so sudo --use root rm -rf build is
--user root and the resolver read root as the command. Expand unique
prefixes from sudo's long option table before the value/non-exec checks.
--help joins the non-executing modes.
2026-10-28 12:28:55 -07:00
Brian La Plume 2a3ed89600 refactor(config-protection): build targetPaths without mutation 2026-10-28 12:14:38 -07:00
Brian La Plume a46e36d488 fix(gateguard): sudo env assignments between options, missing value flags
sudo accepts VAR=value between its options (parse_args.c is_envar), so
sudo FOO=1 -u root rm -rf resolved -u as the command. Keep reading options
past assignments. Add sudo -R/--chroot, -a/--auth-type, -c/--login-class
and doas -a as value flags, and stop a short-cluster scan at any unknown
letter, so sudo -R/live rm -rf no longer reads the l in /live as -l.
doas -C only checks config, so it is non-executing; the existing doas -C dd
case moves to the passive list.
2026-10-28 12:13:25 -07:00
Brian La Plume 7253c8a261 fix(gateguard): treat sudo list/validate/edit modes as non-executing
sudo -l/--list, -v, -K, -V and -e/--edit (and doas -L) do not run the
command operand, so sudo -l rm -rf build was denied as destructive. The
privilege-wrapper resolver now reports no executable command for those
modes. Short clusters stop at the first value flag, so sudo -ul rm -rf
(user l) stays destructive.
2026-10-28 11:54:13 -07:00
Brian La Plume 646b4d1442 fix(gateguard): classify rm/Git behind sudo/doas/env/command wrappers
isDestructiveRm/isDestructiveGit keyed on argv[0], so sudo rm -rf,
command rm -rf and env git reset --hard read as calls to the wrapper and
were allowed once the routine shell gate was satisfied. Run both checks on
the unwrapLeadWrappers argv too, the resolution the dd and sh -c paths
already use. Overlaps #2832, which also reworks sh -c parsing and has
conflicts with main; this is the minimal rm/Git part.
2026-10-27 11:06:20 -07:00
Brian La Plume 1d55d690b9 fix(run-with-flags): fail closed for oversized Bash GateGuard input
Fixes #3762. pre:bash:gateguard-fact-force was missing from
FAIL_CLOSED_ON_TRUNCATION_HOOKS, so a Bash payload over the stdin cap
exited 0 while the Edit and PowerShell GateGuard ids blocked. Share one
GateGuard id set for the fail-closed list and the off-switch branch, and
add runner-level tests for all three ids plus each off switch.
2026-10-27 11:03:36 -07:00
Brian La Plume ed2f02dd06 fix(config-protection): check MultiEdit edits[].file_path targets
Fixes #3761. config-protection only read tool_input.file_path, so a MultiEdit
with the config path inside edits[] edited an existing ruff.toml/.eslintrc
without the block. Check every effective target and block if any is an
existing protected config.
2026-10-27 11:03:02 -07:00