Commit Graph
1835 Commits
Author SHA1 Message Date
Paul BakausandAbdul Wahab ba26730411 COMP-FIDELITY: opus arm and 07 re-pass
AI-assisted (Claude Code).
2026-08-28 06:13:59 +05:00
Paul BakausandAbdul Wahab 356362a410 comp-spec refuses a code region larger than a quarter of the comp
A session named seven regions for a page with three plates, a table, a note, callouts and a spine, so the hero gate could name nothing and the score sat at 70. A code region is one element; a column is a container of several.

AI-assisted (Claude Code).
2026-08-28 06:13:59 +05:00
Paul BakausandAbdul Wahab f5819fbd6a COMP-FIDELITY: fourth sweep
AI-assisted (Claude Code).
2026-08-28 06:13:59 +05:00
Paul BakausandAbdul Wahab 3e7e85daf7 font-fingerprint: full-height inked columns leave the row profile; forceAllowed needs the user's reported words and a downgrade
Staff rules and a black page edge fused eight track rows into one 389px 'line'. A session forced two gates by quoting a brief line ('should feel like an extension of her artwork') as permission; a force now needs the user's words reported or quoted, a downgrade verb, and the comp noun in one reason.

AI-assisted (Claude Code).
2026-08-28 06:13:59 +05:00
Paul BakausandAbdul Wahab 2cc60a5348 font-fingerprint: measure the dominant lettering class in a mixed crop; NEXT prefers generate-image --plate
A comp region drawn on the 10x10 grid over-covers: a body-copy crop carries the last headline line above it and a drawing beside it, and one session measured 'thread-body' at cap 160px off a carburetor drawing and ranked Londrina Shadow for it. Tall non-text 'lines' leave the mass reference; lines cluster by cap height and the cluster holding the most ink (multi-line first) is measured, re-applied after upsampling.

The plates NEXT line now names generate-image.mjs --plate as the tool (harness image tool only as fallback) after a session spent 25 turns keying plates with magick.

AI-assisted (Claude Code).
2026-08-28 06:13:59 +05:00
Paul BakausandAbdul Wahab 08ce88f565 Texture presence at the hero: structure over palette
AI-assisted (Claude Code).
2026-08-28 06:13:59 +05:00
Paul BakausandAbdul Wahab 4f2de6a0b6 Gates: a passed texture with held ground is placed; responsive does not re-score a passed plate as missing
AI-assisted (Claude Code).
2026-08-28 06:13:59 +05:00
Paul BakausandAbdul Wahab caf9744763 Hero gate: a passed plate is placed material; plate rows travel on state; low-detail text with held structure is drift; wait long on plate generation
Also records the third sweep in COMP-FIDELITY.md (branch +7 to +18 points over main on three niches, sol).

AI-assisted (Claude Code).
2026-08-28 06:13:59 +05:00
Paul BakausandAbdul Wahab 99f73390db Comp fidelity: font ranking that holds without a browser, spec refuses painted chrome, control-box veto only for discrete controls
font-match / catalog index
- Index schema 2 adds a third render, 48c (48px cap, ALL CAPS text). Caps headline crops have no x-height band and ranked against mixed-case renders as barcode faces; they now route to the caps render.
- Non-text families (barcodes, redacted, flow, dingbats, effect faces) are excluded from candidates.
- The distance adds a gross width and weight gap (log ratio of advance and ink density) so a face 50% wider or 35% lighter cannot rank first on run-length detail alone; the index stores those readings.
- Multi-line all-caps crops vote on x-height across lines: one line's crossbars no longer give the crop a spurious x band.
- With no browser, --rank records the catalog's nearest face (source catalog, size estimated) so the spec gate can close; the NEXT line and new-work.md say not to install a browser or hand-write a choice.
- font-match stamps the choice it writes; the spec gate refuses a chosen face it did not write (sessions typed Arial Narrow into spec.json to pass).
- IMPECCABLE_NODE_MODULES lets a harness lend a playwright.

comp-spec
- A region note that describes painted material (diagram, drawing, photo, texture...) under a code kind is refused at the spec unless codeDrawn is set: the exploded carburetor filed as chrome is a plate about to be redrawn in SVG.

build-phase
- The control ink-box veto applies only when the comp's ink is a discrete element and the build's box is too; a full-width bar told one session six times that 1376x87 was 1382x102 with no edit able to move it.

AI-assisted (Claude Code).
2026-08-28 06:13:59 +05:00
Paul BakausandAbdul Wahab 919c68d2b9 COMP-FIDELITY: record the second sweep (packets without state, prefix inertia, WebP comps)
AI-assisted (Claude Code).
2026-08-28 06:13:59 +05:00
Paul BakausandAbdul Wahab 48350ffb14 Read WebP/JPEG comps through a sibling PNG cache instead of forcing PNG
comp-spec, comp-diff, build-phase, font-match, and generate-image now decode any comp raster via loadRaster(), converting non-PNG input to <file>.png next to the source. Sessions used to hit 'not a PNG' and rewrite the .webp in place with PNG bytes, which broke transcript replay (a later step rewrites the comp beyond the cut) and left a mislabeled file.

AI-assisted (Claude Code).
2026-08-28 06:13:59 +05:00
95294e464a font-match v2: fingerprint the comp lettering and pick candidates from a Google Fonts catalog index
lib/font-fingerprint.mjs replaces the three-number fingerprint with
size-invariant shape features (x-height ratio, stroke contrast, stem width,
run-length quantiles, roundness, serif signal, width spread) and a
noise-normalized distance; family recall on a held-out self-test rose from
13% to 72% top-5. data/font-index.json carries the whole Google Fonts
catalog (3,092 faces at two cap sizes, 707 KB); font-match --rank fingerprints
the comp crop, takes the 25 nearest faces from the index (plus the model's
own names), renders them at the comp's cap height, ranks by the same
distance, and prints a proof sheet and the CSS to use. scripts/build-font-
index.mjs rebuilds the index at release time.

AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:13:59 +05:00
cacb2868ac No comps outside the state: generate-image refuses .impeccable/mocks/ output while a roll is pending and build-phase has not started
The first paid confirmation sweep showed the failure: models rendered the
three comps first and ran build-phase.mjs start after, so a session cut at
the composition pick carried no state.json and the resumed model followed
the conversation ('translate the comp into HTML now') instead of the
phases. Decision comps (.impeccable/mocks/decision/) are unaffected;
--force-mock overrides.

AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:13:59 +05:00
62f59a3934 build-phase: gate errors are refusals that name themselves, never stack traces; fix ink-box crash on report shape
The first paid confirmation run hit a TypeError in the ink-box check
(report regions carry normalized w/h at the top level, not under box);
runGate now catches a throwing gate and returns a one-line refusal with
an explicit force path so the run is not lost to a tool bug.

AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:13:59 +05:00
cbe89a1969 Round-4 sim fixes: lead text region by cap height, ink-box only for discrete controls, grain allowed where the comp is grainy, textures cannot block responsive alone
AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:13:59 +05:00
f5751c4d75 font-match: choose the face by metrics; chroma-keyed plates; ink-box report; verbatim words in the hero
font-match.mjs fingerprints a text region's lettering in the comp (cap
height, glyph advance per cap = width class, ink fraction = weight class,
tracking), renders candidate faces at that cap height in a headless
browser (yours plus a shortlist for the width class), and ranks them by
distance with a proof sheet; the spec gate refuses to close until the lead
text region is measured and ranked. generate-image --plate keys ink-on-
ground plates to alpha (chroma) so the drawing sits on the page's own
ground; the plates gate scores keyed plates composited over the region's
ground. comp-diff reports each region's ink box; the hero gate names a
control whose box height or width differs from the comp. The hero
instruction copies the comp's words verbatim; rewording is a stated
decision after the hero passes.

Driven by a human review of the r3 side-by-sides: face width and weight,
plate ground, control row height, and content substitution.

AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:13:59 +05:00
b015e26ddf Round-3 sim fixes: record hero is not an attempt; texture bands under present ink are drift; capture guidance
AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:13:59 +05:00
f704fca29c forceAllowed: a 'truthful translation' the model proposed is not the user downgrading the comp
AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:13:59 +05:00
bfa6014796 Round-2 sim fixes: one plate rule, plate size from the gate's floor, missing means empty
plateVerdict() is shared by the plates gate and generate-image's PLATE-WARN
so they cannot disagree; --plate picks a frame that clears the 1.5x width
floor (a square region wider than 682px takes the 1536 landscape frame);
'missing' on text/chrome/control regions requires the build region to be
near-empty, so a 12px rule a few pixels off reads as contradicted or drift,
not missing; the responsive gate does not re-litigate a plate that passed
the hero; record hero after close does not inflate the attempt count.

AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:13:59 +05:00
af4ac68805 Plates: textures tile a clean comp patch first; record hero reports plate rows
AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:13:59 +05:00
e618357a69 Responsive gate: the desktop capture must still read as the comp
Round-1 simulated builds passed the hero at 1536 and shipped a page whose
first viewport collapsed to one column at 1440 (comp-diff 50% on the
final capture, 82% on the hero). The responsive phase now requires
desktop.png and mobile.png and diffs desktop.png against the comp at 65%
with no region missing.

AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:13:59 +05:00
24773eeedf Hero gate: text and chrome regions read as drift once structure and palette hold; scripts run through symlinks
Three simulated builds under the previous gate reached 78-83% overall with
the exploded plate placed and the table right, then spent 12-20 attempts
chasing 'contradicted' verdicts on a headline set in a substitute face and
on 50px chrome strips whose detail was paper grain. Text with structure
above the floor and its palette intact is drift; chrome and controls with
structure and palette held are drift. The adversarial set (swapped
columns, mirror, sepia, noise plate, tile shuffle) still fails.

isMain uses realpath on both sides so a skill mounted through a symlink
(Cursor, worktrees, staged evals) still runs its CLIs.

AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:13:59 +05:00
d9a155be8c Gates that cannot be talked past: metric hardening, one start command, uncovered-ink refusal
From a forensics pass over twelve runs and two adversarial passes over
the metrics:

- comp-diff: detail is signed and penalizes invented energy; regions with
  structure under 0.3 (or painted regions under 0.45 / added detail over
  0.4) are contradicted whatever the mean says; palette ramp tightened;
  region crops inherit the whole-image best translation so a shifted page
  is not eight contradicted regions.
- hero gate: fails on any contradicted plate/image/text region (chrome and
  controls keep the one-third allowance), on a capture that is not the
  comp's frame, on a palette that is not the comp's, and on an organic
  clip-path drawn inside a raster region's box.
- plates gate: scored against the comp crop with overlapping text/chrome
  painted out (comp-spec plateReference; generate-image uses it too), with
  a structure floor and an added-detail veto; the real plate passes, noise,
  mirrors, mosaics, and other regions do not.
- comp-spec refuses a regions file that leaves comp ink unnamed.
- The direction-choice ping is folded into build-phase.mjs start
  --direction --kind; the roll writes .impeccable/build/pending.json and
  context.mjs / detect.mjs report COMP_ROUND_OPEN until the hero gate
  passes. A code-led config makes start print the contract step and stop.

AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:13:59 +05:00
e0ec77b4bb Lock down the scroll-clip case for text-occlusion (#602)
The paintedRect clamp landed in 9d2b0556 without a fixture, so nothing
stopped the false positive coming back. This adds the shape that produced
it: a scroll region with an opaque bar directly beneath.

Text scrolled past the panel's bottom edge still reports its full
unclipped rect, and that rect lands on the bar. The probe then samples
coordinates the text is not painted at, finds the bar, and reports the
text as buried under it. Any sticky footer or toolbar under a scroller
has this shape.

Verified red then green: with the clamp reverted to main's version the
fixture reports a fourth finding and the assertion fails; with it in
place the count holds at three.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-28 06:13:59 +05:00
6dd15238c4 Close the comp-round gap and make the hero gate teach
concept-seed's choice ping now prints the next mandatory step from the
recorded build path (comp-led: build-phase.mjs start --direction <key>),
because every run that skipped the comp round did so right after that
ping. build-phase gains a comps phase ahead of spec (three sidecar'd comps
under .impeccable/mocks/, one approved) and records the approved comp on
close. The hero gate lists the worst region crops first with the fix class
per verdict, and refuses a third value-only attempt on the same stuck
region. Hero instruction is plates first, then the semantic layer. The
finish reviewer treats a comp-led build with no closed comps phase as a
material finding.

AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:13:59 +05:00
2fbfef0b43 docs: final numbers from the overnight sweep
AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:13:27 +05:00
2dcaacbcd1 docs: first eval sweep results for comp fidelity
AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:13:27 +05:00
b450da2082 comp-spec: --help and the exact regions.json shape after --grid
AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:13:27 +05:00
f4987eebba Hero gate refuses while a produced plate is unreferenced by the source
The first live run produced a faithful carburetor plate, then drew the
region in SVG and left the plate on disk. Before diffing, the hero gate
now walks the artifact (or a bounded source tree) for every plate's file
name or a data URI named for it.

AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:13:27 +05:00
63dd7faa0e build-phase: textures skip the size floor, --force needs the user's words
The first live run forced past the plates gate with 'single-file HTML
delivery requires embedded CSS/SVG'. That is not a reason the comp's
authority moves for; the script now refuses a --force whose reason does
not quote the user, and new-work.md says a single-file deliverable inlines
the plate as a data URI. Texture plates are judged on palette and grain,
not size or structure, since they tile.

AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:13:27 +05:00
34ef9ac2c4 Rewrite the comp-led build around the phase gates; reviewer reads the diff first
new-work.md section 6 becomes the spec / plates / hero / sections / motion /
responsive phase list, each closed by build-phase.mjs advance; the
reproduction and hero-checkpoint prose that asked the model to compare
from memory is gone. visualize.md's inventory, medium gate, and produce
sections collapse into the spec and plate mechanism. The finish reviewer
takes the state file and comp-diff reports as inputs and starts its
fidelity matrix from the measured verdicts. docs/COMP-FIDELITY.md records
the design.

AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:13:27 +05:00
5856161014 Plate pipeline, asset producer rewrite, and two detector rules for CSS standing in for material
generate-image.mjs --plate produces one raster region of the measured spec
from the comp crop, scores it against the crop, and refuses under --min.
The asset producer's job becomes producing the spec's plates. Detector
gains organic-clip-path (many-vertex polygon / curved path() clips) and
buried-raster (raster under a near-opaque wash or at near-zero opacity),
wired into both engines with fixtures.

AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:09:46 +05:00
b0fc2e8801 Add comp-diff, comp-spec, and build-phase: measured comp fidelity for the build phase
Dependency-free PNG codec, perceptual metrics (structure / color / detail /
bands), side-by-side + heatmap + per-region crops, a measured spec from the
approved comp (grid overlay, sampled palette, plate list), and a phase state
machine whose spec / plates / hero gates run the diff instead of asking the
model to remember the image.

AI-assisted (Claude).

Co-Authored-By: Claude <noreply@anthropic.com>
2026-08-28 06:09:46 +05:00
github-actions[bot] f86473ba7d Sync generated provider output 2026-08-28 00:53:54 +00:00
377fb112b0 Pass the session key from detached idle-grace tests
Main's #469 tests POSTed /heartbeat and /answer without ?key=, which the
gate now rejects, so those daemons looked dead. The e2e heartbeat counter
also has to match pathname rather than a suffix, now that the URL carries
the key.

Written with AI assistance under maintainer direction.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-28 05:53:25 +05:00
7982002dac Allow bare loopback Host/Origin on port 80, where browsers omit the suffix
Bugbot caught that the exact-match allowlists 403 every request on --port 80
because browsers drop the default-port suffix; other ports stay strict.

Written with AI assistance under maintainer direction.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-28 05:53:25 +05:00
2e075dc58c Gate the build-path flip behind the same session key and origin checks
An unauthenticated POST /build-path wrote the flip event that makes --wait
instruct the agent to generate comps: same class as the /answer hole in #555.

Written with AI assistance under maintainer direction.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-28 05:53:25 +05:00
eaaecbd1fe Fix: require session key and origin/host checks on serve-question POSTs (#555)
Unauthenticated POST /answer copied steer into the agent ANSWER line. The handler now requires the detached session key and rejects foreign Origin and Host.

Written with AI assistance under maintainer direction.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-28 05:53:25 +05:00
d690349db1 Fix: keep URL basic-auth credentials on the scan origin (#657)
page.authenticate is page-wide, so a cross-origin redirect that then 401s would receive the original credentials. Attach Authorization only to requests for the scan origin.

Written with AI assistance (Cursor); reviewed by maintainer.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-28 05:53:01 +05:00
d5873ff8eb Fix: redact URL userinfo from detect findings (#657)
Strip basic-auth credentials from scan-target URLs before goto and finding output, and pass them to page.authenticate instead.

Written with AI assistance (Cursor); reviewed by maintainer.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-28 05:53:01 +05:00
github-actions[bot] 1df992ade0 Sync generated provider output 2026-08-28 00:44:04 +00:00
be87f5eb86 Fix: refuse inert exact ignore-value entries (#662)
ignore-value stored exact values for rules that cannot extract one, so the entries never matched. Refuse them and point at "*" --file.

AI assistance: implemented with Cursor Grok 4.6.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-28 05:43:36 +05:00
af2e8b3ac3 Fix: stream bundle downloads to disk instead of buffering
AI assistance: implemented with Cursor Grok 4.6.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-28 05:43:04 +05:00
5d932f9fbe Fix: safe temp staging and downloadFile error handling (#479)
AI assistance: implemented with Cursor Grok 4.6.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-28 05:43:04 +05:00
63b04e2530 Release: CLI v3.6.1, extension v1.3.3
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
cli-v3.6.1 skill-v4.1.2 ext-v1.3.3
2026-08-26 11:02:54 +05:00
380cfcb08e Release: skill v4.1.2
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-26 11:02:54 +05:00
github-actions[bot] ba68dce41e Sync generated provider output 2026-08-26 05:31:15 +00:00
Abdul WahabandGitHub 8f416aa760 Merge pull request #653 from pbakaus/fix/652-root-relative-stylesheets
Fix: resolve root-relative linked stylesheets in static detect (#652)
2026-08-26 10:30:46 +05:00
Abdul WahabandCursor daae1d4117 Fix: reject root-relative .. segments and warn per scan
Dot-segment hrefs like /../outside.css could leave the project, and a process-wide warning set hid missing-sheet notices on later detectHtml calls.

AI assistance: implemented with Cursor Grok 4.6.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-25 19:47:54 +05:00
Abdul WahabandCursor 2b88aa5231 Fix: resolve root-relative linked stylesheets in static detect (#652)
Root-relative hrefs like /static/app.css were treated as OS-absolute and silently dropped, hiding contrast findings.

AI assistance: implemented with Cursor Grok 4.6.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-25 19:34:55 +05:00