Removes 43 small Sonar findings (unused locals, dead helpers, a misread comment); behaviour unchanged. CHANGELOG entry was already swept into 9f78a15.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Real-library audit (270 records) traced the data damage to:
- identity matching on ANY shared token ("Zwerg", "der Zwerg", "Mann") with
"longer text wins" merging (Arthag b02 = Kolon's species/relationships), and
- csRosterCanonicalName renaming a sheet to the first cast name among its
aliases, which saved 16 whole-sheet copies (Zwerg/Kolon = Arthag b03,
Fremder = Mann, Alchimist = Promos ...).
Fixes:
- static/js/character-identity.js + core/character_records.py: generic labels
are never identity evidence; csFindMergeKey, csConsolidateAliasDuplicates,
csRosterCanonicalName, clSameIdentity use it; own name always wins; clUpsert
writes to the exact-name record before any alias scan; no seed rename onto a
name that has its own record.
- _charsheets_parse: in cast-target mode drop other cast members' names from
aliases / first / last name (Kolon: "Sharraz Garthai"), strip reasoning
leakage ("Warte:", "Der Text sagt ...") from every text field.
- _character_scene_evidence: only a quote naming the character is used,
otherwise its own mannerisms (16 panels showed another character's scene).
- _character_age_category: Junge/Mädchen/boy/girl, number words, Sommer/
Winter ages, evidence clause, age-tagged quotes; "15 Jahre älter" is no age.
- scripts/audit_character_records.py (read-only) and
scripts/clean_character_records.py (dry run by default, --apply backs up).
Tests: tests/test_character_record_hygiene.py, tests/character-identity.test.mjs.
Docs: architecture/character-extraction.md, Manual, CHANGELOG.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Extraction notes in race_species that mention another character's species
("Mensch (oder Zwerg, ...)", "... 'Der Zwerg' wird separat erwähnt ...")
switched on the dwarf body lock (short legs, full beard) for human characters
and carried a sentence about another character into the Subject clause.
Confirmed on the real library: Marrad, Kolon and Arthag (book 02).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Bind the consistent-image Idempotency-Key to the character request so a reused
key cannot return another character's job; add back-to-back and concurrent
two-character regression tests.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
The story moment was a ~5,400-character prompt whose period rules sat at
the end, out of reach of the 4-step model; it opened with "ears clearly
visible" and asked for studio photography by a photographer with a real
actor, and drew a modern man with headphones and a camera in a garden,
captioned with pseudo-text. The prop tile was a stock catalog photo. The
negative prompts were inert because those samplers run at cfg 1.0.
Story moment and signature-item prompts are now short, world-first and
positive-only: The Dark Eye, 900-1300 AD and the book profile's setting
(never the title), the same identity, appearance and costume as the
turnaround, the book moment, a period background and a hand-made,
unmarked world; the item is the character's own, in the craftsmanship
and colours of their costume, on a table in a medieval room. Text and
modern objects are added to the scene and prop negatives.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The sheet composer drew light lines between the three poses and between
the top and bottom rows, cutting through capes and swords.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
- Quality run: per-page missed-text recovery, guarded OCR re-read and a pixel audit
(uncovered ink, overlapping boxes, clipped box edges); report saved as quality_report.json
- Thumbnail grid: quality-stage colours, flag badge, live per-page indicator for every
batch step (OCR, detection, figure fixing, quality run, audio)
- Pages can be approved as advertisements (not narrated, skipped by quality run)
- Driving mode: +/-15 s, seek bar, playback speed, text and image toggles
- Plus the previously uncommitted 1.53.5 magazine/OCR work in the same tree
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Bundles this session's magazine review work: a single "Draw region" tool
replacing six preset-kind buttons; "Table" as a real, non-narrated region
type; uniform auto-OCR for every text-like drawn/re-read region with a
Tesseract fallback when the vision OCR backend is unreachable; a thumbnail
grid view and inline title editing for the article list; batch
approve/reject; standalone MP3 export with embedded title/author/album,
lyrics and cover art (adds mutagen); "Remove all boxes" for starting a
tangled page from scratch; Approve advancing straight to the next article;
a merged, sticky review toolbar; and a fix for stale image previews after
resizing a region's box.
Also fixes several character-portrait rendering biases confirmed live
across this session's DSA audiobook cast (routes/conversation.py): modern
or bald/receding hair regardless of established coverage, armored women
rendering masculinized, duplicated/malformed weapons, a ranged weapon
rendering as a firearm due to a German compound-word regex miss, an
established dwarf rendered with human proportions, and occasional extra
hands or lost non-human species in scene panels.
See CHANGELOG.md [1.43.0] for the full list.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Portrait backdrop measured 0/4 -> 4/4 plain on the failing character, no
change on the one that already passed. After the portrait passes, the vision
model describes hair, facial hair and eyes, and the turnaround and story
prompts are rebuilt with it -- a character with no hair in his sheet got a
different haircut on the sheet and failed the same-person check 3/3.
Costume cut and colours restored for armed characters. v1.41.0.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Measured with the image check: full-body turnarounds 0/5 -> 10/10 (Karyla),
12/12 on Karyla, Darrag and Eolan after the face fixes. The 4-step model
loses the tail of a ~3000-char prompt. Scars are left out of image prompts:
any scar wording, even "fully healed", rendered as fresh gashes. v1.40.0.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The job checks the portrait crop, then the turnaround, story panel and
same-person against the sheet, re-renders on failure (up to 3 attempts) and
keeps the attempt with the fewest faults. ReActor transfers the profile's face
onto the turnaround and the largest face in the story panel. If the checker is
down, retries stop and the pair is marked unverified. The outcome is saved
with the pair and shown on the character page.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The model only reports observations; expectations come from the sheet and the
comparison is in code. Fail-safe: an unreachable checker or unreadable answer
is a failure. Calibrated 14/14 on panels with known defects using the already
loaded LLM; Ling 3.0 Flash VL (free) scored 8/14 with 6 unreadable answers.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Each fix pins a defect seen in a real render. The species test read the raw
sheet field, so a hedged "Mensch (oder Halbelfe...)" matched the elf pattern.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Drawing front/side/rear separately with the edit model reproduced the exact
failure the triptych was introduced to fix: three near-identical front views,
mixed styles between panels, cropped bodies, and the wireframe pose guide
rendered into the costume.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Verify / recast now run span-natively (no text re-emission): a second differently-windowed
pass marks lines agreed/disputed and records the other answer, without changing any speaker
(~9 min vs ~49 min). Measured on the real pipeline, overruling disputed lines with a reasoning
adjudication made them worse (66.5% -> 61.4%), so that step was removed; agreed lines were 83%
right vs 48.5% for disputed ones, which is the signal used for confidence and review.
Auto-repair no longer runs after a span cast; segments carry a spanId.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
- fix: base-appearance matched pair lost its concept image + metadata on reload; visual save
wrote base concept art to the record root; one save path for base and forms now
- fix: extraction no longer lets the LLM author image_prompt (source of avatar/concept drift);
avatar-only generation uses the deterministic prompt and flags an existing pair
- fix: prompt writes and Physical/Clothing edits go to the active form; review endpoint checks
each form's own pair; fingerprint parity with the browser incl. visual_* overrides
- feat: appearance forms panel (add/rename/delete/show, per-form stale flag, generate one/all)
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Split the book into narration/dialogue spans from its own quotation marks and ask
the LLM only who speaks each dialogue span (POST /api/attribute-spans), so text can
no longer be fused, dropped or duplicated and a novel takes ~10 min instead of ~4 h.
Book 1 vs the hand-corrected reference: every-word-right 87.0% -> 92.3%, type
agreement 93.6% -> 97.4%; Books 2/3 (not tuned on) 90.8% / 89.9%.
- static/js/audiobook-spans.js (pure, unit-tested) + audiobook-cast-spans.js
- core/attribution_spans.py, route, tests; scripts/score_attribution.py
- default on; localStorage ab-span-mode=0 restores the classic engine
- architecture/audiobook-attribution.md, Manual, CHANGELOG 1.32.0, TODO
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
