skills/pbakaus_impeccable
1
0
Fork 0
mirror of https://github.com/pbakaus/impeccable.git synced 2026-09-11 21:57:14 +03:00
Code Issues Packages Projects Releases Wiki Activity
1,659 Commits 92 Branches 69 Tags
2dcaacbcd17b7559ea44b061ca20557a528d739b
Commit Graph
21 Commits
Author SHA1 Message Date
Paul BakausandClaude Code 26f54d15c2 feat: just-in-time event instructions + frontier default for the LLM e2e agent 
Field feedback from two more Codex sessions drove both changes.

JIT instructions (live/instructions.mjs): every event live-poll prints
now carries _instructions, the authoritative next step for that exact
situation with real ids, paths, and line numbers substituted, and only
the active path's rules (a svelte-component session never sees JSX
guidance). The boot payload carries loop instructions the same way.
Instructions are versioned with the scripts, so they cannot drift from
behavior, and live.md's plumbing can keep shrinking toward contract plus
craft guidance. The Codex poll-discipline failure observed in the field
("the long poll was started, but I yielded the task instead of actively
servicing its result") gets a named anti-pattern in both the harness
policy and the boot instructions.

LLM e2e agent: default provider/model moves from Claude Haiku 4.5 to
OpenAI gpt-5.6-terra at medium reasoning effort via an Anthropic-shaped
shim over the ai SDK (the three call sites stay provider-agnostic;
Anthropic and DeepSeek remain selectable). The harness should exercise
the model tier that actually drives live sessions. Both the react and
sveltekit fixtures pass end to end with terra driving the trimmed
live.md and the new _instructions.

This work was produced with AI assistance (Claude Code).

Co-Authored-By: Claude Code <noreply@anthropic.com>
 2026-07-27 19:20:02 -07:00
Paul BakausandClaude Code f27bea5bc0 fix: third review round + unmask and fix the astro-vite7 e2e failure 
cursor[bot]:
- variant_mount_failed joins EVENT_TYPES_NEEDING_AGENT_REPLY so stream
  mode waits for the repair reply instead of moving on mid-lease.
- The fake agent's mount-failure repair no longer forces
  sourceEventType generate; the server maps the done reply onto the
  pending failure event, which acknowledges it instead of leaving it to
  be redelivered on every poll.

greptile-apps[bot]:
- With every helper server stopped, repo-root resolution now prefers the
  app whose durable store holds a non-terminal session (the interrupted
  session the user is recovering) over the most recent boot.

astro-vite7 (pre-existing CI failure, root-caused): Astro 7 auto-detects
AI-agent environments and daemonizes `astro dev`; the detached server
holds a lock, outlives the harness, squats dev ports across runs, and
makes the parent exit 0, which the harness read as a crash. The fixture
now sets ASTRO_DEV_BACKGROUND=1 (disables the agent detection) plus
--ignore-lock, and the harness supports per-fixture runtime.env. The
core cycle now passes for the first time; the missed-done recovery
scenario fails identically at origin/main with the daemon bypassed, so
it is marked as a per-scenario known limitation with that rationale.

This work was produced with AI assistance (Claude Code).

Co-Authored-By: Claude Code <noreply@anthropic.com>
 2026-07-27 15:55:03 -07:00
Paul BakausandClaude Code 17dabf4b7e Live v2: root manifest, mount-ack protocol, AST scaffolder, mechanical accept 
A ground-up hardening of live mode, driven by a production session in a
nested-app monorepo that hit six distinct failure classes. Full design
rationale in docs/LIVE-REWRITE-PLAN.md; every Codex-reported failure now
has a mechanical fix and a regression test.

Roots: live/roots.mjs resolves appRoot/repoRoot/contextRoot once at boot
(keyed on dev-server configs, not monorepo brand markers), persists a
manifest, and every live CLI re-anchors onto it at startup, so a helper
run from the wrong directory can no longer fork session state. Context
files are discovered upward to the git root.

Render truth: variant_mounted / variant_mount_failed events give the
journal per-variant mount state; failures reach the agent's poll queue,
raise a persistent error card with Retry (no more localStorage wipe), and
an attach probe names root/dev-server mismatches explicitly. The browser
rehydrates from the server when localStorage is gone.

Svelte: the scaffolder now parses with the app's own svelte 5 compiler.
Control flow survives (an each collection crosses the contract as one
structured prop), keyed each blocks hydrate synthetic keys, and anything
a detached preview cannot support falls back to source-preview instead of
shipping a wrong scaffold. Preview modules live in per-publish revision
directories, defeating stale transform caches.

Accept: CSS is reconciled, not appended. Matching selectors are replaced,
params bake from params.json kinds, the compiler's unused-selector pass
prunes superseded rules (pre-existing dead rules protected), a selector-
loss postcondition refuses any write that would drop hand-written rules,
and live-complete refuses to finish while live plumbing remains in source.

Also: framework registry (live/frameworks/) with a crash-safe injection
journal, session-store snapshot caching with read-only reads, protocol
enum consolidation, steer Send button, honest DESIGN-panel empty states.

Testing: new unit suites (roots, AST scaffolder, accept CSS, accept
pipeline, framework conformance); e2e now fails on preview-tree 404s,
proves computed-style mount for every variant, drives the Tune panel
through baked params, and injects failures (broken mounts, republish,
storage loss). New runtime fixtures: monorepo-nested-vite (repo root !=
app root) and vite8-sveltekit-stateful (each blocks + state). Nightly
full-matrix cron. An independent adversarial review pass preceded this
commit; its blocker and major findings are fixed and regression-tested.

This work was produced with AI assistance (Claude Code).

Co-Authored-By: Claude Code <noreply@anthropic.com>
 2026-07-27 15:09:40 -07:00
Paul BakausandClaude Fable 5 dbe0c12b91 Live: stop the preflight writing source, cache the resolution 
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>
 2026-07-22 22:49:44 -07:00
Paul BakausandClaude Fable 5 3f9fccdfd0 Live: lock down the local server against same-machine token theft (#304) 
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>
 2026-07-22 21:59:28 -07:00
Paul BakausGitHubClaude
 		d0ac67c6e9 Live: polling rework, source locks, preflight scaffolding (#381) 
* Improve Live polling responsiveness and reliability

Restore foreground/background polling as the primary harness architecture, add progressive publication and framework-safe previews, and harden quality and regression coverage. The experimental app-server runtime is intentionally excluded.\n\nPrepared with AI assistance under maintainer direction.

* Fix source-safety, detector, and lock defects in Live polling work

Addresses the review findings on #371, plus several the bots did not catch.
All fixes have regression coverage that fails on the prior code.

Source corruption:
- Vue accept dropped valueless root attrs (disabled, v-cloak) and, worse,
  rewrote @click="x" as a literal click="x" DOM attribute, because the attr
  parser was name-anchored and skipped the sigil. Tokenize the whole Vue attr
  grammar and normalize shorthands so accept round-trips directives.
- --variant was interpolated unescaped into a RegExp, so --variant '.*' matched
  the original block first and reported a successful accept while silently
  restoring the original. Validate against the digits pattern the browser and
  the /events schema already enforce.
- --id reached path.join unvalidated, so --id ../../../../etc/evil wrote and
  read receipts outside the project. Hoist the existing safeSessionId check
  into impeccable-paths and apply it at every id-to-path sink.

Accept/lock correctness:
- Plain HTML/JSX accept and discard did not catch SOURCE_LOCKED, so contention
  exited non-zero with empty stdout and the agent got no JSON to retry on.
- Lock staleness was mtime-only and never read the pid it records: a holder
  whose critical section outran 60s had its live lock swept, admitting a second
  writer to the same file, while a crashed holder blocked accepts for a full
  60s. Decide staleness by owner liveness, and release only our own lock.

Detector:
- isNeutralColor only parses computed color forms, so routing authored CSS
  through it reported inset 4px 0 0 #000 / black / #e5e7eb as chromatic
  side-tab stripes. Add an authored-color neutrality test covering hex and
  named neutrals; the fixture had no literal-color cases at all.
- Rule line numbers were off by one for every rule after the first, and
  commented-out CSS was scanned as live rules.

Server:
- An error reply carries no sourceEventType, and inferSourceEventType returned
  undefined, which acknowledgePendingEvent treats as a wildcard: a stale
  generate worker's failure consumed the user's queued Accept, which then
  reached no agent and left the browser in SAVING forever.
- The generate preflight spawned live-wrap.mjs synchronously inside the request
  handler, freezing the single-threaded server for the whole scaffold (~7.6s
  measured on this repo, 15s ceiling) and stalling Accept/Discard/SSE. Make it
  async, claiming the lease before the first await so no event double-delivers.
- Every browser checkpoint was echoed back as variant_progress, so a Tune
  slider drag remounted the preview under the user's cursor and latched the
  *_reviewable phases from the wrong trigger. Gate on the reason.

Cleanup:
- Collapse four divergent benchmark argv parsers into scripts/lib/cli-args.mjs.
  Three silently misread flags: --iterations 20 benchmarked 5, --agent llm ran
  the fake agent, --median-target=0.4 used the default threshold.
- Drop a snapshot cache this branch made write-only (it grew per session for
  the server's lifetime and was never read), a dead exported reconcile helper,
  and the unused deferReply branch.

Prepared with AI assistance under maintainer direction.

Co-Authored-By: Claude <noreply@anthropic.com>

* Route the last two benchmark scripts through the shared argv parser

Follow-up on review feedback. The previous commit consolidated four of the six
Live benchmark parsers and left these two on their own hand-rolled `arg()`,
which was the inconsistency the first pass was meant to remove.

- benchmark-live-control.mjs and benchmark-live-init.mjs parsed --iterations
  with Number(), so a non-numeric value became NaN and `index < NaN` ran the
  benchmark zero times before failing on the metrics file. They also accepted
  only the space-separated form, so --iterations=20 silently measured the
  default. Both now use parseArgs + positiveIntFlag, which throws on a value
  that was clearly meant as a number.
- benchmark-live-control.mjs read the metrics file with no handling for the case
  where the run produced nothing: a missing file surfaced as a raw ENOENT stack
  and a malformed line as a bare SyntaxError. Report both with a diagnostic
  naming the file and the env var that populates it.
- summarize() now reports a `samples` count and nulls instead of letting
  percentile() read past an empty array, where the NaN serialized to null and a
  report of nothing measured looked like a real measurement.

Prepared with AI assistance under maintainer direction.

Co-Authored-By: Claude <noreply@anthropic.com>

* Stop telling users a busy agent is disconnected

The agent-poll indicator tracks whether a poll is parked, which is the right
signal for "can steering reach the agent right now" and is why the flag itself
is left alone. But it goes quiet for two different reasons, and both got the
same copy: "Agent disconnected - run live-poll.mjs to connect".

Under the one-shot foreground polling that live.md calls the primary contract,
no poll is parked while the agent works, so the second reason is every normal
generation. For its whole duration the bar told the user a healthy session was
broken and advised them to start a poll loop that was already running.

Pick the copy from the live state, which the browser already tracks: GENERATING
and SAVING mean the agent holds work it was handed, so say it is working. Every
other state with no parked poll keeps the original, actionable wording. The
aria-label carries the same distinction, since the tooltip is mouse-only.

The text is derived at read time rather than cached, because the live state moves
between the 5s status polls and a finished generation would otherwise keep
reading "Agent is working" until the next one landed. Deriving it also keeps the
read out of setLiveState, which runs long before agentPollingConnected's
declaration and would hit its temporal dead zone.

Prepared with AI assistance under maintainer direction.

Co-Authored-By: Claude <noreply@anthropic.com>

* Scope design-system-font-size off the injected live overlay

live-browser.js builds a self-contained UI that renders over arbitrary host
pages, so its inline type scale is deliberately independent of DESIGN.md, which
documents the impeccable website's ramp. The rule fired 32 times there and is
the only rule that fires on that file.

Suppress it as a file-scoped value wildcard rather than via ignoreFiles: an
ignoreFiles glob would silence every rule for the file, and the overlay is real
user-facing chrome where a future contrast or side-tab finding should still be
heard. Scoped to this one file, so the rule keeps working everywhere else.

Written by hand because hook-admin's ignore-value cannot emit the `files` array
that detector.ignoreValues supports and existing entries already use.

Prepared with AI assistance under maintainer direction.

Co-Authored-By: Claude <noreply@anthropic.com>

* Let hooks ignore-value scope a rule to files, and stop churning the config

Fallout from suppressing the overlay's font-size findings: the narrowest
exception detector.ignoreValues supports was unreachable from the path the hook
tells the model to use, so the guidance steered to the blunt instrument instead.

- hook-admin's ignore-value now takes --file / --files / --file= / --files=,
  matching `impeccable ignores add-value`, which already had them. Without it the
  only file-scoped option was ignore-file, which silences every rule for a path
  permanently, including rules not yet written.
- A bare wildcard value is now refused with a message pointing at either --file
  or ignore-rule. Previously `ignore-value <rule> "*"` quietly wrote a
  project-wide suppression from a single file's finding.
- ignore-value keyed entries on rule+value only, so a second scope for the same
  rule overwrote the first instead of coexisting. Key on the file scope too.
- An unknown flag folded into the value: `ignore-value overused-font Inter
  --shard` stored "inter --shard", matched nothing, and reported success. Reject
  it, as the sibling command does.

Config churn: normalizeIgnoreValueEntries runs on every write and emitted keys as
rule, value, files, reason, createdAt while the config on disk uses createdAt
before reason. Any edit therefore rewrote every untouched entry (35 churned lines
for a one-line change). Pin the canonical order in both copies of the normalizer
and in ignores.mjs, and add a test that the two copies cannot drift apart.

Also point the hook's own footer and reference/hooks.md at the file-scoped form
first, and say plainly what ignore-file costs.

Prepared with AI assistance under maintainer direction.

Co-Authored-By: Claude <noreply@anthropic.com>

* Correct the prose-gate docs and write down the no-bump-in-a-PR rule

CLAUDE.md said the prose validator "deliberately skips skill/", which is only
half true and cost a build failure this week: validateProse skips it, but
validateSkillProse then scans skill/**/*.md and fails the build on em dashes plus
the phrases with no technical reading. Document both gates, which files each one
reads, and the line that actually matters in practice: an em dash in
skill/reference/*.md fails the build, one in a skill/scripts/*.mjs comment does
not. Each claim was checked against a real `bun run build`.

Also record that feature PRs do not bump manifest versions or add changelog
entries. It was not written down anywhere: not CLAUDE.md, not AGENTS.md, not the
PR template. CLAUDE.md's "Bump when: CLI code changes" reads as an instruction to
bump inside the PR that touches cli/, so say plainly that it names which
component a change belongs to rather than when to edit the manifest.

Put the rule in AGENTS.md too. That is the guide the agents opening PRs here
actually read, so a rule about PR hygiene living only in CLAUDE.md would not
reach them.

Prepared with AI assistance under maintainer direction.

Co-Authored-By: Claude <noreply@anthropic.com>

* Bring Live progressive delivery and the generator subagent to Claude Code

Almost none of this branch's Live work was actually Codex-specific. The publisher,
the fences, the source locks and the browser's partial-arrival UI are plain node
and DOM with zero provider references, and the progressive E2E already passes on
five frameworks driven by a non-Codex agent. The Codex-only part was policy prose
and one frontmatter line, so Claude Code shipped the progressive browser UI it
could never trigger.

Progressive delivery, Codex and Claude Code:
- Add a `live-progressive` capability tag and opt codex, agents, and claude-code
  in. A provider block takes one tag, so naming harnesses would have meant
  duplicating the recipe per tag; a capability reads better than a provider list
  anyway. Cursor and everyone else keep the atomic path until their poll loop is
  known not to stall on the extra publish calls.
- Claude Code publishes variant 1 as soon as it validates rather than waiting to
  write the whole trio in one edit. Nothing about the arrival path needed
  changing: the publisher writes, framework HMR pushes, and the browser's
  MutationObserver counts variants. The parent conversation was never in that
  path, which is why Claude Code's lack of subagent progress streaming does not
  matter here.

Generator subagent:
- Drop `providers: codex` from impeccable-live-generator. The build already maps
  its frontmatter correctly for Claude Code, and impeccable-manual-edit-applier
  has shipped to .claude/agents/ this way all along.
- The reason differs per harness, so the reference says so: Codex delegates to
  unblock a foreground poll, Claude Code delegates to keep a long session's
  screenshots and variant CSS out of the main context. Follows the existing
  manual-edit-applier convention: both agent names, and an inline fallback when
  native subagents are unavailable.

Fixes found on the way:
- The two publish commands hardcoded `.agents/skills/impeccable/scripts/` while
  the other thirteen commands in live.md use {{scripts_path}}. Correct only for
  the Codex repo-skills bundle; it would have pointed Claude Code at a directory
  its install never creates. The shipped .codex variant was already internally
  inconsistent. Now covered by a test.
- `--agent=codex` resolved to the canned fake agent, because the flag parsed as
  `x === 'llm' ? 'llm' : 'fake'`. The private evals Live runner passes exactly
  that, so a real-harness run would have scored deterministic stub variants and
  reported them as Codex output. Unknown values for --agent, --scenario and
  --delivery now fail loudly.
- live-reference tests now compile with each provider's real providerTags instead
  of hand-written lists, so a providers.js misconfiguration fails in tests rather
  than shipping.

Verified: progressive E2E green on vite8-react-plain against a real Vite server
and Chromium; every provider variant's publish and poll paths now agree; Cursor
and Gemini still compile to atomic only.

Prepared with AI assistance under maintainer direction.

Co-Authored-By: Claude <noreply@anthropic.com>

* Fix inset-order detection, the unlocked artifact discard, and stray boolean flags

Three of the four open review findings. The fourth is declined below.

- The inset-stripe scan only matched layers starting with `inset`, but the keyword
  is order-independent: `box-shadow: 4px 0 0 var(--brand-accent) inset` paints the
  same stripe and was silently missed. Strip the keyword wherever it sits, but
  only as a standalone token, so a color like var(--inset-accent) is not mangled
  into `var(-- -accent)` and quietly reclassified as neutral. The fixture now
  covers both orders plus that token, and a trailing-inset neutral still passes.
- The source-artifact discard deleted the preview without the source lock, unlike
  every other discard path. Take the lock. Narrower than reported, though: the
  server journals `discard_requested` as a fenced phase before live-accept runs
  and the publisher checks it three times, so a publish could never land on a
  discarded session. What this actually prevents is deleting the artifact under a
  publisher mid-critical-section, turning a clean stale_generation_epoch into an
  ENOENT crash.
- benchmark-live-providers.mjs still compared `--headed` and `--skip-cleanup-control`
  against a boolean sentinel, so the `=true` spelling silently did nothing. My
  gap: I introduced boolFlag and converted benchmark-live.mjs but not this one.
  skipCleanupControl is now read once rather than twice, so the two call sites
  cannot drift.

Declined: tightening the selector guard that skips `active` / `current` /
`selected` tokens. It does cause false negatives on names like `.selected-feature`,
but the rule's contract makes selection and focus indicators its one exception,
and `.active-tab` / `.current-step` / `.selected-row` are syntactically identical
to `.selected-feature`. No regex separates them, so tightening the guard trades
missed stripes for false positives on exactly the case the rule exempts. The
conservative skip is the intended behavior.

Prepared with AI assistance under maintainer direction.

Co-Authored-By: Claude <noreply@anthropic.com>

* Classify failed accepts as errors, and fix parallel lane race/all misuse

Two of the three new findings, plus the bug that chasing them exposed in my own
earlier fix. The third is mitigated rather than broken; details below.

Failed accepts reported success:
live/completion.mjs only classifies a result as `error` when it carries
`mode: 'error'`. Everything else unhandled falls through to `agent_done` with an
ok ack, which is deliberate for the documented fallback paths (two tests pin it)
but wrong for a real failure. So `accept_receipt_conflict` reported success, and
reference/live.md's `handled: false` without `mode` bullet told the agent to
"read file, find markers, edit" — hand-applying a second accept on top of the one
the receipt already recorded.

The same hole swallowed `source_locked`, which is mine: the earlier commit made
lock contention return clean JSON so the agent could retry, but the classifier
turned that failure into agent_done/ok, so the accept was dequeued and silently
lost. Mark genuine failures with `mode: 'error'` through one `operationFailure`
helper, and give live.md a `mode: "error"` bullet with per-error guidance: retry
the same command on `source_locked`, never hand-edit, and on a receipt conflict
report what the session actually resolved to. The deliberate fallback and
markers-not-found handoffs stay untouched.

parallel-compact lane orchestration:
`Promise.race` settles on the first *settlement*, so one lane failing fast
rejected the whole first-variant step while two lanes were still on their way to
succeeding. `Promise.any` now takes the first success and only a total wipeout is
fatal, reporting every lane's reason. The tail step's `Promise.all` surfaced a
raw lane error non-deterministically; `Promise.allSettled` now reports how many
lanes failed and why. Added a `requestImpl` seam so lane orchestration is
testable without a provider key.

Not a defect: the browser releasing Accept before the source write. That is the
intended optimistic design, and it is safe because poll-lanes ranks accept at
priority 0 against generate at 2, so a queued accept is always leased before a
generate the user queues afterwards, even if the generate arrived first. Its
source write lands inside the poll script before the next generate preflights.
That invariant is load-bearing and had no tests at all; poll-lanes.mjs now has a
suite covering it plus lease and type filtering.

Prepared with AI assistance under maintainer direction.

Co-Authored-By: Claude <noreply@anthropic.com>

* Finish the failed-accept classification my last commit only half did

All three new findings are the same root cause, and it is my incomplete fix:
operationFailure only covered results built from a *thrown* error. Two paths it
missed:

- Two catches wrote the failure result as a multi-line literal, so the
  single-line replace skipped them. The Vue accept catch was still bare, exactly
  as reported; the Svelte one too, though its failures happened to be caught by
  completion.mjs's Svelte-only special case.
- The accept implementations also *return* `{handled: false, error}` for their own
  checks (variant missing, template empty, original text ambiguous). Those never
  throw, so no catch ran and no `mode` was set.

Both layers now agree, because each is reachable on its own:

- live-accept marks any unhandled preview-path result via markPreviewFailure,
  keyed on `previewMode` — a clean discriminator, since only the preview branches
  set it and a plain wrapper never does. This is what the agent reads:
  reference/live.md routes on `mode`, so without it the agent was told "read
  file, find markers, edit" for a preview that has no markers in source.
- completion.mjs replaces its arbitrary svelte-component special case with the
  set of preview modes whose variants live outside the user's source. That case
  existed for precisely this reason; Vue and source-artifact were simply never
  added, so the identical failure on those paths acknowledged as success.

The plain wrapper keeps its manual handoff, which is the one shape with editable
markers in source. Both deliberate handoffs (mode: 'fallback' and markers not
found) still classify as agent_done, now pinned by a test so the generalization
cannot swallow them.

Prepared with AI assistance under maintainer direction.

Co-Authored-By: Claude <noreply@anthropic.com>

* Stop the progressive benchmark agent inventing a second variant on count:1

`Math.max(1, event.count - 1)` floored the tail request at one variant, so a
one-variant request fetched a second direction and assembled two. Ask for
`count - 1` and return the first variant untouched when there is no tail.

Latent rather than live: the only caller hardcodes `count: 3`. The reason it is
worth fixing is the caller inconsistency it exposed. tests/live-e2e/agent.mjs
gates its split-progressive path on `event.count > 1`; benchmark-live-providers.mjs
had no such guard, so it would have run the tail for a one-variant request, and
the parallel strategy would have assembled its three fixed lanes regardless of
what was asked for. Guard the caller the same way.

Prepared with AI assistance under maintainer direction.

Co-Authored-By: Claude <noreply@anthropic.com>

* Drop the live generator subagent; fix the artifact decoy that broke accept

The first real Claude Code Live run failed, and the subagent was not the cause.

Root cause: progressive publication stages each revision as
`.impeccable/live/artifacts/<id>-r<n>.<source-ext>`, nothing ever deleted them,
and findSessionFile's walker skipped only node_modules/.git/dist/build. It
searches src, app, pages, ... then `.`; a project whose source is not under one of
those (this repo's own site lives in site/pages/) falls through to the `.` walk,
where dot-directories sort before letters. So accept found the artifact instead of
the real file. Two outcomes, both reproduced: where isGeneratedFile returns true
it declines with mode: 'fallback' (what the run hit, after which the agent
hand-carbonized several hundred lines across three stylesheets, including
unrequested drive-by edits); where it returns false, accept writes the variant
into the throwaway artifact and reports handled: true while real source never
changes.

The E2E suite could not have caught this. Every fixture puts source under `src/`,
which is searched before the `.` walk can reach `.impeccable`. Five framework
fixtures and three progressive scenarios pass because of fixture layout, not
because the path works. I read that as evidence and shouldn't have.

- Never search `.impeccable`: it is Impeccable's own state, never project source.
- Retire a session's staged artifacts on accept/discard, so they cannot outlive
  the session and become a decoy for anything else that walks the tree.
- Regression tests use a site/pages layout with artifacts present. All three fail
  against the previous code.

Generator subagent removed, on both harnesses:
The parent must hand-compress the design system into the handoff, and compression
is lossy. Measured on the real run: a 6,826-char handoff carrying exactly one
token reference, after the parent had itself read kinpaku-tokens.css. The subagent
then spent 3 of its first 9 turns hunting DESIGN.md, gave up, and emitted 0
var(--token) uses and 22 raw oklch literals — violating its own spec's "Never
invent raw colors when tokens exist" — including a 1:1 gold-on-gold contrast bug.
Isolation is not a benefit here; knowing the design system is the job. Generation
stays in the main thread, which already holds the tokens and writes them from the
first byte, so carbonize is a move rather than a translation.

Copy edits keep their subagent: applying a known set of ops to a named file is
self-contained, so an isolated context costs nothing. That is the line.

Progressive delivery stays for Codex and Claude Code, main-thread driven. Claude
Code keeps the full benefit because its poll is a background task. Codex's poll
blocks the foreground, so with no subagent the user sees variant 1 early via HMR
but cannot accept it until the trio finishes; that is the cost of the
simplification and it is worth naming.

Prepared with AI assistance under maintainer direction.

Co-Authored-By: Claude <noreply@anthropic.com>

* Rip out the dead isolated-preview mode and the private repo's job

Comparing this branch's live against main's turned up two whole features that
never made sense here. -2,466 lines.

1. The isolated source-artifact preview was never switched on.

`scaffoldSourceArtifactSession` is only reachable via live-wrap's `--isolated`,
and nothing passes it: not the server's preflight, not live.md, nothing. Proved
it end-to-end — the default wrap writes markers straight into real source and
creates no previews/ session. So the mode was wired through three modules,
carried its own accept/discard branches, browser branches, server metadata
resolution, preview-mode classifier entry, and test suites, and none of it could
run.

Worse, live.md documented it as the active path and told the agent "The true
source is only the publisher's hash fence and must remain byte-identical until
Accept." That is false: the wrapper lands in source at scaffold time and each
revision rewrites it. An agent following that sentence believes source is
protected when it isn't, and the leftover artifacts are what made accept resolve
the wrong file in the first real run. live.md now describes what actually
happens, including that markers are visible in source until Accept or Discard.

Removed: source-artifact.mjs, --isolated, the preflight's isolated option, the
accept/discard branches, four dead browser branches, the server's previews/
resolution, the classifier entry, and their tests. Kept the previews/ gitignore
pattern: an ignore line for a directory that cannot exist is free, and a test
pins it.

2. Quality judging belongs to the private evals repo, which says so.

runner/live/README.md there is explicit: the public repo owns protocol
correctness, framework coverage, timing, source commit, recovery, and a
rubric-free evidence bundle; the private repo owns the task corpus, baselines,
comparative judges, and release-quality decisions — "Do not add quality rubrics,
competitor comparisons, or broad fixture corpora to the public Live benchmark."

This branch added exactly those: an LLM judge scoring 1-10 on "off-brand,
generic-AI" (live-rendered-quality.mjs, judge-live-rendered.mjs), a
cross-provider comparison with a BRAND_CONTRACT rubric (live-provider-benchmark
.mjs, benchmark-live-providers.mjs), and a brand-fidelity fixture corpus. All
removed, with bench:live:providers and their suite entries.

Also removed tests/framework-fixtures/README.md's "External quality-eval
fixtures" section: it documented a bench:live workflow using --fixture-dir,
--agent=codex, --action and --evidence-bundle, none of which benchmark-live.mjs
implements, plus an evidenceCapture block nothing reads.

Kept: timing benchmarks (the public repo's half of that boundary), progressive
publication, the source lock, poll lanes, and Nuxt/Vue component previews.

Coverage note: deleting the isolated suites took the only tests for
`source_locked` classification with them, so the plain wrapper path — now the
only non-component preview — gets equivalent accept and discard coverage. Both
new tests fail if mode:'error' is removed.

Prepared with AI assistance under maintainer direction.

Co-Authored-By: Claude <noreply@anthropic.com>

* Flag inset stripes written with the two-length box-shadow form

box-shadow takes <length>{2,4}: only the two offsets are required, so
`inset 4px 0 red` is valid and paints the same single-edge stripe as
`inset 4px 0 0 red`. The scan demanded a third length, so the short form was
silently missed.

Blur and spread now default to 0 when omitted, which is exactly the stripe shape
the rule looks for. The neutral-color and blur/spread exclusions still hold:
`inset 4px 0 #000` and `inset 4px 0 5px var(--brand-accent)` both pass. Fixture
covers both orders of the short form plus those two exclusions, and fails against
the previous regex.

Third false negative found in this rule (after trailing `inset` and literal
neutral colors), all from the same cause: the scan was written against one
spelling of the syntax rather than the grammar.

Prepared with AI assistance under maintainer direction.

Co-Authored-By: Claude <noreply@anthropic.com>

* Live: polling rework, source locks, preflight scaffolding, Vue previews

Carved out of #371, minus progressive publication. Everything here works
against real project source the way main's Live already does: the agent
writes variants into the file the browser loaded, HMR fires, Accept
promotes and carbonizes. Nothing is staged anywhere.

Poll lanes. Events now carry an explicit priority: accept/discard/exit
ahead of manual_edit_apply/steer/carbonize_cleanup ahead of generate. A
long generate can no longer sit in front of the Accept the user just
clicked. leaseEvent claims its lease before awaiting, so a slow prepare
cannot hand the same event to two pollers.

Source locks. A per-file mutex around every accept and discard path, keyed
on a digest of the absolute path. Staleness is decided by owner-pid
liveness rather than mtime, so a wedged lock clears when its owner dies
instead of after an arbitrary timeout, and a slow-but-live accept is never
stolen from. Only the owning process can release a lock.

Preflight scaffolding. The server runs live-wrap (or live-insert) before
the poll returns and hands the result back as event.scaffold. That walk is
measured at ~7.6s on a large repo; moving it off the agent's critical path
removes a deterministic tool round trip without touching the generated
design. Falls back cleanly to the agent running the helper itself.

Vue previews. previewMode: "vue-component" for Nuxt/Vue targets, matching
the existing Svelte component path: variants compile as real SFCs from a
dev-only directory so the route is never rewritten during generation, and
Vite mounts them without invalidating page state. Accept is the only route
write. Includes a Vue attr tokenizer that normalizes shorthand bindings
(@x, :x, #x) to their canonical forms.

Accept hardening. Every thrown failure now returns mode: 'error' rather
than an ambiguous unhandled result, so a real failure is never classified
as a deliberate manual handoff and silently dropped. The marker search
skips node_modules/.git/dist/build/.impeccable.

Shared CLI arg parsing extracted to scripts/lib/cli-args.mjs.

Assisted-by: Claude Code

* Drop the progressive benchmark, remove dead wrap scaffolding

Review fallout from removing progressive publication.

The Live benchmark existed to compare atomic against progressive delivery:
compareModelBackedReports measures goToFirstVariantMs improvement of one
over the other. With progressive gone it measures nothing against nothing.
Worse, benchmark-live.mjs still passed `progressive` to bootFixtureSession,
which no longer accepts it, so `--delivery progressive` was silently
ignored and would have emitted reports labeled progressive that actually
ran atomic. Silent wrong data is worse than a crash. It was built for
progressive, so it goes with progressive: benchmark-live.mjs, its lib, its
test, and the bench:live script. If an atomic latency baseline is wanted
later, that is a smaller thing built on purpose.

live-wrap.mjs: sourceOriginalLines was assigned and never read.

Both found by review bots on #381 (Copilot).

Assisted-by: Claude Code

* Drop the Vue preview mode; it never reached Svelte's accept path

Cursor found that inlineVueComponentAccept never receives paramValues,
while the Svelte equivalent uses them in 23 places: Accept on a tuned Vue
variant silently persisted the default and threw the user's tuning away.

Chasing that corrected something I had asserted the other way round. I said
Vue's raw-CSS-append was inherited from the Svelte path. It is not.
svelte-component.mjs calls sanitizeAcceptedSvelteCss before writing, which
sanitizes the CSS and bakes tuned params into it. vue-component.mjs had no
sanitize step at all — it appended the variant's <style scoped> body into
whatever style block came last, so a variant could leak CSS site-wide when
the last block was global, and brace CSS landed in a lang="sass" block.

Both are the same defect: the Vue mode mirrored Svelte's preview path
without its accept-side subsystem (bakeParamValuesInCss,
sanitizeAcceptedSvelteCss, appendSanitizedCssRule,
rewriteAcceptedSvelteSelector, rewriteParamSelectors — roughly 200 lines of
CSS rewriting). Both were introduced here, not inherited. A shipped Vue
session could leak styles and discard tuning without saying so.

So it comes out. The poll lanes, source locks, preflight scaffolding, and
accept hardening do not depend on it and are worth landing now. Vue returns
when its accept path reaches parity. The nuxt-vite7 fixture goes back to
main's plain-wrapper shape.

Assisted-by: Claude Code

* Stop the lease redelivery test racing the scheduler

CI failed `does not drop polled events until the agent acknowledges them`
on a commit whose content was byte-identical to one that passed, which is
the signature of a flake rather than a regression.

The test leased an event for 50ms, then asserted a second poll saw a
timeout because the lease was still held. That gave the whole second HTTP
round trip a 50ms real-time budget: cross it and the lease expires, the
event is redelivered, and the assertion fails for a scheduling hiccup
instead of a bookkeeping bug. Locally it passed 6/6; a loaded runner is
where it bites.

Hold the lease for 1000ms so a round trip cannot cross it, and wait
LEASE_MS + 300 before asserting redelivery, so each half has headroom in
the direction it asserts.

Verified by injecting a 60ms stall before the second poll: the old test
fails with exactly the CI message, the new one passes.

Assisted-by: Claude Code

* Recover live sessions that reload past the generation done broadcast

The preflight scaffold write (new in this PR) triggers a framework
full-reload — Astro reloads the page for any .astro edit. When the
agent's variant write and its done SSE land while the browser is
mid-reload, the resumed page misses both the second HMR reload and the
done broadcast: it comes back up on the scaffold-only source and waits
in GENERATING at 0/N forever, with the finished variants sitting in
source. This is the astro-vite7 CI timeout; the failure artifacts show
the full sequence (scaffold at 26.319s, done at 26.515s, the new page's
browser_resumed checkpoint at 26.653s, DOM still scaffold-only).

Three-part fix:

- session-store: agent_done now stamps a monotone generationCompletedAt
  on the snapshot. Browser checkpoints legitimately regress phase and
  arrivedVariants (a resumed page reports what it sees), so completion
  needed a field checkpoints cannot un-set.
- live-browser: on every SSE (re)connect, compare the session summary's
  generationCompletedAt against local progress; when behind while
  GENERATING, pull the finished variants from source (same settle delay
  as the done handler's HMR-first fallback). Covers both orderings of
  resumed-checkpoint vs agent_done. Also, the source-fallback empty-
  wrapper branch no longer tears the session down mid-generation — a
  scaffold-only wrapper is a legitimate in-flight state, so stay in
  GENERATING instead of destroying a session the agent is still filling.
- live-server: a browser checkpoint reporting generating/behind for a
  session whose generation already completed re-broadcasts the stored
  done (idempotent for every other tab), and connected-payload summaries
  expose generationCompletedAt for the browser-side check.

Coverage: live-server unit tests for redelivery, the no-redelivery
guard, and marker durability across checkpoint regression; plus a
deterministic live-e2e scenario on astro-vite7 that blocks the reloaded
page's SSE stream and mocks its HMR websocket dead until after the agent
finishes, forcing the missed-broadcast window every run. All new tests
fail against the pre-fix code.

The e2e harness additionally gains an IMPECCABLE_E2E_ATOMIC_DELAY_MS
lever (widens the scaffold-to-write window) and env-gated console/nav
tracing (IMPECCABLE_E2E_CONSOLE=1) used to diagnose this.

The hypothesis that preflight opens a wrapper-with-no-variants window
came from Copilot's review sketch in the follow-up WIP PR; the killing
mechanism differs from that sketch (nothing calls recoverEmptyCycling in
the CI trace — the session hangs precisely because no code path runs at
all), but the window is real and the guard it suggested is folded into
the source-fallback fix.

Assisted-by: Claude Code

Co-Authored-By: Claude Code <noreply@anthropic.com>

* Retry a completion-driven source fallback that reads only the scaffold

Greptile flagged a hole in the previous commit's empty-scaffold guard:
when a `done` has already been delivered, the source fallback gets
exactly one read. If that read returns the preflight-only scaffold (a
stale source view, or an agent whose write lands in multiple steps),
the guard's silent return left the tab in GENERATING with no further
event ever coming — the same stuck state the previous commit fixed,
reintroduced through a different door.

Callers that know generation finished (the done handler's fallback and
the SSE-reconnect self-heal) now pass generationCompleted, and an empty
read on that path re-reads the source up to 3 times before surfacing
recoverEmptyCycling instead of hanging. Mid-generation callers are
unchanged and still wait indefinitely — a real agent can legitimately
take minutes between scaffold and write, and tearing that down was the
original #385 hazard.

The missed-done e2e scenario now also serves a captured scaffold-only
copy for the first post-reconnect /source read, forcing the retry path
every run. Verified failing against the pre-retry code (tab stranded in
GENERATING, test timeout) and passing with it.

Assisted-by: Claude Code

Co-Authored-By: Claude Code <noreply@anthropic.com>

---------

Co-authored-by: Claude <noreply@anthropic.com>
 2026-07-19 18:42:41 -07:00
Abdul WahabGitHubCursor
 		49ae0384b9 Fix live variant cycling hydration mismatch on SSR frameworks (#287) (#288) 
* Fix live variant cycling hydration mismatch on SSR frameworks

Drive variant visibility and range/toggle --p-* custom properties through
an injected session stylesheet instead of mutating hidden/style on
server-rendered variant divs. Fixes flaky nextjs-app-router expectConsoleClean
failures (issue #287), same pattern as scroll-anchor (#276) and pick-cursor (#286).

Co-authored-by: Cursor <cursoragent@cursor.com>

* Refactor variant-state stylesheet for readability

Extract named display constants (VARIANT_HIDE_DECL / VARIANT_SHOW_DECL) and
small variantStateSelector / variantParamDecls helpers so the rule-building is
self-documenting. Restore the scroll-lock comment to startScrollLock. No
behavior change; regression guards updated to match.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Fix: keep variant-state stylesheet in sync on first-reveal and paramless cycle

Stop refreshParamsPanel from removing the injected variant-state sheet
during GENERATING first-reveal, and re-sync the sheet when cycling to a
paramless variant so stale --p-* rules do not persist. Harden the
updateVariantStateStylesheet guard to num == null || num < 1.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Fix: apply tuned --p-* inline for client-mounted Svelte component variants

Svelte component sessions mount into [data-impeccable-component-mount]
with no [data-impeccable-variant="N"] wrapper for the state stylesheet to
target. Restore inline --p-* on the client-mounted element for range/toggle
params while keeping the SSR div path on the injected stylesheet.

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-07 17:25:22 -07:00
Abdul WahabGitHubCursor
 		672517f76e Add automatic design hook install and exceptions (#170) 
* docs: add PRD for design detector hook integration

Plans a PostToolUse hook for Claude Code and Codex that runs the
existing design detector after every relevant file write and feeds
findings back to the agent as advisory system-reminder context. No
implementation in this commit; covers UX, technical design, build
pipeline changes, distribution, coverage tradeoffs, and rollout.

Co-authored-by: Cursor <cursoragent@cursor.com>

* docs: revise hook PRD with best-practices review

Folds in the P0/P1/P2 findings from an online best-practices critique
against the official Claude Code and Codex hook references plus 10+
2026 community guides and similar prior-art tools (claw-hooks,
claude-code-hooks-mastery).

Key changes:
- Exec form everywhere (Codex snippet was shell form), with Windows
  rationale.
- Default timeout dropped from 10s to 5s.
- Re-entrancy guard (CLAUDE_HOOK_DEPTH) and per-file edit counter.
- Session-scoped finding dedup promoted from open question to v1.
- Per-language inline-ignore syntax map (HTML/JSX/CSS/JS).
- Hard-skip rules for sensitive paths and generated/lock files.
- Honest framing about Claude Code lacking per-plugin hook disable.
- Honest framing about Bash-written files being invisible in v1.
- Codex Windows-not-supported call-out, feature flag note, trust ceremony detail.
- Optional NDJSON audit log via IMPECCABLE_HOOK_LOG.
- Findings cap lowered 8 → 5 with attention-budget rationale.
- Versioned envelope ([impeccable@1]) on rendered template.
- Expanded test plan, decision log, and stdin payload appendix.

Co-authored-by: Cursor <cursoragent@cursor.com>

* feat(hooks): ship the design detector hook for Claude Code and Codex

Implements docs/hooks-prd.md: a PostToolUse hook that runs the
impeccable design detector after every Edit/Write/MultiEdit on a UI
file and pushes findings into the agent's next-turn context as a
short system reminder. Silent on clean files. Never blocks an edit.

Why this matters: today, design slop (side-tab borders, gradient
text, purple/cyan palettes, bounce easing, etc.) only gets caught
when a human notices or someone explicitly runs /impeccable audit.
The hook closes the loop at the moment slop is written.

What ships in v1
- skill/scripts/hook.mjs: PostToolUse entry. Reads stdin, runs the
  detector in-process (no `npx impeccable` cold start), emits
  hookSpecificOutput.additionalContext when fresh findings exist.
- skill/scripts/hook-lib.mjs: extracted helpers (config, cache,
  filter, render, audit log, runHook orchestrator). 100% unit-testable.
- skill/scripts/hook-session-start.mjs: SessionStart greeting,
  gated by a project-scannable probe + 30-day throttle.
- skill/scripts/hook-admin.mjs: backs /impeccable hooks
  on/off/status/ignore-rule/ignore-file/reset.

Hardening built in
- Re-entrancy guard (IMPECCABLE_HOOK_DEPTH) so the hook can never
  recursively spawn itself.
- Hard-skip regexes for sensitive paths (.env, .pem, id_rsa,
  secrets, credentials, .git) and generated/lock/build output. These
  fire before the file is even read; cannot be turned off via config.
- Path-traversal check on the inbound file_path.
- Session-scoped dedup keyed by (session, file, rule, line) so the
  same finding never lands in context twice. Prevents the ~12.5K
  wasted tokens per chatty session called out in the PRD.
- Per-(session, file) edit counter with a one-shot suppression
  notice on the 7th edit, silent after.
- Fail-open contract: every error path returns exit 0 with no
  stdout. Optional NDJSON audit log via IMPECCABLE_HOOK_LOG.

Three kill switches (precedence high to low):
1. IMPECCABLE_HOOK_DISABLED env var (1/true/yes/on, case-insensitive)
2. .impeccable/hook.json `enabled: false`
3. /impeccable hooks off slash command (writes the JSON)

Inline ignores are language-aware. `// impeccable: ignore <rule>` for
JS/TS, `<!-- impeccable: ignore <rule> -->` for HTML/Vue/Svelte/Astro,
`{/* impeccable: ignore <rule> */}` for JSX/TSX, `/* impeccable:
ignore <rule> */` for CSS. `*` matches any rule. Directive applies
to the next non-blank line. Same shape as ESLint, Stylelint, Biome.

Build pipeline
- scripts/lib/transformers/hooks.js: per-provider hooks.json
  builders, plus the slim .codex-plugin/plugin.json manifest.
- providers.js: emitHooks: 'claude' for claude-code, emitHooks:
  'codex' for codex and agents. Codex also emits emitCodexPlugin.
- factory.js: emits hooks/hooks.json next to the skills tree.
- build.js: syncs hooks/ into harness roots and into the slim
  plugin/ subtree; writes .codex-plugin/plugin.json. Build is
  idempotent (verified: 98 staged files unchanged across two runs).

Claude Code wiring uses exec form (command + args) and the
${CLAUDE_PLUGIN_ROOT} placeholder. Matcher: Edit|Write|MultiEdit.
`if:` glob filters to UI extensions before spawning Node. PostToolUse
timeout 5s, SessionStart timeout 3s.

Codex wiring uses ${PLUGIN_ROOT} (Codex's native placeholder),
matcher Edit|Write|apply_patch, no `if:` analog (the script does the
extension filter). macOS and Linux only; hooks are disabled on
Windows in current Codex builds. The trust ceremony and feature flag
are documented in README.md.

Routing
- /impeccable hooks lives outside the 23-command router table on
  purpose: it is plumbing, not a design skill. The hidden
  routing slot is added to SKILL.md alongside pin/unpin so the LLM
  knows to dispatch it. The 23-command count and all stale-count
  validators remain happy.

Tests
- tests/hook.test.mjs: 38 unit tests covering env parsing, config
  load + defaults + malformed, cache round-trip + GC,
  ignoreRules/minSeverity/inline ignores (all four languages),
  globbing with **/*/{a,b}, render template with cap + clamp + 0-line
  prefix drop, audit log NDJSON, payload event-name parameterization,
  re-entrancy, kill switches, sensitive-path + generated-path +
  traversal skips, allowlist filter, config ignoreFiles, edit
  counter cycle including the 7th-edit notice, MultiEdit and
  apply_patch payload shapes, detector throw swallow, malformed
  stdin, missing file race.
- tests/hook-build.test.mjs: 18 integration tests covering hook
  manifest shape (matcher, timeouts, exec form, if: glob, placeholders),
  Codex differences (${PLUGIN_ROOT}, no if:, no SessionStart),
  Codex plugin manifest (no inline hooks field to avoid the
  duplicate-file error), routing across the hooksJsonFor table, and
  presence of all three committed artifacts plus the bundled detector
  the runtime relative-import path depends on.

Full suite: 175 bun tests + 186 node tests, all green.

Docs
- README.md: new "Design hook" section explaining default behavior,
  per-project / global / inline disable paths, the JSON schema knobs,
  the audit log debug flag, and the slop / a11y coverage split.
- HARNESSES.md: flips the `hooks` row for Codex from No -> Yes
  (Claude was already Yes), adds a per-harness hook-surface table
  with the manifest location and matcher each provider uses.

Open questions from the PRD intentionally deferred to v2: Bash-write
blind spot, effort-aware suppression, Stop-hook session summary,
per-rule severity, async hook mode. None block v1.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Fix Codex hook scanning: apply_patch paths and co-located stylesheets

Parse file targets from Codex apply_patch command bodies, co-scan imported
and sibling CSS when UI components are edited, drop the git-sweep PostToolUse
group, and align Codex SessionStart manifest and trust docs with the official
hooks spec.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Gitignore hook session cache and drop local test HTML

Hook dedup/throttle state in .impeccable/hook.cache.json is per-project
runtime data like other .impeccable/ sidecars. Remove an untracked
bad-nested-flexbox scratch page from site/public/.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Fix Claude Code hook: drop Edit-only if filter so Write/MultiEdit fire

Claude's if permission rule binds to one tool name, so Edit(*.{…}) never
spawned the hook on Write or MultiEdit despite the matcher listing them.
Extension filtering now lives in hook-lib on both Claude and Codex.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Surface Cursor design findings via stop-hook followup

Replace dropped postToolUse additional_context with afterFileEdit recording
and a one-shot stop followup_message so anti-pattern nudges reach the agent.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Fix design hook packaging and scans

* Fix Cursor hook pending bucket fallback

* Fix Sass hook scan coverage

* Fix Cursor hook review findings

* Fix session start dead hook normalization

* Fix hook config and relative scan paths

* Remove SessionStart design hook

* Remove redundant afterFileEdit normalization

* Fix Cursor suppression and module style scans

* Fix sensitive path hook filter

* Fix disabled Cursor stop hook emission

* Refresh hook harness artifacts

* Fix Cursor hook manifest install

* Add hook ignore-value support

* Ignore hook runtime files locally

* Fix Codex plugin hook packaging

* fix: address PR review bot findings

Block numeric hook depth counters from re-entering.

Avoid following stylesheet imports from traversal-looking hook targets.

* fix: gate ignore-value suggestions by supported rules

Only render exact ignore-value commands when the same finding can be suppressed by ignoreValues.

* Package Codex plugin as hook-only

* Remove Codex plugin packaging

* Recover hook install probe plumbing

* Remove Codex hook packaging follow-up doc

* Remove extra hook docs and skill wording changes

* Install real design hooks via skills CLI

* Add provider hook smoke runner

* Fix Cursor hook delivery with preToolUse gate

* Simplify Cursor hook install to preToolUse

* Clarify confirmed hook exceptions

* Persist hook ignores in shared config

* Guard font hook exceptions

* Fix hook install after main rebase

* Fix hook scan target handling

* fix: address hook review findings

* Address hook review feedback

* Stabilize DeepSeek insert live fixture

* Fix Cursor hook Python shell write bypass

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-06-13 21:19:19 -07:00
Paul BakausGitHubCursorClaude Fable 5
 		5b5e487a4f Improve live mode configure bar and pick UX (#242) 
* Fix: tear down annotation overlay when Escape exits live pick mode.

The configure prompt auto-focuses and bypasses the global Escape handler, so its local path must hide the annot overlay; togglePick off now does the same as a safety net.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Improve live mode steer pill typing affordance.

Show a visible caret and placeholder when focused, expand on pointerdown, and drop the muddy border so the graphite surface carries the affordance alone.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Improve live mode configure bar layout and pill styling.

Align pills and input on a shared text track, refine muted pill chrome with a quiet action border, and center the row with symmetric inset so spacing reads evenly in the 36px bar.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Add x1 to live mode variant count picker.

The configure bar count pill now cycles 1→2→3→4→1 so users can request a single variant.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Polish live mode configure bar, edit badge, and action picker.

Refine selection pill layout and tooltips, shrink edit copy to an icon aligned with the outline, right-align the action picker, and sync demo styles and regression coverage.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Fix live mode element nav when configure input is focused.

Passthrough empty arrow keys from the configure and steer prompts so handleKeyDown can move between pickable elements without breaking autofocus typing.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Remove accidental live.js inject from Base.astro.

Strip the localhost helper script tag left over from local live mode iteration so the PR ships only intentional UI changes.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Fix review findings: pick-cursor state sync, anchor recovery, e2e selectors.

Code review of this branch surfaced ten confirmed bugs plus three smaller
ones; this commit fixes all of them.

- Route every interaction-state transition through a new setLiveState()
  helper that re-syncs the pick-mode crosshair, fixing four confirmed
  cursor bugs: never appearing on pick toggle (sync ran before the state
  change), sticking through the configure phase, surviving teardown
  page-wide, and the style mounting inside the adapter's shadow root
  where it can't match the host document (now document.head).
- Anchor recovery: a matching id is decisive again (hashed class names
  and component tags broke recovery), empty-text elements can no longer
  match the fuzzy text passes (".includes('')" hole plus shortest-text
  preference), and the dead 2-class-subset fallback is removed.
- Selection pill: drop the hover-only "armed" guard so keyboard
  activation works; the pill arms on focus as well as hover.
- Configure chrome: remove the configure-bar tooltip on teardown, align
  restorePickerBarChrome padding with initBar (5px), share the
  configure-input stylesheet with the insert row, and sync the
  ui-core.mjs surface inventory with live-browser.js.
- Site demos: delete the stale duplicate .live-demo-ctx-selection rule
  that killed the teal pill on dark pages, and keep the configure-phase
  demo bar on the overlay's dark surface in light mode so the near-white
  prompt text stays readable.
- E2E/contract tests: match the icon-only submit button by aria-label
  ("Generate variants") instead of the removed "Go" text, and update
  source-contract pins for setLiveState and buildConfigureSubmitButton.

Verified: bun run test green, live-mode E2E 23/23 across all fixtures.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* Wire insert voice button into syncVoiceUi listening state.

Voice on the insert configure row runs through the same 'configure' mode,
but syncVoiceUi only stamped data-listening/aria state on the replace
row's #impeccable-live-configure-voice, so the insert button never pulsed
while listening. Target whichever of the two row buttons is mounted, the
same either-row pattern syncConfigureInputChrome uses.

Addresses Bugbot review comment on PR #242.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* Reinject from source when the session wrapper lands during anchor recovery.

The anchor-recovery observer stood down as soon as the session's variant
wrapper appeared in the DOM, without running injectVariantsFromSource.
A wrapper can land incomplete (wrap HMR landed, variant insert did not),
which is exactly the case injectVariantsFromSource's existing-wrapper
replace path handles - so recovery ended with the bar stuck and no
variants. Route both the anchor-found and wrapper-landed cases through
injectVariantsFromSource, which owns wrapper replacement, recovery-flag
clearing, and variant display.

Addresses Bugbot review comment on PR #242.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* Restore inline edit drafts before configure chrome teardown disables editing.

teardownConfigureChrome called disableInlineEdit() ahead of hideBar(),
wiping inlineEditRows and the impeccableOriginalText metadata that
hideBar()'s EDITING-state restoreInlineEditDrafts() needs - so turning
Pick off mid "Edit copy" left edited DOM text in place, neither saved
nor canceled. Let hideBar() own the sequence: it restores drafts first,
then disables inline edit.

Addresses Bugbot review comment on PR #242.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-06-10 22:18:45 -07:00
Paul Bakaus 325aeaf239 Organize skill script support modules 2026-06-08 16:58:55 -07:00
Paul BakausandGitHub 82801a4894 [codex] Improve CI test coverage (#212) 
* Improve CI test coverage

* Stabilize live E2E harness

* Shard live E2E CI

* Cache live E2E CI dependencies

* Stabilize live E2E smoke CI

* Update generated live browser bundles

* Tighten live E2E smoke runtime

* Prevent live E2E smoke hangs

* Stabilize live E2E CI coverage

* Fix stale accept DOM cleanup

* Regenerate live browser outputs
 2026-06-08 10:39:12 -07:00
Abdul WahabandGitHub 6163ca0529 Add Svelte-native live mode adapter (#179) 
* Fix live preview state for framework components

* Complete stateful live preview coverage

* Record Svelte manual validation

* Fix Svelte live mode adapter

* Fix live Steer apply flow

* Fix Svelte live variant refresh recovery

* Fix live exit bar teardown

* Consolidate Svelte live DeepSeek sweep

* Reconcile Svelte live browser after main rebase

* Fix live accept review regressions

* Fix carbonize column-zero indentation

* Fix live poll lease expiry flake

* Fix Svelte shader preview capture
 2026-06-02 00:08:57 -07:00
Abdul WahabGitHubClaude Opus 4.7
 		e8e3665142 Live mode: staged AI copy edits (#158) 
* feat(live): manual text-edit panel + Astro inject + stale-lockfile reap

Adds a manual text-edit popover under the live-mode bar so users can
retype copy directly without going through generate. The footer's
"Apply edits" button fires a manual_edits event; the server writes
the changes back to source via the new live-edit.mjs deterministic
file mutator. Mirrors the wrap+accept flow but skips variant generation.

New scripts:
- skill/scripts/live-edit.mjs: writes manual_edits back to source
- skill/scripts/live-text-rows.js: browser walker that surfaces every
  pure-text descendant of the picked element as an editable row

Touched scripts:
- skill/scripts/live-browser.js: text panel UI, CONFIGURING state hook
- skill/scripts/live-poll.mjs: manual_edits routing
- skill/scripts/live-server.mjs: manual_edits endpoint + handler
- skill/scripts/live-wrap.mjs: small adjustments to support the flow

Docs + tests:
- skill/reference/live.md: manual-edit section
- tests/live-edit.test.mjs, tests/live-text-rows.test.mjs

Also bundles two live-mode reliability fixes that surfaced during
manual testing of the feature:

1. live-inject now emits is:inline when the inject target is a .astro
   file. Astro otherwise processes the <script> tag and rewrites src
   to its own bundled URL, so the literal live.js never loads.

2. readLiveServerInfo now probes the lockfile PID with kill(pid, 0)
   and unlinks the stale lock if dead. Previously a crashed helper
   left server.json with a dead PID and live-poll reported "Live
   server not running" forever.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* feat(live): inline contenteditable text editing

Replace the text-edit popover panel with inline contenteditable activation.
When an element is picked in CONFIGURING, every pure-text descendant becomes
contenteditable="true" directly on the page. Each blur-event fires a single-op
manual_edits save to source. Esc restores original text and stays in CONFIGURING;
successful save exits to PICKING. If Go is clicked while a save is in-flight,
the save completes before generate fires.

Deleted ~340 lines of panel UI (initTextPanel, openTextPanel, closeTextPanel,
renderTextRow, buildTextFooter, etc.). Added enableInlineEdit, disableInlineEdit,
onInlineBlur. Server contract unchanged; live-edit.mjs handles per-op saves as
before. Tests: 186 pass.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix(live): hide annotation overlay during inline edit

Annotation overlay's click handler was intercepting clicks on contenteditable
text elements. Hide the overlay when inline-edit is enabled to allow text
selection and editing. Restore it when exiting inline-edit (if still in
CONFIGURING).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(live): edit content badge mode with batched saves

Replace automatic inline contenteditable on element pick with an explicit "Edit content" badge. The badge appears at the element's top-right corner when an element is picked. Clicking the badge enters a new EDITING state where:

- The contextual bar hides
- The annotation overlay hides
- The badge morphs to show Cancel + Apply buttons
- Text descendants become contenteditable inline

Edits are held in memory (input event tracking) until Apply is clicked, which fires a single batched manual_edits event with all ops. Cancel discards drafts without saving. This eliminates the annotation overlay interference that prevented clicking on text elements.

The EDITING state integrates with the main state machine and handles all exits (Esc, click-outside, teardown) cleanly.

All 186 tests pass.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix(live): use row.el.tagName for tag in applyEditing op

The applyEditing function was trying to use row.tag which doesn't exist on the row object. The tag should be the tagName of the text element itself (row.el.tagName.toLowerCase()).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* feat(live): Edit content badge styling + auto-focus + separate buttons

- Edit content button now matches Go button styling (BP.accent background, BP.mark text, FONT, transitions, hover effects)
- Auto-focus first editable element when entering editing mode (50ms timeout)
- Separate Cancel and Apply buttons with 8px gap (no divider)
- Cancel uses muted styling (BP.hairline background, BP.textDim text)
- Apply keeps brand accent styling
- Remove all focus rings and outlines on edit badge buttons (no blue ring/outline in EDITING mode)

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>

* feat(live): Subtle button UI + cursor positioning + better copy

- Change badge buttons to use impeccable-button aesthetic (ink background, surface text, hover to accent)
  - Removes aggressive styling conflict with Go button
  - No animations; simple 150ms background transition
  - Matches site design language (padding 0.625rem 1.5rem, 0.8125rem font, letter-spacing 0.03em)
- Shorter, clearer button copy: "Edit" instead of "Edit content", "Save" instead of "Apply"
- Fix cursor positioning: cursor now appears at END of text, not beginning
  - Use Selection API to collapse cursor to end of contenteditable element
  - Improves UX for immediate continuation of text
- Update live.md documentation to reflect new button labels

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>

* fix(live): Use site design system colors for edit badge buttons

- Edit/Save buttons: oklch(10% 0 0) background → oklch(60% 0.25 350) on hover
- Cancel button: oklch(55% 0 0) background → oklch(65% 0 0) on hover
- All buttons: 6px border-radius (matches Go button), oklch(98% 0 0) text
- Smooth transition: 0.3s cubic-bezier(0.16, 1, 0.3, 1) (--ease-out)
- Uses site color palette instead of live-overlay constants

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>

* fix(live): Match slop-callout style for edit badge buttons

- Use exact .slop-callout aesthetic: paper background, accent border + text, uppercase 10px (0.625rem)
- 600 weight, 0.06em letter-spacing, 4px 8px padding, 6px border-radius
- Box-shadow: 0 2px 8px rgba(0,0,0,0.1) matches site callouts
- Hover: inverts to filled background (accent fill, paper text)
- Cancel uses ash color variant for muted state, Save uses accent
- Smooth 0.3s cubic-bezier(0.16, 1, 0.3, 1) transition on background and color

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* fix(live): Pill-shaped edit badge buttons, 2px padding, no uppercase

- Border-radius: 999px (pill shape)
- Padding: 2px 8px (more compact)
- Removed text-transform: uppercase

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* fix(live): Cancel button uses mist border + ash text

- Border: 1px solid oklch(92% 0 0) (--color-mist)
- Color: oklch(55% 0 0) (--color-ash)
- Hover: inverts to ash background with paper text

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* fix(live): Remove blue focus outline from contenteditable elements in EDITING mode

- Add inline outline: none on each row's element when contenteditable activates
- Inject [data-impeccable-editable] CSS rule to override browser default focus ring
- Use !important to win against site styles that re-apply focus outlines
- Cleanup restores outline/data-attribute on disable

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* feat(live): Decouple manual edits from agent/poll pipeline

Manual text edits now POST directly to a new /manual-edit endpoint
that runs live-edit.mjs synchronously and returns the result. The
event is never enqueued, never reaches the poll loop, never reaches
the agent.

Why: every Save was costing an LLM turn. The poll script would
dequeue the manual_edits event, run live-edit.mjs deterministically,
post a completion ack, then print the event JSON to stdout. The
Claude agent would read that output and decide "loop and re-poll".
Zero real work for the agent but every Save burned context.

Changes:
- live-server.mjs: new POST /manual-edit handler that runs live-edit.mjs
  synchronously and returns the result. Does not enqueue, does not log
  to session store. Defense-in-depth: /events rejects manual_edits.
- live-browser.js: applyEditing() POSTs to /manual-edit instead of
  sendEvent({type: 'manual_edits'}).
- live-poll.mjs: removed manual_edits handler branch (dead code now).
- reference/live.md: removed "Handle manual_edits" section; replaced
  with a one-line note that manual edits are server-direct.

The HMR-triggered page reload remains (dev server detects source file
change) but that is a separate dev-server behavior, not our pipeline.
resumeSession() already restores variants and selection after reload.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* feat(live): Stash manual edits server-side; commit via AI on request

Decouples manual-edit Save from source file writes. Save now stashes
to .impeccable/live/pending-manual-edits.json with no HMR refresh.
The user explicitly asks the AI to commit when ready.

Why: even with the prior /manual-edit fix, every Save still wrote to
source and triggered the dev server's HMR/full reload. The page flash
was the actual user pain. Now there's zero source touch on Save, and
the user controls when the dev server reloads.

Server (live-server.mjs):
- /manual-edit-stash POST: append to buffer file. Returns {ok, pendingCount, totalCount, perPage}.
- /manual-edit-stash GET: query counts by page for counter UI.
- /manual-edit-discard POST: drop entries (all if no pageUrl).
- Old /manual-edit returns 410 Gone (defense in depth).
- Buffer ops merge by (pageUrl, ref): keep first originalText, update newText.

CLIs:
- live-commit-manual-edits.mjs: read buffer, shell out to live-edit.mjs
  per entry, truncate succeeded entries, surface failures.
- live-discard-manual-edits.mjs: truncate buffer (optionally scoped by page).
- Both take optional --page-url=<url>.

Browser (live-browser.js):
- applyEditing() POSTs to /manual-edit-stash, no source write.
- Pending pill (• N staged) + trash icon next to Exit in global bar.
- One-time onboarding toast on first Save: "Saved. Tell the AI to commit when ready."
- Counter persists across reloads via GET /manual-edit-stash on init.
- Trash icon: confirm dialog scoped to current page, then POST /manual-edit-discard.

Variant pipeline interaction:
- live-wrap.mjs: when wrapping an element, apply pending manual edits to
  the source range so the wrap block's "original" variant reflects the
  user's edited DOM (their pre-Go view), not the raw source.
- live-accept.mjs: after accept writes the variant to source, scrub
  buffer ops whose originalText no longer appears in that file. The
  accept embodies the manual edit; the pending op is consumed.
- Variant discard does NOT touch the buffer.

Reference docs:
- reference/live.md: full commit/discard contract, trigger guidance
  (narrow action-verb intent), do-not-auto-commit rule.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* feat(live): Staged-edits pill becomes an "Apply" button

Click the "• N staged" pill → confirm dialog "Apply N staged edits
to source? The page will reload." → POST /manual-edit-commit on the
server, which shells out to live-commit-manual-edits.mjs. Same path
the AI uses, just triggered from the overlay.

Trash icon stays for discard. The AI-driven commit path also stays
(useful for inspecting failures or scripting). The pill is now the
primary apply affordance because it removes the chat-context-switch
for the common case.

Pill styling: pointer cursor, accent border + text at rest, fills
on hover (accent bg, paper text). Tooltip: "Click to apply staged
edits to source".

First-save toast updated: "Saved. Click the 'staged' badge to apply,
or ask the AI."

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* chore(live): gitignore pending-manual-edits.json runtime buffer

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore: drop stray site/ test edits from PR

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(live): Pill label reads "Apply N staged"

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(live): Manual edit ops use the leaf element's locator, not parent's

Multi-row inline editing captures each contenteditable leaf (row.el) but
the op was being built with selectedElement.id / classList — i.e. the
parent card, not the editable text node. live-edit.mjs then searched
source for the parent's class on the leaf's tag (e.g. <span class=
"foundation-card">), found nothing, and silently failed.

Use row.el's own id / classList instead.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(live): Climb to nearest classed ancestor when leaf has no locator

A bare <em>/<strong>/etc. with no id or class produced ops the CLI
rejected with insufficient_locator. Prefer the leaf's own id/class; if
neither exists, walk up to the nearest ancestor with one and adopt its
tag + locator. Text-replace still works because the CLI narrows by
originalText inside the matched element's source range.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(live): Make mixed-content paragraphs editable

The text-rows walker skips elements with mixed children (text + element +
text), so paragraphs like "Some text <code>x</code> more text" or "Body
text · <a>link</a>" exposed zero rows for the surrounding copy. At edit
time, wrap each non-whitespace direct text-node child in a marker span so
the walker emits a row for it. Unwrap on save/cancel. The locator climbs
to the parent's class as before, and live-edit narrows by originalText
inside that parent's source range.

hasTextRows now uses a lightweight subtree check that matches the new
wrap+walk path so the edit affordance shows up on mixed-content elements.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(live): Address Cursor Bugbot findings (CB-2 through CB-6)

CB-2 - Escape reverted DOM text but inlineEditDrafts retained the
pre-revert value; clicking Apply afterwards committed the undone edit.
Clear the draft entry when restoring innerText.

CB-3 - The scrub gate !result.handled || result.handled !== false was
a tautology that ran the scrub regardless of accept outcome. Use the
intended result.handled !== false.

CB-4 - The buffer-aware "original" content step in live-wrap iterated
every entry in the buffer with no pageUrl filter, so an edit on /a
could leak into a wrap call on /b. Add --page-url to the CLI; filter by
it; skip the buffer-aware step entirely when omitted. live.md updated.

CB-5 - removeEntries returned entry count while truncateBuffer returned
op count, causing the discard CLI and HTTP endpoint to report mixed
units. Make removeEntries return ops removed.

CB-6 - applyTextReplace used string truthiness to gate prepending
content above the edit, which silently dropped a leading empty line
when the file started with '\n'. Gate on the line index instead, and
mirror the fix on the trailing-empty-line side.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(live): A3+A4 data-integrity guards, A6 test coverage

A3 — applyTextReplace refuses with text_ambiguous_in_block when
originalText appears more than once in the matched element block.
Refusing is safer than picking the first indexOf hit when we can't
tell which leaf the user edited; user can rephrase one occurrence.

A4 — newText is rejected if it contains <, >, {, }, or a backtick.
Two layers: server-side validator in /manual-edit-stash returns 400,
CLI-side guard in applyTextReplace returns invalid_chars_in_newText.
Browser surfaces the specific reason via toast. The shared char list
lives in live-edit.mjs (validateNewTextChars). reference/live.md
documents the rule.

A6 — New test files cover the orchestration gap:
 - live-manual-edits-buffer.test.mjs (17 tests across read/stage/
   remove/find/count/truncate; pins removeEntries returns OPS count)
 - live-wrap-buffer-aware.test.mjs (3 tests; CB-4 regression test)
 - live-commit-manual-edits.test.mjs (4 tests; partial-failure,
   --page-url scope, no_pending_edits)
 - live-discard-manual-edits.test.mjs (3 tests; CB-5 unit consistency)
 - live-accept-scrub.test.mjs (4 tests; keep/drop/prune)
Plus 2 new cases in live-edit.test.mjs for A3 and A4.

Side-effect refactors:
 - scrubManualEditsAgainstFile accepts cwd for unit-testing and is
   exported.
 - Failed-op entries in live-edit.mjs now propagate forbidden and
   occurrences fields so callers can surface specifics.

41 tests across the 6 affected files pass; full suite green at 186/186.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore: drop .claude/pr-review.md from PR

Local review notes belong in the working tree, not the PR diff. Kept
in the file system; just untracked.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore: drop stray site/ test edits from PR (round 2)

Live-inject script tag and the "Impeccable Works!" / "WHAT'S INCLUDED
IN THE BOX" / "Wow Impeccable. ---- " strings were test edits that
slipped back into the branch. Restore both files to match main.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* feat(live): Disable Edit badge while variants are generating

Clicking Edit during GENERATING would open inline text editing on the
same DOM region the variant wrapper is about to land in, racing the
HMR and the mutation observer. The badge now switches to an
'idle-disabled' rendering (ash + mist, not-allowed cursor, disabled
attribute, tooltip) the moment state transitions into GENERATING.
Returns to 'idle' on the normal CONFIGURING re-entry paths.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(live): live-wrap refuses without --page-url when buffer has pending edits

When a manual edit is staged ("Impeccable Works!") but not yet committed,
the buffer holds the user's edited DOM while source still has the un-
edited text ("Impeccable"). live-wrap's buffer-aware step exists to
rewrite the wrap block's <div data-impeccable-variant="original"> to
match the staged DOM, but per CB-4 it is gated by --page-url. When the
agent invoking live-wrap omits --page-url, the buffer-aware step
silently no-op'd and the variant authoring saw stale source — the
user's manual edit appeared lost.

Make the silent no-op a loud error: when buffer.entries.length > 0
and --page-url is missing, exit 1 with
{ error: 'missing_page_url_with_pending_edits', pendingEntries, hint }.
Empty buffer = no risk = no requirement, so existing flows without
pending edits keep working.

Updated reference/live.md to flag --page-url as required when the
buffer has entries. Added regression test in
live-wrap-buffer-aware.test.mjs. live-wrap.test.mjs gained a buffer-
clear hook so any leftover .impeccable/live/pending-manual-edits.json
from local dev doesn't trip the new check.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* change back

* chore: drop stray site/ test edits from PR (round 3)

Live-inject script tag in Base.astro slipped back in via git add -A
while a local live server was running. Restore both site/ files to
main.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* Fix live manual edit staging

* Rename live edit copy badge

* Use sentence case for live edit copy badge

* Move copy edit apply control outside live bar

* Improve live copy edit apply flow

* Clean up live copy edit AI apply flow

* Polish live copy edit docs and toast

* Fix staged copy edit review issues

* Fix CI jsdom dependency

* Fix Cursor Bot live edit findings

* Fix remaining live edit review issues

* Fix Bugbot staged edit edge cases

* Fix latest Bugbot live edit edges

* Fix remaining Bugbot wrap and discard issues

* Fix live copy edit safety contracts

* Fix copy edit rollback coverage

* Fix live manual copy edit apply flow

* Adjust live pending dock offset

* feat(live): route manual-edit Apply through the chat agent

Make the staged copy-edit Apply work when no CLI AI runner is
authenticated by routing the batch through the active chat session,
and surface runner failures clearly instead of opaque exit codes.

- live-poll: add --reply --data '<json>' so the chat agent can return
  a structured manual_edit_apply result (the documented flag was
  missing, so the server resolved with an empty object)
- live-server: manual_edit_apply event + deferred map, chat-vs-subprocess
  dispatch in /manual-edit-commit, resolve the deferred from the ack
- live-copy-edit-agent: chat provider, extractRunnerErrorMessage and
  commandAuthed pre-flight, diagnostic describeNoProviderError; drop the
  stale CLAUDE_CODE_SIMPLE and --no-session-persistence flags so headless
  CLAUDE_CODE_OAUTH_TOKEN auth works
- live-browser: clear pendingApplyInFlight on commit_done and add a
  watchdog so a missed signal can no longer freeze element picking
- reference/live.md: tight Handle manual_edit_apply handler plus a
  separate diagnostics reference section; advertise the event in the
  opening contract and dispatch table

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* Add live manual edit apply coverage

* Fix manual edit apply review issues

* Fix manual edit review follow-ups

* Fix manual apply poll acknowledgements

* Fix manual apply failed-entry rollback

* Clarify manual apply LLM prompt

* Fix stale manual apply discard events

* Fix manual apply dynamic source edits

* Fix large manual apply chunks

* Clarify manual edit apply is first-class work

* Clarify manual apply resume flow

* Compact live manual apply evidence

* Reject malformed manual apply replies

* Recover legacy manual apply summaries

* Fix Astro live script injection

* Add live manual edit apply coverage

* Slim live manual apply flow

* Slim manual edit test dependencies

* Stabilize real browser LLM smoke

* Generalize manual edit LLM prompt examples

* Remove retired live edit wrapper

* Inline live text row walker

* Slim manual edit prompts

* Drop AGENTS doc churn

* Stabilize live manual apply prompts

* Stabilize manual apply visible Haiku flow

* Add hard framework manual edit coverage

* Stabilize manual edit LLM retries

* Fix manual apply transaction rollback

* Fix live shader text capture

* Clean up manual apply runtime artifacts

* Fix live manual edit apply reliability

* Clean up manual apply coverage

* Slim manual apply test cleanup

* Fix manual edit prompt contract test

* Align manual edit cancel hover

* Fix live loading shader capture

* Fix manual apply review findings

* Restore live e2e tests for CI

* Fix live loading shader halftone

* Tune live loading shader dots

* Restore main live shader behavior

* Fix manual apply review findings

* Fix manual apply bot follow-ups

* Clarify manual apply rollback changes

* Fix manual apply state naming

* Address PR review cleanup

* Fix manual apply review follow-ups

* Fix multiline manual apply verification

* Restore inline drafts when hiding live bar

---------

Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
 2026-05-28 19:02:12 -07:00
Paul BakausGitHubClaude Opus 4.7Cursor
 		9ffd3211d5 Neo Kinpaku design system + Live Mode v3 (#169) 
* Add neo kinpaku design system page

* skill: rip out baked-in category recipes and saturated-default motion tropes

Programmatic bias mining (impeccable-evals) traced four major defects
back to specific lines in this skill that contradicted SKILL.md's own
first-order-reflex warning:

- brand.md "Pairing and voice" prescribed four category→aesthetic
  recipes (editorial → serif+sans, tech/dev/fintech → tight tracking,
  consumer/food/travel → script/display serif, creative → rule-break).
  These directly drove OpenAI's 76% extreme-negative letter-spacing
  on tech briefs and Anthropic/Google's 28-34% italic-serif-display
  slop on editorial/food briefs. Replaced with one sentence: the
  shape depends on the brand, not on the brand's category.
- brand.md "Brand permissions" had "Typographic risk. Enormous
  display type, unexpected italic cuts, mixed cases, hand-drawn
  headlines, a single oversize word as a hero." — a four-for-one
  slop driver behind 97% OpenAI comically-large H1, 42% bad-SVG
  illustration, and the editorial-italic slop. Deleted outright.
- typeset.md and teach.md repeated the same category recipes;
  trimmed to the principle without the recipe.
- SKILL.md Typography: added a hard hero-H1 ceiling (clamp() max
  ≤ 6rem ≈ 96px), with a <codex> block to make it explicit since
  OpenAI over-indexes here (97% ≥128px vs 24% for Anthropic).
- animate.md, bolder.md, brand.md: removed "staggered reveals" and
  "scroll-triggered transitions" as the prescribed default ambitious
  motion. By 2026 that's the saturated AI tell, not a choreography.
  Reserved stagger for legitimate list-sibling rhythm.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* skill: anti-cream + codex-specific defect bans + universal slop bans

Second pass after measuring more biases against the eval corpus.

- SKILL.md Color: explicit "cream/sand/beige body bg is the saturated
  AI default of 2026" rule. Tone down the "tint every neutral" line so
  it doesn't read as "default to warm-tinted near-white" (which OpenAI
  hits at 74% and Anthropic at 31%-47%).
- SKILL.md Absolute bans: add universal bans for two slop patterns
  detected at 55-95% across providers — tiny uppercase tracked eyebrow
  above every section (the 2023-era kicker that's now AI grammar) and
  numbered section markers (01/02/03). Also explicit "text that
  overflows its container is the universal defect on tablet/mobile."
- SKILL.md Absolute bans → <codex> block: ban the GPT-specific defects
  Paul annotated repeatedly — `border:1px solid` + soft-wide-shadow
  (≥16px blur) "ghost cards", `border-radius:32px+` over-rounding,
  hand-drawn/sketchy SVG illustrations (loose-sketch / *-sketch classes,
  feTurbulence paper-grain filters), repeating-linear-gradient stripes,
  "X theater" AI-slop copy phrases.
- SKILL.md Motion → <gemini> block: the image :hover transform tell
  (38% Google skill-on rate). Hover effects on images add no info; the
  image isn't an action target. Animate card chrome, not the image.
- SKILL.md Typography: hard display letter-spacing floor ≥-0.04em
  (OpenAI defaults to -0.075em → cramped). Existing hero ceiling
  <codex> block extended with the letter-spacing rule.
- codex.md Step A example: stop seeding "warm-grounded (deep oxblood +
  cream)" as the warm-palette template, which primes the cream default.
- colorize.md Tinted backgrounds: stop printing the literal cream
  recipe `oklch(97% 0.01 60)`; replace with brand-anchored guidance.
- document.md examples: warm-ash-cream → cool-paper so the example
  doesn't seed cream as the canonical neutral example.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* skill: universal anti-slop bans + contrast/font-count/all-caps-body rules

Third pass after measuring the rest of the cross-provider matrix:

- Color: explicit "Verify contrast" rule. Low-contrast text fires at
  68% across all providers skill-on (90+% off). The most common
  failure is muted gray body on a tinted near-white; light-gray-for-
  elegance is named as the single biggest cause of unreadable AI
  pages.
- Typography: max-3-font-families rule. Overused-fonts (>4 families)
  fires at 28% Anthropic / 36% Google / 0% OpenAI skill-on; >50% off.
  Also: universal "no all-caps body copy" (moved from brand-only ban
  to Shared design laws since product-register also overuses caps).
- Copy: anti-aphoristic-cadence ban targets Anthropic's signature
  "X. No Y." / "X. Just Y." voice (63% skill-on copy-slop rate, 77%
  off — the worst rate in the matrix). Once-is-voice / three-or-more-
  is-tell framing per the runner's copy-slop detector.
- Copy: anti-SaaS-buzzword-string ban with the literal phrase list
  the detector watches for (streamline/empower/supercharge, trusted-
  by-leading, best-in-class/enterprise-grade/cutting-edge, etc).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* skill: strengthen anti-cream rule across full warm-neutral band

Smoke validation showed the cream fix worked for Google + OpenAI but
Anthropic Sonnet italian-restaurant still shipped `--paper: oklch(90%
.018 88)` — cream just outside the L≥95% band the rule cited.

Broaden the rule:
- Band: OKLCH L 0.84-0.97, C < 0.06, hue 40-100 (was 95-97% / 60-95).
- Name the token-name tells explicitly (paper / cream / sand / bone /
  flour / linen / parchment / wheat / biscuit / ivory) — the model
  defaults to one of these regardless of what hex it lands on.
- Call out the specific brief patterns ("warm, traditional, family-
  coastal-Italian" / "editorial-restraint") that the model translates
  into cream by reflex. Then provide three explicit non-cream options:
  saturated brand color, true off-white at C=0, or darker mid-tone.

Warmth in the brand is carried by accent + typography + imagery, not
by body bg.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* v3.2.0: skill bias-fix release

Bumps version from 3.1.1 to mark the four-commit skill cleanup that
rips out baked-in category recipes (brand.md), saturated-default motion
tropes (staggered reveals everywhere), the cream/sand body-bg AI tell,
codex-specific defects (1px+wide-shadow, over-rounding, hand-drawn SVGs,
stripes, X-theater copy), the extreme-letter-spacing default, and
universal slop bans (all-caps eyebrow on every section, numbered-section
markers, all-caps body, font-family-count > 3, aphoristic copy cadence,
SaaS buzzword strings). Plus a hard hero-H1 ceiling (clamp() ≤6rem) and
a Gemini-specific image:hover transform block.

Validated against ~190 post-fix samples — see impeccable-evals
biases tab for per-provider deltas.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* drop "no pure black/white" rule entirely

The rule was contested in the design world and causing more damage than
good — pushing every page into the tinted-near-white default which is
the cream/sand AI tell we already explicitly ban elsewhere. Vercel,
SVKMS, Brutalist sites, et al. use pure black/white successfully; the
skill shouldn't second-guess that.

Skill markdown deletions:
- SKILL.md Color: drop the "Never use #000 or #fff" bullet.
- color-and-contrast.md: drop the "Never Use Pure Gray or Pure Black"
  subsection, the "Never pure black" table-row prescription, and the
  "Avoid: Using pure black for large areas" bullet.
- colorize.md: drop the "NEVER use pure black or pure white for large
  areas" bullet.
- polish.md: drop the "Tinted neutrals: No pure gray or pure black"
  half of the bullet (the gray-on-color bullet survives).

Detector code (cli/engine):
- registry/antipatterns.mjs: remove the `pure-black-white` entry.
- rules/checks.mjs: remove the three `findings.push({ id:
  'pure-black-white', ... })` emit points (inline #000 bg, Tailwind
  bg-black class, plain-HTML scan path).
- engines/regex/detect-text.mjs: remove the two pure-black-white regex
  rules (CSS `background: #000…` + Tailwind `bg-black`).
- detect-antipatterns-browser.js: regenerated via
  scripts/build-browser-detector.js.

Tests:
- detect-antipatterns-fixtures.test.mjs: invert the assertion that
  pure-black-white fires; expect it to NOT fire post-v3.2. Drop the
  Tailwind bg-black-opacity edge-case test (no longer relevant).
- detect-antipatterns.test.js: drop the standalone "detects pure-
  black-white in styled-components" test and remove pure-black-white
  from the multi-detector assertions in PricingCard, globals.css, and
  GlobalStyle.tsx tests.

166 bun tests pass; 24 node fixture tests pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* skill: strip example patterns from copy rules, strengthen gemini block

v3.2 rerun validation surfaced two issues:

1. Copy-slop detector fires more on Gemini under v3.2 (48% → 84%) than
   under no-skill baseline. Root cause: the anti-aphoristic-cadence rule
   printed the literal "X. No Y." / "X. Just Y." patterns as examples,
   and Gemini imitated them as the recommended voice. Same recipe-becomes-
   bias trap we hit with brand.md:116's "Enormous display type, unexpected
   italic cuts, mixed cases, hand-drawn headlines" enumeration. Fix:
   describe the cadence as a rhythm ("serious statement, then punchy
   short negation") without printing literal patterns. Buzzword list
   trimmed to a single inline phrase family rather than quoted strings.

2. Gemini image:hover transform Gemini-tell hadn't dropped (31% off →
   32% v3.2). Strengthen the <gemini> block: explicit "Never animate
   <img> elements on hover", call out the Tailwind group-hover:scale /
   group-hover:rotate / group-hover:translate parent-hover patterns by
   name (Gemini was reaching for these via Tailwind even though the
   prior text talked about :hover on the image directly).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* skill: simplify context loading and inline register directive

Replaces load-context.mjs's JSON output with a tight markdown block from
the renamed context.mjs. The script now extracts PRODUCT.md's `## Register`
field and appends a `NEXT STEP:` directive naming the matching reference
(brand.md / product.md), which moved Gemini from skipping the register
load entirely to honoring it. Drops the `.impeccable.md` auto-migration;
makes IMPECCABLE_CONTEXT_DIR a lazy escape hatch consulted only when the
default paths come up empty.

Setup is now four bullets in one list. The DESIGN.md nudge is gone; in
its place, a "familiarize with the existing design system" step that
calls out CSS / tokens / running app as authoritative sources alongside
DESIGN.md. The standalone `### Register` H3 stays for the cascade rules
(task cue → surface → register field).

New LLM-backed test suite at tests/skill-behavior/ runs five scenarios
against claude-haiku-4-5, gpt-5.4-mini, and gemini-3.1-flash-lite via
Vercel AI SDK. Captures real tool traces, asserts on context.mjs calls,
brand.md loads, and teach.md fallback. Skips cleanly when API keys are
unset. 13-14/15 pass; only stable failure is the v3.2.0-era gpt-mini S4
"don't re-run" regression. Adds @ai-sdk/google as devDep and the
test:skill-behavior npm script.

Touches em-dashes in skill/SKILL.md and four reference files so
`bun run build:skills` passes its skill-prose validator. teach.md and
document.md drop their "re-run the loader to refresh session cache"
steps since the agent's own write is now the freshest source.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* skill: merge orphan reference files into command sub-skills + inline S-tier invariants

Two related restructurings:

1. SKILL.md now carries the cross-domain invariants that catch defects in any
   project (contrast/placeholder/gray-on-color, similar-font pairing, text-wrap,
   tabular-nums, centered-stack default, Flex/Grid choice, auto-fit grids,
   semantic z-index, reduced motion, stagger vs section-fade, premium motion
   materials, focus-visible, placeholders-aren't-labels, dropdown overflow trap,
   button/link copy). Greenfield-only rules (theme picking, color strategy,
   tinted neutrals) live under "New projects only".

2. Reference files merged into their command counterparts:
   - spatial-design.md  -> layout.md
   - motion-design.md   -> animate.md
   - color-and-contrast.md -> colorize.md
   - responsive-design.md  -> adapt.md
   - ux-writing.md         -> clarify.md
   - typography.md         -> typeset.md (bolder.md redirected)
   - cognitive-load.md + heuristics-scoring.md + personas.md -> critique.md

   craft.md and shape.md "load references" lists updated to new file homes.
   interaction-design.md stays standalone (no 1:1 command verb).

Net: 36 -> 27 reference files. Same content, fewer files, no orphaned
reference loaded only from craft.md.

Also extends the routing rules: if the user's first word doesn't match a
command but the intent clearly maps to one, load that command's reference
and proceed as if invoked.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* skill: add sub-command + existing-project scenarios; move sub-command load to step 2

Adds three new LLM-backed scenarios to tests/skill-behavior:
- S6: `/impeccable polish` → loads polish.md
- S7: `/impeccable audit` → loads audit.md
- S8: existing SvelteKit project (PRODUCT.md + DESIGN.md + src/app.css +
  src/lib/components/*.svelte + src/routes/+page.svelte) → agent reads
  at least one project code file to understand the existing design system

S6/S7 surface a real model-floor: gpt-5.4-mini reads brand.md, reads the
target index.html, and just does the polish/audit without ever loading
the sub-command reference. Stronger SKILL.md wording didn't move it.
Captured in the README baseline as a known weakness. Claude and Gemini
honor the load reliably.

To fix Gemini on S6/S7, sub-command reference loading is now Setup step 2
(right after context.mjs), not step 4 — placing it before the model gets
focused on "doing the work". Step 3 (design-system familiarization) is
tightened to require at least one project code read even when a
sub-command reference loads in step 2, so Claude doesn't laser-focus on
the sub-command flow and skip the broader exploration.

Two new fixtures: MINIMAL_LANDING_HTML (a tiny static landing page for
S6/S7) and SVELTE_PROJECT_FILES (a minimal SvelteKit scaffold with
tokens, components, and a routes/+page.svelte for S8). Both designed to
look real enough that agents treat them as production code.

Suite is now 24 tests across three providers; baseline is 21-22/24, with
the stable failures being gpt-5.4-mini scenarios 6 and 7.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* skill: add reveal-animation safety rule (must enhance, not gate visibility)

Class-triggered visibility transitions pause on hidden tabs and headless
renderers. The italian-restaurant smoke produced a build where 2 sections
shipped opacity:0 because the CSS transition never advanced past
currentTime=0 (timeline paused). Added one-liner under Motion to prevent
the antipattern: reveals must enhance an already-visible default, never
gate content visibility on a class-triggered transition.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* skill: restore prescriptive cream/sand/beige paragraph

Bisection across 5 historical skill commits on Gemini 3.5 flash fast
lane n=3 found that 0cf2debd was the peak quality state. The regression
between 0cf2debd and HEAD came from simplifying the long anti-cream
paragraph into a one-liner.

Restoring the paragraph (with em-dashes replaced by parens to satisfy
prose lint) recovers ~0.22pt average on Gemini vs HEAD, with the
largest gains on:
- 09-luxury-hotel: +0.50 (restores editorial drama in photo-led briefs)
- 10-food-magazine: +0.67
- 03-italian-restaurant: +0.51

The paragraph's load-bearing parts are the (a)(b)(c) alternatives that
give the model actionable replacements for cream-tinted body bg
("saturated brand color as body", "true off-white at chroma 0",
"darker mid-tone tinted neutral"). Without them, the one-line warning
left the model with no concrete alternative.

Cross-provider validation showed the pattern matches historical
behavior: Gemini benefits from prescriptive scaffold (+0.12 over off),
Sonnet is roughly neutral (+0.01), GPT-5.5 slightly regresses (-0.11
matching the v3.1.0 pattern of -0.11). The skill has never been
uniformly better than skill-off across providers; this is the closest
achievable state without provider-specific rework.

The structural improvements from the prior restructure stay (file
merges, S-tier inlines, routing rule extension, reveal-animation
safety rule).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* docs: teach CLAUDE.md / AGENTS.md / DEVELOP.md about the skill-behavior tests

Adds the `bun run test:skill-behavior` script to the test commands lists
in all three docs. CLAUDE.md gets a full `### Skill-behavior tests`
subsection paralleling the existing Live-mode E2E one: how the suite
works (inlines source SKILL.md, scoped tools, asserts on the trace),
which providers it always runs (claude-haiku-4-5, gpt-5.4-mini,
gemini-3.1-flash-lite — all three every run), the eight scenarios, the
baseline (21-22/24 with stable gpt-mini sub-command-routing failures),
auth via repo-root `.env`, and how to add a scenario.

AGENTS.md gets the one-liner plus a paragraph in Testing Guidelines that
points contributors at the suite for Setup-touching edits (SKILL.md
Setup section, context.mjs, teach.md, document.md, register / sub-command
refs).

DEVELOP.md gets a short Testing section that didn't exist before, plus a
nudge in the "Test across providers" bullet pointing at the new suite as
the automated way to do that.

No code changes.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* detector: add 5 new antipatterns (em-dash-overuse, broken-image, marketing-buzzword, numbered-section-markers, aphoristic-cadence)

Consolidates eval-side detection logic into the canonical impeccable
detector. Before this change, the eval harness had its own duplicate
implementations of em-dash, copy-slop, and broken-image checks. They
now live alongside the existing 28 antipatterns in the impeccable
registry, available to the CLI, browser extension, critique skill,
and eval (via the existing slop grader child-process call).

New antipatterns:
- em-dash-overuse: 5+ em-dashes in body text content (threshold
  permits legitimate prose use of em-dash; only triggers on AI
  cadence-level density)
- broken-image: <img> with empty src, missing src, or src="#"
- marketing-buzzword: SaaS phrase list (streamline / empower /
  supercharge / enterprise-grade / cutting-edge / etc)
- numbered-section-markers: repeated 01 / 02 / 03 sequence as
  section labels — the AI editorial scaffold one tier deeper than
  tracked eyebrow chips
- aphoristic-cadence: 3+ manufactured-contrast ("Not a X. A Y.")
  or short-rebuttal ("Sentence. No clause." / "Sentence. Just
  clause.") constructions in body text

Engine wiring:
- broken-image runs as a static-html element rule (selector: img)
  and a fallback regex matcher (for non-HTML files)
- em-dash / buzzword / numbered / aphoristic run as regex
  page-analyzers, factored into a new runTextContentAnalyzers()
  helper that both detectText (non-HTML) and detectHtml (HTML)
  call, so .html files get the same coverage as .css/.tsx

Tests: 166 detector + 12 browser + 24 fixture all pass.
Browser detector rebuilt (162.7 KB).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* skill: drop unvalidated anti-centering rule; add image-led hero carve-out

The anti-centering rule ("Don't default to centering everything") was
added without empirical support. We have a detector for it
(everything-centered, threshold ≥70%) that fires on 0 / 998 samples
in the corpus — never validated, never useful.

Meanwhile the rule was almost certainly responsible for collapsing
Gemini 3.5 flash's luxury-hotel skill-on output from the canonical
"full-bleed photo + centered overlay headline" cinematic hero (the
shape skill-off Gemini chooses 67% of the time) to a 50/50
magazine grid (full-bleed rate drops to 18% under skill-on, -49pp).

Changes:
- skill/SKILL.md #### Layout: drop "Don't default to centering..."
- skill/reference/brand.md ## Layout: drop the same rule; replace
  with a positive carve-out — image-led briefs (hotels, restaurants,
  magazines, photography) often want full-bleed hero with overlaid
  menu and centered headline; let the photograph be the design
- skill/reference/layout.md: drop the assessment question and the
  "asymmetric breaks centered-content pattern" framing

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* Apply neo-kinpaku design system and improve live picker UX

Restyle the live picker to match the site kinpaku kit, persist pick mode
in localStorage, fix DESIGN.md color swatches in the parser, and land the
neo-kinpaku site refresh with new tokens, assets, palette script, and
detector rules.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Add live Steer end-to-end: poll protocol, browser UI, and E2E harness.

Wire page-level Steer through the live server and agent poll loop with steer_done
unlock semantics, extend live.md for agents, and add smoke tests with LLM
handleSteer plus recovery for hidden heroes, HMR lag, and dev-tool overlays.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Add experimental live-poll --stream mode; keep one-shot default for Cursor.

Stream keeps one process alive with ack-aware resume, but live.md documents
that Cursor should stay on one-shot background notify after testing showed
~5s pickup vs sub-second on exit-based notify.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Sync harness output and fix build validators for poll stream release.

Regenerate provider skills after live-poll --stream work, update homepage
detection counts to 41, and replace em dashes in site/skill copy so
bun run build passes prose and count checks.

Co-authored-by: Cursor <cursoragent@cursor.com>

* homepage: add testimonials marquee section

A two-row testimonial marquee on a tinted graphite plinth, sitting
between the hero and the slop teaser.

29 testimonials sourced via api.fxtwitter.com (lightly cleaned: leading
@-mention reply targets stripped, trailing self-links removed). Avatars
downloaded into site/public/assets/testimonials/ so they're served
locally. Quote order curated for impact — both rows lead with the
punchiest quotes (Ben Davis spotlight, "Impeccable > Claude design",
"THIS. This shit works.", "Uninstall whatever frontend skill you're
using.") so the first viewport is loaded with the most memorable
testimonials.

Engineering notes:
- Section uses width:100vw + margin-left:calc(50% - 50vw) to escape
  main.site-content's max-width + side padding (cards now clip cleanly
  at the actual viewport edges).
- Marquee runs at 110s linear infinite. Both rows share the same
  duration so on-screen speeds match; track is doubled so the loop
  back to 0 reads as continuous.
- Hero min-height reduced from 100svh to calc(100svh - 115px) so the
  dotted divider and top of row A peek above the fold on landing,
  signalling the section is there.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* homepage: keep the hero demo clear of the fixed header on short viewports

The hero centers its content in the full viewport (the site header is a fixed
overlay), so on shorter screens the tall Live Mode demo tucked under the nav.
Raise the hero's top padding above the 97px header (113px wide, 108/92px when
stacked) so content always pins below the header while still centering on tall
viewports, and cap the demo frame to the viewport so the whole demo stays on
screen.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* Add steer voice input and refine processing animation.

Wire Web Speech API on the Steer mic with auto-submit, block Cursor's preview browser with a clear message, and replace truncated "Working" text with a dots-only processing state.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Add agent poll connectivity indicator and tighten global bar spacing.

Surface poller state on the Impeccable mark via SSE and /status, with an instant disconnected tooltip, steer timeout failsafe, and matched brand/chat section gaps.

Co-authored-by: Cursor <cursoragent@cursor.com>

* Fix steer focus to allow page text selection without losing type-to-steer.

Blur the hidden steer input on page interaction, pause refocus during selection gestures, and reschedule focus recovery after clicks and cleared selections.

Co-authored-by: Cursor <cursoragent@cursor.com>

* site: rework "Design in production" section glyphs and audience band

Put the three how-it-works steps back into thin-line cards and drop the
overused browser-chrome bars from each glyph. Redraw the step 2 and 3
visuals to mirror the real Live Mode UI: step 2 shows the on-canvas pick
outline with an attached comment bubble, step 3 shows the floating
contextual accept bar plus the source-write confirmation. Re-treat the
audience tiles as verdigris-lined text (no card box) under a "Who it's
for" eyebrow, so each role reads as distinct from the gold step band.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* Add live insert mode with HMR-safe placeholder recovery.

Ships insert picking, scaffold helpers, variant cycling fixes for hidden
variants, and placeholder snapshot/recreation so Astro HMR does not drop
the wait-state box or re-anchor to the hero container.

Co-authored-by: Cursor <cursoragent@cursor.com>

* site: mobile pass — hamburger nav + designing hero overflow fix

The header was rendering inline nav links + GitHub button that overflowed
narrow viewports (~363px). Pre-existing display:none hacks hid Designing
and Live to make the row fit, but those items still belonged in the menu.

Header.astro: added a hamburger toggle button + inline script. The right
cluster (nav + GitHub) becomes a collapsible drawer below the header on
mobile, with data-nav-open driving the open/closed state and animating
the two-line glyph into an X.

kinpaku-kit.css: hamburger button (kinpaku-bordered glyph), mobile drawer
panel (solid lacquer-deep bg, hairline separators between rows, full-width
tappable rows), and overrides for the older sub-pages.css mobile rules
(horizontal-scroll mask on the nav, hidden [data-nav="home"] item, hidden
GitHub star label) — all redundant now that the drawer surfaces everything.

home-kinpaku.css: dropped the @media (max-width: 560px) block that hid
Designing / Live / GitHub. The drawer pattern shows them all.

designing-kinpaku.css: hero h1 "Designing with Impeccable" was overflowing
at narrow viewports. Three fixes:
  - grid-template-columns 1fr → minmax(0, 1fr) so the column shrinks to
    fit container instead of growing to "Impeccable"'s 472px intrinsic
    min-content width.
  - mobile h1 size override (clamp(2.2rem, 11vw, 3rem) at <=480px) since
    the display token's 3.4rem minimum is sized for desktop hero impact.
  - hide the decorative loop-wheel SVG below 600px (was overflowing 22px
    past the right edge).

Verified clean at both 363px and 403px viewports across /, /docs,
/docs/animate, /slop, /designing, /live-mode. scrollWidth matches viewport
width on every page (no horizontal scroll).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* detector: refine new rules + run provider tells in browser env

Follow-up to the detector port (rules landed in 7648af00):
- oversized-h1: flag long headlines set at display size, not punchy
  one/two-word heroes (length, not size alone, is the tell)
- provider tells (--gpt/--gemini) now always run in a real browser env
  (detector page, live overlay, extension); gating is a CLI-output
  concern only, applied in the Node engine return paths
- move theater-slop-phrase into checkHtmlPatterns so it runs in the
  bundled browser path, not just CLI/static (browser bundle excludes
  detect-text.mjs)
- hero-eyebrow-chip overlay highlights the eyebrow, not the heading
- gemini-tells fixture: data-URI images so the hover-zoom renders
- rebuild browser bundle

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* site: migrate /detector lab to neo-kinpaku design system

Rebuild the detector lab tool shell on --ks-* tokens (lacquer ground,
gold hairlines, champagne/mono type) instead of the legacy warm-paper
palette. Swap the "/" placeholder for the real carved-tile brand lockup,
restyle the toolbar actions as kinpaku primary/secondary buttons, and
recolor the finding overlay from off-brand magenta to vermilion.

Update the global theme-color from #fafafa to #010101 (the sRGB render
of the lacquer ground) so the browser chrome matches the dark site.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* Homepage: hero finalist, compact live demo, real picker bar.

Switch the hero to m-01-v2-01, tighten the in-hero demo layout, and replace
the marketing gbar with a shared LiveDemoGbar that mirrors live-browser.js.
Size the bar with max-content so controls are not clipped inside the capsule.

Co-authored-by: Cursor <cursoragent@cursor.com>

* site: migrate /cases/neo-mirai to neo-kinpaku design system

Rebuild the Neo Mirai case-study page on --ks-* tokens: lacquer ground
(drops the off-brand magenta radial spotlight), Alumni Sans Pinstripe
display headings instead of the banned italic serif, gold eyebrow/labels,
gold hairline image frames, kinpaku primary/secondary buttons, and a
lacquer-deep command panel with a gold-bordered code block.

Opt .neon-case-page into the shared kinpaku site-header/footer chrome in
kinpaku-kit.css (per the "add new kinpaku pages to the selector list"
note) so the global header and footer go dark to match the page.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* site: consolidate kinpaku header+footer into one reusable .kinpaku-chrome class

The dark header/footer were not a reusable unit: the header was scoped to
a per-page selector list, the github star pill was home-only, and the
default footer was copy-pasted into four page stylesheets. Pages not on
the lists (like /cases/neo-mirai) fell back to the legacy light chrome.

Collapse all of it into one `.kinpaku-chrome` block in kinpaku-kit.css —
header, github pill, and default footer — and opt every kinpaku page in
via a single body class. Delete the four duplicated per-page footer
blocks and the home-only github pill. The home page keeps its textured
verdigris footer as a deliberate override, raised to body.home-kinpaku
specificity so it wins regardless of import order. Genuinely light pages
(privacy, tutorials) just omit the class.

Fixes on /cases/neo-mirai: footer and github star now render dark/kinpaku
(were legacy-light), and the content sections are wrapped in the .neon-case
container so they sit in header-aligned gutters instead of bleeding to the
viewport edge.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* site: migrate privacy + tutorials to kinpaku via a reusable surface class

These were the last two light pages. Rather than rewrite their per-rule
styling, add a reusable .kinpaku-surface class that remaps the legacy
--color-* / --font-* tokens to kinpaku values at the body scope, so the
existing legacy-token CSS (sub-pages.css prose, the pages' inline styles)
renders dark for free. Same trick docs-kinpaku/slop-kinpaku use per page,
lifted into one shared class. Pair it with .kinpaku-chrome for header +
footer.

privacy + both tutorials pages now carry both classes. Also force the
sub-1.2rem headings (tutorial card titles, prose h1/h2) back to the
upright body face: the legacy display face was italic serif, and the
kinpaku Pinstripe face reads wrong synthesized-italic at small sizes.

No light pages remain.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* site: re-add Tutorials to the /docs sidebar

Tutorials lost its docs placement across two refactors: the Astro docs
rebuild never carried over the sidebar tutorials list the old generated
pages had, and the kinpaku homepage redesign dropped the "Full
walkthrough" link. It survived only via /designing and /live-mode.

Add a "Tutorials" group at the top of the docs sidebar (matching the
command-category styling) linking the index plus all four tutorials,
restoring the old information architecture.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* site: make kinpaku the default — flip legacy :root tokens to dark (phase 1)

Repoint the legacy design tokens in tokens.css from light-mode to kinpaku:
--font-* now reference the --ks-* brand faces (retiring Cormorant/Instrument/
Space Grotesk), surfaces carry dark-lacquer oklch, and --color-accent is gold
instead of magenta. Values mirror the per-page kinpaku remaps.

Every live page already overrides these at its body-class scope, so this
changes the fallback (any classless/new page now renders kinpaku) without
altering existing pages — verified home, designing, slop, live-mode, docs
unchanged, and the deliberate-light demos (slop specimens, home's Aurelia
mock) still render light via their own colors.

First step toward removing the per-page remaps; those become redundant next.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* detector + slop: cream-palette rule, drop everything-centered, polish catalog

- new deterministic cream-palette rule ("claude beige"): flags warm
  lightly-tinted off-white page backgrounds; wired into static + browser
  engines, with fixture + test
- remove everything-centered rule entirely (no longer in the skill) from
  registry, regex analyzer (+ index-offset fix), checkPageLayout, and tests
- catch Instrument Serif in overused-font (regex + OVERUSED_FONTS)
- /slop: reconcile catalog (cream card in, everything-centered out; counts),
  and fix demo visuals — visible hairline border, gigantic clipped hero,
  more extreme crushed tracking, padded gray-on-color card, uniform-rhythm
  monotonous-spacing, long line-length line, elastic-overshoot dialog for
  bounce easing, real zooming image for image-hover; flip the demo surface
  off warm beige to a cool neutral

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* detector page: add cream-palette fixture to the catalog

Surfaces the new cream/beige palette rule on /detector alongside the
other Color specimens.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* site: shared docs sidebar + tutorial pages join the layout

Extract the /docs section sidebar into a reusable DocsSidebar component
and wire it into all three entry points so the navigation is consistent
across docs index, command pages, and tutorial pages.

site/components/DocsSidebar.astro (new): one source of truth. Loads the
tutorials + skills collections, renders Tutorials → Commands grouped by
category, and highlights the active entry via activeCommand / activeTutorial
props.

site/pages/docs/index.astro: swap the inline sidebar markup for the
component. Drop the "All tutorials" link — the dedicated tutorials
listing page wasn't earning its slot in the rail.

site/layouts/Doc.astro: same swap. Command pages now also see the
Tutorials section above Commands, matching /docs.

site/pages/tutorials/[...slug].astro: rewrite from a standalone page
(custom .tutorial-page wrapper, ad-hoc breadcrumb) to the full
skills-layout shell with DocsSidebar in the left rail. Tutorial content
now reads in the same layout as command reference pages.

site/content/tutorials/brand-vs-product.md (deleted): the skill picks
the register automatically from PRODUCT.md, so a tutorial telling users
to pick it themselves was misleading.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* detector: catch Tailwind warm-light bg utilities in cream-palette

The static engine can't resolve Tailwind classes to computed CSS, so a
`bg-amber-50` on <body> slipped past the cream-palette rule. Add a
class-list fallback that scans body/html for arbitrary `bg-[...]` values
and named warm-light utilities (amber/orange/yellow/stone), each run
through the same isCreamColor test so neutrals and over-saturated shades
drop out. Fixture + test for the class-only case.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* site: drop redundant per-page token remaps (phase 2)

With kinpaku now the :root default, the --color-* / --font-* remap blocks
in docs/slop/designing/live-mode-kinpaku.css re-declared values identical
to :root. Removed them, keeping only the --ks-muted alias (still read by
name in those files) and each page's shell (gradient bg, color, min-height).

home-kinpaku.css keeps its remap: it uses home-specific values (e.g.
--color-charcoal: var(--ks-text), --color-cream: var(--ks-lacquer-raised))
plus the --cat-* gradient overrides, so it is not redundant.

Verified designing (PRODUCT.md viz), slop (specimens stay light), docs,
live-mode unchanged.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* site: drop italic from 15 dead editorial-serif heading rules

Audited every font-style: italic in sub-pages.css and main.css against
the live markup. Removed italic from the 15 rules whose selectors don't
appear in any page/component/content/script:

  sub-pages.css: docs-home-card-title, docs-category-title,
    tutorial-embed-caption, skill-demo-caption, skill-source-card-subtitle,
    skill-references-heading, skill-reference-title
  main.css: hero-title-combined, hero-tagline-combined, impeccable-title,
    loading-state, install-primary-howto .install-path-desc em,
    install-howto-steps > li::before, install-step-status, consulting-title

These were dormant remnants of the retired Cormorant italic-serif look —
the kinpaku Pinstripe face renders them as bad synthesized-italic, but
no markup matches the selectors so nothing rendered. Removed only the
font-style declaration; the rest of each rule stays (whole-rule cleanup
is out of scope).

Kept the 5 live selectors (slop-section-heading, tutorial-card-title,
visual-mode-demo-caption, visual-mode-method-name, gallery-card-title)
per the "if they're not used anywhere" condition, plus .prose em (real
emphasis) and .prose blockquote (conventional blockquote italic).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* skill: brand-seed palette.mjs + Setup step to run it

New-brand color now starts from a curated seed color (129 OKLCH seeds)
instead of the model guessing or defaulting to warm-cream. The script
returns one seed + composition guidance (pure-bg architecture, perceptual
text-on-fill, anti-cliché moods, jewel-tone range), with inverse-frequency
hue weighting for fair rainbow exposure and deterministic --from picking.
SKILL.md Setup step 5 makes it run for greenfield projects. Curation
tooling lives in the impeccable-evals repo (tools/palette/).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* Remove accidental live mode inject from Base.astro.

The localhost live.js tag was left in the site layout after a dev session and should never ship in the Astro template.

Co-authored-by: Cursor <cursoragent@cursor.com>

* site: dedicated /changelog + /faq, epic v3.5.0 notes, Live Mode → Beta

Split changelog and FAQ out of the homepage into two standalone kinpaku
pages, linked from the footer (and a quiet hint under the Get-started CTA).

/changelog: every release inline (no collapsible), newest first. The
v3.5.0 entry leads with a one-line summary, a real before/after pair from
the GPT-5.5 eval corpus (luxury-hotel brief, skill off vs on), and a stat
row (74% cream-bg, 76% extreme tracking, 90%+ low-contrast — measured
across ~190 samples). Then five scannable bold-led bullets, biggest
takeaway first: per-provider skill compilation, the bias-fix, Live Mode,
the 7 new detector rules, the tighter skill. Before/after JPGs optimized
to ~470KB total (down from ~2.5MB PNGs).

/faq: the six support questions, each deep-linkable.

Live Mode is now Beta everywhere it surfaces: the /live-mode eyebrow
badge and note, the homepage bento tile badge, and the changelog entry.
The historical v3.0 changelog entry stays "Alpha" — accurate to what
shipped then.

Footer trimmed to the four links not already in the top nav (Changelog,
FAQ, Privacy, GitHub).

Version bumped 3.2.0 → 3.5.0 across the three plugin manifests; the
3.2 bias-fix work folds into this release rather than shipping separately.

astro.config.mjs: disable the dev toolbar.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* site: point /design-system hero at the m-01-v2-01 finalist

design-system.css referenced kintsugi-hero-v2.png, an untracked orphan
that was never committed. Repoint it at the committed m-01-v2-01 finalist
so /design-system and the homepage hero share one image, and the page
no longer depends on a file outside the repo. The v2 orphan moved to tmp/.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* build: sync harness mirrors + green the prose gate

Rebuild propagates the committed skill source (palette.mjs Setup step,
detector rule updates, brand.md) into the 13 harness output dirs and the
plugin subtree, which had drifted from source.

Also fixes the prose validator, which had been red on six pre-existing
hits across committed files:
- Four em dashes in code comments (Testimonials.astro, LiveDemoGbar.astro,
  index.astro) and one in skill/reference/live.md — reworded to colons/commas.
- Two in the slop catalog (an em-dash-overuse specimen and the
  marketing-buzzword rule naming "empower"). Those are intentional: the
  slop page documents every antipattern by example, so it must contain
  them. Exempted site/pages/slop from validateProse rather than neutering
  the specimens.

`bun run build` is now green end to end: counts validate, prose passes,
site builds.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* skill: rewrite no-section-fade rule to fix Gemini zero-motion overcorrection

The old rule ("whole-section fade-on-scroll is the saturated AI motion
reflex") drove Gemini to overcorrect into shipping pages with no motion
at all: motion-variety 39% / zero-motion 12% with the skill on, vs
~74-78% variety and ~3% zero-motion without it.

Rewrite keeps the legitimate-stagger carve-out, names the defect at
shape level (one identical entrance on every section) without
enumerating motion primitives, and adds an explicit clause that
suppressing the reflex is never grounds for a static page.

Validated on Gemini 3.5-flash (n=10, luxury-hotel + infra-platform):
motion-variety 39% -> 70%, zero-motion 12% -> 0%, staggered-reveal
stays 0% (reflex not re-inflated).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* release: bump CLI to 2.2.0 and extension to 1.1.0

Both ship the expanded detector: the 7 new rules (cream-palette,
em-dash-overuse, marketing-buzzword, numbered-section-markers,
aphoristic-cadence, broken-image, italic-serif-display) plus
hero-eyebrow-chip, with everything-centered removed. 41 rules total.

The extension settings page already supports toggling them: the rule
list renders from detector/antipatterns.json, grouped by category, and
disabledRules flows through chrome.storage.sync into the scan config,
which detect.js honors by rule id. New rules are toggleable with no UI
change.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* release: fix release.mjs for the moved changelog + add CLI/ext entries

The changelog moved from site/pages/index.astro to its own
site/pages/changelog.astro with new markup (cf-version / cf-entry /
cf-items), which left release.mjs reading the wrong file with the old
selectors. All three release commands would have failed at note
extraction. Point it at changelog.astro, match cf-version, and scope
notes to the <ul class="cf-items"> bullet list — that also skips the
lead paragraph, before/after figure, and stat row on the v3.5.0 entry,
keeping release notes to clean bullets.

Add CLI v2.2.0 and Extension v1.1.0 changelog entries (the shared
detector update: 7 new rules, everything-centered removed, 41 total;
plus the extension's per-rule toggles) so release:cli and release:ext
have notes to extract.

Verified extraction for all three labels: v3.5.0 (5 bullets),
CLI v2.2.0 (3), Extension v1.1.0 (2).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix: correct dev server port to 4321 and drop stale pnpm-lock

Astro serves on 4321, not 3000 as the docs claimed; update CLAUDE.md,
AGENTS.md, and screenshot-antipatterns.js. Remove the leftover
pnpm-lock.yaml from the Astro migration so Cloudflare's frozen install
uses the maintained, in-sync bun.lock instead of a drifted pnpm lockfile.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* site: rework /designing flow, rhythm, Live Mode mock, and CTA

Restructure the page so iteration reads as the core value, not net-new.
The four loop phases are wrapped in a track with a sticky scroll-spy nav
(Start/Iterate/Polish/Maintain) that pins under the header and highlights
the active phase; the surfaces section (skill/CLI/extension) moves out of
the loop into the post-loop context group so the loop runs uninterrupted.

Fix the iterate split: shared subgrid row tracks so the terminal and the
Live Mode mock align on the same baseline regardless of paragraph length,
wider intro measure (52ch, was a crammed 36ch), and a deeper picker stage
so the context and global bars breathe instead of stacking on the card.

Rebuild the Live Mode mock to mirror the real picker: carved-tile mark plus
Pick / Insert / Detect / DESIGN.md controls on lacquer-deep with the gold
border, and a /impeccable live entry line so the reader knows how to start.

Reframe Start as the hard mode, move h3 subheads off the thin display face
onto Albert Sans, and trim Start so it no longer dominates the loop.

Rework the closing CTA into two standalone raised cards (the bento plinth
made them read as boxes nested in a box), and fix the tutorials copy: there
are three walkthroughs now, and the brand-vs-product tutorial is gone, so
drop it from the CTA and remove the dead lane link to it.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* site: reorder Get Started so usage follows setup, link out to more

Move the /impeccable usage examples below the Chrome extension, CLI, and
Stay-updated block. Running a command is the logical next step once the
skill, extension, CLI, and subscriptions are all in place, so the section
now reads install -> set up the extras -> use it. Add a closing "Go deeper"
line linking to the Designing with Impeccable workflow page and the docs.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix: install compiled per-provider skill variants, not uncompiled source

`npx skills add` (and `impeccable skills install`, which wrapped it) installed
the uncompiled skill/ source verbatim: the skills CLI dedupes discovery by name
and picks skill/SKILL.md first, so installs shipped unresolved {{placeholders}}
and no vendored detector (#168).

- Rename skill/SKILL.md -> skill/SKILL.src.md so the skills CLI's discovery
  skips the source and falls through to a compiled .agents variant; update the
  build reader, skill-behavior harness, and docs to match.
- Refactor `impeccable skills install` to copy each harness's compiled variant
  from the universal bundle (real dirs, no npx skills, no symlink), with
  project/global harness detection and a --providers override.
- Fix stale unit tests (replacePlaceholders, readPatterns, transformer
  prefix/summary) that asserted removed pre-v3.0 behavior, and wire the three
  orphaned test files into `bun run test` so the drift can't recur.
- Split skills-cli.test.js: pure blocks run by default, network blocks move
  behind a new `bun run test:cli-e2e`; fix its stale update assertions.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* site: default to `npx impeccable skills install`, restore install-method panel

Get Started recommended `npx skills add`, which installs a single shared build
across harnesses. Make our CLI the default (it installs the build compiled for
each harness) and bring back the "Other install methods" disclosure the
neo-kinpaku redesign dropped.

- Homepage: primary command is now `npx impeccable skills install`; a native
  <details> panel offers the Claude Code plugin and `npx skills` (caveated as
  installing one shared build rather than the per-harness one).
- FAQ: recommend `npx impeccable skills install` to install, `--force` to
  reinstall, and note the npx skills shared-build caveat.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* site: reword craft tagline so it doesn't lead with "Shape"

The craft card's tagline began with the word "Shape", which reads like
the name of the sibling /shape command and made the two cards look
swapped (#166). Reword to "Design it, then build it, all in one flow."
No data was actually swapped; this is a copy collision fix.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* skill: rename teach -> init and expand its setup flow

Rename the `/impeccable teach` command to `/impeccable init` across the
skill, site, CLI, and tests. `teach` stays as a deprecated router alias and
/docs/teach + /skills/teach redirect to /docs/init.

Expand the command beyond writing PRODUCT.md/DESIGN.md: the same codebase
crawl now also pre-configures `.impeccable/live/config.json` (Step 6, with
CSP consent) so live mode boots with no first-time detour, and the flow ends
by recommending the best commands to run next from what the scan surfaced
(Step 7).

Fold two items into the unreleased v3.5.0 changelog entry: the init rename
and the brand-seed palette picker. No version bump.

Regenerates all harness skill output dirs and the _redirects file.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs: lead README install + usage with the CLI installer

Add `npx impeccable skills install` as the recommended install option and
update the Usage section to the `/impeccable <command>` form, dropping the
nonexistent `/normalize` example.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test(skill-behavior): swap to production-tier models (sonnet + gpt-5.5)

Replace the cheap-tier default lineup (claude-haiku-4-5, gpt-5.4-mini) with
production-tier models (claude-sonnet-4-6, gpt-5.5) so the skill-behavior
suite reflects what users actually run. gemini stays on flash-lite.

Sync the docs (CLAUDE.md, AGENTS.md, tests/skill-behavior/README.md): new
model names, cost estimate raised to ~$0.50-1.50/sweep, and the old 21-22/24
baseline reframed as previous-cheap-tier history pending re-measurement on
the new lineup.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat: self-updating skill via boot-time version check

context.mjs now polls a new lightweight /api/version endpoint at most once
per day (cached globally in ~/.impeccable) and appends an UPDATE_AVAILABLE
directive when a newer skill version has shipped, prompting the agent to
offer `npx impeccable skills update`. Best-effort and silent on any failure;
asks before updating; suppresses re-prompts for a declined version for a
week. Opt out with IMPECCABLE_NO_UPDATE_CHECK=1.

- skill/scripts/context.mjs: version read, throttle + anti-nag cache, directive
- scripts/build.js + _redirects: /api/version endpoint (from plugin.json version)
- skill/SKILL.src.md: document the UPDATE_AVAILABLE boot branch
- tests/context.test.mjs: coverage for cached/newer/suppressed/opt-out paths
- changelog: v3.5.0 entry
- synced harness skill dirs via bun run build

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test: cover the self-update path (network + LLM behavior)

context.test.mjs: add a localhost stub-server integration test for the live
fetch path (poll /api/version, cache a newer version, stay silent on
same-or-older, fail silent + stamp lastCheck when unreachable). Runs against
127.0.0.1 only, never the real site; uses async spawn so the in-process stub
isn't deadlocked by spawnSync blocking the event loop.

skill-behavior: add scenario 9 asserting the agent surfaces UPDATE_AVAILABLE
but never auto-runs `npx impeccable skills update` without asking. New
prepareWorkspace `skillVersion` copy-mode (so context.mjs has a SKILL.md to
version-check), env threading through runTurn -> execBash, and bash-output
capture to prove the agent actually received the directive. Passed on
claude-sonnet-4-6, gpt-5.5, and gemini-3.1-flash-lite.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-05-28 14:22:22 -07:00
Abdul WahabandGitHub 84135db0e6 Add DeepSeek live E2E adapter (#163) 
* Add DeepSeek live E2E adapter

* Fix DeepSeek live E2E review issues

* Harden live-e2e helpers against silent failures

- htmlToJsx: match multi-line inline style attributes ([\s\S]*?)
- readCliOption: throw when --flag value is missing or another --flag
- llm-agent: echo parsed payload (first 500 chars) in schema-error throws

* Bind hoisted inline styles to their owning tag

normalizeVariantOutput previously hoisted every stripped style attribute
onto a selector derived from the variant's first tag, so a style on a
nested <span> landed on <h1>. Now walks each opening tag and emits one
rule per styled element with a descendant combinator so nested-element
styles target the correct node. Also fixes the duplicated multi-line
style regex bug (.*?) -> ([\s\S]*?) that survived the previous round.

Extracts parseVariantResponse from llm-agent for direct schema-throw
testing, and lifts readCliOption into its own module so its new
missing-value throws can be unit-tested.

Adds tests for:
- multi-line style hoisting
- nested-element tag binding and per-tag rule emission
- astro-global-prefixed selector shape
- no-op identity-return path
- opts.config short-circuit in createLlmAgent
- all four parseVariantResponse schema previews + JSON-parse failure
- readCliOption value/throw matrix

* Hoist inline styles via data attribute, not tag name

Two bugs in normalizeVariantOutput that Bugbot flagged:

1. Hoisted rules like `:scope span` matched every same-tag descendant of
   the variant wrap, so a style on one of several <span>s leaked onto its
   siblings.
2. The opening-tag scan used `[^>]*` for attributes, so a literal `>`
   inside a quoted attribute value (e.g. `aria-label="x > y"`) terminated
   the match early and the trailing `style="..."` was never seen.

stripInlineStylesPerElement now walks each opening tag character by
character respecting quoted attribute values, and tags every styled
element with `data-impeccable-hoist-id="N"`. Rules select on the
attribute so they bind to exactly the one element they came from.
The attribute is stripped during carbonize cleanup so it does not
survive into the final source.

* Harden live E2E variant CSS normalization

* Fix Radix tests

* Harden live E2E pick clicks
 2026-05-22 09:28:36 -07:00
Paul BakausGitHubPaul BakausClaude Opus 4.7
 		e587004ee4 Refactor: cleaner top-level directory structure (#138) 
* refactor(content): merge content/site/ into site/content/

Phase 1 step 1 of the directory restructure. The dual content tree was
called out in CLAUDE.md as cleanup; both trees were already in sync
except for anti-patterns-catalog.js, which moves to site/data/.

- Delete content/site/skills/ and content/site/tutorials/ (duplicates of
  site/content/, which is what Astro's content collection actually reads).
- Move content/site/anti-patterns-catalog.js -> site/data/.
- Update scripts/lib/sub-pages-data.js and scripts/build.js to read from
  site/content/ and site/data/.
- Drop content/site/ from validateProse target list (site/content was
  already there).
- Rewrite the "Two content trees" section in CLAUDE.md as a single-tree
  pointer; update stale dev-server text mentioning the deleted
  server/index.js.

Tests: 186/186 pass. Skills build: clean.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* refactor(skill): rename source/skills/impeccable/ -> skill/

Phase 1 step 2 of the directory restructure. The path was redundantly
nested ("source/" wrapper plus "skills/impeccable/" — singular content
hidden behind the plural). Collapses to flat skill/SKILL.md +
skill/reference/ + skill/scripts/.

- Move source/skills/impeccable/ -> skill/.
- Rewrite scripts/lib/utils.js readSourceFiles(): drop the multi-skill
  iteration (CLAUDE.md commits to a single user-invocable skill); read
  skill/SKILL.md directly.
- Update scripts/build.js, scripts/generate-og-image.js, and the
  sub-pages data layer to point at skill/.
- Update tests/lib/utils.test.js: drop the "multi-skill" and "dir-name
  fallback" cases, update single-skill paths to skill/.
- Update tests/build.test.js similarly: drop "multiple skills"
  integration test, update paths.
- Update non-glob path joins in tests/framework-fixtures.test.mjs,
  tests/live-e2e/session.mjs, tests/live-e2e/agents/llm-agent.mjs,
  tools/live-loop.mjs.
- Update prose/text references in CLAUDE.md, AGENTS.md, DEVELOP.md,
  README.md, scripts/lib/sub-pages-data.js, bin/commands/skills.mjs,
  site/data/anti-patterns-catalog.js, site/pages/docs/[...slug].astro,
  docs/adr-live-variant-mode.md, docs/plans/.

Eval framework note: the separate impeccable-evals repo reads
../impeccable/source/skills/impeccable/ and needs a coordinated
rename to ../impeccable/skill/.

Tests: 186/186 pass. Skills build: clean.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* refactor: rename docs/ -> notes/

Phase 1 step 3 of the directory restructure. The internal docs/ dir
(ADRs and plans) clashed with the site's /docs route. Renaming it
"notes/" makes the difference unambiguous: notes/ is project-internal
process, /docs is the user-facing route under site/pages/docs/.

No code references the dir; the rename is a clean git mv.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* refactor(site): move public/ under site/public/

Phase 2 step 4 of the directory restructure. Public assets and the
Astro publicDir now live alongside the rest of the site, so site/
is fully self-contained for static content.

- git mv public site/public.
- astro.config.mjs: add publicDir: './site/public'. Astro defaults to
  ./public at the project root, so the override is required.
- scripts/build.js: write generated _data, _headers, _redirects,
  _routes.json, and js/detect-antipatterns-browser.js into
  site/public/. Also delete the dead _REMOVED() Bun static-site
  builder (replaced by Astro at #130; the placeholder no longer earns
  its keep).
- scripts/build.js validateProse: replace the stale public/index.html
  reference (deleted at the Astro migration) with site/pages/index.astro
  in the count-validation file list, restoring homepage drift detection.
- scripts/generate-og-image.js: write OG image into site/public/.
- scripts/screenshot-antipatterns.js: read examples from + write
  screenshots to site/public/antipattern-{examples,images}/.
- scripts/lib/sub-pages-data.js: load command demos from
  site/public/js/demos/commands.
- .gitignore: rename the public/* generator-output entries to
  site/public/*.
- CLAUDE.md: refresh CSS/data-file paths (still pointing at the old
  pre-Astro public/css/ + public/js/ tree), point the changelog and
  command-add checklists at site/pages/index.astro and
  site/scripts/data.js + site/scripts/components/framework-viz.js.

Cloudflare Pages note: functions/ stays at the repo root because
CF Pages auto-discovers it there with no configuration knob to
relocate. Moving it under site/ would either break deployment or
require a build-time copy step that adds more complexity than the
cleanup is worth.

Tests: 186/186 pass. Skills + site build clean. _headers,
_redirects, _routes.json, _data/ all land in build/ correctly.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* refactor(cli): consolidate bin/ + src/ + lib/ under cli/

Phase 2 step 5 of the directory restructure. The CLI surface was split
across three top-level dirs whose names were easy to mistake for each
other (especially src/ vs source/ pre-step-2). Consolidates under cli/.

- git mv bin -> cli/bin (CLI entry + skills sub-command)
- git mv src -> cli/engine (detect-antipatterns engine + browser variant)
- git mv lib -> cli/lib (download-providers helper)

Update package.json:
- bin.impeccable: cli/bin/cli.js
- main + exports: cli/engine/detect-antipatterns.mjs and the
  ./browser variant
- files: ["cli/", "LICENSE"]

Update internal references:
- cli/bin/cli.js: dynamic import points at ../engine/, package.json
  read goes one level deeper (../../package.json).
- functions/api/download/[type]/[provider]/[id].js + bundle/[provider].js:
  cli/lib/download-providers.js path.
- scripts/build.js, scripts/build-browser-detector.js,
  scripts/build-extension.js: cli/engine path constants.
- scripts/lib/sub-pages-data.js, scripts/lib/utils.js, skill/scripts/
  live-server.mjs: comment refs.
- tests/detect-antipatterns{,-browser,-fixtures}.test.{js,mjs},
  tests/windows-path-fix.test.js: import + read paths.
- AGENTS.md, CLAUDE.md: doc paths.

Verified:
- npx node cli/bin/cli.js --version, --help, detect --help all work.
- bun run build, bun run build:browser, bun run build:extension all
  clean. Browser detector lands at cli/engine/detect-antipatterns-browser.js;
  extension/detector/detect.js still emits to the same location.
- bun run test: 186/186 pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix: update browser-detector paths missed in cli/ rename

Bugbot caught two runtime path leaks where the comment got renamed
to cli/engine/ but the actual code still used the old src/ segment.

- skill/scripts/live-server.mjs: detectPaths array now joins cli, engine,
  detect-antipatterns-browser.js for both the repo-relative lookup
  (4 dirs up from .claude/skills/impeccable/scripts/ to repo root) and
  the npm node_modules fallback. Without this fix, the detection
  overlay would silently not load during live-server sessions.

- scripts/build.js: the post-build copy of the browser detector into
  site/public/js/ was reading from src/. The if (fs.existsSync(...))
  guard meant the copy was silently skipping, so antipattern-examples
  pages would 404 on /js/detect-antipatterns-browser.js once the site
  was deployed.

Tests: 186/186 pass. Build clean. site/public/js/detect-antipatterns-browser.js
re-emits as expected.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix: cleanup-deprecated import path missed an extra .. in cli/ rename

Bugbot caught three call sites in cli/bin/commands/skills.mjs that
import '../../skill/scripts/cleanup-deprecated.mjs'. Pre-rename, that
was correct from bin/commands/ (one parent to bin/, one to repo root).
After moving the file from bin/commands/ to cli/bin/commands/, the
path is one directory deeper, so it needs three .. segments to reach
the repo root. Without the fix, every cleanup invocation throws on
import and gets swallowed by the surrounding try/catch — silent skip.

cli/bin/cli.js's package.json read already uses '../../package.json'
(the same depth pattern), confirming three levels is correct.

Verified: dynamic import resolves and exports the expected functions.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore: sweep stale path/file references missed in the restructure

Same root cause as the two bugbot finds: some references in moved or
related files weren't tracked because they didn't match a simple
sed pattern. Caught the rest by walking each moved dir's depth and
each Astro-migration deletion.

Stale path references (post-Astro migration, missed earlier):
- CLAUDE.md: legacy URL redirects "live in server/index.js" -> point
  at the actual sources (scripts/build.js generateCFConfig +
  site/public/_redirects).
- AGENTS.md: counts.js path (public/ -> site/public/), changelog file
  (public/index.html -> site/pages/index.astro), screenshots note
  (public/ -> site/), source-of-truth dirs (source/, src/ -> skill/,
  cli/).
- tests/detect-antipatterns-browser.test.mjs: comment about routes
  "in server/index.js".
- skill/reference/live.md: workflow.css example for "this repo" was
  pre-Astro (public/css/) -> site/styles/. (User-project Vite/Next
  example unchanged.)

Stale path that pointed at moved files:
- tests/skills-cli.test.js: CLI path was '..', 'bin', 'cli.js'; now
  '..', 'cli', 'bin', 'cli.js'. Test isn't wired into bun run test
  but it would have failed if invoked.

Dead files (orphaned by Astro migration, never cleaned up):
- tests/server/download-validation.test.js: imported from
  ../../server/lib/{validation,api-handlers}.js which were deleted in
  b8f09c8. Test was a silent failure waiting to happen.
- scripts/lib/render-markdown.js: 156-line module with zero consumers
  (the only caller, scripts/lib/render-page.js, was deleted in the
  Astro cleanup).
- scripts/build.js: dead commented-out generateSubPages import.

Tests: 186/186 pass. Build clean.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(build): remove invalid Corepack packageManager spec

Cloudflare Pages rejects the build with `Unsupported package manager
specification (bun@1.3.11)`. The packageManager field follows
Corepack's syntax which only validates npm/pnpm/yarn — `bun@X.Y.Z`
parses as a malformed Corepack directive even though Bun itself
treats it as a hint.

Pre-existing on main since d874af0 (CF Pages deploy on main also
failing); just surfaces here because the PR triggers a fresh deploy.

CF Pages auto-detects Bun anyway (the build log confirms:
"Detected the following tools from environment: bun@1.3.11,
pnpm@10.11.1, nodejs@22.16.0"). Removing the field unblocks the
deploy without changing local dev behavior.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Paul Bakaus <paulbakaus@pauls-mbp-3.lan>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-04 16:38:03 -07:00
Ngo Quoc HuyGitHubPaul Bakaus
 		d874af046a feat(live): make live sessions recoverable (#125) 
* feat(live): make live sessions recoverable

tired of live mode losing the plot when the browser moved faster than the agent.
now the state is boring: journal it, resume it, finish it.

---
- add durable live-session journal, checkpoint events, and status/resume/complete commands
- split browser session storage into a testable helper and harden accept/discard completion
- fix Astro live CSS preview mode and add recovery/live E2E coverage
- declare Bun as the package manager and add a Bun-native audit script

* fix(live): acknowledge fallback recovery states

* fix(live): flush recoverable handoffs promptly

* fix(live): keep recovery handoffs accurate

* fix(live): preserve poll reply metadata

* fix(live): treat event HTTP failures as failed sends

* fix(live): acknowledge manual completion through helper

* Add .impeccable project state paths

* Fix live disconnect recovery phase

* Refine live CSS authoring contract

* Test live CSS authoring guidance

* Harden live LLM E2E recovery

* Fix live recovery review issues

---------

Co-authored-by: Paul Bakaus <paulbakaus@pauls-mbp-3.lan>
 2026-05-03 19:03:22 -07:00
Paul BakausandClaude Opus 4.7 54d9f05ea5 fix(live): land valid TSX through wrap → preview → accept → carbonize 
Closes #114.

Three orthogonal bugs that surfaced together when live mode picked an
element inside a Vite React/TSX component with sibling branches:

1. JSX wrapper insertion produced invalid TSX
   - Replacing a single picked JSX child with [comment, <div>, comment]
     yields three adjacent siblings, which oxc rejects with "Adjacent
     JSX elements must be wrapped in an enclosing tag."
   - A Fragment `<></>` solves the adjacency case but breaks
     `cloneElement`-using parents (Radix `asChild`, Headless UI, etc.)
     with "Invalid prop supplied to React.Fragment."
   - Fix: keep the wrapper `<div data-impeccable-variants="ID">` as the
     single JSX-slot child and tuck both marker comments INSIDE it.
     accept/discard now expands its replacement range to include the
     wrapper's `<div>` open/close lines via div-depth tracking.

2. carbonize produced nested template literals in TSX `<style>`
   - extractCss captured `{` / `` `} `` lines from the agent's existing
     `<style>{`…`}</style>` template, then handleAccept re-wrapped with
     another pair, producing `<style>{`{`@scope…`}`}</style>` which oxc
     rejects with "Expected `}` but found `@`".
   - Fix: extractCss now strips a leading `{` and trailing `` `} ``
     wherever they appear in the captured content (own line OR attached
     to the first/last CSS line), so re-wrapping always yields exactly
     one `{` ` … ` `}` pair.

3. Ambiguous source matching for repeated JSX branches
   - `findElement` returned the first substring match. Multiple
     `<aside className="card">` siblings all matched the same query, so
     wrap silently landed on the first regardless of which one the user
     picked.
   - Fix: live-wrap accepts `--text TEXT` (the picked element's
     textContent), collects ALL candidates via `findAllElements`, and
     narrows by a tag-stripped, JSX-expression-stripped substring match.
     Returns `element_ambiguous + candidates[]` when multiple branches
     match equally; falls back to first-match when source uses dynamic
     content (`<h1>{title}</h1>`) so existing flows aren't broken.
   - The fake e2e agent now forwards `event.element.textContent` to
     wrap, and live.md tells the agent to do the same.

Test coverage:
- New `vite8-react-tsx-repeated-aside` e2e fixture: three identical
  `<aside>` branches, picks the second card's <h1>, runs the full
  wrap → Go → cycle → accept → carbonize cycle on a real Vite + TSX
  dev server, asserts that Hero One and Hero Three survive untouched
  (proving wrap landed on the correct branch).
- Six new unit tests across live-wrap.test.mjs and live-accept.test.mjs
  covering the Fragment-replacement design, both leading/trailing
  template-literal placements, --text disambiguation, the dynamic-
  content fallback, and the element_ambiguous error shape.
- New `runtime.assertSourceContains` fixture hook so other regression
  fixtures can assert sibling-branch survivability cheaply.

All 186 unit + static-fixture tests pass; all 21 live e2e fixtures
(20 prior + new TSX) pass with no console errors.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-28 13:23:20 -07:00
Paul BakausandClaude Opus 4.7 6e96f62803 fix(live): readable freeform input on dark bar + tools/live-loop.mjs 
The configure row's text input filled its background with translucent
magenta (BP.accentSoft) on focus. Composited against the dark bar surface
this produced a murky purple where the browser's default placeholder
gray washed out — flagged in a real session as "godawful styling, gray
text on dark magenta really hurts my eyes". Fix: focus state shows an
accent-colored border only, no fill; placeholder color is set explicitly
to BP.textDim via a one-shot stylesheet so it reads in both themes.

tests/live-e2e/agent.mjs: runAgentLoop's wrapTarget now accepts either a
static {classes,tag,elementId} (test fixture mode) OR a function that
derives the target from each generate event (real-use mode where the
picked element is unknown ahead of time).

tools/live-loop.mjs: standalone runner that attaches the LLM agent to a
running live-server. Used as a test-harness shortcut for validating live
mode out of band; in production the user's coding agent (Claude Code,
Cursor, etc.) plays this role directly via the live skill spec.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-25 01:35:32 -07:00
Paul BakausandClaude Opus 4.7 d26ccac1be feat(test): pluggable LLM agent for live-mode E2E suite 
tests/live-e2e/agents/llm-agent.mjs: a Claude-backed VariantAgent that
implements the same one-method interface as the fake agent
(generateVariants(event, context) → { scopedCss, variants[] }). Default
model claude-haiku-4-5; override via IMPECCABLE_E2E_LLM_MODEL.

Prompt caching is on — the system prompt (instructions + the live-mode
spec from reference/live.md) is the cacheable prefix. First call writes
~10K tokens to cache; subsequent fixtures pay only the cache-read rate.
JSON output is validated for shape (scopedCss, variants[N].innerHtml),
with light error messages on parse failure.

tests/live-e2e.test.mjs: read IMPECCABLE_E2E_AGENT (fake|llm). When 'llm',
construct the LLM agent and skip the case cleanly if ANTHROPIC_API_KEY is
unset. Param-manifest assertions are gated to fake mode (LLM may emit
zero-param "fixed point" variants per the live.md spec). The accepted-h1
class assertion now allows hero-title as one of multiple classes so an
LLM agent that adds classes alongside the original still passes.

Test timeouts widen for LLM mode: 25s first-pass on conditional-render
fixtures (vs 5s for fake), 60s on direct waits (vs 30s). Without these,
the LLM's 3-8s generate latency races the orchestration's state-loss
recovery window.

tests/live-e2e/ui.mjs: clickGo retries up to 3× on stability failures.
Required because conditional-render fixtures (modal/tabs) animate the bar
mid-transition when preActions trigger framework HMR; a single click can
land during a re-render and Playwright's stability gate times out.

Pass rate on a typical sweep: 18/19 in LLM mode, 19/19 in fake mode.
The modal fixture's intrinsic state-loss flake (Fast Refresh resetting
useState(open) when source changes) is amplified by LLM latency and may
need a re-run; documented in CLAUDE.md.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-25 01:06:06 -07:00
Paul BakausandClaude Opus 4.7 c8de59d81e test(live): add full-cycle E2E framework-fixture suite with pluggable agent 
19 fixtures (11 styling/build variants + 4 conditional-render scenarios + 4
meta-frameworks) drive the entire user flow end-to-end: handshake, pick,
configure, Go, cycle, accept, carbonize cleanup. Each fixture installs real
deps, boots the framework dev server, and runs Playwright Chromium against a
deterministic fake agent that produces realistic variants (colocated style
with @scope rules, full data-impeccable-params manifests covering range +
steps + toggle, JSX/HTML/Svelte syntax-aware rendering).

The agent is pluggable via a one-method interface — generateVariants(event) —
so a future LLM-backed agent slots in by implementing the same shape. The
orchestrator handles wrap, file write, accept, and carbonize cleanup
deterministically regardless of which agent is plugged in.

Schema extensions (tests/framework-fixtures/README.md): runtime block adds
preActions / reloadProbe / pickSelector / scheme / ignoreHTTPSErrors so
fixtures can drive conditional UI (modal, tab, route) before pick and verify
the carbonized variant survives a reload.

Static fixture suite filtered to skip dirs without fixture.json so empty
scaffold dirs no longer break discovery. Total: 178 static checks, 19 E2E
full cycles, ~107s wall clock for the E2E suite.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-24 23:37:04 -07:00