A .pptx landing in someone's own storage is worth having; a markdown blob is
not, and it is not what they would have downloaded. So this renders through
exactly the path the download uses — stored deck, its figures, the chosen
theme — and PUTs the bytes. The file never travels through the browser.
Offered only when a Nextcloud is connected: an action that always fails is
worse than one that is not offered. An article offers Word, a deck PowerPoint,
and asking for slides from an article is refused with the reason.
Putting a file in Nextcloud now lives in src/utils/nextcloudFiles.js. Two
callers want it and neither should grow its own copy of the WebDAV dance — make
the dated folder a segment at a time, PUT, migrate a legacy plaintext token —
because it reaches into storage that is not ours and a second slightly
different copy is how the two drift. It also replaces a route importing another
route.
Also: a model that leaves the roster now leaves every list that names it.
clinical_assistant.allowed_models and the image roster are advisory copies of
the roster, and a stale id there was invisible until someone asked a clinical
question and the request failed at the gateway. Removing or disabling a model
prunes it; clearing the roster clears them. Re-enabling deliberately does not
re-allow it — that is a separate decision.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dv6sqaY6Vq3ChZHMem3cnU
**The regex is gone.** The route ran a pattern over the user's message and
enqueued an image from the answer text when the model had not called the tool.
It was a compatibility path for models without tool calling and it did more harm
than good: it decided in English only, it could not see the conversation, and
"image summary" fell through it while reading as an obvious image request to the
model itself — which was measured, not assumed. A second and worse
decision-maker sitting behind the first. Whether a message deserves a picture is
now the model's call, made from the tool description, which is the only place it
ever belonged.
**Lending eyes.** The same shape, for a different capability. When someone
attaches a photograph and the chat model cannot accept image input, the
attachment was either refused by the provider or silently dropped — an answer
about a picture nobody had looked at, which is worse than a refusal.
The chat model is now offered look_at_image beside the image tool and decides
when to use it. The attachment goes to clinical_assistant.vision_model, whose
description comes back as a tool result, and the chat model answers in its own
voice with its own sources. Only the seeing is delegated; the clinical reasoning
stays with the model an administrator chose. The seeing model is told to report
and not to diagnose, because it has a picture and no context and an opinion from
it would carry weight it has not earned.
Delegation triggers only on an explicit supports_vision: false from the gateway.
An unknown is left alone — most of a roster reports nothing, and treating
silence as blindness would route good models through a detour. The capability
lookup moved to its own module, is cached for five minutes because it runs on
exactly the requests that are already slowest, and is never inferred from the
model id. liteLLMBaseUrl moved from the admin route to litellm.js, where the
other gateway helpers live.
The new setting is guarded like the slide reviewer: a model the gateway calls
text-only cannot be saved as the one that looks at images.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dv6sqaY6Vq3ChZHMem3cnU
The reviewer is shown rendered images of the deck, so a text-only model there
fails on every generation — at request time, long after the one moment an
administrator could have picked differently. Nothing checked it.
Saving my_resources.review_model now asks the gateway what it reports for that
model and refuses only an explicit supports_vision === false.
Three answers, not two. Most of this roster carries no supports_vision at all
(every openrouter-* entry here), and refusing unknowns would block the reviewer
this deployment already runs on. An unreachable gateway is not evidence about a
model either, so it never blocks the save. Empty means review is off and skips
the lookup entirely.
The capability is read from the gateway, never inferred from the model id.
Verified against a mutation: relaxing `canSee === false` to `canSee !== true`
fails the two tests that say unknown must stay allowed.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dv6sqaY6Vq3ChZHMem3cnU
The model that writes a deck never sees it. It cannot tell that slide four
overflowed, that a nine-item list would read better in two columns, or that two
labelled groups want to be a comparison — those are facts about the rendered
page, not about the text. So each generated deck is now rendered to PDF through
Gotenberg, rasterised to one image per slide with pdftoppm, and shown to a
vision model.
Off unless an administrator names a reviewer, in its own admin card because it
is the one setting that spends money on every generation without a user having
asked for anything. One pass, on generation only: a second pass costs as much as
the first and fixes far less, and refining is a text edit.
It returns a patch, not a deck. Asking for the corrected deck back put the reply
in proportion to the deck rather than to the number of problems, and a
fourteen-slide deck came back cut off mid-object at every output budget the
provider would honour — measured twice before changing shape.
The patch is better for a second reason. The reviewer names a slide and an
action — two columns, one column, split after bullet N, compare with these two
labels — and the server moves the text it already has. The words never pass
through the model, so a review cannot reword, drop or invent a single bullet.
That is a stronger guarantee than instructing it not to and checking afterwards.
The check runs anyway, because a bug in applyChanges would be as bad as a model
rewriting the words and worse for being trusted: body text must come out the
same multiset, figures the same set, and a heading may only be reused or
extended. A continuation heading is the reviewer's one piece of text and is
replaced when it does not continue anything.
Nothing here can fail a generation — no reviewer, an unreachable one, an
unparseable reply, a deck too long to look at, or a patch that applies to
nothing each return the deck that was written.
Verified end to end against a deck with a deliberately overloaded slide: three
slides rendered and sent, one change returned, ten bullets split into five and
five under "Stepwise Management … (continued)", text intact. Left switched off;
enable it under Admin.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dv6sqaY6Vq3ChZHMem3cnU
An expired code is as dead as a used one and just as accounted for, so it is now
deletable. The rule the code enforces is the one that matters: a code that could
still be redeemed is never deleted, because that takes it off the list without
taking it out of anybody's inbox — the holder keeps something that looks valid,
it quietly stops working, and nothing is left to say who had it.
One condition, shared by the single delete and the bulk clear:
(used_at IS NOT NULL OR (revoked_at IS NULL AND expires_at <= NOW()))
Written that way rather than as "used OR past its date" because the second form
also catches a revoked code whose date has since passed — a row the list still
labels revoked and offers no delete on, so the button and the query would have
disagreed about the same row.
Revoked codes keep their rows. Revoking records a decision somebody took, and a
handful of them is not the clutter a pile of expired codes is.
Verified against the live database across every state: active refused, used
deleted, expired deleted, revoked refused, and revoked-with-a-past-date refused
rather than slipping through as expired.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dv6sqaY6Vq3ChZHMem3cnU
The delete button was offered on every invitation regardless of state, and the
query behind it deleted any row it was given. Deleting an unused code takes it
off the list without taking it out of anybody's inbox: the person still holds
something that looks like a valid invitation, it silently stops working, and
there is no longer a record of who it went to or why. Revoke is what stops a
live code — it leaves the row behind, marked.
So the delete is now for spent codes only, in three places rather than one: the
query carries AND used_at IS NOT NULL, the route answers 409 with the reason
instead of pretending the row is missing, and the button is rendered only on a
used row.
A "Clear N used" control alongside, since the complaint was clutter and clearing
them one at a time is not much of an answer. Same rule — nothing unused or
revoked is touched — and it confirms first, because it is still a delete.
The bulk route is declared before /invites/:id, or Express reads "used" as an id.
Verified against the live database: deleting an unused invitation is refused and
the row survives, deleting a used one works, the bulk clear removes only used
ones, and the unused probe row was still there afterwards.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dv6sqaY6Vq3ChZHMem3cnU
PubMed joins web search as an optional source for a generated resource: a
literature search on the topic, with abstracts, cited by PMID in References.
Off by default, admin-enabled, with its own optional API key (NCBI raises the
rate limit from 3/sec to 10/sec; it works without one).
Neither search is a tool any more, and that is the point. Offering them as
function calls meant the model decided whether to search, and with a prompt
ending "Output ONLY Pandoc markdown" it decided not to — every time, with and
without corpus grounding, no matter how the tool description was worded.
Calling callAI with the tool directly produced a correct pubmed_search call, so
the plumbing was never the problem. The search only ever needed the topic, and
the route knows the topic before it calls the model, so both searches now run up
front and their results go into the prompt as findings, exactly the way corpus
excerpts do. Ticking the box now means the search happened.
Verified live against deepseek-v4-flash: 30 corpus excerpts and 6 PubMed
results, and a References slide carrying both the library sources and four real
PMIDs (29562151, 38506440, 35721052, 28814254).
Three fixes to illustration, which had never once fired:
- The dispatch call had been lost in a refactor. The tool was still offered, the
model still called it, and the call was dropped, so no job was ever enqueued.
- imageContext was passed as a bare topic string where dispatch expects
{ request, history }, which made the bound request undefined.
- The prompt never mentioned the tool existed while explicitly demanding only
markdown — the same suppression that killed the searches. It now says an
illustration is available and that calling it is not a violation of that rule.
my_resources is its own image workflow rather than a reuse of learning_hub,
because generated_image_links only accepts learning_hub assets, and that is
exactly the barrier that keeps a private illustration out of published content.
The illustration renders in the panel, rather than a toast pointing at an image
history this feature does not have.
Verified end to end: job queued, rendered, and the asset served to its owner as
a correctly labelled subglottic-anatomy teaching diagram.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dv6sqaY6Vq3ChZHMem3cnU
The one feature here that sends text outside the building, so the defaults are
the careful ones: disabled unless an administrator turns it on, opt-in per
generation even then, and the option is hidden entirely rather than shown as
something a user can tick and be refused.
Only the search query leaves. Library excerpts, the generated resource and
anything about the user never do. Both screens say so plainly, because a topic
typed while drafting clinical material can carry clinical detail and the
provider keeps its own logs.
Four providers behind one shape, so swapping changes nothing downstream: Tavily,
Serper over Google, Brave, and SearXNG — the only one where the query does not
reach a commercial third party at all, which is why it is worth supporting even
though it needs somewhere to run.
The tool description says when NOT to search, because a model handed a search
tool will reach for it constantly: not for settled clinical knowledge, which is
what the indexed library is for, and one search per resource. That last one is
enforced in the route with toolChoice: 'none' on the continuation rather than
trusted to the model.
A failed search never fails a generation — same contract as corpus retrieval.
The resource is written without it and the response says what was searched for
and what came back, so a query that left the network is visible rather than
silent.
The API key is masked on read and preserved when the field is left blank, the
handling the OIDC client secret already gets, so changing provider cannot
silently wipe a working key.
Verified on the running instance: with nothing configured, webSearchAvailable is
false, and a request asking for it anyway is ignored rather than honoured.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dv6sqaY6Vq3ChZHMem3cnU
npm audit reports 0 vulnerabilities. It reported 2 high and 2 moderate this
morning.
@google-cloud/vertexai was the last source of findings — gaxios and a uuid with
a missing buffer bounds check, neither reachable in this deployment because
GOOGLE_VERTEX_PROJECT is unset and the require sits inside that check. Dormant
is not the same as gone, and the provider is available through the gateway
anyway, so the direct path has been removed rather than left to rot:
- the SDK client and callVertex, which without the package could never run
- the dispatch and discovery branches that reached them
- VERTEX_MODELS, a list of ids nothing could route any more, and the two
places in adminConfig that concatenated it into the built-in set
- the health endpoint's vertex line, and the env vars documented for it
AI_PROVIDER=vertex now says where to configure the model instead of quietly
becoming something else. The Google STT and TTS paths keyed off the same
variable are untouched; neither ever used this SDK.
Verified after deploy: provider litellm, the assistant answers with 8 sources,
/api/models returns 10, and @aws-sdk/s3-request-presigner — which documents.js
needs for presigned MinIO URLs — is still declared and resolvable.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dv6sqaY6Vq3ChZHMem3cnU
Citation quality
- A citation naming a source that never came back is never rendered as a
link, so it appears as plain text and nobody learns it happened. It is now
measured on the server, where the answer and the sources both exist, so it
is seen whether or not a browser rendered it.
- Four Prometheus counters feed a Grafana dashboard (Ped-AI Citation
Quality): answers, citations written, answers affected, and individual
unresolved markers. Only answers with at least one unresolved citation are
stored, with the question and the titles retrieval returned, so an operator
can judge whether retrieval came back thin or the model over-cited. Rows
expire after 30 days: this is a quality signal, not a transcript log.
- Both answer paths are covered. /chat/stream is normal; /chat is the
fallback the client uses when streaming fails, so auditing only the first
would have hidden exactly the answers produced under failure.
- The tracker is resolved on demand and allowed to be absent. Seven test
files load this route with a hand-built list of permitted imports, and
adding a hard dependency would mean editing all seven — and the eighth
written later would break. Observation must never be able to fail an
answer, so a missing module simply means no tracking.
- Metric registration reuses an already-registered counter, because this
module can legitimately load twice in one process.
SSO settings on mobile
- Six rows were laid out inline: flex with a 160px label and an input that
would not shrink, so on a phone the row was wider than the screen with
nothing to scroll and no way to reach the rest. They use .admin-row now,
which already stacks below 640px. Verified at 390px and 360px: nothing
off-screen, no sideways overflow.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dv6sqaY6Vq3ChZHMem3cnU
With more than one admin, every setting in the panel was editable by all of
them — prompts, model policy, retrieval budgets, SMTP, email templates.
ADMIN_LOCKDOWN separates running the service from changing how it behaves.
It is an environment variable on purpose: a setting could be switched off by
the very admin it restrains, so lifting this needs host access and a restart.
The server is the control. One gate refuses configuration writes rather than
a check in each of the fifteen write routes, because that list grows and a
route added later would quietly miss it. Reads always pass — lockdown hides
nothing. Day-to-day operation stays available: invitations, announcements,
registration, feature flags, and the test endpoints, which persist nothing.
A setting invented later is locked until someone deliberately makes it
editable, rather than defaulting to open.
The panel disables what it cannot save and says why, but that is courtesy;
the refusal is what enforces it.
Two things this taught me, both fixed: my first version painted the panel
from an IIFE, which the module conventions forbid, and fetched the whole
config a second time just to read one flag — breaking the test that pins
admin loaders firing exactly once. The state now rides on the invites
response the panel already requests.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dv6sqaY6Vq3ChZHMem3cnU
registration_enabled was a single switch: open to anyone, or closed to
everyone. This adds the setting an operator actually wants in between — open
to people you invited.
A code is single-use, expires (7 days by default, 90 maximum), and can be
revoked or deleted. It is stored hashed with only its last four characters
kept, because an invite grants account creation and a database dump should
not hand someone a working one. The code is readable exactly once, in the
response that creates it.
The claim is a single conditional UPDATE carrying every condition, so two
registrations racing the same code cannot both succeed. It happens after the
account exists, so a code is never spent on a failed registration — and if
the race is lost, the just-created account is removed rather than left behind
as a free registration. The rejection never says which of the four reasons
applied; distinguishing them would tell someone probing codes which guesses
were closer.
Codes avoid I, L, O and U so they survive being read aloud or copied off a
screen, and matching ignores case and separators.
The sign-up field appears only when the server says a code is required. The
admin card creates, lists, revokes and deletes, and carries the toggle.
Verified against the live database: create, claim, second claim refused,
unknown code refused, revoking a used code refused, delete. 684 tests pass.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dv6sqaY6Vq3ChZHMem3cnU
Image models
- The Clinical Assistant "Image models" list waited on an old
#assistant-image-model dropdown that no longer exists, so discovery never
reached it and only four hard-coded fallbacks appeared — with no way to
add any of the gateway's 50 image models.
- Image Generation search rows now have + Add / Added. Added models are
saved as clinical_assistant.image_model_roster (validated server-side:
up to 100 ids) and appear in the Clinical Assistant list at once; ticking
one there offers it to users. Anything already allowed or configured
stays listed. Unsaved ticks survive an add.
- The roster notification is guarded, so it can never fail the settings load.
Phone top bar
- The page is drawn under the status bar (viewport-fit=cover) and its
theme colour was the removed header's blue, so on an iPhone content showed
scrolling at the top of the screen. The row is now a real fixed element
that extends behind the status bar (env(safe-area-inset-top), 0 in a
normal tab), the menu button, sources pill and drawers clear it, and the
theme colour is white.
Verified in Chromium: + Add -> saved roster -> listed unticked; tick kept;
remove works. Top bar is the only thing in the top 48px on all 22 pages;
phone menu positions unchanged.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01W4rptBNvn6RYieQw54GXNS
Sources (correcting what I built earlier)
The previous toggle branched the SYSTEM PROMPT, so the same question could get a
different answer depending on a display setting — the bias this was meant to
avoid. The prompt is now unconditional: buildSystemPrompt takes no display
argument and is byte-identical either way. Hiding sources happens on the way out
— the server omits them and strips the now-orphaned [n] markers from the copy it
sends. The answer is generated, stored and exported with citations intact, so
turning the setting back on restores them without re-asking anything. Renamed to
clinical_assistant.show_sources; the old key is still honoured.
Signed-out preview (admin opt-in, default off)
A visitor may try the assistant; reaching for the workspace asks them to sign in.
Deliberately narrow:
- Reachable paths are an exact allow-list, not a pattern, so a new endpoint is
private unless someone adds it on purpose.
- A preview visitor gets no identity at all (id: null), so nothing can be owned,
saved, billed or addressed to them.
- The image tool is withheld rather than left to fail on a null owner, and no
audit rows are written.
- A caller presenting a token is authenticated normally, so preview can never
downgrade a real session; if the setting cannot be read, authentication is
required.
- Actions needing an account are hidden rather than offered and refused.
Composer
The bar above the transcript is gone. Patient take home, Export PDF, Download
transcript and Attach images moved into a + menu in the composer, and the model
selector moved beside send — shown only when there is more than one model, as
before. Both views now start at the same top edge, so switching modes cannot
nudge the page up or down. On an empty transcript the tiled ground runs behind
and below the composer, which floats on it above centre.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GmpYHPSLGmXGZMyLpn2Lbe
New setting clinical_assistant.citations_enabled (default true, admin checkbox).
With it off, retrieval, grounding and every other rule are unchanged — answers
are still built only from retrieved sources — but:
- buildSystemPrompt swaps only the citation block: the "cite factual claims with
[1]" rules are replaced with "do not include citations, source numbers or
bracketed markers", and the note that the sourcing requirement itself is
unchanged. Grounding, scope, table formatting and tone rules are byte-identical
between the two modes.
- The server strips any stray [n] the model emits anyway, from the stored answer
rather than only the view, so saved chats and exports match what was shown.
- No sources are sent to the client at all, and the status endpoint reports the
mode so the UI hides the Sources panel and gives its 330px column back to the
chat instead of showing an empty rail.
Validated as a boolean in adminConfig, like the feature.* keys.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BkfrkQwA4YGrGw9LZSpeAq
Translation
- Stop scrubbing markdown before sending it to LibreTranslate. The scrub
deleted ordered-list numbering ("1. Give amoxicillin" -> "Give amoxicillin"),
flattened tables into ambiguous whitespace and ate underscores inside
identifiers. Raw markdown now goes to the translator unchanged.
- Render the translation through the same markdown pipeline as the original
bubble, with the message's own sources, so [n] markers come back as the usual
clickable .assistant-cite chips instead of escaped literal text. Headings,
lists and tables survive with them.
- When the translator drops citation markers, surface the affected sources in a
recovery block rather than letting the evidence disappear.
- Image cards are live nodes: they are now re-attached on every path out of a
translation (success, failure and Show original), so a failed translation no
longer silently removes a generating image from the message.
Patient take home
- Add a language selector to the take-home modal, reusing the existing
/translate endpoint and offering only what the local LibreTranslate reports.
- Copy, Export and Email carry what the caregiver is actually reading; the
original stays canonical behind "Original".
Conversation budget
- The admin field no longer prefills with the environment value, which turned
the next Save into an accidental override and made the documented "leave
empty to use the environment" path unreachable. The effective limit is shown
as a placeholder instead.
- Report source 'default' honestly instead of naming an unset env var.
- The load-failure notice now lands on the <p> instead of an <input>'s
textContent, where it rendered nothing.
- One validator for the budget everywhere: conversationLimit() replaces a
parseInt that accepted "120000abc".
Other
- /assistant is addressed by its URL, not by ped_last_tab, so "/" no longer
reopens the assistant; the URL follows tab changes and Back leaves it.
- Remove the dead DeepL path (it referenced an undefined DEEPL_BASES) and stop
offering admins a provider the server silently ignores.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BkfrkQwA4YGrGw9LZSpeAq
Voice lists were a single flat set from LITELLM_TTS_VOICES, so picking a
model could leave an incompatible voice selected and the request would
fail at the gateway. Voices are now resolved per model family (Kokoro,
Kitten, Supertonic, Groq Orpheus EN/AR), with a compatibility check that
falls back through user → admin → env → first valid voice. Groq Orpheus
requests also pin response_format to wav.
Also refreshes the cardiac/respiratory auscultation samples, extends the
well-visit component, and fixes the Android launch theme background
(@null → colorPrimary) so the splash does not flash through.
NOTE: this is in-progress work that was already sitting uncommitted in
the working tree; it is committed here as-is so the tree was clean for
the release bump.
- Add logger.audit/access calls to auth route (login, login_failed,
login_blocked, register, password_changed, 2fa_backup_code_used,
2fa_backup_codes_regenerated) — these previously only wrote to DB
via raw SQL, bypassing Loki shipper
- Replace logger.info with logger.apiCall in callAI() so every AI call
ships to Loki with model, tokens, cost, duration
- Add device identifier (parsed user agent) to audit and access logs
- Fix TTS voice/model provider mismatch: auto-detect Vertex voices
(Puck, Charon, Kore, etc.) and ElevenLabs voice IDs, override model
to match provider regardless of what model was previously set
- Fix TTS discovery: model IDs saved to tts.voice are detected and
redirected to tts.model (regex for openai-tts, elevenlabs, vertex-tts)
- Fix STT transcription route: add scribe/elevenlabs/transcri to the
isTranscriptionModel regex so ElevenLabs Scribe uses /audio/transcriptions
endpoint instead of chat completions
- Remove OpenObserve/SigNoz code from logger (reverted to Loki-only)
- Add neonatal assessment calculator: GA classification (extremely preterm through
post term), weight-for-GA percentile (AGA/SGA/LGA) using Fenton 2013 LMS data,
birth weight category (ELBW/VLBW/LBW/normal/macrosomia)
- Add DOCX support via mammoth, PPTX/ODT/EPUB via jszip in Learning Hub content
generator file upload
- Add gatewayUrl() helper for consistent API URL construction — handles
LITELLM_API_BASE with or without /v1 suffix, works with any OpenAI-compatible
gateway (LiteLLM, Bifrost, etc.)
- Fix TTS model/voice separation: discovery now tags items as MODEL or VOICE,
auto-detects provider from voice name (Vertex, ElevenLabs, OpenAI)
- Fix STT discovery to include ElevenLabs Scribe and Chirp models
- Fix TTS discovery to include ElevenLabs and Vertex voices alongside models
- Fix admin model test to bypass allowlist check (skipAllowlistCheck) so
discovered models can be tested before adding
- Fix Nextcloud token decryption in learningAI.js WebDAV browse and file import
- Fix admin embedding test to show DB model name instead of hardcoded default
- Fix admin STT test to use correct endpoint for Whisper models
- Add AI gateway migration guide to configuration docs
- Add Grafana dashboard JSON for Loki log visualization
- Add Cloudflare Turnstile to login, register, and password reset forms
- Switch AI provider to LiteLLM, transcription to OpenAI Whisper
- Change domain to scribe.pedshub.com
- Fix PPTX export: add tables, bold/italic, numbered lists, code blocks, blockquotes
- Fix announcement banner close button (CSP was blocking inline onclick)
- Fix auth middleware: empty Bearer token now falls through to cookie auth
- Fix audio backups: only save on transcription failure, stop auto-deleting on success
- Soften AI correction injection to prevent model hallucination from correction history
- Fix LiteLLM TTS model name handling (no incorrect openai/ prefix)
- Expand AI instructions textarea in Learning Hub CMS
- Update README for v6 with all features and providers
- Add comprehensive docs/: architecture, API reference, database schema,
authentication, AI providers, speech, learning hub, configuration, deployment
- Fix model search for all providers: Bedrock now falls back to built-in
list (with live ListFoundationModels attempt), Azure returns built-in list
- Add Test button on every model row (built-in, discovered, custom) that
sends a live prompt and shows response + latency in a toast
- Add TTS management section: search voices from provider API (Google TTS
voices.list, LiteLLM /v1/models, ElevenLabs /v1/voices), Set as Default
writes tts.voice/tts.model to DB, runtime respects DB override
- Add STT management section: search models from provider (Gemini, Whisper,
LiteLLM, OpenAI, local), Set as Default writes stt.model to DB, runtime
respects DB override in transcribe.js
- Add Embedding models section: search from provider (LiteLLM, Vertex,
OpenAI), Set as Default writes embeddings.model+dimensions to DB,
embeddings.js respects DB override
- Add record-and-transcribe STT test (browser MediaRecorder)
- Add TTS synthesize-and-play test (returns base64 audio)
- Add embedding generate test (shows dims + vector sample)
- Expand PUT /config/:key(*) whitelist to include tts., stt., embeddings.
- Add @aws-sdk/client-bedrock as optional dependency for live Bedrock discovery
Emails: white card, clean typography, dark button, no gradients.
Same minimal aesthetic as Linear/Resend/Notion emails.
Verify page responses also updated to match.
- LITELLM_MODELS = [] — no hardcoded models, global selector now only
shows what admin has actually added via Search API
- getAvailableModelsWithOverrides: for LiteLLM returns only custom list
- Remove toggle safety check — admin can disable any/all models freely
- Admin panel always reloads on tab open (was cached, showing stale data)
- Add 'Clear all models' button for LiteLLM to wipe and start fresh
- Add POST /config/models/clear-all endpoint
- Root cause: PUT /config/:key(*) wildcard was registered before
/config/models/toggle and /config/models/default, intercepting them
and returning "value is required" (body had modelId not value)
- Fix: move all model-specific PUT routes before the wildcard
- LiteLLM: return empty built-in list with discovery hint (hardcoded
models don't match user's proxy — must use Search API)
- After adding a discovered model: auto-select it in the default dropdown
- GET /config/models now returns defaultModel so dropdown pre-selects it
- Add Vertex AI provider (Gemini models via @google-cloud/vertexai SDK)
- Add LiteLLM proxy support (OpenAI-compatible, routes to any provider)
- Admin panel: model search/discover from provider API, enable/disable, custom models, set default
- New endpoints: /config/models/discover, /config/models/add-discovered, /config/models/default
- Updated models.js with VERTEX_MODELS and LITELLM_MODELS lists
- Updated health endpoint with vertex + litellm status
- APK: Add WAKE_LOCK, BOOT_COMPLETED, ACCESS_NETWORK_STATE permissions
- APK: Disable allowBackup for medical data security
- APK: AudioRecordingService now acquires wake lock, has stop action in notification
- Serve /.well-known/assetlinks.json for TWA domain verification
- Service worker: cache app shell, stale-while-revalidate for assets, network-first for API
- Admin model management: validate model ID format, prevent built-in conflicts, audit toggle actions, prevent disabling all models
- Bump version to v9.0.0, Docker tag to v9
