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_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
- 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
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
- 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
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.
- 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
- 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
- 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
- WNL/Normal systems now expand to 1-3 specific pertinent negatives instead of
just "WNL" — varies each time, relates to chief complaint and differential
(e.g., Skin: "no rash, no petechiae, no bruising" instead of "WNL")
- Abnormal systems: AI expands physician's brief note into clinical description
favoring most common presentation, adds only 1-2 related pertinent negatives
(e.g., "pimples on face" → "inflammatory papules on bilateral cheeks...")
- Format function now passes system domain details for context
- Rules applied to well visit (full + short) and sick visit prompts
- Growth reference data by age (newborn through 21y): expected weight/length/HC
gains per day/month/year, puberty growth spurt details
- Feeding/nutrition guidance by age: formula amounts, breastfeeding frequency,
solid food introduction timeline, juice limits, milk transitions, calorie needs
- BMI/obesity classification per AAP 2023 CPG + CDC Extended BMI:
Underweight, Healthy, Overweight, Obesity Class I/II/III with action items
(≥120% and ≥140% of 95th percentile thresholds)
- Weight-for-length guidance for children <2 years
- "By Visit" panel now shows growth reference + feeding guidance + BMI table
- Well visit AI prompt updated to include growth assessment, BMI classification,
and feeding counseling in generated notes
- Backend injects age-appropriate growth/nutrition data into AI context
- Bedrock: Add 14 non-vendor model models (Amazon Nova, Meta Llama 4, DeepSeek R1/V3,
Mistral Large 3, Cohere Command R+, AI21 Jamba) with verified AWS model IDs
- Bedrock: Implement Converse API for non-Anthropic models (unified cross-model API),
keep native Messages API for vendor model models (best performance)
- Milestones: Add Newborn / 1 month developmental milestones (Gross Motor, Fine Motor,
Language, Social/Emotional, Cognitive) — previously started at 2 months
- Bump version to 3.0.0, docker-compose tag to v3.0
- Source: docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html
- Added: vendor model Opus 4.6 (anthropic.agent-config-opus-4-6-v1)
- Added: vendor model Opus 4.5 (anthropic.agent-config-opus-4-5-20251101-v1:0)
- Added: vendor model Sonnet 4.6 (anthropic.agent-config-sonnet-4-6) — new default
- Added: vendor model Sonnet 4.5 (anthropic.agent-config-sonnet-4-5-20250929-v1:0)
- Kept: vendor model Sonnet 4, Haiku 4.5, vendor model 3.5 Haiku
- Fallback updated to vendor model Haiku 4.5
- Bump version to 2.9.0
- resetChartReview() clears all pasted notes, visit cards, labs, demographics, and output on New
- clearTab('chart') in encounters.js now calls resetChartReview() for complete reset
- chartReview route injects today's date so AI understands time-relative terms
- Bedrock models updated to vendor model-only with verified 2025 IDs (Sonnet 4, 3.7 Sonnet, 3.5 Sonnet v2, 3.5 Haiku)
- Removed Llama/Mistral/Titan from Bedrock; fixed incorrect vendor-model-4.6 Bedrock IDs
- Bump version to 2.8.0
Replace checkmark/X symbol format with plain numbered sentences:
achieved → 'Can walk independently'
not achieved → 'Cannot walk' / 'Does not yet use 2-word sentences'
- CSP connectSrc was blocking service worker re-fetches to cdnjs.cloudflare.com
causing Font Awesome icons to go blank (settings, logout, nextcloud buttons)
- Add cdnjs, googleapis, gstatic, google to connectSrc to fix icon rendering
and Chrome Web Speech API (which connects to Google servers for TTS voices)
- Add vendor model Opus 4.6 and vendor model Sonnet 4.6 to all three provider lists
(OpenRouter, Bedrock, Azure-compatible); Sonnet 4.6 now default for Bedrock
