pediatric-ai-scribe-v3/public/components
Daniel 1ad72b134b
Some checks failed
Forgejo Android APK / Root app tests (push) Successful in 54s
Forgejo Docker Build / Root app tests (push) Successful in 48s
Forgejo Android APK / Build signed APK (push) Successful in 2m22s
Forgejo Docker Build / Build Docker image (push) Successful in 12s
Forgejo Docker Build / Deploy to the host (push) Failing after 0s
feat: a resource can have several illustrations, on its own path
My Resources used imageTool.dispatch, which permits exactly one image per
request — "Only one image tool invocation is permitted per request". That is the
right rule for a chat reply and the wrong one for a twelve-slide deck where the
author asked for three figures. Rather than relax a limit the clinical assistant
and the Learning Hub also depend on, this adds a separate dispatcher for this
feature. Same queue, same storage, same my_resources workflow, same asset
endpoint — only the number of figures differs, bounded at six because each one
is a paid request.

"Use 3 diagrams" in the instructions is read as the number it is, and the
illustration option now says several are possible rather than promising one.

Three things had to be got right, each found by measuring rather than assuming:

The illustration guidance has to be the last thing in the prompt. Placed before
the output rules it lost — with the tool offered and the paragraph present, the
model returned 3297 characters of markdown and zero tool calls, while the same
tool and wording in a shorter prompt produced three calls.

Even last, it loses to a prompt carrying thirty library excerpts:
deterministically, with the library off "use 3 diagrams" made three calls and
with the library on it made none and wrote a longer deck instead. So when the
author names a number the call is required rather than merely offered. With no
number named the choice stays the model's.

And a model that has just made three tool calls tends to sign off instead of
writing: "I'll create the presentation and the three teaching diagrams." was
returned as the resource — 61 characters — because only a completely empty body
counted as missing. A body with no title block and no heading is not a Pandoc
document whatever its length, and if the continuation is no better than the
first attempt, whichever actually reads like a resource is kept.

Verified end to end with the library on: generate produced three figures and an
eight-slide deck; modify added two more figures and a ninth slide. The figures
were fetched and looked at — labelled airway anatomy, and a croup/epiglottitis/
bacterial tracheitis comparison.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dv6sqaY6Vq3ChZHMem3cnU
2026-09-11 19:19:22 +02:00
..
admin-docs.html feat: ED multi-stage UX, extensions polish, docs viewer + application-logic docs 2026-04-28 03:09:38 +02:00
admin.html feat: PubMed search for My Resources, and an image tool that actually fires 2026-09-11 16:47:08 +02:00
assistant.html fix: metrics are not public, and the workspace launcher renders again 2026-09-11 05:18:02 +02:00
bedside.html feat: don't-miss tooltip after notes + bedside suture selector 2026-04-28 03:09:38 +02:00
calculators.html fix(nav): move image lightbox to index.html so NRP + seizure pathways 2026-04-23 18:58:38 +02:00
catchup.html Fix quiz SQL bug, security hardening, componentize HTML, speed improvements 2026-03-23 20:01:54 -04:00
chart.html v10: Local Whisper transcription, bigger text areas, flexible AI memory 2026-03-28 22:00:30 +00:00
cms.html feat: the Learning screen can ask for grounding, and says what it got 2026-09-11 14:39:49 +02:00
diagrams.html stabilize assistant and add diagrams 2026-05-08 00:23:00 +02:00
dictation.html v10: Local Whisper transcription, bigger text areas, flexible AI memory 2026-03-28 22:00:30 +00:00
ed-encounter.html feat: ED multi-stage UX, extensions polish, docs viewer + application-logic docs 2026-04-28 03:09:38 +02:00
encounter.html Fix TTS axios/Vertex, generic toast, add stop button to encounter 2026-03-29 22:09:56 -04:00
extensions.html feat: add extension import preview 2026-05-08 22:26:53 +02:00
faq.html remove browser whisper transcription 2026-05-08 07:33:12 +02:00
hospital.html v10: Local Whisper transcription, bigger text areas, flexible AI memory 2026-03-28 22:00:30 +00:00
learning.html Render presentations as slides in Learning Hub viewer 2026-03-24 03:04:14 -04:00
my-resources.html feat: a resource can have several illustrations, on its own path 2026-09-11 19:19:22 +02:00
notes.html feat: ED encounters + notes model selector; remove AI corrections; fix notes framing 2026-04-28 03:09:38 +02:00
pe-guide.html feat(pe-guide): Cardiovascular system with APTM auscultation SVG 2026-04-22 20:15:08 +02:00
settings.html fix: correct a false Settings claim; make every test child's stdout pure TAP 2026-09-10 15:41:44 +02:00
sickvisit.html v6.2: Session management, password change, audit logging, refine context, UI fixes 2026-04-08 20:27:45 +02:00
soap.html Add pause/stop buttons to SOAP note recording 2026-04-11 05:19:12 +02:00
vaxschedule.html Fix quiz SQL bug, security hardening, componentize HTML, speed improvements 2026-03-23 20:01:54 -04:00
wellvisit.html Match TTS voices to the selected LiteLLM model 2026-07-30 17:34:34 +02:00