Answering whether the caption merge breaks the page-space key in
eval/chapter-truth.json. It does not. _merge_plan only groups adjacent
fragments and slice_webtoon cuts at gutter midpoints, so a vstacked panel's
[x, y0, w, sum(heights)] is the exact page region.
The defect is one line up. slice_webtoon skipped any segment shorter than
min_seg instead of absorbing it, so this chapter's 116 panels have a 62px hole
between panel_order 70 and 71 and lose 18px at the strip's end. A merge
spanning that hole reports a bbox 62px short of the page span it covers, and
every consumer mapping a detection back to the page is then wrong by that much,
silently. The 62px held the credits line, found at p_050.png row 338.
A short band is now held and absorbed by the next segment, or by the previous
one when it is last. min_seg still suppresses a tiny panel and no strip pixel
is discarded. The self-check asserts the bboxes tile the strip end to end.
Checks: worker_crop.py self-check passes and fails on the old code, where the
first band starts at 49 instead of 0. ruff check . exits 0.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
ARCHITECTURE.md step 0. eval/chapter-truth.json holds the 38 occurrences the
user walked crop by crop on the 19:44 run of 2026-08-12, and audit_registry.py
now prints purity per cluster and fragmentation per person against it. All six
baseline numbers reproduce.
Rows key on page-space geometry, purity is a share, and fragmentation is a
count of ids, so nothing in the file names a panel_id or a character_id. The
fifth cycle re-crops and calls /characters/reset, and the file survives both.
That was the ordering trap in the handoff.
NEXT.md said 2 of woman B's 9 crops were really woman A and never said which.
They are panel_order 31 and 33, identified from p030 and p032.
Four fixes to the audit itself, all pre-existing:
- 20 characters counted where 14 are live and 6 are merge losers kept on purpose
- the assignment spread keyed on name, so the two Seonhos summed into one line
- the default worked example was panel_index 7, a panel vision skips. NEXT.md's
"panel 7" is panel_order 7, one lower
- nothing about skipped panels. 41 of 116 are skip=True, four checked and all
four correct, and they hold 28 of the chapter's 122 dialogue lines
That last count is the measured case for an offscreen speaker_ref kind: 23% of
dialogue sits on panels with no character to attribute to.
Checks: audit_registry.py --selftest covers the IoU match, the greedy tie-break
and the purity maths with no database. ruff check . exits 0.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
merge_faceless_captions had been written and never called; both crop
endpoints called the non-destructive context_fragment_links instead, with no
decision recording that choice. Wiring it changes panel count and every panel
index, so the chapter needs a re-crop with the panels prefix cleared first --
crop_webtoon skips an upload when the key already exists, which is right for a
resume and silently wrong after a slicing change. Noted at the line.
It does not cover the head-in-one-shot body-in-the-next split that prompted
the question. _merge_plan only folds a fragment that has text and no face.
ARCHITECTURE.md is the target shape from the user's design, with what exists
against each section today. Nothing in it is built.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The gallery gemma chose from was the union of the tracklet members' cosine
shortlists. Cosine cannot separate people on this data, so a metric that
cannot tell two men apart decided who gemma was allowed to consider, and the
right character was often not on the list.
The gallery is now the live cast: gender-compatible rows from
get_known_characters, named first, capped, re-read per tracklet so a minted
character is visible to later ones. Every crop reaches the resolver now,
including one whose cosine top-k was empty; those used to be dropped.
worker_vision spreads reference images across a budget instead of sending 3
per candidate, so a 9-character cast costs 9 images and not 27.
Ran on a GPU, 19:44-19:52 UTC. The lead's assignments drop from 36 to 16 and
14 of the 16 are him; the other two are art inside a panel.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The user checked the lead's crops. LIM SEONHO's 36 assignments cover at least
six different men, a chibi and a cat, so 36 of 68 is a bug. 22 came from
native resolves and 14 from reconcile merges.
Two fixes are written in the orchestrator repo, tested, not deployed and not
run on a GPU. `link_tracklets` caps a tracklet's panel span, because `window`
bounded each pair while transitivity was unbounded and the lead's 22 native
assignments came from tracklets spanning 22 and 30 panels. And one shared
appearance tokenizer drops generic words, because whole chains hung on the
word `short` and one pair on the word `hair`.
The obvious third fix is ruled out by measurement. Over all 22 crop
embeddings, the cat scores up to 0.82 against men, two different men score
0.93, and the highest pair is 0.96. No threshold separates them, so
crop-to-crop cosine is not a link signal.
Item 1 of the agreed plan, sending the live cast instead of a cosine top-k
gallery, is not started.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
`_bbox_to_pixels` sorts each coordinate pair after clamping. Run B returned
`p007 person_1` as `[226, 417, 130, 551]`, x1 > x2, which cropped to nothing
and lost that detection silently. The third GPU cycle came back with 0
degenerate boxes over 119 detections.
The plan's first item cannot run as written. All 145 rows of `identity_labels`
belong to chapter 8ca8249b, a different manga. Chapter 7c944dd4 has none, so
`/review/identity` reports `accuracy: null`. Scoring 8ca8249b gives 7/138 on
an identity run that predates every fix.
The cycle also settled the coverage question. All 68 assignments landed on
face-bearing detections and none on a gated one, so recall among face-bearing
detections is 96%, up from 82%. Coverage is the `has_face` gate and nothing
else. What is now open is precision: the lead holds 36 of 68 assignments.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
No worker code changed. This is the evidence from the 2026-08-12 16:39 and
17:38 runs, and where each finding now lives.
The fourth session's four identity changes all work on real panels. Panel 7's
two wrong bindings are gone. The lead going unassigned there is correct and
was measured, not assumed: face_detect finds one face on the whole panel at
conf 0.599, nothing else above 0.056 even at a 0.04 threshold, and the crop
shows him drawn from behind.
Two decisions, both closed: a roster name is a guess so it never reaches
detection, and merged_into is exactly one hop deep. Two caveats, both open:
detection can order a bbox backwards (1 in 117), and identity coverage has
fallen on every run since the gate landed (70 -> 61 -> 50).
Coverage is the thing to settle next, and not by reading the number.
identity_labels already holds 145 rows of ground truth.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The registry reset deleted Lim Seonho and character_afa7623b, so there is nothing
to merge or split until the rerun mints a new set. What was done instead is the
safety net for that rerun, since reconcile runs inside it: a merge retires the
losing row rather than deleting it, and records which assignments moved.
Half-closes caveats/audit-open.md#destructive-reconcile. The unmerge path and the
split stay unwritten on purpose, with the revisit trigger named.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Two identity fixes, neither yet run on a GPU.
has_face, the extras gate: fixing the bbox coordinate space made extras worse,
because crops finally landed on their subjects and a background extra bound to
the lead at 1.00. /vision stamps has_face per character using face_detect and
_pair_faces_to_present, so containment and its margin match the speaker path.
Identity skips has_face is False before it crops or embeds. Fails open on a
missing or raising detector, and gates on `is False` so an older vision blob
behaves as before.
The NONE mint: /identity/resolve now writes each crop's embedding to the crop's
key with a .npy suffix and returns emb_uri. The orchestrator cannot compute an
embedding of its own (siglip and gemma cannot both be resident), which is why it
was clearing a deliberate NONE instead of minting an anonymous character.
Also: audit_registry.py, and the tmux respawn-window trap, which
leaves a bare shell rather than re-running the window command.
decisions/identity-bbox.md#face-gates-enrollment
decisions/identity-bbox.md#none-mints-an-anonymous-character
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The rebuild after 1457556 came out byte-identical to the broken file,
which proved the xfade fix never runs for this chapter. An all-cut chapter
goes down the concat demuxer with -c copy, which writes the output in the
FIRST input's time_base and reinterprets every later packet in it. 14 of
49 clips are 30/1 at 1/15360 against 35 at 25/1 at 1/12800, so those 14
play 15360/12800 = 1.2 too long with their audio untouched. collage_cmd
hardcoded -r 30 and yesterday's FPS sweep missed it.
collage_cmd now emits -r FPS, and assemble probes r_frame_rate across the
clips and routes mixed rates through the re-encoding tree. Rebuilt
chapter.mp4 is 364.120s video against 364.122s audio at 25/1, from
436.392 over 363.675.
Also settle the bbox coordinate space, measured over all 113 detections:
47 boxes have x2 past the 900px panel width, none has y2 past 1000 on
panels up to 2307px tall, and the range is exactly [0, 1000]. It is
gemma's normalized grid, not pixels, whatever the prompt asks for.
/vision converts before returning, which fixes identity's crop, the gated
face pairing that was comparing pixel face boxes against grid boxes, the
set-of-mark boxes and the review UI at once. Checked by eye on panel 7:
five of six boxes now land on their subject, including the foreground
character who had no identity.
The registry still holds boxes and embeddings enrolled from the wrong
space. vision and identity have to re-run, which is GPU work and was not
started.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
_xfade_chain positioned every transition using _audio_dur, which probes
format=duration, which is max(video, audio). A clip's audio outlasts its
video by about a frame, so the offset accumulator crept ahead of the real
picture timeline. Once the creep exceeded the transition width, xfade
emitted the transition and silently discarded the second input and every
clip downstream, exiting 0 with nothing on stderr. That is the whole of
the shipped chapter's 436.39s of video over 363.67s of audio.
Offsets now come from min(video, audio). Every input is floored to a
whole frame count and trimmed on both streams, so the accumulator tracks
the real timeline instead of estimating it. _check_assembled verifies
each encode against the predicted length and against its own audio,
because both assembly branches drop stream time without failing.
Verified over the 49 real clips of chapter 7c944dd4: the round that
turned 359s of video into 100s now loses 0.85s, and the chapter comes out
358.76s video against 358.76s audio.
The single-item passthrough was not the cause. Two round-0 groups of 8
fresh clips collapse without one, recorded void in decisions/.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Somebody watched chapter.mp4 for the first time. Two failures came out of it
that no stage counter could see.
chapter.mp4 is video 436.39s over audio 363.67s, so narration finishes 72.7s
before the picture. The 49 clips are clean: all 25fps, video and audio agree
to 0.03s, summing to 363.6s. A per-round probe puts the loss in the final
round of _assemble_batched, which turns 359s of video into 100s while the
audio survives. Round 0 is correct. Round 1 differs by holding a 7th input,
the leftover clip that skips encoding, so the tree mixes concat output, xfade
output and a raw clip. Not fixed.
worker_render.py gains an FPS constant, fps normalization in the xfade branch
to match concat, _stream_dur, and a self-check that compares video against
audio instead of asserting the file is non-empty. That old check is how a 20%
sync failure shipped. The fps inconsistency is real but not proven to be the
shipped cause. Pinning -r on the output was tried and reverted: it drops
frames to force CFR, which the concat branch comment already warned about.
Panel 7 checked against the art has zero correct identity bindings out of two,
and Seonho, the one character who matters, is unbound. bbox values are
consumed as absolute pixels; on a 900x1650 panel that puts all six boxes in
the top third, two inside a speech balloon. Identity therefore embeds crops of
balloon edges and window frames, which is how confidence 0.9 lands on the
wrong person. The colleague has no name in the story and was labelled Choi
Haeseon; that row holds 25 of 26 assignments, so it is the label the pipeline
stamps on any unnamed woman.
Four caveats added. Two earlier claims are withdrawn in place: rescaling bbox
by 1000 does not make the boxes correct, and the constraint is not 16 nameless
rows needing names. Cast profiles already exist, since all 53 rows populate
ref_image_uris and embedding_uri, but they are enrolled from the wrong crops.
worker_render.py self-check passes. No pipeline ran.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The run completed: chapter.mp4 at 50MiB from 49 clips. layers reported
completed 116/116 with an empty bucket, so nothing has parallax, and the completed
job still carries the error string from a failure three resumes earlier. Both
recorded as caveats, neither fixed.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Adds decision entries for the unpaired set-of-mark label, the interjection
verifier false positive, and the vision-blob clearing bug, plus the per-run
speaker audit script used to measure the chapter.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
_annotate_speaker_methods stamped `tail`, the highest-trust provenance, on any
line whose speaker matched a present local_id, at gemma's confidence of 1.0. No
balloon was read. Three of three sampled two-character panels had the speakers
swapped, so a multi-character guess is now dropped to unknown, and a solo-panel
guess is kept as model_solo at 0.7.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The baseline run died in `script` at 87/116. Every lost beat cites
`unsupported-proper-noun: ['Choi', 'Haeseon']`, because verify_script puts the
full name in the allowed set and then tests single capitalized tokens against
it. No fix applied.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XD7cAy81MZrc7gCr6aZGWr
Panels, wavs, layers, clips, and the chapter mp4 leave the `manga` bucket for
`panels`, `audio`, `layers`, and `video`. The key under the bucket is unchanged,
so every reader that derives the bucket from the first path segment keeps
working. The orchestrator half moves in the same commit, per invariant 7.
The 2026-08-11 chapter run proves the split for `raw` and `panels` and produced
the first quality read on speaker attribution, which is wrong in every sampled
multi-character panel.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XD7cAy81MZrc7gCr6aZGWr
#117 done: stowage was dead on an arm64 digest pin, not a MinIO fault.
#116 staged: rustfs runs on 9010/9011, buckets not mirrored, no cutover.
Also logs the ISP port 80/443 interception that made three external
reachability measurements worthless, so the next session does not repeat them.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Implements every P0 from AUDIT.md plus four P1s, across both halves of the
pipeline. Verified by CPU-only self-checks and the orchestrator test suite.
No GPU work ran and no pipeline ran.
workpc:
- worker_scene: read speaker_ref, not the rewritten speaker field. Every line
narrated as "Someone" before this. Emit `actions` for the verifier.
- worker_script: declare beat + verifier_feedback (pydantic dropped both, so
the retry was blind) and render them as a repair prompt.
- worker_vision: gate face->identity pairing on containment, assign globally
shortest-first, map an out-of-range resolver index to `unresolved` instead
of minting a character, parse JSON with raw_decode.
- session_manager: tear down a server whose lease vanished mid-load, and spawn
the supervisor respawn unlocked.
orchestrator (edited in place, NOT committed there):
- tracklets: canonicalize gender, add co-presence cannot-links, block
transitive bridges across a hard constraint.
- correctness: stop failing valid narration on sentence-initial capitals and
short quotes; read action evidence from the singular key.
- db: stop orphan flags leaking into every chapter; resolve by flag id.
- service: TTS returns instead of raising under GATES, auto-resolves under
autonomous mode; job admission control; registry names on dialogue resume.
- session_proxy: queue on 409 instead of stealing the lease; run heartbeats.
Docs restructured per the repo-structure layout: CLAUDE.md is a pointer table,
NEXT.md replaces HANDOFF.md, plus ROADMAP.md, JOURNAL.md, decisions/ and
caveats/. AUDIT.md now points at those instead of restating them.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XD7cAy81MZrc7gCr6aZGWr
kami