The prompt behind a generated image was recorded three different ways,
a sidecar in the eval harness, nothing in the skill's API tool, nothing
for native tools, so intent survived or vanished depending on where you
ran. One dependency-free script now embeds the prompt inside the image
itself, PNG tEXt or JPEG COM with a sidecar fallback for other formats,
idempotent, and reads it back from any impeccable-generated file. The
API tool embeds automatically; the prose directs every native-tool
generation through it; copies between machines and harnesses keep their
intent. Comps meanwhile are declared the build thread's own work, never
delegated, and the comp-skeleton guidance now asks for the surface's
actual regions instead of prescribing navs onto pages that have none.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Two findings from the first human-validated probe. The comps rendered
as scene vignettes because the generation prompts led with the world's
atmosphere; the model painted the fish market instead of the fish
market's website. The comp guidance now demands the page's literal
skeleton in the prompt, nav and its items, headline block, sections in
order, footer, with a self-check: a render that could hang as a poster
is not a comp. And generation context is part of the asset: the thread
that wrote a prompt knows what the image contains and why, so build-
critical imagery prefers the build thread, and subagent-produced assets
must carry their prompts, via the tool's new sidecar or the manifest,
read by the builder before composing.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Rating grades quality, breadth says whether a world can serve an
arbitrary build at all; while they shared one field, the only way to
hold a narrow world back was calling it marginal, which made excellent
but narrow unrecordable and corrupted the ratings as a calibration
signal for the next authoring round. Both axes now exclude
independently, either kind of hold keeps its approval for direct
briefs, an all-niche tier falls back rather than starving, and
stagings honour the same gate with the same fallback. Tests cover the
niche exclusion at strength, the fallback parity with marginal-only
tiers, and the staging gate.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A hidden backface still hit-tests in Chrome, so after flipping a card
the front's picture-in-picture sat invisibly over the back's chips,
showing its zoom cursor and eating the flip-back click. Pointer events
now follow visibility: the back is inert until the card flips, and the
front goes inert while it is flipped.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Field data: the first image of a real batch took ninety seconds and the
page's 150-second fallback then silently promoted catalog art to full
bleed, unlabeled, which is exactly the this-is-your-design misread the
picture-in-picture treatment exists to prevent. The policy is now
patience while there is progress: a slot shows its inspiration only
after waiting four minutes with nothing landing anywhere on the page
for four minutes, the stand-in is dimmed and labeled 'inspiration ·
sketch pending', and polling continues so the real sketch still swaps
in whenever it arrives. Slots with no inspiration keep the honest
elapsed shimmer instead of folding. The parent's reclaim rule matches:
files landing steadily is health at any pace, and only total silence,
no first file in three minutes, takes the batch back inline.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Field feedback: with every fact stacked under the media the cards ran
past a screen tall. The front now carries only what the choice needs,
sketch, lineage, title, thesis, identity, and the honest risk clamped
to two lines, while first viewport and the case read on the back behind
a Details chip, sharing the face with the board when the world has one.
Risk stays on the front because the counterweights are pointless if the
downside hides behind a flip, and once the sketch lands the first
viewport is a picture anyway. The schema notes now ask for one-sentence
facts, since a long fact should cost the reader a flip, not the page
its scanability.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A codex field run dealt six challengers into an eight-sketch batch
behind an opaque subagent, and the user stared at a page of shimmer
asking whether anything was happening at all. Four fixes from that run.
A hand now holds at most three challengers, the rest banked for
re-rolls, so fairness within the hand stops multiplying into a queue.
Sketches greek everything but the product's real name and one real
headline, because an invented spec, price, or ship date in a sketch is
a claim PRODUCT.md never made, and comps have solved this for a century.
Sketch production follows the user's reading order with the first file
doubling as the producer's heartbeat, and the parent's --wait loop
checks the sketch directory each pass, reclaiming the batch inline when
two minutes pass with nothing landed. And a failed --start now captures
the daemon's stderr to a per-key log and names the sandbox as the usual
suspect, instead of reporting only that failure occurred. The shimmer
counts its elapsed seconds, and gives up at 150 instead of 300.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Three field notes from a live review. The deck now escapes the content
column and runs edge to edge, so a cut-off card sits at the screen edge
where it reads as more cards instead of at an invisible container edge
where it reads as a bug; the first card still aligns with the column
via scroll padding. Whichever side hides more content wears a fade, and
a hard edge means the end. The vertical pager grows from a bare chevron
into labeled Back and More pills, because in a column deck it is the
primary way forward. And hovering the inspiration thumb now takes over
the whole media region instead of a timid zoom; the sketch is the
promise, the inspiration is a glance, and the glance must cost nothing.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Field-checked in a real browser, which surfaced three defects the DOM
tests could not: the generic .media img display rule defeated [hidden]
and floated an empty block over the shimmer and its sketching note; the
deal animation left every card at opacity zero in an unfocused tab,
because rAF throttling is real and decoration must never gate content;
and the sketch poll's cache-busting query missed the anchored /img
route, so a landed sketch kept shimmering forever.
The grid is now a snap-scrolling deck: one row in a wide viewport, one
column in a tall one, with edge arrows that appear only on overflow and
page one card at a time.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The decision page compared unlike things: the grounded direction was a
wall of text beside curated catalog art, the catalog art read as a
promise of the build, the weighing silently shrank the challenger set,
and the standing exit hid in the footer under the cards it must not
soften. Every card now shares one anatomy (thesis, palette chips,
material tags, first viewport, case, risk), every dealt challenger is
presented with the weighing written on it rather than applied to it,
the catalog image rides picture-in-picture as labeled inspiration with
the lightbox a click away, and canonCard renders the category standard
as one honest, subordinate card.
When image generation exists, each card declares a sketch slot the page
polls: serve first, generate after, through one shared deliberately
unfinished frame, so the comparison stays about direction instead of
rendering luck. The asset producer takes the batch when subagents
exist; the chosen sketch returns in ANSWER to seed at most one comp
probe, and the comp round still renders its full set.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Round eight closes the stale-local class completely: the develop
candidate sits before the remote-default entries, so when origin/HEAD
itself points at develop, its name claim let a stale local develop win
over the fresher origin/develop. The candidate now leads with any
remote-advertised develop rev, exactly as the remote-default and
upstream candidates already lead with theirs. main/master were already
covered since their remote-default entries come first in the order.
Failing-first test forces local develop two commits behind.
Prepared with AI assistance (Claude Code), directed by @pbakaus.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Round seven: a remote-advertised default candidate tried the local
branch first, so a stale local main outranked the fresher origin/main
the symref points at and refilled changedFiles with the divergence.
The candidate now leads with the advertised remote rev, mirroring the
upstream candidate's reasoning. Failing-first test: local main forced
two commits behind the remote default, feature delta stays clean.
Prepared with AI assistance (Claude Code), directed by @pbakaus.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Round six, and the upstream-parsing ambiguity dies at the root: @{u} is
now resolved via rev-parse --symbolic-full-name, where refs/heads/...
IS a local upstream and refs/remotes/<r>/... IS remote-tracking. The
previous remote-membership heuristic still misread a local feature/foo
upstream when a remote literally named "feature" existed. The
adversarial test now configures exactly that remote and passes.
Prepared with AI assistance (Claude Code), directed by @pbakaus.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Round-five bot findings, one real root cause: splitRemoteRef treated the
first slash in any ref as a remote separator. A local upstream named
release/2.0 was truncated to "2.0", and feature/foo tracking from branch
foo collapsed to the current branch's own name and was self-skipped,
discarding a valid base both times.
The split now happens only when the prefix names a configured remote;
otherwise the whole ref is one local branch name. The per-remote HEAD
symref loop strips its own queried prefix directly (that remote may be
fabricated in tests or partial clones without appearing in git remote).
The reported pruned-upstream shape already resolves via the multi-remote
rev lists from the previous round; its test now guards that.
Prepared with AI assistance (Claude Code), directed by @pbakaus.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Cursor and Greptile converged on one root cause from the previous round:
candidate revs stopped at origin (develop tried only develop and
origin/develop; a remote-default entry carried only its own rev), so the
name-level dedup discarded a same-name base living on another remote. A
fork-parent layout with develop only as upstream/develop, or a pruned
origin/main beside a live upstream/main, lost its base entirely.
revsFor(name) now expands to the local branch plus <remote>/<name> for
every remote (origin first), and all named candidates use it, which is
exactly what makes the dedup safe. Two failing-first tests cover the
upstream-only develop and the pruned-origin/live-upstream main shapes.
Prepared with AI assistance (Claude Code), directed by @pbakaus.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Two more real gaps from the post-rebase review round: a detached
checkout reads its branch as the literal HEAD, so the integration guard
never fired and candidate selection could diff a detached tip on main
against develop; and the remote-default check only consulted origin, so
a fork-parent layout whose only remote is upstream lost the guard on
its default branch entirely.
The guard now treats a detached HEAD as no-diff-base, and default-branch
symrefs are collected from every remote (origin first), feeding both the
guard and the candidate list. Two failing-first tests cover a detached
tip beside a diverged develop and an upstream-only trunk default.
Prepared with AI assistance (Claude Code), directed by @pbakaus.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Cursor Bugbot: sitting on a non-standard default such as trunk (the
origin/HEAD target) still ran candidate selection, where develop or main
could win and produce an integration-vs-integration diff. The guard now
treats the remote default branch as an integration branch alongside the
conventional names. Failing-first test: on trunk with a develop branch
present, the scope stays the working tree.
Prepared with AI assistance (Claude Code), directed by @pbakaus.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Cursor Bugbot's remaining round-1 finding held for the current code
too: in a git-flow repo whose platform default was never flipped off
main, a feature branch without an upstream picked origin/HEAD's main
over the develop branch features actually merge to, dragging the
develop-vs-main divergence into scan targets. develop now sits between
the upstream signal and origin/HEAD in the candidate order; repos
without a develop branch are unaffected. Failing-first test covers the
exact shape (develop exists, origin/HEAD -> main).
Prepared with AI assistance (Claude Code), directed by @pbakaus.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Cursor Bugbot round two, both real: an upstream or origin/HEAD naming a
DIFFERENT integration branch bypassed the conventional-name guard, so
sitting on develop with the remote default at main still produced the
integration-vs-integration divergence this detection exists to prevent.
And splitRemoteRef returned null for a slashless @{u}, silently dropping
local upstreams (branch.<x>.remote = ".").
Base detection is now skipped entirely on an integration branch: no
signal may override the working-tree scope there. A slashless upstream
resolves as its own name and rev. Two failing-first tests: origin/HEAD
pointing at main while sitting on develop, and a feature branch
tracking a local canary branch.
Prepared with AI assistance (Claude Code), directed by @pbakaus.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Both review bots found real gaps in the first pass: candidates were
verified as local branch names only, so an origin/HEAD target with no
local checkout fell through, and stripOrigin() dropped upstreams on any
remote not named origin (fork workflows tracking upstream/release).
Candidates now carry a display name plus the revs to try in order: the
upstream's remote rev wins outright (it tracks the actual merge target,
so it beats a possibly stale local branch of the same name), origin/HEAD
tries the local branch then the remote-tracking ref, and the
conventional names each try local then origin/<name>. git.base keeps
reporting the friendly branch name while the diff runs against whichever
rev resolved. Two new failing-first tests: remote-only default branch,
and an upstream on a remote named upstream with no local base branch.
Prepared with AI assistance (Claude Code), directed by @pbakaus.
Co-Authored-By: Claude Code <noreply@anthropic.com>
context-signals hardcoded ['main', 'master'] as diff-base candidates, so
repos integrating through develop (or any other branch) diffed against
the wrong base: git.changedFiles carried the entire divergence and
downstream commands scanned the wrong set (issue #302).
The base is now detected, most specific signal first: the branch's
configured upstream (@{u}; a branch pushed with -u tracks itself and is
skipped by the self-check), then the remote's default-branch symref
(origin/HEAD), then the conventional integration names including
develop. The conventional fallbacks are withheld when the current branch
is itself one of them, so sitting on main in a repo that also has
develop keeps the working-tree scope instead of diffing two integration
branches against each other.
Five tests (three failing-first): develop-based feature branch,
origin/HEAD detection with a non-standard default name, upstream
tracking, on-the-integration-branch fallback, and the
integration-vs-integration guard.
Prepared with AI assistance (Claude Code), directed by @pbakaus.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Cursor Bugbot caught a real hole: accept unlocks at the first variant,
so a late generation agent_done for the same session id could arrive
after Accept and close the awaited failure window early, reopening the
exact #384 gap. The SSE broadcast carries no sourceEventType, so only a
carbonize agent_done is provably accept-side; the release is now gated
on it. Copilot's wording point led somewhere real too: a carbonize-phase
failure raises the same error after the source WAS promoted, so the
toast now says "may not have been saved" and normalizes the server
message's terminal punctuation. Regression guard extended to pin both.
Prepared with AI assistance (Claude Code), directed by @pbakaus.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Accept is optimistic: POST /events acknowledging the intent schedules
cleanupAcceptedSession(), which nulls pendingAcceptedSession before
live-accept.mjs has run. When the accept later failed (missing markers,
preview error, receipt conflict, source_locked), the SSE 'error' guard
keyed on pendingAcceptedSession could no longer match its id, so the
tailored recovery never fired: the user got a generic error toast, the
session was gone, and nothing said the variant was never written
(issue #384, analysis by Cursor Bugbot on #381).
Following the issue's fix sketch, an awaitingAcceptResult id is set on
the optimistic success path and deliberately survives the teardown. The
'error' case matches it and tells the user plainly that the variant was
not saved and to pick + generate again (post-teardown the wrapper may
already be gone, so restoring CYCLING is not honestly possible). The
marker is released when the real accept result arrives (complete /
accept / post-accept agent_done) or when a new session supersedes it.
Regression guard covers the set-before-teardown ordering, the error
match, and cleanupAcceptedSession leaving the marker alone; the existing
source contract now also asserts handleGo clears it.
Prepared with AI assistance (Claude Code), directed by @pbakaus.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Cursor Bugbot correctly noted classic VuePress keeps theme layouts,
components, and styles under .vuepress/, which the walker scanned before
the hidden-dir rule. Same treatment as .vitepress and .storybook.
Prepared with AI assistance (Claude Code), directed by @pbakaus.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Greptile's review correctly flagged a regression in the blanket
hidden-dir skip: .vitepress/theme/*.vue and .storybook/ preview files are
real UI source that the walker scanned before this branch. Both the
walker and the scan-target filter now carry a two-entry allowlist
(HIDDEN_SOURCE_DIRS) for those conventional locations; every other
hidden dir keeps being skipped.
Prepared with AI assistance (Claude Code), directed by @pbakaus.
Co-Authored-By: Claude Code <noreply@anthropic.com>
The documented abort flow in reference/live.md (live-poll.mjs --reply <id>
error "...") reset the browser bar to PICKING but left the localStorage
checkpoint written for the GENERATING phase in place. Every reload then
resurrected a dead session the server no longer knew about, and the page
stayed wedged until the user hand-cleared the impeccable-live* keys in
the console (issue #362, diagnosed by @yourcodekitten).
An agent error reply is terminal for the session it names: when the id
matches the current session, run the same markSessionHandled + cleanup
teardown as 'discarded' (cleanup includes clearSession); when it matches
a stored-but-not-current checkpoint (the error raced a reload), drop that
checkpoint too. Errors that name no session keep the existing UI-only
reset, and the accept-cleanup and steer branches are untouched.
Regression guard added to tests/live-browser-regression.test.mjs.
Prepared with AI assistance (Claude Code), directed by @pbakaus.
Co-Authored-By: Claude Code <noreply@anthropic.com>
When impeccable (or any agent tool) is installed into a project's
.claude/.cursor/.codex tree, a root scan descended into the vendored skill
code and reported the detector's own example strings as findings, and
context-signals returned installed-skill files as scan candidates whenever
the harness tree appeared in the branch diff (issue #303).
Rather than growing SKIP_DIRS by a denylist of harness names that drifts
as new tools appear, the walker now skips every hidden directory during
recursion — which already covered .git/.next/.nuxt/.svelte-kit/.turbo/
.vercel, and covers all present and future harness installs plus
.impeccable itself. SKIP_DIRS shrinks to the four non-hidden entries.
An explicitly passed hidden target still scans: only child entries are
name-checked, never the root the walker is given.
scanTargets() applies the same rule to git-changed files (directory
segments only, so root dotfiles keep their existing behavior), and falls
through to source-dir targeting when the only dirty files are vendored.
Prepared with AI assistance (Claude Code), directed by @pbakaus.
Co-Authored-By: Claude Code <noreply@anthropic.com>
From the paired Opus and Codex manual-run analyses. DESIGN.md moves to
the end of the flow and into a shipped documenter subagent that derives
the system from the built artifact: a rulebook written before the build
gets defended against reality, and a half-stable DESIGN.md hands the
design-system detector an unstable target that buries the build in
noise and invites laundering. The finish reviewer gains the handoff
that failed three times live: the parent captures desktop and mobile
screenshots and passes paths, the reviewer never attempts to render
and names missing inputs in one line, the parent verifies the
five-section return and respawns once on empty. Fidelity against the
approved comp joins its checks; the card keeps commitment only. The
comp ingredient inventory becomes a written gate with raster-by-default
materials and no gradient-as-texture, comps persist under
.impeccable/mocks, the degraded seed names the sandboxed-exec cause,
and the finish line is explicit: a clean detector pass is not finished.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The release-gate audit traced four ways the roll's output was defeated
downstream of a perfectly healthy seed. Gemini's harness keeps only the
tail of tool output, so the header-only ASSIGNED INDEX never reached
the model in 18 of 18 samples; the seed now restates the assignment
and key at the end of its output. Astro strips frontmatter comments,
so half the anthropic contracts vanished from built artifacts; the
contract now must survive the production build as an HTML comment in
emitted markup. A brief that paints its own picture (the album named
Soft Cathedrals) converged every arm regardless of assigned index; its
literal reading now joins the rut with at most one candidate. And Opus
under 4.0.1 skipped the seed 42% of the time while hand-authoring
plausible contracts; the finish reviewer now verifies FORM carries a
corroborable seed key before any craft point.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The release-gate campaign confirmed two skill bugs with transcripts.
Sandboxed harnesses reject absolute paths, so following the CHOSEN
CARD directive with the absolute card-base path failed view_image; the
directive and the quality-bar clause now say download into the
workspace and open the relative path. And under the openai worker's
turn cap, models spent the budget on init, cards, and comp generation
and never built the page (a third of small-n supplement slices); the
visualize mandate gains its one exception: at a hard cap the shipped
page outranks optional imagery.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Paul's call: the reviewer-local authorization patch covered one
command while the harness gate silently disables every shipped
subagent, critique panels and the manual-edit applier included. The
argument now lives beside the autonomy counter in context.mjs, emitted
as tool-result content every run: invoking the skill is the user
request such gates ask for; spawn where a reference directs; the
in-thread substitute is for absent capability only and gets disclosed
in one line. new-work keeps the reviewer mechanics and drops the
now-central argument.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Three browser-side fixes for the same 3.5-to-4.0.1 regression.
- Source-preview targets no longer source-inject per variant_progress
checkpoint. Immediate injection raced framework (React/Vue) ownership and
triggered removeChild errors, which surfaced as static previews. HMR now
owns reconciliation while variants stream in; source injection runs only on
the final done (its 750ms settle + retry ladder stays for non-HMR harnesses
like Cursor). Progress counts still advance from the variant observer, and
the svelte-component progressive path is unchanged.
- The agent-phase progress bar advances monotonically. A behind/resumed
checkpoint re-broadcasts an earlier phase (the server regresses the snapshot
phase to generating), which moved the visible bar backward; a phase rank
table now blocks a known-lower phase from overwriting a known-higher one.
- The server-lost toast now frames the drop as resumable (session saved,
reopen or restart live-poll.mjs) instead of "Session ended", which had led
agents to rationalize bailing to direct edits.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The polling-rework preflight wrote the variant scaffold into source during the
poll lease, before the agent acted. On source-preview targets (React/Vue/Vite,
everything but the svelte-component path) that write full-reloaded the
framework; a browser caught mid-reload missed the agent's variant write and the
SSE done, and sat stranded at 0/N.
Restore the 3.5 single-atomic-edit semantics: the preflight still resolves the
element location and computes the scaffold, but --defer-source-write leaves
source untouched and hands the agent the wrapper text plus the picked source
range. The agent splices variants into the wrapper and replaces the range in
one write, so the framework reloads exactly once. The svelte-component path is
untouched (it never writes route source). The missed-completion recovery stays
as defense in depth.
Also cache the resolved source file per target signature (locator + route):
the ~7.6s tree search re-ran on every generate for the same element; a hit now
points the helper straight at the file via --file, invalidated when the target
changes or a resolution fails.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Live mode had no TanStack coverage: a TanStack Start user hit disconnects
and static previews because there is no static index.html to inject and no
adapter for the SSR root document.
- New tanstack-adapter.mjs, modeled on the SvelteKit/Nuxt adapters: detects
a TanStack Start project (@tanstack/react-start + src/routes/__root.tsx)
and patches the __root document to mount a generated dev-only React
component (src/impeccable/ImpeccableLiveRoot) that appends the live bundle
on the client after hydration, carrying the ?token= param via
buildLiveScriptSrc. Patch/unpatch round-trips byte-for-byte and is
idempotent; refuses to clobber an unmanaged file at the component path.
- Wire detection into live-inject.mjs (insert + remove + gitignore),
ordered so SvelteKit/Nuxt win and a plain TanStack Router SPA falls
through to the baseline Vite index.html path.
- tanstack-router-vite fixture (baseline, no adapter) and tanstack-start
fixture (SSR adapter), both with runtime blocks. Both pass the full
live-e2e cycle (handshake, steer, pick, Go, cycle, accept, carbonize,
reloadProbe).
- Unit tests for detection + patch round-trip + apply/remove; tanstack-start
branches in framework-fixtures.test.mjs; live.md framework table + adapter note.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Two defense-in-depth layers close the P1 in issue #304, where any browser
tab on the machine could fetch /live.js, extract the embedded token, and
drive every token-gated route.
1. Loopback-restricted CORS. The shared handler replaced its wildcard
`Access-Control-Allow-Origin: *` with reflection gated on a strict
isLoopbackOrigin() that URL-parses the Origin (so localhost.evil.com and
127.0.0.1.evil.com fail) and accepts only http/https on localhost,
127.0.0.1, or [::1]. Reflection always pairs with `Vary: Origin` so a
cache never hands one origin's authorized response to another. Remote
origins get no ACAO header; origin-less callers (script tags, curl, the
agent's own fetches) are unaffected.
2. Token-gated /live.js. The handler now 401s unless `?token=` matches
state.token, so the bundle (which embeds the token) is no longer served
to unauthenticated local pages. The injected <script src> carries the
token: live.mjs passes --token to live-inject.mjs, which threads it
through every injection path (HTML/JSX tag, Nuxt plugin, SvelteKit root
component) via a shared buildLiveScriptSrc(). The token stays optional in
live-inject so static fixture tests keep their bare src.
Tests: new live-server integration cases for the 401 gate, remote-origin
denial, loopback reflection + Vary, and token-guarded routes under a
loopback Origin; e2e session harness now injects with the token.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The /source route confined paths with `absPath.startsWith(process.cwd())`,
a string-prefix check with no separator. An absolute request path to a
sibling directory whose name extends the project dir name (projeto ->
projeto-backup) shared the prefix and was served. Switch to the relative-path
check already used by sessionFileMetadataFromPollReply: reject when the
relative path is empty (the root dir itself, never a file this route serves),
starts with `..`, or is absolute.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The deep staleness pass extracted a hook-script path with a greedy `\S*`
prefix that swallowed the `${CLAUDE_PROJECT_DIR}/` placeholder, then
existsSync'd the literal string. That string never exists, so every project
installed by `impeccable hooks on` got a `hook-script-missing` finding with
text claiming UI edits were going unscanned — the opposite of the truth.
Split extraction from resolution. hookScriptTokenFrom now pulls the path
token (quoted-first, so it handles the #399 guarded `[ ! -f "PATH" ] || node
"PATH"` form and absolute user-level installs) without absorbing shell
syntax. resolveHookScriptPath then applies a per-placeholder policy:
- ${CLAUDE_PROJECT_DIR} expands to the scanned root (the runtime mapping).
- ${CLAUDE_PLUGIN_ROOT} / ${PLUGIN_ROOT} / ${GROK_PLUGIN_ROOT}, $(...) command
substitution (GitHub's $(git rev-parse)), and any other $VAR are SKIPPED:
the doctor cannot know those locations and must never assert a negative it
cannot verify.
The check stays real: a placeholder that expands to a genuinely absent path
still flags. Adds TDD coverage for every command form.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The Stop deep pass (runStopHook) never read the stop_hook_active field
from the Claude Code Stop-hook event. When a prior fire kept the turn
alive via hookSpecificOutput.additionalContext and the agent legitimately
declined to act, the hook re-scanned and re-blocked every re-invocation
until Claude Code's consecutive-block cap force-ended the turn (issue #400).
Read stop_hook_active early in runStopHook, right after the event is
parsed and before any scan, and exit 0 with no output when it is true. The
prior fire already surfaced the findings; acting on them is the agent's
call. Only Claude Code sends this field, so the strict === true is a no-op
for other harnesses. runHook (PostToolUse) and hook-before-edit.mjs
(PreToolUse) never receive the field, so they are unchanged.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The local-image map fell through to image/jpeg for anything that was
not webp or png, so an svg hero (the fake comp generator's native
format) silently failed to render on the decision page.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A cheap, LLM-free E2E tier for the interactive parts of new-work, mirroring
the two-layer live-e2e pattern (deterministic now, opt-in LLM tier later).
- generate-image.mjs: IMPECCABLE_IMAGE_GEN_FAKE=1 writes a deterministic
offline image (SVG with wrapped prompt + SYNTHETIC COMP label, or a valid
palette-stripe PNG carrying the prompt/marker in a tEXt chunk). Same CLI
contract, no key, no network, $0.00 cost line.
- tests/new-work-e2e/user-bot.mjs: scripted user bot (module + CLI) that
resolves the serve-question daemon from the workspace and drives the real
page via Playwright (pick, re-roll + steer, canon, tab close).
- tests/new-work-e2e.test.mjs: node --test coverage of the serve-question
cycles (pick + CHOSEN CARD, re-roll + --update re-deal, canon + CANON
CHOSEN, tab-close exit-4, text-only card) plus fake image determinism.
- Registered as the opt-in new-work-e2e suite; added test:new-work-e2e.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Em-dashes are used legitimately by humans, so em-dash-overuse fired far too
often. Reclassify it as the first advisory-tier rule: detected, but never a
failure.
Engine
- Add `advisory: true` to the rule metadata schema (em-dash-overuse is the
first). findings.mjs stamps `advisory: true` on advisory findings so every
consumer can partition without a registry lookup. Rule count stays 58.
- Raise the firing threshold from a flat 5 dashes to two gates: an absolute
floor of 8 and a density of about one dash per 500 characters of body text.
A long article that uses a few em-dashes no longer trips; a short,
dash-per-clause page still does. Entity decoding (mdash, numeric, hex) is
unchanged. Thresholds live in shared/constants.mjs so every engine agrees.
Browser parity
- The browser bundle carried a registry entry but no logic, so the overlay and
extension could never flag it. Add checkEmDashOveruse / checkEmDashOveruseDOM
in rules/checks.mjs (reads rendered text, no entity decoding needed), wire it
into the injected page-level pass, and carry the advisory flag through
serializeFindings so the overlay/extension can render it with the mildest
affordance.
CLI
- Advisory findings print under a separate dimmed "Advisory" section, are
excluded from the failure count, and never change the exit code (an
advisory-only scan exits 0). JSON keeps them with `"advisory": true`.
`--no-advisory` suppresses them entirely.
Hook
- Advisory rules are skipped by default in both the per-edit and Stop deep-pass
hooks, so the hook never nags about them. Opt in with
`.impeccable/config.json` -> `detector.advisoryRules: "include"`.
Tests
- Fixture + threshold + browser-adapter coverage; advisory-skip default and
opt-in for the hook; formatFindings partitioning. The em-dash-overuse stand
for a deferred copy rule in the tier tests is swapped to marketing-buzzword.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
From Paul's approved UX and the eb686f36 session post-mortem:
The standing exit: direction rounds carry a quiet, permanent "Play it
straight" action (payload flag canon, reserved id) on the decision page
and as the last structured-tool option. It is the user's door, never
the model's: never recommended, never weighed against the roll, and
choosing it swaps the bar rather than lowering it, two or three named
reference products become the craft level, canon executed at full
commitment. Safer/conventional steers resolve here, never to a
stranger re-roll.
Session fixes, each mechanical where possible: the ANSWER line now
names the chosen card's hero and board and directs opening them before
code (the session built from text alone after viewing a different
world's card); generation scale joins the imagery rule (a library of
centered 128px subjects foreclosed the atmospheric hero); DESIGN.md
rules are checked against the world's native devices and never added
to silence a hook finding (the session banned arcade lettering's own
offset shadow and laundered 8px through the ramp); staging joins the
FORM contract block (the axis was dropped silently at world-choice);
the finishing reviewer audits the ceiling against the QUALITY BAR card
after persistence (floor rigor was disguising unreached ambition); the
icon-tile clause names hand-drawn icons as remedy, not target.
Dist rebuild deferred: the release-gate campaign reads the pinned dist.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Abort signals do not cancel the TCP connect phase, so an unreachable API
stalled the seed ~10s before degrading. All API calls now share one
deadline, the roll fetch races it, and the CLI exits explicitly.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A grounded direction with no hero rendered a blank 16:9 void where the
card image belongs (seen live: the assigned Xerox Zine card led the
hand as a black hole next to two rendered challengers). An option with
no imagery now drops the media region entirely and leads with its
kicker and text; an option with only a board shows the board as its
front image with no flip.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A live retest showed the model dropping to the structured question tool
when the roll degraded: with no challengers and no cards it judged the
page pointless and presented one option in plain text. The degraded seed
output and the new-work rule now both state that degradation changes the
cards, not the channel; a browser session presents the assigned
direction as a single text-only card with re-roll on the decision page.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A traced Claude Code injection asserts for whole model families that the
user is not watching and cannot answer questions; it ships default-on
with no off switch, and it suppressed every interactive step of a live
run (interview skipped, PRODUCT.md inferred, decision page never
served). Prose in a reference file loses that argument, placement wins
it: context.mjs now emits AUTONOMY_DIRECTIVE_CHECK as tool-result
content in the working turn, telling the model such a claim is a
harness default, never session evidence, and to probe once with the
question tool before inferring. init.md makes the same test mechanical:
tool presence proves an answer mechanism, one real probe round is
required, inference afterward must be labeled and disclosed in the
first reply. The degraded concept-seed path now also tells the model to
disclose the degraded roll instead of presenting it as a full one.
Image-gen signaling stays positive-only per Paul: key present emits the
capability, absence stays silent so harness-native tools are not
suppressed.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Paul reproduced the Opus smoke failure in a fresh repo: given a
natural-language build intent, the model runs concept-seed directly and
skips the init divert entirely, so PRODUCT.md never exists and nothing
grounds the challenger fusion. Prose already says init-first in both
SKILL.md routing and new-work.md; prose alone does not hold the floor.
The deal path now refuses with a NO_PRODUCT_MD directive routing to
reference/init.md when loadContext finds no PRODUCT.md. The --chosen
telemetry ping stays ungated.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
