Quality only, no behaviour change (four cleanup reviewers, one implementer;
npm test 2480/0 on the working tree):
- threat-model.mjs splitBacked(): the one known_outside backing check of
plan-gate (record and bare gate), verdict-gate and review-finalize, with
one why-text; the engines' security keys derived from ENGINES; isSecurity.
- coordinator-contract: "not a security engine" read from ENGINES (a string
engine only), not the code-review literal.
- review-rounds owns trailingBlock, findingsBlockSha, isMajor, isBlocker;
review-answers imports them (review-rounds still imports nothing from it).
prepare keeps the archive bytes it read instead of reading the previous
archive again.
- engine-compare exports rowIn and payloadEngine; finalize uses them.
- plan-gate: one accepted_open builder; the stop-rule check hoisted; one
top-level lookup for --record --brief.
- security-engine: notFullShas(), runCli's usage flag, readScopeList shared
with engine-findings; findReport and reviewRoundSummary module-private;
two dead defaults gone.
- tests: shared plan-gate harness and threat-model brief helpers; the [CNV]
table cases call convertReport in-process, one CLI case per exit path.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
lib/review/security-engine.mjs (decisions 175, 196, 219):
- choose: Claude Security when available and base..head has committed
changes; else /security-review when origin/HEAD resolves and
origin/HEAD...HEAD is non-empty; else no engine (no-engine, no-origin,
empty-diff), which is "not measured", never 0. A git failure or bad
usage is exit 2, never a reason.
- convert: reads the newest CLAUDE-SECURITY-<ts>/ report whose stamp is a
changes scan of exactly base..head; confidence high becomes engine
findings through toReviewerPayload, the rest go to below_threshold and
never into findings. An unverified scan, missing researcher counts,
fewer researchers returned than dispatched, an empty diff or scope, or
a malformed record is exit 2.
- NO_ENGINE_REVIEWER: with no engine chosen the expected reviewer
security-engine never reports, so the verdict gate exits 2.
ENGINES gains claude-security (its own reviewer and brief_ref, the
engines' key) with a per-engine label for the written action; it is a
security engine in isSecurityFinding, RAN_ENGINES, the coordinator
contract (out-of-scope and brief-conflict rules) and the coordinator
prose; engine:below-threshold is an unverified reason fed like
engineOutOfScope. Pins of the changed coordinator prose follow.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The verifier's look at ff46f57 found three fail-safe MINOR findings, all
text that did not yet say decision 221 or said it inaccurately:
- commands/trekplan.md Phase 9 and the plan-gate.mjs comment said only that a
backed finding leaves the count and the stop rule; both now say it applies
to the round's new findings, and a finding counted in an earlier round
stays counted until a reviewer marks it resolved.
- Handover 4 said a known_outside entry "left the counted findings"; it now
says that holds for a new finding of its round, and that a carried copy of
the same id stays counted, so one id can sit in both findings and
known_outside.
- The CHANGELOG Known issues bullet said the loop "then stops" and that the
way on is the operator's choice at the stop rule. The stop rule fires only
when the blocking findings do not get fewer, and a counting security
finding is never accepted (PLAN_GATE_SECURITY_OPEN): the way on is a
reviewer marking it resolved or "New mechanism". The bullet also names the
shared id (two findings at one line and key, one mark resolves both).
No code change.
Part 2 of the E plan, decision 221.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Undone: item 2 of the Part 2 fix round (1be961a). recordVerdict no longer
drops a copy rule A carried as counted when a finding with the same id is
backed this round, and no longer recomputes the counts, `lowered` and the
stop-rule summary for it; the isLowered helper and the SEVERITIES import it
needed are gone. Why: the id is (file, line, rule_key), so a DIFFERENT
backed security finding at the same line and key knocked a counted security
finding inside the threat model out of the count (round 2 PASS, its text
gone), against decisions 218 and 220.
The rule now, as decided: the threat model applies only to this round's
new findings (the deduped findings, before countRound); a finding counted
in an earlier round stays counted, through rule A's carry, until a reviewer
marks it resolved. The gate never counts less. Items 1 and 3-8 of the fix
round are untouched.
Tests: the fix-round case for item 2 now asserts the decided rule (the
carried copy stays counted, BLOCK, the stop rule fires not-fewer, the gate
stops); a new case pins that a different backed finding at the same line
and key leaves the counted one, with its own text, in the count.
The plan-gate header and the known_outside comment, and Handover 4's
known_outside sentence, state the rule. CHANGELOG Unreleased, Known issues:
a finding counted earlier stays counted when an Outside: line approved
later puts it outside, or when it moves to another plan line; the way on is
the operator's choice at the stop rule.
Part 2 of the E plan, decision 221.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
1. plan-review-dedup skips only a null or undefined finding; any other
entry that is not an object (a string, a number, an array) goes on as
before E, a finding with no valid severity that the plan gate counts as
a blocker (it was dropped, so a string blocker recorded PASS).
2. plan-gate --record: a previous finding that rule A carried as counted and
whose id is backed this round leaves the counted set, the counts, the
verdict and the stop rule's summary (it was counted and listed in
known_outside at once: BLOCK, not-fewer, and --accept-open refused).
3. A known_outside entry keeps rule_keys; extractVerdict accepts it (a list
of strings), and the bare gate re-checks with the same keys the recorder
used, so a merged finding whose security key is only in rule_keys is a
WARN, not a STOP.
4. plan-critic, scope-guardian and /trekplan Phase 9's round-2 sentences say
the Critic Verdict also lists known_outside and each is marked by id in
previous. Code already accepts such a mark (dedup passes it; countRound
ignores ids it does not carry; --record removes the entry on true);
pinned in diff mode and full count.
5. The approval prose names ## Threat Model where it named only ## Intent +
## Goal: skills/annotating/SKILL.md (description, step 4, guard list),
docs/command-modes.md, Handover 1's intent_approved_hash row, README
(approval, Approve row, intent approval gate) and CLAUDE.md's /trekbrief
row.
6. threat-model.mjs gains usableInRepo (a brief path relative to the repo
top level) and repoRelativeBrief; --record stores brief_path relative to
the top level, never absolute, and both gates read it from there, so the
gate run from a subdirectory reads the same brief. reviewThreatModel
uses usableInRepo. Handover 4 and the gate header say so.
7. review-finalize's outside pass puts an entry back only when no finding
carries its row yet (engine-compare rowOf): an engine finding listed in
known_outside while its payload is saved went back twice.
8. A test runs scripts/release-check.mjs on a review whose known_outside
entry the brief does not back: exit 2 (control: backed passes the review
check).
Existing tests changed: plan-gate-threat-model's entry-keys assertion now
expects rule_keys (item 3), and its planted non-security entry drops the
security key from rule_keys too, since the gate reads rule_keys (item 3).
Part 2 fix round of the E plan.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The code-correctness reviewer's dimension 6 shrinks to what the engines do
not read: command, skill and agent markdown carrying shell, with Claude
Code's threshold (a concrete attack path, high confidence), the keys
SECURITY_INJECTION or SECURITY_RISK, and threat_model_ref quoting the
brief's Outside: line; the code-level bullets go to the engines.
The coordinator puts a Voyage security finding with a threat_model_ref
into the trailing JSON block's known_outside, never into findings.
review-finalize gains the pass `outside`, right after engine: it only
raises. An entry the brief at the review's brief_path does not back now
(line gone, threat model not usable, an engine finding, not a security
finding) goes back into the findings at its catalogue tier with a Source
line, R-step and raised verdict, as the engine put-back does; the rest are
listed under the new `## Outside the Threat Model` section.
verdict-gate decideOpenFindings (and so scripts/release-check.mjs)
re-checks every entry against brief_path through the new
notBackedOutside and exits 2 for one not backed. review-validator
shape-checks the optional known_outside (REVIEW_KNOWN_OUTSIDE_MALFORMED).
threat-model.mjs gains reviewThreatModel and isKnownEntry for the three.
/trekreview Phase 8.8 lists the known issues outside the threat model
(not answered, not counted); the review template shows the section and
field; Handover 1 names the optional ## Threat Model and its code,
Handover 6 names known_outside and its code.
Part 2, step 2.5 of the E plan.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
plan-gate.mjs --record --brief <brief.md> (a known flag; its value is kept
out of the positional arguments, a missing value is a usage error) applies
the brief's threat model to the deduped findings before countRound when
threat-model.mjs usable() says it may: a backed finding (Voyage's own
security finding whose threat_model_ref equals an Outside: line's text)
leaves the counted set and the stop rule and goes to the new optional
verdict field known_outside ({id, rule_key, text, line}), carried to later
rounds until a reviewer marks it resolved or it is reported again under its
id. The verdict stores brief_path (carried when a later round has none).
The --record line adds known_outside (a count) and threat_model
({applied, why}): a threat model that is not usable backs nothing, every
security finding counts, and the output says why. extractVerdict
shape-checks both new fields.
The bare gate re-reads the brief at brief_path each run: an entry still
backed is a warning, PLAN_GATE_KNOWN_OUTSIDE; one no longer backed (line
gone, approval stale or not logged, brief unreadable, no brief_path, or not
a Voyage security finding) stops the plan, PLAN_GATE_OUTSIDE_NOT_BACKED: it
counts in full. gatePlan takes an optional threatModel for tests.
plan-review-dedup keeps threat_model_ref on a merge only when every merged
copy carries the same one; the S160 known issue is fixed: a null in a
reviewer's findings list is skipped instead of crashing the CLI.
plan-critic and scope-guardian: a security finding needs a concrete attack
path and high confidence (Claude Code's threshold, 167), uses
SECURITY_INJECTION or SECURITY_RISK, and quotes the Outside: line's text in
threat_model_ref when one applies; the json template carries the field.
/trekplan Phase 9 passes the brief path to plan-critic and --brief to
--record. Handover 4 names the two fields, the two codes and the flag.
Part 2, step 2.4 of the E plan.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A brief may carry an optional `## Threat Model` with one line per bullet,
`- Inside: <text>` or `- Outside: <text>`. Present and malformed (no such
bullet, another label or form, empty text, two sections) is
BRIEF_THREAT_MODEL_MALFORMED; absent is today's rule. No brief_version bump
(the ceremony / artifact_store precedent). Sections are found fence- and
comment-aware through intent-approval's new sectionTexts, so the validator
and the hash count the same sections; brief-validator exports
parseThreatModel for the reader.
The intent hash covers `## Threat Model` when present (two sections -> null
hash, as Intent and Goal), so an edited, added or removed threat model
makes the approval stale; a brief without one hashes exactly as before. The
stale message and the /trekplan halt table name the section.
/trekbrief offers the section in its question round when the task touches
a guard, a gate, untrusted input, secrets or publishing, writes it only
when given, shows it verbatim at the Phase 4h approval, and --approve reads
it out. The template documents it; brief-gate-coverage pairs the new code.
Part 2, step 2.1 of the E plan.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- plan-gate: the bare gate's stale-verdict reason no longer says "run the
next round" once the stop rule fired; it says there is no next round, as
acceptOpen already does.
- trekplan Phase 9: "REVISE after the last round" (Fix now with
--extra-round) is qualified "and the stop rule did not fire", pinned in
review-loop-docs.test.mjs next to the [STP] pins.
- plan-gate-stop-rule tests: a planted stop-rule acceptance claiming an open
security blocker stays STOP; a planted acceptance without under:
"stop-rule" stays STOP; the "a blocker -> refused" test now asserts the
blocker refusal; --accept-open under the stop rule covers an open MAJOR
and the gate passes with a WARN.
- review-rounds prepare: when the stop rule is judged (P >= 2) and either
round's JSON block cannot be read, exit 2 (not measured) with "stop rule:
a round has no readable JSON block" instead of skipping the rule. The
[RND] differing-archive and [CAP] fixtures now use readable archives; one
new [STP] test covers an unreadable archive and an unreadable review.md.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
recordVerdict appends each round's summary to a new optional verdict
field `rounds` (carried from the previous verdict; newByClass null for a
round counted in full) and stores `stop_rule`; extractVerdict shape-checks
both. After a fired stop rule --record exits 1 with PLAN_GATE_STOP_RULE
and writes nothing (--extra-round included). The bare gate stops with
PLAN_GATE_STOP_RULE and the operator line in place of the open-blocker and
open-major reasons; --json and --record output carry the decision.
--accept-open after a fired stop rule is allowed with rounds left, covers
open blockers and majors (`under: "stop-rule"`), refuses a counting
security finding (PLAN_GATE_SECURITY_OPEN); the gate then warns.
Known issue fixed: REVIEW_LOG_SECTIONS drops "Adversarial Pass 2 (v5.1.1
high-effort)"; the CHANGELOG known-issue line closes and Handover 4 names
the heading list, the new fields and codes.
Existing tests updated for the planned rule: fixtures that ran a later
round after one with no fewer blocking findings now use a falling count
(plan-gate.test round cap, plan-gate-open-major lastRound, diff-mode
5/18/27 resolve two earlier majors in round 2); the diff-mode CLI pipe
case now expects PLAN_GATE_STOP_RULE (round 3: 2 blocking) after its
clean round 2.
Part 1, step 1.2 of the E plan.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The four profiles, the resolver, the profile validator and docs/profiles.md go;
/trekbrief Phase 3.5 and the brief's phase_signals checks go (an older brief's
key is ignored); MANIFEST_PROFILE_DRIFT and profile_used go. Every Profile,
Composition rule, Sequencing gate and High-effort section leaves the commands.
Decision 209: /trekresearch runs the full swarm with contrarian-researcher as
wave 2 every run; /trekreview and the coordinator run all four passes with no
high-effort normalization. Voyage agents are spawned with no model (their own
model: opus applies); the two built-in spawns pass model "opus". --profile
stays in the parser as a retired flag that swallows its value. §Model & effort
moves to docs/architecture.md; the sequencing-gate eval case goes.
Files removed: 44 (43 from the R3 list + tests/commands/trekreview.test.mjs,
whose every test pinned removed text). Files edited: 43.
Tests: 2467 (2466 pass / 0 fail / 1 skipped) before, 2309 (2309 pass / 0 fail /
0 skipped) after. Durable check: all three groups green, none pending.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
/trekresearch loses Phase 4.5, the bounded Phase 5 loop (Phase 5 keeps its
single pass of at most 2 follow-ups), the --engine flag, the deep-research
adapter and its output self-check. hooks.json loses the pre-agent-cap
PreToolUse entry (README: 9 hooks = 9 scripts). The STORM env vars leave the
docs; query-privacy-gate.mjs stays, called by no command, and says so.
Files removed: 13 (4 docs, 1 hook, 1 lib module, 1 script, 5 tests, 1 fixture).
Files edited: 17. Tests: 2600 (2598 pass / 0 fail / 2 skipped) before,
2467 (2466 pass / 0 fail / 1 skipped, R3 pending) after.
Durable check: group R2 green and no longer pending.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Removes Voyage's measurement, statistics and export apparatus (decision 189;
condition 175 met in step 1) and the R-a leftovers: lib/stats/, lib/exporters/,
the otel-export and post-bash-stats hooks, yardstick, end-state and comparison
gates, synthesis-measure, gold-scorer, docs/observability.md,
examples/observability/, docs/T1-cc26-delegated-orchestration.md and their
tests and fixtures. The six command stats phases and the /trekexecute
main-merge event blocks go; intent-approval --stamp no longer emits
brief-approved. README and docs point to Claude Code's own OpenTelemetry.
Files removed: 52. Files edited: 37.
npm test: 2930 tests (2928 pass / 0 fail / 2 skipped) before, 2600 tests
(2598 pass / 0 fail / 2 skipped) after. removed-surfaces group R1 green.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
R4-R7 of the cleanup list (decision 188): the June trial docs and
fixtures, the three orchestrator reference docs, the dormant
synthesis-agent, code with no caller (project-discovery, bash-normalize,
fidelity-diff, test-census, the next-session prompt validator, arm B and
the --workflow flag) and the fix-round chain. Living docs repointed; the
reasons for in-session orchestration and the all-opus pin are now written
in docs/architecture.md and docs/profiles.md.
New tests/lib/living-paths.test.mjs: living tracked text names only
plugin paths that exist (seen red with 22 dead pointers before this
commit). docs/T1-cc26-delegated-orchestration.md and
lib/review/gold-scorer.mjs stay until R-b: the frozen end-state registry
names them.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- park-attempt-files: parks in the git dir (outside the work tree, so Sub-step C.2 never registers a parked file again), reads a path with a space, names a new file under a header it cannot read, parks a symlink, never overwrites a parked file, and exits 1 while a file the attempt made is still in the tree; the upward diff is saved in one form whatever the git config.
- brief-validator: BRIEF_SC_NOT_RUNNABLE only when a later backticked span is a command; a criterion that only names a flag or a path stays prose (Handover 1 says so now).
- review ids: counted over the final list (runContract), as fill-finding-ids counts review.md; trimmed_count matches rows by id; engine-findings and fidelity-diff use computeFindingIds; the --workflow dedup keeps one source's different findings apart, the decision-23 put-back stays one copy per triplet.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The runner reads the first backticked span and reports such a criterion unrunnable, and voyage:writing-criteria says the validator uses the same allowlist; the validator skipped it (voyage-lekerepo trial 5, finding 1).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Operator decision 56 (2026-10-17): the product shows English.
- Annotation HTML: the intent buttons, sidebar badges and the copied
prompt read Fix / Change / Question. The stored keys stay
fiks / endre / spørsmål, so annotations saved earlier still load.
- /trekreview project-memory approval: "Add the line" / "Not now".
- README, CLAUDE.md, docs/architecture.md, package.json and plugin.json
describe what the product shows; README's hollow-answer line and the
"anslag" in the profile section are English; a Norwegian code comment
in profile-validator.mjs translated.
The Norwegian hollow-answer list in approval-log.mjs and trekbrief.md
stays: it matches what a user types. Both new tests failed on the code
before the change. Suite 2606 (2604/0/2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
/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>
The step check read File: anywhere on the Test first lines, so a 1.9 plan whose only File: stood mid-line validated while the executor, K6 and the red proof read no test file. From 1.9 checkSteps reads the test the way testFirstFiles does; below 1.9 it reads as before (decision 16). Found by the step 5 controller in /trekexecute --session 2; fixed on the operator's decision.
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>
Round 3 (v6.2.0..96cb977, BLOCK: 1 BLOCKER, 8 MAJOR, 2 MINOR), each fixed
behind a test that failed first.
- Every allowlisted runner, not only git, takes plain words and a short list
of options that only read: an option that writes a file or loads code
(--test-reporter-destination, --outputFile, --junitxml, --basetemp,
--import, --config, -p, -o, -exec, a reporter path) is on no list; after
`npm test --` only paths follow; `make test` takes no VAR=value. A built-in
node test reporter (tap, spec, dot, junit, lcov) stays allowed.
- /trekexecute: a restore the guard refuses (destructive git, in the mode
that shows no prompts) or the operator declines is never recorded as
reverted: simplify = "revert-refused" and the run stops before review; a
refused step revert is reported with its paths.
- stepTestsOnly: a fixture document under tests/ is a test file, "e.g." is
not a path, ./ is dropped; the plan-file sweep reads Files: with the same
reader (fieldPaths); the validator hands its parsed fields over.
- plan-validator --steps-from asks for Verify: on a 1.8 plan too.
- skill frontmatter: a value starting with # is a hazard; a quote after an
escaped backslash closes the value. Routing reads kind tags with hasOwn.
- release-check reads scope_sha_end as written (an all-digit sha keeps its
leading zero), and Voyage's own artifacts under .claude/projects/ and
.claude/voyage/ committed after the review do not count as unreviewed.
Suite 2170 (2168/0/2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Round 2 (v6.2.0..0d044f6, BLOCK: 2 BLOCKER, 11 MAJOR, 1 MINOR), each fixed
behind a test that failed first.
- The git runner checks only words /bin/sh passes through unchanged (no
quote, backslash, $, glob or brace) and refuses --output and its
abbreviations: round 1's --output refusal was bypassed by quoting.
- fieldPaths: backticked paths are kept as written, parentheses and all; in
plain text every path-like word counts, and a parenthesised note does not.
- plan-validator --steps-from reads the plan's ## Verification for an
appended End-to-end step, and warns instead of failing under --soft.
- regression-check prints progress_status, the value progress.json takes;
/trekexecute copies it.
- release-check: a plugin in a subdirectory is checked in its own directory,
the suite is not run when a cheaper check already makes the answer exit 2,
and a bad argument or a crash is exit 2.
- Skill routing looks a skill up among skills only, and builds the corpus
vectors once.
- /trekexecute Phase 7.2 says plainly that remediation steps in the review
template's own form stop with a re-plan; making them runnable is a later
order (operator 2026-10-10).
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>
Union lines resolved: CLAUDE.md command table keeps main's /trekresearch
and /trekplan rows and this branch's /trekexecute row. README's
architecture block now counts the three skills main ships (it said 2
after 7b added researching-sources).
Contracts run against the real ones on the merged tree: K10/K11 (plan
validator refuses a piped Regression:, warns on an unknown On failure:;
regression-check passes/fails/absent/unrunnable), S2 (skills/test-first
and skills/debugging exist, voyage:<name> form as 7a chose), K7 (real
review_version 1.1 WARN -> 0, a BLOCK copy -> 1, a 1.0 review with no
verdict -> 2). npm test: 2102 / 2100 pass / 0 fail / 2 skipped.
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 minor points (B8-B12, C13, C14, C16, C17) of the second voyage-lekerepo
trial (2026-10-08), each verified against the code and started with a test
that failed first.
- K10: optional step field `Regression:` - one command the criteria runner
allows, unpiped; plan-validator refuses one that can never run
(PLAN_STEP_REGRESSION_NOT_RUNNABLE). Any plan_version, no bump.
- K11: `On failure:` opens with revert | retry | skip | escalate, or the
validator warns (PLAN_STEP_ON_FAILURE_UNKNOWN); onFailureAction in
plan-schema.
- B8 (operator decision 2026-10-08): minors open after the last critic round
are listed numbered in the Phase 10 summary; the ones the operator picks are
fixed and get one more round (--extra-round when the 3 are spent).
- B11: plan-review dedup merges two reviewers' findings on the same file:line
with the same content (trial pair: Jaccard 0.44, overlap 0.83); the Jaccard
threshold for every other pair is unchanged.
- B12: /trekbrief Step 4c says the reviewer runs in the background and is
waited for, not "foreground, blocking".
- C13: the Phase 4 size count includes .mjs, .cjs, .mts, .cts.
- C14: --evidence shows the first output line on PASS rows.
- C16: findings-schema checks path:line citations in finding prose (error) and
in the prose around the block (warning) against the file.
- C17: git-historian gets the brief, never proposes changing a frozen file,
and names the remote from `git remote -v`.
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>
voyage-lekerepo trial 2 (2026-10-08), report section A; the operator decided
they are fixed before the next release:
- A1: a /code-review finding whose category is simplification, efficiency,
style or readability enters as CODE_REVIEW_IMPROVEMENT (MINOR), not MAJOR.
- A2: recommended_action is the engine's own fix when transcribed, otherwise
a test-first step; never the failure scenario dressed as a remedy.
- A3: a /code-review finding outside the exact range it was given is declined
and listed, but no longer holds ALLOW back; /security-review's still does.
- A4: the manifest must_contain recipe uses grep -E -e ... -- so a pattern
like --sep is not read as an option.
- A5: indented sub-points belong to their criterion (counted), and a
criterion with sub-points and no command warns BRIEF_SC_SUBPOINTS.
- A6: a brief requiring bash 3.2 whose criterion runs plain bash warns
BRIEF_SC_BASH_NOT_PINNED; /trekbrief proposes /bin/bash.
- A7: the plan template's and /trekplan's checkpoints stage the step's files.
Tests fail on 5f9faee first (tests/lib/trial2-fixes.test.mjs, 11 of 14).
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 6, operator decision 2026-10-08
(«samme skala, og du spør»): the critics rated a non-discriminating test
minor in round 3, there was no way to fix it after the last round, it was
built, and /trekreview called the same weakness MAJOR (MISSING_TEST).
- plan-critic, scope-guardian: rate on the review catalogue's tiers; a test
that cannot fail on a wrong implementation is major, never minor.
- plan-gate: an open MAJOR stops (PLAN_GATE_OPEN_MAJOR: revise and run the
next round; PLAN_GATE_OPEN_MAJOR_FINAL after the last round: ask the
operator). --accept-open records "build as is" after their yes, bound to
the round and the plan hash; never for a blocker.
- trekplan Phase 9: REVISE after the last round asks fix now (one extra
round) or build as is, instead of carrying the majors silently.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
voyage-lekerepo trial (2026-10-06) point 14, operator decision 2026-10-08
(«alle agenter, ny briefsjekk bare ved endring»):
- trekplan: the "Adaptive" hard rule (a 10-file project does not need 7
agents) contradicted Phase 5 ("All agents run for all codebase sizes");
it is gone, in line with quality before cost.
- brief-review-stamp.mjs: /trekbrief stamps the brief body when its
brief-reviewer gate passes; /trekplan Phase 4b skips its own review only
while the stamp is current. Stale (edited) or absent (another producer,
or a gate that did not pass) reviews as before. Additive optional
frontmatter fields, documented in Handover 1.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
voyage-lekerepo end-to-end trial (2026-10-06), report points 2, 3, 4, 9:
11 of 13 brief criteria were NOT RUN at review with no warning in /trekbrief;
a plan `git grep` criterion passed validator, gate and three critic rounds,
then felled the run in Phase 7; the End-to-end field and Phase 7's text
search never met; a prose Verify left the test command undefined.
- criteria-runner: runnableCheck() screens a declared check without running
it (same allowlist; an npm run script is not looked up at write time);
/bin/bash tests/<script> allowed; the plan report carries end_to_end,
verified when a passed criterion runs a step's End-to-end command (the
older text form still counts).
- plan-validator 1.8: PLAN_VERIFICATION_NOT_RUNNABLE,
PLAN_STEP_VERIFY_NOT_RUNNABLE, PLAN_END_TO_END_NOT_RUNNABLE,
PLAN_END_TO_END_NOT_VERIFIED (the gate inherits them).
- brief-validator: BRIEF_SC_NOT_RUNNABLE warning; /trekbrief offers a
tests/ script; brief-reviewer no longer proposes unrunnable commands.
- trekexecute: Phase 7 copies end_to_end from the runner; Verify's test
command is its first backticked span.
Measured on the trial's own brief and plan: 11 warnings (the 11 NOT RUN),
and the plan stops on V5 git grep and the unlisted End-to-end command.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
CLAUDE.md command table: each row from its owner (trekplan from order 3,
trekexecute from order 1, trekreview from order 5).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Wave 1, order 3 (P3 plan mode as the start, P2 design as its own part, P9
plan side). Contracts K3-K6 for the later merges.
- plan_version 1.8 (1.7 plans stay valid): Test first on every step, one
End-to-end ("run the thing") step, optional Interface in / Interface out /
Review focus fields, a ceremony class in the header (absent =
architectural), and for architectural plans a ## Design part: module map
without cycles, architecture rules that name their enforcer and the step
that proves them, a requirements check asked as keep / change.
- K3 lib/validators/plan-gate.mjs: the critic verdict is recorded INSIDE the
plan (Claude Code's plan approval hands a hook only the plan file's text),
bound to the hash taken before the reviewers read it; 0 go / 1 stop / 2
could not run; at most 3 critic rounds, then stop and ask.
- K5 lib/verification/arch-rules.mjs: runs the target repo's own
dependency-cruiser or import-linter (installs nothing; 2 = not measured,
never green); --prove --rule shows pass -> fail on a planted violation of
that rule -> pass. Verified against dependency-cruiser 18.5.0 and
import-linter 2.15; madge 8.0.0 left out (missed a planted .mjs cycle).
- K6 lib/verification/plan-scope-sweep.mjs: changed files no step names.
- /trekplan Phases 8-10: design part, bounded critic loop, the gate before
"execute", a plan-mode path through ExitPlanMode (not yet run end to end
inside plan mode). plan-critic 10 -> 12 dimensions; scope-guardian checks
the ceremony.
- Fixed on the way: plan-validator and plan-review-dedup used the
file://argv[1] main guard (no-op under a symlink or a space); CRLF plans
failed every manifest; the dedup dropped finding severity.
Borrowed, credited in place: obra/superpowers, Kiro (docs), addyosmani/
agent-skills, mattpocock/skills, GitHub Spec Kit, bashebr/ai-native-sdlc,
Boris Cherny's public threads.
Suite 1497 (1495 / 0 / 2), 86 new tests.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
