The annotation surface's provenance is now described as the pattern it
follows (pencil toggle, intent buttons, popover form, structured export)
rather than by naming a repository that no longer exists. Touches the
plugin/package descriptions, README, docs/architecture.md, the v5.0.3
CHANGELOG entry, and two comments in scripts/annotate.mjs and its test.
Retired-reference check: 12 hits in 7 files -> 0 (content and path names).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A node:test pin that scans every tracked text file and path for the terms
in a gitignored local list (tests/.excluded-terms.local.txt), so the terms
never live in tracked text. The scanner is validated against a planted
known-positive (content and path name), an empty scan fails closed, the
named EXEMPT list is empty and rot-checked, and without the local list the
scan is skipped with an explicit message.
Red on 0be152a with the list present: 12 hits in 7 files.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Measured on 687710a: a correct case-6 reply said "**FAIL**: ... did not pass
... The other checks passed." With lower case accepted, says-pass matches that
reply, so a wrong case-8 reply of the same shape would pass the case. The test
pins that a reply whose capitalised verdict is the opposite one is refused,
while the opposite word in lower case (a side clause) or negated is not.
Red on 687710a: 11 of 12 in tests/lib/proevesett.test.mjs.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The PM re-measurement of ea66a98 had case 8 pass 10 of 12. Both failures were
correct replies that gave the verdict only in lower case ("passed"), and
\bPASS(?:ED)?\b is case-sensitive. The test pins lower-case pass/passes/passed
and fail/fails/failed as verdicts, keeps "not passed", "doesn't pass", "failed"
refused by says-pass, and checks that each case's recorded reply does not
satisfy the other case's grader.
Red on ea66a98: 10 of 11 in tests/lib/proevesett.test.mjs.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Known-positive for case 4, in a scratch copy (never this tree):
brief-validator.mjs with the BRIEF_V51_MISSING_SIGNALS check made
'if (false)'. The case still passed 3 of 3: the child read the rule in
the command prose, halted, named phase_signals, and even found the
planted 'if (false)'. So the halt alone does not show the validator
fired, and no grader checked what expected_outcome already promised
('brief-validator ... reports BRIEF_V51_MISSING_SIGNALS').
New test: case 4 needs a names-code grader reading the validator's JSON
code from the trace (same form as the intent case). Red: 1 of 10.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The scaffold writes a current intent_approved_hash (sha256 over ## Intent +
## Goal) into the case-4 brief. Chose a literal marker over running
intent-approval.mjs --stamp in the scaffold because --stamp emits a
brief-approved record into the live stats the yardstick reads: every eval
run would count as an approval.
New grader no-intent-halt (regex, trace, not_contains
code\W{1,12}BRIEF_INTENT_): a halt at the intent gate fails the case
instead of passing it for the wrong gate.
says-fail / says-pass take FAILED / PASSED as the verdict word. v2's word
boundary dropped them. The one says-fail failure (PM, 1 of 7) is not
explained: its trace was deleted, and 0 of 13 kept replies used another
spelling than FAIL.
Case 4 alone, 10 runs: 10 of 10. In 3 of 10 the child ran the intent gate
first, passed it and went on to the brief-validator. That order halted the
case before. Before the fix, same day: 5 of 6.
Green: tests/lib/proevesett.test.mjs 9 of 9.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Case 4 (plan-halts-without-phase-signals) measured on dc9b480, 6 runs:
5 of 6. The failing run called only intent-approval.mjs, halted on
BRIEF_INTENT_NOT_APPROVED, and so failed validator-ran and
halt-names-signals: the fixture has no intent marker, so the case can
measure the wrong gate. PM: 6 of 12 on dc9b480, 7 of 10 on 66e1fa1.
New tests: the case-4 fixture must pass intent-approval --check and fail
only BRIEF_V51_MISSING_SIGNALS; a not_contains grader must fail the case
on any BRIEF_INTENT_* code in the trace. says-fail / says-pass must take
FAILED / PASSED as the verdict word (v2's word boundary dropped them).
Red: 3 of 9 in tests/lib/proevesett.test.mjs fail, each for its own reason.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Offline structure tests for evals/ (the suite itself needs headless runs):
- no case reaches the steg 1 intent gate (PM: 0 traces touched it). The
new case's scaffold is in: its brief passes brief-validator --soft
(2.1 WITH phase_signals) and --check gives BRIEF_INTENT_NOT_APPROVED —
that test is green, so the fixture reaches the gate.
- review-requires-project: trekreview.md composes 'Error: --project <dir>
is required.' in prose (8/10 in the PM run, backticks broke the regex),
and its arg-parser line passes "$@", which the Bash tool never has.
- no-error-code misses REVIEW_WRONG_TYPE; PASS/FAIL graders are raw
substrings; no-write cannot see a write through Bash.
7 tests, 6 red.
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>
M1: headings inside fenced code blocks and HTML comments are text, not
headings, and ## Intent / ## Goal must each appear exactly once. A second
section, an example section in a code block or comment, or a '## ' line in
a code block inside Intent no longer carries the old approval: check gives
INVALID (duplicate) or STALE, stamp refuses a duplicate. A plain brief
hashes exactly as before (pinned), so no stamped brief goes stale.
Re-run of the PM's 29 probes: vi-a, vi-b, vii-a, vii-b now stop; the rest
unchanged. The PM's p7c probe was a no-op (its replace string is not in the
base brief); vii-c is covered by its own test, red on 66e1fa1.
M2: /trekbrief --approve takes <project-dir | brief-file>. New
intent-approval.mjs --resolve decides: a directory → <dir>/brief.md and
/trekplan --project; a file → itself and /trekplan --brief. Phase 4h and the
stamp line use {BRIEF_PATH}; /trekplan's halt table names
/trekbrief --approve {brief_path}, which works on both brief modes, and so
does the gate's hint. HANDOVER-CONTRACTS' "open to every producer's brief"
is now true. Chose fixing the path over rewording the contract because two
real briefs (docs/*-brief.md) had no approval path at all.
Red ff760ed 9/29 → green 29/29. Suite 1219: 1217 pass / 0 fail / 2 skip.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
M1 (PM probes vi-a, vi-b, vii-a, vii-b, vii-c): extractSection takes the first
## Intent and does not see code blocks or HTML comments, so an added, hidden
or cut-off section rides on the old approval. 5 red. vii-d (comment inside
Intent) and the plain-brief hash are pinned green so the fix cannot move them.
M2: --approve resolves only <dir>/brief.md; a brief planned with
--brief docs/x-brief.md has no approval path but a raw --stamp. 4 red.
The stamp helper now substitutes {BRIEF_PATH} as well as {PROJECT_DIR}.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Phase 7 of /trekbrief and Phase 12 of /trekplan say "skip silently" when
CLAUDE_PLUGIN_DATA is unset, and the Bash tool env never carries it — the
same silent skip that left brief-approved at 0 records. Økt 2's countable
form (brief-approved + intent_approved: true + a trekplan record with the
same slug) cannot be counted until those records land where the yardstick
reads. 7 tests, 7 red: no stats-append line in either command.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Veikart steg 1, økt 1 av 2. The three holes measured in the grounds:
(1) ## Intent / ## Goal were only checked for existence, (2) no approval
marker existed, (3) brief-approved was emitted only on the auto path.
- lib/validators/intent-approval.mjs: --check / --stamp. The marker is
intent_approved_hash (sha256 over normalized ## Intent + ## Goal) +
intent_approved_at. Editing either section after approval → STALE.
- /trekplan Phase 1 (Read the brief, both --brief and --project): runs
--check and HALTS on BRIEF_INTENT_NOT_APPROVED / _STALE / _INVALID with
the remedy spelled out; an unrunnable check halts too.
- /trekbrief Phase 4h (before the Phase 5 fork, asked even in --quick):
shows Intent + Goal verbatim, AskUserQuestion Approve / Revise / Leave;
only "Approve" runs --stamp. --stamp emits brief-approved, so the manual
(default) path records it; the auto path's own emission is removed.
New mode /trekbrief --approve <project-dir> = Phase 4h alone.
- README, CLAUDE.md, command-modes, HANDOVER-CONTRACTS §Handover 1,
jsonl-schemas (trekbrief-stats gains intent_approved).
Valgt ingen brief_version-bump fordi skjemaendringen er rent additiv (to
valgfrie felt) og kravet sitter i /trekplan — enhver produsents brief kan
godkjennes via /trekbrief --approve uten produsentendring. Valgt eget
--check-kall i stedet for et flagg på brief-validator fordi --brief-stien
i dag ikke kjører validatoren i det hele tatt; et nytt validatorkall der
ville også stoppe på andre feil. Valgt fallback-datamappe = målestokkens
(plugins/data/voyage-…) fordi CLAUDE_PLUGIN_DATA er tom i Bash-miljøet og
event-emits egen fallback er stille skip — slik ble brief-approved 0 records.
What the marker does NOT prove (module header, command prose, contract):
same user, same machine — any session can stamp. A trace, not a signature.
Suite 1183 → 1201 (1199/0/2). Mutants M1–M5 (stale check off, check
always valid, gate line removed, stamp emits nothing, no normalization)
each fell ≥ 1 test. yardstick unchanged: RED, 1 of 3 countable.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Veikart steg 1, økt 1 av 2. 18 tests, all failing today:
(a) a brief without an approval marker → the gate line in
commands/trekplan.md exits non-zero (today: no gate, planning proceeds);
(b) marker + ## Intent or ## Goal edited after approval → stale, stops;
(c) a valid marker passes (known negative), and edits outside the two
sections or whitespace-only reflow keep it valid;
(d) the stamp runs before the Phase 5 manual/auto fork and emits
brief-approved, so the manual (default) path records it too.
The gate and stamp lines are extracted from the command prose and
executed, so removing the line or stubbing the module fells the test.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
One command, `node scripts/yardstick.mjs`, prints use, trust and
interrupts. Each row gives countable YES/NO, the value, the denominator and
the source it was read from. A fourth row asks whether the end-state gate can
be fooled by a mutant that keeps the module's signature. Exit is non-zero
while any number is not countable, the mutant is not felled, or the verdict
over the first five deliveries is not judged. Nothing counts a delivery yet,
so today it is RED for the right reasons:
use NO no order in the queue carries work-class
trust YES current ALLOW streak 0 of 37 (BLOCK 14, WARN 12, ALLOW 11,
last 2026-09-05 BLOCK, ordered by ts, read as JSON)
interrupts NO 0 user_input records of ~141k lines in 5 files, 0 emitter
call sites outside lib/stats/ and tests/
mutants 0 of 1 signature-preserving mutants felled: on M9 (every export
returns {status:'PASSED'}, every named test only checks typeof)
the gate closes both D-03 and D-04
It only measures. The gate, the emitter and the order writer are untouched.
The mutant row is meant to stay red until the gate learns to fell M9.
Choices, and why:
- Use counts over the order queue (pending, archive/ and claimed/), because
an order is the unit of work. The denominator is orders dated on or after a
cutoff (default 2026-09-21) that carry `work-class: new`. They count as
having gone through Voyage when a Voyage run in the stats has the order's
`slug:`. Both fields are the contract the order writer must meet. No order
carries them today, so the number is NOT COUNTABLE, not 0 %.
- Mailboxes whose names start with a dot are mailboxes too. A shell `*`
glob skips them, which is why a hand count of `coord/*/orders` comes out
lower. The row names them so a re-measure can reconcile.
- M9 must be LIVE before its row can count. Its typeof tests have to pass on
the M9 tree, checked by a runner independent of the gate, so a broken
fixture can never read as "felled".
Also: tests/fixtures/red-first/02243c6-always-allow-shim.mjs, the shim that
makes the red-first claim of 02243c6 reproducible (6 of 55). The recipe is in
its header.
Red first: the new test file failed to load before scripts/yardstick.mjs
existed, and a dot-mailbox test was red before the census learned about
dot-mailboxes. Suite 1161 -> 1183 (1181/0/2), also green on a clean tree
exported from the index.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
`origin` is a public mirror. Comments in tracked test files named the internal
review mechanism by its role rather than the measurement they came from; the
same class as the frozen file's overclaim fixed in 83d82f1. Replaced with what
they actually are: a re-measurement on a named commit, with the date.
The one remaining occurrence is the assertion that FORBIDS those phrases in
tests/fixtures/end-state-frozen.json - a guard has to spell out what it guards.
Suite 1161 (1159/0/2). Comment-only change.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Measured 2026-09-18: nine ordinary shapes of a plan's `## Verification`
section parsed to zero criteria - an untagged fence, a ```text fence, a
markdown table, `## Verification (acceptance)`, `## Verification:`,
`### Verification`, an unclosed fence earlier in the document. Every one came
out as `0 of 0`, NOT OK, exit 1, and Phase 7 then forbade `result: completed`
without anyone being told that the FORMAT, not the code, was the problem.
"The section is empty" and "I cannot read this format" are different facts.
Three changes, one hole:
- The runner reports `NO_CRITERIA` with a source line (`plan.md:NN`) when the
section is there and nothing in it parsed, and names the two forms it does
read. Same for a brief's `## Success Criteria`, so the evidence block the
conformance reviewer gets says which of the two it is looking at rather than
showing an empty table.
- Phase 7 says it out loud instead of failing silently: report the source line
and the two forms, and say that the plan is what failed there, not the run.
- `/trekplan` now pins what it produces to what the runner reads: the heading
is exactly `## Verification`, the criteria are a bullet whose first
backticked span is the command or a shell-tagged fence, and the command must
be one the allowlist runs. A doc-consistency test holds the writer and the
reader together, so a runner that learns a new form must update the source.
Honest about the round trip: the two round-trip tests were GREEN on arrival -
the template already writes the bullet form the runner reads. What was missing
was not the format but the PIN: `/trekplan` mandated neither the heading string
nor the format, so a plan could satisfy the command's own instructions and
still parse to nothing. The tests now hold that.
Red first: 5 of the 7 new tests failed before the change (3 NO_CRITERIA, 2
doc-consistency); the 2 round-trip tests are guards, and said so above.
Suite 1161 (1159/0/2). Gate unchanged: defects 0 of 7, intact, exit 1.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The cosmetic close came back one level up. The probe reads the test file from
the same tree it measures, so a four-line file holding two EMPTY tests with the
two named names closed D-03 and D-04 on a tree where `lib/verification/` did
not exist at all - "defects 0 of 7, registry intact" (measured 2026-09-18).
First a two-line stub exporting the right symbols; then an empty test with the
right name. A name is always forgeable.
So the named test is now run twice. Once on the tree, as before - and once in a
sandbox where the module the condition declares in `stubs` is replaced by a
stub exporting the same names, all inert. If the test still passes there, it
binds the name and not the behaviour, and the condition THROWS: NOT FELLABLE,
counted open. A condition that declares no `stubs`, or names a module that is
not there, cannot fire either.
The sandbox is a symlink overlay: every entry of the tree is symlinked, and
only the test file and the stubbed module are materialised for real - Node
resolves an ESM import through the realpath, so a symlinked test file would
import the original module and never see the mutant. Nothing is ever written
inside the measured tree, and the only directory removed is the one this code
made under the system temp dir (pinned by a test).
M7 is now a permanent mutant beside M6, in two forms: the checkpoint's own
reproduction (unfixed tree + empty named tests) and the harder one (the real
module present, so the stub can be built and the empty test passes against it).
Both report `defects 2 of 7`. A positive control pins that D-03/D-04 still
CLOSE on the real tree, so "not closed" everywhere cannot read as a working
probe.
The frozen denominator moves a third time, deliberately, and its `why` no
longer claims authority it does not have: the second and third amendments were
maintenance decisions by the maintainer, not operator decisions, and the
tracked file now says exactly that.
Measured after:
real tree node scripts/end-state-gate.mjs -> defects 0 of 7, intact, exit 1
M6 (stub) 8d1669e + current gate/registry/frozen + lib/cosmetic/stub.mjs -> 2 of 7
M7 (empty) 8d1669e + current gate/registry/frozen + 3-line
tests/lib/criteria-runner.test.mjs with the two named tests -> 2 of 7
Red first: 4 of the new tests failed before the change. Suite 1154 (1152/0/2).
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
A denylist in front of /bin/sh is whack-a-mole. Measured 2026-09-18, end to
end through both screens: 5 of 11 named evasions ran with real effect - a
`command` prefix reached git, an escaped `rm` inside a shell fence deleted a
directory, `find -delete` deleted a file, `>|` and `tee` wrote outside the
working tree, a python one-liner deleted the whole tree - and 19 of 28 got
past the refusal list on its own. Every quoting, aliasing and indirection form
of the shell is another mole.
So the screen is now an ALLOWLIST. A criterion runs only when its first word
is a known test runner (npm test, npm run <script package.json declares>,
node --test, vitest, jest, pytest, python -m pytest, uv run pytest,
cargo test, go test, make test, bash <script under tests/>, a read-only git
subcommand) AND the command carries no shell operator and no newline.
Everything else is NOT RUN with the reason said out loud: never run, and never
reported as a failure either - an absent measurement is not a finding. That
also closes the smaller hole in the same file: a bare word a sentence merely
names (`whoami`, `login`, `package.json`) is no longer executed, because it is
not a runner.
REFUSED_BY_POLICY is gone with the list that produced it; a command outside
the allowlist is `unrunnable`, which in plan mode still fells the run and in
brief mode is reported to the reviewer as an absent measurement.
What the allowlist deliberately does NOT do, said in the file and in the
reviewer's rubric: it is not a sandbox. `npm test`, `npm run <script>` and
`make test` run whatever the repo's own package.json/Makefile says they run,
including a script that pushes - that is the repo's responsibility. And it
rejects honest commands too: an env prefix, a project's own binary, anything
piped. A check that needs one of those is declared through
`bash tests/<script>.sh`, the documented way in.
Red first: 6 of the new tests fail against the previous runner (measured with
an always-allow shim so the module still loads), including the end-to-end one
where the canary directory was deleted and files were written outside the
tree. The fixtures move from `true`/`false` to two allowlisted shell fixtures,
because `false` is no longer a runner - the fail case must still be a real
non-zero exit, not an unrun criterion.
Suite 1148 (1146/0/2).
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
/trekreview passed --cwd and trekexecute Phase 7 did not, so the same criterion
could resolve two ways in the two phases (PM checkpoint 2026-09-18, MINOR).
It stopped being cosmetic with the refusal list: --cwd is the boundary a write
is measured against, so leaving it unset silently moves that boundary to
whatever the process cwd happens to be. Both phases now resolve
CRITERIA_CWD="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
- one form, with a fallback, so a repo-less checkout falls back instead of
passing an empty --cwd. Pinned in tests/lib/doc-consistency.test.mjs.
Red first: the new pin failed on both phases before this change.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
/trekreview now runs the commands a BRIEF declares, and a brief is an artifact
that can arrive from outside the repo. Measured 2026-09-18 on 6cafb4c: the
executor denylist stopped a download piped into a shell, but the remote-writing
git subcommand and a recursive delete of a path both RAN. The denylist screens
catastrophe (root deletion, fork bombs, mkfs); it was never meant to screen an
artifact under review.
A second screen, in the runner and ahead of the denylist, refuses four classes:
- a remote-writing git subcommand. The subcommand is found by walking git's own
options (`-C`, `-c`, `--git-dir`, ... take a value), so `git status` and
`git log` still run and `git -C sub push` does not.
- a recursive delete: any `rm` carrying `-r`/`-rf`/`--recursive`. A plain
`rm build/artifact.txt` still runs.
- a download piped straight into a shell (also caught by the denylist; pinned
here so the runner does not depend on another file for it).
- a write outside the working tree. `/dev/null`-class devices are fine, and so
is anything under the working tree; `~/...`, an absolute path elsewhere, and
a target carrying an unexpanded `$VAR` are refused - the runner cannot know
where a variable points, and guessing is how a screen stops screening.
A refusal is its own outcome, REFUSED_BY_POLICY: the command never reaches a
shell, and `summary.ok` is false in both plan and brief mode. For the reviewer,
REFUSED is like NOT RUN - the absence of a measurement, never on its own a
finding - and the rubric and the evidence block both say so.
Chosen deliberately, and it is stricter than today's habit: writing scratch to
/tmp is refused too. The repo's own example plan does `> /tmp/out`. Verification
output belongs in the working tree; exempting the whole system temp dir would
have made the rule unstatable, since a working tree created under /tmp then
contains its own escape hatch.
NOT covered, stated rather than implied:
- other writing git subcommands (tag, remote, config, gc) - only push is listed
- writes through a wrapper: `sh -c '...'`, `xargs`, `find -exec`, a Makefile
target, a script the criterion invokes. The screen reads the command it is
given, not what that command goes on to do.
- `>` inside a quoted string reads as a redirect, so a criterion echoing a
literal `>` is refused. Fail-closed, on purpose.
- the whole surface still runs with the invoking process's permissions; this is
a refusal list, not a sandbox.
The denylist-layer test now uses a stand-in command with a screen double: the
refusal list catches a recursive delete first, so naming one there would have
stopped exercising the denylist layer at all.
Red first: the 6 new tests failed before this change (`refuseCommand` did not
exist), and the fixture brief's four writes ran.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Measured 2026-09-18 (PM checkpoint on 6cafb4c, mutant M6): a two-line file
export function runPlanVerification() { return { ok: true }; }
export function formatCriteriaEvidence() { return ''; }
dropped into an otherwise UNFIXED tree closed both D-03 and D-04, and the gate
reported "defects 0 of 7, registry integrity: intact". The same checkpoint felled
5 of 5 mutants with the SUITE and 0 of 5 with the GATE. Both probes called
themselves `behaviour` while asking a grep whether an export name was present -
a phrase probe pointed at code.
A check condition may now name a test instead of a pattern:
{ "test": "tests/lib/criteria-runner.test.mjs", "name": "<exact test name>",
"expect": "fails" }
The gate spawns the test runner on that one test and reads its TAP line.
`expect: "fails"` holds - the defect stays open - while the test does not pass.
A missing file, a name that matches nothing, a runner that will not start: all
throw, which counts as NOT FELLABLE and therefore open. A check that cannot fire
is never "fixed".
The child's `NODE_TEST_*` env is stripped. The gate usually runs UNDER the test
runner, and an inherited `NODE_TEST_CONTEXT` makes the grandchild report over
the parent's IPC channel instead of stdout - the TAP line would never arrive and
the probe would silently stop felling anything.
M6 is now a permanent mutant in the gate's own test, so the cosmetic close
cannot come back. Verified end to end against a real stub tree:
git archive 8d1669e | tar -x -C $TMP
cp scripts/end-state-gate.mjs scripts/end-state-registry.json $TMP/scripts/
cp tests/fixtures/end-state-frozen.json $TMP/tests/fixtures/; cp STATE.md $TMP/
printf 'export function runPlanVerification…' > $TMP/lib/cosmetic/stub.mjs
node scripts/end-state-gate.mjs --root $TMP
-> defects 2 of 7, both NOT FELLABLE, exit 1
The gate also now states the limit out loud, as its own line above the table:
a behaviour probe proves the capability WORKS; that Phase 7 and Phase 4.5 CALL
it is pinned by TEXT in doc-consistency, not proven deterministically - real
proof is a headless plugin-eval run against a fixture plan (week 40).
FROZEN DENOMINATOR AMENDED, second time in one day, by the work order that
carries this change: D-03 and D-04 signatures moved because their checks
changed on purpose. tests/fixtures/end-state-frozen.json and the FROZEN literal
in tests/scripts/end-state-gate.test.mjs are updated together, both dated, both
saying why. No entry was removed.
Gate after this change: defects 0 of 7, registry integrity intact, exit 1.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
"The first backtick span is the command" is right for a plan, whose template
puts the command first, and wrong for a brief, whose criterion usually opens
by NAMING the thing under discussion. Measured 2026-09-18 on the repo's own
example brief: 5 of 6 criteria FAILED, 3 of them parse artifacts - `--verbose`
run as a command gave exit 2 ("invalid option"), `tests/` gave exit 126 ("is a
directory"). The rubric reads a FAILED result as decisive, so each one became
a BROKEN_SUCCESS_CRITERION BLOCKER about prose.
looksLikeCommand() screens the span by SHAPE only - no filesystem lookup, so a
span parses the same everywhere. Refused: a leading flag, a directory, a token
carrying quotes/braces/prose, and a lone relative path with a slash (an
explicit ./, ../, / or ~/ still runs, as do env-var prefixes). A refused span
is `unrunnable` with reason `not-a-command` - its own outcome, never FAILED,
and it never reaches a shell.
It deliberately does NOT scan on to a later span. "The first span that LOOKS
like a command" invents commands out of prose: in that same example brief it
would have run `whoami` and `login`, two real binaries a sentence happens to
name. An absent measurement is honest; a guessed one is not.
The shape check applies to prose spans only. Inside a shell-tagged fence the
author has already declared shell, so `[ -f x ] || exit 1` still runs.
The rubric follows: a NOT RUN result is never on its own a finding. The
Partial row now describes half-built DELIVERED CODE, and the reviewer gets a
table of the three reason strings - no-command, placeholder, not-a-command -
with what each says about the sentence rather than about the code.
Not covered, stated for the record: a multi-token span whose first token is a
non-executable file (`tests/golden/login.stdout --check`) still runs, and a
criterion whose command is real but whose binary is absent still reports the
shell's exit 127 - that is a true measurement of a missing binary, not a
parse artifact.
Red first: 4 runner tests + 1 doc-consistency pin failed before this change.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The runner read bullet lines only. The repo's own example plan writes its
whole acceptance run as a fenced bash block, so `## Verification` parsed to
ZERO criteria, the runner exited 1, and Phase 7 forbade `result: completed`
- a correct plan felled every single-session run. Measured 2026-09-18 on
6cafb4c: none of the repo's plan artifacts exited 0.
Fences are now read twice over, for two opposite reasons:
- a `## ` heading INSIDE a fence is quoted text and no longer opens a
section. examples/02-real-cli/REGENERATED.md is a report that quotes a
plan outline inside one fence; it used to yield an empty section that
read as "0 of 0", and now yields the honest NO_VERIFICATION_SECTION.
- a shell-tagged fence inside the section holds the commands. The tag list
is closed (bash/sh/shell/zsh/console/shell-session): an untagged fence is
more often expected OUTPUT than input, and inventing a criterion from
output is the failure this file exists to prevent.
Blank and comment-only lines inside the block declare nothing. A `$`/`>`
console prompt is stripped; a `#` root prompt is NOT, because it cannot be
told from a comment and running a comment is the worse mistake.
Measured after the fix (parse only - one example names a fictional CLI):
examples/01 6 criteria, plan-template 2 (both placeholders, correctly NOT
RUN), the two runner fixtures 2 each, plan-run-C 1, REGENERATED.md 0 with
NO_VERIFICATION_SECTION.
Divergence from the order's premise, stated for the record: it said 2 of 3
example plans write `## Verification` as a fenced bash block. Ground truth
is 1 of 3 - REGENERATED.md has no section of its own at all - and the
example plan's block holds 6 command lines, not 5.
Red first: 4 of the 6 new tests failed before this change.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The operator decided on 2026-09-18 that the two checks must stop measuring a
phrase and start measuring behaviour. The reason is the gate's own caveat: a
phrase probe closes on rewording, so "Phase 7 no longer says 'Skip for
trekplans'" and "the rubric no longer says 'exists and passes'" could both have
been satisfied by an edit that changed no behaviour at all. Both entries now
point at code a test exercises:
D-03 lib/**/*.mjs exports runPlanVerification
D-04 lib/**/*.mjs exports formatCriteriaEvidence
Verified open against the pre-fix tree (8d1669e) and closed against this one —
a check that cannot be seen to fire is not evidence.
What the probes can and cannot prove is now stated by the gate itself rather
than left to the reader. `PROBE_NOTES` carries one note per kind, the detail
line prints a note for every kind PRESENT in the row (and none for a kind no
entry declares), and the open/closed tags name the kind instead of labelling
`phrase` alone and leaving every other kind unlabelled. A behaviour probe
proves the capability exists; it does not prove a prose phase calls it — the
wiring is pinned by tests/lib/doc-consistency.test.mjs, and the gate says so.
THE DENOMINATOR MOVED ON PURPOSE. `tests/fixtures/end-state-frozen.json` and
the `FROZEN` literal in `tests/scripts/end-state-gate.test.mjs` carry new
signatures for D-03 and D-04, amended together and dated in both places. That
is the freeze mechanism working, not a bypass: the integrity check went
VIOLATED the moment the checks changed and stayed red until the amendment was
written down. The list may change — only as a decision said out loud. Nothing
else about the denominator moved: seven defect ids, three experiment ids, and
the agents/decisions/freeze configuration are unchanged, and no entry was
removed.
Gate after: defects 0 of 7, registry intact, still RED and exit 1 on the other
four rows — which is correct.
Suite: 1120 (1118/0/2), up 3.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The rubric required `brief-conformance-reviewer` to classify a Success
Criterion as Full only when "its verification command/test exists and passes".
Its tools are `Read`, `Glob`, `Grep`. It cannot run anything, so "passes" was
either guessed from the command's mere existence or quietly downgraded to
"exists" — a BLOCKER-tier rule key resting on an impression.
The reviewer stays read-only — a reviewer that executes the code it reviews is
not an independent reviewer. The command does the running instead:
- `/trekreview` Phase 4.5 runs the brief's `## Success Criteria` commands
through `lib/verification/criteria-runner.mjs --brief --evidence` and captures
the block as `sc_evidence_block`, pasted verbatim into the reviewer prompt in
Phase 5. The exit code does not stop the review — a failing criterion is
exactly what the review exists to find.
- `formatCriteriaEvidence` builds that block in code: one row per criterion with
the command, the exit code and the first output line. Chose a code-built block
over an orchestrator-written summary so the orchestrator cannot narrate a pass
that never happened.
- The rubric now judges the supplied result: `PASS` supports Full, `FAILED` /
`BLOCKED` is `Broken` with the exit code cited, and `NOT RUN` is the absence
of a measurement — never evidence in either direction.
- Phase 4.5 is skipped in `quick` mode: that mode does not launch the
conformance reviewer, so there is nobody to hand the result to.
Red first: seven tests in `tests/lib/criteria-runner.test.mjs` against a
committed brief fixture whose three criteria pass, fail, and are prose-only.
The two doc pins were verified red against the pre-fix files (rubric asked
"exists and passes"; no Phase 4.5; the block reached nobody).
Suite: 1117 (1115/0/2), up 9.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
A trekplan's `## Verification` section is where the brief's success criteria
land. Phase 7 opened with "**Skip for trekplans.**", and only the multi-session
wave path (Phase 2.6 Step 3) ran master verification. A plan executed in ONE
session therefore reported `completed` without ever running the criteria it was
measured against — the executor's own belief was the only evidence.
The check now exists as code, not as an instruction:
- `lib/verification/criteria-runner.mjs` parses the criteria an artifact
DECLARES (a plan's `## Verification`, a brief's `## Success Criteria`), runs
each command, and returns a verdict built from exit codes. Fail-closed
throughout: a placeholder, a prose-only criterion, or an unavailable screen
is `unrunnable`/`blocked`, never `passed`. A plan with no `## Verification`
section exits 1 — a plan that promises no end-to-end check cannot be reported
as verified.
- Every command is screened through the plugin's own PreToolUse denylist
(`hooks/scripts/pre-bash-executor.mjs`) before it reaches a shell. Chose
invoking that hook over its documented stdin protocol rather than copying its
rules, because a command spawned from node never passes through the Bash tool
and so the hook cannot fire by itself — this keeps exactly one denylist.
- Phase 7 is now "Exit / verification check": session specs run the exit
condition, trekplans run the criteria runner. Phase 4's entry-condition skip
for trekplans stands — a plan carries no entry condition; the exit side is
not symmetrical.
- A failing criterion FELLS the run: `plan_verification.status != "passed"`
forbids `result: completed`. That is clause 2 of the stop-signal contract,
now enforced on the single-session path too.
Red first: `tests/lib/criteria-runner.test.mjs` (26 tests) against two committed
fixture plans, one of which declares a criterion that fails on purpose. The
doc pin in `tests/lib/doc-consistency.test.mjs` guards the wiring — a capability
no phase calls is the same defect wearing a lib/ file; verified red against the
pre-fix Phase 7 (skip present, runner absent, no fell-the-run clause).
Suite: 1108 (1106/0/2), up 27 from 1081.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
D-07 had been closed on CLAUDE.md alone. The same false claim lived on elsewhere:
- README.md's "Switch the planning model" said four commands default to opus.
- The same README section offered a sed recipe for `model: opus` frontmatter lines, which
0 of 7 command files have.
- commands/trekresearch.md said "the orchestrator runs on Opus".
Since v5.9.0 no command pins model:, so the orchestrator follows the session model.
- README: the section now says how it actually works. You pick the orchestrator's model with
the session model (`claude --model sonnet` or `/model`). Sub-agent models are resolved at
the spawn sites: brief phase_signals, then profile phase_models, then the agents/*.md pins
as fallback. `--profile economy` still moves the sub-agents to Sonnet.
- trekresearch Launch rules: "Use model: "opus" for all sub-agents" contradicted the same
file's own three-layer resolution, which v5.9.0 wired into the spawn sites and the file
documents in Phase 1 and Hard rules -> Cost. The rule now injects
`phase_signal_result.model` with agent frontmatter as the fallback, and says the
orchestrator follows the session model. Nothing changes under the default premium
profile: it still resolves to opus. The engine=swarm note now names the resolved-model
injection as the anchor, instead of the removed literal.
- Two doc-consistency pins were written first and failed before this change:
- no opus-orchestrator claim in README/CLAUDE.md/trekresearch, and no `^model: opus$`
recipe;
- the Launch rules name `phase_signal_result.model` and carry no blanket opus rule.
- Not touched: the follow-up agent in the default-off STORM phase still says model: "opus".
That is part of an experiment whose fate is an operator decision.
End-state gate D-07: open -> closed. Defects 3 -> 2 of 7 (D-03, D-04 remain, by design);
registry integrity intact. Suite 1081 (1079/0/2), run on a clean export of the index.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
An independent adversarial review of the end-state gate reproduced a GREEN result, exit 0,
with the gate's 18 tests passing. Only the registry and the STATE markers were edited; every
other file stayed byte-identical. The judged party owned the denominator, and nothing
guarded it. This change closes that finding and three more, and reopens a defect the gate
had closed too early.
Registry integrity (the blocker):
- tests/fixtures/end-state-frozen.json freezes the denominator. It holds the 7 defect ids
and 3 experiment ids, each with a sha256 signature of its check (canonical JSON, key
order irrelevant), plus the exact agents / decisions / freeze configuration.
- The rule: an entry may close; it may never disappear or have its check changed. New
entries are allowed. spawnSites may never include agents/.
- The test file pins the manifest literally, with a comment that the denominator was
frozen on 2026-09-17 and that changing it is a decision. The gate verifies the registry
against the manifest on every run.
- A violation makes the gate red and names what moved. A missing manifest makes integrity
n/a, which is also red.
Dormant means "never spawned", not "never mentioned":
- An agent counts as spawned only when a command names it in a spawn instruction: a row of
a table headed `Agent`, a line that starts with Launch/Spawn, or a **name** block followed
by a Prompt: line.
- Prose, negations, HTML comments and fenced code never count. Block quotes cannot match
either, because every form is anchored at the start of the line.
- Re-measured under this definition: still 1 of 20 (synthesis-agent). Per agent, every other
spawnable agent has a spawn instruction in at least one command.
A fifth tally, feat-after-freeze:
- It counts commits after the `end-state-freeze` tag whose subject matches
^feat(\(|!|:).
- The row is n/a, and therefore red, when there is no tag yet, the root is not a git work
tree, or the root is not the top of its work tree. It is never 0.
Honest output:
- Every registry entry now declares its probe kind (phrase or byte).
- Open phrase probes are labelled as such, and closed ids are listed. The output states that
a closed phrase probe is evidence, not proof of behaviour. D-03 and D-04 stay open and
labelled; how they are fixed is still to be decided.
- The decisions row now says it counts ticks, not verified decisions.
D-07 reopened:
- Its check now also covers README.md and commands/trekresearch.md, where the "orchestrator
runs on opus" claim still lives. README even ships a sed recipe for `model: opus` lines no
command has.
- Defects are 3 of 7 until the separate docs fix lands.
Three surviving review mutants were killed with tests:
- an empty glob over an existing dir is silent;
- the header counts n/a rows as zero;
- a dormant-row error reads as 0.
Measured on a clean export of the index:
- Mutation harness, adapted from the review's: review code mutants 18 of 18 killed. Four of
them were re-targeted at the equivalent new code. M02 survived until a test with an
intact registry plus a missing freeze tag was added.
- New-logic mutants: 12 of 12 killed. One equivalent mutant (block-quote stripping) was
removed together with the dead clause it targeted.
- Registry attacks: 7 of 7 killed.
- The review's combined green attack (registry + STATE only) is now RED, exit 1:
"defects: D-03 is frozen but missing from the registry".
- Gate tests 38/38. Suite 1059 -> 1079 (1077/0/2).
- Gate: RED, defects 3 of 7, experiments 3 of 3, dormant 1 of 20; decisions and
feat-after-freeze are n/a in a clean export.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Voyage now has a destination that can fail: finish the phase-2 pipeline, close the open
experiments, freeze. This adds the gate that measures the distance to it. Nothing is
fixed or removed here; every defect and every removal is its own change.
scripts/end-state-gate.mjs counts four tallies; finished = all four at 0.
defects listed in scripts/end-state-registry.json, each with a runnable check
experiments listed in the registry, each with a runnable check
dormant-agents spawnable agents no commands/*.md references (structural, word-bounded;
files carrying the reference-document marker are excluded)
decisions open operator decisions in the local STATE.md, by a fixed marker
Exit 0 green, 1 red, 2 usage/registry error. `--json` for machines.
Fail-closed by construction: an entry with no check, or whose check cannot run (missing
file, empty glob, missing section), is NOT FELLABLE and counts as open; a missing STATE.md,
a missing section, or an unmarked list item in it makes the decisions tally n/a, which
keeps the gate red. The decisions row is therefore n/a in any clean clone.
Result today (clean export of the index): RED, 0 of 4 tallies at 0 -
defects 7 of 7, experiments 3 of 3, dormant agents 1 of 20, decisions n/a.
With the local STATE present: decisions 11 of 12.
Verified in both directions: 18 fixture tests pin each tally at 0 and above 0. Each of the
10 registry checks was measured open on this tree and closed after a simulated fix on a
throwaway copy (10 of 10). That run caught a too-broad D-03 check - Phase 4's legitimate
entry-condition skip also matched - which is now scoped to the Phase 7 section.
Suite 1041 -> 1059 (1057/0/2), also run on the clean export.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The two "High-effort behavior (v5.1.1)" pins still described the rules as
"Decision B + gemini-bridge" and "contrarian-researcher + gemini-bridge
always-on". Both became wrong in 1ca48e0: trekplan's Pass 2 is now
"unavailable, skipped" and trekresearch forces only contrarian-researcher.
npm test stayed green throughout, and that is the point. The pins match on the
heading regex, not on their own message, so a stale message can never fail
them — and this file is structurally excluded from the S95 live-surface
scanner, because the S95 block is itself full of the word it bans everywhere
else. The blind spot is now written into the S95 comment rather than left for
the next reader to rediscover: when the high-effort rules change, these two
messages have to be re-read by hand.
Suite 1041 (1039/0/2), unchanged.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
gemini-bridge is dropped by operator directive (three repetitions). The drop is
permanent, not a wait-for-SDK-upgrade state, so the change clears every LIVE
surface that could still steer a run toward the agent and leaves the historical
record alone.
Live surfaces cleared: agents/gemini-bridge.md deleted; trekresearch (bridge
launch block, --local help, high-effort always-on pair, stats record,
degradation list), trekplan, trekbrief, research-orchestrator (mode table,
agent table, prompting block, summary line), README (feature prose, mode table,
agent prose, mermaid EXTERNAL node, conditional legend, optional-MCP
requirement, --local section), CLAUDE.md, settings.json (the whole
trekresearch.geminiBridge block), both templates, architecture.md,
command-modes.md.
trekplan high-effort Adversarial Pass 2 now degrades EXPLICITLY: it emits its
section with status "unavailable, skipped" instead of failing or vanishing. A
high-effort plan carrying no Pass 2 marker is indistinguishable from one whose
Pass 2 crashed, which is the failure mode this wording exists to prevent.
gemini_used is deliberately KEPT as a vestigial trekresearch stats field pinned
to false. Removing it would break the observability export schema for existing
consumers, and the directive was about the agent, not the field.
Not touched: CHANGELOG history and the measurement/decision docs keep their
gemini references. They record what a past version did or what was measured
then; rewriting them is the same defect class as bumping a version string
inside a measurement doc.
Driven test-first. Five new pins in tests/lib/doc-consistency.test.mjs, verified
RED before the edits, including a KNOWN-POSITIVE CONTROL asserting the
historical records still DO carry gemini references — so the empty result on
live surfaces is a measurement and not a broken query (Verifiseringsloven
ansikt 4). Agent inventory 24 -> 23 (20 spawnable + 3 orchestrator reference
docs); the <example>-block floor moves 34 -> 32 because an agent legitimately
left the inventory, not because examples went missing from a surviving one.
Docs: docs/T1-cc26-delegated-orchestration.md §8 item 3 claimed both the §6
synthesis-agent PoC and the §5 bake-off were "designed but unbuilt". That was
written in S7 and falsified the same afternoon by S12, which ran the §6 PoC and
recorded Δ main-context (faithful flow) = 0.0%, NEGATIVE. The stale wording is
what caused the settled PoC to be re-ordered as new work on 2026-09-02, so it is
struck rather than deleted and §6 gained a RUN AND DECLINED status block. The
finding is structural, not stochastic: Phase 5 spawns the exploration swarm
foreground (trekplan.md:158,338-341), so the outputs are already resident in
main before Phase 7 — delegating only the Phase-7 digest evicts nothing.
Also measured 2026-09-03 (CC 2.1.259): claude -p --output-format stream-json
runs on subscription auth with no ANTHROPIC_API_KEY and now emits a
subagent_stats block, so S12's environment-block premise is half stale. Recorded
in §8 item 4. It lowers the cost of §5; it changes nothing about §6.
Suite 1041 (1039/0/2), up from 1036 by exactly the five tests added.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Follow-up defect in the reviewer accounting added by e2aec01, found by review
and confirmed by probe before fixing.
validateFindings only WARNS on a missing `reviewer` field, so a payload can
fail schema while carrying no name. ingest then records `reviewer: null`, and
runContract turned that null into the literal reviewer name "unnamed reviewer".
MEASURED before the fix:
runContract([{findings:[{file:'x.mjs',line:1,rule_key:'NOPE',severity:'MAJOR'}]}],
{expectedReviewers:['code-correctness-reviewer']})
-> missing_reviewers = ["unnamed reviewer", "code-correctness-reviewer"]
One failure, two entries, one of them an agent nobody launched. The
`reported.delete(s.reviewer)` line was also inert for that case, since a null
name was never in the set to begin with.
Fix: skipped payloads are split by whether they carry a name. Named ones go to
missing_reviewers as before; anonymous ones increment the new
`unattributable_payloads` count, which forbids ALLOW on its own - so stripping
a reviewer name from a payload cannot restore ALLOW, and the floor does not
depend on the caller passing expectedReviewers. `allow_blocked_by` reports the
two facts separately: `missing-reviewer:<name>` and `unattributable-payload (n)`.
The old behaviour never produced a false ALLOW - it failed in the safe
direction - but it named a reviewer that did not exist, which is the kind of
output an operator would chase.
Iron Law: two failing tests first (double entry; anonymous-payload-alone must
forbid ALLOW), then the fix.
Also verified in this pass, by temporarily adding a fake reason to
UNVERIFIED_REASONS: the prose-vocabulary pin does go red when a reason is
declared in the lib but missing from agents/review-coordinator.md. A pin that
cannot fail is not a pin.
Suite 1034 (1032/0/2) -> 1036 (1034/0/2), 0 failures.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
computeVerdict counted only the findings handed to it (reasoned.kept), so a
finding removed by Pass 2 or Pass 3, and a reviewer whose payload was thrown
away or never arrived, were arithmetically identical to a finding that never
existed. All three pushed the verdict toward ALLOW.
Measured before the fix (probes, 2026-09-01):
- a BLOCKER with a 101-character title -> ALLOW (Pass 2 succinctness)
- a payload with one ad-hoc rule_key is skipped WHOLE at ingest, taking a
valid BLOCKER sibling with it -> ALLOW
- a reviewer that never reported -> ALLOW
Pass 3's own no-citation / unknown-rule_key branches turned out unreachable
through runContract (validateFindings rejects those payloads first), so the
reachable exposure was Pass 2 plus the skipped/absent reviewer.
THE OPEN DESIGN DECISION, and why it went against the order's default.
The order proposed: indeterminate file-existence YES, plain succinctness NO
("a too-long finding is not an uncertain finding"). I kept the first and
overrode the second, on one principle:
A removal is `dropped` only when the test REFUTED the finding as a claim
about this codebase. Every other removal is `unverified`.
Succinctness and actionability read a `.length`. They never examine the claim,
so they cannot establish the finding is unreal - and dropping a BLOCKER for a
101-character title is precisely the fail-open shape being fixed. Three things
settled it:
1. Under the order's default the fix would have been almost inert. Pass 3's
drop branches are unreachable via runContract, so leaving Pass 2 out would
have left the only reachable finding-level exposure open.
2. Cost asymmetry, priced rather than asserted: the verdict is not a gate.
Handover 6 feeds `findings` filtered to BLOCKER+MAJOR into /trekplan
(commands/trekplan.md:218); `verdict` is optional metadata
(docs/HANDOVER-CONTRACTS.md:353). Nothing loops or re-plans on WARN. So a
false `unverified` costs WARN plus a printed reason; a false drop costs a
silent ALLOW over a live BLOCKER.
3. unknown-rule_key joins them for the same reason: an ad-hoc key is a real
defect wearing the wrong label, and v5.1.1 high-effort mode already KEEPS
those, normalised to PLAN_EXECUTE_DRIFT. Refuting them at normal effort
while keeping them at high effort would be incoherent.
no-citation stays a drop: a finding whose file is empty or whose line is
negative names no location, so it makes no checkable claim at all - the one
deterministic refutation, and what the Pass 3 prose already said it was.
Iron Law: tests/lib/coordinator-contract.test.mjs first, red (missing export +
the three measured ALLOWs), then production code. Two existing assertions were
updated AFTER implementation as contract changes, not to make the red pass.
A known-positive control pins that ALLOW is still reachable - without it,
"no ALLOW" is not a fail-closed contract, only a broken one.
lib/review/coordinator-contract.mjs
+ classifySuppression / REFUTING_REASONS / UNVERIFIED_REASONS - one
vocabulary owned by the lib, including the tokens only the LLM
coordinator emits (accuracy:refuted, file-existence:refuted/indeterminate),
so prose and lib cannot drift. Unclassified reasons default to unverified:
the default fails closed.
~ judgeFilter / reasonablenessFilter return {kept, dropped, unverified}
~ computeVerdict(findings, {unverified, missingReviewers}) -> + allow_blocked_by.
Never raises a verdict, only withholds ALLOW. Unverified findings are NOT
counted into a severity tier: their severity was never substantiated, and
counting it would be invention.
~ runContract(payloads, {expectedReviewers}) -> + unverified,
missing_reviewers, allow_blocked_by. `suppressed` stays the union of
dropped + unverified, so existing consumers (gold-eval) keep their meaning.
agents/review-coordinator.md - Pass 2/3 tables gain a fate column, new
"Suppression is two-valued" section, Pass 4 threshold table gains the two
fail-closed rows, Executive Summary must state a withheld ALLOW, Suppressed
Findings tags each line [dropped]/[unverified]. Pass 3's unknown-rule_key
bullet explicitly says high-effort does not reach that branch, so the same
input never has two documented fates.
commands/trekreview.md - Phase 5 "Reviewer accounting": the expected set is
written down before the spawn, a silent reviewer gets one re-ask and then
STOP. That extends the pattern already in the file (schema failure -> 2
bounded re-asks -> "do not feed unvalidated findings to the coordinator") to
the other two ways a reviewer goes missing, rather than softening it to WARN.
The lib's missing_reviewers stays as belt-and-braces for direct callers.
docs/agent-return-channel-defect.md - the "inferred, not observed" caveat on
the unnamed arm above 66 lines is struck: akashic-intelligence S27
(f168630) measured 2/2 unnamed agents returning against a 4370-line plan,
30449 B and 10989 B, both valid JSON. Recorded with akashic's own two
caveats intact - the measurer owns the finding, and byte-identity between
the returned string and the file on disk was not proven. The separate S25
named-arm figures are left standing; these are two measurements, not a
correction of one by the other.
No release, no version bump, no tag, no catalogue ref, no Workflow port.
Suite 1025 (1023/0/2) -> 1034 (1032/0/2), 0 failures.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
D-census (order 6242020304, from .claude, 2026-08-20/21) measured that
registry.npmjs.org/voyage answers 200 with someone else's package: "Advanced
HTTP Routing System for Node.js" (NEURS/voyage, v0.0.1, 2022). This manifest
declared `"name": "voyage"` with no `private` flag, so nothing stopped an
accidental `npm publish` against a name we do not own - and publishing is
one-way.
This manifest is test tooling for a Claude Code plugin distributed through the
marketplace catalogue (`ref: vX.Y.Z`), never through npm. The sibling
non-package manifests (okr, repo-mailbox, repo-standard) all carry
`private: true`; voyage was the exception.
Operator decision S93: option A (set `private: true`), not option B (scope the
name to `@<org>/voyage` for a future publish) - there is no publishing plan,
so B would only defer the same choice.
Tests first (Iron Law): tests/lib/doc-consistency.test.mjs pins
`pkg.private === true`, seen red (actual `undefined`) before the manifest
change.
New baseline: 1025 tests, 1023 pass / 0 fail / 2 skip (was 1024: 1022/0/2).
No `npm publish` in any form, no version bump, no tag, no catalogue change.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude Code 2.1.218 changed /deep-research to start only when invoked
manually; from there the Skill tool refuses a model invocation outright
with `disable-model-invocation` (measured in a real `--engine deep-research`
run 2026-09-01 18:32Z - the SC3 fallback to swarm held). The engine was
built against 2.1.196 and the prose still promised a path Claude Code has
removed ("requires Claude Code 2.1.154+").
The flag is KEPT as an additive opt-in that never hard-fails. Prose only:
no lib/ change, no adapter-contract change, no default change, no version
bump.
- commands/trekresearch.md: flag bullet states the closed window
`2.1.154 <= CC < 2.1.218`; the pre-gate gained an UPPER ceiling (still a
numeric comparison, not a string one) that skips straight to the fallback
with reason `disable-model-invocation`; step 3 names the Skill-tool
refusal as a known failure manifestation; step 4 lists the reason tokens.
- docs/command-modes.md + README.md: same window, one sentence each, on the
reference row itself.
- CHANGELOG.md: Unreleased/Docs entry.
Tests first (Iron Law): tests/lib/doc-consistency.test.mjs gained a pin
requiring 2.1.218 + disable-model-invocation on all three surfaces, on both
reference rows, and in both load-bearing regions of the command (flag
bullet + pre-gate). Seen red on all three surfaces before the prose change.
tests/commands/trekresearch-engine.test.mjs unchanged and green.
New baseline: 1024 tests, 1022 pass / 0 fail / 2 skip (was 1023: 1021/0/2).
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Follow-up to 63e78c5. Adversarial review found that the fix had reintroduced,
in a smaller form, the exact defect the order was filed about.
1. The rewritten Check 2 block opened with
`git ls-files --error-unmatch "$PLAN_PATH"` while the assignment lived in
the prose above it ("Set PLAN_PATH to the plan path, then run:"). Nothing
upstream sets it — Check 2 is Phase 2.55, and REPO_ROOT/WORKTREE_DIR are
only created in Phase 2.6 Step 1, which runs after. An agent copying the
block verbatim would have run it with PLAN_PATH empty. The note was prose,
the code was what ran. The block now carries
`PLAN_PATH="{plan-path}"` as its first line, the same placeholder idiom
the rest of the file uses (`BRANCH_NAME="trek/{slug}/session-{N}"`).
The three Check 2 tests could not have caught this: they injected
PLAN_PATH through the environment, supplying what the doc has to supply
itself. They now substitute `{plan-path}` the way an agent does, assert
the placeholder is present, and pass PLAN_PATH="" in the environment so a
block that fails to assign it goes red. Control run with the assignment
line stripped: `fatal: empty string is not a valid pathspec` -> exit 1.
2. Both copied blocks contained an em-dash (one in an `echo` string, one in a
comment). Shell that bash 3.2 executes stays ASCII — a multibyte char
under `set -u` has crashed it before. Replaced with plain `-`; the prose
outside the fences keeps its em-dashes. New test asserts both blocks are
ASCII-clean, with a known-positive proving the detector fires on an
em-dash.
Suite 1022 (1020/0/2) -> 1023 (1021/0/2). No version bump, no release.
63e78c5 stays valid in history: the order archive and two coord messages
point at it.
Co-Authored-By: Claude <claude-opus-5>
Two independent defects took down a real voyage on macOS today
(llm-ingestion-okf, wave 1, zero steps executed). Both paths led to the same
end state: the worktree had no plan.
1. Phase 2.6 Step 2a' derived the project relpath with
`realpath --relative-to`, which is GNU coreutils only. On BSD realpath
(macOS default) the substitution fails silently: PROJECT_REL ends up
empty, `mkdir -p "$wt/"` and `cp ... "$wt//"` both succeed, and
brief.md/plan.md land at the worktree root where no child session looks.
The portable form existed only as a prose note saying an operator "may
substitute" it — the note was prose, the code was what ran. The block now
uses `python3 -c os.path.relpath` (stdlib), resolves both operands with
bare realpath (identical on BSD and GNU, and correct across the macOS
/var -> /private/var symlink), and aborts loudly when the relpath is
empty or escapes the repo instead of dropping files at the root. The
coreutils note is deleted rather than extended: two forms means the next
reader picks, and that pick is what failed.
Measured on this machine 2026-08-31 (Intel Mac, no coreutils):
`realpath --relative-to=...` -> `realpath: illegal option -- -`;
bare `realpath /Users/ktg/.claude` -> correct path, exit 0.
2. Phase 2.55 Check 2 ran `git add {plan-path}` unconditionally. When the
project directory is gitignored (`.claude/projects/` is tool-managed and
local-only — normal, not exotic) the add refuses and the plan never
reaches HEAD. Check 2 now probes with `git check-ignore` and branches:
tracked -> nothing; untracked -> add + commit as before; ignored -> step
aside and let Step 2a' be the delivery path. `git add -f` was rejected as
the fix: forcing operator-local artifacts into history publishes them to
whatever remote the repo pushes to. A `check-ignore` exit code other than
0 or 1 is fatal and stops execution — a probe that failed is not a probe
that answered "not ignored".
Also fixed in the same block: `[ -d research ] && cp -r ...` as the last
statement of the loop body made a project without research/ exit the wave
non-zero.
TDD, Iron Law: tests/commands/trekexecute-parallel-portability.test.mjs
extracts both shell blocks from commands/trekexecute.md by grep-able anchor
and executes them, so the tests bind to what an agent actually copies. The
assertions check FILE PLACEMENT, not exit status — the whole defect is that
the broken form exits 0. Controls, all present before the fix: a
known-positive BSD-realpath stub (bare path resolves, GNU flag rejected with
`illegal option`), a negative control running the old GNU form under that
stub and asserting plan.md lands at the worktree root, a known-positive
Check 2 arm where a non-ignored plan is still added and committed, and a
stubbed fatal `git check-ignore` (128). Red first: 7 failed, 2 passed (the
two controls). Green after: 9/9.
Suite 1013 (1011/0/2) -> 1022 (1020/0/2). No version bump, no release.
Order: 20260831T214411Z-941965142-from-.claude (from .claude).
Co-Authored-By: Claude <claude-opus-5>
akashic-intelligence lost /trekplan Phase 9 twice to reviewer agents that
never returned. Reproduced here and measured: the cause is the Agent tool's
`name` parameter, not the agent definitions.
Passing `name` does not label a subagent - it changes its kind. The spawn is
recorded as taskKind "in_process_teammate" (spawnDepth 0) instead of a real
subagent (spawnDepth 1). A teammate's final assistant text is not a return
value; it reaches the parent only if the teammate itself calls
SendMessage(to: "main"). plan-critic and scope-guardian declare
tools: [Read, Glob, Grep] - no SendMessage - so as teammates they are
structurally incapable of returning, whatever the prompt says.
Denominators: named 0/5 returned; named + explicit SendMessage 1/1; unnamed
3/3 (plan-critic and scope-guardian each returned full findings + the JSON
block in ~110s). Model override 2/2 non-returning, so the override is not
the variable. All 5 named agents produced correct final text in their
transcripts - only delivery failed, and that output is recoverable on disk.
The defect is a harness behaviour, so it is documented rather than silently
worked around: docs/agent-return-channel-defect.md carries the mechanism,
every denominator, the two broken queries that nearly became facts, the
unmeasured cells, and a recommended working shape for consumers (use agents,
drop `name`; do not fall back to inline review, which costs the dedup step).
Prevention is pinned, TDD red->green: the four spawning commands each state
the rule and name the mechanism, and doc-consistency derives the spawning set
from the command files so the pin cannot go vacuous.
Suite 1013 (1011/0/2), +5 from baseline 1008.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014MfB5Ecp8vvGyou8uFGxBV
The Phase 4.5 amendment to the Independence hard rule crosses that rule
deliberately, and the crossing is defensible: bounded to Phase 4.5 and the
Phase 5 loop, the initial swarm stays blind, and it resolves a tension the
brief created itself by asking for exactly this mining of Phase-4 output.
The defect was the compensating-control claim. query-privacy-gate.mjs was
named as THE control for the crossing, but it inspects outbound query
CONTENT for paths, repo identifiers and secret-shaped strings. It cannot
prevent a local finding from steering an external agent's question. It
compensates the EGRESS risk; the BIAS risk was left with no control while
the text read as though it had one.
Both risks are now stated separately with the control that actually bears on
each:
Bias - structural, not a gate. The initial external swarm stays blind, so
an independent baseline exists BEFORE anything crosses; the
crossing only ADDS to that baseline; and at effort: high - the only
effort at which any of this runs - contrarian-researcher is forced
always-on, so the brief always carries an adversarial
counter-evidence pass over the result the crossed queries fed.
Egress - query-privacy-gate.mjs, unchanged, with its non-overridable
hard-block tier.
Fixed at both sites: the Hard rules entry and the Phase 4.5 paragraph that
repeated the same attribution.
A doc-consistency pin now fails if the amendment names the privacy gate as
the compensating control again, and requires it to name both
contrarian-researcher and the egress framing - so the two cannot quietly
re-merge.
Review finding 4888ae847240142933469d70bafb6a9c23b7b2eb (MINOR).
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LuGhWAbWyRFBFeemfhxoVv
The bounded-cost NFR asks for explicit ceilings on BOTH axes - max
conversation turns and max discovered dimensions. The turn axis got
MAX_CONV_TURNS, a ledger-backed reader and a PreToolUse enforcer. The
discovery axis got one sentence in Phase 4.5 prose ("append candidates only
while the whole list stays at or below maxDimensions: 8") with no constant
of its own, no reader, and no test that a run exceeding it is caught. That
is the brief_reviewer_iter_cap shape the operator decision warned about: a
cap nothing reads.
checkDimensionCeiling() is the reader, exposed on the CLI as
--check-dimensions N (exit 0 within, exit 1 rejected), and Phase 4.5 step 3
now calls it once the final list is settled instead of merely describing the
bound.
Three deliberate choices:
- The ceiling IS MAX_TOTAL_DIMENSIONS, the constant that sizes the turn
budget. Both axes read one settings.json:16 value, so they cannot end up
enforcing different numbers - a second constant is how that drift starts.
- An unreadable count is REJECTED ('abc', null, undefined, {}, -1, NaN,
non-integers). A cost ceiling that waves through what it cannot measure is
not a ceiling.
- --check-dimensions requires no run id, effort or VOYAGE_STORM_ENABLED.
Phase 4.5 never calls the budget gate - that is why its skip-guard reads
the flag directly - so the ceiling check must not inherit the gate's
preconditions.
The mitigation the review already verified still holds and is unchanged:
MAX_TOTAL_DIMENSIONS bounds actual retrieval cost regardless of how many
dimensions discovery appends. What was missing was anything that FAILS on a
list over the bound, and now a run over it is rejected by exit code.
Review finding 96a3ee51152dfe72aca703f771843f2f3639e7b6 (MINOR).
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LuGhWAbWyRFBFeemfhxoVv
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
The SC asks two things of an effort: high run: that it discovered at least
one dimension AND that the dimension list in the output brief is a TRUE
SUPERSET of the interview-derived ones. activationCheck computed
dimensions - dimensions_baseline >= 1 and returned ok on that alone. A
count delta says nothing about membership: a run that dropped two
interview dimensions and appended three discovered ones is +1 and passed
the check while violating the second half outright. Supersetness was
asserted only by Phase 4.5's prose contract that discovery appends -
nothing read it.
The stats record cannot carry the dimension names that would show it
directly: names are free prose, and lib/exporters/field-allowlist.mjs
denies prose by omission (question, project_dir, brief_path are already
excluded for that reason). So the run attests membership with
dimensions_baseline_preserved, a boolean set in a new Phase 4.5 step 5,
and the gate refuses to call activation OK without it. An ABSENT
attestation fails rather than falling back to the old count-only rule -
otherwise legacy rows would keep passing on the defect.
Producer side wired end to end: the record format, the measurement-fields
prose (five fields -> six), the exporter allowlist, the jsonl-schemas
fixture row, and the --activation-check comment in
docs/storm-measurement.md.
Review finding d2786604458207a5a73478cdcb6a54bbdb92141d (MINOR).
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LuGhWAbWyRFBFeemfhxoVv
Two defects in the adoption gate, both in the direction that flatters
adoption.
1. A non-numeric empty_turns counted as an eligible run.
Number('many') is NaN, and the test was `Number.isFinite(empty) &&
empty > 0`, so NaN fell through to the eligible branch. Measured
before: 0 -> eligible, 2 -> excluded, undefined -> eligible, null ->
eligible, 'many' -> ELIGIBLE, NaN -> ELIGIBLE. The exclusion is one of
the two properties docs/storm-measurement.md names as carrying this
gate's honesty, and the run whose bookkeeping broke is the run whose
numbers deserve the least trust. Now excluded. Absent and null stay
eligible via `?? 0` - a field never written is a genuine zero on a run
where the loop never armed.
2. The printed threshold line said "adopt >= 30.0% on BOTH - decline <
15.0% on BOTH" while decideVerdict evaluates OR on both sides. S82
restored the pre-registered OR rule in the logic (c37bf50d) and left
this line describing the stricter AND gate, one line above the verdict
that OR produced. The summary is the only form of the rule most readers
ever see, so it now states EITHER on both sides and that adopt wins
ties. Found while fixing (1); not a review finding.
A test pins the printed line against the string "on BOTH" so the two
cannot drift apart again silently.
Review finding 24a76c21ffc694cd782cd449212c9502d31aeda6 (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
countTurns-then-appendFileSync is read-then-write. N callers that all
observe used == budget-1 all decide to grant, and the bound is exceeded
by N-1. The comment above allowTurn asserted "Append-only: never
read-modify-write" and named the concurrent case - Phase 4.5/5 may spawn
several agents in a single message - as the reason it had to be. The
decision path was exactly what the comment denied, so the concurrency
claim had nothing under it.
Each grant now creates <data root>/trekresearch-loop-claims/<runId>-<slot>.claim
with flag 'wx' (O_CREAT|O_EXCL) before appending. The kernel picks the
winner per slot, slot numbers are bounded by the budget, and each can be
created exactly once - so total grants for a run cannot exceed the budget
however many callers arrive together. The ledger count now only says
where to start looking for a free slot.
Two of the three tests are deterministic and do not race anything: they
assert the invariant directly by pre-creating claims, including the state
a mid-append competitor leaves behind (ledger 7, slots 1-8 claimed, budget
8 -> deny). That matters because the third test - six real concurrent shim
processes at the boundary - passed even BEFORE the fix, since process
startup jitter serialised them. A race test that passes by luck is not
evidence, so it ships as a real-world regression guard next to the two
that are.
Stated rather than left to be discovered: claim files are empty, at most
budget per run, and never cleaned - the same standing as the ledger, which
also grows for the life of the data root. Reusing a runId across runs, or
two runIds colliding after filename sanitisation, both deny a turn, which
is the safe direction for a budget control.
Review finding 3994491ef1fdba6e0e3645b5b713cbdbdeb2b328 (MINOR).
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
A fractional TREKRESEARCH_MAX_CONV_TURNS below 1 cleared the `n <= 0`
guard on its raw value and only then floored, so '0.5' and '0.9' became
0 and the budget became 0 x MAX_TOTAL_DIMENSIONS = 0: every turn denied,
the loop silently dead rather than bounded.
README.md:229 and docs/architecture.md:15 both promise that invalid
values fall back to 3. docs/command-modes.md:42 enumerated "empty,
non-numeric, zero, or negative" and happened to sidestep the case; the
enumeration is now exhaustive about it.
Measured before: '0.5' -> 0, '0.9' -> 0, '2.7' -> 2, '' / 'abc' / '-2'
/ '0' -> 3. Measured after: '0.5' -> 3, '0.9' -> 3, '2.7' -> 2, and
'Infinity' -> 3 (it is not a cap either).
A cap of 0 is not a narrower cap, it is an off switch. The tests pin
both directions: the fraction falls back, and allowTurn cannot report a
budget of 0 under it.
Review finding fc516799e6042e246a4b62d81903ac27c2efab84 (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
