/simplify over a97efb6..HEAD (the plan_version 1.9 / trial-4 delivery).
- coordinator-contract: engine names come from engine-findings ENGINES;
one markedMajorCodeReview predicate under both lowering checks;
isEngineFinding everywhere; the unreachable branch (c) of
illegalBriefLowering folded into (e).
- armB workflow: RULE_KEYS = Object.keys(RULE_TIERS); the engine map is a
literal pinned equal to ENGINES by the workflow test.
- plan-schema: usesFilesGrammar() is the one 1.9 check (validator, sweep,
testFirstFiles, stepTestsOnlyFromFields); opensEntry built on opensChunk.
- plan-validator: one issue builder for the Files and Test first grammar.
- plan-scope-sweep: the 1.9 and the 6.2.0 reader are one if/else.
- artifact-commit: TRAILER_RE/trailerProblem no longer exported (no
importer); the order comment says the CLI finds the repo root first.
- tests: the lock drivers in session-id-isolation (d) run side by side per
mode (~100 s -> ~30 s); a shared artifact-repo helper; severityRank and
extractFindingsBlock reused; childEnv(env) without a spread; one copy of
the PLAN_VERSION_CURRENT check.
Plan readers: validator errors/warnings, plannedPaths, fieldPaths,
testFirstFiles and stepTestsOnlyFromFields compared byte for byte against
HEAD over 510 plans / 1692 steps plus 210 synthetic 1.7-1.9 cases: same.
Suite 2384 (2382/0/2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
npm test now preloads tests/helpers/no-session-id.mjs, which deletes CLAUDE_CODE_SESSION_ID before any test file loads, and the 18 files that spread process.env into a child use childEnv() instead (23 sites). A live session's stop guard is no longer pointed at a temp-repo lock (S133).
engines stays >=18: --import exists from Node 18.18/20.6, and the quoted test glob already needs Node 21 (criteria-runner NODE_GLOB_MAJOR), so the real floor does not move.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Round 9 (0f400d3..a10018f, WARN: 0 BLOCKER, 12 MAJOR): seven findings and
three brief notes, by operator choice. Each finding began with a test that
failed on a10018f on its assertion; suite 2230 (2228/0/2).
- A check refused for its comment (a quote, $, backtick or backslash) keeps
its command and its reason, and every reader refuses it out loud: a nested
## Verification bullet stays a criterion (PLAN_VERIFICATION_NOT_RUNNABLE)
and a brief SC warns (BRIEF_SC_NOT_RUNNABLE). It was folded into a
sub-point or read as prose, a regression from a10018f. Readers that took a
command as runnable (the end-to-end lists) skip a refused one.
- The verdict gate reads the last fenced block's info string and body from
one reading, and exits 2 unless the info string is exactly json: a last
block opened as ```json {x} held a BLOCKER the gate passed with exit 0
(also in 6.3.0). A last block never closed is exit 2 too.
- One fence reader (findings-schema fencedBlocks) for the gate and every
trailing-json reader: a fence closes only on a run at least as long as its
opener, as in Markdown, so a four-backtick example of a json block is one
block; CRLF and an indented fence read alike in the gate and the readers.
- Files: a description runs on past a comma and onto the next line until a
new entry starts (a list item on a new line, or a backticked path), and a
plain path followed by a colon starts its description. Measured over all
939 Files: fields in the .md files under the marketplace and the test repo
(560 of them in the 48 plan.md files outside worktrees): 0 read
differently, tests-only changed in 0.
- The test lock compares --cmd by its words, so other blanks between the
same words are the step's command.
- release-check decides "two files" on real paths: one review.md reached
through a symlinked --repo is one file.
- Brief notes: red proof's stopped control run has its own test (green at
once, red with the branch deleted); the two tests that assumed jest is not
installed run with a PATH that finds only git (red on a10018f with a jest
on PATH, green now); the Files: reader's doc states the measured counts
(520 fields in 48 plan files at rounds 7-8, not "182 plans"; 560 now).
Not in this round (operator 2026-10-11): a144e9ce, 1dc2e785, dc3a467e,
2fa88853, 26873fa5.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Round 8 (0f400d3..29b4ac9, BLOCK: 1 BLOCKER, 12 MAJOR, 1 MINOR). Each fix
began with a test that failed on 29b4ac9 (13 tests, all red there); suite
2221 (2219/0/2).
- BLOCKER: a backticked check whose trailing comment holds a quote, $,
backtick or backslash is refused, not dropped. The comment was never
screened, while the executor hands the Verify span as written to red
proof, the test lock and the done line inside --cmd "...", where a $(...)
runs and a quote ends the argument. trekplan's text and the reviewer's
NOT RUN table say so.
- A span that is only a comment is not-a-command, not a placeholder. The
dropComment text says the allowlist still refuses a word with a # in it.
- The criteria runner, comparison-gate and end-state-gate use isMain: they
did nothing and exited 0 under a symlinked path. The test now refuses any
process.argv[1] comparison outside lib/util/is-main.mjs.
- Files: in a field with backticked paths, a plain word counts only before
the entry's description (a dash, or a colon after the path); a name with
no slash only first in its entry or after and/or/+/&. "mocks
fs.readFileSync", "runs on Node.js 22.x" or "no change to package.json"
no longer make a tests-only step look like it builds something.
Lowercase makefile, rakefile and justfile are build files. Measured on the
520 Files: fields in 48 plans of the marketplace and the test repo:
3 fields read differently (two notes no longer read as files, one
duplicate name dropped), tests-only changed in 0.
- The test lock compares --cmd without its trailing comment, and the test
lock and the done line read a stop with stoppedBy, the one reading.
red-proof drops its second reading, spawnError.
- release-check reads a relative --review in --repo or, when only that one
exists, from the current directory as 6.3.0 did; two different files are
exit 2, never guessed. The runbook says so.
- One trailing-json reader: a closing fence may be longer than three
backticks, in the block reader and the verdict gate alike, and the review
validator and the synthesis digest use it, so three backticks inside a
JSON string no longer hide a BLOCKER from the remediation-step check.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Round 7 (516dffa..45aa9e1, WARN: 12 MAJOR, 0 BLOCKER) and the fence defect
found while writing its review.md. Each fix began with a test that failed on
0f400d3 (v6.3.0); suite 2208 (2206/0/2), 14 tests more.
- Tests-only (operator 2026-10-11): the plan's Files: alone decides, and the
text says so (red-proof, trekexecute Sub-step B, step-implementer,
HANDOVER-CONTRACTS). red-proof no longer reads the step's diff, so a change
already in the tree when the step began no longer counts against it, and a
plan placed outside .claude/ reads the same. The round-6 test that had the
diff overrule the plan is rewritten to the new rule.
- The Files: reader keeps a plain file beside a backticked path
(", Dockerfile", "the CLI entry src/cli.mjs", "and Makefile"). Measured on
the 520 Files: fields in 182 plans: no field reads differently.
- Red proof reports a command its timeout killed as killed after the timeout,
not "could not start"; the release check tells a timeout from output past
its buffer and from another signal. One reading of a stop
(criteria-runner stoppedBy) for red proof, the criteria runner and the
release check.
- A trailing `# comment` is dropped in a backticked check too, and in a
command passed as written, so the words screened are the words run.
- The release check reads a relative --review in --repo.
- The 15-minute timeout is defined once (criteria-runner.mjs).
- The findings check reads each cited file once per validation.
- One isMain helper (lib/util/is-main.mjs) for every CLI: the 31 copies of
the realpath guard and the 20 modules still on the file:// guard, which
exited 0 having done nothing under a symlink or a path with a space.
- The Bash guard writes its no-one-to-ask refusal once, on a direct condition.
- The findings check ends a ```json block only at a fence on its own line, so
three backticks inside a JSON string no longer end it (also in 6.2.0).
- Brief-conformance notes: a test for test-lock green on exit 127 (it
passed at once; it fails when 127 is read as could-not-run); the prose now
names the git revision `@~1` as the one leading-@ exception.
Not changed: the example plan's steps 1-2 keep their tests-only warning
(operator decision 2026-10-09; the r5 test records it). Brief note 4 (a
Regression: whose runner is not installed goes to the fix rounds) is a
routing question for the operator.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The review of v6.2.0..f669b87 (BLOCK: 1 BLOCKER, 12 MAJOR, 1 MINOR), each
fixed behind a test that failed first, or, for the two missing tests, a test
shown to fail on a stub of the branch it covers.
- Review steps appended by /trekexecute Phase 7.2 are held to the step rules
on any plan version: plan-validator --steps-from <N> (on a plan below 1.8 a
template review step validated and was executed).
- The guard refuses where no one can be asked also when its rules will not
load; the wave merge path names that refusal instead of MERGE_REFUSED.
Tests for the classifier-error refusal and post-approval-log's own check.
- release-check: the version files may change only in their version after
the review (JSON compared without it), README diff lines are read inside
hunks only, an unreadable diff is exit 2, and npm test runs without
NODE_TEST_CONTEXT.
- What counts as a step of only tests: a note in parentheses is not a path,
and a data file under specs/ is not a test. End-to-end: rides on the last
step that builds behaviour (validator hint, trekplan, template).
- A removed line is cited as <rev>:<path>:<line> (findings-schema hint,
trekreview re-ask).
- skill-lint counts a trailing newline as no line; regression-check takes
commandEnv from lib/util/command-env.mjs; CLAUDE.md names four mode-read
exemptions.
- /security-review, older than v6.2.0: the criteria runner refuses git
--output, which writes a file.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
1. A step of only tests can never be proven red. One reading,
stepTestsOnly (lib/parsers/plan-schema.mjs, test paths from the new
lib/util/test-path.mjs): the plan validator warns PLAN_STEP_TESTS_ONLY,
red-proof --plan/--step adds tests_only to a not-red-at-base, and
/trekexecute and the step helper send such a step straight up to the
plan instead of into fix rounds that cannot succeed. /trekplan, the plan
template and plan-critic (dimension 8, still 12) say the test belongs in
the step that builds the behaviour.
2. Timing tests under load: the hook helper's kill limit is 30 s and per
call overridable; SC #14 passes on the fastest of up to three runs
against the same 800 ms limit (tests/helpers/timing.mjs).
3. The example plan's On failure lines open with a K11 word.
4. /trekreview saves the reviewer's whole answer for the findings check and
names FINDING_PROSE_LINE_OUT_OF_RANGE (error: re-ask; warning: report).
5. The criteria runner's commands run without NODE_TEST_CONTEXT
(commandEnv, moved to lib/util/command-env.mjs).
6. The resolver returns effort only when the brief's phase signal sets one;
the four commands said it always did.
Also: the K2 hook tests used fixed session ids in a per-user temp dir, so
two suites running at once took each other's approval records; the ids are
now unique per run.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Wave 2, order 6. /trekexecute now:
- refuses a plan whose logged approval does not cover its current sha256
(K2, approval-log verify --kind plan), before step 1;
- runs the step check (K9) and the step's optional Regression: (K10, new
lib/verification/regression-check.mjs through the criteria runner) at step
end, before the checkpoint; exit 2 is "not measured", never green;
- runs the architecture rules (K5) and the plan-file sweep (K6) after the last
step; a violation or a file outside the plan turns completed into partial;
- reviews by itself in the closing run (Phase 7.2): run the thing, /simplify,
/trekreview, verdict-gate; a BLOCK adds the review's remediation steps after
the plan validator accepts them and the operator re-approves the plan, capped
at TREKEXECUTE_MAX_REVIEW_ROUNDS (3);
- makes the main-merge gate a lock on the verdict: BLOCK or undecided keeps
the merge closed; when open, the executor merges and the guard's question is
the one question (operator decision 2026-10-08). The --gates pause before
the wave merge-back is gone for the same reason.
The guard refuses a merge into main and a push in the permission mode that
shows no prompts, since no one can be asked (operator decision 2026-10-09; two
mode-read exemptions approved by the operator).
progress.json gains optional coupling fields (Handover 5); the validator
rejects the runner's exitCode in plan_verification.failed_criteria (C15).
Pointer lines name the skills test-first and debugging (S2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- The pre-compact hook read only a checkpoint that started with `git commit`,
so every plan in the new `git add … && git commit` form rebuilt nothing, and
an empty match also skipped the session-state refresh. It now finds the
commit anywhere in the span and always refreshes; first test for the hook.
- A sub-bullet that carries its own command stays a criterion (folding it
left the command unrun); the shallowest bullet sets the base indent.
- Only a MINOR/SUGGESTION /code-review finding outside the range is released
from forbidding ALLOW: a MAJOR one may be a break cited at an unchanged
caller.
- `reuse` is an improvement category; the session-spec template stages too;
a negated bash 3.2 constraint, an env prefix and `bash -c` are handled.
- Stale comment, Declined-to-Judge wording and rule-key counts brought in line.
Tests fail on 7c11c2a first (9 of 24).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Independent read-only review of c56f852..2d29966 (2026-10-08), each defect
reproduced by the reviewer; each new test fails on that code.
- test-lock green ran ANY allowlisted command: `green --cmd "git status"`
marked a red step green and the stop guard let it stop. The lock now
stores the step's test command (`lock --cmd`); `green` runs only that
one (a different --cmd, or a lock without one, exits 2). trekexecute D1
calls `green` with no command, which also removes the quoting hazard.
- plan-gate --accept-open worked at round 1 and passed the gate; it now
refuses while rounds are left.
- findings-schema --repo-root swallowed a following flag, or took a root
that does not exist, and silently skipped the line check: exit 2.
- brief-review-stamp hashed only the body, so a changed `framing` or
`research_topics` stayed "current"; it now covers the reviewed
frontmatter too (only the post-review stamps are left out).
- red-proof red_kind read an assertion message naming SyntaxError as a
load error; the signatures are now specific.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
voyage-lekerepo trial (2026-10-06) point 7, operator decision 2026-10-08
(«grønt merke på låsen»): the stop guard blocked Stop three times while the
executor waited for the controller, with the step's test already green.
- test-lock.mjs green --cmd "<Verify>" runs the step's test command (same
allowlist + denylist as done-line) and records green_at only on exit 0;
pending clears it; a new lock starts without it.
- stop-test-lock lets a green-marked lock stop; the write guard still
refuses the locked test files.
- trekexecute: D1 marks green after a PASS; each fix round marks pending.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Wave-1 order 4 (P7, P12, the P9 test lock, the P3 plan-approval guard).
All command hooks; none runs a model.
- P12: pre-bash-executor answers permissionDecision "ask" before merge
into main, push, tag/publish and destructive git (holds in auto mode).
post-approval-log writes exactly what the person was asked to the K2
approval log: merge/push to main as `merge`, tag/publish as `release`,
with a one-hour expiry; nothing when no person was asked.
- P3: pre-plan-gate runs the K3 plan gate on a Voyage plan leaving plan
mode and sends a refused plan back; "not measured" asks, never passes.
- P9: lib/util/test-lock.mjs (K8). pre-write-executor refuses edits to
locked test files; stop-test-lock refuses "done" for the locking
session (stop_hook_active guarded).
- P7: post-edit-check runs the target repo's own formatter/linter per
edit, only during a Voyage plan run or after opt-in
(.claude/voyage-guards.json); lib/verification/step-check.mjs (K9) fails
the step on findings; no tool reads "not measured", never green.
- STORM cap matcher also names `Agent` (the tool's name since 2.1.63).
- Mod precondition stated in README, SECURITY.md and every PreToolUse stop
guard: Voyage's guards are deterministic only when no installed mod
handles `tool.check`.
K2, K3 and K5 are stubbed in tests until orders 2 and 3 are merged.
Two independent review rounds; every finding has a regression test.
Suite 1600 (1598 pass / 0 fail / 2 skipped).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
hooks.json wired pre-write-executor.mjs to the Write tool only, so Edit and
NotebookEdit reached .git/hooks/, .env, shell configs and the other protected
paths unguarded. The matcher is now Write|Edit|NotebookEdit.
The guard reads the target path per tool: file_path for Write and Edit (hooks
reference, PreToolUse tool_input tables), notebook_path for NotebookEdit (the
tool's input schema). When it cannot read a path (unparseable input, unknown
tool, missing field) it now blocks instead of allowing.
New tests resolve hooks.json with Claude Code's matcher semantics and run the
hooks that would fire per tool: 9 failed on the old code, all pass now. The two
fail-open pins in path-guard.test.mjs are flipped to fail closed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
order_id / order_claimed_at / order_reason on the five surfaces: (1) record
format = the writer (pinned in stats-landing), (2) Phase 7 prose with "the
writer adds", (3) the field-allowlist header names them as dropped and
TREKBRIEF_ALLOWED leaves them out, (4) the trekbrief-stats fixture row's
`fields` column + EXPORT_DENYLIST, (5) docs/architecture.md Stats. Plus: the
row's line_ref must contain the Phase 7 stats-append line (it said 657-672,
the line is at 958); /trekbrief --approve reaches Phase 7 with mode "approve"
(PM 04.10, point 3) and CLAUDE.md, README.md, docs/command-modes.md say so.
Red: 7 doc pins fail. Green on arrival: the yardstick-header pin (Step 6
already rewrote the header) and the otel DROP guard (the fields were never
allowlisted).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
M4: the halt regex matched any **halt** in a 2500-char window, so the PM's
mutant (first **halt** → "continue anyway") survived. Two new tests pin the
sentence right after the gate command and the could-not-run halt. Mutant
run: old test ok, both new tests not ok.
M5: nothing guarded 2045432's allowlist line. New test: trekbrief keeps
intent_approved, drops task/project_dir. Mutant (line removed): not ok.
M3 (red): the header claims a reflow keeps the approval; joining lines is
STALE. Pins the honest wording + the STALE behaviour.
M7 (red): the trekreview exemption is not documented as a bypass of the
same trust class as self-stamping (header, HANDOVER-CONTRACTS, trekplan).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
DEFAULT_TTL_MS was 6h, measured from marker.startedAt rather than last
activity, and `claude --resume` keeps the same session_id - so a run that
died holding its marker handed the resumed session the remainder of that
window, denying every WebSearch/WebFetch/Task including work unrelated to
research. The header's design goal ("An unrelated session must never be
denied") held across sessions and read as broader than it was: by this
scope key a resume IS the same session.
Three changes, none of which pretends to close it:
- The tombstone boundary (32e20fc) already removed the common case. A run
that crashed MID-loop leaves no denial record, so the resume is allowed;
only a crash AFTER the cap denied a turn opens a window at all. Pinned by
a test with a part-spent ledger and no tombstone.
- TTL 6h -> 2h. A 24-turn loop at a couple of minutes per turn is under an
hour, so nothing needed six, and debris no longer owns the rest of the
working day.
- Every denial now prints the marker path with "if this loop is not
running, delete it", plus the auto-reset horizon. The window existed
before with no stated remedy, which is what made it expensive.
A liveness check would close it properly. This hook has nothing
trustworthy to check liveness against - the marker's writer is a shell
snippet whose $$ is a subshell, not the session - so the limit is written
into the header as a limit instead of being papered over.
Review finding d913d1b655012fe206ea925b9fc77b401566a39e (MINOR).
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LuGhWAbWyRFBFeemfhxoVv
Two gaps, both test-side. No production behaviour changes here: the
branches were already correct, they were simply unpinned, so a later edit
could have broken them silently.
1. Crash-time states the hook header's TTL discussion anticipates and no
test exercised: a partially written marker (valid prefix, no close - what
an interrupted printf leaves), a marker with no runId, a marker whose
runId is empty or not a string, and malformed ledger lines. All must
ALLOW, because a marker we cannot read cannot say which run we are in,
and a half-written ledger line is not a spent turn. One test pins the
other direction too: skipping bad lines must not mean skipping the run's
tombstone.
2. The marker snippet is now RUN, not asserted about. Every existing pin on
the marker lifecycle (tests/lib/doc-consistency.test.mjs) is a substring
assertion on prose, so a snippet emitting invalid JSON or writing to a
path the hook never reads would keep the whole suite green while the hook
allowed everything - the failure S82 had to find by hand with a
scratchpad probe. Three tests now extract the real ```bash blocks from
commands/trekresearch.md and execute them with CLAUDE_PLUGIN_DATA
stripped and HOME sandboxed:
- the write snippet lands parseable JSON at the exact path the hook
looks up, with runId and a Date.parse-able startedAt;
- an empty CLAUDE_CODE_SESSION_ID produces NO `.json` marker and says
the cap stays inert;
- write snippet -> real hook denies -> removal snippet -> real hook
allows, which is the writer/reader agreement end to end.
On the non-string runId: it clears the falsy guard and then matches no
ledger record, so the run reads as 0 turns and is allowed. Allow is correct
either way and no writer emits one, so that stays a pin on the outcome
rather than an argument for a type guard on an unreachable state.
Review finding 823d8c28d7c993717606433fd6711d5a67877967 (MINOR).
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LuGhWAbWyRFBFeemfhxoVv
allowTurn() appends BEFORE the turn runs, so during granted turn N the
ledger holds N records. The hook denied at `used >= budget`, which blocked
every tool call of the FINAL granted turn: the primitive granted B turns
and the harness permitted B-1. Worse, an exhausted run therefore always
terminated through an exit-2 tool denial instead of the graceful "cap
exhausted" exit at commands/trekresearch.md - and the prose says in as
many words that exit 2 is not exit 1, so the model was pushed out through
the one exit it is told NOT to treat as a cap.
The review recommended denying at `used > budget`. Taken alone that fixes
the count and breaks the hook: once the O_EXCL claim (previous commit)
makes a breached ledger impossible, `granted > budget` can no longer fire,
and the case this hook exists for - the loop consults the gate, is denied,
and issues the tool call anyway - would be allowed. A deny branch that
cannot be reached is a dead security claim, which is the same thing S82
removed two of rather than leave standing.
So the denial itself became a record. allowTurn() appends a tombstone
{runId, exhausted: true} when it denies for budget, and the hook denies on
the tombstone. Both properties now hold at once:
granted == budget, no tombstone -> turn B is in flight -> ALLOW
tombstone present -> the gate already said no -> DENY
granted > budget -> breached, any cause -> DENY
A tombstone is not a turn: readLedger reports {granted, exhausted}
separately so it can never consume budget. allowTurn short-circuits on an
existing tombstone, so a hammered gate neither re-walks every slot nor
grows the ledger. The tombstone write is best effort on purpose - the
denial is already the correct answer, so a ledger that cannot take the
record must not turn a denial into a grant.
The parallel-boundary test now asserts GRANTED turns rather than raw
ledger lines, because the denied callers legitimately add tombstones.
Review finding 8eb53458ac3efec778094f9f03b09e1cc1077a09 (MINOR).
Operator decision: tombstone over the literal recommended_action.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LuGhWAbWyRFBFeemfhxoVv
An unreadable ledger returned 0 from countTurns in BOTH the primitive and
the hook, so a run whose ledger existed but could not be read (EISDIR,
EACCES, EIO) was handed the full budget again on every call - unbounded.
research-loop-cap.mjs argues against exactly that three lines above the
code that did it, and its missing-DIRECTORY case already failed closed.
The unreadable-FILE case now agrees with it.
Only ENOENT still counts as zero turns spent: that is the legitimate
first-turn state, and the reason this cannot just throw on any read
failure.
The hook no longer carries its own countTurns. It imports the primitive's
exported readLedger(), the same way it already resolves the data root
through resolveDataRoot() - a reader and a writer with private copies of
the counting rule is how a hook ends up enforcing a different bound than
the gate it backs. In scope + cannot count now exits 2 with a message
that says counting failed, not that the budget is spent.
Fail-closed stays scoped to the loop: a test pins that an unreadable
ledger in an OUT-of-scope session still exits 0, because a PreToolUse
hook that over-blocks bricks every session on the box.
Also dropped the existsSync pre-check before the read - readFileSync's
own ENOENT carries the same information without a second syscall that
can disagree with the read that follows it.
Review finding 5e1c6230f48ead38fa77cd8f4b06bfdc2b5b7bbf (MINOR).
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LuGhWAbWyRFBFeemfhxoVv
CLAUDE_PLUGIN_DATA is empty in the Bash tool's process env, and the Phase 5
bash snippet is the cap's only caller. resolveLedgerPath() returned null there
and allowTurn() failed closed, so the budget gate denied turn 1 of every real
run: the loop this delivery exists to bound could never spend a turn, and the
pre-registered measurement could not be run at all.
resolveDataRoot() is now the single root for everything the loop writes --
CLAUDE_PLUGIN_DATA when the harness sets it, ~/.claude/voyage when it does
not. Three consumers resolve through it, which is the point: the cap ledger,
the PreToolUse hook's scope-marker lookup, and the command's bash snippets.
A writer and a reader that resolved the root separately are what made the
enforcement hook allow unconditionally in every real run while CLAUDE.md and
docs/architecture.md called it enforcing.
Same root cause, same commit:
- Marker write and remove now share ONE absolute-path guard and one root; the
write requires a non-empty CLAUDE_CODE_SESSION_ID before composing the path
(unset, the marker was named `.json`, which no lookup matches and no TTL
sweep cleans up).
- The per-turn gates resolve VOYAGE_ROOT with a plugin-cache fallback and
reserve exit 2 for "gate could not run". Interpolating an empty
${CLAUDE_PLUGIN_ROOT} ran `node /lib/...` -> exit 1, which the contract read
as "privacy gate says no" -- an unsatisfiable rewrite loop no query could
clear.
Two now-unreachable deny branches are removed rather than left as dead safety
claims (allowTurn's no_plugin_data_dir; the hook's uncountable-ledger deny).
The fail-closed stance stays where it is still real: a ledger that cannot be
WRITTEN denies the turn.
Verified end-to-end through the real bash snippets and the real hook with both
variables stripped and HOME sandboxed: marker written under the fallback root,
8 turns spent, 9th denied, hook exits 2, and exits 0 again after removal.
Note: the fallback exit-2 branch fires against the installed v5.9.1 cache,
which predates lib/util/research-loop-cap.mjs -- correct behaviour, and it
clears when the plugin is reinstalled.
Review findings 2670c10a, fbd6d534, 93550dfb.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011vPSXe88qp5aqWUqbDNWoF
Review finding 4638fea9 (MAJOR emitted, catalogue tier BLOCKER). Live in every
session regardless of the STORM flag, so it is not deferrable to the measurement
decision.
Anchoring the rule to command position (S75-S78) was right in intent - the
unanchored word match blocked quoted grep patterns, heredoc data and commit
messages - but it ran against the whitespace-collapsed string. Measured against
normalizeCommand() output, five forms that the previous rule blocked were
allowed:
- newline separator: \s+ -> ' ' collapsed the newline BEFORE the pattern ran,
making the \n branch of the separator class dead code
- `&` background separator: absent from the class entirely
- `bash -c` / `sh -c`: the wrapped command sits inside quotes, never at
command position
- `xargs <cmd>`: no separator in front of the command at all
And it missed its own motivating case: `grep "a|b" f` stayed blocked, because
the `|` inside the quotes still read as a separator.
Fix: the rule now runs against a command-position view (`commandView: true`,
per-rule input selection) instead of the collapsed string. The view keeps
newlines, adds `&` to the separator class, and classifies each span:
- quoted spans -> data (one space), so a grep alternation, echoed prose and a
commit message pass
- EXCEPT the argument of a shell wrapper (`sh -c`, `bash -c`, with optional
sudo and absolute path) -> spliced back in at command position
- heredoc bodies -> data, keeping the operator line. Restoring the newline
separator without this would newly block every heredoc line starting with a
matched word - the exact friction anchoring existed to remove
- `xargs [flags]` -> separator inserted after the flags
Two defects found while verifying, both the same regression class and both
fixed here rather than left:
- `\name` runs name (the backslash only suppresses alias expansion). The old
unanchored rule blocked it; the anchored one allowed it.
- heredoc bodies, as above - a false positive this change would otherwise have
introduced.
Known limit, stated rather than implied: `xargs -I {} <cmd>` is not parsed, so
the inserted separator lands before the argument, not the command.
Other BLOCK rules are untouched and still run against the collapsed string.
Verified by a 37-case adversarial probe through the real hook (all five bypass
forms, both wrapper forms, backslash, heredoc, quoted alternation, ordinary
commands, and the unrelated rules): 37/37 as expected. 9 new tests.
Suite 952 (950/0/2, baseline 937 + 15 across both Track A fixes).
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013zNqxP8qTWgJhn3wMYUFEh
S21 = devil's-advocate blind spot #2 (security/safety), operator scope
"security-core": fix genuine defects, honestly record the rest.
SSRF fix (CWE-918). validateOtlpEndpoint classified the host by literal
string match. Decimal/hex/octal/trailing-dot encodings are already caught
(the WHATWG URL parser canonicalizes them), but IPv4-mapped IPv6 literals
(::ffff:127.0.0.1, ::ffff:192.168.x, ::ffff:169.254.169.254) render as
::ffff:HHHH:HHHH and matched neither the loopback set, the RFC-1918 regex,
link-local, nor HARD_BLOCKED_HOSTS — they passed over https and would reach
loopback / private / cloud-metadata, defeating the comment's "PERMANENTLY
block metadata" promise. Added mappedV4() to decode the embedded IPv4
(dotted + hex-pair forms) and classify on it. TDD: 4 tests failing-first —
mapped loopback/RFC-1918/metadata rejected (metadata stays HARD_BLOCKED even
with VOYAGE_OTEL_ALLOW_PRIVATE=1), mapped public ::ffff:8.8.8.8 still valid
(no over-block). Threat model narrow (endpoint is operator-set env; export
opt-in; a brief cannot set env).
Survivor #18 honest-residual. T2-bakeoff §3 "Classifier interference: 0"
read as satisfied, but the auto/bypass-mode re-run that matters for headless
trekreview was never run (mode is operator-set, not settable in-session) —
footnoted, not gating. Per recommendation #9, moved to an OPEN RESIDUAL
(untested), guarded by a new doc-consistency pin.
Audit record. ## S21 resolution block in devils-advocate-results.md
dispositions all four sub-questions: SSRF (fixed), hooks-block (verified;
advisory-rail residuals: Write-only matcher, Bash-redirect, regex gaps — by
design), malicious-brief-headless (catastrophe-blocked, exfil NOT blocked —
inherent limit). S21b flagged (NOT done): operations.md:15 mis-describes
autonomy-gate.mjs state machine + --gates table.
Test count: real baseline 700 (698 pass / 2 skip), NOT 715 — the node:test
headline carried in S20 commit msgs was stale/miscounted (census figures
were correct). Now 705 (703 pass / 2 skip / 0 fail); census behavior
601->605, doc-pins 71->72, total 672->677.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LqBYc8Ltrk7LipyJmGxXiB
S2 of the 2.1.181 upgrade. Schemas verified verbatim against the official
slash-commands and hooks docs before editing (a first-pass camelCase
'disallowedTools' claim was caught and corrected to kebab-case against the doc).
- CC-14 (SHIP): migrate all 7 hooks in hooks/hooks.json to exec-form
{command:"node", args:["${CLAUDE_PLUGIN_ROOT}/hooks/scripts/X.mjs"]}. Doc
recommends exec-form whenever a hook references a path placeholder; protects
consumers installing under a path with spaces. ${CLAUDE_PLUGIN_ROOT}
interpolates inside args (verified). hooks-json-stop-wired test made
form-agnostic (normalizes command+args to one invocation string).
- CC-11 (SHIP): add `disallowed-tools: Agent, TeamCreate` to trekexecute
frontmatter, enforcing its documented "No Agent tool, no TeamCreate" rule.
allowed-tools grants auto-approval but does NOT remove tools from the pool,
so the prior omission left Agent callable; disallowed-tools removes it.
trekexecute is the only command with a documented exclusion.
- CC-15 (DECIDE: keep universal): re-affirm F2 deferral. pre-bash/pre-write
executors stay universal -- session-agnostic safety (rm -rf /, ~/.ssh, .env)
that narrowing to execute-only would only weaken. Header comments corrected.
- CC-10 (DECIDE: design note, no code): no blanket Agent(model:opus) deny rule
-- would break balanced/economy profiles; any model-enforcement must be
profile-aware, deferred into W2. Folded into open question #3.
Matrix updated with S2 resolutions section. Tests 578 pass / 0 fail / 2 skip;
claude plugin validate passes (only pre-existing root-CLAUDE.md warning).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LqBYc8Ltrk7LipyJmGxXiB
Found by simulert v4.1 smoke — doc/code-drift in v4.1 ship:
docs/observability.md claims "Cloud metadata endpoints (169.254.169.254)
are permanently blocked" but the validator allowed them when
VOYAGE_OTEL_ALLOW_PRIVATE=1. Cloud metadata services expose IAM
credentials and instance secrets — operator-trust extended to
RFC-1918 home-lab access does NOT extend here, because the
blast-radius (cloud-account compromise) is qualitatively different.
New HARD_BLOCKED_HOSTS set checked BEFORE the link-local opt-in path:
- 169.254.169.254 (AWS / GCP / Azure metadata)
- 100.100.100.200 (AliCloud metadata)
- metadata.google.internal
- metadata.azure.com
New error code ENDPOINT_HARD_BLOCKED. Existing test for
ENDPOINT_LINK_LOCAL_REJECTED on 169.254.169.254 updated to assert
the new code; 3 new tests verify the hard-block holds even with
VOYAGE_OTEL_ALLOW_PRIVATE=1, plus AliCloud + GCP-hostname coverage.
Tests: 487 → 490 pass + 2 skipped.
Step 13 of v4.1 — adds Stop hook entry pointing to
hooks/scripts/otel-export.mjs (added in Step 12 / commit cced21b).
Mounts the orchestrator on Claude Code's Stop event so OTel/Prometheus
export runs at session-end when VOYAGE_EXPORT_MODE is set.
HIGH-risk-mitigering: tests/hooks/hooks-json-stop-wired.test.mjs
asserter at Stop-key finnes, refererer otel-export.mjs, bruker
\${CLAUDE_PLUGIN_ROOT}-substitusjon, og har type:command.
Tests: 464 → 468 (4 new). All green.
Pins existing BLOCK rules in the two pre-* executor hooks so a future
silent weakening of BLOCK_RULES surfaces as test failures instead of
slipping through code review.
50 new tests covering both hooks plus allow-list pins (lib/, tests/,
docs/, ls, git, npm) and fail-open on malformed input. Reuses
tests/helpers/hook-helper.mjs child-process spawner.
[skip-docs]
New hooks/scripts/post-compact-flush.mjs (PostCompact event, CC v2.1.105+):
auto-discovers <cwd>/.claude/projects/*/.session-state.local.json (most
recently modified), validates it via session-state-validator, emits
additionalContext via stdout so the post-compact assistant turn has
Handover 7 resume context loaded immediately.
Read-only — never writes. Always exits 0; never blocks compaction. Uses
only node:fs sync APIs available since Node 12 (no glob dependency).
Companion to the existing pre-compact-flush.mjs:
- PreCompact: refresh progress.json + .session-state.local.json
- PostCompact: re-inject .session-state.local.json into context
Wired in hooks/hooks.json under a new PostCompact matcher block.
Both files staged via /tmp/claude-* and copied into hooks/* via Bash to
respect the llm-security plugin path-guard (which blocks direct Write to
hooks/scripts/*.mjs and hooks*.json).
Test: tests/hooks/post-compact-flush.test.mjs (4 tests) covers no-state,
malformed-state, valid-state, and multi-project mtime selection.
