Three concurrent themes from this session:
═══════════════════════════════════════════════════════════════════
ED ENCOUNTERS — per-stage cards + consolidate→MDM finalize
═══════════════════════════════════════════════════════════════════
UX redesign per Daniel's feedback ("every stage note should be shown,
if AI is told to modify that particular note then the modified version
is used in final mdm"):
- Each generated stage stays on screen as its own editable card with
its own embedded "Don't Miss" panel. No more single rolling note
element that gets replaced on each generation.
- gatherCurrentNotes() reads contenteditable text from each stage card
before any operation (advance, finalize, persist) so inline edits
flow into the next AI call and the final consolidate.
- Stage badge is now state-accurate. "Stage N (recording)" with yellow
background after Add-more before generation; "Stage N" with gray
after generation. Fixes the bug where the badge flipped to Stage 2
the moment Add-more was clicked.
- Save & Done now runs TWO server-side AI calls in /finalize:
1. edConsolidate (new prompt) → polished single final note that
integrates every stage chronologically (HPI / ROS / PE / ED Course /
A&P with disposition).
2. edFinalize (rewritten with full inline 2023 AMA E/M element
rubric — problems / data / risk definitions, level mapping with
concrete examples) → MDM JSON.
- Two new cards render after finalize: blue-bordered Final Consolidated
Note + green-bordered MDM. Stage cards become read-only.
- partial_data on the saved row now stores {stages, finalNote, mdm,
finalized} so resume re-renders the full state.
Why two-call finalize: a single combined prompt makes the model cut
corners on one task. Two focused calls cost ~2× latency at the very end
of an encounter — acceptable since finalize is a one-time terminal
action, not a per-stage hot path.
Files: public/components/ed-encounter.html, public/js/ed-encounters.js,
src/routes/edEncounters.js, src/utils/prompts.js (edConsolidate added,
edFinalize rewritten).
═══════════════════════════════════════════════════════════════════
EXTENSIONS / PAGERS — visual polish
═══════════════════════════════════════════════════════════════════
Multiple iterations based on Daniel's feedback:
- Layout: align-items:flex-start so action buttons stay pinned top-right
when long numbers wrap (was align-items:center → buttons drifted into
the text area, causing visible overlap).
- Number: word-break:break-all + min-width:0 + font-feature-settings:tnum
so long numbers wrap within their column instead of pushing under the
buttons. Click-to-copy with a 0.55s green flash + ✓ copied badge.
- Phone/pager Font Awesome icon next to the number in the type color —
at-a-glance type signal (replacing an earlier 3px left stripe that
Daniel found visually bulky).
- Name: font-weight 700, font-size 14.5px, color g900, letter-spacing
-0.012em — scan-target headline typography for long lists.
- Alternating subtle backgrounds by index (white vs #fafbfc) so a long
list reads as distinct rows.
- Hover: card lifts 1px with a soft shadow; action buttons fade from
55% to 100% opacity. Cubic-bezier transition on transform.
- Entrance: staggered fade-up animation per card (35ms × index, capped
at 12). prefers-reduced-motion media query disables motion.
- Empty state: 48px FA icon + heading instead of plain gray text.
Files: public/js/extensions.js, public/css/styles.css.
═══════════════════════════════════════════════════════════════════
DOCS REORGANIZATION + APPLICATION-LOGIC DOCS + ADMIN VIEWER
═══════════════════════════════════════════════════════════════════
Document moves (preserving git history via git mv):
BROWSER_WHISPER_SETUP.md → docs/browser-whisper-setup.md
BROWSER_WHISPER_TROUBLESHOOTING.md → docs/browser-whisper-troubleshooting.md
DEVELOPER_GUIDE.md → docs/developer-guide-extended.md
EMBEDDINGS_SETUP.md → docs/embeddings-setup.md
FEATURES_EXPLAINED.md → docs/features-explained.md
IMPROVEMENTS.md → docs/improvements.md
OPENID_SETUP.md → docs/openid-setup.md
TRANSCRIPTION_OPTIONS.md → docs/transcription-options.md
README.md updated with the new paths + a Documentation section that
links to docs/logic/ at the top.
New application-logic doc series (~8,300 lines total) at docs/logic/.
Built with 5 parallel doc-writing agents per Daniel's "use multiple
agents" directive. Each doc explains how a part of the app actually
works — application logic, data flow, design decisions, sacred zones,
how-to-extend recipes — at a depth that lets a new dev (or an AI
assistant) modify the code confidently.
docs/logic/README.md — index + recommended reading order
docs/logic/architecture.md (2166 L) — frontend IIFE pattern, lazy tab
load, backend route convention,
schema, encryption, deployment
docs/logic/clinical-notes.md (1546L) — every note tab + helper trio
docs/logic/bedside-and-calculators.md (1373L) — bedside ES module
pocket + calculators + PE Guide
+ suture selector
docs/logic/auth-admin-learning.md (1281L) — auth (local+OIDC+2FA) +
admin panel + Learning Hub
(Quiz engine logic at sub-detail
only — TODO follow-up)
docs/logic/ai-and-voice.md (1128 L) — callAI 5-provider routing,
prompts, voice/STT, helper trio
docs/logic/ed-encounters.md (821 L) — multi-stage ED + MDM (this
session's worked example)
Admin-only docs viewer:
- New route /api/admin/docs/{tree,file}: recursively walks docs/, returns
the tree as JSON; /file?path=X validates path stays inside docs/ and
renders markdown via marked. Both gated by req.user.role==='admin'.
- New tab "Docs" (book icon) in the sidebar, hidden by default and
revealed in auth.js when user.role==='admin' (same pattern as the
existing Admin and CMS tabs).
- New component public/components/admin-docs.html: split-pane layout
with a tree sidebar + filter input + a markdown reader pane.
- New module public/js/admin-docs.js: lazy-loads the tree on first tab
activation, renders collapsible folders, persists expanded state and
last-opened path via UIState. Server-rendered HTML so no client
markdown parser needed.
- CSS for the viewer (responsive split-pane, code-block styling, table
scrolling, etc.).
- Mounted at /api/admin/docs (NOT /api) — important: mounting a router
with router.use(authMiddleware) at /api accidentally 401s every other
/api/* path (caught and fixed during testing — /api/health was 401'ing).
Files: docs/* (moved + new), README.md, public/components/admin-docs.html
(new), public/js/admin-docs.js (new), src/routes/adminDocs.js (new),
public/index.html (tab + section + script), public/js/auth.js (admin
gate + logout cleanup), public/css/styles.css (viewer styles), server.js
(mount).
═══════════════════════════════════════════════════════════════════
KNOWN GAPS (TODO follow-ups)
═══════════════════════════════════════════════════════════════════
- Learning Hub quiz engine (MCQ / multi-select / T-F scoring + attempt
tracking + progress dashboard) is covered at the architectural level
in docs/logic/auth-admin-learning.md but not drilled into the quiz
data model and scoring flow. Worth a focused follow-up doc.
- ED finalize: if MDM step JSON parse fails, server returns 502 with
the consolidated finalNote in the error payload, but client doesn't
surface the partial result. Add a "MDM failed, retry" affordance.
- No e2e Playwright coverage for ED encounters or the new docs viewer.
#2 — Don't-miss tooltip (encounters HPI + sick visit, max 5)
- New POST /api/dont-miss returning {points: [{point, why}]} capped at 5
(cap defended both in the prompt and server-side .slice(0,5))
- New dontMissTooltip prompt in prompts.js
- New suggestDontMiss() helper in app.js mirroring suggestBillingCodes;
inserts an orange-bordered card next to the note output, silent on empty
- Wired into liveEncounter.js (encounter HPI) and sickVisit.js. Not added
to wellvisit/soap/hospital/chart per spec.
#1 — Bedside suture selector
- New ES module public/js/bedside/sutures.js (~300L) following the
burns.js pattern: site × age × tension × cosmetic × contamination ×
hours-since-injury → material, size, technique, removal day range,
glue/Steri-strip alternative, warnings, tetanus reminder.
- 15 anatomic sites covered (face, eyelid, lip vermilion, intraoral,
ear, scalp, neck, trunk, upper/lower ext, hand, foot, joint surface,
genitalia, fingertip).
- Bites: cat/human → don't-close-primarily warning; dog bite to hand →
loose-approximation note. Heavy contamination → delayed primary
closure. >12h non-face/scalp → judgment call note.
- Removal days shown as ranges (3–5, 7–10, 10–14) per source norms,
not single midpoints.
- Subungual hematoma trephination guidance corrected: any painful
hematoma with intact nail and no displaced fracture (especially if
25–50% or more), per current UpToDate guidance.
- Inline citation: Roberts & Hedges 7e (2019), Fleisher & Ludwig 8e,
AAP Section on EM, UpToDate (Pope JV).
- Pill registered in sub-nav SECTIONS + bedside/index.js. Persists
active state via existing UIState helper.
All 46 tests pass.
Four changes batched:
1. ED Encounters tab (new) — multi-stage emergency note with don't-miss
tooltips and 2023 E/M MDM finalize. New route /api/ed-encounters
(generate per-stage + finalize MDM), new ed-encounters.js owning all
client logic, new ed-encounter.html component, new template_ed memory
category. Persists draft to localStorage every keystroke and to
saved_encounters on stage advance. encounters.js touched only to
register the new tab in sessionStorage restore + tabMap (save and
idempotency code untouched).
2. Notes model selector — /notes/from-voice now accepts a client-supplied
model (validated by the existing callAI allow-list); falls back to the
admin default. Added <select class="tab-model-select"> to notes.html
so the existing app.js populator handles options + default.
3. Remove AI-learning-from-corrections — deleted correctionTracker.js,
POST /memories/correction, the corrections branch in
/memories/context, the settings UI section, the FAQ entry, and all
dead trackAIOutput/saveCorrection guards in callers. Legacy
correction_* DB rows are filtered (NOT LIKE) rather than dropped, so
no destructive migration.
4. Fix notes AI framing — /notes/from-voice prompt no longer assumes
"physician dictation". Plain notes (shopping lists, reminders,
ideas) now match the dictation tone instead of being forced into
clinical structure.
All 46 tests pass.
Symptom Daniel reported: "note recording, not working nor going into
textbox". Root cause was on the server side — /api/notes/from-voice
asked the AI for HTML in its prompt, but real-world models return
markdown ~25% of the time. Tiptap's setContent only renders HTML;
markdown comes through as literal text or a partial render, looking
like the textbox didn't fill.
Server (src/routes/notes.js):
• New toHtmlBody() helper. If the AI returned real HTML (any
block tag), pass through. Otherwise run through `marked` so
markdown becomes <p>/<h*>/<strong>/etc.
• Strips ```json / ```html code fences before JSON parsing.
• Stricter JSON-recovery: only accepts {title|body} parsed shape;
falls back to wrapping the AI's full reply via toHtmlBody().
• Final guard: if body would be empty after sanitisation, wrap
the raw transcript so the user can at least edit it manually.
Client (public/js/notes.js):
• applyGeneratedNote prefers _editor.commands.setContent over a
full remount — avoids the toolbar-reattach flicker + the brief
window where the body looked empty.
• Logs to console when the editor target is missing or Tiptap
setContent throws, so a future regression is greppable.
Plus the two infra fixes Daniel approved earlier in the same
session — keeping them in this commit since they're already
deployed and tested:
• src/db/database.js: cleanup interval handle exposed; server
shutdown now clearInterval()s it before pool.end(). Removes
the SIGTERM → 9-second-hang → Docker SIGKILL race.
• src/routes/audioBackups.js: switch multer.memoryStorage() to
diskStorage with cleanup. 10 concurrent 25 MB uploads no
longer pin 250 MB of RAM. Identical user-visible perf since
upload is wire-bound.
New dep: marked@latest (used server-side only in toHtmlBody).
Soft-delete for notes — Daniel asked for "deleted notes go to trash"
so a slip of the finger doesn't lose work.
Schema: migrations/1777090000000_notes-trash.js adds a deleted_at
timestamptz column to personal_notes (NULL = active) plus an index
on (user_id, deleted_at).
Server (src/routes/notes.js):
GET /api/notes now filters deleted_at IS NULL
GET /api/notes/trash new — list trashed items, newest-
deleted first
DELETE /api/notes/:id now soft-deletes (sets deleted_at)
DELETE /api/notes/:id?hard=1 hard-delete, only allowed on items
already in trash (UI bug can't
erase an active note)
POST /api/notes/:id/restore pull a note out of trash
POST /api/notes/trash/empty hard-delete every trashed note for
the user
Frontend (public/components/notes.html + public/js/notes.js +
public/css/styles.css):
• Sidebar gets two tabs — "Notes" / "Trash (n)" with live count
• Trash tab shows deleted-at timestamps, Restore + delete-forever
per row, Empty-trash button at the bottom
• Active list and trash count refresh in parallel after every
save / delete / restore
• Delete button in the editor now says "Move to trash" and uses
the showConfirm helper (no native dialogs)
Sanitizer swap (public/js/notes.js):
Replaced the homegrown allowlist walker with DOMPurify (already
loaded from cdnjs in index.html, used by learningHub.js too).
Custom HTML sanitizers historically have bypasses; DOMPurify is
the right primitive.
Tests (test/notes-sanitize.test.js — node:test + jsdom + dompurify
as new dev deps):
9 contract tests covering script-tag stripping, inline event
handlers, img onerror, iframe/object, style attributes, every
preserved tag in the allowlist, javascript: URI rejection,
null/undefined input, and nested-script-inside-paragraph. Total
test count: 37 → 46 passing.
SW cache bumped to pedscribe-v12-notes5.
Four changes landing together so the UX flows properly.
1. Fix voice-generation model error.
/api/notes/from-voice was passing `req.body.model` (undefined)
through to callAI, which resolved to LITELLM_DEFAULT_MODEL (empty
for LiteLLM deployments with no explicit default) → `model=""` →
LiteLLM 400 "Invalid model name". Server now reads the admin-
configured `models.default` setting, falls back to the
LITELLM_DEFAULT_MODEL env var, and only passes a model if one
resolved. Empty string never reaches the provider.
2. Read mode as the default post-save.
Opening an existing note or saving a new one now lands on a
clean, read-only rendering of the body (sanitized HTML with an
allowlist — p/h2/h3/strong/em/u/s/a/ul/ol/li/blockquote/code/pre).
Click the "Edit" button to switch to the Tiptap editor. Matches
the mental model of "notes are documents I review, not drafts I'm
always editing."
3. Autosave during edit.
Title-input + Tiptap onUpdate trigger a 1.2-second-debounced save.
In-flight saves coalesce: if the user types more while a save is
in progress, a follow-up fires right after it lands so the last
keystroke never gets stranded. beforeunload uses navigator.
sendBeacon to best-effort flush on tab close. The manual Save
button is kept as a "save + switch to reader" shortcut. Ctrl/
Cmd+S still works in the editor.
4. Mobile layout.
The two-pane layout collapses to a single-pane view below 900px,
driven by a data-view attribute on .notes-layout. Back buttons
appear in the reader + editor heads on mobile to return to the
list. Desktop layout unchanged (sidebar + right pane always
visible).
Also:
• CSS specificity fix — .hidden{display:none} was losing to
.notes-rec-indicator{display:inline-flex} on source order, so
the "Recording" indicator was showing when idle. Added explicit
.notes-rec-indicator.hidden + .notes-voice-bar .btn-sm.hidden
overrides at higher specificity.
• Reader-body sanitizer — allowlist of safe tags + attributes;
<a> links get target=_blank + rel=noopener.
• SW cache bumped to pedscribe-v12-notes2 so clients pick up the
new module / component / CSS.
New "Notes" tab under Clinical Tools — a per-user scratchpad that's
explicitly NOT fed into AI prompts (distinct from user_memories).
Two-pane layout: searchable list on the left, rich-text editor with
title + save/edit/delete on the right.
Backend:
migrations/…_add-personal-notes.js — personal_notes table
(id, user_id → users ON DELETE CASCADE, title, body, created_at,
updated_at) with indexes on user_id + (user_id, updated_at).
src/routes/notes.js — CRUD + one AI endpoint:
GET /api/notes list, newest-updated first
GET /api/notes/:id fetch one
POST /api/notes create (title + body required)
PUT /api/notes/:id update
DELETE /api/notes/:id remove
POST /api/notes/from-voice transcript → { title, body }
via callAI (admin-controlled
provider — never selectable by
the clinician).
Body + title encrypted at rest via the same cryptoUtil used for
user_memories; 500-note per-user cap; 200-char title / 50 KB
body limits.
Frontend:
public/components/notes.html — empty-state card ("Hello 👋"),
sidebar list with search, editor head with voice-bar (Dictate /
Pause / Resume / Stop + live timer + pulse indicator), Tiptap
body, metadata footer. Uses existing .tp-* toolbar classes.
public/js/notes.js — lazy-init on first tab activation; Tiptap
editor built from window.Tiptap (same bundle the Content
Manager uses); delegated list clicks; Ctrl/Cmd+S to save;
uses app.js's AudioRecorder + transcribeAudio so the STT
pipeline is shared. On stop → transcribe → /api/notes/from-
voice → drop the AI-structured title + body into the editor;
clinician reviews then saves.
public/css/styles.css — 70 lines of .notes-* styles (card
layout, warm empty-state with gradient icon + tips, pulse
animation for the recording indicator, focus states, hover
nudges).
public/sw.js — bump cache from pedscribe-v12 → pedscribe-v12-
notes1 so clients pick up the new module/component.
Admin-controlled STT provider: the recorder posts its audio blob
to the existing /api/transcribe (Google / LiteLLM / ElevenLabs /
Browser Whisper — whatever admin wired up in Settings). Users
cannot pick the provider from this UI.
The route destructured PROMPTS/INJECTION_GUARD/wrapUserText from
../utils/prompts, but PROMPTS is the module's default export and the
other two live in ../utils/promptSafe. All three resolved to undefined,
so every /api/generate-pe-narrative request crashed with
"Cannot read properties of undefined (reading 'peGuideNarrative')"
and the client surfaced "Request failed" for PE Guide narrative and
summary generation. Split the require into the two-line form that
every other AI route already uses.
New top-level tab positioned after Physical Exam Guide. Per-user
directory of hospital phone extensions and pagers — grouped by location
then type, searchable, soft-deleted.
Data:
- New table user_phone_extensions (id, user_id, location, name, number,
type CHECK (extension|pager), notes, trashed_at, timestamps).
Partial indexes on active vs trashed rows for fast filtering.
- Not PHI — hospital internal phone directory. Plaintext.
API (all user-scoped, all params validated):
- GET /api/extensions?trash=1&q=text — list active or trash, optional search
- POST /api/extensions — create
- PUT /api/extensions/:id — update (requires all three core fields)
- DELETE /api/extensions/:id — soft-delete (sets trashed_at)
- POST /api/extensions/:id/restore — un-trash
- DELETE /api/extensions/:id/purge — hard-delete (only if trashed)
All :id params parsed + validated (positive integer) before query.
All queries parameterized, every WHERE includes user_id scoping.
UI (public/js/extensions.js + components/extensions.html):
- Search bar with 200ms debounce, server-side LIKE on location/name/number/notes
- Add button expands inline form — location (with datalist of existing
locations for autocomplete), name/dept, number, type, optional notes
- Each entry renders as a card: big monospace number, dept, type badge,
edit + delete inline
- Grouped by location → type (Extensions / Pagers subheaders)
- Trash view: toggle shows trashed items with Restore + Purge actions
- Trash count badge on the Trash button updates after every delete/restore
- Delete requires confirm() dialog, then soft-delete (easy to undo)
- Purge from trash requires a second confirm() ("cannot be undone")
- Esc closes the form; form resets between Add and Edit
Replaces the generic one-line-per-component format with a step-level
checklist. Each exam component now contains 3–13 discrete steps, each
with its own Normal/Abnormal/Skip toggle and optional abnormal note.
Physician ticks the exam off step-by-step; report generation
summarises at the component level but knows exactly which steps were
performed.
Example — previously the adolescent "Cranial nerves (II–XII)" was a
single row: "How to perform: Full formal adult-pattern exam. Expected:
All cranial nerves intact." That's unhelpful. Now it's 14 discrete
steps: CN I, CN II acuity, CN II fields, CN II fundoscopy, CN II/III
pupils, CN III/IV/VI EOM, CN V sensation V1/V2/V3, CN V motor, CN V
corneal, CN VII forehead/eye-close/smile/puff, CN VIII, CN IX/X, CN
XI, CN XII — each with specific method and expected finding. Same
depth for MSK: scoliosis = 5 discrete steps (standing inspection,
Adam forward-bend, rib-hump check, scoliometer, plumb-line), joint
stability = 8 named tests (Lachman, anterior drawer, varus/valgus,
McMurray, apprehension, Neer/Hawkins, anterior drawer ankle, talar
tilt), Beighton = 5 per-joint measurements, etc.
Sources cited in code header: Bates' Guide 13th ed, Nelson Textbook
22nd ed, Hutchison's Clinical Methods 25th ed, Fenichel Clinical
Pediatric Neurology 8th ed.
Backend route accepts the flat step array (grouped by component on
the server), passes structured text to the AI with methods and
expected findings per step. Prompts updated to summarise at the
component level rather than step-by-step, so output is clinically
readable.
Scope: MSK + Neuro × 6 age groups (newborn, infant, toddler, preschool,
school-age, adolescent). More systems follow the same pattern —
append to PE_DATA.
New top-level tab (positioned after Catch-Up Schedule) combining two
functions:
1. Study reference — for each (age group, system) shows OSCE-style
components with technique, expected normal finding, and abnormal-
feature watch-list.
2. Documentation generator — physician marks each component
Normal / Abnormal (with free-text detail) / Skip; AI produces a
two-section report (Technique + Findings), narrative or structured
list format.
Scope v1: MSK + Neuro × 6 age groups (newborn, infant, toddler,
preschool, school-age, adolescent). More systems can be added to the
embedded PE_DATA in peGuide.js without route changes.
Files:
- src/routes/peGuide.js — POST /api/generate-pe-narrative (mirrors
milestone-narrative pattern: AppRole-level
injection guard, clinical audit category,
PHI redaction upstream already in place)
- src/utils/prompts.js — peGuideNarrative + peGuideList prompts,
structured two-section output
- public/components/pe-guide.html — demographics bar + sub-pills + cards
- public/js/peGuide.js — embedded PE_DATA (all clinical content),
render + state + AI call
- public/index.html — tab button, section, script include
- server.js — mount route at /api
No schema change. No PHI stored — findings live in memory only, exported
via existing copy/read-aloud/Nextcloud actions.
Two independent PHI-leak hardenings folded together:
1. forgot-password timing oracle
The hit path previously did SELECT + token gen + UPDATE + SMTP send
before responding; the miss path returned after the SELECT. An
attacker could distinguish registered emails by response latency
(SMTP RTT is hundreds of ms). Response is now sent immediately after
Turnstile, with the DB and email work fired-and-forgotten in a
background async block. Hit and miss take identical wall-clock time.
Also hardened req.body.email to tolerate missing/non-string input
instead of throwing 500.
2. logger.file redaction
logger.info/warn/error wrote straight to /app/data/logs/YYYY-MM-DD.log
without going through redact(). Current callers are metadata-only and
safe, but any future caller writing logger.error('boom', req.body)
would silently drop PHI to disk. Route both message and optional data
through redact() — same helper the audit path already uses. Benign
startup messages pass through unchanged; SSN/phone/email/DOB patterns
are tokenised, long note-body-shaped text is truncated.
Extends the existing crypto helper (already used for audio backups and the
Nextcloud token) to cover every column that can hold PHI:
- saved_encounters.transcript, .generated_note, .partial_data
- user_memories.content (templates + Dragon-style corrections)
- user_memories.name (auto-derived from original snippet on corrections,
so effectively PHI)
Reads decrypt transparently. Legacy plaintext rows continue to work —
decryptString passes non-enc1: values through unchanged — so no migration
is required; rows re-encrypt on their next save.
The encounters list query previously used LEFT(transcript, 200) for a
preview. With ciphertext that slice is meaningless, so the route now
fetches the full columns, decrypts in Node, then slices. At 7-day auto-
delete the row count is bounded and the cost is a handful of GCM
decrypts per list call.
user_memories ORDER BY moved from (category, name) to (category, id)
since SQL can no longer order on encrypted names.
Closes the HHS breach-notification safe-harbor gap on at-rest PHI.
- 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
Age parser (src/routes/billing.js):
- Now sums year + month + week + day matches so "4 yr 11 mo"
(59 months) correctly maps to the 5-11y billing bracket instead
of being billed as 1-4y. Added bounds sanity check.
Graceful SIGTERM shutdown (server.js):
- Closes the HTTP listener first, then drains batched audit queues,
then ends the Postgres pool. 9-second hard deadline to beat
Docker's 10-second SIGKILL. Previously an in-flight note save
during a container restart could truncate the write.
Explicit LLM fallback opt-in (src/utils/ai.js):
- The OpenRouter / LiteLLM silent fallback now requires admin
setting `ai.allow_model_fallback = true` (default: false). If
primary fails and fallback is disabled, the error is surfaced
to the caller. Prevents silent spillover from a BAA-covered
primary to a non-covered fallback.
Prompt injection delimiters (src/utils/promptSafe.js):
- Wraps user transcripts, dictations, refine-instructions, and
pasted documents in <UNTRUSTED_*>...</UNTRUSTED_*> tags and
appends an explicit system instruction telling the model to
treat the wrapped content as data rather than commands.
- Applied to soap.js, hpi.js, refine.js. Extend to other AI
routes incrementally.
Cross-tab logout sync (public/js/authFetch.js, auth.js):
- BroadcastChannel('pedscribe-auth') — logout in one tab posts
a message; all sibling tabs clear state and reload, dropping
any PHI-containing UI immediately.
Backup code race-free consumption (src/routes/auth.js):
- tryConsumeBackupCode() now uses a Postgres transaction with
SELECT ... FOR UPDATE so concurrent login attempts using the
same code serialize. First wins, second sees the already-
shortened array.
Optimistic encounter locking (migrations/...add-encounter-version):
- saved_encounters.version INTEGER NOT NULL DEFAULT 1
- POST /api/encounters/saved accepts an expected_version and
rejects with 409 if the row has advanced. Falls back to
last-write-wins if the client doesn't pass one (backward compat).
Audit log batching (src/utils/auditQueue.js):
- Audit / api_log / access_log writes are buffered in memory and
flushed every 1s or every 50 entries via one multi-row INSERT.
Under load this reduces DB pressure by ~50x. On SIGTERM the
shutdown path drains the queue before exiting.
Two findings from review:
1. callAI() previously accepted any model string from the client.
POST /api/hpi with { model: "openai/o1" } would call the reasoning
model regardless of whether the operator enabled it. Added
getAllowedModelIds() in src/utils/models.js (60s TTL DB-backed
cache) and a guard at the top of callAI() that rejects with
"model_not_permitted" when the requested ID isn't in the active
roster. No model supplied → silent fallback to DEFAULT_MODEL.
2. Middleware was updating user_sessions.last_activity on every
request, including GETs. Client-side polling (/api/auth/me
heartbeats, dashboard refreshes, log tail calls) kept sessions
alive indefinitely, defeating the 24h sliding idle policy. Now
only POST/PUT/DELETE/PATCH count as "user activity". GETs are
read-only and often automated — they no longer extend the
session. Idle enforcement still runs on every method, so a
24h-idle user still gets kicked on their next GET.
Infrastructure only — no existing data or tables modified.
src/db/migrate.js — programmatic runner, fires at boot after
the existing idempotent initDatabase()
migrations/1744600000000... — intentionally empty example, documents
the file shape. Registered in the new
pgmigrations tracking table so it won't
rerun.
.node-pg-migraterc.json — CLI config (migrations-dir, utc naming)
docs/migrations.md — workflow + conventions
package.json — migrate:up/down/new/status npm scripts
(status is a direct pgmigrations query
since node-pg-migrate v7 lacks a status
subcommand)
src/utils/sessions.js:
- parseUserAgent now recognizes the Capacitor wrapper (UA suffix
"PedScribe-Android" / "PedScribe-iOS") and labels sessions
"PedScribe (Android)" instead of "Chrome on Android".
Going forward: schema changes go in /migrations as versioned files
with up() + down(); the inline init in database.js is the implicit
baseline for everything already in production.
After the hybrid auth migration, web users log in but the
setAuthCookie() helper was never actually called in /login or
/register — only in the OIDC callback. Result: local sign-in worked
until the first page reload, then the user appeared logged out. The
Settings page's Active Sessions list came up empty because
/api/sessions received no auth.
Added setAuthCookie(res, token) calls on successful:
- /register (auto-verified first admin path)
- /login (after TOTP / backup code verification)
Mobile is unaffected — it uses Bearer from Keychain and always has.
settings load2FAStatus():
- Explicit credentials: 'same-origin' on the /me fetch (was relying
on fetch defaults, which can behave oddly in some browsers/edges)
- Fall back to window.CURRENT_USER (cached at login) if /me fails,
so local-auth users still see their password/2FA sections after
a transient error. Keeps cache in sync on each successful fetch.
enterApp():
- Cache the logged-in user object on window.CURRENT_USER so modules
that need the canLocalAuth flag don't have to re-fetch /me.
2FA regenerate modal:
- Previous call passed a wrong-shape options object to showConfirm.
Updated to the correct (message, callback, opts) signature with
input:true, inputType:'password', placeholder, required.
OIDC email_verified check:
- Accept boolean true or string 'true' for robustness. Some IdPs
serialize ID-token booleans as strings.
Endpoint guards (defense-in-depth over hidden UI):
- POST /api/auth/change-password: 400 with SSO-aware message if
the caller's stored password is not a real bcrypt/argon2 hash.
Prior behaviour was to fail at passwords.verify() with an
ambiguous "current password is incorrect".
- POST /api/auth/setup-2fa: 400 with same SSO-aware message for
SSO-only accounts. Prior behaviour allowed TOTP setup on an
account where it could never actually trigger (user never logs
in locally).
OIDC account-link safety (src/routes/oidc.js):
- Auto-link to an existing local account now requires the IdP to
assert email_verified=true in the ID token (or userinfo). If
absent/false, the callback redirects with ?error=email_unverified.
Prevents an attacker at a misconfigured IdP from taking over a
local account by claiming an email they don't own.
- If an existing user already has oidc_sub set and the incoming
sub is different, refuse with ?error=sub_mismatch. Prior
behaviour silently did nothing, hiding a potential attack.
- Audit 'oidc_linked' written on first successful link.
Frontend:
- Added user-facing messages for the two new SSO error codes.
Middleware:
- Log to console.warn + audit_log when a session is killed for
inactivity. Shows up in Grafana/Loki so you can see how often
users actually get kicked. Audit action: 'session_idle_timeout'
- last_activity throttle bumped 5 min → 10 min — halves DB writes
per active user. Idle precision slop widens to 24h00-24h10;
still invisible in practice.
Per-user local-auth visibility:
- /api/auth/me now returns user.canLocalAuth: true when the stored
password is a real bcrypt / argon2 hash, false for the random
blob OIDC auto-creates for SSO-only users.
- Settings page hides "Change Password" and "Two-Factor
Authentication" sections when canLocalAuth is false — those UIs
are meaningless for users whose sign-in lives at the IdP.
- Password hash is not leaked in the /me payload.
Mobile (restating existing behaviour for clarity): no idle check,
365-day JWT in Keychain/Keystore, never auto-logs-out. Only logout
triggers are: manual logout, password change, admin revoke, JWT hit
365d, or app uninstall.
Session model:
Web — 24h sliding idle timeout enforced server-side via
user_sessions.last_activity. 30-day JWT + cookie are a
safety net; middleware is the real clock. Cookie is
re-set on active use so browsers match the sliding window.
Mobile — 365-day JWT, no idle timeout (stays persistent via Keychain
/ Keystore). Detected via User-Agent ("PedScribe" /
"Capacitor") or X-Client: mobile header.
2FA backup codes:
- 10 single-use codes generated when 2FA is first enabled
- Stored as bcrypt hashes in new users.totp_backup_codes column
- Consumed atomically on successful login fallback (when TOTP fails)
- Regenerate endpoint (POST /api/auth/2fa/backup-codes) requires
current password; invalidates prior codes
- Count endpoint (GET /api/auth/2fa/backup-codes/count) powers a
"N codes remaining" indicator on the 2FA settings card
- Modal shows codes exactly once with Copy + Download .txt actions
- Codes cleared when 2FA is disabled
New files:
src/utils/platform.js — isMobileClient() helper
Schema migration (idempotent):
ALTER TABLE users ADD COLUMN IF NOT EXISTS totp_backup_codes TEXT
Shortens both JWT expiresIn and httpOnly cookie maxAge to 24h in
auth.js (local + register + reset flows) and oidc.js (SSO callback).
Rationale: shorter absolute session window for a PHI-adjacent app.
No sliding idle refresh — user re-logs in once a day.
idx_users_email and idx_sessions_token_hash now use byte-order
collation so a future ICU library bump cannot silently corrupt the
indexes the way it did this week. The columns themselves retain
their default collation; only the index comparison is C, which is
safe for these because:
- users.email is lowercased ASCII in practice
- user_sessions.token_hash is SHA-256 hex (pure ASCII)
Both are used for equality lookups only, never ORDER BY. Migration
is idempotent, gated on app_settings.migration.text_indexes_c.
Slug indexes on learning_* tables left at default for now — those
are also ASCII in practice but under lighter load; the startup
drift check + auto-REINDEX covers them.
Root cause of recent "invalid credentials on correct password" was
a silent btree index corruption: pgvector/pgvector:pg16 was pulled
with a different ICU library than the one used to build existing
indexes. Queries returned 0 rows even though matching heap rows
existed. Postgres logged nothing (corrupt index → empty result set
is a "successful" query) and the login path never logged unknown-
user attempts (enumeration protection).
Three defenses:
1. Pin postgres image by digest in docker-compose.yml so a
silent pull can't change ICU under our feet.
2. Startup collation-drift check in src/db/database.js:
compares pg_database.datcollversion to the library's actual
version and, on mismatch, runs REINDEX DATABASE + ALTER
DATABASE REFRESH COLLATION VERSION. Logs "Collation versions:
aligned" on clean boot.
3. Server-side console.warn on login lookup-miss (no email, no
audit row — preserves enumeration protection but gives
Grafana/Loki a signal for unusual miss rates).
Root cause for "invalid credentials" on correct password was a
corrupt btree index (idx_users_email) causing user lookups to miss
existing rows. Fixed by REINDEX DATABASE. Keeping a typed catch
around passwords.verify() so any future verify throw is logged
cleanly instead of bubbling as 500.
- App-layer AES-256-GCM crypto helper (src/utils/crypto.js)
- Nextcloud tokens encrypted at rest; transparent migration on next use
- Audio backups encrypted at rest (version byte 0x01 envelope); legacy
rows still decrypt as-is until overwritten
- argon2id password hashing via src/utils/passwords.js with bcrypt
fallback; bcrypt hashes rehashed to argon2id on next successful login.
argon2 package is optional — server keeps running with bcrypt only
until npm install adds the native dep
- PHI redactor for audit log details (src/utils/redact.js) — strips SSN,
phone, email, DoB, long IDs; caps at 500 chars; detects note bodies
- DOMPurify (cdnjs, SRI-pinned) replaces custom regex sanitizer in
Learning Hub content rendering
- SRI integrity hashes added for Font Awesome CSS and Chart.js
- Magic-byte file-type verification on document uploads
(src/utils/fileType.js)
- Generic 500 error responses via src/utils/errors.js applied to
nextcloud and audioBackups; full detail still logged server-side
- DATA_ENCRYPTION_KEY env documented in .env.example
Deploy: requires rebuild of the container image to pick up the new
files and `npm install` (adds argon2). Existing users keep working
because bcrypt stays available and crypto helpers pass through
plaintext when the key is not yet set in dev.
- JWT_SECRET fails fast at startup in production
- CORS fails closed if APP_URL + CORS_ORIGINS are both missing
- Explicit HSTS (1y, includeSubDomains, preload)
- Rate limit sensitive auth endpoints (change-password, 2FA)
- /api/health now returns {ok:true}; details gated behind admin auth
- Login enumeration removed — generic 401 + dummy bcrypt on miss
- ReDoS guard: 20KB input cap on /suggest-codes
- showToast uses textContent, no innerHTML
- clearSession() clears service worker caches on logout
- OIDC state is now HMAC-signed and stateless (survives restart)
- SSRF guard on admin-set OIDC issuer (blocks private IPs, requires HTTPS)
Adds docs/mobile-build.md covering APK build, release, git push,
keystore, and troubleshooting for both PedScribe and PedsHub apps.
Loki logs now include:
- User agent string (browser/device identification)
- Session ID (ties actions to specific login session)
- Status field (success/failure)
New logging:
- encounter_load: logged when user opens a saved encounter (with label)
- copy_to_clipboard: logged when user copies note content (PHI access)
- Client event endpoint: POST /api/logs/client-event (auth required)
Encounter save/delete/load all include the encounter label for
patient identification in audit trail.
HIPAA audit trail now covers: who, what, when, from where, which
device, which session, what patient data, success/failure.
New feature: after generating any clinical note, the app automatically
suggests relevant billing codes displayed as clickable chips below the output.
Backend (src/routes/billing.js):
- POST /api/suggest-codes endpoint analyzes note text
- Extracts diagnoses from Assessment section via regex
- Looks up ICD-10 codes: local common pediatric map (40+ conditions)
first, then NLM Clinical Tables API for unknown terms
- Suggests CPT E/M codes based on note type, visit complexity,
ROS/PE system counts, and MDM level estimation
- Supports: outpatient (new/established), well visit (age-based),
ED, inpatient (admit/subsequent/discharge)
Frontend (public/js/app.js):
- suggestBillingCodes() renders collapsible card with ICD-10 and CPT chips
- Click any chip to copy the code to clipboard
- Shows E/M level assessment (diagnosis count, ROS, PE, MDM complexity)
- Disclaimer: "Suggestions only. Always verify codes."
Integration: called after note generation in all 6 tabs
(encounter, SOAP, sick visit, well visit, hospital course, chart review)
- Fix: DELETE all other sessions query used empty string fallback when
req.sessionId was undefined, causing id != '' to match ALL rows
(including current session). Now skips deletion if sessionId unknown.
- Fix: Revoke All endpoint returns error if current session not identified
- Fix: var confirm shadowing window.confirm in password change handler
Security:
- Add session management: users can view/revoke active sessions in Settings
- Add password change in Settings (requires current password, HIBP check)
- Force logout all sessions on password reset
- Fix logout to destroy server-side session (was only clearing cookie)
- Add trust proxy for correct client IP in rate limiting and audit logs
- Add CORS support for multiple domains (CORS_ORIGINS env var)
- Add HIBP breach check endpoint and inline warnings on password fields
Audit logging:
- Add audit logging to all 24 PHI-handling endpoints across 13 route files
- Covers: generation, transcription, TTS, refine, encounters, documents, Nextcloud
- All fire-and-forget (no response delay)
AI improvements:
- Refine now includes original source material (transcript, notes, labs)
so AI can reference the full input when modifying output
- Add correction tracking (trackAIOutput) to sick visit and well visit tabs
- Fix sickvisit missing from encounter save noteIdMap
UI fixes:
- Non-blocking busy bar for transcription and AI generation (replaces full-screen overlay)
- Fix encounter recording: hide record button during recording (was showing two stop buttons)
- Fix ROS/PE "All WNL" stacking duplicate event handlers; add Clear buttons
- Enlarge AI instructions textarea in Learning Hub CMS
Domain:
- Primary domain now app.pedshub.com, with scribe.pedshub.com and peds.danvics.com as CORS origins
- 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
NEW FEATURES:
- Bulk Import button in Admin Panel → Developmental Milestones section
- "Import Default Milestones Data" button appears when database is empty
- "Re-import All" button to clear and re-import all static data
- Visible notice when no milestones exist with one-click import
IMPROVEMENTS:
- Auto-shows empty state notice when database has no milestones
- Backend bulk-import endpoint now supports clearExisting parameter
- Imports ALL age groups from static data (birth to 11 years)
- Better UX - admin doesn't need CLI to populate milestone data
FIXES:
- Makes milestone admin editing feature discoverable and usable
- No need to manually run import script anymore
FIXES:
- Milestones now show correctly on encounter page (use static fallback if DB empty)
- Static data preserved as MILESTONES_DATA_STATIC for compatibility
- Database-driven milestones still work (admin can edit via CMS)
NEW FEATURES:
- OpenID Connect (OIDC) authentication support (PocketID, Keycloak, Azure AD, etc.)
- Comprehensive setup guide: OPENID_SETUP.md
- Auto-linking existing users by email on SSO login
- Multiple PDF upload support in Learning Hub (up to 10 files)
- 100 MB per file limit (was 20 MB)
- Full PDF content used for AI generation
- Embeddings use first ~8K chars for semantic search
IMPROVEMENTS:
- Updated UI to show multiple file selection with list
- Drag-and-drop supports multiple files
- Better file upload validation and error handling
- Added clarifying comments about embedding truncation
Features:
- Admin can add, edit, and delete developmental milestones via dashboard
- Milestones stored in PostgreSQL (developmental_milestones table)
- Client-side loads milestones from API instead of static file
- Import script to migrate existing static data to database
- Organized by age group and domain
- Supports sorting and filtering
Admin UI:
- New section in Admin panel for milestone management
- Filter by age group
- Add/Edit modal with validation
- Delete with confirmation
- Auto-complete for age groups and domains
API Endpoints:
- GET /api/milestones-data - Public endpoint for authenticated users
- GET /api/admin/milestones - List all milestones (admin only)
- GET /api/admin/milestones/meta - Get age groups and domains
- POST /api/admin/milestones - Create milestone
- PUT /api/admin/milestones/:id - Update milestone
- DELETE /api/admin/milestones/:id - Delete milestone
- POST /api/admin/milestones/bulk-import - Bulk import
Usage:
1. Run import script: node scripts/import-milestones.js
2. Access Admin dashboard → Developmental Milestones section
3. Add/Edit/Delete milestones as needed
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 /audio/transcriptions gives 'Unmapped provider' for Vertex AI Chirp.
The correct approach: use /v1/chat/completions with a Gemini model and send
audio as base64 input_audio content block — Gemini natively understands audio.
Set LITELLM_STT_MODEL to your Gemini model name (e.g. gemini-2.5-flash).
- Bug 1: When user selected "Outpatient" review type but had any subspecialty
visit cards filled in, the backend ignored the top-level type and switched to
the subspecialty prompt. Fixed: top-level type dropdown is now definitive.
Per-visit note types only control data formatting/labeling, not prompt selection.
- Bug 2: Labs entered in a visit card were silently dropped for outpatient and
subspecialty visits (only ED visit labs were included). Fixed: per-visit labs
now appear immediately after their visit content, labeled with the visit date.
- Improved lab labeling: visit labs are labeled "Labs from this visit (date)"
and the separate labs section is labeled "ADDITIONAL LABS (not tied to a
specific visit)" so the AI clearly distinguishes them.
- TTS response now includes X-TTS-Provider header (google-tts, litellm/model, elevenlabs)
- Frontend reads header and shows actual provider in toast instead of hardcoded "Adam/ElevenLabs"
- CORS exposes X-TTS-Provider header so frontend can access it
- Updated .env.example: clarify that LITELLM_TTS_MODEL and LITELLM_STT_MODEL
can be either the model_name alias OR the full provider/model path depending
on your LiteLLM config (important for BAA compliance routing)
vertex_ai/chirp does not work via LiteLLM's audio transcription proxy.
Changed default LITELLM_STT_MODEL from vertex_ai/chirp to whisper-1.
Updated .env.example documentation to match.
STT: Vertex AI Chirp not supported via LiteLLM proxy (confirmed by docs).
Now uses Gemini directly (transcribeGoogle.js) — auto-detected when
GOOGLE_VERTEX_PROJECT is set, fallback to AWS then OpenAI.
TTS: LiteLLM Vertex TTS DOES work but requires the model_list ALIAS
(tts-1) not the underlying path (vertex_ai/text-to-speech).
Also pass voice param — LiteLLM supports Google Cloud voice names.
Auto-detected when LITELLM_API_BASE is set.
LiteLLM's atranscription has a routing bug with Vertex AI Chirp proxy.
AWS Transcribe is already configured and working. Auto-detect now prefers
AWS over LiteLLM. Use TRANSCRIBE_PROVIDER=litellm to force LiteLLM.
- TTS: switch to axios, drop voice param (configured in LiteLLM per model)
- STT: log full LiteLLM error body so 500s are diagnosable in logs
- TTS: same error detail logging
- Fix 'ElevenLabs unavailable' toast to generic 'TTS unavailable'
- Add red Stop button to encounter recording UI
- TTS: switch from OpenAI SDK to axios (same fix as STT), drop voice
param since it's configured inside LiteLLM per model
- Fix 'ElevenLabs unavailable' toast shown even when provider is LiteLLM
- Add dedicated red Stop button to encounter recording UI
Vertex AI Chirp via LiteLLM rejects/hangs when 'prompt' and
'response_format' are included — these are OpenAI Whisper-only params.
Send only file + model for LiteLLM/Chirp.
Having LITELLM_API_BASE for AI text was auto-routing audio transcription
through LiteLLM even when the proxy has no Whisper model configured,
causing silent hangs. Now LiteLLM STT only activates when LITELLM_STT_MODEL
is explicitly set. Falls back correctly to AWS Transcribe when configured.
OpenAI SDK's audio.transcriptions.create() hangs with LiteLLM
(no timeout, SDK-level incompatibility with multipart handling).
Use axios + form-data directly with 120s timeout — same approach
as ElevenLabs TTS. Handles both {text:"..."} and plain string responses.
- 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
- TRANSCRIBE_PROVIDER=litellm routes audio to LiteLLM /audio/transcriptions
- TTS_PROVIDER=litellm routes to LiteLLM /audio/speech
- Both auto-detect when LITELLM_API_BASE is set (no extra config needed)
- LITELLM_STT_MODEL (default: whisper-1), LITELLM_TTS_MODEL (default: tts-1)
- LITELLM_TTS_VOICE (default: alloy) — alloy/echo/fable/onyx/nova/shimmer
- ElevenLabs still works if ELEVENLABS_API_KEY is set and TTS_PROVIDER=elevenlabs
- Health endpoint now reports tts provider
- 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
Audio Backups:
- New audio_backups table in PostgreSQL (bytea, gzip compressed)
- POST /api/audio-backups — upload with gzip compression (level 6)
- GET /api/audio-backups — list user's backups
- GET /api/audio-backups/:id/audio — download decompressed audio
- DELETE /api/audio-backups/:id — delete backup
- Auto-cleanup every hour (24h expiry)
- Frontend saves to server first, falls back to IndexedDB
- Settings shows source badge (server/local) per backup
AI Corrections:
- Corrections list is now expandable — click to view original vs corrected
- Shows red "Original" and green "Corrected to" sections
- Click arrow to expand/collapse each correction
- Date shown on each correction
- Add GET /api/transcribe/status endpoint — returns whether any server
transcription provider (Whisper/AWS/Local) is configured
- Frontend checks status on login via checkTranscribeStatus()
- When no provider configured: recording stops instantly, keeps live
Web Speech API text, shows friendly toast — no error, no upload wait
- Works in encounter, dictation, and SOAP tabs
- App now works fully out-of-the-box with just an AI provider key
Keep 8KB CHUNK_SIZE (proven stable) but replace 10ms setTimeout delay
with a microtask break every 16 chunks. This avoids the AWS SDK
"Deserialization error: inspect {error}.\$response" while still
eliminating the ~1.25s/MB artificial delay from the old 10ms sleep.
- AWS Transcribe: remove 10ms delay between chunks (was adding ~1.25s/MB),
increase chunk size from 8KB to 32KB (AWS max per frame)
- Add detailed timing logs (ffmpeg, streaming, total) for diagnostics
- OpenAI Whisper: use response_format='text' for faster response parsing
- Frontend: show transcription time in toast, request 16kHz sample rate,
increase bitrate to 32kbps Opus (better quality, still small files)
- Return duration in API response for all providers
- 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
- Add local Whisper (whisper.cpp / faster-whisper) as transcription provider
Set TRANSCRIBE_PROVIDER=local with configurable model size and binary path
- Upgrade all refine/instruction inputs to resizable textareas across
encounter, dictation, hospital course, chart review, well visit, sick visit
- Make AI memory injection flexible: physician preferences and corrections
are now actively applied (not just "formatting reference"), while still
overridable by current prompt instructions
- OIDC callback now passes only ?sso=ok flag, token stays in
httpOnly cookie (prevents token leaking to logs/referrer/history)
- Frontend auth.js uses cookie-based auth for SSO flow
- Add [PHYSICIAN TEMPLATES] boundary markers around physicianMemories
in all 5 generation routes to mitigate prompt injection
- Consistent boundary format across wellVisit, sickVisit, hpi, soap,
hospitalCourse
OIDC/SSO:
- New /api/auth/oidc route with PKCE for secure authorization
- Supports Azure AD, Okta, Keycloak, PocketID, Google, any OIDC provider
- Admin configurable: issuer, client ID/secret, button label
- Option to disable local auth (force SSO only)
- Auto-creates users on first SSO login, links existing by email
- SSO button on login page, hidden until admin enables OIDC
Firefox:
- Show info toast on first recording that live preview requires
Chrome/Edge; server-side transcription still works in all browsers
AWS Transcribe rejects audio event frames over ~16KB with a
cryptic "Deserialization error" / "Your stream is too big" message
hidden inside the SDK error object. Reducing to 8KB per chunk
fixes both Standard and Medical Transcribe streaming.
When Medical Transcribe fails (wrong IAM permissions, region not
supported), automatically falls back to Standard Transcribe instead
of returning an error. Logs the specific failure reason.
- Add try-catch to /nextcloud/disconnect route (was crashing on DB errors)
- Update docker-compose.yml image tag from v7 to v8
- Remove unused SESSION_SECRET from .env.example
Previously only well-visit and sick-visit used saved physician
templates. Now HPI encounter, HPI dictation, SOAP, and hospital
course all fetch getUserMemoryContext() and pass physicianMemories
to the backend so the AI learns from saved templates/preferences.
- transcribeAWS.js: convert browser WebM/Opus → PCM 16kHz mono via
ffmpeg before sending to AWS Transcribe — PCM is unambiguous and
most reliable; gracefully falls back to ogg-opus if ffmpeg absent
- Dockerfile: install ffmpeg (apk add ffmpeg) so Docker image works
out of the box with AWS Transcribe
- README: document Amazon Transcribe setup, ffmpeg requirement,
Transcribe Medical specialty options, and env vars reference
- New src/utils/transcribeAWS.js: streams audio directly to AWS
Transcribe without requiring an S3 bucket
- Supports AWS_TRANSCRIBE_MEDICAL=true for Transcribe Medical
(better clinical accuracy: drug names, diagnoses, procedures)
- AWS_TRANSCRIBE_SPECIALTY configures specialty (default PRIMARYCARE)
- transcribe.js auto-selects AWS when AWS_BEDROCK_REGION is set,
or can be forced with TRANSCRIBE_PROVIDER=aws|openai
- Falls back to OpenAI Whisper when AWS is not configured
- Add @aws-sdk/client-transcribe-streaming as optional dependency
- Update .env.example with transcription configuration docs
- Re-added Opus 4.6 (JSON sanitizer now handles its output)
- Added Logs & Debugging section with docker logs commands and prefixes
- Added Bedrock Model Notes (inference profiles, maxTokens, JSON sanitization)
- Updated version history through v5.8
- Updated rate limiting docs, build/push process, current image tag
Sonnet 4.6 outputs literal newline characters inside JSON string
values (e.g. in HTML body field) instead of \n escape sequences.
Added sanitizeJsonString that walks the string character by character
and escapes unescaped control chars inside quoted values.
- ALL models that need inference profiles now use us. prefix IDs:
Anthropic (all 8), Nova (3), Meta Llama (3), DeepSeek R1, Writer
- Models with low max output tokens (Cohere 4096, Jamba 4096) now
have maxOut field; callBedrock clamps maxTokens automatically
- Removed Qwen3 235B (no us-east-1 support, no inference profile)
- Added better debug logging for response block structure
Opus 4.6, Opus 4.5, Sonnet 4.6, Haiku 4.5 do NOT support direct
on-demand invocation — they require cross-region inference profile IDs
(us.anthropic.* prefix). Updated all affected bedrockIds. Also fixed
isAnthropic check to handle us.anthropic.* prefix.
Sonnet 4.5, Sonnet 4, 3.5 Haiku also updated to use profiles for
consistency (profiles work everywhere, direct IDs are limited).
- Opus 4.6 returns multiple content blocks (thinking + text); was only
reading content[0] which was the thinking block (just '{')
- Now iterates all blocks and extracts only type:'text' blocks
- Added debug logging for Bedrock response structure
- Re-added Nova Pro, Nova Lite, Nova Micro with correct region metadata
Opus 4.6 and other large models add preamble/thinking text before
JSON output. Fix: add system message enforcing JSON-only, strip
leading text before first {, trim trailing text after last }, and
log raw output on parse failure for debugging.
- Removed Amazon Nova models (not available for on-demand invocation)
- Replaced DeepSeek V3 with V3.2 (correct model ID)
- Removed Mistral Large 24.07 (us-west-2 only), added Magistral Small
- Added vendor model Opus 4.1, Writer Palmyra X5, Qwen3, Command R
- Each model now has region metadata; getAvailableModels() filters
to only show models available in the configured AWS_BEDROCK_REGION
- Fixes "on-demand throughput not allowed" and region mismatch errors
- New GET /api/learning/content/:slug/slides (authMiddleware only)
Renders Marp markdown via marp-core, returns {css, slides[]} for
any authenticated user — no moderator access required
- showViewer: when content_type === 'presentation', hides the body card
and shows a presentation card with title, slide count, and View Slides button
Auto-opens the slide modal immediately on load; button allows re-opening
- openSlidesFromSlug(): fetches slides from user-accessible endpoint
then opens the existing slide preview modal (arrow keys, swipe, dots)
- Viewer already correctly hides feed/categories/search when viewing content;
"Back to Feed" button returns to the main list
Login flash:
- Auth screen now hidden by CSS default (#auth-screen{display:none !important})
- auth.js shows it only when there is no valid token or token is expired
- No more flash of login page on refresh for logged-in users
Presentation quiz option (AI Generate panel):
- Presentation type now shows optional quiz question toggle (same as article)
- Backend: when questionCount>0, returns JSON {marpMarkdown, questions[]}
instead of plain Marp markdown
- applyAiContent fills both the Marp textarea and question blocks for presentations
Viewer revert:
- Removed the viewer presentation card change (user wants markdown as-is)
- Removed dangling viewer button wiring
Feed/CMS list:
- Presentation type shows correct icon (fa-presentation-screen) and
label "Slides" in the CMS content list
REVERT: httpOnly cookie auth removed — reverts to JWT in localStorage.
The cookie implementation broke the login page (always-hidden auth screen).
localStorage token approach is restored fully:
- Login/register return token in JSON body
- getAuthHeaders() sends Authorization: Bearer header
- Session check reads localStorage token on load
- clearSession() removes localStorage token
Fix: slide preview padding — section elements now have 40px 48px padding
so text is not flush against the frame edges.
Kept from v3.14: AI panel context-aware options (word count, slide count,
quiz question toggle), delete confirmation wording per content type.
AI Generate panel:
- Content type synced from editor on open
- Article/Pearl: optional word count field
- Presentation: optional slide count field
- Questions row: checkbox toggle for article/pearl (optional), always on for quiz,
hidden for presentation; count input shown only when enabled
- Backend: passes wordCount/slideCount to prompt; questionCount=0 skips questions
Delete confirmation:
- Wording built dynamically from content type
- Presentation: no mention of questions
- Quiz: "All quiz questions will be permanently removed"
- Article/pearl: "Any quiz questions attached will also be removed"
Auth refactor — JWT → httpOnly cookie:
- Backend: setAuthCookie() sets ped_auth as httpOnly, Secure, SameSite=Lax, 7d
- Backend: clearAuthCookie() on POST /api/auth/logout (new endpoint)
- Backend: auth middleware reads ped_auth cookie first, falls back to Bearer header
- Login/register: no longer return token in JSON body; cookie is the session
- Frontend: getAuthHeaders() returns only Content-Type (no Authorization header)
- Frontend: session check uses /api/auth/me via cookie (no localStorage token)
- Frontend: clearSession() calls /api/auth/logout to clear cookie server-side
- Frontend: no token in localStorage; window.AUTH_TOKEN removed
- All FormData fetches use credentials:'same-origin' (cookie sent automatically)
- index.html: optimistic auth-screen hide (removed localStorage token check)
Tested: login, logout, /api/auth/me, admin routes, FormData uploads, cookie httpOnly
flag, 401 without cookie, cookie cleared on logout.
