Make the bake-off-validated Workflow substrate (Arm B) reachable behind an
opt-in --workflow flag for /trekreview. Default Phase 5-6 path stays prose
to preserve the lower portability floor; --workflow raises the consumer
floor to Claude Code 2.1.154+ (the Workflow tool).
- arg-parser: --workflow added to trekreview boolean flags
- commands/trekreview.md: flag row + Phase 5 substrate-routing gate +
new section 'Phase 5-6 via the Workflow substrate' (invocation contract,
S10 gotchas, bake-off citation, auto/bypass residual as Known limitation)
- docs/command-modes.md: --workflow row in /trekreview table
- routes to existing scripts/trekreview-armB.workflow.mjs (byte-identical to
the S10 part-B POSITIVE build); integration is pure routing, no script change
TDD: 8 new tests (arg-parser flag recognition + combine; command/doc prose
pins for route, opt-in posture, 2.1.154+ floor, bake-off evidence).
Suite 662 -> 670 (668 pass / 2 skip / 0 fail). plugin validate clean modulo
known root-CLAUDE.md warning. Resolves W1-narrow-wins-plan.md S11.
Run the full T2 §5 prose-vs-Workflow /trekreview bake-off (operator GO,
choice "a"): 3 runs/arm on a rich-finding JWT-auth fixture, resolving the
smoke's 0-finding limitation.
Deliverables:
- tests/fixtures/bakeoff-rich/ — JWT-auth brief + diff with 5 seeded blatant,
brief-traceable issues (varied severity/rule_key, one dual-flaggable).
- scripts/bakeoff-armA-merge.mjs — Arm A (prose) validate (NW1) + triplet-dedup,
matching Arm B's dedup exactly.
- scripts/bakeoff-fidelity.mjs — cross-arm + within-arm + granularity-ladder
fidelity analysis over the structured arm outputs.
- docs/T2-bakeoff-results.md §Full run — the T2 §5 verdict.
Result (3 runs/arm, both arms ran the coordinator):
- Verdict fidelity EQUIVALENT — all 6 runs BLOCK, cross-arm verdict-match 1.0.
- Finding-set: substrate is fidelity-neutral. Cross-arm jaccard 0.41 (triplet)
→ 0.71 (file,rule_key) → 1.0 (file); cross-arm ≈ within-arm at every
granularity. Issue coverage 5/5 in 6/6 runs. Low triplet jaccard is
line-citation noise shared by both arms, not a substrate effect.
- Token +4.4% (Arm B vs A; <=+15%). Classifier interference 0 at 9-agent
concurrency. JSON-robustness: Arm B schema-forced; Arm A 6/6 valid via NW1.
- VERDICT POSITIVE → S11 proceeds with opt-in --workflow flag.
Caveat (per plan posture): strict triplet-jaccard>=0.7 flag is 0/9, a
metric-calibration artifact (both arms sub-0.7 against themselves), not a
regression. Residual: F4 auto/bypass explicit-mode check (mode not settable
in-session).
Suite green (662/660 pass, 2 skip); plugin validate clean (modulo the
pre-existing root-CLAUDE.md warning). No production code changed.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LqBYc8Ltrk7LipyJmGxXiB
Build the prose-vs-Workflow bake-off machinery for /trekreview Phase 5-6 and
run a 1-run/arm smoke to de-risk before the full measurement (operator posture:
build + smoke, then pause for go/no-go on the full >=3-runs/arm run).
New:
- lib/review/fidelity-diff.mjs (+ tests) — the PRIMARY metric: parse two
review.md (or two structured arm outputs) and compare verdict + jaccard over
(file,line,rule_key)-IDs + per-finding severity/rule_key. Reuses jaccard +
frontmatter + NW1 findings-schema + finding-id. fidelityDiffStructured avoids
rendering review.md per run.
- scripts/trekreview-armB.workflow.mjs — Arm B: Phase 5-6 as a Workflow
(parallel([conformance, correctness]) schema-forced -> JS dedup-by-triplet ->
agent(review-coordinator) verdict schema). Path-based input via args (reviewers
carry Read). Inlines dedup + the 12-key rule_key enum (scripts have no imports).
- tests/fixtures/bakeoff/ — committable fixture: real diff of b149538 (NW1) +
brief reconstructed from plan S9. Both arms review the same pinned input.
- docs/T2-bakeoff-results.md — smoke results + verdict + go/no-go recommendation.
Smoke result: SMOKE PASS. Arm B runs the full pipeline (3 agents) with ZERO
classifier interference; fidelity EQUIVALENT to Arm A at the verdict level
(both ALLOW; jaccard 1.0). Caveat: the clean TDD'd fixture yielded ~0 findings,
so finding-SET fidelity was not stressed (only verdict fidelity proven). A
reviewer-level divergence appeared (Arm B raised 1 raw finding, coordinator
filtered it; Arm A raised 0) — to be quantified in the full run on a
richer-finding-surface fixture. NOT the T2 §5 POSITIVE/NEGATIVE verdict.
Suite 647 -> 662 (660 pass / 2 skip / 0 fail; +15 fidelity-diff). claude plugin
validate clean (known root-CLAUDE.md warning only). Plan: docs/W1-narrow-wins-plan.md S10.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LqBYc8Ltrk7LipyJmGxXiB
Codify the /trekreview Phase 5 reviewer JSON contract as a validated schema so
main validates each reviewer's output instead of merely JSON.parse-ing it, and
re-asks on schema failure (not just parse failure). Retires the fragility at
trekreview.md:202-204. No Workflow dependency (S8 tier 1, ships regardless).
New lib/review/findings-schema.mjs (3-layer Content -> Raw-text -> CLI shim,
reusing result.mjs error-shape + rule-catalogue RULE_KEYS/SEVERITY_VALUES):
- validateFindings(payload): hard errors on load-bearing fields the dedup
triplet + verdict depend on — file, rule_key (in catalogue), severity (enum),
line (integer >= 0); accumulates all errors; per-finding location.
- extractFindingsBlock(text): last fenced ```json block (the :202 contract).
- validateReviewerOutput(text): extract + parse + schema, unifying parse and
schema failures under one bounded re-ask path.
Stable codes: FINDINGS_NOT_OBJECT/_NOT_ARRAY/_NO_JSON_BLOCK/_PARSE_ERROR (top),
FINDING_MISSING_FILE/_MISSING_RULE_KEY/_UNKNOWN_RULE_KEY/_BAD_SEVERITY/_BAD_LINE
(per-finding). Descriptive fields + unknown keys tolerated (forward-compat).
Phase 5 prose: replace "parse last json block; on parse error re-emit" with
"validate against findings-schema; on failure re-ask conforming JSON, bounded
N=2; never feed unvalidated findings to the coordinator".
TDD: 27 failing tests first, then minimal code to pass. Suite 606 -> 647
(645 pass / 2 skip / 0 fail). claude plugin validate clean (only the known
root-CLAUDE.md warning). Plan: docs/W1-narrow-wins-plan.md S9.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LqBYc8Ltrk7LipyJmGxXiB
Implements the CLAUDE.md cross-cutting invariant "brief framing must match
operator intent" as a controlled brief_version 2.1->2.2 bump (operator option A1).
Three defense layers, version-gated at >=2.2 so existing 2.0/2.1 briefs stay
valid (forward + backward compatible), mirroring the phase_signals >=2.1 gate:
- L1 framing: enum field (preserve|refine|replace|new-direction). Enum-checked
on any version when present (BRIEF_INVALID_FRAMING); missing at >=2.2 ->
BRIEF_MISSING_FRAMING. /trekbrief Phase 2.5 collects it BEFORE any brief prose
(non-skippable, even in --quick).
- L2 memory alignment: new brief-reviewer dimension 6 comparing brief Intent/Goal
+ framing against operator memory for explicit contradictions; degrades to
score 5 (N/A) when no memory context is supplied. Wired into Phase 4e gate
(memory_alignment.score >= 4).
- L3 obligatory ## TL;DR (<=5 content lines) at >=2.2; soft cap ->
BRIEF_TLDR_TOO_LONG warning.
trekreview briefs are exempt from the framing/TL;DR gate. Handover 1 PUBLIC
CONTRACT doc, README "What's new", and the CLAUDE.md invariant + agents table
(brief-reviewer 5->6 dimensions) updated to 2.2 (schema axis only; plugin
version badge + CHANGELOG remain S10).
Iron Law followed: validator tests red->green first. Tests 586 -> 606
(+20, 604 pass / 2 skip). claude plugin validate passes (pre-existing
CLAUDE.md root-context warning unchanged).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LqBYc8Ltrk7LipyJmGxXiB
Elevate Handover 1 (brief.md → research) from an internal pipeline handover
to an explicit PUBLIC CONTRACT — the only public producer↔Voyage integration
boundary (Trinity asymmetry invariant: Voyage stays unaware of upstream tiers;
any compatible producer may feed it; no producer privileged).
Scope = freeze + document (operator-gated, option A). No schema change, no
plugin version bump (that is S10 RELEASE). Per S3, phase_signals stays optional
and brief_version 2.1 is the frozen public-contract baseline.
- docs/HANDOVER-CONTRACTS.md: PUBLIC CONTRACT label + callout on Handover 1
(asymmetry, breaking-for-downstream, additive-vs-breaking, frozen 2.1 baseline);
resolve the speculative "v5.4 may promote phase_signals to required → 3.0" line
to the S3 freeze decision; fix stale schema-table baseline 2.0 → 2.1; annotate
the Stability summary row (symmetric with Handover 3's "external" flag).
- CLAUDE.md: Trinity note now points at docs/HANDOVER-CONTRACTS.md §Handover 1.
- tests/lib/doc-consistency.test.mjs: +4 failing-first doc-truth pins (Iron Law)
— PUBLIC CONTRACT label, callout + breaking-for-downstream guarantee, frozen
2.1 baseline (no stale 2.0), freeze-not-promote. 586/584 pass/0 fail/2 skip.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LqBYc8Ltrk7LipyJmGxXiB
S4 of the 2.1.181 upgrade — implementation, not a gate. TDD: failing test
written first for the resolver gate, then the fix; suite green throughout.
- Resolver MAJOR (FIX): lib/profiles/phase-signal-resolver.mjs now imports
BASE_ALLOWED_MODELS from profile-validator and gates `model`
(if 'model' in entry && BASE_ALLOWED_MODELS.includes(entry.model)),
mirroring the EFFORT_LEVELS gate one line up. Out-of-allowlist models
(gpt-4, haiku) are dropped instead of handed to an agent spawn —
defense-in-depth behind brief-validator's validation-time check. No
circular import (brief-validator already imports the same symbol).
+2 tests (drops-invalid / keeps-valid).
- Native effort: (SHIP, static additive): effort: frontmatter on 8 agents —
retrieval (task-finder, git-historian, dependency-tracer,
architecture-mapper) = medium; adversarial-reasoning (plan-critic,
risk-assessor, contrarian-researcher, review-coordinator) = high. The
other 15 stay unset -> inherit Opus-4.8 default (high). This per-spawn
REASONING effort is a different axis from brief phase_signals.effort
(ORCHESTRATION shape) per the S3 decision.
- Doc-truth + axis distinction: new canonical docs/profiles.md
§Model & effort axes (opus->Opus 4.8 default-high; orchestration vs
reasoning effort table; native-effort precedence; per-agent levels).
Short notes in CLAUDE.md (after Agents table) and README.md (Cost
profile), both pointing to profiles.md.
- Open (non-blocking, unchanged): only STATIC effort shipped — the
verified-safe minimum. Profile-driven DYNAMIC effort still needs
verification of the per-spawn effort param or env-var injection.
Matrix: new "S4 resolutions" section. Tests 582 total / 580 pass / 0 fail /
2 skip (was 578 pass; +2). claude plugin validate passes (only pre-existing
root-CLAUDE.md warning).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LqBYc8Ltrk7LipyJmGxXiB
S2 of the 2.1.181 upgrade. Schemas verified verbatim against the official
slash-commands and hooks docs before editing (a first-pass camelCase
'disallowedTools' claim was caught and corrected to kebab-case against the doc).
- CC-14 (SHIP): migrate all 7 hooks in hooks/hooks.json to exec-form
{command:"node", args:["${CLAUDE_PLUGIN_ROOT}/hooks/scripts/X.mjs"]}. Doc
recommends exec-form whenever a hook references a path placeholder; protects
consumers installing under a path with spaces. ${CLAUDE_PLUGIN_ROOT}
interpolates inside args (verified). hooks-json-stop-wired test made
form-agnostic (normalizes command+args to one invocation string).
- CC-11 (SHIP): add `disallowed-tools: Agent, TeamCreate` to trekexecute
frontmatter, enforcing its documented "No Agent tool, no TeamCreate" rule.
allowed-tools grants auto-approval but does NOT remove tools from the pool,
so the prior omission left Agent callable; disallowed-tools removes it.
trekexecute is the only command with a documented exclusion.
- CC-15 (DECIDE: keep universal): re-affirm F2 deferral. pre-bash/pre-write
executors stay universal -- session-agnostic safety (rm -rf /, ~/.ssh, .env)
that narrowing to execute-only would only weaken. Header comments corrected.
- CC-10 (DECIDE: design note, no code): no blanket Agent(model:opus) deny rule
-- would break balanced/economy profiles; any model-enforcement must be
profile-aware, deferred into W2. Folded into open question #3.
Matrix updated with S2 resolutions section. Tests 578 pass / 0 fail / 2 skip;
claude plugin validate passes (only pre-existing root-CLAUDE.md warning).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LqBYc8Ltrk7LipyJmGxXiB
The v5.x doc consolidation (67f6dd5) moved phase_models into docs/profiles.md and phase_signals into docs/HANDOVER-CONTRACTS.md, leaving CLAUDE.md to only link them via Reference docs. Two doc-consistency assertions still read CLAUDE.md and went red on main. Retarget both to the canonical doc homes (legacy-alias check preserved on docs/profiles.md). Suite: 578 pass / 0 fail / 2 skipped.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LqBYc8Ltrk7LipyJmGxXiB
v5.1.0 shipped with an unquoted brief_version: 2.1 in trekbrief-template.md.
parseScalar coerced it to Number 2.1, and the sequencing gate guarded on
typeof === 'string', silently bypassing BRIEF_V51_MISSING_SIGNALS.
Three-part atomic fix:
- brief-validator.mjs:87+149 now accepts both string and number forms via
String(fm.brief_version) coercion.
- trekbrief-template.md quotes the value so new briefs parse as String.
- doc-consistency.test.mjs pins the QUOTED form going forward.
Three regression tests added in brief-validator.test.mjs.
Operator runs Ghostty (also iTerm2, modern Terminal.app) — all support
cmd+click on file:// URLs. Producing commands (/trekbrief, /trekplan,
/trekreview) already emit both forms but the contract was implicit.
This commit makes it explicit:
1. CLAUDE.md gains an "Operator-UX guarantee" paragraph stating both
forms must always appear in the final report: (a) plain file://
URL with absolute path (for cmd+click), (b) copy-pasteable
`open file://` command (for terminals without cmd+click).
2. tests/lib/doc-consistency.test.mjs gains a pin asserting both
patterns appear in all three producing commands' final report
blocks. Drift catches at test time.
Non-functional change to the commands themselves — they already
emit both forms (verified at trekbrief.md L510/L519, trekplan.md
L798/L802, trekreview.md L299/L317).
Operator request 2026-05-13: "Noter ned i Voyage at jeg ALLTID får
en slik direkte file:// lenke."
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>
Step 30 of v4.3 plan — Wave 7 Group D:
- voyage-playground-a11y.spec.mjs (3 tests): light + dark theme axe-core
scans (compared against baseline JSON, fails only on NEW or GROWN
violations) + pixel-diff smoke for SC1 (light + dark, 1280x900,
maxDiffPixelRatio=0.02).
- voyage-playground-network.spec.mjs (1 test): SC7 authoritative gate via
page.on('request') instrument — verifies zero external (http/https/ws)
requests during page load.
- playwright.config.mjs: snapshotPathTemplate routes to tests/e2e/snapshots/
(matches Step 31 expected_paths).
Baseline policy: HTML is FROZEN in Sesjon 6 (Wave 7 = verification, not
fix). Existing critical/serious WCAG violations (aria-hidden-focus +
color-contrast) recorded in tests/e2e/snapshots/a11y-baseline.json as
delta-baseline. Actual a11y fix deferred to v4.4.
Verify: npm run test:e2e -> 4 passed (3 a11y + 1 network).
Step 20 of v4.3 playground plan. Document-level keydown handler:
- J = next annotation (next sorted-by-line draft, wraps)
- K = prev annotation (wraps)
- ] = toggle sidebar visibility
- Escape = clear active anchor + sidebar list selection
Active annotation gets yellow-tint (Step 18 setActiveAnchor) and the
matching gutter-badge receives focus + scrollIntoView. Aria-live region
announces position + target: "Annotering 3 av 7: <target> — <snippet>".
Skips input/textarea/select/contenteditable so playground never steals
keystrokes from form fields. Modifier keys (Ctrl/Alt/Meta) pass through
to browser shortcuts. Wired in init() after dashboard nav.
Trace: SC2 (WCAG AA keyboard), SC6, research/04 Dim 2 + Insight 5 +
Recommendation keyboard-navigation.
Step 19 of v4.3 playground plan. Sidebar now default aria-hidden=true
(translateX collapses panel, leaves 40px FAB rail). FAB toggle has
data-action=toggle-sidebar for keyboard binding (] in Step 20).
New annotation-list section in sidebar panel:
- filter radiogroup: Alle (default), Åpne (unresolved), Resolved
- voyage-jumplist ordered list with numbered badges matching the
gutter-badge ordering (sorted by line ASC)
- aria-live jumplist count: "X av N" (filtered/total)
- click list-item -> setActiveAnchor + scrollIntoView + data-active
renderAnnotationList wires into mountRender so list refreshes on every
render. Filter state (voyageFilterState) persists across renders within
the session.
Trace: SC6, research/04 Dim 1 (hidden-by-default) + Insight 1 +
Recommendation sidebar/navigation.
