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>
The preview carries each page's regions (percent of the page, type, reading
order) for the reading pass and the labelling pass, drawn over the page image
with a legend. A server restart that killed the import left it "running" for
ever; the status route now reports it as failed. v1.42.0.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
original_text is now a Block field, so paths that rebuild blocks keep it
instead of crashing. Undo snapshots are sealed with a digest of the saved
state and refused once anything else changed; actions without their own undo
point clear the Undo button. v1.41.1.
Co-Authored-By: Claude Opus 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>
Bulk delete/type for a click- or rectangle-selected set; every destructive
region change returns an undo token (one level, refused once something newer
happened); text inside a region that becomes a picture is folded into it.
TODO: model-based layout detection (PP-DocLayout, LayoutReader) with licence
notes. v1.39.0.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The review selection now follows deletes, merges, splits and text-to-image
changes; approve sends only existing ids and no longer overwrites the image
list with a stale one; deleting a region removes it from articles. v1.38.1.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Split at the cursor and merge-with-next keep article membership right; typed
letters in the editor never fire shortcuts; focus returns to the same row
after a redraw. v1.38.0.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Rules sized on a real 204-page issue before writing them; each re-types
(not read aloud, reversible), none deletes. A run-on author line's sentence
becomes its own paragraph instead of being glued to "the next paragraph",
which was right in only 1 of 5 real cases. Runs on import and re-OCR, and on
demand with a layout backup. v1.37.0.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
A hand-ordered page is locked: Fix reading order, type changes and newly drawn
boxes leave it alone until Automatic order. v1.36.0.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Columns are found from where column-width text starts, not from the whitespace
between them (loose OCR boxes shrank one gutter to 4-6 pt and a pull-quote
bridged it, collapsing page 38 into one interleaved column). Headlines get
their own band, pull-quotes are read at the end of the page. Measured over a
204-page issue: 89 sentence continuations kept vs 85.
Each review row gets a type picker (text kinds, page number, source, ad,
image) and its own delete button; text<->image conversions keep the region
in its article. Fix reading order re-reads existing issues without OCR and
leaves hand-ordered pages alone. The shared confirm dialog is now an
alertdialog for screen readers. v1.35.0.
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>
A cold-booting model server would otherwise time out the first passage into tag guessing.
Documents that the custom attribution prompt applies to the classic engine only.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Pooled over three hand-corrected novels (~54k spoken words): agreed 82% right, disputed 48%,
Unknown ~0%, unverified ~76%. The old heuristic bands claimed 16% for lines that were 62% right
and tag/role signals did not discriminate in span casts; classic casts keep the old model.
Co-Authored-By: Claude Sonnet 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>
- fix: Edit boxes and page-nav controls were dead clicks (handlers never exported
to root); resize from any edge/corner instead of only bottom-right
- feat: two-page spread in review (page images above, OCR lists beneath)
- feat: searchable voice picker for narrator and podcast hosts
- feat: Prepare audio synthesises the whole article ahead of playback; playback
also stays three sentences ahead
- fix: sync index.html cache-busting version with VERSION (was stuck at 1.26.12)
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Adds "Edit boxes" mode to article review: drag an already-detected
region to move it, its corner handle to resize it, or press its x to
delete it -- for correcting a box the layout engine got wrong, not one
it missed entirely ("Draw it" still covers that case). Moving or
resizing opens a confirm panel; "Save" keeps the region's existing
text at its new position, and for text regions "Save & re-OCR" reads
the corrected area again and replaces the text.
New core/magazine.py update_region()/delete_region() and PATCH/DELETE
/api/magazine/{doc}/pages/{page}/regions/{block_id}. An image region
is re-cropped from the page render whenever its bbox changes, since
its saved file is exactly that crop.
Live-verified against the real ingested c't KI Wissen 2026 magazine:
add -> move -> move+re-OCR (correctly kept old text when the corrected
area had nothing readable) -> delete -> confirmed gone, repeat delete
404s.
275 tests passing.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
_docker_get_json/_docker_post called sock.connect(sock_path) a second
time after _docker_connection() had already connected the socket --
sock_path was never defined in either function, so every call raised
NameError. Surfaced in the UI as every engine card reporting "Not
installed" and the Active OCR Engine model dropdown reporting "Not
Found" regardless of what was actually running, found while diagnosing
a user report of that dropdown. Docker socket API calls (list/status/
start/stop/restart) were affected for every engine card, not just OCR.
Added tests/test_docker_client.py, which did not exist before, to
catch this class of regression going forward.
Also records a request to make the magazine ingestion "watching it
work" panel draw detected region boxes live over the page image as
each is classified, instead of today's static page-image-plus-text-
list (TODO.md; no code change for that yet).
254 tests passing.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Adds a "Describe" action per figure in article review: sends the cropped
image to the configured vision engine (with fallback) for a type-aware
one- or two-sentence description -- a chart gets a prompt about what it
measures and its trend, a table about headings and what stands out, etc.
Editable before approval. A new "Read figure descriptions" toggle in the
reading controls speaks these where they occur; purely additive, off by
default, and a figure with no description behaves exactly as before.
New core/magazine.py describe_visual_region()/_chain() reuse the same
reliability guards as page OCR (repetition-loop detection, sentence-
boundary truncation). New routes: POST .../images/{id}/describe
(background job), PATCH .../images/{id} (manual edit), descriptions=1 on
the article-text endpoint.
Live-verified end to end against the ingested c't KI Wissen 2026
magazine. Also found and documented a real, config-dependent limitation:
the currently-configured primary vision engine is transcription-only and
returns empty content for any descriptive prompt (confirmed with three
different prompts) -- not a code defect, but description generation
needs a genuinely caption-capable engine reachable as the fallback.
251 tests passing.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Connect and "Use as LLM" on the LiteLLM Gateway card now resolve that
card's own saved key (engine_api_keys[name]) server-side in
routes/docker.py, ahead of the old global llm_api_key fallback. The
browser can no longer reliably forward a saved key at all -- it's
masked to "__configured__" in every /api/settings response the moment
it's saved -- so relying on a frontend-forwarded header alone left
Connect silently using a stale global key after LiteLLM's own key was
rotated, surfacing a misleading /api/version 404 instead of the real
401.
"Use as LLM" now goes through a dedicated /use-as-llm endpoint that
saves the exact credential Connect just verified (llm_url normalized
to .../v1, llm_api_key copied from the card), rather than a
separately-typed value that could drift again.
Also documents per-user provider-key storage as an explicit item for
the deferred multi-user/identity planning pass.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
No code change. User set explicit priority for upcoming feature work:
Magazine reader roadmap first, then the character-identity system,
then audiobook speaker attribution. Recorded in TODO.md so it survives
a context reset. Deployment and the deferred multi-user initiative
stay explicitly parked, not part of this order.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
The NFS blocker from TODO.md's deployment entry is resolved (export
set up by the user on the DGX); picks up from there and completes the
deployment end to end.
- Mounted the DGX's TTS_Voices export read-write on the NUC at
/mnt/dgx-tts-voices, persisted in /etc/fstab -- confirmed writable
and confirmed the NUC instance sees the DGX's real voice library
(344 voices), not a separate copy.
- Deployed by rsyncing the working tree from the DGX (excluding .git,
config/, logs/ and other local-only paths) and building the image
directly on the NUC, rather than pulling ghcr.io/martin-b78/... --
that registry copy turned out to be both several versions stale and
private with no credentials configured on the NUC, and the source
was already right there to build from.
- Found and fixed a real gap while wiring it up: vision_ocr_url and
vision_ocr_fallback_url default to host.docker.internal, which
resolves to whichever host the container is running on -- correct
on the DGX itself, silently wrong on the NUC (would have pointed at
the NUC's own nonexistent OCR engine). Pinned both explicitly to the
DGX's LAN IP via environment overrides.
- The container crash-looped on first start (sqlite3.OperationalError:
unable to open database file) because docker compose had created
config/ and logs/ root-owned under this session's root SSH access to
the NUC, while the image's app user is uid 1000 -- chown -R 1000:1000
fixed it.
- New docker-compose.nuc.yml, tracked here as the reviewable reference
for that host (docker-compose.yml stays the DGX's own -- different
build/network/socket-proxy shape). Deployed to the NUC as its own
docker-compose.yml, since that host has no .git checkout to diff
against, only the rsynced tree.
Verified: container stable (no restart loop), HTTP 200, settings
confirm all four engine URLs correctly resolve to the DGX, voice count
matches the DGX exactly, restart policy is unless-stopped.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Two reports from the same mobile session tied together: a voice-library
crash ("fmtDbfs is not defined") and a save button reporting "No audio
ready" despite a file being correctly loaded and trimmed. Root cause
was the same in both -- the module loader fetched each JS file once
with no retry, so a single dropped request on a flaky connection left
that module's functions/variables undefined while every other module
kept executing anyway, producing confusing symptoms nowhere near the
real cause.
loader.js: _load() now retries up to 3 times with backoff before
rejecting. If a module still can't load after that, the app says so
plainly via a toast (or a plain DOM banner if even utils.js failed to
load) instead of silently revealing a partially-broken page. Wired into
both the core-module fallback path and ensureFeatureModules' lazy path.
Loading every section of the app at a 375px viewport and checking for
elements running past the viewport edge (all now 0) found eight real,
independent layout bugs, each with a distinct root cause:
- .section-head's mobile wrap rule targeted .section-header, a class
nothing in the app uses -- dead since it was written. Every section's
icon/title/action row (e.g. "+ New voice") ran off-screen unreachable.
- The synth-mode toggle and Clone-a-Voice source tabs' icon-only mobile
rules matched a <span> wrapper the markup didn't have. Added it, plus
aria-labels so hiding the text doesn't erase the accessible name.
- voice-design.css loads after style.css and re-declares
.design-sample-grid unscoped -- style.css's mobile override always
lost the cascade regardless of viewport. Moved the override to the
file that actually wins.
- Three separate minmax(380-440px,1fr) engine-card grids couldn't fit
one column under ~460px. Collapsed to 1fr with min-width:0 on the
items -- the column fix alone wasn't enough, since a grid item's
content-based min-width is still a floor even inside a 1fr track.
- The routing test row (450px+ minimum) and the conversation input bar
(a single non-wrapping flex row for text field + mic + gate + three
toggles) now wrap under 767px.
- Try It Out's EQ sliders shrank to fit beside their toggle instead of
ever wrapping below it, overflowing their own squeezed container.
Forced onto their own full-width line.
Verified with a Playwright sweep of all 16 sections (0 overflowing
elements, 0 console errors) plus the existing 225-test suite and the
frontend syntax gate.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Confirmed live: re-ingesting c't KI Wissen 2026 with a local Qwen VL
engine, page 18's chart transcription degenerated into "das Produkt,
das Produkt, das Produkt, ..." repeated hundreds of times, filling the
whole response budget -- and was accepted as real region text, which
would have been narrated verbatim.
The codebase already had two narrow signatures for specific observed
failures (a formatting-instruction echo, a fabricated LaTeX loop), both
scoped to the plain-text fallback path only. Added a general detector
(_looks_like_repetition_loop): any short phrase containing a real word,
repeated 8+ times immediately back-to-back. Deliberately excludes
patterns with no letters -- a dot-leader contents line, a repeated
number sequence -- which are legitimate and must not be flagged.
Applied at both call sites: vision_ocr_page (the labelled-region path
most engines use) and _whole_page_region (the plain-text fallback).
Treated as a failed call in both, so vision_ocr_page_chain's existing
fallback (secondary engine, then tesseract) gets a real chance instead
of garbage being accepted as the page's transcription.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Real failures found by re-inspecting a fresh re-ingest of c't KI Wissen
2026 after the previous figure-boundary-snapping release: a bar chart
was still truncated to roughly a third of its real height, and a
chart's top edge cut into an unrelated paragraph above it.
Root causes, each independently confirmed against the real page render
before fixing:
- A bar chart's bars/gridlines/axis labels rarely reach the "solid
ink" density a photo does (measured 0.25-0.5 vs the 0.55 threshold),
so the existing pass anchored only on the one fully-solid element
(the zero-line) and never grew further. Added a second, looser pass
that grows an anchor -- or the seed itself -- through any real mark
at all, fenced by the same blocked cells.
- Anchor selection ("which solid component does the seed overlap
most") was seed-size-dependent: a small seed touching only the
zero-line anchored there, but re-running the SAME function on the
box it had just produced -- now large enough to also touch a dense
axis-label strip -- picked that instead and shrank an already-good
box back down. Fixed by dilating the solid mask and labelling once,
BEFORE any seed is considered, so which components count as one
figure is a property of the page alone.
- A merged bounding box can enclose real text sitting between two
components even though neither component's own cells touched it (a
rectangle union, not the components' actual shape). Added
_trim_blocked_edges() to pull each edge back to the nearest text
wall found searching outward from the box's own centre.
- Two adjacent figures fencing each other's growth made each one's
result depend on the other's CURRENT box -- for two dark photos
sharing a caption strip, this never settled, swinging by over 100pt
call after call. snap_visual_bboxes() now re-seeds every visual on a
page from every other's last result for a bounded number of rounds,
deciding same-graphic ambiguity once up front (fenced against the
original seeds, before any iteration) so two disputed seeds can't
mutually fence each other into a tidy-looking split instead of being
recognised as the same disputed claim.
- A result is now only accepted once it reproduces itself when fed
back through the same rules (IoU-checked), and the minimum
seed/graphic overlap for repositioning a badly-offset box was
lowered slightly -- it was narrowly rejecting some real cases.
Verified against the full 204-page/147-figure document: idempotency
holds except for one confirmed non-convergent pair, which now lands on
the same deterministic answer every run instead of continuing to
drift.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Resumes an in-progress, uncommitted change from a previous session: the
live "page image + recognised text" preview shown during ingestion was
reworked to render formatted HTML (styled headings, a figure
placeholder) instead of a plain-text dump, but was left with a
duplication bug, dead code, inline styles, and no tests.
- Fixed duplication: a figure block's own transcribed text (usually its
on-screen UI copy) was rendered as an ordinary paragraph in addition
to the new figure placeholder box. Figure/chart/table/code blocks are
now represented only by the placeholder.
- Furniture/sidebar/pullquote/ad text is shown muted instead of being
dropped with no replacement, and is never promoted to a heading
regardless of font size.
- Factored the formatting logic out of the progress closure into a
standalone, unit-tested _render_ingest_preview_html().
- Replaced dead getattr(bbox, "y0", ...) calls (bbox is always a plain
[x, y, w, h] list) with direct indexing, moved statistics/logging
imports to module level, switched manual character replacement to
html.escape(), and bounded the preview by an accumulated line budget
instead of a blind slice that could truncate mid-tag.
- Replaced inline style="..." with CSS classes matching the panel's
existing dark console treatment.
- The frontend now always uses innerHTML (every text node is escaped
server-side), dropping the startsWith('<') content-type sniffing.
- Marked the preview panel aria-hidden -- decorative, and would
otherwise churn noisily for screen reader users on top of the
adjacent progress bar.
Verified against the real c't KI Wissen 2026 layout: a figure's raw
OCR text no longer appears twice, a real headline renders as <h3>, a
footer/pull-quote render muted, and all text is correctly escaped.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
No code change. Added to TODO.md:
- Magazine contents view (#s-magazine): logged three candidate layouts
as open options rather than picking one -- three-column page/text/
figures, synthesis-state-and-inline-play (the recommended quick win
under any layout), and a flipbook with content columns underneath.
Needs a decision before implementation.
- Browsing free PDF magazine sources: the two sites given as examples
(freemagazines.top, pdf-magazines.org) redistribute current commercial
titles without licence, so no scraper was built against them. Scoped
instead against OPDS catalogues, archive.org's public-domain
periodicals, publisher-run free issues, and open-access journals.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
A vision OCR engine grounds a figure far less precisely than it
transcribes one. Over all 138 figure regions of a 204-page issue the
transcribed contents were right while the boxes were routinely offset,
undersized, or sitting on the neighbouring text column -- page 23's card
grid was reported at x 0.24-0.54 where the graphic runs 0.41-0.95.
snap_visual_bboxes() reduces the page render to an ink-coverage grid,
seeds a connected-component search with the engine's box, and re-joins
tiles a gutter apart so a card grid comes back as one figure. Text
blocks are excluded from the mask, which is what stops a figure
swallowing the column beside it. A candidate must be solidly inked or
framed on nearly all of its rows and columns (admitting a white-interior
screenshot), may not shrink below 30% of the seed, and reverts when two
figures land on the same graphic; anything else keeps the box it had.
Runs before the figure crop in both OCR paths, so the images shown
during playback are framed correctly too. Replaces refine_picture_
bounds(), which only recognised coloured panels and had no text fence.
Also adds "Fix figure boundaries" in review and POST
/api/magazine/{id}/figures/refine behind it, so an issue ingested before
this pass can be corrected without re-running OCR. Verified live against
c't KI Wissen 2026: 78 of 138 boxes corrected, the rest declined.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
