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."
Flip model: sonnet → model: opus across 20 agent files, 4 prose references
in commands (trekplan, trekresearch), trekendsession command frontmatter,
and CLAUDE.md tables. Aligns CLAUDE.md premium-profile row to actual
premium.yaml content (all-opus, which has been the case since v4.1.0 but
the doc was drift). Companion to VOYAGE_PROFILE=premium env-var (set in
~/.zshenv same day) — env-var governs orchestrator phase model; this
commit governs sub-agent models which are frontmatter-pinned and not
reachable by the profile resolver.
npm test: 516 pass, 0 fail, 2 skipped (unchanged from baseline).
Operator rationale: complete Opus coverage across all Voyage activity,
including the 20 sub-agents that the profile system does not control
(architecture-mapper, task-finder, plan-critic, scope-guardian,
brief-reviewer, code-correctness-reviewer, brief-conformance-reviewer,
review-coordinator, session-decomposer, plus the 6 researcher agents,
plus the 5 codebase-analysis agents).
Cost implication: sub-agent runs ~5x more expensive vs sonnet. Accepted.
Informational blockquote after the v3.0.0 note. Documents that voyage is
Tier 1 (per-task) of a three-tier architecture under the author's private
marketplace: Tier 2 app-creator (per-app), Tier 3 app-factory (per-portfolio).
Both are pre-implementation. Asymmetry-invariant preserved: voyage stays
unaware of Tier 2/3 — Handover 1 (brief format) is the only integration
point. Brief-schema changes therefore breaking for downstream consumers,
formalized in v5.4.
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>
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 27 of v4.3 plan — adds Playwright 1.59.1 + axe-core/playwright 4.10.2
as devDependencies, npm script test:e2e, and playwright.config.mjs with
file:// baseURL pointing at playground/. Chromium browser binary installed
to ~/Library/Caches/ms-playwright/.
Trace: SC2 (WCAG verifikasjon krever browser-driver), research/04
Recommendation security; brief Constraint linje 64 (zero new deps i
playground/) er OK fordi Playwright er devDependency på voyage-plugin-rot,
ikke i playground/.
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.
Step 18 of v4.3 playground plan. Replaces v4.2 Gesture 2 pencil-icon
hover-reveal with numbered circular badges in the left gutter (one per
anchored paragraph; ordering matches sidebar jumplist). 2-3px accent stripe
extends right from the badge into the gutter. Yellow-tint highlight
(rgba 255, 235, 59, 0.25 — Google Docs pattern) applies to the anchored
paragraph when an annotation is active. Body text never reflowed or
recolored. Gesture 1 (text-select adder) and Gesture 3 (page-level note)
remain for new annotation creation.
CSS uses --color-scope-voyage token for badge background and stripe.
JS adds injectAnchorBadges() + setActiveAnchor() and rewires mountRender.
Trace: SC1 + SC6, research/04 Insight 3 + Recommendation marker-design.
Step 17 of v4.3 playground plan. Pure function relocateAnchorsToBlockBoundaries
(text, anchors) detects atomic markdown blocks (fenced code, tables, deeply
nested lists) and relocates anchor-comment insertion to the line BEFORE block
opening rather than inside the block. Pure markdown-text -> markdown-text
transform (no DOM, no markdown-it dependency).
Companion test tests/integration/annotation-block-boundary.test.mjs extracts
the function via balanced-brace scan and exercises it through Function() —
7 unit tests covering empty anchors, outside-block stays, fenced-code
relocation, table relocation, deeply-nested list relocation, mixed
inside/outside, and shape contract.
Trace: SC6, research/04 Dim 3 (Notion block-level fallback), plan-critic
major #6 (DOM-vs-no-DOM contradiction resolved via pure-function design).
