Conflicts on the union lines only: CHANGELOG Unreleased (both orders'
entries kept), CLAUDE.md (/trekexecute row from A, /trekreview row from
B), tests/fixtures/jsonl-schemas.md (trekplan line_ref from B,
trekexecute line_ref from A). Suite on the merged tree 2682 (2680/0/2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The three producing commands name voyage:annotating where they build the page; the description of the page and the freehand revision left them. The skill: the person writes every note, Fix/Change edit only the quoted text, a Question is answered and changes nothing, the approval an edit costs is said before the edit, the page is rebuilt. Research documents on request (decision 62). Red baseline 3 runs per scenario without and with the skill; six eval cases; 11 pins.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The coupling to Claude Code's built-in run skill (wave 4, order A2,
decisions 54 and 64). The plan's "run the thing" step, the executor's
End to end part and the plan template each say in one sentence that the
app is seen and driven with run, and that the verdict is still the
End-to-end: command, because run gives no exit code. The template quotes
the name instead of backticking it: every backticked span on a template
step bullet is read as a runnable example.
R2: lib/skills/routing.mjs keeps a short fixed list of Claude Code's own
skills a quiet case may name as owner (BUILTIN_OWNERS, only run, seen in
2.1.303). For such an owner only "not taken" is checked, and the report
says so; ROUTING_NEGATIVE_WON stands, and an owner on no list is still
ROUTING_UNKNOWN_OWNER. skill-writing-criteria-quiet-2 gets owner=run.
The trekplan.md paragraph is reflowed to its old line count so the stats
line_ref there does not move (order B edits the same file); the
trekexecute Phase 9 line_ref fixture moves by two lines.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
P10's model-free part (wave 4, order A1, decision 63). The routing test now
checks every case in evals/ for from=, not only the skill-tagged ones (R1):
a case with no skill tag is not routed, only checked, and the report gives
both counts ("45 cases checked for from=, 37 routed"). The eight test-set
cases get from=proevesett-eval-suite (d311f3b) or
from=proevesett-intent-gate (3892a83), the commits that added them.
The release gate that reads the last test-set run is written into the
runbook as exempted with its reason (it waits for the fixed test set to run
again) and still says where it goes (scripts/release-check.mjs).
review-630's prototype-tag stub gets from=test: under R1 an unrouted case is
still checked for from=, and the stub tests that a prototype name is never
routed, which stands.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Wave 3 (voyage:reviewing-adversarially, voyage:writing-criteria,
voyage:interviewing), decision 56 (English labels) and decision 59 (trial-5
findings 1, 4 and 7), each with its line under ### Doors. Known issues: the
eleven other trial-5 findings grouped by consequence, and the release
review's 13 MAJOR and 1 MINOR (WARN, no BLOCKER; decision 52).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Version 6.4.0 in plugin.json, package.json, package-lock.json and the
README badge; the Unreleased CHANGELOG section becomes v6.4.0 with its
title unchanged, and its Doors list (all two-way) unchanged.
Release review over v6.3.1..main (a97efb6..4e28dc5, 82 files, operator
decision 52): WARN, 0 BLOCKER, 4 MAJOR, 6 MINOR, verdict gate exit 0.
Under decision 52 the four MAJOR go to Known issues, no fix round:
ef1633b6 (a dedup merge lets rule A lower a major in the changed text),
38a8ad34 (regression A also reads a mentioned plain path below 1.9),
20b626e2 and c614baad (two fail-closed exit-2 paths in the verdict gate).
Each was reproduced by running the code at HEAD before it was written
here; 38a8ad34 also against v6.3.1.
Between the review and this commit, b794958 (test-only) lets two docs
tests find the section under its release heading; its own quick review
(4e28dc5..b794958) is WARN, 0 BLOCKER, 6 MAJOR, 2 MINOR, all in test
code, verdict gate exit 0.
The session-id entry under Fixed is narrowed to what the suite does: a
test file run on its own still passes the id to a child it starts
without an env (43 such files measured).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Version 6.3.1 in plugin.json, package.json, package-lock.json and the
README badge; the 6.3.1 CHANGELOG section with its Doors list (all
two-way) and the Known issues from round 11 of the release review (WARN:
0 BLOCKER, 10 MAJOR; the operator chose to release with it on
2026-10-11).
Measured against 6.3.0 for the Doors list: the plan validator reports the
same errors and warnings for 233 plan files, the verdict gate gives the
same exit for 123 review files, and tests-only reads the same for 1408
plan steps, over the marketplace and the test repo.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Version 6.3.0 in plugin.json, package.json, package-lock.json and the
README badge; the 6.3.0 CHANGELOG section with its Doors list and the
Known issues for 6.3.1 (release review round 7: WARN, 0 BLOCKER, 12 MAJOR;
the operator chose to release with it on 2026-10-11).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Wave 1 (five orders, merged 2026-10-06), the fixes from the two end-to-end
trials in the test repo, and the defects an independent reader found in
them. Plan 1.7, brief 2.0-2.2 and review 1.0 files stay valid; the new
fields are optional.
Suite 1972 (1970 pass, 0 fail, 2 skipped).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
S117 fixes (8a56187..84a0621) plus the /trekreview remediation (cb68c4f).
/trekreview verdict WARN (0 BLOCKER, 3 MAJOR, 1 MINOR, 1 MAJOR suppressed
for length); every finding closed red -> green. Operator approved the
release 05.10 (decision 15).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Kildefiks C (e7ac34b..3f073b7) plus the /trekreview remediation test
(5329355). /trekreview verdict WARN (0 BLOCKER, 1 MAJOR: a missing test,
now added); operator approved the release 05.10 (decision 14).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Valgt 6.0.0 (major) because the change is incompatible for a 5.11.1 user:
/trekexecute multi-session no longer finishes in one call, /trekplan
--decompose no longer writes launch.sh, and the per-session turn/budget
environment variables no longer apply. Version synced in plugin.json,
package.json, package-lock.json (both fields), the README badge and the
CHANGELOG heading.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The operator decision of 2026-09-27 stands where every session reads it:
a short binding rule in CLAUDE.md that names the replacement (order plus
starter, subagents inside one session) and the gate that enforces it.
CHANGELOG gets an Unreleased entry; the version is left for the release
round to set.
npm test 1250 (1245 pass, 0 fail, 5 skipped). The gate is unchanged:
the new changelog text adds no hit line.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
5.11.0 ships from the base commit before this branch lands, so the
reference cleanup and its hygiene check go out as 5.11.1: plugin.json,
package.json, package-lock.json (both fields), the README badge and a new
CHANGELOG entry. No tag.
Suite after staging: 1240 tests, 1238 pass, 0 fail, 2 skipped;
verify.sh 7 pass, 0 fail.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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>
Version 5.11.0 in every file that carries it: .claude-plugin/plugin.json,
package.json, package-lock.json (both entries; they said 5.10.0, drift
from before 5.10.1), the README badge, and a CHANGELOG entry for
everything since v5.10.1. Chose a minor bump because /trekplan gains a
halt (a new capability, additive schema). Handover 1 changes for
downstream producers: their briefs stop at /trekplan until approved.
No tag and no catalog bump here: release-plugin.mjs runs in the operator's
push round.
Suite after git add: 1234 tests, 1232 pass / 0 fail / 2 skip in 2 of 3
runs. The third failed only the known timing test otel SC #14 tail-latency
(877 ms against an 800 ms ceiling), which this order leaves alone.
Co-Authored-By: Claude Opus 5.5 <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>
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>
Version sync across the five surfaces that carry it (plugin.json, package.json,
package-lock.json x2, README badge) plus the CHANGELOG section for the 38
commits since v5.9.1. The two docs that print "voyage 5.9.1" are measurement
records and keep the version they were measured against.
Suite 1013 (1011 pass / 0 fail / 2 skip), unchanged by the bump.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018w5KWrbxzmki5wdXULT8nU
Phase 3 (atomic-write) and Phase 4 (validator) used !`...` eager-exec
with unresolved runtime placeholders; the harness executes those at
command LOAD time, so zsh parsed <project-dir> as input redirection and
/trekendsession aborted before the model saw a single instruction.
Both blocks are now plain runtime Bash fences with {curly} placeholders
(shell-inert, trekplan.md convention) and absolute ${CLAUDE_PLUGIN_ROOT}
paths (cwd-relative plugin paths were a latent ERR_MODULE_NOT_FOUND in
any user repo). Phase 1 discovery block keeps its legitimate eager-exec.
Regression guard: new tests/commands/trekendsession.test.mjs flags any
!`-block in commands/*.md containing <angle>/{curly} placeholders, and
pins Phase 3/4 as runtime Bash. Suite 828 -> 832 (830/0/2). E2E: fixed
blocks run with real values write both state files, validator valid:true;
trekcontinue.md:147 runtime-verified self-contained.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013NXzF3F2zAM8S7FCBXCqAb
Version sync 5.7.1 -> 5.8.0 across plugin.json, package.json,
package-lock.json, README badge, and CHANGELOG top entry (guarded by
doc-consistency.test.mjs). Suite 822 (820/0/2).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BJQYC5vpkJWxndS55vQQZ6
The v5.6.1 entry labelled "739 pass" as canonical; 739 is the
`node --test 'tests/**/*.test.mjs'` glob subset, not the canonical gate.
Canonical bare `node --test` from root = 756 total, 754 pass, 0 fail,
2 skipped. Correct the entry; the 0-fail invariant is unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CrTb8ktf1XZWEVwgz5MTTo
Trim the always-loaded token cost of the agent listing Claude Code injects
into every session. The three *-orchestrator reference docs
(planning/research/review) and the dormant synthesis-agent carried
multi-paragraph description: frontmatter (full rationale + CC-2.1.172
history + a usage example) despite never being spawnable from the live
/trek* pipeline; their description is now a single line, with the full
rationale already living — and remaining — in each file's body. ~700
tokens trimmed, no behavior change.
The three orchestrators retain the self-declaration "reference document,
not a spawnable capability" (doc-consistency pin); synthesis-agent retains
its DORMANT / not-wired flag + docs/T1-synthesis-poc-results.md pointer.
Bump plugin.json, package.json, package-lock.json, and the README badge to
5.6.1; prepend CHANGELOG v5.6.1 entry + README What's-new note. Surfaced
via config-audit always-loaded token-audit dogfooding.
Additive — no breaking change, no runtime behavior change. Canonical
node --test: 739 pass, 0 fail (2 skipped); version-consistency + agent
inventory + frontmatter pins green.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CrTb8ktf1XZWEVwgz5MTTo
Bump plugin.json, package.json, package-lock.json, and the README badge
to 5.6.0; prepend CHANGELOG v5.6.0 entry + README "What's new" block for
the S38 loop-hardening work (machine-verifiable completion gate, bounded
recovery cap hierarchy + global budget, iterations_remaining signal,
fan-out hedge harmonization).
Additive — no breaking change. Canonical node --test stays 756 (0 fail);
version-consistency test green across all five version refs.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Closes devils-advocate audit §Top changes #8 (MINOR×MED). Reports the
behavior-test count separately from the doc-consistency prose-pin count so the
cited total no longer oversells behavior coverage, and removes the clearest
reword-fragile redundancies. Conservative scope (operator-chosen): no genuine
regression guard dropped.
1. Suite census (report separately). lib/util/test-census.mjs +
tests/lib/test-census.test.mjs walk tests/**/*.test.mjs and bucket top-level
test() declarations into behavior vs doc-consistency-pins (bucket per file,
regex PIN_FILE_RE), asserting the two sum to the total so neither can drift
silently. Split emitted as a t.diagnostic: behavior=601 doc-consistency-pins=69.
Metric = top-level declarations; node:test's runtime total counts subtests
too and is therefore >= it.
2. Conservative prune (3 tests, each provably subsumed):
- "trekexecute.md still parses v1.7 plan schema" — tautological OR-chain;
real coverage = the plan_version:1.7 template pin + plan-validator /
plan-schema behavior tests.
- "CLAUDE.md mentions all six pipeline commands" — hardcoded six-string list
subsumed by the filesystem-driven "commands table mentions every
commands/*.md file" structural pin.
- "CLAUDE.md mentions /trekcontinue command" — same subsumption.
Each removal leaves an in-place note (why + where coverage lives).
3. doc-consistency.test.mjs header now documents the structural-invariant vs
prose/existence-pin distinction so new pins land in the right kind.
TDD: census test written failing-first (ERR_MODULE_NOT_FOUND before
lib/util/test-census.mjs existed). Suite 699->698 (696 pass / 2 skip / 0 fail):
-3 prune +2 census. plugin validate passes (1 accepted warning).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LqBYc8Ltrk7LipyJmGxXiB
Closes devils-advocate audit #4–#6 (MAJOR×MED). Four additive, non-breaking
changes to the v5.5 framing-alignment machinery:
1. --min-brief-version <ver> gate (audit #4). Opt-in version floor on
/trekplan + /trekresearch, forwarded to brief-validator as --min-version.
New opts.minBriefVersion warns BRIEF_VERSION_BELOW_MINIMUM (never blocks)
when a brief declares a version below the floor; trekreview exempt; absent
opt = no check. CLI shim parses --min-version and skips its value token in
filePath detection.
2. memory_alignment.status field (audit #5). brief-reviewer now emits
status: verified | n_a | contradictions so a score-5 N/A (no memory) is
distinguishable from a score-5 verified-aligned brief — the score≥4 gate
passes in both, status reveals whether the wrong-premise defense ran.
3. Document pre-2.2 = zero framing enforcement (audit #4). HANDOVER-CONTRACTS
§Handover 1 now states the producer-elective hole + two remedies. Also
fixes a stale "current is 2.1" line (current is 2.2).
4. Soften flagship overselling (audit #6). CLAUDE.md Context-Engineering
principle now hedges that main-context relief is asserted-by-design, not
measured (T1 PoC found Δ≈0); README carried no false claim to fix.
TDD: 8 new tests written failing-first (5 validator, 1 trekbrief status pin,
2 doc-consistency cross-file pins). Suite 691→699 (697 pass / 2 skip / 0 fail).
No flagship prose-pin added (deliberate, per S19 anti-bloat).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LqBYc8Ltrk7LipyJmGxXiB
Survivor #3 (bake-off data un-archived): per-run JSON a1..b3.json was never
committed (git diff-filter=A empty), so the medians/jaccard ladder cannot be
re-derived or audited. Commit-path would require fabricated data (forbidden) →
downgraded "POSITIVE" to "opt-in-defensible (single un-archived run)" in
docs/T2-bakeoff-results.md (verdict line + §5 header + new §Reproducibility
caveat) and the v5.5.0 CHANGELOG entry. New doc-consistency pin fails if the
doc re-asserts bare POSITIVE or drops the un-archived disclosure.
Survivor #5 (latent dispatch risk): planning/research/review orchestrators are
inline reference docs no command invokes, yet shipped tools:["Agent",...]. The
harness cannot spawn sub-agents with Agent, so the grant was pure latent risk.
Dropped "Agent" from all three frontmatters; flipped the agent-frontmatter
invariant (its canonical home) from "must include Agent" to "must NOT include
Agent". Removed the duplicate orchestrator pin from doc-consistency to avoid a
double guard (S19 anti-bloat).
Tests 690 → 691 (689 pass / 2 skip / 0 fail). claude plugin validate passes
(1 accepted CLAUDE.md-at-root warning).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LqBYc8Ltrk7LipyJmGxXiB
The operator pointed at ~/repos/claude-code-100x/claude-code-100x/build-site.js
as the annotation reference from the start. v4.2/v4.3 built a bespoke
playground instead. v5.0.0 deleted it. v5.0.1 pointed at /playground
document-critique (Claude-leads, wrong direction). v5.0.2 was operator-led
but too thin (line-click + freeform note, no intent). v5.0.3 finally
matches the reference.
scripts/annotate.mjs rewritten:
- Markdown rendered as proper article HTML (h1/p/li/ul/table/blockquote/pre)
instead of line-numbered raw lines.
- Pencil-toggle annotation mode in the topbar, default ON.
- Select text OR click any element → form popover at cursor.
- Three intent buttons: Fiks (red) / Endre (orange) / Spørsmål (blue).
- Comment textarea. Save (Cmd+Enter), Cancel (Esc).
- Section context auto-detected from nearest h1/h2.
- Sidebar panel: annotations grouped by section, intent badges,
snippet quotes, delete buttons, click-to-scroll with flash highlight.
- Copy Prompt: structured markdown export with intent labels.
- localStorage persistence keyed on absolute artifact path
(voyage-annotate:v2: prefix to avoid colliding with v5.0.2 state).
Tests: 12 (up from 10), all passing. npm test: 518 / 516 pass / 0 fail / 2 skipped.
Reference: ~/repos/claude-code-100x/claude-code-100x/build-site.js
lines 1431–2255 (annotation UI section).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
v5.0.0 added a read-only HTML render. v5.0.1 deleted that and pointed at
/playground document-critique, which pre-generates Claude's suggestions
and asks the operator to approve/reject them. The operator asked for the
opposite — a surface where THEY drive every annotation. v5.0.2 lands it.
scripts/annotate.mjs (~430 lines, zero deps) takes any artifact .md and
writes a self-contained HTML next to it. The HTML renders the document
with line numbers, lets the operator click any line to add their own
note (inline textarea, save with Cmd+Enter or button), keeps a sidebar
of all notes (editable + deletable + persisted in localStorage per
artifact path), and exposes Copy Prompt to gather every note into one
structured prompt. Operator copies, pastes back, Claude revises the .md.
The three producing commands now run annotate.mjs at their last step and
print the file:// link with explicit "Click any line to add YOUR OWN note"
instructions. The v5.0.1 /playground document-critique line is gone.
npm test green: 516 tests, 514 pass, 0 fail, 2 skipped.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
The v5.0.0 stop-gap had /trekbrief, /trekplan, and /trekreview each render
a read-only {artifact}.html (via scripts/render-artifact.mjs) AND print a
vague "run the /playground plugin" instruction. In practice the read-only
HTML was redundant with what /playground produces and the instruction
wasn't copy-paste-ready — the operator had to guess the right invocation.
v5.0.1 deletes scripts/render-artifact.mjs + its test + npm run render,
and makes each producing command end with a single boxed, literal,
copy-paste-ready line:
/playground build a document-critique playground for {artifact_path}
One paste from the operator launches the official playground skill's
document-critique template, which builds an interactive HTML — artifact
on the left, per-line Approve/Reject/Comment cards on the right, Copy
Prompt button at the bottom. Mark suggestions, click Copy Prompt, paste
back, Claude revises the .md. Doc-consistency test pins the literal
invocation so the prose cannot soften back into vagueness.
npm test green: 503 tests, 501 pass, 0 fail, 2 skipped.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
The v4.2/v4.3 bespoke playground SPA (~388 KB), the /trekrevise command,
Handover 8 (annotation → revision), the supporting lib/ modules
(anchor-parser, annotation-digest, markdown-write, revision-guard), the
Playwright e2e suite, and the @playwright/test / @axe-core/playwright
devDeps are removed. A browser walkthrough found the playground borderline
unusable, and it duplicated the official /playground plugin's
document-critique / diff-review templates.
In their place: scripts/render-artifact.mjs — a small, zero-dependency
renderer that turns a brief/plan/review .md into a self-contained,
design-system-styled, zero-network .html (frontmatter folded into a
<details> block). /trekbrief, /trekplan, and /trekreview call it on their
last step and print the file:// link; to annotate, run /playground
(document-critique) on the .md and paste the generated prompt back.
Resolves the v4.3.1-deferred findings as moot (their target files are
deleted). npm test green: 509 tests, 507 pass, 0 fail, 2 skipped.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Bumps .claude-plugin/plugin.json 4.2.0 -> 4.3.0 (package.json, package-lock.json,
and the README badge were already at 4.3.0). Updates the v4.3.0 CHANGELOG entry with
the verified test count (711 pass / 0 fail / 2 skipped, 713 total), a "Re-review
remediation (Sesjon 13-18)" note covering the 11-finding cycle Waves 1-3 closed, and
a "Known issues — deferred to v4.3.1" subsection listing the 3 new findings the Sesjon
18 re-review surfaced in the remediation code (87069b35 SECURITY_INJECTION defense-in-
depth, 4cc3bfc9 PLAN_EXECUTE_DRIFT, c6c64a58 MISSING_TEST). Updates root CLAUDE.md
(voyage v4.0.0 -> v4.3.0, seven-command + playground), root README + plugin README
(test count, Known-limitations note, fixes the stale "trekplan@" install snippet ->
"voyage@"), root marketplace.json (voyage description), and plugin CLAUDE.md (Playground
paragraph). A plan-critic-reviewed Wave-4 remediation plan for the 3 deferred findings
is ready (.claude/plans/, gitignored).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
