Remove the --gh flag from release.sh

release.sh --gh ran `gh release create` against GitHub. This project
publishes releases to Forgejo, and CI does it automatically on a v* tag
push (.forgejo/workflows/android-apk.yml attaches the signed APK for
Obtainium). The flag could not do anything useful here, and having it in
the usage text implied a manual publish step that does not exist.

Drops the flag, its DO_RELEASE branch, and the usage/header references.
--push remains the only option.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

.dockerignore

@@ -3,7 +3,6 @@
 !.env.example
 .git
 .gitignore
-.agent-config
 node_modules
 data/
 *.log

.forgejo/workflows/android-apk.yml

@@ -0,0 +1,184 @@
+name: Forgejo Android APK
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - '**'
+    tags:
+      - 'v*'
+
+jobs:
+  build:
+    name: Build signed APK
+    runs-on: forgejo-local
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up JDK 17
+        uses: https://github.com/actions/setup-java@v4
+        with:
+          distribution: temurin
+          java-version: '17'
+
+      - name: Set up Node 20
+        uses: https://github.com/actions/setup-node@v4
+        with:
+          node-version: '20'
+          cache: npm
+          cache-dependency-path: mobile/package-lock.json
+
+      - name: Set up Android SDK
+        uses: https://github.com/android-actions/setup-android@v3
+
+      - name: Install Capacitor dependencies
+        working-directory: mobile
+        run: |
+          npm install --no-audit --no-fund
+          npx cap sync android
+
+      - name: Restore signing keystore
+        env:
+          KEYSTORE_B64: ${{ secrets.ANDROID_KEYSTORE_BASE64 }}
+        run: |
+          test -n "$KEYSTORE_B64"
+          CLEAN_KEYSTORE_B64="${KEYSTORE_B64#ANDROID_KEYSTORE_BASE64=}"
+          printf '%s' "$CLEAN_KEYSTORE_B64" | tr -d '\r\n' | base64 -d > "$RUNNER_TEMP/pedscribe-release.jks"
+          test -s "$RUNNER_TEMP/pedscribe-release.jks"
+
+      - name: Build signed release APK
+        working-directory: mobile/android
+        env:
+          KS_PASS: ${{ secrets.ANDROID_KEYSTORE_PASSWORD }}
+          KEY_ALIAS: ${{ secrets.ANDROID_KEY_ALIAS }}
+          KEY_PASS: ${{ secrets.ANDROID_KEY_PASSWORD }}
+        run: |
+          ./gradlew assembleRelease \
+            -Pandroid.injected.signing.store.file="$RUNNER_TEMP/pedscribe-release.jks" \
+            -Pandroid.injected.signing.store.password="$KS_PASS" \
+            -Pandroid.injected.signing.key.alias="$KEY_ALIAS" \
+            -Pandroid.injected.signing.key.password="$KEY_PASS" \
+            --no-daemon --stacktrace
+
+      - name: Check Google Play secret
+        id: play_publish
+        run: |
+          if [[ "$GITHUB_REF" != refs/tags/v* ]]; then
+            echo "enabled=false" >> "$GITHUB_OUTPUT"
+          elif [ -z "${GOOGLE_PLAY_SERVICE_ACCOUNT_JSON_B64:-}" ]; then
+            echo "enabled=false" >> "$GITHUB_OUTPUT"
+          else
+            echo "enabled=true" >> "$GITHUB_OUTPUT"
+          fi
+        env:
+          GOOGLE_PLAY_SERVICE_ACCOUNT_JSON_B64: ${{ secrets.GOOGLE_PLAY_SERVICE_ACCOUNT_JSON_B64 }}
+
+      - name: Build signed release App Bundle
+        if: steps.play_publish.outputs.enabled == 'true'
+        working-directory: mobile/android
+        env:
+          KS_PASS: ${{ secrets.ANDROID_KEYSTORE_PASSWORD }}
+          KEY_ALIAS: ${{ secrets.ANDROID_KEY_ALIAS }}
+          KEY_PASS: ${{ secrets.ANDROID_KEY_PASSWORD }}
+        run: |
+          ./gradlew bundleRelease \
+            -Pandroid.injected.signing.store.file="$RUNNER_TEMP/pedscribe-release.jks" \
+            -Pandroid.injected.signing.store.password="$KS_PASS" \
+            -Pandroid.injected.signing.key.alias="$KEY_ALIAS" \
+            -Pandroid.injected.signing.key.password="$KEY_PASS" \
+            --no-daemon --stacktrace
+
+      - name: Install fastlane
+        if: steps.play_publish.outputs.enabled == 'true'
+        working-directory: mobile/android
+        run: |
+          gem install bundler -N
+          bundle install
+
+      - name: Upload bundle to Google Play (internal track)
+        if: steps.play_publish.outputs.enabled == 'true'
+        working-directory: mobile/android
+        env:
+          GOOGLE_PLAY_SERVICE_ACCOUNT_JSON_B64: ${{ secrets.GOOGLE_PLAY_SERVICE_ACCOUNT_JSON_B64 }}
+          PLAY_TRACK: internal
+        run: |
+          test -n "$GOOGLE_PLAY_SERVICE_ACCOUNT_JSON_B64"
+
+          CLEAN_PLAY_JSON_B64="${GOOGLE_PLAY_SERVICE_ACCOUNT_JSON_B64#GOOGLE_PLAY_SERVICE_ACCOUNT_JSON_B64=}"
+          printf '%s' "$CLEAN_PLAY_JSON_B64" | tr -d '\r\n' | base64 -d > fastlane/google-play-service-account.json
+
+          AAB=$(find app/build/outputs/bundle/release -name '*.aab' | head -1)
+          test -n "$AAB"
+
+          AAB_PATH="$AAB" bundle exec fastlane android publish_internal
+
+          rm -f fastlane/google-play-service-account.json
+
+      - name: Collect APK
+        run: |
+          mkdir -p artifacts
+          APK=$(find mobile/android/app/build/outputs/apk/release -name '*.apk' | head -1)
+          test -n "$APK"
+          cp "$APK" "artifacts/pedscribe-${GITHUB_REF_NAME:-manual}.apk"
+
+      - name: Upload APK artifact
+        uses: https://github.com/actions/upload-artifact@v3
+        with:
+          name: pedscribe-android-apk
+          path: artifacts/*.apk
+          retention-days: 30
+
+      - name: Publish Forgejo release
+        if: startsWith(github.ref, 'refs/tags/v')
+        env:
+          FORGEJO_TOKEN: ${{ secrets.FORGEJO_TOKEN }}
+          TAG_NAME: ${{ github.ref_name }}
+          TARGET_COMMIT: ${{ github.sha }}
+        run: |
+          test -n "$FORGEJO_TOKEN"
+          API_URL="${GITHUB_SERVER_URL}/api/v1/repos/${GITHUB_REPOSITORY}"
+          APK=$(find artifacts -name '*.apk' | head -1)
+          test -n "$APK"
+
+          node - <<'NODE'
+          const fs = require('fs');
+          fs.writeFileSync('release-payload.json', JSON.stringify({
+            tag_name: process.env.TAG_NAME,
+            target_commitish: process.env.TARGET_COMMIT,
+            name: process.env.TAG_NAME,
+            body: 'Signed Android APK for Obtainium updates.',
+            draft: false,
+            prerelease: false,
+          }));
+          NODE
+
+          status=$(curl -sS -o release.json -w '%{http_code}' \
+            -X POST "$API_URL/releases" \
+            -H "Authorization: token $FORGEJO_TOKEN" \
+            -H 'Content-Type: application/json' \
+            --data-binary @release-payload.json)
+          if [ "$status" = "409" ]; then
+            curl -fsS "$API_URL/releases/tags/$TAG_NAME" \
+              -H "Authorization: token $FORGEJO_TOKEN" > release.json
+          elif [ "$status" != "201" ]; then
+            cat release.json
+            exit 1
+          fi
+
+          RELEASE_ID=$(node -e "console.log(JSON.parse(require('fs').readFileSync('release.json', 'utf8')).id)")
+          ASSET_NAME=$(basename "$APK")
+          export ASSET_NAME
+          curl -fsS "$API_URL/releases/$RELEASE_ID/assets" \
+            -H "Authorization: token $FORGEJO_TOKEN" > release-assets.json
+          EXISTING_ASSET_ID=$(node -e "const fs=require('fs'); const name=process.env.ASSET_NAME; const assets=JSON.parse(fs.readFileSync('release-assets.json','utf8')); const asset=assets.find((item)=>item.name===name); if (asset) console.log(asset.id);" )
+          if [ -n "$EXISTING_ASSET_ID" ]; then
+            curl -fsS -X DELETE "$API_URL/releases/$RELEASE_ID/assets/$EXISTING_ASSET_ID" \
+              -H "Authorization: token $FORGEJO_TOKEN"
+          fi
+
+          curl -fsS -X POST "$API_URL/releases/$RELEASE_ID/assets?name=$ASSET_NAME" \
+            -H "Authorization: token $FORGEJO_TOKEN" \
+            -F "attachment=@$APK" > release-asset.json

.forgejo/workflows/docker-build.yml

@@ -0,0 +1,45 @@
+name: Forgejo Docker Build
+
+on:
+  workflow_dispatch:
+    inputs:
+      push_image:
+        description: Push image to Forgejo container registry
+        required: false
+        default: 'true'
+
+jobs:
+  build:
+    name: Build Docker image
+    runs-on: forgejo-local
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Prepare compose env files
+        run: |
+          touch .env
+
+      - name: Validate Compose config
+        run: docker compose -f docker-compose.yml config >/tmp/ped-ai-compose.yml
+
+      - name: Build compose service
+        run: docker compose -f docker-compose.yml build pediatric-scribe
+
+      - name: Tag image
+        run: |
+          IMAGE="git.danvics.com/danvics/pediatric-ai-scribe-v3"
+          SHORT_SHA=$(git rev-parse --short HEAD)
+          docker tag ped-ai-local:latest "$IMAGE:$SHORT_SHA"
+          docker tag ped-ai-local:latest "$IMAGE:latest"
+
+      - name: Push image to Forgejo registry
+        if: ${{ github.event.inputs.push_image != 'false' }}
+        env:
+          FORGEJO_TOKEN: ${{ secrets.FORGEJO_TOKEN }}
+        run: |
+          IMAGE="git.danvics.com/danvics/pediatric-ai-scribe-v3"
+          SHORT_SHA=$(git rev-parse --short HEAD)
+          echo "$FORGEJO_TOKEN" | docker login git.danvics.com -u danvics --password-stdin
+          docker push "$IMAGE:$SHORT_SHA"
+          docker push "$IMAGE:latest"

.github/pull_request_template.md

@@ -0,0 +1,16 @@
+## Summary
+-
+-
+-
+
+## Type of change
+- [ ] refactor
+- [ ] feature
+- [ ] fix
+- [ ] docs
+
+## Verification
+What did you run locally? (e.g. `npm test`, `npm run typecheck`, manual smoke)
+
+## Linked issues
+Closes #

.github/workflows/android-release.yml

@@ -21,6 +21,7 @@ permissions:
 
 jobs:
   build:
+    if: ${{ github.server_url == 'https://github.com' }}
     name: Build signed APK
     runs-on: ubuntu-latest
     steps:

.github/workflows/auto-version.yml

@@ -31,7 +31,7 @@ permissions:
 jobs:
   version:
     runs-on: ubuntu-latest
-    if: "!contains(github.event.head_commit.message, 'Release v') && !contains(github.event.head_commit.message, '[skip ci]')"
+    if: "github.server_url == 'https://github.com' && !contains(github.event.head_commit.message, 'Release v') && !contains(github.event.head_commit.message, '[skip ci]')"
     steps:
       - name: Checkout
         uses: actions/checkout@v4

.github/workflows/build-apk.yml

@@ -14,6 +14,7 @@ env:
 
 jobs:
   build-apk:
+    if: ${{ github.server_url == 'https://github.com' }}
     runs-on: ubuntu-latest
     permissions:
       contents: write

.github/workflows/ci.yml

@@ -0,0 +1,34 @@
+name: CI
+
+# Runs root app tests on every PR and push to main.
+
+on:
+  pull_request:
+  push:
+    branches: [main]
+
+# Cancel superseded runs on the same ref to save minutes.
+concurrency:
+  group: ci-${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    name: Root app tests
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Node 22
+        uses: actions/setup-node@v4
+        with:
+          node-version: '22'
+          cache: 'npm'
+          cache-dependency-path: package-lock.json
+
+      - name: Install
+        run: npm install
+
+      - name: Unit tests
+        run: npm test

.github/workflows/docker-publish.yml

@@ -24,6 +24,7 @@ env:
 
 jobs:
   build:
+    if: ${{ github.server_url == 'https://github.com' }}
     # Build one variant per matrix entry, push by digest only.
     name: Build ${{ matrix.platform }}
     runs-on: ${{ matrix.runner }}
@@ -80,6 +81,7 @@ jobs:
           retention-days: 1
 
   merge:
+    if: ${{ github.server_url == 'https://github.com' }}
     # Combine the two single-platform digests into one multi-arch manifest
     # published under the real tags (vX.Y.Z and latest).
     name: Merge manifests

.github/workflows/security.yml

@@ -0,0 +1,30 @@
+name: Security audit
+
+# Weekly npm audit at high+ severity for the root app. Reports to the job summary; does NOT fail the build
+# (advisories appear constantly and a red checkmark train would just get
+# muted). Re-run on demand via workflow_dispatch.
+
+on:
+  schedule:
+    - cron: '0 6 * * 1'  # Mondays 06:00 UTC
+  workflow_dispatch:
+
+jobs:
+  audit:
+    name: npm audit (high+)
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup Node 22
+        uses: actions/setup-node@v4
+        with:
+          node-version: '22'
+
+      - name: Audit root app
+        run: |
+          echo '## Root app advisories' >> "$GITHUB_STEP_SUMMARY"
+          npm audit --audit-level=high --json > legacy-audit.json || true
+          node -e "const a=require('./legacy-audit.json');const m=a.metadata?.vulnerabilities||{};console.log('high:'+(m.high||0)+' critical:'+(m.critical||0));" >> "$GITHUB_STEP_SUMMARY"
+        continue-on-error: true

.github/workflows/version-bump.yml

@@ -30,6 +30,7 @@ permissions:
 
 jobs:
   bump:
+    if: ${{ github.server_url == 'https://github.com' }}
     runs-on: ubuntu-latest
     steps:
       - name: Checkout

.gitignore

@@ -36,3 +36,8 @@ public/models/
 e2e/node_modules/
 e2e/test-results/
 e2e/playwright-report/
+
+.codex
+.firecrawl/
+
+# Refactored test stack stays local for now

BROWSER_WHISPER_SETUP.md

@@ -1,174 +0,0 @@
-# Browser Whisper Self-Hosted Setup
-
-## Overview
-
-As of v3, Browser Whisper is **fully self-hosted** with **zero CDN dependencies**. All models and libraries are bundled with the application and served from your own server.
-
-## What Changed
-
-**Before (v2 and earlier):**
-- Loaded transformers.js from `cdn.jsdelivr.net`
-- Downloaded models from `cdn-lfs.huggingface.co`
-- Failed in corporate/clinical networks with firewall restrictions
-
-**Now (v3+):**
-- Transformers.js library (v2.6.2) bundled at `/models/transformers.min.js` (760KB)
-- Whisper model bundled at `/models/Xenova/whisper-tiny.en/` (42MB)
-- Everything served from your own server
-- **Works in any network environment** (firewalled, air-gapped, offline)
-
-## Files Included
-
-```
-public/models/
-├── transformers.min.js                    (760KB) - Transformers.js v2.6.2 (worker-compatible)
-└── Xenova/
-    └── whisper-tiny.en/                   (42MB total)
-        ├── config.json
-        ├── tokenizer.json
-        ├── preprocessor_config.json
-        ├── generation_config.json
-        └── onnx/
-            ├── encoder_model_quantized.onnx
-            └── decoder_model_merged_quantized.onnx
-```
-
-## How It Works
-
-1. **Worker loads transformers.js locally:**
-   ```javascript
-   importScripts('/models/transformers.min.js');
-   ```
-
-2. **Transformers.js configured for local models:**
-   ```javascript
-   T.env.localModelPath = '/models/';
-   T.env.allowRemoteModels = false;
-   ```
-
-3. **Models load from your server:**
-   - Browser requests: `GET /models/Xenova/whisper-tiny.en/config.json`
-   - Served by Express static middleware
-   - No external network calls
-
-## Docker Build
-
-Models are downloaded **during Docker build** (not runtime):
-
-```dockerfile
-RUN curl -sL -o onnx/encoder_model_quantized.onnx \
-    https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/onnx/encoder_model_quantized.onnx
-```
-
-This means:
-- Docker image is ~200MB larger (one-time cost)
-- Runtime has zero dependencies
-- Works in air-gapped environments (after image is pulled)
-
-## Development Setup
-
-If you're running locally (not Docker), download models:
-
-```bash
-cd public/models
-mkdir -p Xenova/whisper-tiny.en/onnx
-
-# Download transformers.js
-curl -L -o transformers.min.js \
-  https://cdn.jsdelivr.net/npm/@xenova/transformers@2.17.2/dist/transformers.min.js
-
-# Download model files
-cd Xenova/whisper-tiny.en
-curl -L -o config.json \
-  https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/config.json
-curl -L -o tokenizer.json \
-  https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/tokenizer.json
-curl -L -o preprocessor_config.json \
-  https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/preprocessor_config.json
-curl -L -o generation_config.json \
-  https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/generation_config.json
-curl -L -o onnx/encoder_model_quantized.onnx \
-  https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/onnx/encoder_model_quantized.onnx
-curl -L -o onnx/decoder_model_merged_quantized.onnx \
-  https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/onnx/decoder_model_merged_quantized.onnx
-```
-
-Or use the helper script:
-
-```bash
-./scripts/download-whisper-models.sh
-```
-
-## Adding More Models
-
-To add base or small models:
-
-1. **Create directory:**
-   ```bash
-   mkdir -p public/models/Xenova/whisper-base.en/onnx
-   ```
-
-2. **Download from HuggingFace:**
-   - https://huggingface.co/Xenova/whisper-base.en
-   - https://huggingface.co/Xenova/whisper-small.en
-
-3. **Update UI in `settings.html`:**
-   ```html
-   <option value="Xenova/whisper-base.en">Base (~74MB, better quality)</option>
-   ```
-
-4. **Update Dockerfile** to download during build
-
-## Benefits
-
-✅ **Works everywhere** - No firewall/CDN issues
-✅ **Privacy-first** - Audio never leaves browser
-✅ **Offline capable** - After initial page load
-✅ **No API costs** - Zero transcription expenses
-✅ **Predictable** - Same model, same results
-✅ **Fast** - Local processing, no network latency
-
-## Limitations
-
-- Docker image is larger (~200MB vs ~150MB)
-- Only tiny model included by default (base/small optional)
-- Slower than cloud APIs for long recordings
-- Requires modern browser with WebAssembly support
-
-## Testing
-
-```bash
-# 1. Start server
-docker-compose up -d
-
-# 2. Open browser DevTools → Network tab
-# 3. Go to Settings → Browser Transcription
-# 4. Click "Pre-download model"
-# 5. Watch for requests to /models/* (should all be 200 OK from your server)
-# 6. NO requests to cdn.jsdelivr.net or huggingface.co
-```
-
-## Troubleshooting
-
-**Issue: "Failed to load transformers library"**
-- Check: `GET /models/transformers.min.js` returns 200 OK
-- Verify file exists: `ls public/models/transformers.min.js`
-
-**Issue: "Model load failed"**
-- Check: `GET /models/Xenova/whisper-tiny.en/config.json` returns 200 OK
-- Verify files exist: `ls public/models/Xenova/whisper-tiny.en/`
-
-**Issue: Still seeing CDN requests**
-- Clear browser cache (Ctrl+Shift+R)
-- Check you're running v18+ (`/api/health` should show version)
-
-## Migration from v17
-
-If upgrading from v17:
-
-1. Pull new Docker image: `docker-compose pull`
-2. Restart: `docker-compose up -d`
-3. Clear browser cache
-4. Test: Settings → Browser Transcription → Pre-download
-
-No configuration changes needed - it just works!

BROWSER_WHISPER_TROUBLESHOOTING.md

@@ -1,240 +0,0 @@
-# Browser Whisper Troubleshooting
-
-## 🎙️ What is Browser Whisper?
-
-Browser Whisper is an **optional** client-side transcription feature that runs entirely in your browser using WebAssembly. It provides:
-- ✅ Zero network transmission (HIPAA-safe)
-- ✅ No API costs
-- ✅ Works offline
-- ✅ Privacy-first (audio never leaves device)
-
-**However**, it requires downloading AI models from CDN servers.
-
----
-
-## ⚠️ Common Issue: CDN Blocked
-
-### Error Message:
-```
-NetworkError: Failed to execute 'importScripts' on 'WorkerGlobalScope':
-The script at 'https://cdn.jsdelivr.net/npm/@xenova/transformers@2.17.2' failed to load.
-```
-
-### What This Means:
-Your network/firewall is blocking access to:
-- `cdn.jsdelivr.net` (JavaScript library CDN)
-- `cdn-lfs.huggingface.co` (AI model files)
-
-### Why It Happens:
-1. **Corporate firewall** - Many organizations block CDN domains
-2. **Browser extensions** - Ad blockers, privacy tools may block CDN
-3. **Network proxy** - Company proxy might filter JavaScript CDN
-4. **CSP restrictions** - Very strict Content Security Policy
-
----
-
-## ✅ Solutions
-
-### Option 1: Use Server Transcription (Recommended)
-
-**Browser Whisper is optional!** The app works perfectly fine with server-side transcription.
-
-**Server transcription providers:**
-- Google Gemini (via Vertex AI) - HIPAA-eligible
-- AWS Transcribe - HIPAA-eligible
-- OpenAI Whisper - Fast, accurate
-- LiteLLM - Routes to any provider
-
-**To use server transcription:**
-1. Go to Settings → Browser Transcription
-2. **Leave it disabled** (or if stuck, disable it)
-3. Record audio normally - will use server
-
-**Advantages:**
-- More accurate (larger models)
-- No download needed
-- Works immediately
-- Professional grade
-
-### Option 2: Whitelist CDN Domains
-
-If you control your network/firewall, whitelist these domains:
-
-```
-cdn.jsdelivr.net
-cdn-lfs.huggingface.co
-cdn-lfs-us-1.huggingface.co
-cdn-lfs-us-2.huggingface.co
-huggingface.co
-```
-
-**For corporate IT:**
-- These are legitimate AI/JavaScript CDNs
-- Used by major companies worldwide
-- No security risk (public CDN content)
-- Required only for browser-based AI features
-
-### Option 3: Disable Browser Extensions
-
-Try disabling:
-- Ad blockers (uBlock Origin, AdBlock Plus)
-- Privacy extensions (Privacy Badger, Ghostery)
-- Script blockers (NoScript, ScriptSafe)
-
-Then refresh and try again.
-
-### Option 4: Try Different Browser
-
-Some browsers have stricter security:
-- ✅ **Chrome** - Best compatibility
-- ✅ **Edge** - Works well
-- ⚠️ **Firefox** - May block CDN
-- ❌ **Safari** - Limited WebAssembly support
-
----
-
-## 🧪 How to Test If It's Working
-
-### Test 1: Check CDN Access
-```bash
-# From your computer, run:
-curl -I https://cdn.jsdelivr.net/npm/@xenova/transformers@2.17.2
-
-# Should return: HTTP/2 200
-# If 403 or timeout: CDN is blocked
-```
-
-### Test 2: Browser Console
-1. Open DevTools (F12)
-2. Go to Console tab
-3. Settings → Browser Transcription
-4. Click "Pre-download model"
-5. Watch for:
-   ```
-   ✅ [WhisperWorker] Transformers library loaded successfully
-   OR
-   ❌ NetworkError: Failed to load
-   ```
-
-### Test 3: Network Tab
-1. Open DevTools (F12)
-2. Go to Network tab
-3. Click "Pre-download model"
-4. Look for requests to:
-   - `cdn.jsdelivr.net` (should be 200 OK)
-   - `cdn-lfs.huggingface.co` (should be 200 OK)
-5. If blocked: Status will show "failed" or "blocked"
-
----
-
-## 📊 When to Use Each Option
-
-| Scenario | Recommendation | Why |
-|----------|---------------|-----|
-| Corporate network | **Server transcription** | CDN likely blocked |
-| Home network | **Browser Whisper** | Fast, free, private |
-| Mobile device | **Server transcription** | Limited storage/memory |
-| Offline use needed | **Browser Whisper** | Works without internet (after initial download) |
-| High accuracy needed | **Server transcription** | Larger models available |
-| Maximum privacy | **Browser Whisper** | Audio never leaves device |
-| Can't access CDN | **Server transcription** | No choice - CDN blocked |
-
----
-
-## 🔧 Technical Details
-
-### What Gets Downloaded (First Time Only):
-
-**Tiny model** (~39 MB):
-- onnx-runtime.wasm (~10 MB)
-- whisper-tiny.en model files (~29 MB)
-- Cached in browser IndexedDB (permanent)
-
-**Base model** (~74 MB):
-- Larger model, better accuracy
-
-**Small model** (~244 MB):
-- Best quality, slower processing
-
-### Where It's Stored:
-- **Location:** Browser IndexedDB
-- **Persistence:** Permanent (until you clear browser data)
-- **Shared:** Across all tabs/windows for this domain
-- **Size:** Selected model size (39/74/244 MB)
-
-### Performance:
-- **Tiny:** 2-3 seconds per 30-second clip
-- **Base:** 3-5 seconds per 30-second clip
-- **Small:** 6-10 seconds per 30-second clip
-
----
-
-## ❓ FAQ
-
-**Q: Is Browser Whisper required?**
-A: No! It's completely optional. Server transcription works great.
-
-**Q: Why doesn't it work on my corporate network?**
-A: Most corporate firewalls block CDN domains for security. Use server transcription instead.
-
-**Q: Can I download the models manually?**
-A: Not easily - they're optimized for CDN delivery. Use server transcription if CDN is blocked.
-
-**Q: Will server transcription cost money?**
-A: Depends on your provider:
-- Google Vertex AI: ~$0.005 per minute
-- AWS Transcribe: ~$0.024 per minute
-- OpenAI: $0.006 per minute
-- Very affordable for typical use
-
-**Q: Is server transcription HIPAA-safe?**
-A: Yes, if using:
-- Google Vertex AI (with BAA)
-- AWS Transcribe (with BAA)
-- Azure OpenAI (with BAA)
-
-OpenAI Whisper direct is NOT HIPAA-eligible.
-
-**Q: Can I use both?**
-A: Yes! Enable Browser Whisper in Settings. If it fails (CDN blocked), it automatically falls back to server transcription.
-
-**Q: How do I know which one is being used?**
-A: Check the toast notification after recording:
-- "Transcribed locally" = Browser Whisper
-- "Transcribed via google-gemini/aws/openai" = Server
-
----
-
-## 🚀 Recommended Setup
-
-### For Maximum Privacy (Home Network):
-1. Enable Browser Whisper
-2. Choose "Tiny" model (fast, good enough for dictation)
-3. Pre-download model
-4. Use offline
-
-### For Corporate/Clinical Use:
-1. Keep Browser Whisper **disabled**
-2. Configure server transcription:
-   ```bash
-   # In .env:
-   TRANSCRIBE_PROVIDER=google
-   GOOGLE_VERTEX_PROJECT=your-project
-   ```
-3. Use with BAA for HIPAA compliance
-
-### For Best Accuracy:
-1. Use server transcription
-2. Configure Google Gemini 2.0 Flash or AWS Transcribe Medical
-3. Audio quality + large models = best results
-
----
-
-## 🛠️ Still Having Issues?
-
-1. **Check console logs:** DevTools → Console → Look for `[BrowserWhisper]` errors
-2. **Check network logs:** DevTools → Network → Filter by `jsdelivr` or `huggingface`
-3. **Verify server transcription works:** Just disable Browser Whisper and record
-4. **Contact IT:** Ask to whitelist CDN domains (if you need Browser Whisper)
-
-**Remember:** Browser Whisper is a nice-to-have feature. Server transcription is the primary, production-ready method that works everywhere!

CONTRIBUTING.md

@@ -28,7 +28,7 @@ or Actions tab → **Version bump & release** → Run workflow → pick bump typ
 
 | Workflow | Output |
 |---|---|
-| `android-release.yml` | signed APK on GitHub release, `make_latest=true` |
+| `.forgejo/workflows/android-apk.yml` | signed APK on Forgejo release (`pedscribe-<tag>.apk`), optional Google Play internal track upload |
 | `docker-publish.yml` | `danielonyejesi/pediatric-ai-scribe-v3:{version,latest}` on Docker Hub (amd64) |
 
 ## Local dev

DEVELOPER_GUIDE.md

@@ -1,976 +0,0 @@
-# Pediatric AI Scribe — Developer Guide
-**Version:** 6.0 | **Stack:** Node.js / Express / PostgreSQL / Vanilla JS
-
----
-
-## Table of Contents
-
-1. [Project Overview](#1-project-overview)
-2. [Architecture](#2-architecture)
-3. [Directory Structure](#3-directory-structure)
-4. [Environment Variables](#4-environment-variables)
-5. [Database Schema](#5-database-schema)
-6. [Authentication System](#6-authentication-system)
-7. [Backend API Reference](#7-backend-api-reference)
-8. [Frontend Architecture](#8-frontend-architecture)
-9. [AI Integration](#9-ai-integration)
-10. [Learning Hub & CMS](#10-learning-hub--cms)
-11. [Deployment](#11-deployment)
-12. [Known Issues & Security Notes](#12-known-issues--security-notes)
-13. [Adding New Features](#13-adding-new-features)
-14. [Resetting Admin Password via Console](#14-resetting-admin-password-via-console)
-
----
-
-## 1. Project Overview
-
-Pediatric AI Scribe is a clinical documentation platform for pediatric healthcare providers. It uses AI (via OpenRouter, AWS Bedrock, or Azure OpenAI) to generate:
-
-- HPI notes from live encounter recordings
-- SOAP notes from dictation
-- Hospital course summaries
-- Chart reviews
-- Well-visit notes (including SSHADESS, ROS/PE, milestones)
-- Sick visit notes
-- Learning Hub content (articles, quizzes, clinical pearls, presentations)
-
-**Key design principle:** Single-page application. All tabs are lazy-loaded HTML components (`/public/components/*.html`). JavaScript modules initialize only when their tab is first activated via the `tabChanged` custom event.
-
----
-
-## 2. Architecture
-
-```
-Browser (Vanilla JS + Tiptap)
-       |
-       | HTTP (JWT Bearer token in Authorization header)
-       |
-Express.js (Node.js) — server.js
-       |
-       |— Helmet (CSP, security headers)
-       |— CORS (restricted to APP_URL in production)
-       |— express-rate-limit (login: 10/15min, register: 5/hr, resend-verify: 3/15min, general: 60/min)
-       |— cookie-parser
-       |— Routes (/src/routes/)
-       |
-PostgreSQL (pg driver, no ORM)
-       |
-       |— users, app_settings, audit_log, saved_encounters
-       |— user_memories, learning_*, access_log, api_log
-```
-
-### How Requests Flow
-
-1. **Browser** sends HTTP request with `Authorization: Bearer <jwt>` header
-2. **Express middleware chain:** Helmet (security headers) → CORS → rate limiter → body parser → logging middleware → route handler
-3. **Auth middleware** (`src/middleware/auth.js`) decodes JWT, queries `users` table, attaches `req.user` with `{ id, email, name, role }`
-4. **Route handler** processes the request — for AI routes, calls `callAI()` which routes to the configured provider
-5. **Database** is accessed via the `pg` driver directly (no ORM). All queries use parameterized placeholders (`$1`, `$2`) to prevent SQL injection
-6. **Response** is JSON for API calls, or static files served from `/public`
-
-### AI Providers
-
-Configured via environment variables. The provider is selected at startup in `src/utils/ai.js` using this priority:
-
-1. **AWS Bedrock** — if `AWS_BEDROCK_REGION` is set. HIPAA eligible with BAA. Uses `@aws-sdk/client-bedrock-runtime`. Anthropic models use the native Messages API (`InvokeModel`); all others use the Converse API.
-2. **Azure OpenAI** — if `AZURE_OPENAI_ENDPOINT` is set. HIPAA eligible. Uses the OpenAI SDK pointed at your Azure endpoint.
-3. **OpenRouter** — default fallback if `OPENROUTER_API_KEY` is set. Routes to 20+ models from various providers. Not HIPAA compliant.
-
-The provider cannot be changed at runtime — it's determined once at startup. To switch providers, update `.env` and restart the container.
-
-### Database Layer
-
-The app uses **raw SQL via the `pg` driver** — no ORM (Sequelize, Prisma, etc.). This is intentional:
-
-- **Simplicity:** Every query is visible and explicit. No magic, no migrations framework, no model definitions to sync.
-- **Performance:** No ORM overhead or N+1 query problems.
-- **Schema management:** `src/db/database.js` runs `CREATE TABLE IF NOT EXISTS` on startup, plus `ALTER TABLE ... ADD COLUMN IF NOT EXISTS` for migrations. This means the schema is always up-to-date when the app starts.
-- **Future ORM migration:** If needed, the queries are standard PostgreSQL and can be wrapped by any ORM. The main work would be defining models and replacing direct `db.get()`/`db.run()` calls.
-
-The `database.js` file exports a helper object (`db`) with convenience methods:
-- `db.get(sql, params)` — returns first row or `null`
-- `db.all(sql, params)` — returns all rows as array
-- `db.run(sql, params)` — executes INSERT/UPDATE/DELETE, returns `{ rowCount }`
-- `db.getSetting(key)` / `db.setSetting(key, value)` — shorthand for `app_settings` table
-
----
-
-## 3. Directory Structure
-
-```
-/
-├── server.js                   # Express app entry point (route registration, Helmet CSP,
-│                               #   rate limiters, static file serving, error handlers)
-├── package.json                # Dependencies (~25 production deps, no devDeps)
-├── Dockerfile                  # Multi-stage Node.js 20 Alpine build
-├── docker-compose.yml          # Production compose (uses Docker Hub image)
-├── docker-compose.local.yml    # Local development (builds from source, port 3552)
-├── admin-cli.js                # CLI tool for admin tasks (create user, reset password)
-├── DEVELOPER_GUIDE.md          # This file
-│
-├── src/
-│   ├── db/
-│   │   └── database.js         # DB connection pool (pg.Pool), schema init
-│   │                           #   (CREATE TABLE IF NOT EXISTS for all tables),
-│   │                           #   column migrations (ALTER TABLE ADD COLUMN IF NOT EXISTS),
-│   │                           #   helper methods: db.get(), db.all(), db.run(),
-│   │                           #   db.getSetting(), db.setSetting()
-│   ├── middleware/
-│   │   ├── auth.js             # authMiddleware (JWT decode → req.user),
-│   │                           #   adminMiddleware (role === 'admin'),
-│   │                           #   moderatorMiddleware (role === 'admin' || 'moderator')
-│   │   └── logging.js          # Logs every request to api_log table (method, path, user, IP, duration)
-│   ├── routes/
-│   │   ├── auth.js             # Login, register, 2FA, password reset, /me
-│   │   ├── admin.js            # User management (admin only)
-│   │   ├── adminConfig.js      # Site settings, feature flags, AI prompts, models
-│   │   ├── encounters.js       # Save/load/delete draft encounters
-│   │   ├── memories.js         # User templates (physical exam, ROS, etc.)
-│   │   ├── hpi.js              # Generate HPI from encounter/dictation transcript
-│   │   ├── soap.js             # Generate SOAP note
-│   │   ├── hospitalCourse.js   # Generate hospital course summary
-│   │   ├── chartReview.js      # Generate outpatient chart review
-│   │   ├── milestones.js       # Generate developmental milestone narrative
-│   │   ├── wellVisit.js        # Well-visit note generation (ROS/PE/ICD-10)
-│   │   ├── sickVisit.js        # Sick visit note generation
-│   │   ├── refine.js           # Refine/shorten any generated document
-│   │   ├── transcribe.js       # Whisper audio transcription
-│   │   ├── tts.js              # Text-to-speech (if configured)
-│   │   ├── nextcloud.js        # Nextcloud WebDAV connect/export/disconnect
-│   │   ├── learningHub.js      # User-facing: feed, content, quiz submission
-│   │   ├── learningAdmin.js    # CMS: categories, content, questions CRUD
-│   │   ├── learningAI.js       # AI generation for Learning Hub content
-│   │   └── logs.js             # Usage/audit/API/access logs + client error
-│   └── utils/
-│       ├── ai.js               # callAI(messages, options) — routes to OpenRouter/Bedrock/Azure.
-│       │                       #   Handles Anthropic InvokeModel (Messages API) vs Converse API,
-│       │                       #   thinking block extraction, fallback model retry, duration tracking.
-│       ├── models.js           # OPENROUTER_MODELS[], BEDROCK_MODELS[], AZURE_MODELS[]
-│       │                       #   Each model: { id, name, cost, tag, category, bedrockId, maxOut, regions }
-│       │                       #   getBedrockModelId() maps app IDs to Bedrock/inference profile IDs.
-│       │                       #   getAvailableModels() filters by region. getAvailableModelsWithOverrides()
-│       │                       #   applies admin-disabled/custom models from DB.
-│       ├── prompts.js          # Default prompt templates for every AI route. Loaded on startup,
-│       │                       #   then overridden by DB values (app_settings: 'prompt.*' keys).
-│       │                       #   PROMPTS.get('key') returns the DB override or default.
-│       ├── config.js           # App configuration helpers
-│       └── logger.js           # Winston logger (file + console, JSON format)
-│
-├── public/
-│   ├── index.html              # Single HTML shell, loads all components
-│   ├── 404.html                # Custom 404 page
-│   ├── css/
-│   │   └── styles.css          # All CSS (single file, ~750 lines)
-│   ├── js/
-│   │   ├── app.js              # Core: tab switching via data-tab buttons, loadComponent()
-│   │   │                       #   fetches HTML from /components/, global helpers (showToast,
-│   │   │                       #   showLoading, getAuthHeaders, getSelectedModel, etc.)
-│   │   ├── auth.js             # Login/register/forgot-password forms, JWT storage in
-│   │   │                       #   localStorage ('ped_scribe_token'), enterApp()/clearSession(),
-│   │   │                       #   resend verification link handler, 2FA code input
-│   │   ├── admin.js            # Admin panel: user management, site settings, SMTP config,
-│   │   │                       #   model enable/disable, prompt editor, announcement banner
-│   │   ├── liveEncounter.js    # MediaRecorder → Whisper transcription → AI HPI generation.
-│   │   │                       #   Handles start/stop recording, timer, save/load encounters
-│   │   ├── voiceDictation.js   # Web Speech API (real-time) or Whisper (recorded) dictation
-│   │   ├── hospitalCourse.js   # Paste/dictate hospital course → AI summary
-│   │   ├── chartReview.js      # Paste/dictate chart data → AI outpatient review
-│   │   ├── soap.js             # Paste/dictate → AI SOAP note
-│   │   ├── milestones.js       # Age-based milestone checklist → AI narrative
-│   │   ├── wellVisit.js        # Well Visit guide: vaccine schedule display, age calculator
-│   │   ├── shadess.js          # SSHADESS psychosocial form + ROS/PE checkboxes → AI note
-│   │   ├── sickVisit.js        # Chief complaint + HPI → AI sick visit SOAP
-│   │   ├── nextcloud.js        # Nextcloud WebDAV connect/disconnect/export settings UI
-│   │   ├── encounters.js       # Save/load/delete encounter drafts (shared across all tabs)
-│   │   ├── memories.js         # User template CRUD (physical exam defaults, ROS, etc.)
-│   │   ├── learningHub.js      # Learning Hub (user feed, content viewer, quiz engine) +
-│   │   │                       #   CMS (category CRUD, content editor with Tiptap, question
-│   │   │                       #   builder, AI generation panel, Nextcloud file picker,
-│   │   │                       #   slide preview modal). Single file, ~1400 lines.
-│   │   ├── milestonesData.js   # Static milestone data by age group (2mo → 6yr)
-│   │   └── pediatricScheduleData.js  # CDC vaccine schedule data + catch-up schedule
-│   ├── components/             # Lazy-loaded tab HTML (injected by loadComponent)
-│   │   ├── encounter.html      ├── dictation.html   ├── hospital.html
-│   │   ├── chart.html          ├── soap.html        ├── wellvisit.html
-│   │   ├── sickvisit.html      ├── vaxschedule.html ├── catchup.html
-│   │   ├── learning.html       ├── cms.html         ├── admin.html
-│   │   └── settings.html
-│   └── vendor/
-│       └── tiptap.bundle.js    # Tiptap 2 + extensions (esbuild bundle, self-hosted)
-```
-
----
-
-## 4. Environment Variables
-
-Set in `.env` file (copy `.env.example` to get started):
-
-```bash
-# ── Required ──────────────────────────────────────────────────
-DATABASE_URL=postgresql://user:<password>@host:5432/dbname
-JWT_SECRET=change-this-to-a-random-64-char-string
-
-# ── AI Provider (choose one or let it default to OpenRouter) ──
-OPENROUTER_API_KEY=sk-or-...         # Default provider
-# OR
-AZURE_OPENAI_ENDPOINT=https://...    # Azure (HIPAA eligible)
-AZURE_OPENAI_API_KEY=...
-AZURE_DEPLOYMENT_NAME=gpt-4o-mini
-AZURE_OPENAI_API_VERSION=2024-08-01-preview
-# OR
-AWS_BEDROCK_REGION=us-east-1         # AWS Bedrock (HIPAA eligible)
-AWS_ACCESS_KEY_ID=...
-AWS_SECRET_ACCESS_KEY=...
-
-# ── Optional ──────────────────────────────────────────────────
-OPENAI_API_KEY=sk-...                # For Whisper transcription only
-APP_URL=https://yourdomain.com       # Enables secure CORS + Secure cookies
-NODE_ENV=production                  # Enables production optimizations
-PORT=3000                            # Default: 3000
-
-# ── Email (for password reset, registration verification) ──────
-SMTP_HOST=smtp.example.com
-SMTP_PORT=587
-SMTP_USER=noreply@example.com
-SMTP_PASS=...
-SMTP_FROM=Pediatric AI Scribe <noreply@example.com>
-```
-
-**Note:** If no SMTP is configured, registration auto-verifies and password reset won't work. Configure SMTP or use the console reset method (see Section 14).
-
----
-
-## 5. Database Schema
-
-All tables are created automatically on first run by `src/db/database.js`. The file runs `CREATE TABLE IF NOT EXISTS` for every table, followed by `ALTER TABLE ... ADD COLUMN IF NOT EXISTS` migrations for upgrades.
-
-### Core Tables
-
-#### `users`
-| Column | Type | Notes |
-|--------|------|-------|
-| id | SERIAL PK | |
-| email | TEXT UNIQUE | Lowercase |
-| password | TEXT | bcrypt hash (cost 12) |
-| name | TEXT | Display name |
-| role | TEXT | `'user'` \| `'moderator'` \| `'admin'` |
-| totp_enabled | BOOLEAN | 2FA status |
-| totp_secret | TEXT | TOTP secret (base32) |
-| disabled | BOOLEAN | Soft disable |
-| email_verified | BOOLEAN | |
-| verify_token / verify_expires | TEXT / BIGINT | Email verification |
-| reset_token / reset_expires | TEXT / BIGINT | Password reset |
-| nextcloud_url / nextcloud_user / nextcloud_token / nextcloud_folder | TEXT | Nextcloud integration |
-| webdav_learning_path | TEXT | Default WebDAV path for Learning Hub file picker |
-| created_at | TIMESTAMPTZ | |
-
-#### `app_settings`
-Key-value store for all site configuration. Read via `db.getSetting(key)`, written via admin panel or direct DB.
-
-Important keys:
-- `registration_enabled` — `'true'` / `'false'`
-- `announcement.enabled` / `announcement.text` / `announcement.type`
-- `smtp.*` — SMTP config (overrides env vars)
-- `ai.prompt.*` — AI prompt overrides
-- `model.*` — enabled/disabled models
-
-#### `saved_encounters`
-Draft encounters (7-day auto-expiry). Columns: `label`, `enc_type`, `transcript`, `generated_note`, `partial_data` (JSON), `status`, `expires_at`.
-
-#### `user_memories`
-User templates fed into AI generation. `category` is one of: `physical_exam`, `ros`, `encounter_format`, `family_history`, `assessment_plan`, `custom`.
-
-### Learning Hub Tables
-
-#### `learning_categories`
-Simple category list with `name`, `slug`, `sort_order`.
-
-#### `learning_content`
-Articles, quizzes, pearls, presentations. Key columns: `title`, `slug`, `body` (HTML for articles/pearls/quizzes; Marp markdown for presentations), `content_type` (`article` | `quiz` | `pearl` | `presentation`), `published`, `author_id`.
-
-#### `learning_questions`
-Quiz questions linked to `learning_content`. `question_type`: `mcq` | `true_false` | `multi`. `explanation` = general explanation shown after answering.
-
-#### `learning_options`
-Answer options for quiz questions. `is_correct: boolean`, `explanation` = shown when this wrong option is chosen.
-
-#### `learning_progress`
-Quiz attempt scores per user per content item.
-
----
-
-## 6. Authentication System
-
-**Current implementation: JWT in localStorage**
-
-### Flow
-1. `POST /api/auth/login` → returns `{ success, token, user }`
-2. Frontend stores token in `localStorage` as `ped_scribe_token` and in `window.AUTH_TOKEN`
-3. All API calls include `Authorization: Bearer <token>` header via `getAuthHeaders()`
-4. `src/middleware/auth.js` validates the Bearer token, attaches `req.user`
-5. Logout: `clearSession()` removes token from localStorage (client-side only)
-
-### Token
-- Signed with `JWT_SECRET` env var
-- 7-day expiry
-- Payload: `{ userId: number }`
-
-### Roles
-- `user` — standard access (clinical tools only)
-- `moderator` — can create/edit Learning Hub content
-- `admin` — full access including user management and site settings
-
-### Middleware
-- `authMiddleware` — validates JWT, populates `req.user`
-- `adminMiddleware` — run after auth, requires `role === 'admin'`
-- `moderatorMiddleware` — run after auth, requires `role === 'admin' OR 'moderator'`
-
-### 2FA
-Uses TOTP (speakeasy). If enabled, login returns `{ requires2FA: true }` and the client must POST the TOTP code to complete login.
-
-### Session Check on Page Load (auth.js)
-```javascript
-var savedToken = localStorage.getItem('ped_scribe_token');
-if (savedToken) {
-  fetch('/api/auth/me', { headers: { 'Authorization': 'Bearer ' + savedToken } })
-  .then(/* if ok → enterApp(), else → clearSession() */);
-}
-```
-The `has-session` CSS class on `<html>` hides the auth screen immediately when a localStorage token exists, preventing a white flash.
-
----
-
-## 7. Backend API Reference
-
-All routes are prefixed `/api`. Routes requiring auth are marked (A). Admin-only: (ADM). Moderator+: (MOD).
-
-### Auth — `/api/auth/`
-| Method | Path | Auth | Description |
-|--------|------|------|-------------|
-| POST | `/login` | — | Email + password login. Returns `{ token, user }` |
-| POST | `/register` | — | Create account (checks `registration_enabled` setting) |
-| GET | `/me` | A | Returns current user object |
-| POST | `/logout` | — | Clears server-side state (currently no-op, kept for future) |
-| POST | `/setup-2fa` | A | Generates TOTP secret + QR code |
-| POST | `/verify-2fa` | A | Confirms TOTP code, enables 2FA |
-| POST | `/disable-2fa` | A | Disables 2FA (requires password) |
-| POST | `/forgot-password` | — | Sends reset email |
-| POST | `/reset-password` | — | Sets new password via reset token |
-| GET | `/registration-status` | — | Returns `{ registrationEnabled: bool }` |
-| GET | `/verify-email` | — | Verifies email via token in query string |
-
-### Clinical — AI Generation
-| Method | Path | Auth | Description |
-|--------|------|------|-------------|
-| POST | `/generate-hpi-encounter` | A | HPI from live encounter transcript |
-| POST | `/generate-hpi-dictation` | A | HPI from dictation |
-| POST | `/generate-soap` | A | SOAP note |
-| POST | `/generate-hospital-course` | A | Hospital course summary |
-| POST | `/generate-chart-review` | A | Chart review |
-| POST | `/generate-milestone-narrative` | A | Milestone narrative |
-| POST | `/generate-milestone-summary` | A | 3-sentence milestone summary |
-| POST | `/well-visit/note` | A | Full well-visit note |
-| POST | `/sick-visit/note` | A | Sick visit SOAP |
-| POST | `/transcribe` | A | Whisper audio → text (multipart/form-data, field: `audio`) |
-| POST | `/refine` | A | Refine existing document |
-| POST | `/shorten` | A | Shorten existing document |
-| POST | `/clarify` | A | Find missing info in a document |
-
-### Encounters (Save/Load)
-| Method | Path | Auth | Description |
-|--------|------|------|-------------|
-| GET | `/encounters` | A | List user's saved encounters |
-| POST | `/encounters` | A | Save/update encounter draft |
-| DELETE | `/encounters/:id` | A | Delete a draft |
-
-### User Templates
-| Method | Path | Auth | Description |
-|--------|------|------|-------------|
-| GET | `/memories` | A | List user's templates |
-| POST | `/memories` | A | Create template |
-| PUT | `/memories/:id` | A | Update template |
-| DELETE | `/memories/:id` | A | Delete template |
-| GET | `/memories/context` | A | Returns templates formatted for AI injection |
-
-### Nextcloud
-| Method | Path | Auth | Description |
-|--------|------|------|-------------|
-| POST | `/nextcloud/connect` | A | Connect + test Nextcloud credentials |
-| POST | `/nextcloud/export` | A | Export text file to Nextcloud |
-| POST | `/nextcloud/disconnect` | A | Remove Nextcloud credentials |
-
-### Learning Hub (User-Facing)
-| Method | Path | Auth | Description |
-|--------|------|------|-------------|
-| GET | `/learning/categories` | A | List categories |
-| GET | `/learning/feed` | A | Paginated published content |
-| GET | `/learning/category/:slug` | A | Content by category |
-| GET | `/learning/content/:slug` | A | Single content item + questions |
-| POST | `/learning/submit-quiz` | A | Submit quiz answers, returns scored results |
-| GET | `/learning/search` | A | Full-text search |
-
-### Learning Hub CMS (Moderator+)
-| Method | Path | Auth | Description |
-|--------|------|------|-------------|
-| GET | `/admin/learning/categories` | MOD | All categories with counts |
-| POST | `/admin/learning/categories` | MOD | Create category |
-| PUT | `/admin/learning/categories/:id` | MOD | Update category |
-| DELETE | `/admin/learning/categories/:id` | MOD | Delete category |
-| GET | `/admin/learning/content` | MOD | All content (including drafts) |
-| GET | `/admin/learning/content/:id` | MOD | Single item with questions |
-| POST | `/admin/learning/content` | MOD | Create content |
-| PUT | `/admin/learning/content/:id` | MOD | Update content |
-| DELETE | `/admin/learning/content/:id` | MOD | Delete content + questions |
-| POST | `/admin/learning/content/:id/questions` | MOD | Add question to content |
-| PUT | `/admin/learning/questions/:id` | MOD | Update question + options |
-| DELETE | `/admin/learning/questions/:id` | MOD | Delete question |
-| GET | `/admin/learning/stats` | MOD | Dashboard stats |
-
-### Learning Hub AI (Moderator+)
-| Method | Path | Auth | Description |
-|--------|------|------|-------------|
-| POST | `/admin/learning/ai-generate` | MOD | Generate content from topic/file/Nextcloud (multipart/form-data) |
-| POST | `/admin/learning/ai-refine` | MOD | Refine body HTML with instructions |
-| POST | `/admin/learning/preview-slides` | MOD | Render Marp markdown → `{ css, slides[] }` for preview |
-| POST | `/admin/learning/generate-pptx` | MOD | Marp markdown → `.pptx` download (pptxgenjs) |
-| GET | `/admin/learning/webdav-browse` | MOD | PROPFIND Nextcloud folder |
-| POST | `/admin/learning/webdav-path` | MOD | Save user's default WebDAV path |
-
-### Admin (Admin Only)
-| Method | Path | Auth | Description |
-|--------|------|------|-------------|
-| GET | `/admin/users` | ADM | List all users |
-| POST | `/admin/users` | ADM | Create user |
-| PUT | `/admin/users/:id` | ADM | Update user (role, disable) |
-| DELETE | `/admin/users/:id` | ADM | Delete user |
-| GET/POST | `/admin/config/*` | ADM | Site settings (announcement, SMTP, models, prompts, etc.) |
-
-### Logs & Health
-| Method | Path | Auth | Description |
-|--------|------|------|-------------|
-| GET | `/health` | — | Returns `{ status: 'running', version, provider }` |
-| GET | `/models` | — | Returns available AI models list |
-| POST | `/logs/client-error` | — | Client-side error logging (public) |
-| GET | `/logs/usage` | ADM | API usage log |
-| GET | `/logs/audit` | ADM | Audit log |
-
----
-
-## 8. Frontend Architecture
-
-### Tab Loading (Lazy Components)
-Every tab's HTML lives in `/public/components/<tabname>.html`. When a tab button is clicked, `loadComponent()` in `app.js` fetches the HTML, injects it into the tab section, then fires `tabChanged` event.
-
-```javascript
-// app.js
-document.dispatchEvent(new CustomEvent('tabChanged', { detail: { tab: tabName } }));
-```
-
-**Critical pattern:** Every JS module that needs to access tab DOM elements MUST listen for `tabChanged`, not `DOMContentLoaded`:
-
-```javascript
-// Correct pattern for every tab module
-(function() {
-  var _inited = false;
-  document.addEventListener('tabChanged', function(e) {
-    if (e.detail.tab !== 'myTab' || _inited) return;
-    _inited = true;
-    // Now safe to querySelector elements — they exist in the DOM
-    var btn = document.getElementById('my-btn');
-    btn.addEventListener('click', ...);
-  });
-})();
-```
-
-If you use `DOMContentLoaded` instead, the elements won't exist yet (they're loaded async) and you'll get `null.addEventListener` errors.
-
-### Global Functions (defined in app.js)
-These are available everywhere — no imports needed:
-
-| Function | Description |
-|----------|-------------|
-| `getAuthHeaders()` | Returns `{ 'Content-Type': 'application/json', 'Authorization': 'Bearer <token>' }` |
-| `getSelectedModel()` | Returns model ID from active tab's selector or global selector |
-| `showLoading(msg)` | Shows full-screen loading overlay |
-| `hideLoading()` | Hides loading overlay |
-| `showToast(msg, type)` | Shows toast notification. `type`: `'success'`\|`'error'`\|`'info'`\|`'warning'` |
-| `setOutputText(el, text)` | Sets text on contenteditable div, converting `\n` to `<br>` |
-| `transcribeAudio(blob)` | Sends audio blob to `/api/transcribe`, returns `{ success, text }` |
-| `createSpeechRecognition()` | Returns Web Speech API recognition instance |
-| `createTimer(el)` | Returns timer object with `.start()` / `.stop()` |
-
-### Rich Text Editor (Tiptap)
-The body editor in the CMS uses Tiptap 2 (headless, no styling framework). The bundle is pre-built at `/public/vendor/tiptap.bundle.js` and exposes `window.Tiptap = { Editor, StarterKit, Link, Underline, TextStyle, Color }`.
-
-To rebuild the bundle after updating Tiptap packages:
-```bash
-cat > tiptap-entry.js << 'EOF'
-import { Editor } from '@tiptap/core';
-import StarterKit from '@tiptap/starter-kit';
-import Link from '@tiptap/extension-link';
-import Underline from '@tiptap/extension-underline';
-import { TextStyle } from '@tiptap/extension-text-style';
-import { Color } from '@tiptap/extension-color';
-window.Tiptap = { Editor, StarterKit, Link, Underline, TextStyle, Color };
-EOF
-npx esbuild tiptap-entry.js --bundle --format=iife --minify --outfile=public/vendor/tiptap.bundle.js
-rm tiptap-entry.js
-```
-
----
-
-## 9. AI Integration
-
-### `src/utils/ai.js` — `callAI(messages, options)`
-
-The single function used by all routes. It routes to the correct provider automatically.
-
-```javascript
-const { callAI } = require('../utils/ai');
-
-const result = await callAI(
-  [{ role: 'user', content: 'Generate a note...' }],
-  {
-    model: 'google/gemini-2.5-flash', // optional, uses default if omitted
-    temperature: 0.3,                 // optional, default 0.3
-    maxTokens: 4000                   // optional, default 4000
-  }
-);
-
-// result = { success: true, content: '...', model: '...', provider: '...', duration: ms }
-```
-
-### Bedrock Model Notes
-
-**Inference Profiles:** Most newer models (Anthropic vendor model 4.x, Meta Llama 4, DeepSeek R1, Amazon Nova, Writer) require cross-region inference profiles. These use a `us.` prefix on the model ID (e.g. `us.anthropic.agent-config-sonnet-4-6`). Direct model IDs will return "on-demand throughput not supported" errors.
-
-**Max Output Tokens:** Some models have low output limits (Cohere Command R/R+: 4096, AI21 Jamba: 4096). The `maxOut` field in `models.js` auto-clamps `maxTokens` in `callBedrock()`.
-
-**JSON Sanitization:** Some models (notably vendor model Sonnet 4.6, Opus 4.6) output literal newline characters inside JSON string values. `learningAI.js` includes a `sanitizeJsonString()` function that escapes these before parsing.
-
-### Prompt System
-Prompts are defined in `src/utils/prompts.js`. Admins can override any prompt via the Admin panel (`/admin/config/prompts`). Overrides are stored in `app_settings` table and loaded into memory on startup (with 3s grace period for DB readiness).
-
-To add a new prompt:
-1. Add a default in `prompts.js`
-2. Use `PROMPTS.get('your-prompt-key')` in your route
-3. The admin panel will auto-discover it
-
-### AI Generate for Learning Hub
-The `src/routes/learningAI.js` file handles all Learning Hub AI generation.
-
-**For presentations:** The AI is prompted to return raw Marp markdown (not JSON). The response is stored in the `body` column. Detection: `content_type === 'presentation'`.
-
-**For articles/quizzes/pearls:** The AI returns JSON:
-```json
-{
-  "title": "...",
-  "subject": "...",
-  "body": "<p>HTML content</p>",
-  "questions": [
-    {
-      "question_text": "...",
-      "question_type": "mcq",
-      "explanation": "...",
-      "options": [
-        { "option_text": "...", "is_correct": true, "explanation": "..." }
-      ]
-    }
-  ]
-}
-```
-
----
-
-## 10. Learning Hub & CMS
-
-### Content Types
-| Type | Body format | Has questions |
-|------|-------------|---------------|
-| `article` | HTML (Tiptap) | Optional |
-| `quiz` | HTML (brief intro) | Always |
-| `pearl` | HTML | Optional |
-| `presentation` | Marp markdown | Never |
-
-### Quiz Question Types
-- `mcq` — Single choice (radio buttons), 4 options, 1 correct
-- `true_false` — 2 options: "True" / "False", 1 correct
-- `multi` — Multiple select (checkboxes), scoring: all correct chosen AND no incorrect chosen
-
-### PPTX Generation
-`POST /admin/learning/generate-pptx` parses Marp markdown (splits on `---`), extracts `#` headings as slide titles, bullet points as content, and uses `pptxgenjs` to create a real `.pptx`. **No Chromium required** — pure Node.js.
-
-### Slide Preview
-`POST /admin/learning/preview-slides` uses `@marp-team/marp-core` to render Marp markdown to HTML, then extracts individual `<section>` elements. Returns `{ css, slides[] }`. The frontend renders these one at a time in a full-screen modal with arrow key + swipe navigation.
-
-### Content Display
-In the Learning Hub viewer, content `body` is rendered via `sanitizeHtml()` in `learningHub.js`. This function allows a safe subset of HTML tags only (no `<script>`, no `on*` attributes, no `style` attributes except `class`).
-
----
-
-## 11. Deployment
-
-### Local Development
-```bash
-cp .env.example .env   # Fill in your credentials
-docker compose -f docker-compose.local.yml build --no-cache
-docker compose -f docker-compose.local.yml up -d
-# App runs at http://localhost:3552
-```
-
-### Logs & Debugging
-
-**View container logs (live):**
-```bash
-docker logs -f pediatric-ai-scribe
-```
-
-**View last N lines:**
-```bash
-docker logs --tail 50 pediatric-ai-scribe
-```
-
-**Filter for specific issues:**
-```bash
-# AI/Bedrock errors
-docker logs pediatric-ai-scribe 2>&1 | grep -i "Bedrock\|LearningAI\|callAI"
-
-# Auth errors
-docker logs pediatric-ai-scribe 2>&1 | grep -i "Auth\|login\|verify"
-
-# All errors
-docker logs pediatric-ai-scribe 2>&1 | grep -i "error\|ERR\|fail"
-```
-
-**Key log prefixes:**
-| Prefix | Source |
-|--------|--------|
-| `[Bedrock] Model:` | AI response metadata (block types, stop reason) |
-| `[LearningAI]` | JSON parse failures with raw output context |
-| `[Auth]` | Login, registration, verification events |
-| `[TTS]` | Text-to-speech generation |
-| `🤖 Provider:` | Startup: which AI provider is active |
-| `✅ AWS Bedrock:` | Startup: Bedrock configured successfully |
-
-**Database logs (PostgreSQL):**
-```bash
-docker logs pedscribe-db
-```
-
-### Production (Docker Hub image)
-```bash
-# docker-compose.yml (production)
-services:
-  app:
-    image: danielonyejesi/pediatric-ai-scribe-v3:latest
-    ports: ["3000:3000"]
-    env_file: .env
-    depends_on:
-      db:
-        condition: service_healthy
-  db:
-    image: postgres:16-alpine
-    environment:
-      POSTGRES_DB: pedscribe
-      POSTGRES_USER: pedscribe
-      POSTGRES_PASSWORD: your_secure_password
-    volumes:
-      - pgdata:/var/lib/postgresql/data
-```
-
-### Docker Hub
-Repository: `danielonyejesi/pediatric-ai-scribe-v3`
-
-Tags use versioned format: `v5.0`, `v5.1`, etc. Production should always pin to a specific tag.
-
-### Git Repository
-Repository: `ifedan-ed/pediatric-ai-scribe-v3` (private)
-
-### Build & Push Process
-```bash
-# 1. Test locally first
-docker compose -f docker-compose.local.yml build --no-cache
-docker compose -f docker-compose.local.yml up -d
-# Test at http://localhost:3552
-
-# 2. When ready, tag and push to Docker Hub
-docker tag scribe-pediatric-scribe:latest danielonyejesi/pediatric-ai-scribe-v3:v5.x
-docker push danielonyejesi/pediatric-ai-scribe-v3:v5.x
-
-# 3. Update production docker-compose.yml to use new tag
-```
-
----
-
-## 12. Known Issues & Security Notes
-
-### Active Known Issues
-1. **`nodemailer` HIGH vulnerability** — v6.9.x has an email domain interpretation conflict. Upgrade to `^6.10.0` when available.
-2. **`unsafe-inline` in CSP** — `scriptSrc` includes `'unsafe-inline'` to support inline event handlers in HTML components. Should migrate to event listeners and remove this directive.
-3. **JWT in localStorage** — Tokens stored in `localStorage` are readable by JavaScript and therefore vulnerable to XSS attacks. A future migration to `httpOnly` cookies would eliminate this risk. See notes in auth.js and Section 6.
-4. **`window.prompt()` in `runAiRefineBody`** — Uses browser native prompt, which can be blocked in certain contexts. Should be replaced with an inline input field.
-5. **`webdav-learning-path` endpoint** — Sits behind `moderatorMiddleware` but is a user preference that non-moderator users might reasonably need. Consider moving to plain `authMiddleware`.
-
-### Security Hardening Already In Place
-- Helmet.js with custom CSP (no external script sources)
-- CORS restricted to `APP_URL` in production
-- Rate limiting on login (10/15min), register (5/hr), forgot-password (5/hr), resend-verification (3/15min), general API (60/min)
-- bcrypt cost 12 for password hashing
-- JWT with 7-day expiry
-- SQL injection protection: all queries use parameterized `?` / `$1` placeholders
-- Dynamic table names validated against an explicit allowlist (`ALLOWED_SLUG_TABLES`)
-- User input in HTML contexts goes through `sanitizeHtml()` (tag allowlist, strips `on*` attributes)
-- File upload MIME type validated by extension + content type
-- Admin/moderator route protection via middleware
-
----
-
-## 13. Adding New Features
-
-### Adding a New Clinical Tab
-1. Create `public/components/mytab.html` with the tab's UI
-2. Add to `index.html`:
-   - Tab button: `<button class="tab-btn" data-tab="mytab">...</button>`
-   - Tab section: `<section id="mytab-tab" class="tab-content" data-component="mytab"></section>`
-   - Script tag: `<script defer src="/js/myTab.js"></script>`
-3. Create `public/js/myTab.js`:
-   ```javascript
-   (function() {
-     var _inited = false;
-     document.addEventListener('tabChanged', function(e) {
-       if (e.detail.tab !== 'mytab' || _inited) return;
-       _inited = true;
-       // Wire up DOM elements here
-     });
-   })();
-   ```
-4. Create `src/routes/myTab.js` with the API route
-5. Register in `server.js`: `app.use('/api', require('./src/routes/myTab'));`
-
-### Adding a New AI Prompt
-1. In `src/utils/prompts.js`, add to the defaults object:
-   ```javascript
-   'my-prompt': 'You are a pediatric physician...'
-   ```
-2. In your route: `const prompt = PROMPTS.get('my-prompt') + '\n\n' + userInput`
-3. The admin panel will show an editor for this prompt automatically.
-
-### Adding a New Learning Hub Content Type
-1. Add the new type to the `content_type` selector in `cms.html`
-2. Handle it in `toggleEditorMode()` in `learningHub.js`
-3. Add to the type detection in `buildGeneratePrompt()` in `learningAI.js`
-4. Handle rendering in `learningHub.js` `loadContent()` function
-5. No DB migration needed — `content_type` is a free-text column
-
----
-
-## 14. Resetting Admin Password via Console
-
-If you lose admin access and have no SMTP for password reset, use the Docker console:
-
-```bash
-# Step 1: Get a shell in the running app container
-docker exec -it pediatric-ai-scribe sh
-
-# Step 2: Open Node.js REPL
-node
-
-# Step 3: Hash your new password
-const bcrypt = require('bcryptjs');
-const hash = await bcrypt.hash('YourNewPassword123!', 12);
-console.log(hash);
-// Copy the hash output
-
-# Step 4: Exit Node REPL
-.exit
-
-# Step 5: Open a DB shell
-# (Exit app container first, then:)
-docker exec -it pedscribe-db psql $POSTGRES_USER $POSTGRES_DB
-
-# Step 6: Update the password (paste the hash)
-UPDATE users
-SET password = '$2a$12$...(your-hash-here)...'
-WHERE email = 'your-admin@email.com';
-
-# Verify:
-SELECT email, left(password, 7) as hash_prefix FROM users WHERE email = 'your-admin@email.com';
-
-# Exit:
-\q
-```
-
-### Enabling Registration via Console
-```bash
-docker exec -it pedscribe-db psql $POSTGRES_USER $POSTGRES_DB
-UPDATE app_settings SET value = 'true' WHERE key = 'registration_enabled';
-\q
-```
-
-### Creating First Admin User (empty database)
-The first user to register is automatically made admin. Enable registration, register, then disable registration again.
-
-Or directly:
-```bash
-# In the Node REPL inside the app container:
-const bcrypt = require('bcryptjs');
-const { Pool } = require('pg');
-const pool = new Pool({ connectionString: process.env.DATABASE_URL });
-const hash = await bcrypt.hash('YourPassword', 12);
-await pool.query(
-  "INSERT INTO users (email, password, name, role, email_verified) VALUES ($1, $2, $3, 'admin', true)",
-  ['admin@yourdomain.com', hash, 'Admin']
-);
-pool.end();
-```
-
----
-
-## 15. Version History (Recent)
-
-| Tag | Key changes |
-|-----|-------------|
-| v3.19 | Login flash fixed (auth screen hidden by CSS default); presentation quiz option; feed labels corrected |
-| v3.18 | pdf-parse downgraded to v1.1.1; WebDAV selection UX fixed; topic context on upload/WebDAV tabs; inline refine bar replaces window.prompt(); CSP: removed unsafe-inline (all onclick= converted to data-action delegation); webdav-path moved to /api/user/webdav-path (auth-only) |
-| v3.17 | AI panel context-aware options fixed (style.display replaces classList — CSS cascade bug); quiz card redesign |
-| v3.16 | DEVELOPER_GUIDE.md created |
-| v3.15 | Auth reverted to localStorage tokens; slide preview padding fixed |
-| v3.14 | AI panel context-aware options (word count, slide count, quiz toggle); delete wording per type |
-| v3.13 | Delete confirm inline bar CSS bug fixed; slide preview in-page modal (arrow/swipe nav); Marp textarea placeholder |
-| v3.12 | Delete inline confirm bar; lighter login screen; Presentation type (Marp + pptxgenjs PPTX) |
-| v3.11 | AI content generation for Learning Hub (topic/file/Nextcloud, pdf-parse, pptxgenjs) |
-| v3.10 | Custom 404 page; server returns 404 for unknown paths |
-| v3.8  | Quill replaced with Tiptap 2 (self-hosted bundle, inline link bar) |
-| v5.0  | Resend verification link on login + rate limit (3/15min) |
-| v5.1–v5.4 | Bedrock model fixes: inference profiles, region filtering, thinking block handling |
-| v5.5  | Comprehensive Bedrock fix: all us. prefix IDs, maxTokens clamping |
-| v5.6  | Re-add Qwen3 235B |
-| v5.7  | Remove Opus 4.6 (JSON issues) |
-| v5.8  | Fix JSON parse: sanitize literal newlines in strings; re-add Opus 4.6 |
-| v5.9  | Re-add Opus 4.6 with sanitizer; updated DEVELOPER_GUIDE |
-| v6.0  | Increase PDF/doc context to 50k chars; maxTokens ceiling to 8k |
-
-## 16. Current Docker Image
-
-**Latest stable:** `danielonyejesi/pediatric-ai-scribe-v3:v6.0`
-
-```bash
-docker pull danielonyejesi/pediatric-ai-scribe-v3:v6.0
-```
-
----
-
-## 17. PDF & Document Uploads
-
-### How It Works
-
-The Learning Hub AI generator accepts documents via two paths — both produce the same result:
-
-1. **Direct upload** — user selects a file from their computer (up to 20 MB)
-2. **Nextcloud WebDAV** — user browses their Nextcloud and picks a file
-
-The flow:
-1. `extractText()` in `learningAI.js` detects file type by MIME/extension
-2. **PDF:** `pdf-parse` v1.1.1 extracts all text pages into a single string
-3. **PPTX/DOCX/TXT:** extracted via appropriate parser or read as UTF-8
-4. Text is truncated to **50,000 characters** (~25-30 pages) and sent as context in the AI prompt
-5. AI generates structured content (title, HTML body, quiz questions) from the full context
-
-### Supported File Types
-| Extension | Handler | Notes |
-|-----------|---------|-------|
-| `.pdf` | `pdf-parse` | Extracts text only — images, charts, tables are lost |
-| `.pptx` | Text extraction from slides | Slide text only |
-| `.docx` | Text extraction | Body text only |
-| `.txt`, `.md`, `.csv` | Read as UTF-8 | Full content preserved |
-
-### Limits
-- **Upload size:** 20 MB (`multer` limit in `learningAI.js`)
-- **Context sent to AI:** 50,000 characters (configurable in `buildGeneratePrompt()`)
-- **AI response tokens:** 8,000 max (ceiling — model stops when done)
-
-### Why No Vector Embeddings / RAG
-
-Embeddings and RAG (Retrieval Augmented Generation) are unnecessary for this use case:
-
-- **Single document → single generation** — the full text fits in the model's context window
-- Most Bedrock models support 100K-200K token inputs — 50,000 chars is well within that
-- Embeddings would add complexity (pgvector, chunking, retrieval pipeline) with no benefit
-
-If you later need to **search across hundreds of stored documents** or handle 200+ page PDFs, then consider pgvector + chunked retrieval. For now, the direct approach is correct.
-
----
-
-## 18. Scalability
-
-### Current Architecture (Single Instance)
-The app runs as a single Node.js process. This is fine for a team/department deployment (tens to hundreds of concurrent users).
-
-### What Scales Well Already
-- **Stateless JWT auth** — no server-side session store; any instance can validate any token
-- **PostgreSQL** — handles concurrent connections well; supports read replicas
-- **Lazy-loaded component HTML** — reduces initial page size; tabs load on demand
-- **AI calls** — fully async; expensive calls don't block other requests
-
-### Bottlenecks to Address Before Horizontal Scaling
-
-| Issue | Current | Fix for multi-instance |
-|-------|---------|----------------------|
-| Rate limiting | In-memory (per process) | Replace with Redis (`rate-limit-redis`) |
-| File uploads | `multer` in RAM | Route uploads to S3/object storage |
-| Scheduled cleanup | `setTimeout` in server.js | Use a dedicated cron job or DB-scheduled task |
-
-### How to Scale Horizontally
-```yaml
-# docker-compose with 3 app replicas + nginx load balancer
-services:
-  app:
-    image: danielonyejesi/pediatric-ai-scribe-v3:latest
-    deploy:
-      replicas: 3
-    environment:
-      DATABASE_URL: postgresql://...  # shared external Postgres
-      REDIS_URL: redis://redis:6379   # add when rate-limit-redis is wired
-  nginx:
-    image: nginx:alpine
-    # upstream: round-robin across app replicas
-  redis:
-    image: redis:7-alpine
-  postgres:
-    image: postgres:16-alpine
-```
-
-Cloud deployment options (all work with the current Docker image):
-- **AWS ECS/Fargate** — managed containers, easy auto-scaling
-- **Railway / Render / Fly.io** — simple push-to-deploy with Docker
-- **Kubernetes** — full control, overkill for most deployments
-
----
-
-## 19. Security Architecture — localStorage vs httpOnly Cookies
-
-The app stores JWT tokens in `localStorage`. This is a deliberate choice appropriate for this scale. The key security facts:
-
-**Current protections in place (more important than storage location):**
-- `Content-Security-Policy: script-src 'self'` — blocks all external scripts and inline JS (v3.18)
-- Input sanitization via `sanitizeHtml()` allowlist on all user-generated HTML
-- All 26 `onclick=` inline event handlers removed (v3.18) — reduces XSS surface
-- Rate limiting on auth endpoints
-- Helmet.js security headers
-- Parameterized SQL queries throughout
-
-**The reality about localStorage vs httpOnly cookies:**
-> "Unless you're a bank or large enterprise, it doesn't really matter. Focus on preventing XSS, because that's what actually matters... fundamentally, the security benefit of using httpOnly cookies is very minimal. If your site suffers any kind of XSS, it makes it slightly more difficult for an attacker to use the auth token." — Security engineering community consensus
-
-httpOnly cookies prevent token *copying* but not token *use* — an XSS attacker can still make authenticated requests on the user's behalf regardless of where the token is stored.
-
-**If you later want httpOnly cookies:** The infrastructure is already in place (cookie-parser, CORS `credentials:true`). The change is: (1) set cookie on login, (2) remove token from `getAuthHeaders()`, (3) add `/api/auth/logout` to clear cookie. See notes in `auth.js`. This was implemented and reverted in v3.14 — it works but adds CSRF considerations.
-
-**Token lifetime:** Currently 7 days. For higher security, reduce to 1-2 hours and add refresh token rotation.
-
----
-
----
-
-*Last updated: March 2026 — v6.0*
-*Generated for developer handover.*

Dockerfile

@@ -8,7 +8,7 @@ FROM node:20-alpine
 WORKDIR /app
 
 # ffmpeg: audio conversion for AWS Transcribe (WebM → PCM)
-# curl:   download Whisper models for browser-based transcription
+# curl:   HTTP helper used by the OpenBao entrypoint and health/debug tooling
 # jq:     JSON parsing for the entrypoint's OpenBao secret-fetch step
 RUN apk add --no-cache ffmpeg curl jq
 
@@ -30,22 +30,6 @@ RUN chmod +x /app/docker-entrypoint.sh
 
 RUN mkdir -p /app/data/logs
 
-# Download Browser Whisper (COMPLETE self-hosting - zero CDN dependencies)
-# Library + Models all bundled and served from our server
-RUN mkdir -p /app/public/models/Xenova/whisper-tiny.en/onnx && \
-    cd /app/public/models && \
-    echo "Downloading transformers.js library (worker-compatible build)..." && \
-    curl -sL -o transformers.min.js https://cdn.jsdelivr.net/npm/@xenova/transformers@2.0.0/dist/transformers.min.js && \
-    cd Xenova/whisper-tiny.en && \
-    echo "Downloading Whisper model files..." && \
-    curl -sL -o config.json https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/config.json && \
-    curl -sL -o tokenizer.json https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/tokenizer.json && \
-    curl -sL -o preprocessor_config.json https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/preprocessor_config.json && \
-    curl -sL -o generation_config.json https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/generation_config.json && \
-    curl -sL -o onnx/encoder_model_quantized.onnx https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/onnx/encoder_model_quantized.onnx && \
-    curl -sL -o onnx/decoder_model_merged_quantized.onnx https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/onnx/decoder_model_merged_quantized.onnx && \
-    echo "✅ Browser Whisper: 100% self-hosted (library: 760KB, models: 42MB)"
-
 EXPOSE 3000
 
 HEALTHCHECK --interval=30s --timeout=5s --start-period=20s \
@@ -56,4 +40,3 @@ HEALTHCHECK --interval=30s --timeout=5s --start-period=20s \
 # unset, so legacy .env-only deployments continue to work unchanged.
 ENTRYPOINT ["/app/docker-entrypoint.sh"]
 CMD ["node", "server.js"]
-

FEATURES_EXPLAINED.md

@@ -1,347 +0,0 @@
-# Features Explained - Pediatric AI Scribe v14
-
-## 🎙️ **Audio Backups**
-
-### How It Works:
-Audio backups happen **automatically every time you record**, regardless of transcription success/failure.
-
-**Flow:**
-1. You press "Stop" on recording
-2. Audio is immediately saved **before** transcription starts
-3. Server-side backup (PostgreSQL, gzip compressed) attempted first
-4. If server fails → fallback to browser IndexedDB
-5. After successful transcription → audio backup is deleted
-6. If transcription fails → audio backup remains for retry
-
-**Location:**
-- Server: PostgreSQL `audio_backups` table (auto-deleted after 24 hours)
-- Browser: IndexedDB `PedScribeAudioBackup` database (manual cleanup)
-
-**Purpose:**
-- Retry transcription if it fails
-- Recover audio if browser crashes
-- Audit trail (24 hour retention)
-
-**Access:**
-Settings → Audio Backups section shows:
-- Date/time of recording
-- Module (encounter, dictation, etc.)
-- File size
-- "Retry Transcription" button (if transcription failed)
-- "Delete" button
-
-**Cost:**
-Server backups are compressed (gzip) to ~1/10 original size. A 2MB recording becomes ~200KB in database.
-
----
-
-## 🌐 **S3 Document Storage**
-
-### How It Works:
-Upload documents (PDFs, images, Word docs, text files) to S3-compatible storage.
-
-**Supported Providers:**
-- AWS S3 (default)
-- Backblaze B2
-- MinIO (self-hosted)
-- Any S3-compatible service
-
-**Configuration (.env):**
-```bash
-# AWS S3 (uses Bedrock credentials if available)
-S3_BUCKET=your-bucket-name
-S3_REGION=us-east-1
-S3_PREFIX=documents/  # Optional: folder prefix
-
-# Backblaze B2
-S3_BUCKET=your-bucket-name
-S3_ENDPOINT=https://s3.us-west-004.backblazeb2.com
-S3_REGION=us-west-004
-S3_ACCESS_KEY_ID=your-b2-application-key-id
-S3_SECRET_ACCESS_KEY=your-b2-application-key
-
-# MinIO (self-hosted)
-S3_BUCKET=your-bucket
-S3_ENDPOINT=http://minio:9000
-S3_REGION=us-east-1
-S3_ACCESS_KEY_ID=minio-access-key
-S3_SECRET_ACCESS_KEY=minio-secret-key
-S3_FORCE_PATH_STYLE=true  # Required for MinIO
-```
-
-**Features:**
-- ✅ 10 MB file size limit
-- ✅ AES-256 server-side encryption
-- ✅ Per-user folder organization (`documents/{userId}/{uuid}/filename`)
-- ✅ Metadata stored in PostgreSQL (filename, mime type, size, description)
-- ✅ Presigned URLs for secure access (1 hour expiry)
-
-**Allowed File Types:**
-- PDF (`.pdf`)
-- Images (`.jpg`, `.jpeg`, `.png`, `.gif`)
-- Word documents (`.doc`, `.docx`)
-- Text files (`.txt`, `.csv`)
-
-**Access:**
-Settings → Documents section
-
-**Status Check:**
-If S3 is not configured, the Documents section shows empty with message: "S3 not configured"
-
----
-
-## 📚 **Learning Hub - Default Browse Path**
-
-### What It Is:
-A user preference that sets the **starting folder** when browsing Nextcloud files for AI content generation.
-
-### When It's Used:
-Only in the **Learning Hub AI Content Generator** (Admin/Moderator feature).
-
-**Scenario:**
-1. Admin/Moderator wants to create AI-generated learning content
-2. They choose "Upload from Nextcloud"
-3. File browser opens
-4. Instead of starting at root `/`, it opens at the configured path
-
-**Example:**
-```
-Default path: /Medical-Resources
-↓
-When you click "Browse Nextcloud", it opens:
-/Medical-Resources/
-  ├── Pediatric-Guidelines/
-  ├── Clinical-Protocols/
-  └── Research-Papers/
-
-Instead of:
-/
-  ├── Personal/
-  ├── Photos/
-  ├── Medical-Resources/  ← you'd have to navigate here every time
-  └── ...
-```
-
-**Configuration:**
-Settings → Nextcloud Integration → "Learning Hub — Default Browse Path"
-
-**Examples:**
-- `/Medical-Resources` - Opens in Medical Resources folder
-- `/Shared/Clinical-Content` - Opens in shared clinical content
-- `/` (empty) - Opens at root (default behavior)
-
-**Who Can Use This:**
-- Any authenticated user (not just moderators)
-- It's a personal preference per user
-- Only affects Learning Hub AI file picker
-
-**Why This Exists:**
-If you store learning resources in a specific Nextcloud folder, you don't want to navigate there every single time you generate content. Set it once, it remembers.
-
----
-
-## 🎤 **Browser Whisper Pre-Download**
-
-### Issue You Reported:
-"Pre-download models works, stuck at starting download"
-
-### What's Happening:
-The download **is actually working** but progress updates are slow because:
-1. HuggingFace CDN serves large files (39-244 MB)
-2. Progress callbacks are not granular (reported per-file, not per-chunk)
-3. Initial ONNX runtime download has no progress tracking
-
-### Fixed:
-- ✅ Added console logging to track progress
-- ✅ Added 30-second timeout warning (doesn't stop download)
-- ✅ Better error messages
-
-### How to Test:
-1. Open browser DevTools (F12) → Console tab
-2. Click "Pre-download model"
-3. Watch console for progress logs:
-   ```
-   [BrowserWhisper] Starting preload...
-   [BrowserWhisper] Progress: onnx-runtime 0%
-   [BrowserWhisper] Progress: model.bin 23%
-   [BrowserWhisper] Progress: model.bin 47%
-   ...
-   [BrowserWhisper] Progress:  100%
-   ```
-
-### Expected Download Times:
-- **Tiny** (39 MB): 5-15 seconds (fast connection)
-- **Base** (74 MB): 10-30 seconds
-- **Small** (244 MB): 30-90 seconds
-
-### If Still Stuck:
-**Check these:**
-1. Open DevTools → Network tab
-2. Filter by "HuggingFace"
-3. Look for downloads from `cdn-lfs-us-1.huggingface.co`
-4. Check if files are actually downloading
-
-**Common issues:**
-- Slow internet connection (244 MB takes time!)
-- Corporate firewall blocking HuggingFace CDN
-- Browser IndexedDB quota exceeded
-
-**Workaround:**
-Just enable it and record audio - the model will download on first use (same as pre-download, but triggered automatically).
-
----
-
-## 🔊 **TTS Voice Preview**
-
-### Issue You Reported:
-"Preview button next to TTS seems to do nothing"
-
-### Fixed:
-- ✅ Added error logging to console
-- ✅ Better validation (checks for empty selection)
-- ✅ Clear user feedback messages
-
-### How to Use:
-1. Go to Settings → Voice Preferences
-2. Select a voice from "Text-to-Speech Voice" dropdown
-3. Click "Preview" button
-4. Wait 2-3 seconds
-5. Audio should play automatically
-
-### If Nothing Happens:
-**Check browser console for errors:**
-- Open DevTools (F12) → Console tab
-- Click Preview
-- Look for `[VoicePrefs] Preview error:` message
-
-**Common issues:**
-1. **No voice selected** → Select from dropdown first
-2. **TTS not configured** → Check `.env` has `GOOGLE_VERTEX_PROJECT` or `LITELLM_API_BASE`
-3. **Network error** → Check server logs for TTS API errors
-4. **Browser autoplay policy** → Some browsers block autoplay, click page first
-
-### Testing Checklist:
-```bash
-# 1. Check TTS is configured
-curl http://localhost:3000/api/health | grep tts
-
-# 2. Test TTS endpoint directly
-curl -X POST http://localhost:3000/api/text-to-speech \
-  -H "Authorization: Bearer YOUR_JWT" \
-  -H "Content-Type: application/json" \
-  -d '{"text":"Test"}' \
-  --output test.mp3
-
-# 3. Play the audio file
-mpg123 test.mp3  # or open in browser
-```
-
----
-
-## 📋 **Summary of User Settings**
-
-### Voice Preferences
-**Location:** Settings → Voice Preferences (top section)
-
-| Setting | Options | Default | Purpose |
-|---------|---------|---------|---------|
-| **STT Model** | gemini-2.0-flash-exp, gemini-2.0-flash, gemini-1.5-flash, gemini-1.5-pro, whisper-1 | Server default | Controls transcription accuracy |
-| **TTS Voice** | Journey-F/D, Studio-O/M, Neural2 series, alloy, echo, fable, onyx, nova, shimmer | Server default | Controls read-aloud voice |
-
-### Browser Whisper
-**Location:** Settings → Browser Transcription (Local Whisper)
-
-| Setting | Options | Default | Purpose |
-|---------|---------|---------|---------|
-| **Enable** | On/Off | Off | Local transcription (HIPAA-safe) |
-| **Model** | Tiny, Base, Small | Tiny | Accuracy vs speed tradeoff |
-
-### Nextcloud
-**Location:** Settings → Nextcloud Integration
-
-| Setting | Purpose |
-|---------|---------|
-| **Nextcloud URL** | Your Nextcloud instance |
-| **Username** | Nextcloud username |
-| **App Password** | Generate in Nextcloud → Security |
-| **Default Browse Path** | Starting folder for Learning Hub AI picker |
-
-### Documents (S3)
-**Location:** Settings → Documents
-
-Shows list of uploaded documents if S3 is configured. Upload limit: 10 MB per file.
-
-### Audio Backups
-**Location:** Settings → Audio Backups
-
-Shows last 24 hours of recordings. Can retry transcription or delete.
-
----
-
-## 🔧 **Troubleshooting Guide**
-
-### Pre-Download Stuck
-1. ✅ Open browser console (F12)
-2. ✅ Look for `[BrowserWhisper] Progress:` logs
-3. ✅ Check Network tab for HuggingFace downloads
-4. ✅ Wait - 244 MB takes time!
-5. ✅ If truly stuck (no network activity): refresh page, try again
-
-### Preview Button Silent
-1. ✅ Check voice is selected in dropdown
-2. ✅ Open console for error messages
-3. ✅ Test TTS endpoint directly (curl command above)
-4. ✅ Check server logs for TTS provider errors
-5. ✅ Verify `.env` has TTS provider configured
-
-### S3 Not Working
-1. ✅ Check `.env` has `S3_BUCKET` set
-2. ✅ Verify credentials: `S3_ACCESS_KEY_ID` + `S3_SECRET_ACCESS_KEY`
-3. ✅ Test bucket access from server:
-   ```bash
-   aws s3 ls s3://your-bucket/ --region us-east-1
-   ```
-4. ✅ Check server logs for S3 errors when uploading
-
-### Audio Backups Not Showing
-1. ✅ Record audio first (they're created on recording, not transcription)
-2. ✅ Check database: `SELECT COUNT(*) FROM audio_backups;`
-3. ✅ Verify IndexedDB in browser: DevTools → Application → IndexedDB → `PedScribeAudioBackup`
-4. ✅ Backups auto-delete after 24 hours
-
-### Learning Hub Path Not Working
-1. ✅ This only affects **AI content generator file picker**
-2. ✅ It does NOT affect manual Nextcloud document browsing
-3. ✅ Path must exist in your Nextcloud
-4. ✅ Path format: `/Folder/Subfolder` (starts with `/`)
-
----
-
-## 📊 **Feature Status Matrix**
-
-| Feature | Status | Config Required | HIPAA-Safe | Notes |
-|---------|--------|-----------------|------------|-------|
-| **Audio Backups** | ✅ Working | None (auto) | ✅ Yes | Server + IndexedDB |
-| **S3 Documents** | ✅ Working | S3_BUCKET | ✅ Yes (AWS) | Optional feature |
-| **Browser Whisper** | ✅ Working | None (optional) | ✅ Yes | Client-side only |
-| **Voice Preferences** | ✅ Working | Provider config | Depends | Google/AWS = yes |
-| **Learning Hub Path** | ✅ Working | Nextcloud config | ✅ Yes | User preference |
-| **TTS Preview** | ✅ Fixed | TTS provider | Depends | Check logs if fails |
-| **Embeddings** | ✅ Working | Vertex/LiteLLM | ✅ Yes | Requires pgvector |
-
----
-
-## 🚀 **Next Steps**
-
-1. **Push v14 to Docker** (in progress via GitHub Actions)
-2. **Test features after deployment**
-3. **Check browser console for any errors**
-4. **Verify TTS preview works with your provider**
-5. **Test browser whisper download with different models**
-
----
-
-**Questions? Check the logs:**
-- Browser: F12 → Console tab
-- Server: `docker logs pediatric-ai-scribe -f`
-- Database: `psql -d pedscribe -c "SELECT COUNT(*) FROM audio_backups;"`

README.md

@@ -1,78 +1,103 @@
-# Pediatric AI Scribe v6
+# Ped-AI
 
-AI-powered clinical documentation platform for pediatric medicine. Generates HPIs, hospital courses, chart reviews, SOAP notes, well/sick visit notes, and developmental milestone assessments from voice recordings or dictation.
+Ped-AI is a pediatric clinical documentation, education, and bedside decision-support app. This fork has moved well beyond the original scribe app: it now combines encounter documentation, clinical workflows, Learning Hub CMS, admin controls, MCP-backed clinical assistant integration, Redis-backed operational state, and hardened deployment defaults.
 
-## Features
+The app runs as an authenticated Express/Postgres service with a browser frontend and optional integrations for LiteLLM, Vertex/Gemini, AWS, OpenAI-compatible APIs, Nextcloud WebDAV, S3-compatible storage, OpenBao, Redis, OIDC, TOTP, and Cloudflare Turnstile.
+
+## Current Scope
 
 ### Clinical Documentation
-- **Live Encounter** — record doctor-patient conversations, AI generates structured OLDCARTS HPI
-- **Voice Dictation** — dictate narrative, AI cleans and restructures
-- **Hospital Course** — paste progress notes, generates prose, day-by-day, organ-system (ICU), or psych format
-- **Chart Review / Precharting** — summarize outpatient, subspecialty, and ED notes
-- **SOAP Notes** — full SOAP or subjective-only from dictation
-- **Well Visit** — AAP 2025 Bright Futures periodicity with vaccines, screenings, billing codes, SSHADESS (12+), milestones
-- **Sick Visit** — quick documentation with auto-suggested ROS and PE from chief complaint
-- **Developmental Milestones** — AAP/Nelson tracker (birth-11y) with narrative/structured/summary output
 
-### AI & Speech
-- **5 AI Providers** — OpenRouter, AWS Bedrock, Azure OpenAI, Google Vertex AI, LiteLLM
-- **5 STT Providers** — Google Gemini, Amazon Transcribe (Medical), OpenAI Whisper, Local Whisper, LiteLLM
-- **3 TTS Providers** — Google Cloud TTS, LiteLLM (OpenAI), ElevenLabs
-- **Browser Whisper** — fully offline in-browser transcription via WebAssembly (HIPAA-safe)
-- **Per-tab model selector** — choose fast vs. smart vs. premium models per task
-- **Physician memory system** — Dragon-like learning from your corrections
+- Live encounter capture with structured pediatric HPI generation.
+- Dictation cleanup for narrative notes.
+- SOAP, sick visit, well visit, hospital course, chart review, precharting, and ED encounter workflows.
+- Parent-facing education handouts generated from clinician notes, with diagnosis, medication, emergency-care guidance, and preferred-language support.
+- Pediatric developmental milestone tooling.
+- Templates, physician memory, and per-tab model overrides.
+- Server-side speech-to-text routing through configured providers.
+
+### Bedside Tools
+
+- Pediatric calculators and emergency dosing helpers.
+- PE guide and clinical reference content.
+- Vaccines, catch-up schedules, growth/vitals, bilirubin, BSA, GCS, equipment, and resuscitation helpers.
+- Mobile-friendly PWA layout for bedside use.
+- Per-user phone extension and pager directory with soft-delete, search, ZIP export, and JSON/ZIP import for handoff between users.
 
 ### Learning Hub
-- **Content Management** — articles, clinical pearls, quizzes, presentations
-- **AI Content Generation** — generate from topics, uploaded PDFs, or Nextcloud files
-- **Marp Presentations** — slide editor with preview and PPTX export
-- **Semantic Search** — vector-based search via pgvector embeddings
-- **Quiz System** — MCQ, multi-select, true/false with scoring and progress tracking
 
-### Platform
-- **Multi-user with roles** — admin, moderator, user
-- **OIDC/SSO** — Azure AD, Okta, Keycloak, PocketID, Google
-- **2FA** — TOTP-based two-factor authentication
-- **Cloudflare Turnstile** — bot protection on login, register, password reset
-- **Email verification** — with customizable templates
-- **Nextcloud integration** — WebDAV export
-- **S3 Document Storage** — AWS S3, Backblaze B2, MinIO
-- **PWA** — installable, works on mobile
-- **Admin Panel** — user management, settings, prompt editor, model configuration, logs
+- CMS for articles, clinical pearls, quizzes, and presentations.
+- Tiptap article editor, quiz builder, category management, and draft/publish flow.
+- AI-assisted content generation from topic text, uploaded files, or connected Nextcloud WebDAV files.
+- Marp slide editing with preview and PPTX export.
+- Keyword, semantic, and hybrid search using Postgres/pgvector where configured.
 
----
+### Clinical Assistant
+
+- Optional MCP-backed clinical assistant integration.
+- Prompt suggestions backed by Redis operational cache.
+- No clinical answer response caching.
+- Designed to retrieve from indexed clinical material while keeping provider selection explicit.
+
+### Admin And Security
+
+- Local auth, role-based access, TOTP 2FA, OIDC/SSO, email verification, and optional Turnstile.
+- Admin panel for users, settings, prompts, models, logs, and Learning Hub content.
+- Audit, API, access, and client-error logs with redaction hardening.
+- OpenBao secret loading support at container startup.
+- S3-compatible document storage support.
+
+## Removed Browser STT
+
+Browser Whisper has been removed from the runtime. The app should not ship browser Whisper workers, browser-local Whisper model downloads, Transformers.js browser STT, or Browser Whisper setup docs.
+
+Speech-to-text is handled server-side through configured providers such as Google/Gemini, AWS Transcribe, LiteLLM, or OpenAI Whisper. Browser-native Web Speech remains gated behind an explicit user setting when present in the browser.
 
 ## Quick Start
 
-### 1. Configure
-
 ```bash
 cp .env.example .env
+docker compose up -d --build
 ```
 
-Edit `.env` — at minimum set:
+The default compose exposes the app on `127.0.0.1:3552` and starts:
 
-```env
-AI_PROVIDER=litellm          # or openrouter, bedrock, azure, vertex
-LITELLM_API_BASE=https://your-litellm.example.com
-LITELLM_API_KEY=sk-...
+- `pediatric-ai-scribe` for the Node app.
+- `pedscribe-db` for Postgres with pgvector.
+- `ped-ai-redis` for operational Redis state.
 
-OPENAI_API_KEY=sk-...        # for Whisper transcription (if not using LiteLLM STT)
-
-JWT_SECRET=<64-char random>  # openssl rand -hex 32
-DB_PASSWORD=<strong password>
-APP_URL=https://your-domain.com
-```
-
-### 2. Start
+Health check:
 
 ```bash
-docker compose up -d
+curl -fsS http://127.0.0.1:3552/api/health
 ```
 
-App runs on **port 3552**. First user to register becomes admin.
+Prometheus metrics are exposed at `GET /metrics` with the `ped_ai_` metric prefix.
 
-### 3. Admin CLI
+The first registered user becomes an admin unless registration has already been configured differently.
+
+## Core Environment
+
+Set real values in `.env` before production use.
+
+```env
+APP_URL=https://your-domain.example
+JWT_SECRET=<64-char-random-secret>
+DB_PASSWORD=<strong-database-password>
+
+AI_PROVIDER=litellm
+LITELLM_API_BASE=https://your-litellm.example/v1
+LITELLM_API_KEY=<key>
+
+TRANSCRIBE_PROVIDER=litellm
+LITELLM_STT_MODEL=whisper-1
+
+REDIS_URL=redis://ped-ai-redis:6379
+```
+
+Supported text AI providers include LiteLLM, OpenRouter, AWS Bedrock, Azure OpenAI, and Google Vertex AI. Supported STT routing includes Google/Gemini, AWS Transcribe, OpenAI Whisper, and LiteLLM. Supported TTS routing includes Google Cloud TTS, LiteLLM/OpenAI-compatible audio, and ElevenLabs where configured.
+
+## Admin CLI
 
 ```bash
 docker exec pediatric-ai-scribe node admin-cli.js list-users
@@ -83,270 +108,70 @@ docker exec pediatric-ai-scribe node admin-cli.js toggle-registration
 docker exec pediatric-ai-scribe node admin-cli.js stats
 ```
 
----
+## Maintenance
 
-## AI Provider Configuration
-
-Switch providers by setting `AI_PROVIDER` in `.env`. No code changes needed.
-
-| Provider | HIPAA | Config |
-|----------|-------|--------|
-| **LiteLLM** | Depends on backend | `LITELLM_API_BASE`, `LITELLM_API_KEY` |
-| **AWS Bedrock** | Yes (with BAA) | `AWS_BEDROCK_REGION`, `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY` |
-| **Azure OpenAI** | Yes (with BAA) | `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_API_KEY`, `AZURE_DEPLOYMENT_NAME` |
-| **Google Vertex AI** | Yes (with BAA) | `GOOGLE_VERTEX_PROJECT`, `GOOGLE_VERTEX_LOCATION` |
-| **OpenRouter** | No | `OPENROUTER_API_KEY` |
-
----
-
-## Transcription (Speech-to-Text)
-
-Set `TRANSCRIBE_PROVIDER` or let the app auto-detect.
-
-| Provider | HIPAA | Config |
-|----------|-------|--------|
-| **Google Gemini** | Yes | `GOOGLE_VERTEX_PROJECT`, `GOOGLE_STT_MODEL` |
-| **Amazon Transcribe** | Yes | AWS creds + `TRANSCRIBE_PROVIDER=aws` |
-| **Amazon Transcribe Medical** | Yes | `AWS_TRANSCRIBE_MEDICAL=true`, `AWS_TRANSCRIBE_SPECIALTY=PRIMARYCARE` |
-| **Local Whisper** | Yes (offline) | `TRANSCRIBE_PROVIDER=local`, `WHISPER_BINARY`, `WHISPER_MODEL_SIZE` |
-| **OpenAI Whisper** | No | `OPENAI_API_KEY` |
-| **LiteLLM** | Depends | `TRANSCRIBE_PROVIDER=litellm`, `LITELLM_STT_MODEL` |
-| **Browser Whisper** | Yes (client-side) | No config needed — toggle in user settings |
-
----
-
-## Text-to-Speech
-
-| Provider | HIPAA | Config |
-|----------|-------|--------|
-| **Google Cloud TTS** | Yes | `GOOGLE_VERTEX_PROJECT`, `GOOGLE_TTS_VOICE` |
-| **LiteLLM** | Depends | `LITELLM_TTS_MODEL`, `LITELLM_TTS_VOICE` |
-| **ElevenLabs** | No | `ELEVENLABS_API_KEY` |
-
----
-
-## OpenID Connect / SSO
-
-Supports Azure AD, Okta, Keycloak, PocketID, Google, and any OIDC-compliant provider.
-
-1. Register callback URL: `https://your-domain.com/api/auth/oidc/callback`
-2. Admin Panel > Settings > Configure OIDC (Issuer URL, Client ID, Client Secret)
-3. Users are auto-created and linked by email on first SSO login
-
-See [OPENID_SETUP.md](OPENID_SETUP.md) for provider-specific guides.
-
----
-
-## Cloudflare Turnstile (Bot Protection)
-
-Optional CAPTCHA on login, registration, and password reset forms.
-
-```env
-TURNSTILE_SITE_KEY=0x4AAA...
-TURNSTILE_SECRET_KEY=0x4AAA...
-```
-
----
-
-## Email
-
-Without SMTP, email verification is skipped and users are auto-verified.
-
-```env
-SMTP_HOST=smtp.gmail.com
-SMTP_PORT=587
-SMTP_USER=your-email@gmail.com
-SMTP_PASS=your-app-password
-SMTP_FROM=noreply@yourdomain.com
-```
-
----
-
-## Maintenance CLI
-
-After a Postgres image upgrade (major version bump or silent base-layer change),
-btree indexes on text columns can become inconsistent with the new ICU/glibc
-library. The app auto-detects this at startup and reindexes on drift, but you
-can also trigger it manually:
+The app checks Postgres collation drift on startup and can reindex text indexes after image or OS-library changes.
 
 ```bash
-# Health check — no writes
 docker exec pediatric-ai-scribe npm run maint:check
-
-# Rebuild all indexes + refresh collation + ANALYZE
 docker exec pediatric-ai-scribe npm run maint:reindex
 ```
 
-Run `maint:reindex` any time after:
-
-- Upgrading the Postgres image (major or minor)
-- Restoring from a dump created on a different Linux distro
-- Seeing "invalid credentials" on credentials you know are correct
-- Seeing `0 rows` returned from a lookup that should match
-
-The reindex takes seconds on a small DB and a minute or two on larger ones.
-Safe to run while the app is serving traffic, though queries may slow briefly.
-
----
-
-## Docker Hub
-
-```bash
-docker pull danielonyejesi/pediatric-ai-scribe-v3:latest
-```
-
-Minimal compose without building:
-
-```yaml
-services:
-  app:
-    image: danielonyejesi/pediatric-ai-scribe-v3:latest
-    ports:
-      - "3552:3000"
-    env_file: .env
-    depends_on:
-      postgres:
-        condition: service_healthy
-    restart: unless-stopped
-
-  postgres:
-    image: pgvector/pgvector:pg16
-    environment:
-      POSTGRES_DB: pedscribe
-      POSTGRES_USER: pedscribe
-      POSTGRES_PASSWORD: ${DB_PASSWORD}
-    volumes:
-      - pgdata:/var/lib/postgresql/data
-    restart: unless-stopped
-    healthcheck:
-      test: ["CMD-SHELL", "pg_isready -U pedscribe"]
-      interval: 10s
-      retries: 5
-
-volumes:
-  pgdata:
-```
-
----
-
-## HIPAA Notice
-
-This application processes data through third-party AI APIs.
-
-- All connections use HTTPS/TLS
-- Authentication required for all AI endpoints
-- 2FA and SSO available
-- Cloudflare Turnstile bot protection
-- **AWS Bedrock**, **Azure OpenAI**, and **Google Vertex AI** offer BAAs
-- **OpenRouter** and **ElevenLabs** do NOT offer BAAs
-- **Browser Whisper** and **Local Whisper** keep audio fully private
-
-**Do not use real PHI without executed BAAs with all providers in your deployment.**
-
----
-
-## Documentation
-
-See the [docs/](docs/) directory for detailed documentation:
-
-- [Architecture Overview](docs/architecture.md)
-- [API Reference](docs/api-reference.md)
-- [Database Schema](docs/database.md)
-- [Authentication & Security](docs/authentication.md)
-- [AI Providers & Models](docs/ai-providers.md)
-- [Speech (STT/TTS)](docs/speech.md)
-- [Learning Hub & CMS](docs/learning-hub.md)
-- [Configuration Reference](docs/configuration.md)
-- [Deployment Guide](docs/deployment.md)
-- [Developer Guide](docs/developer-guide.md)
-
----
-
-## Development
-
-```bash
-npm install
-cp .env.example .env   # edit with your keys
-# Requires PostgreSQL with pgvector
-node server.js
-```
-
----
+Run the reindex command after major Postgres image changes, restoring a dump from another distro, or seeing lookup behavior that suggests collation/index drift.
 
 ## Testing
 
-Two layers, both zero-config after the initial setup.
-
-### Unit tests — pure dose math (Node built-in)
+Run the Node test suite:
 
 ```bash
 npm test
 ```
 
-Runs `node --test test/` against `public/js/calc-math.js` — pure functions for
-APLS / Best Guess weight, Parkland, Holliday-Segar 4-2-1, PRAM, Westley,
-epi (anaphylaxis vs arrest vs NRP, different concentrations), RSI drugs,
-min SBP, ETT sizing, Lund-Browder TBSA. **36 assertions, no dependencies.**
-
-### End-to-end tests — Playwright smoke suite
-
-Runs a headless Chromium against the live app. **128 tests** covering every
-calculator tab, every Bedside sub-pill + widget, auth-gated pages (encounter,
-well visit, charts, vaccines, catch-up, learning hub, dictation, settings,
-FAQ), at **both desktop and mobile (Pixel 5) viewports**.
+Run syntax checks for touched files when doing focused backend work:
 
 ```bash
-# First-time setup: spin up the auth-less test container (port 3553)
-docker compose -f docker-compose.yml -f docker-compose.e2e.yml up -d pediatric-scribe-e2e
+node --check server.js
+node --check src/routes/transcribe.js
+```
 
-# Then run the full suite (runs inside an official Playwright container)
+Run the Playwright smoke suite against the e2e compose stack:
+
+```bash
+docker compose -f docker-compose.yml -f docker-compose.e2e.yml up -d pediatric-scribe-e2e
 npm run e2e
 ```
 
-The runner script (`scripts/e2e.sh`) uses `mcr.microsoft.com/playwright` so you
-don't need Node or browsers on the host.
+## Deployment Notes
 
-**Test environment:**
+- Put the app behind HTTPS before clinical use.
+- Use only AI/STT/TTS providers covered by your BAA and data-processing requirements.
+- Configure OIDC/SSO and 2FA for production users.
+- Keep `JWT_SECRET`, database credentials, provider keys, S3 keys, SMTP credentials, and OpenBao tokens out of git.
+- Treat logs as sensitive operational data even with redaction enabled.
+- Use the Caddy/reverse-proxy layer to expose only intended public routes.
 
-- `pediatric-ai-scribe` (port 3552) — your normal app
-- `pediatric-ai-scribe-e2e` (port 3553) — identical image, but with
-  `TURNSTILE_SECRET_KEY=""` and `SMTP_HOST=""` so Playwright can log in
-  without a bot challenge. Shares the same Postgres + pgdata volume.
-- Test user: `e2e-user@ped-ai.test` (auto-verified on first register)
-- Harness page: `public/e2e-harness.html` loads the calculators component
-  without the auth wall for smoke tests that don't need a logged-in session.
+## Documentation
 
-**Viewing failures** — Playwright writes `e2e/test-results/<test-name>/`
-with:
+Primary references:
 
-- `test-failed-1.png` — screenshot at the point of failure
-- `trace.zip` — full action trace (replay with `npx playwright show-trace`)
-- `error-context.md` — DOM snapshot and console logs
+- `docs/ARCHITECTURE.md` for the current system map and service boundaries.
+- `docs/DEVELOPMENT.md` for day-to-day code-change workflow.
+- `docs/SCALING.md` for scaling priorities and readiness work.
+- `docs/CLINICAL_ASSISTANT.md` for MCP-backed assistant behavior and safety rules.
+- `docs/MODULE_CONVENTIONS.md` for CommonJS, ESM, globals, and rendering rules.
+- `docs/architecture.md` for high-level architecture.
+- `docs/api-reference.md` for API routes.
+- `docs/authentication.md` for auth, OIDC, and security configuration.
+- `docs/ai-providers.md` for model/provider setup.
+- `docs/speech.md` for server-side STT/TTS setup.
+- `docs/learning-hub.md` for the CMS and education workflow.
+- `docs/configuration.md` for environment variables.
+- `docs/deployment.md` for production deployment.
+- `docs/mobile-build.md` for the Capacitor wrapper and app-store build notes.
+- `docs/logic/README.md` for the deeper code walkthrough.
 
-Everything but the specs and config is gitignored under `e2e/`.
+Some deep `docs/logic/` files still describe historical implementation details. Prefer runtime code and tests when documentation conflicts with current behavior.
 
-**Files:**
+## Clinical Safety
 
-- `e2e/tests/bedside-smoke.spec.js` — 26 tests for the Bedside module
-- `e2e/tests/top-calculators.spec.js` — 27 tests for BP / BMI / Growth /
-  Bili / Vitals / BSA / Dose / Resus / GCS / Equipment
-- `e2e/tests/auth-gated-smoke.spec.js` — 11 tests for the auth-gated tabs
-- `e2e/playwright.config.js` — runs all the above under both `chromium`
-  (Desktop Chrome) and `mobile-chrome` (Pixel 5) projects
-
-**Writing a new test:**
-
-```js
-const { test, expect } = require('@playwright/test');
-
-test('my new smoke test', async ({ page }) => {
-  await page.goto('/e2e-harness.html');             // bypasses auth for calculators
-  await page.waitForFunction(() => window.__harnessReady === true);
-  await page.click('button.calc-nav-pill[data-calc="bedside"]');
-  await expect(page.locator('#calc-bedside')).toBeVisible();
-});
-```
-
-For auth-gated routes, use the login fixture in `auth-gated-smoke.spec.js`
-as a template — it caches the token at module scope so you don't hit the
-login rate-limit.
+Ped-AI is documentation and education support software. It does not replace clinical judgment, local policy, medication verification, or attending review. Validate generated notes, calculations, and recommendations before use in patient care.

TRANSCRIPTION_OPTIONS.md

@@ -1,279 +0,0 @@
-# Transcription Options Guide
-
-## Overview
-
-Pediatric AI Scribe v2+ offers **three transcription methods**, allowing you to choose between **privacy**, **speed**, and **real-time feedback**.
-
----
-
-## 📊 Comparison Table
-
-| Feature | Browser Whisper | Server Transcription | Web Speech API |
-|---------|----------------|---------------------|----------------|
-| **Privacy** | ⭐⭐⭐⭐⭐ 100% offline | ⭐⭐⭐⭐ (with BAA) | ⭐ Sends to cloud |
-| **Accuracy** | ⭐⭐⭐⭐⭐ Whisper | ⭐⭐⭐⭐⭐ Gemini/AWS | ⭐⭐⭐ Browser-dependent |
-| **Speed** | ⭐⭐⭐ 2-10s | ⭐⭐⭐⭐⭐ ~1s | ⭐⭐⭐⭐⭐ Instant |
-| **Real-time** | ❌ Batch mode | ❌ Batch mode | ✅ Live streaming |
-| **HIPAA** | ✅ Yes | ✅ (Vertex/AWS) | ❌ No |
-| **Cost** | Free | ~$0.005/min | Free |
-| **Internet** | ❌ Not required | ✅ Required | ✅ Required |
-| **Setup** | None (bundled) | API keys | None (built-in) |
-
----
-
-## Option 1: Browser Whisper (Offline, Private) ⭐ RECOMMENDED
-
-### What It Is
-- Runs **OpenAI Whisper** entirely in your browser using WebAssembly
-- Audio **never leaves your device** - 100% offline after initial page load
-- Models bundled in Docker image (self-hosted, no CDN)
-
-### When to Use
-- ✅ Clinical documentation (HIPAA-compliant)
-- ✅ Maximum privacy required
-- ✅ Offline/air-gapped environments
-- ✅ No API costs
-- ✅ Zero vendor dependency
-
-### How to Enable
-1. Settings → Browser Transcription
-2. Toggle "Enable browser transcription" ON
-3. (Optional) Click "Pre-download model" if you want to cache it first
-4. Start recording - transcription happens automatically after recording
-
-### Models Available
-- **Tiny** (~39MB) - Fast, good for short clips (2-3 seconds)
-- **Base** (~74MB) - Balanced accuracy and speed (3-5 seconds)
-- **Small** (~244MB) - Best quality, slower (6-10 seconds)
-
-### Performance
-- Transcribes ~30-second clip in 2-10 seconds (depending on model)
-- First run may be slower (model loading)
-- Subsequent runs are instant (cached)
-
-### Privacy
-- ✅ Audio never transmitted
-- ✅ Models run locally in WASM
-- ✅ No network calls during transcription
-- ✅ HIPAA-compliant
-
----
-
-## Option 2: Server Transcription (Cloud, Fast)
-
-### What It Is
-- Sends audio to your configured AI provider
-- Uses Google Gemini, AWS Transcribe, OpenAI Whisper, or LiteLLM
-
-### When to Use
-- ✅ Maximum speed (~1 second for 30-second clip)
-- ✅ Best accuracy (cloud models)
-- ✅ Long recordings (Browser Whisper can be slow for 5+ minutes)
-- ✅ HIPAA-compliant with BAA providers
-
-### HIPAA-Eligible Providers
-- **Google Vertex AI** (with BAA) ✅
-- **AWS Transcribe** (with BAA) ✅
-- **Azure OpenAI** (with BAA) ✅
-- **OpenAI Whisper Direct** ❌ Not HIPAA-eligible
-
-### How to Enable
-- Configured via environment variables (`.env`)
-- No user action needed - just works if API keys present
-- Falls back automatically if Browser Whisper fails
-
-### Cost
-- Google Gemini: ~$0.005/minute
-- AWS Transcribe: ~$0.024/minute
-- OpenAI: $0.006/minute
-
----
-
-## Option 3: Web Speech API (Real-Time, Experimental) ⚠️
-
-### What It Is
-- Uses your browser's built-in speech recognition
-- Shows transcription **in real-time** as you speak (streaming)
-- Chrome/Edge → Google Cloud Speech
-- Safari → Apple Speech Recognition
-
-### ⚠️ PRIVACY WARNING
-- **Audio IS sent to cloud servers** (Google, Apple, etc.)
-- **NOT HIPAA-compliant**
-- Only use for non-clinical, personal use
-
-### When to Use
-- ✅ Personal notes (non-clinical)
-- ✅ Want real-time feedback while speaking
-- ✅ Demonstration/testing
-- ❌ **NEVER for patient data**
-
-### How to Enable
-1. Settings → Real-Time Streaming Transcription
-2. Read privacy warning carefully
-3. Toggle "Enable real-time streaming" ON
-4. Confirm warning dialog
-5. Grants microphone permission
-6. Start recording - see words appear live
-
-### Limitations
-- Not available in all browsers (requires Web Speech API)
-- Accuracy varies by browser
-- Requires internet connection
-- May have usage limits
-
----
-
-## Choosing the Right Option
-
-### For Clinical Use (HIPAA Required)
-**Use:** Browser Whisper (offline) OR Server (Vertex AI/AWS with BAA)
-- Browser Whisper: Maximum privacy, no costs
-- Server: Faster, better for long recordings
-
-### For Personal Use (Non-HIPAA)
-**Use:** Any option
-- Browser Whisper: Best balance of privacy and accuracy
-- Server: Fastest
-- Web Speech: Real-time feedback
-
-### Decision Tree
-
-```
-Is this clinical/patient data?
-├─ YES → Use Browser Whisper or Server (Vertex/AWS)
-│   ├─ Need offline? → Browser Whisper
-│   ├─ Need speed? → Server (Vertex AI)
-│   └─ Want free? → Browser Whisper
-│
-└─ NO → Any option
-    ├─ Want real-time? → Web Speech API
-    ├─ Want privacy? → Browser Whisper
-    └─ Want speed? → Server
-```
-
----
-
-## Configuration
-
-### Browser Whisper
-```bash
-# No configuration needed - bundled in Docker image
-# Models at: /app/public/models/Xenova/whisper-tiny.en/
-```
-
-### Server Transcription
-```bash
-# .env file
-TRANSCRIBE_PROVIDER=google  # google, aws, openai, litellm
-
-# Google Vertex AI
-GOOGLE_VERTEX_PROJECT=your-project-id
-GOOGLE_APPLICATION_CREDENTIALS=/path/to/key.json
-
-# AWS Transcribe
-AWS_BEDROCK_REGION=us-east-1
-AWS_ACCESS_KEY_ID=your-key
-AWS_SECRET_ACCESS_KEY=your-secret
-
-# OpenAI
-OPENAI_API_KEY=sk-...
-
-# LiteLLM (proxy)
-LITELLM_API_BASE=http://localhost:4000
-LITELLM_API_KEY=optional
-```
-
-### Web Speech API
-```bash
-# No configuration - uses browser built-in
-# Privacy warning shown in Settings UI
-```
-
----
-
-## FAQ
-
-### Q: Which is most accurate?
-**A:** Browser Whisper and Server (Gemini/Whisper) are equally accurate. Web Speech is slightly less accurate.
-
-### Q: Which is fastest?
-**A:** Server transcription (~1s) > Web Speech (real-time) > Browser Whisper (2-10s)
-
-### Q: Which is most private?
-**A:** Browser Whisper (100% offline) > Server (with BAA) > Web Speech (not private)
-
-### Q: Can I use multiple at once?
-**A:** No. Priority: Web Speech > Browser Whisper > Server (whichever is enabled first)
-
-### Q: What if transcription fails?
-**A:** Automatic fallback chain:
-1. Browser Whisper (if enabled)
-2. Falls back to Server (if configured)
-3. Falls back to live transcript (if available)
-
-### Q: Is Browser Whisper really offline?
-**A:** Yes! Models are bundled in the Docker image. After the page loads once, transcription works with zero network access.
-
-### Q: Does Web Speech work offline?
-**A:** No. It requires internet to send audio to cloud servers.
-
-### Q: Can I train/customize the models?
-**A:** No. Browser Whisper uses pre-trained models. Server transcription uses cloud models. No custom training available.
-
----
-
-## Troubleshooting
-
-### Browser Whisper stuck at "Initializing"
-- **Cause:** Models not loaded or network blocked during initial download
-- **Fix:** See BROWSER_WHISPER_TROUBLESHOOTING.md
-
-### Server transcription returns "No provider"
-- **Cause:** API keys not configured
-- **Fix:** Set environment variables in `.env`
-
-### Web Speech says "Not supported"
-- **Cause:** Browser doesn't support Web Speech API
-- **Fix:** Use Chrome, Edge, or Safari
-
-### Transcription is slow
-- **Browser Whisper:** Try switching to "Tiny" model
-- **Server:** Check API provider status
-- **Web Speech:** Check internet connection
-
----
-
-## Best Practices
-
-### Clinical Documentation
-1. Use Browser Whisper for all patient data
-2. Enable audio backups (automatic in v2)
-3. Keep recordings under 5 minutes for faster processing
-4. Use "Tiny" model for quick notes, "Base" for detailed documentation
-
-### Personal Use
-1. Web Speech for quick, informal notes
-2. Browser Whisper for anything you want private
-3. Server for long recordings
-
-### Performance Optimization
-1. Pre-download Browser Whisper model before first use
-2. Use shorter clips (30-60 seconds) for fastest results
-3. Clear browser cache if models seem corrupted
-
----
-
-## Summary
-
-| Need | Recommendation |
-|------|---------------|
-| Clinical/HIPAA | Browser Whisper (offline) |
-| Fast transcription | Server (Vertex AI) |
-| Real-time feedback | Web Speech (non-clinical only) |
-| Maximum privacy | Browser Whisper |
-| Zero cost | Browser Whisper |
-| Long recordings | Server (faster for 5+ min clips) |
-| Offline use | Browser Whisper |
-
-**Default recommendation:** Browser Whisper for 95% of use cases. It's private, accurate, free, and offline. Only use alternatives when you have specific needs for speed or real-time feedback.

docker-compose.e2e.yml

@@ -18,10 +18,26 @@ services:
     env_file:
       - .env
     environment:
-      # Disable Turnstile bot-check so tests can log in without a challenge
+      # Disable Turnstile entirely — both server-side verification AND the
+      # client-side widget. Without clearing the SITE_KEY the frontend tries
+      # to initialise the Turnstile iframe against the prod domain and
+      # throws error 110200, which Playwright's pageerror guard correctly
+      # flags as an uncaught exception.
       TURNSTILE_SECRET_KEY: ""
+      TURNSTILE_SITE_KEY: ""
       # Disable SMTP so register auto-verifies the user and returns a session
       SMTP_HOST: ""
+      # Raise the login rate-limit so Playwright multi-worker runs don't
+      # trip the production 10/15min cap. Only affects this e2e container.
+      LOGIN_RATE_LIMIT_MAX: "500"
+      # Also raise the global /api/ limit so multi-spec Playwright runs
+      # that make hundreds of API calls don't burn through the 200/min cap.
+      API_RATE_LIMIT_MAX: "5000"
+      # Allow fetches from the two origins Playwright serves tests from —
+      # the in-network hostname and the host-port loopback. Without this
+      # the CORS middleware (scoped to /api) rejects any non-GET request
+      # because .env's APP_URL points at the production domain.
+      CORS_ORIGINS: "http://pediatric-ai-scribe-e2e:3000,http://host.docker.internal:3553,http://localhost:3553"
     volumes:
       - scribe-logs-e2e:/app/data/logs
     depends_on:

docker-compose.yml

@@ -6,13 +6,31 @@ services:
       - "127.0.0.1:3552:3000"
     env_file:
       - .env
+    environment:
+      CLINICAL_ASSISTANT_MCP_URL: http://mcp:8000/mcp
+      REDIS_URL: redis://ped-ai-redis:6379
+      LOKI_URL: http://monitoring-loki:3100
+      LITELLM_API_BASE: http://litellm:4000
+      TTS_PROVIDER: litellm
+      LITELLM_TTS_MODEL: local-kokoro-tts
+      LITELLM_TTS_VOICE: sherpa/kokoro:am_adam
+      LITELLM_TTS_VOICES: sherpa/kokoro:am_adam,sherpa/kokoro:am_michael,sherpa/kokoro:af_bella,sherpa/kokoro:af_nicole,sherpa/kokoro:bf_emma,sherpa/kokoro:bm_lewis
+      CLINICAL_ASSISTANT_PROMPT_POOL_TARGET: 1000
     volumes:
       - scribe-logs:/app/data/logs
+      - clinical-assistant-mcp-data:/app/mcp-data:ro
     depends_on:
       postgres:
         condition: service_healthy
+      redis:
+        condition: service_healthy
     restart: unless-stopped
     container_name: pediatric-ai-scribe
+    networks:
+      - default
+      - danvics_mcp
+      - danvics_monitoring
+      - danvics_speech
     healthcheck:
       test: ["CMD", "wget", "--spider", "-q", "http://localhost:3000/api/health"]
       interval: 30s
@@ -28,7 +46,7 @@ services:
     environment:
       POSTGRES_DB: pedscribe
       POSTGRES_USER: pedscribe
-      POSTGRES_PASSWORD: ${DB_PASSWORD:?set DB_PASSWORD}
+      POSTGRES_PASSWORD: ${DB_PASSWORD:-pedscribe}
     volumes:
       - pgdata:/var/lib/postgresql/data
     restart: unless-stopped
@@ -40,6 +58,34 @@ services:
       retries: 5
       start_period: 10s
 
+  redis:
+    image: redis:8-alpine
+    command: redis-server --appendonly yes
+    restart: unless-stopped
+    container_name: ped-ai-redis
+    volumes:
+      - redis-data:/data
+    healthcheck:
+      test: ["CMD", "redis-cli", "ping"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+    networks:
+      - default
+      - danvics_mcp
+
 volumes:
   pgdata:
   scribe-logs:
+  redis-data:
+  clinical-assistant-mcp-data:
+    external: true
+    name: mcp-server_mcp-data
+
+networks:
+  danvics_mcp:
+    external: true
+  danvics_monitoring:
+    external: true
+  danvics_speech:
+    external: true

docker-entrypoint.sh

@@ -38,9 +38,34 @@ if [ -n "${OPENBAO_ADDR:-}" ]; then
     exit 1
   fi
 
-  # Export each key/value as a shell-safe env var.
-  # jq's @sh filter single-quote-escapes values so eval is safe.
-  eval "$(printf '%s' "${SECRET_JSON}" | jq -r 'to_entries[] | "export \(.key)=\(.value | @sh)"')"
+  # Export each key/value as a shell-safe env var — but ONLY if the key
+  # isn't already set by docker (env_file / environment: block). This
+  # lets a docker-compose override win over the OpenBao value, which is
+  # needed for e2e (TURNSTILE_SECRET_KEY="" / SMTP_HOST="") and any
+  # environment-specific override.
+  #
+  # Pattern: write jq output to a temp file, then while-read in the main
+  # shell so exports persist (pipes into while run in a subshell and lose
+  # them). Pre-snapshot env keys and skip those already defined.
+  _PRESET_KEYS_FILE=$(mktemp)
+  env | cut -d= -f1 | sort -u > "$_PRESET_KEYS_FILE"
+
+  _SECRET_ASSIGNS=$(mktemp)
+  printf '%s' "${SECRET_JSON}" | jq -r 'to_entries[] | "\(.key)\t\(.value | @sh)"' > "$_SECRET_ASSIGNS"
+
+  _APPLIED_COUNT=0
+  _SKIPPED_COUNT=0
+  while IFS="$(printf '\t')" read -r _K _VAL_QUOTED; do
+    if [ -z "$_K" ]; then continue; fi
+    if grep -qxF "$_K" "$_PRESET_KEYS_FILE"; then
+      _SKIPPED_COUNT=$((_SKIPPED_COUNT + 1))
+    else
+      eval "export $_K=$_VAL_QUOTED"
+      _APPLIED_COUNT=$((_APPLIED_COUNT + 1))
+    fi
+  done < "$_SECRET_ASSIGNS"
+  rm -f "$_PRESET_KEYS_FILE" "$_SECRET_ASSIGNS"
+  echo "[entrypoint]   applied ${_APPLIED_COUNT} secrets; ${_SKIPPED_COUNT} already set by docker (kept override)"
 
   # Bootstrap credentials are no longer needed in the Node process env.
   unset OPENBAO_ROLE_ID OPENBAO_SECRET_ID BAO_TOKEN

docs/ARCHITECTURE.md

@@ -0,0 +1,90 @@
+# Architecture
+
+This document is the current high-level map for Ped-AI. It is intentionally shorter and more operational than the older deep-dive files under `docs/logic/`.
+
+## System Shape
+
+Ped-AI is a self-hosted Express application with a browser frontend, PostgreSQL storage, Redis operational state, LiteLLM model routing, and optional MCP-backed clinical retrieval.
+
+| Area | Owner | Notes |
+|---|---|---|
+| Web app | Ped-AI | Auth, UI, clinical workflows, admin settings, notes, Learning Hub, bedside tools |
+| Database | PostgreSQL | Users, sessions, settings, saved app data, audit/API/access logs |
+| Operational cache | Redis | Prompt suggestions, lightweight state, queue groundwork; not clinical answer caching |
+| Model gateway | LiteLLM | Text, speech, image, embedding model discovery and routing |
+| Clinical retrieval | MCP service | Nextcloud access, indexing, search, rerank, source metadata |
+| Reverse proxy | Caddy or equivalent | TLS and public routing |
+
+## Request Flow
+
+Normal app request:
+
+```txt
+browser
+  -> reverse proxy
+  -> Express middleware
+  -> auth/session check when protected
+  -> route handler
+  -> PostgreSQL/Redis/provider calls as needed
+  -> JSON or HTML fragment response
+```
+
+Clinical Assistant request:
+
+```txt
+browser
+  -> Ped-AI clinical assistant route
+  -> MCP semantic search for indexed clinical sources
+  -> Ped-AI builds grounded answer prompt
+  -> LiteLLM chat model
+  -> Ped-AI returns answer plus source metadata
+  -> browser renders markdown, citations, and source cards
+```
+
+Ped-AI owns the user workflow and rendering. MCP owns retrieval and indexed source metadata. LiteLLM owns model routing.
+
+## Runtime Boundaries
+
+| Boundary | Main Risk | Current Direction |
+|---|---|---|
+| Browser to Ped-AI | XSS, stale shell, session handling | Sanitized rendering, httpOnly cookie for web, cache busting |
+| Ped-AI to PostgreSQL | schema drift, slow queries | migrations, maintenance checks, indexes where needed |
+| Ped-AI to Redis | unavailable operational state | Redis is useful but should not hold required clinical answers |
+| Ped-AI to LiteLLM | provider downtime, wrong model mode | metadata-based model discovery and timeouts |
+| Ped-AI to MCP | retrieval latency/failure | explicit MCP client layer and graceful fallback messages |
+| MCP to Nextcloud | stale indexed metadata | scanner/indexer updates source metadata over time |
+
+## Source Of Truth
+
+| Data | Source Of Truth |
+|---|---|
+| User accounts and sessions | Ped-AI PostgreSQL |
+| Admin app settings | Ped-AI PostgreSQL `app_settings` |
+| Clinical source documents | Nextcloud and MCP index |
+| Clinical source title/path shown to users | MCP result metadata, especially indexed `file_path` |
+| Clinical answer text | Generated per request; intentionally not cached |
+| Model availability | LiteLLM metadata and configured fallbacks |
+
+## Deployment Shape
+
+Production usually runs:
+
+```txt
+Caddy/TLS
+  -> pediatric-ai-scribe container
+     -> pedscribe-db container
+     -> ped-ai-redis container
+     -> LiteLLM endpoint
+     -> MCP endpoint
+```
+
+The app should stay private behind the reverse proxy. Do not expose PostgreSQL, Redis, MCP internals, or provider keys publicly.
+
+## Design Principles
+
+- Keep Ped-AI stateless enough to run more than one app container.
+- Keep clinical answer generation live and source-grounded; do not cache final clinical answers.
+- Prefer model capability metadata over model-name regexes.
+- Prefer indexed file names and paths over embedded PDF metadata for source titles.
+- Keep renderer fixes narrow and tested because LLM markdown is messy.
+- Keep old frontend globals working until the affected feature is intentionally converted to ESM.

docs/CLINICAL_ASSISTANT.md

@@ -0,0 +1,97 @@
+# Clinical Assistant
+
+The Clinical Assistant is a retrieval-grounded assistant for pediatric clinical reference questions. It is not the same as the app's note-generation/HPI workflow.
+
+## Responsibilities
+
+| Component | Responsibility |
+|---|---|
+| Browser UI | question input, source display, markdown/citation rendering, export |
+| Ped-AI backend | settings, MCP search call, answer prompt construction, model call |
+| MCP server | Nextcloud access, indexing, vector search, rerank, source metadata |
+| LiteLLM | model routing and provider abstraction |
+
+## Request Flow
+
+```txt
+User asks a question
+  -> browser posts to Ped-AI
+  -> Ped-AI calls MCP `nc_semantic_search`
+  -> MCP returns source excerpts and metadata
+  -> Ped-AI builds an answer prompt with source constraints
+  -> LiteLLM model returns answer text
+  -> browser renders answer and source cards
+```
+
+## Source Rules
+
+- Prefer MCP `file_path` basename for displayed source titles when present.
+- Do not relabel one source as another requested source.
+- If the user names a source and retrieval does not return it, say that before using other sources.
+- Use citations only for returned source numbers.
+- Unknown citation numbers should remain plain text instead of being guessed.
+
+## Table And Markdown Rendering
+
+LLM output is not guaranteed to be valid markdown. The browser renderer defensively handles common problems:
+
+- adjacent citation clusters,
+- missing closing bracket in narrow citation cases,
+- smashed bullet lists,
+- inline headings,
+- malformed pipe tables,
+- bare source numbers in source/citation table columns,
+- orphan markdown emphasis markers,
+- code blocks that must not be modified.
+
+Renderer fixes must be narrow. Do not add broad repairs that turn arbitrary clinical numbers into citations.
+
+## Image Routing
+
+Table lookup requests should stay in retrieval flow.
+
+Examples that should use retrieval:
+
+```txt
+show me the table
+show me Table 13.1
+summarize the developmental table
+```
+
+Explicit visual creation/display requests can use image flow.
+
+Examples:
+
+```txt
+create an infographic
+generate a diagram
+show me the image/figure
+```
+
+## Caching Policy
+
+Clinical answer response caching is intentionally disabled. Redis can support prompt suggestions and operational metadata, but final answers should be generated from current retrieval context.
+
+## Settings
+
+Important settings include:
+
+| Setting | Purpose |
+|---|---|
+| `clinical_assistant.chat_model` | Chat model used for answers |
+| `clinical_assistant.image_model` | Image model used for explicit image generation |
+| `clinical_assistant.search_limit` | Number of MCP results requested |
+| `clinical_assistant.context_chars` | Context characters requested from MCP |
+| `clinical_assistant.system_behavior` | Admin-editable assistant behavior guidance |
+
+## Testing Priorities
+
+Add or update tests when changing:
+
+- citation rendering,
+- source title cleanup,
+- named-source provenance behavior,
+- table rendering,
+- image intent routing,
+- MCP result normalization,
+- model discovery or settings behavior.

docs/DEVELOPMENT.md

@@ -0,0 +1,103 @@
+# Development
+
+This is the practical guide for changing Ped-AI safely.
+
+## Local Start
+
+```bash
+cp .env.example .env
+docker compose up -d --build
+curl -fsS http://127.0.0.1:3552/api/health
+```
+
+Run tests from the repository root:
+
+```bash
+npm test
+```
+
+Run a focused syntax check when touching backend entrypoints:
+
+```bash
+node --check server.js
+node --check src/routes/clinicalAssistant.js
+```
+
+## Code Map
+
+| Path | Purpose |
+|---|---|
+| `server.js` | Express entrypoint, middleware, static serving, route mounting |
+| `src/routes/` | API route handlers |
+| `src/utils/ai.js` | Text model routing through configured providers |
+| `src/utils/clinicalAnswer.js` | Clinical Assistant answer prompt and source-grounding rules |
+| `src/utils/clinicalRetrieval.js` | MCP result normalization and source title cleanup |
+| `src/utils/clinicalMcpClient.js` | MCP streamable HTTP client/session handling |
+| `src/utils/litellm.js` | LiteLLM API/admin header helpers |
+| `src/db/database.js` | PostgreSQL pool and compatibility helpers |
+| `public/js/app.js` | SPA shell, tab loading, shared browser actions |
+| `public/js/admin.js` | Admin panel logic |
+| `public/js/assistant/` | Clinical Assistant rendering, sources, images, export, API helpers |
+| `public/js/learningHub/` | Newer modular Learning Hub frontend code |
+| `test/` | Node test suite and frontend module regression tests |
+
+## Change Workflow
+
+1. Read the relevant route, utility, frontend module, and tests before editing.
+2. Make the smallest correct change.
+3. Add or update a regression test when changing clinical rendering, model routing, auth, settings, or source handling.
+4. Run focused tests first if available.
+5. Run `npm test` before deploy or commit.
+6. Deploy with Docker only after tests pass.
+7. Verify `/api/health` after deploy.
+
+## Clinical Assistant Changes
+
+Clinical Assistant changes should usually include tests because small rendering or prompt changes can affect clinical trust.
+
+High-risk areas:
+
+- citation linking,
+- table rendering,
+- source title cleanup,
+- named-source provenance rules,
+- image intent detection,
+- MCP result normalization,
+- provider/model selection.
+
+When a real answer renders badly, save a de-identified example as a fixture or direct test input. Do not make broad global repairs that convert arbitrary numbers into citation links.
+
+## Frontend Rendering Rules
+
+Use `textContent` for plain text. Use `innerHTML` only for static templates, sanitized markdown, or HTML built entirely from escaped values.
+
+Safe patterns:
+
+```js
+el.textContent = userText;
+el.innerHTML = escapeHtml(userText).replace(/\n/g, '<br>');
+el.innerHTML = sanitizeHtml(renderMarkdown(modelOutput));
+```
+
+Unsafe pattern:
+
+```js
+el.innerHTML = modelOutput;
+```
+
+If a dynamic value enters an HTML string, escape it at the point of insertion. If it is an attribute value, escape quotes too.
+
+## Deployment Checks
+
+After deployment:
+
+```bash
+curl -fsS http://127.0.0.1:3552/api/health
+docker compose ps pediatric-scribe
+```
+
+If the browser still shows old frontend behavior, force-refresh or check the injected `BUILD_ID` asset query string.
+
+## Documentation Expectations
+
+Keep docs close to operational truth. If a behavior changes, update the most specific doc in the same change. Prefer short, current docs over long historical explanations.

docs/MODULE_CONVENTIONS.md

@@ -0,0 +1,88 @@
+# Module Conventions
+
+Ped-AI currently uses mixed JavaScript module styles. This is intentional during incremental modernization.
+
+## Current Convention
+
+| Area | Module Style | Notes |
+|---|---|---|
+| Backend `server.js`, `src/**` | CommonJS | Use `require` and `module.exports` for now |
+| New frontend modules | ESM | Use `import` and `export` |
+| Older frontend files | Classic browser globals | Convert only when touching the feature intentionally |
+| Dual browser/test files | Case-by-case | Keep classic style only when tests or browser globals require it |
+
+Do not add root-level `"type": "module"` without a full backend migration plan. It would change how every `.js` file is interpreted by Node.
+
+## CommonJS Example
+
+```js
+var express = require('express');
+var router = express.Router();
+
+module.exports = router;
+```
+
+## ESM Example
+
+```js
+import { escapeHtml } from './assistant/citations.js';
+
+export function renderSourcesList(sources) {
+  return '';
+}
+```
+
+## Frontend Modernization Path
+
+1. New frontend code should be ESM where possible.
+2. Existing globals can remain until that feature is refactored.
+3. Keep browser script load order stable while refactoring.
+4. Export pure helper functions so Node tests can import them.
+5. Use `CustomEvent` or explicit imports instead of adding new global APIs when practical.
+
+## Acceptable Globals
+
+Globals are acceptable when they are part of the current shell contract.
+
+Examples:
+
+- `window.activateTab`,
+- `window.getAuthHeaders`,
+- shared UI helpers still consumed by legacy feature files.
+
+Do not add new globals when an import or event would be clearer.
+
+## Rendering And `innerHTML`
+
+`innerHTML` is allowed only when one of these is true:
+
+- the HTML is a static template controlled by the app,
+- all dynamic values are escaped before insertion,
+- the HTML has passed through the approved sanitizer,
+- the content is a trusted app component fetched from `public/components/`.
+
+Prefer `textContent` for plain text.
+
+Unsafe:
+
+```js
+el.innerHTML = userText;
+el.innerHTML = modelOutput;
+```
+
+Safer:
+
+```js
+el.textContent = userText;
+el.innerHTML = escapeHtml(userText).replace(/\n/g, '<br>');
+el.innerHTML = sanitizeHtml(renderMarkdown(modelOutput));
+```
+
+## Test Expectations
+
+When converting a frontend file to ESM, add or update tests for:
+
+- exported helper functions,
+- expected globals still present if legacy code needs them,
+- no browser-native `prompt`, `alert`, or `confirm`,
+- no unescaped dynamic text inserted through `innerHTML`.

docs/SCALING.md

@@ -0,0 +1,119 @@
+# Scaling
+
+This document describes how Ped-AI should scale without becoming harder to debug or maintain.
+
+## Current Scaling Model
+
+Ped-AI is currently a single app container backed by PostgreSQL and Redis. That is acceptable for self-hosted use, but the code should keep moving toward a shape where multiple app containers can run safely.
+
+```txt
+reverse proxy
+  -> pediatric-ai-scribe replica 1
+  -> pediatric-ai-scribe replica 2
+  -> shared PostgreSQL
+  -> shared Redis
+  -> LiteLLM
+  -> MCP
+```
+
+## Horizontal Scaling Requirements
+
+| Requirement | Why It Matters |
+|---|---|
+| Session state in PostgreSQL/Redis | Any app replica can handle the next request |
+| No clinical state only in memory | Restarting or scaling containers should not lose required state |
+| Shared uploads/storage if files grow | Local container disk does not scale across replicas |
+| Idempotent migrations | Deploying more than one app container should not corrupt schema state |
+| Request timeouts | Slow providers should not exhaust Node workers |
+| Queue for slow jobs | Long work should not block interactive requests |
+| Readiness endpoint | Load balancer should only send traffic to ready replicas |
+
+## What Can Stay In Memory
+
+Small process-local caches are acceptable when they are optional and short-lived.
+
+Examples:
+
+- settings cache with short TTL,
+- provider model metadata cache,
+- static configuration derived at boot.
+
+Do not store required user workflow state only in memory if the action must survive restart or run across replicas.
+
+## Redis Use
+
+Redis is appropriate for:
+
+- prompt suggestion pools,
+- rate-limit coordination if needed,
+- queues and job status,
+- short-lived provider metadata,
+- operational locks.
+
+Redis should not be used for final clinical answer response caching. Clinical answers should be generated live from current retrieval context.
+
+## Queue Candidates
+
+Consider moving these to a queue when latency or concurrency becomes a problem:
+
+- long transcription jobs,
+- file import/export,
+- Learning Hub AI generation from large files,
+- image generation,
+- bulk document operations,
+- provider metadata refresh,
+- long-running admin maintenance actions.
+
+BullMQ with Redis is a natural fit if a queue is added.
+
+## Readiness And Health
+
+Keep `/api/health` fast and simple for liveness.
+
+Add a separate readiness endpoint when scaling:
+
+```txt
+GET /api/ready
+```
+
+It should check:
+
+- PostgreSQL query works,
+- Redis ping works if Redis is required for this deployment,
+- core settings can be read,
+- MCP health is reachable if Clinical Assistant is enabled,
+- LiteLLM metadata or configured model endpoint is reachable if AI features are enabled.
+
+## Database Scaling
+
+Priorities:
+
+- confirm indexes on hot user/session/settings/log tables,
+- keep migrations explicit and reversible where practical,
+- monitor slow queries,
+- cap admin log queries with safe limits,
+- keep audit/log writes batched where possible,
+- avoid long transactions around provider calls.
+
+## Provider Scaling
+
+LiteLLM and MCP can become the bottlenecks before Ped-AI does.
+
+Track:
+
+- LiteLLM request latency,
+- LiteLLM error rate by model,
+- MCP search latency,
+- MCP timeout/error rate,
+- queue depth if async jobs are added,
+- Postgres connections,
+- app container memory and event-loop delay.
+
+## Scaling Order
+
+1. Add request IDs across browser, Ped-AI, MCP, and LiteLLM calls.
+2. Add `/api/ready` for dependency readiness.
+3. Ensure sessions and settings are not process-local.
+4. Add a queue for slow jobs if interactive requests block.
+5. Run a second app replica behind the reverse proxy in a staging/test environment.
+6. Add metrics and alerts around latency, errors, and resource saturation.

docs/ai-providers.md

@@ -1,13 +1,18 @@
 # AI providers
 
 All AI calls flow through `callAI(messages, options)` in `src/utils/ai.js`.
-Provider is selected once at startup and is transparent to callers.
+Provider is selected at startup and is transparent to route handlers.
 
 ## Provider selection
 
-1. If `AI_PROVIDER` env var is set, use it.
-2. Otherwise, check credentials in priority order:
-   `bedrock > azure > vertex > litellm > openrouter`.
+1. If `AI_PROVIDER` is set, it chooses `bedrock`, `azure`, `vertex`,
+   `litellm`, or `openrouter` explicitly.
+2. If `AI_PROVIDER` is unset, `ai.js` initializes every configured client and
+   the last configured non-OpenRouter provider wins in current load order:
+   Bedrock → Azure → Vertex → LiteLLM. If none of those are configured,
+   OpenRouter is the default.
+3. If the selected provider cannot initialize, the code falls back to
+   OpenRouter and surfaces an error if `OPENROUTER_API_KEY` is missing.
 
 ## Providers
 
@@ -15,7 +20,7 @@ Provider is selected once at startup and is transparent to callers.
 
 - SDK: `@aws-sdk/client-bedrock-runtime`.
 - Uses Bedrock **inference profiles** for newer models (cross-region routing).
-- Model families: vendor model (Anthropic), Amazon Nova, Llama (Meta), Mistral, DeepSeek, Cohere.
+- Model families: Amazon Nova, Llama (Meta), Mistral, DeepSeek, Cohere, and other Bedrock-hosted families.
 
 ### Azure OpenAI (BAA-eligible)
 
@@ -27,7 +32,7 @@ Provider is selected once at startup and is transparent to callers.
 
 - SDK: `@google-cloud/vertexai`.
 - Also serves STT (Gemini inline audio) and TTS (Vertex TTS endpoint).
-- Families: Gemini 2.5 / 2.0, vendor model on Vertex (Anthropic via GCP), Llama.
+- Families: Gemini 2.5 / 2.0 and Llama.
 
 ### LiteLLM proxy (self-hosted)
 
@@ -124,9 +129,11 @@ Applied to: `soap.js`, `hpi.js`, `refine.js`, `sickVisit.js`, `wellVisit.js`,
 
 ### Physician memories
 
-Saved corrections are injected into prompts as `[STYLE HINTS (low priority)]`
-with 200-character snippets. The low-priority wording prevents smaller models
-from hallucinating content from the correction examples into the current note.
+Saved templates and prompt preferences are injected into prompts as
+`[STYLE HINTS (low priority)]` when they belong to AI-context categories. The
+low-priority wording prevents smaller models from hallucinating content from a
+stored template into the current note. `custom` memories and legacy
+`correction_*` rows are not prompt context.
 
 ## API call logging
 

docs/architecture.md

@@ -1,7 +1,6 @@
 # Architecture
 
-Self-hosted, single-tenant clinical documentation platform. Dockerized Node.js
-server + PostgreSQL + vanilla-JS SPA. No build step on the frontend.
+Self-hosted clinical documentation platform. Dockerized Node.js server, PostgreSQL, Redis, and vanilla-JS SPA. No build step on the frontend.
 
 ## Stack
 
@@ -9,9 +8,11 @@ server + PostgreSQL + vanilla-JS SPA. No build step on the frontend.
 |---|---|
 | Runtime | Node.js 20 (Alpine) + Express 4 |
 | Database | PostgreSQL 16 with `pgvector` extension |
+| Cache / state | Redis for operational cache, prompt suggestions, and queue groundwork |
 | Frontend | Vanilla JavaScript SPA, service-worker cache |
 | Mobile | Capacitor 6 wrapper (Android + iOS) |
-| Container | Docker Compose (app + db) |
+| Container | Docker Compose (app + db + Redis) |
+| Observability | Prometheus metrics at `/metrics`; structured app logs in files, Postgres, and optional Loki |
 | Reverse proxy | External (Caddy, Nginx, Traefik — any) |
 
 ## Repository layout
@@ -47,9 +48,9 @@ src/
     logger.js                    # audit/api/access + Loki shipper
     errors.js                    # generic 500 responder
     models.js, prompts.js, ai.js # AI provider + model + prompt management
-    embeddings.js                # Vertex / LiteLLM / OpenAI embeddings
-    transcribe*.js, tts*.js      # STT / TTS provider clients
-  routes/                        # 27 Express routers (auth, hpi, soap, …)
+    embeddings.js                # LiteLLM embeddings
+    transcribe.js, tts.js        # LiteLLM STT / TTS routes
+  routes/                        # Express routers (auth, hpi, soap, patient education, …)
 
 public/                          # SPA
   index.html                     # shell, loads components on demand
@@ -57,16 +58,19 @@ public/                          # SPA
   js/                            # 24 vanilla JS modules
   components/                    # per-tab HTML fragments
   css/styles.css
-  models/                        # bundled Whisper WASM + model files
 
 mobile/                          # Capacitor wrapper
   capacitor.config.json          # appId com.pedshub.scribe
   src/                           # launcher (server-URL picker)
   android/                       # generated AS project + native Java
 
+.forgejo/workflows/
+  android-apk.yml                # signed APK on tag push; optional Play upload
+  docker-build.yml               # Forgejo registry Docker image build
+
 .github/workflows/
   auto-version.yml               # conventional-commits → semver bump → tag
-  android-release.yml            # signed APK on tag push
+  android-release.yml            # legacy GitHub tag APK release path
   docker-publish.yml             # multi-arch image on tag push
   version-bump.yml               # manual dispatch override
   build-apk.yml                  # legacy TWA APK
@@ -82,7 +86,7 @@ request
   → express.json    (10 MB cap)
   → rate limiters   (general 200 req/min, per-endpoint tighter on auth)
   → static          (public/ with no-cache on HTML, 1h on JS/CSS; ?v=BUILD_ID busts cache per deploy)
-  → route           (27 routers under /api/*)
+  → route           (feature routers under /api/*)
     → authMiddleware (on protected routes: JWT, DB session check, 24h idle, last_activity update)
   → handler
   → response
@@ -121,6 +125,12 @@ per-feature HTML fragments under `public/components/` fetched on demand. JS
 modules talk via `window` globals and `CustomEvent` on `document` — no
 bundler, no framework. Loader order is fixed in `index.html`.
 
+Post-note helpers such as billing suggestions, don't-miss review, and patient
+education handouts are reusable browser-side actions backed by authenticated
+JSON APIs. The patient education helper generates a parent-facing plain-text
+draft from the edited note and keeps the clinician in the review loop before
+copying or sharing.
+
 `authFetch.js` installs a global `fetch` interceptor that treats any 401 on an
 authenticated request as a signal to clear local session state and redirect to
 login. A `BroadcastChannel('pedscribe-auth')` pushes that signal to sibling
@@ -132,8 +142,9 @@ tabs so logging out in one tab drops UI in every open tab.
 |---|---|---|---|
 | `pediatric-ai-scribe` | `ped-ai-local:latest` (built from repo) | 3000 | 127.0.0.1:3552 |
 | `pedscribe-db` | `pgvector/pgvector:pg16` | 5432 | not exposed |
+| `ped-ai-redis` | Redis | 6379 | not exposed |
 
-Named volumes: `pgdata` (database), `scribe-logs` (filesystem audit logs).
+Named volumes: `pgdata` (database), `scribe-logs` (filesystem audit logs), and Redis data if persistence is enabled by compose.
 Application health-check polls `GET /api/health`.
 
 A reverse proxy terminates TLS and forwards to `127.0.0.1:3552`. The app is
@@ -149,3 +160,11 @@ never bound to a public interface directly.
 
 Precached on install: `index.html`, core JS, main stylesheet, login component.
 Cleared on logout (`caches.keys() → caches.delete()`).
+
+## Clinical Assistant And MCP
+
+The clinical assistant can call an external MCP-backed retrieval service. Ped-AI remains responsible for the user workflow, provider selection, prompts, and display. MCP remains responsible for Nextcloud access, indexing, retrieval, and vector search. Clinical answer response caching is intentionally disabled; Redis is used for operational metadata and prompt suggestions, not answer reuse.
+
+## Speech
+
+Browser Whisper and browser-local Whisper model downloads are removed from runtime. Speech-to-text routes through LiteLLM; upstream provider choice belongs in LiteLLM config. Browser-native Web Speech remains available only when explicitly enabled by user settings and browser support.

docs/authentication.md

@@ -123,9 +123,23 @@ necessary UX tradeoff over perfect indistinguishability.
 
 ## Turnstile (Cloudflare bot protection)
 
-Applied to `/api/auth/login`, `/register`, `/forgot-password` when
+Applied to `/api/auth/register` and `/api/auth/forgot-password` when
 `TURNSTILE_SECRET_KEY` is set. No-op when unset (dev mode).
 
+`/api/auth/login` is deliberately **not** gated: the widget could not
+reliably complete a challenge inside the Capacitor WebView, which locked
+mobile users out of the app. Login is covered instead by its per-IP rate
+limit (10 / 15 min), the constant-time credential check, and TOTP 2FA.
+
+The two remaining widgets are rendered explicitly (`api.js?render=explicit`)
+the first time their form becomes visible — Turnstile does not reliably
+complete a challenge inside a `display:none` container, and both forms start
+hidden. Tokens are captured from the render callback, not read back out of
+the injected `[name="cf-turnstile-response"]` input.
+
+Note that the site key is currently **hardcoded** in `public/index.html`.
+`TURNSTILE_SITE_KEY` exists in OpenBao but is not read by any code.
+
 ## Encryption at rest
 
 `src/utils/crypto.js` provides AES-256-GCM helpers. Key loaded from
@@ -146,7 +160,7 @@ Helmet defaults plus:
 - `Strict-Transport-Security: max-age=31536000; includeSubDomains; preload`
 - Content-Security-Policy:
   - `script-src 'self' 'wasm-unsafe-eval' 'unsafe-eval' cdn.jsdelivr.net cdnjs.cloudflare.com challenges.cloudflare.com`
-    (`unsafe-eval` is required by @xenova/transformers for in-browser Whisper)
+    (do not add `unsafe-eval` unless a reviewed dependency requires it)
   - `script-src-attr 'none'` (blocks inline event handlers)
   - `frame-src 'self' challenges.cloudflare.com`
   - `object-src 'none'`

docs/configuration.md

@@ -29,39 +29,33 @@ keys):
 
 | Variable | Purpose |
 |---|---|
-| `AI_PROVIDER` | `openrouter` / `bedrock` / `azure` / `vertex` / `litellm`. Auto-detected by credential presence if unset. |
+| `AI_PROVIDER` | `openrouter` / `bedrock` / `azure` / `vertex` / `litellm`. If unset, the startup loader uses configured credentials and the last initialized provider in Bedrock → Azure → Vertex → LiteLLM order wins; otherwise OpenRouter is the default. |
 | `OPENROUTER_API_KEY` | OpenRouter key (not HIPAA-eligible). |
-| `AWS_BEDROCK_REGION`, `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY` | Bedrock / Transcribe / Transcribe-Medical. |
+| `AWS_BEDROCK_REGION`, `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY` | Bedrock chat provider. |
 | `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_API_KEY`, `AZURE_DEPLOYMENT_NAME`, `AZURE_OPENAI_API_VERSION` | Azure OpenAI. |
-| `GOOGLE_VERTEX_PROJECT`, `GOOGLE_VERTEX_LOCATION`, `GOOGLE_APPLICATION_CREDENTIALS` | Vertex AI + Gemini (STT/TTS). |
+| `GOOGLE_VERTEX_PROJECT`, `GOOGLE_VERTEX_LOCATION`, `GOOGLE_APPLICATION_CREDENTIALS` | Vertex AI chat provider. |
 | `LITELLM_API_BASE`, `LITELLM_API_KEY` | OpenAI-compatible AI gateway (Bifrost, LiteLLM, or similar). |
 
 ### Speech-to-text
 
 | Variable | Purpose |
 |---|---|
-| `TRANSCRIBE_PROVIDER` | `google`, `aws`, `local`, `openai`, `litellm`. Auto-detects if unset. |
-| `OPENAI_API_KEY` | OpenAI Whisper. |
-| `GOOGLE_STT_MODEL` | Gemini model used as STT (default `gemini-2.0-flash`). |
-| `AWS_TRANSCRIBE_MEDICAL` | `true` enables Transcribe Medical. |
-| `AWS_TRANSCRIBE_SPECIALTY` | `PRIMARYCARE` / `CARDIOLOGY` / `NEUROLOGY` / `ONCOLOGY` / `RADIOLOGY` / `UROLOGY`. |
-| `WHISPER_BINARY`, `WHISPER_MODEL_SIZE`, `WHISPER_MODEL_PATH`, `WHISPER_LANGUAGE`, `WHISPER_THREADS` | Local whisper.cpp / faster-whisper. |
+| `TRANSCRIBE_PROVIDER` | Use `litellm`; auto mode uses LiteLLM when configured. |
 | `LITELLM_STT_MODEL` | Model name for LiteLLM-routed STT. |
 
 ### Text-to-speech
 
 | Variable | Purpose |
 |---|---|
-| `GOOGLE_TTS_VOICE` | Google Cloud TTS voice (e.g. `en-US-Journey-F`). |
-| `ELEVENLABS_API_KEY` | ElevenLabs (not HIPAA-compliant). |
-| `LITELLM_TTS_MODEL`, `LITELLM_TTS_VOICE` | LiteLLM-routed TTS. |
+| `LITELLM_TTS_MODEL`, `LITELLM_TTS_VOICE` | LiteLLM-routed TTS model and default voice. |
+| `LITELLM_TTS_VOICES` | Comma-separated LiteLLM-compatible voices exposed in voice search and user preferences. |
 
 ### Embeddings
 
 | Variable | Purpose |
 |---|---|
-| `EMBEDDING_MODEL` | Embedding model name (default `text-embedding-005`, Vertex). |
-| `EMBEDDING_DIMENSIONS` | Vector dimensions (default 768). |
+| `EMBEDDING_MODEL` | LiteLLM embedding model name (default `openai-text-embedding-3-large`). |
+| `EMBEDDING_DIMENSIONS` | Vector dimensions (default 3072). |
 
 ### Email (SMTP)
 
@@ -178,8 +172,8 @@ OpenAI-compatible gateway — LiteLLM, Bifrost, or other proxies.
 
 3. **Update model names** — Different gateways use different naming
    conventions. Bifrost requires `provider/model` format
-   (e.g., `openrouter/vendor-model-sonnet-4.6`), while LiteLLM uses aliases
-   (e.g., `openrouter-vendor-model-sonnet-4.6`). Update model names in:
+   (e.g., `openrouter/gpt-4.1`), while LiteLLM can use deployment aliases
+   (e.g., `openrouter-gpt-4.1`). Update model names in:
    - Admin Panel → Models (chat models)
    - Admin Panel → Settings → `stt.model` (speech-to-text)
    - Admin Panel → Settings → `tts.model` (text-to-speech)

docs/database.md

@@ -138,20 +138,23 @@ Draft/complete encounter workspace. Auto-expires (default 7 d,
 
 ### `user_memories`
 
-Per-user clinical-style hints injected into AI prompts.
+Per-user template and preference rows. Only selected categories are injected
+into AI generation through `/api/memories/context`; `custom` rows are stored
+for the user but not included in prompt context.
 
 | Column | Type | Notes |
 |---|---|---|
 | id | SERIAL PK | |
 | user_id | INTEGER FK users.id ON DELETE CASCADE | |
-| category | TEXT NOT NULL DEFAULT 'custom' | `physical_exam`, `ros`, `encounter_format`, `custom`, `template_*`, `correction_*` |
-| name | TEXT NOT NULL | |
-| content | TEXT NOT NULL | |
+| category | TEXT NOT NULL DEFAULT 'custom' | Valid categories: `physical_exam`, `ros`, `encounter_format`, `family_history`, `assessment_plan`, `custom`, `template_soap`, `template_hpi`, `template_wellvisit`, `template_sickvisit`, `template_ed`. Legacy `correction_*` rows may exist but are filtered out. |
+| name | TEXT NOT NULL | Encrypted with `enc1:` for new rows |
+| content | TEXT NOT NULL | Encrypted with `enc1:` for new rows |
 | created_at, updated_at | TIMESTAMPTZ DEFAULT NOW() | |
 
 ### `audio_backups`
 
-Retry store for failed-transcription audio.
+Optional 24-hour encrypted recovery store for recordings when transcription
+fails, so users can retry without re-recording.
 
 | Column | Type | Notes |
 |---|---|---|

docs/deployment.md

@@ -10,8 +10,9 @@
 
 | Image | Role |
 |---|---|
-| `danielonyejesi/pediatric-ai-scribe-v3:latest` | App container. Published by CI on every tag push (multi-arch: `linux/amd64` + `linux/arm64`). Pull directly or build from source. |
+| `danielonyejesi/pediatric-ai-scribe-v3:latest` | App container. Published by CI on every tag push where configured. Pull directly or build from source. |
 | `pgvector/pgvector:pg16` | Database. |
+| `redis:7-alpine` | Operational Redis cache/state. |
 
 ## Build from source
 
@@ -23,8 +24,7 @@ cp .env.example .env
 docker compose up -d --build
 ```
 
-Two containers come up: `pediatric-ai-scribe` on `127.0.0.1:3552`, `pedscribe-db`
-internal only.
+The default compose starts `pediatric-ai-scribe` on `127.0.0.1:3552`, `pedscribe-db` internally, and `ped-ai-redis` internally.
 
 ## Minimum `.env`
 
@@ -80,7 +80,7 @@ App sets `trust proxy: 1` so rate limiting uses the original client IP.
 | Volume | Contents | Backup priority |
 |---|---|---|
 | `pgdata` | All user data, encounters, memories, audit logs, settings, embeddings | Critical |
-| `scribe-logs` | Filesystem audit log files (JSONL by day) | Low — Postgres also has these in `audit_log` table |
+| `scribe-logs` | Filesystem audit log files (JSONL by day) | High for compliance evidence; Postgres also has audit/API/access tables |
 
 ### Postgres backup / restore
 
@@ -120,6 +120,7 @@ REINDEXes if the ICU library version changed between image builds.
 | `GET /api/health` | `{ok:true}` — public, used by Docker health check |
 | `GET /api/health/detailed` | Provider status — admin-auth required |
 | `GET /api/build` | Build ID (short git SHA) — useful for debugging cache invalidation |
+| `GET /metrics` | Prometheus metrics in text exposition format |
 
 Docker health check in `Dockerfile`: every 30 s, wget-spiders `/api/health`.
 Container marked unhealthy after 5 failures.
@@ -127,7 +128,7 @@ Container marked unhealthy after 5 failures.
 ## Resource footprint
 
 - RAM: 256 MB minimum, 512 MB recommended for one instance with a handful of concurrent users.
-- Disk: ~220 MB image (self-hosted Whisper WASM included). Postgres size scales with audit log retention.
+- Disk: Postgres size scales with audit log retention, saved encounters, documents, and Learning Hub content.
 - CPU: idle load negligible; AI calls are network-bound on the LLM provider side.
 
 ## Production checklist
@@ -141,14 +142,15 @@ Container marked unhealthy after 5 failures.
 - Turnstile keys set for public-facing deployments
 - Reverse proxy serves valid TLS certs
 - Postgres dump scheduled off-host
+- Log retention and backup policy covers `audit_log`, `api_log`, `access_log`, and filesystem `scribe-logs`
 
 ## CI / CD
 
-Four workflows fire on tag push:
+On push (and tag push), these workflows run (depending on runner/site):
 
 | Workflow | Output | Runtime |
 |---|---|---|
-| `android-release.yml` | Signed APK attached to the GitHub release | ~8 min |
+| `.forgejo/workflows/android-apk.yml` | Signed APK attached to the Forgejo release, plus optional Google Play internal track upload | ~8 min |
 | `docker-publish.yml` | Multi-arch image (amd64 + arm64 via native runners) on Docker Hub | ~4 min |
 | `build-apk.yml` | Legacy TWA APK (optional second artifact) | ~2 min |
 
@@ -162,6 +164,7 @@ Triggered by `auto-version.yml` (reads commit messages, bumps + tags via
 |---|---|---|
 | App | 3000 | 127.0.0.1:3552 |
 | Postgres | 5432 | not exposed |
+| Redis | 6379 | not exposed |
 
 Change the app's external port by editing the `ports:` mapping in
 `docker-compose.yml`.
@@ -174,6 +177,8 @@ Change the app's external port by editing the `ports:` mapping in
    via `src/utils/auditQueue.js`, drained on SIGTERM.
 4. Loki (if `LOKI_URL` set) — pushed fire-and-forget per event.
 
+A central Prometheus/Loki/Grafana stack can also scrape `GET /metrics` and collect Docker logs with Promtail. Keep direct Loki push enabled only for structured application events that are useful for compliance and operations.
+
 ## Auto-cleanup
 
 | Target | Policy | Frequency |

docs/developer-guide.md

@@ -37,10 +37,10 @@ src/
     fileType.js                  magic-byte upload verifier
     errors.js                    generic 500 responder
     logger.js                    audit + api + access + Loki shipper
-    embeddings.js                Vertex / LiteLLM / OpenAI embeddings
+    embeddings.js                LiteLLM embeddings
     notify.js                    ntfy push
-    transcribe*.js, tts*.js      STT / TTS provider clients
-  routes/                        27 routers
+    transcribe.js, tts.js        LiteLLM STT / TTS routes
+  routes/                        Express routers for auth, AI workflows, education, logs, and user data
 
 public/
   index.html                     SPA shell, version-stamped asset refs
@@ -49,7 +49,7 @@ public/
   js/                            24 vanilla JS modules (no bundler)
   components/                    per-tab HTML fragments loaded on demand
   css/styles.css
-  models/                        bundled Whisper WASM
+  template-guide.md              downloadable user template guide
 
 mobile/                          Capacitor 6 wrapper (Android + iOS)
 .github/workflows/               CI (auto-version, APK, docker)
@@ -243,24 +243,19 @@ docker exec -w /app pediatric-ai-scribe npm run migrate:new -- add_my_table
 3. Admin-editable automatically through `PUT /api/admin/config` which accepts
    arbitrary keys.
 
-## Physician memory / correction tracker
+## Physician Templates And Preferences
 
-1. On note generation, `trackAIOutput(elementId, text)` captures the original
-   output in memory.
-2. User edits the note in a contenteditable field.
-3. On Save, `saveCorrection(elementId, section)` diffs current vs. original.
-4. If changed by > 2 words or > 20 characters, `POST /api/memories/correction`
-   stores the before/after in `user_memories` with category
-   `correction_{section}`.
-5. Next generation: `GET /api/memories/context` fetches the 10 most recent per
-   category and `src/utils/prompts.js` injects them as
-   `[STYLE HINTS (low priority)]` 200-character snippets.
-
-Tabs with correction capture: Live Encounter, SOAP, Dictation, Sick Visit,
-Well Visit (Hospital Course and Chart Review save corrections when available
-but don't always have a trackable single output element).
-
-Maximum 20 corrections retained per category (oldest deleted).
+1. Settings saves user templates/preferences through `/api/memories` into
+   `user_memories`.
+2. New rows encrypt `name` and `content` with the shared `enc1:` string format.
+3. `GET /api/memories/context` decrypts rows and returns only AI-context
+   categories: `physical_exam`, `ros`, `encounter_format`, `family_history`,
+   `assessment_plan`, `template_soap`, `template_hpi`, `template_wellvisit`,
+   `template_sickvisit`, and `template_ed`.
+4. `custom` rows remain visible in settings but are not included in prompt
+   context.
+5. Legacy `correction_*` rows from the removed correction-learning feature are
+   filtered out rather than deleted.
 
 ## Route reference
 
@@ -277,10 +272,10 @@ Maximum 20 corrections retained per category (oldest deleted).
 | `sickVisit.js` | `/api` | Auth | Sick visit |
 | `milestones.js` | `/api` | Auth | Developmental milestone narratives |
 | `refine.js` | `/api` | Auth | Refine / shorten / clarify |
-| `transcribe.js` | `/api` | Auth | STT (5 providers) |
-| `tts.js` | `/api` | Auth | TTS (3 providers) |
+| `transcribe.js` | `/api` | Auth | LiteLLM STT |
+| `tts.js` | `/api` | Auth | LiteLLM TTS |
 | `encounters.js` | `/api` | Auth | Save / load / optimistic-lock encounters |
-| `memories.js` | `/api` | Auth | Templates + corrections |
+| `memories.js` | `/api` | Auth | Templates + prompt preferences |
 | `audioBackups.js` | `/api` | Auth | Encrypted audio retry store |
 | `documents.js` | `/api` | Auth | S3 documents (magic-byte checked) |
 | `userPreferences.js` | `/api` | Auth | Per-user STT/TTS choice |
@@ -307,10 +302,8 @@ Maximum 20 corrections retained per category (oldest deleted).
 | `milestones.js` + `milestonesData.js` | Milestones tab |
 | `shadess.js` | SSHADESS adolescent assessment |
 | `encounters.js` | Save / load / resume with optimistic lock |
-| `memories.js` | Physician templates + corrections UI |
-| `correctionTracker.js` | Captures AI-output edits |
-| `browserWhisper.js` | In-browser WASM Whisper |
-| `speechRecognition.js` | Web Speech API preview |
+| `memories.js` | Physician templates and prompt preferences UI |
+| `speechRecognition.js` | Explicit opt-in browser Web Speech support |
 | `voicePreferences.js` | Per-user STT/TTS override |
 | `audioBackup.js` | Server + IndexedDB backup retries |
 | `nextcloud.js` | Connect / export |

docs/embeddings-setup.md

@@ -1,8 +1,8 @@
-# Embeddings & Semantic Search Setup
+# Embeddings And Semantic Search Setup
 
 This guide explains how to set up and use the new vector-based semantic search for the Learning Hub.
 
-## 🎯 What's New
+## What This Enables
 
 - **Semantic search** - Find content by meaning, not just keywords
 - **3 search modes**:
@@ -10,9 +10,9 @@ This guide explains how to set up and use the new vector-based semantic search f
   - **Semantic** (`/api/learning/search/semantic`) - AI-powered vector similarity
   - **Hybrid** (`/api/learning/search/hybrid`) - Combines both for best results
 - **Auto-embedding** - Content is automatically vectorized when created/updated
-- **HIPAA-compliant** - Uses Vertex AI embeddings (BAA available)
+- **Gateway-routed** - Uses LiteLLM embeddings so provider policy stays in one place
 
-## 📋 Prerequisites
+## Prerequisites
 
 ### 1. Install pgvector Extension
 
@@ -37,39 +37,24 @@ postgres:
   # ... rest of your config
 ```
 
-### 2. Configure Embedding Provider
+### 2. Configure LiteLLM Embeddings
 
 Add to your `.env` file:
 
 ```bash
-# Option 1: Vertex AI (HIPAA-eligible, recommended)
-EMBEDDING_MODEL=vertex_ai/text-embedding-005
-EMBEDDING_DIMENSIONS=768
-VERTEX_PROJECT=your-gcp-project-id
-VERTEX_LOCATION=us-central1
-GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json
-
-# Option 2: LiteLLM Proxy (routes to any provider)
 LITELLM_API_BASE=http://localhost:4000
 LITELLM_API_KEY=your-key
-EMBEDDING_MODEL=text-embedding-005  # LiteLLM will route to configured provider
-
-# Option 3: OpenAI (NOT HIPAA-eligible, fallback only)
-OPENAI_API_KEY=sk-your-key
-# Uses text-embedding-3-small automatically
+EMBEDDING_MODEL=openai-text-embedding-3-large
+EMBEDDING_DIMENSIONS=3072
 ```
 
-## 🚀 Available Vertex AI Embedding Models
+## Available Embedding Models
 
-Tested and working via LiteLLM:
+The Admin embedding search reads LiteLLM `/model/info` and only shows models with `model_info.mode = "embedding"`. Do not add app-side built-in Vertex/OpenAI embedding lists; configure those choices in LiteLLM.
 
-| Model | Dimensions | Use Case | HIPAA |
-|-------|-----------|----------|-------|
-| **vertex_ai/text-embedding-005** | 768 | English + code (recommended) | ✅ Yes |
-| **vertex_ai/gemini-embedding-001** | 768-3072 | Multilingual + code, best quality | ✅ Yes |
-| **vertex_ai/text-multilingual-embedding-002** | 768 | Multilingual focus | ✅ Yes |
+The local LiteLLM instance currently exposes examples such as `openai-text-embedding-3-large`, `openai-text-embedding-3-small`, and Mistral embedding models. Dimensions are read from LiteLLM metadata when available.
 
-## 🔧 Setup Steps
+## Setup Steps
 
 ### 1. Database Migration
 
@@ -113,12 +98,12 @@ Response:
   "total": 50,
   "withEmbeddings": 50,
   "missing": 0,
-  "model": "vertex_ai/text-embedding-005",
-  "dimensions": 768
+  "model": "openai-text-embedding-3-large",
+  "dimensions": 3072
 }
 ```
 
-## 🔍 Using Semantic Search
+## Using Semantic Search
 
 ### Keyword Search (existing)
 ```bash
@@ -144,12 +129,12 @@ GET /api/learning/search/hybrid?q=fever management
 ```
 Combines keyword + semantic for best results. Automatically deduplicates and ranks by relevance.
 
-## 🔬 How It Works
+## How It Works
 
 1. **Content Creation/Update**:
    - Text is extracted from `title`, `subject`, and `body` (HTML stripped)
-   - Sent to embedding model (Vertex AI)
-   - Returns 768-dimensional vector
+   - Sent to the configured LiteLLM embedding model
+   - Returns an embedding vector
    - Stored in `learning_content.embedding` column
 
 2. **Semantic Search**:
@@ -164,35 +149,23 @@ Combines keyword + semantic for best results. Automatically deduplicates and ran
    - Deduplicates by content ID
    - Sorts by relevance score
 
-## 💰 Cost Estimate (Vertex AI)
+## Cost Estimate
 
-**Titan Text Embeddings (AWS) pricing:**
-- ~$0.10 per 1M tokens
-- Average article: 2,000 words (~2,700 tokens) = $0.00027
-- 1,000 articles: ~**$0.27 one-time**
-- Search queries: ~500 tokens = $0.00005 per query
+Embedding cost depends on the upstream configured in LiteLLM.
 
-**Google Vertex AI pricing:**
-- text-embedding-005: $0.025 per 1M characters
-- Average article: 10,000 chars = $0.00025
-- 1,000 articles: ~**$0.25 one-time**
-- Search queries: ~$0.0000125 per query
-
-## 🐛 Troubleshooting
+## Troubleshooting
 
 ### "pgvector extension not available"
 - Install: `apt-get install postgresql-16-pgvector`
 - For Docker: Use `pgvector/pgvector:pg16` image
 
 ### "Embeddings not configured"
-- Verify `.env` has `VERTEX_PROJECT` or `LITELLM_API_BASE` or `OPENAI_API_KEY`
-- Check service account credentials: `GOOGLE_APPLICATION_CREDENTIALS`
+- Verify `.env` has `LITELLM_API_BASE`
 - Test: `curl http://localhost:3000/api/admin/learning/embeddings/status`
 
 ### "Embedding generation failed"
 - Check logs for API errors
-- Verify Vertex AI API is enabled in GCP
-- Verify service account has `aiplatform.endpoints.predict` permission
+- Verify LiteLLM `/model/info` shows the selected model with `mode: embedding`
 - Check content isn't empty (skips empty bodies)
 
 ### "No results from semantic search"
@@ -200,23 +173,23 @@ Combines keyword + semantic for best results. Automatically deduplicates and ran
 - Lower threshold: `?threshold=0.3` (default 0.5)
 - Verify pgvector index exists: `\di` in psql
 
-## 📊 Performance
+## Performance
 
-- **Embedding generation**: ~500ms per article (Vertex AI)
+- **Embedding generation**: latency depends on the LiteLLM upstream
 - **Search latency**:
   - Keyword: 10-50ms
   - Semantic: 20-100ms (with IVFFLAT index)
   - Hybrid: 30-150ms
 - **Index build time**: ~1-5 seconds per 1,000 articles
 
-## 🔐 Security & Compliance
+## Security And Compliance
 
-- **HIPAA-eligible**: Vertex AI supports BAA (Business Associate Agreement)
+- **Compliance**: controlled by the upstream provider configured in LiteLLM
 - **Data retention**: Embeddings stored in your database only
 - **No PHI**: Only article content (not patient data) is embedded
 - **Encryption**: TLS in transit, at-rest encryption via PostgreSQL
 
-## 🎓 Example Queries
+## Example Queries
 
 **Before (keyword):**
 ```
@@ -244,7 +217,7 @@ Results:
 - Bronchiolitis vs asthma (keyword: 1.0)
 ```
 
-## 📚 API Reference
+## API Reference
 
 ### Admin Endpoints
 

docs/features-explained.md

@@ -0,0 +1,81 @@
+# Features Explained
+
+This file is a practical operator-oriented overview of major Ped-AI features. It intentionally describes the current fork, not historical browser Whisper behavior.
+
+## Clinical Documentation
+
+Ped-AI generates pediatric clinical notes from typed input, dictation, or recorded audio. Major workflows include live encounters, dictation cleanup, sick visits, well visits, SOAP notes, hospital courses, chart review, ED documentation, and developmental milestones.
+
+Model selection is available per task where the UI exposes a tab-level selector. Admin defaults provide the baseline model and user/task choices can override that baseline.
+
+Generated notes can expose post-note helper panels. Billing suggestions and don't-miss review are clinician-facing. Patient education handouts are parent-facing drafts generated from the edited note, with optional diagnosis, medication, and preferred-language context. The clinician must verify the handout before sharing it.
+
+## Phone Extensions And Pagers
+
+The bedside tools include a per-user phone extension and pager directory. Entries support active/trash views, search, soft delete/restore, permanent purge, ZIP export, and JSON/ZIP import. Import preview flags exact active duplicates, exact trashed matches that can be restored, and possible duplicates before committing changes.
+
+## Speech
+
+Final transcription is server-side through LiteLLM. Configure upstream STT providers in LiteLLM rather than in Ped-AI.
+
+Browser-native Web Speech is only an explicit opt-in preview path. It is not the final clinical transcript and may use browser-vendor cloud services.
+
+Browser Whisper and browser-local model workers are removed. Do not expect a pre-download model button, public Whisper worker, or bundled Xenova model path.
+
+## Text To Speech
+
+The voice preview button calls LiteLLM TTS and plays the returned audio in the browser. If preview is silent, check that a LiteLLM voice is selected, the gateway is configured, the user is authenticated, and browser autoplay has not blocked playback.
+
+## Learning Hub
+
+Learning Hub is both a learner-facing content area and an admin/moderator CMS.
+
+- Articles and pearls render sanitized content.
+- Quizzes support single-answer, multi-select, and true/false questions.
+- Presentations use Marp-style markdown with preview and PPTX export.
+- AI generation can use topic text, uploaded source files, or connected Nextcloud WebDAV files.
+- Categories can organize content without deleting the content when category assignments change.
+
+## Nextcloud WebDAV
+
+Users can connect a Nextcloud account with an app password. Learning Hub AI generation can browse files from the connected WebDAV account, and users can set a default browse path to avoid repeatedly navigating to the same clinical content folder.
+
+## Documents And S3
+
+Document upload is optional and depends on S3-compatible storage configuration. Treat uploaded documents as PHI unless you have a separate deployment reason not to.
+
+## Audio Backups
+
+Audio backups exist to recover failed transcription attempts.
+
+- They are created when transcription fails.
+- They are encrypted before persistent storage.
+- They expire automatically.
+- Users can retry or delete them from Settings.
+
+## Admin Panel
+
+Admins can manage users, roles, registration, security settings, model defaults, prompts, logs, and Learning Hub content. Production deployments should enable SSO/2FA and restrict admin access.
+
+## Feature Status
+
+| Feature | Status | Notes |
+|---|---|---|
+| Clinical note generation | Active | Provider depends on `AI_PROVIDER`. |
+| Server transcription | Active | Google/AWS/LiteLLM/OpenAI paths. |
+| Browser Web Speech preview | Optional | Explicit opt-in only. |
+| Browser Whisper | Removed | No public worker or model download path. |
+| Learning Hub CMS | Active | Articles, pearls, quizzes, presentations. |
+| Nextcloud WebDAV | Active | Used for file browsing/content import. |
+| Patient handouts | Active | Parent-facing, note-derived, preferred-language draft. |
+| Extension transfer | Active | ZIP export plus JSON/ZIP import preview. |
+| Audio backups | Active | Failure recovery only. |
+| TTS preview | Active | Depends on configured provider. |
+
+## Troubleshooting
+
+- Check browser console for frontend errors.
+- Check `docker logs pediatric-ai-scribe -f` for backend errors.
+- Check `/api/health` for service status.
+- Check provider credentials and model names before debugging UI state.
+- For Learning Hub file import failures, verify Nextcloud URL, username, app password, and folder path.

docs/improvements.md

@@ -52,7 +52,7 @@ This is the highest-impact improvement for adoption but also the most complex to
 
 ### 5. Offline Mode
 
-**Current state:** The app requires an internet connection for AI generation and cloud-based transcription. Browser Whisper works offline for transcription only.
+**Current state:** The app requires configured server-side providers for AI generation and final transcription. Browser Whisper has been removed from the runtime.
 
 **Improvement:** Add a local AI model option (e.g., a small medical LLM running on the device or local server) so the entire workflow — record, transcribe, generate note — can happen without any network calls. This would be valuable for:
 - Rural clinics with unreliable internet
@@ -74,9 +74,9 @@ Each specialty has unique documentation requirements that could be addressed wit
 
 ### 7. Billing Code Suggestions
 
-**Current state:** The well visit tab includes some billing code references.
+**Current state:** Post-note billing suggestions are active as clinician-facing helper panels on supported note outputs.
 
-**Improvement:** Automatically suggest ICD-10 and CPT codes based on the generated note content. After the AI generates a note, it could analyze the diagnoses, procedures, and visit complexity to suggest appropriate billing codes. This saves time on coding and reduces missed charges.
+**Further improvement:** Improve payer-specific rules, add institution-specific favorites, and add export formats that match common EHR coding workflows.
 
 ### 8. Quality Metrics Dashboard
 
@@ -85,7 +85,7 @@ Each specialty has unique documentation requirements that could be addressed wit
 **Improvement:** Add a dashboard showing:
 - Average note generation time by type
 - Most-used AI models and their accuracy (based on how often users edit the output)
-- Transcription accuracy metrics (if corrections are tracked)
+- Transcription quality metrics from explicit user feedback or retry outcomes
 - Usage patterns by time of day and day of week
 - Cost tracking across AI providers
 
@@ -93,9 +93,9 @@ This would help administrators optimize model selection and identify training op
 
 ### 9. Patient Education Materials
 
-**Current state:** The Learning Hub serves educational content to physicians.
+**Current state:** Patient education handouts are active as post-note helpers. Generated notes can open a Handout panel that creates a parent-facing plain-text draft from the clinician note, with optional diagnosis, medication, patient age, and preferred language context. The Learning Hub remains the physician-facing education/CMS area.
 
-**Improvement:** Add a patient-facing education module that generates age-appropriate handouts based on the diagnosis. For example, after generating a note for a child with asthma, the app could produce a parent-friendly handout explaining the diagnosis, medications, and when to seek emergency care — in the parent's preferred language.
+**Further improvement:** Add handout templates, saved handout history, institution-approved language libraries, and printable/PDF export.
 
 ### 10. Multi-Language Support
 
@@ -140,7 +140,7 @@ This mirrors the real workflow in training institutions and group practices.
 
 ### 14. Template Library
 
-**Current state:** Physician memories and corrections provide some personalization.
+**Current state:** Physician templates and prompt preferences provide per-user personalization. Legacy correction-learning rows may exist but are no longer active behavior.
 
 **Improvement:** Add a shared template library where physicians can create, share, and browse note templates:
 - "My asthma follow-up template"
@@ -182,7 +182,7 @@ Compared to existing medical scribes and documentation tools:
 
 - **Pediatric-specific** — prompts, calculators, milestones, and growth charts designed for children, not adapted from adult tools
 - **Self-hosted** — runs on your own infrastructure, not a SaaS that holds your data
-- **Provider-agnostic** — works with any AI provider (swap between them without changing anything)
-- **Privacy-first** — optional fully offline transcription, auto-expiring data, no permanent PHI storage
-- **Learning system** — AI improves its output based on each physician's editing patterns
+- **Provider-flexible** — routes through OpenRouter, Bedrock, Azure, Vertex, or LiteLLM depending on deployment configuration
+- **Privacy-conscious** — self-hosted app, encrypted sensitive fields, auto-expiring encounter/audio recovery data, and configurable BAA-eligible providers
+- **Template-aware** — user templates and prompt preferences can shape output without relying on automatic correction learning
 - **All-in-one** — documentation, calculators, education, and administration in a single platform

docs/logic/README.md

@@ -0,0 +1,114 @@
+# Application Logic — index
+
+> Deep, dev-friendly documentation of how each part of the ped-ai app
+> actually works. Written so a human developer can understand the
+> codebase without spelunking, and so an AI assistant can confidently
+> modify code without breaking high-risk workflows.
+
+These docs explain **application logic** — what the user does, what the
+system does in response, what the data flow is, and **why** the design
+looks the way it does. They are not API reference (see
+[`../api-reference.md`](../api-reference.md)) and not deployment
+recipes (see [`../deployment.md`](../deployment.md)).
+
+## Read in this order
+
+For someone brand new to the codebase:
+
+1. **[architecture.md](architecture.md)** — Start here. The big picture:
+   current frontend pattern, lazy tab loading, backend route convention,
+   PostgreSQL schema, encryption at rest, Dockerfile + compose layout,
+   and high-risk zones.
+
+2. **[clinical-notes.md](clinical-notes.md)** — How every clinical note
+   tab works. The shared "record → transcribe → generate → save"
+   lifecycle, then per-tab deep dives for Encounter HPI, Dictation HPI,
+   Sick Visit, Well Visit, SOAP, Hospital Course, Chart Review, and
+   Personal Notes. Includes the helper trio (refine / billing-codes /
+   don't-miss).
+
+3. **[ed-encounters.md](ed-encounters.md)** — The ED encounter feature
+   (multi-stage notes, per-stage don't-miss, consolidate→MDM finalize).
+   Newest, most explicit explanation of how a clinical workflow gets
+   composed in this codebase. Read this for a worked example.
+
+4. **[bedside-and-calculators.md](bedside-and-calculators.md)** —
+   Bedside emergencies module, the pediatric calculators (BP percentile, Fenton growth,
+   bilirubin nomograms, etc.), the PE Guide, vax schedule, milestones.
+   Includes the suture selector. **Important:** lists every clinical
+   formula that must NOT be modified without test vectors.
+
+5. **[ai-and-voice.md](ai-and-voice.md)** — AI provider routing
+   (`callAI`), the centralized `PROMPTS` object with DB overrides, the
+   `wrapUserText` + `INJECTION_GUARD` safety pattern, server-side STT
+   routing, TTS, and the AudioRecorder. Voice/STT plumbing is high-risk — the
+   doc describes it without proposing changes.
+
+6. **[auth-admin-learning.md](auth-admin-learning.md)** — Authentication
+   (local + OIDC SSO + 2FA), session management, OpenBao secret loading
+   at container start, the Admin panel (model allowlist, prompt
+   overrides, milestone editor), and the Learning Hub (AI-authored
+   quizzes / outlines / Marp presentations).
+
+## What's NOT here
+
+- **Reference data details.** Every clinical formula's *math* lives in
+  the source files; this doc series points to the formula and explains
+  *what it does* but doesn't reproduce the lookup tables.
+- **API endpoint signatures.** See [`../api-reference.md`](../api-reference.md).
+- **Operational runbooks.** See [`../deployment.md`](../deployment.md),
+  [`../configuration.md`](../configuration.md).
+- **Recent change history.** See git log + the rollback tags
+  (`pre-ts-migration-2026-04-26`, `pre-ed-encounters-2026-04-26`, etc.).
+
+## Voice + conventions
+
+Each doc follows the same structure:
+
+- **Overview** — what this part is and why it exists
+- **User flow** — what the physician does and sees
+- **Data flow** — what HTTP calls happen, what the server does
+- **File map** — which files do what
+- **Key design decisions** — *why* it works the way it does
+- **High-risk zones** — what requires small, tested changes
+- **How to extend** — concrete recipes for adding a new X
+
+When a doc mentions a high-risk zone, changes should be small, well-tested, and
+directly tied to the requested behavior. Current high-risk areas:
+
+| Zone | Why |
+|---|---|
+| `public/js/encounters.js` save/load/idempotency | Save/version/idempotency logic has been carefully tuned; refactors keep silently breaking it. |
+| Voice/STT plumbing (`audioBackup.js`, `speechRecognition.js`, `voicePreferences.js`, `transcriptionSettings.js`, recorder paths in each clinical tab) | Recording UX has been hardened against many edge cases; refactor only with smallest-diff bug fixes. |
+| Validated clinical formulas (BP percentile LMS, Fenton 2013, bilirubin AAP 2022, Bhutani, APLS / Best-Guess weight, PE Guide SCALES) | Validated against peditools / AAP tables; modifying without test vectors risks miscoding patient care. |
+| Auth + crypto (`crypto.js`, `passwords.js`, `sessions.js`, `auth.js`, `oidc.js`) | Security; changes without security review are unsafe. |
+| MDM rubric in `PROMPTS.edFinalize` | Load-bearing for billing accuracy; trim only with explicit AMA/coding source citation. |
+
+## Cross-cutting topics
+
+A few topics span multiple docs. Use these as your jump-off points:
+
+| Topic | Where to look |
+|---|---|
+| Frontend globals, ES modules, and lazy tab loading | architecture.md |
+| Lazy tab loading (`loadComponent`, `tabChanged` event) | architecture.md |
+| `getUserMemoryContext` → templates feeding into AI prompts | clinical-notes.md §6, ed-encounters.md §9 |
+| The helper trio: `refineDocument`, `suggestBillingCodes`, `suggestDontMiss` | ai-and-voice.md §12, clinical-notes.md §5 |
+| `wrapUserText` + `INJECTION_GUARD` prompt-injection defense | ai-and-voice.md §5 |
+| `saveEncounter` API + optimistic locking + idempotency keys | architecture.md §13, clinical-notes.md §4, ed-encounters.md §5 |
+| `cryptoUtil.encryptString` / `encryptBuffer` "enc1:" format | architecture.md §12 |
+| AI provider routing (`callAI`) | ai-and-voice.md §2-3 |
+| 2023 AMA E/M MDM rubric | ed-encounters.md §6 |
+| User templates (`user_memories` table, `template_*` categories) | clinical-notes.md §6, ed-encounters.md §9 |
+
+## How to keep these docs current
+
+Each doc has a date implicit in the most recent feature it describes.
+When you add a feature, update the relevant doc in the same commit.
+When you remove a feature (e.g., the Dragon-style AI corrections
+removal in late April 2026), remove its section + leave a one-line
+historical note in the relevant doc.
+
+When you write a new doc, follow the same structure as these (Overview /
+User flow / Data flow / File map / Design decisions / Sacred zones /
+How to extend) and add it to this index.

docs/logic/ai-and-voice.md

@@ -0,0 +1,101 @@
+# AI, Speech, And Post-Note Helpers
+
+This doc summarizes the current AI/STT/TTS pipeline without line-number
+citations. For exact behavior, read `src/utils/ai.js`, `src/routes/transcribe.js`,
+`src/routes/tts.js`, and the relevant frontend scripts.
+
+## Text Generation
+
+All text-generation routes call `callAI(messages, options)` from
+`src/utils/ai.js`.
+
+Supported providers:
+
+- OpenRouter.
+- AWS Bedrock.
+- Azure OpenAI.
+- Google Vertex AI.
+- LiteLLM or another OpenAI-compatible gateway.
+
+`AI_PROVIDER` can explicitly choose the provider. If unset, the startup loader
+initializes configured clients and the final active provider follows the current
+load order described in [`../ai-providers.md`](../ai-providers.md). Route
+handlers do not call provider SDKs directly.
+
+## Model Allowlist
+
+`callAI()` rejects model IDs outside the active server-side allowlist unless a
+specific admin test path opts out. The allowlist is assembled from built-in
+provider models, `models.disabled`, and `models.custom` in `app_settings`.
+
+The default model comes from the configured provider/model settings. Admins can
+set defaults and custom models from the Admin Panel.
+
+## Prompt Safety
+
+Clinical routes should build prompts with:
+
+- canonical templates from `src/utils/prompts.js`
+- optional DB prompt overrides through `app_settings` keys `prompt.*`
+- `INJECTION_GUARD`
+- `wrapUserText(label, text)` around user-derived text
+
+User-derived text includes transcripts, dictated notes, pasted chart data,
+refine instructions, template preferences, and patient education source notes.
+
+## User Templates
+
+`getUserMemoryContext()` fetches `/api/memories/context` and passes the returned
+template/preference context as `physicianMemories`. Server routes wrap that block
+as low-priority style/template context. `custom` memories and legacy
+`correction_*` rows are not prompt context.
+
+## Speech-To-Text
+
+`POST /api/transcribe` accepts one audio file up to 25 MB. Provider selection:
+
+- explicit `TRANSCRIBE_PROVIDER=litellm`, or
+- auto mode when `LITELLM_API_BASE` is configured.
+
+Direct Google, AWS, local Whisper, and OpenAI Whisper branches are not part of the runtime. Browser Whisper/browser-local model downloads are also absent.
+
+## Browser Web Speech
+
+Browser-native Web Speech is an explicit opt-in preview. It may rely on browser
+vendor cloud services and must not be treated as the final clinical transcript.
+Final transcription should come from the configured server-side STT provider.
+
+## Audio Backup
+
+Failed transcription attempts can create encrypted 24-hour audio backups through
+`src/routes/audioBackups.js`. The user can retry or delete backups from
+Settings. Browser fallback storage is only for cases where the server cannot
+store the failed recording.
+
+## Text-To-Speech
+
+`POST /api/text-to-speech` returns audio from LiteLLM and marks the LiteLLM
+model in `X-TTS-Provider`. Voices are LiteLLM-compatible strings configured by
+`LITELLM_TTS_VOICES`.
+
+## Post-Note Helpers
+
+Generated note outputs can expose helper panels:
+
+- `refineDocument` for editing/refining/shortening generated text.
+- `suggestBillingCodes` for clinician-facing ICD/CPT suggestions.
+- `suggestDontMiss` for clinician-facing safety review.
+- `attachPatientEducation` for parent-facing handout drafts.
+
+These helpers are authenticated API-backed actions. They should treat the edited
+note as the source of truth and keep the clinician in the review loop.
+
+## Change Checklist
+
+When changing this area:
+
+1. Keep provider-specific code inside utility/provider modules.
+2. Wrap all user-derived text with `wrapUserText` before AI calls.
+3. Do not add browser-local Whisper back without a new design review.
+4. Do not add clinical answer response caching.
+5. Run touched-file `node --check` commands and `npm test`.

docs/logic/architecture.md

@@ -0,0 +1,93 @@
+# Application Architecture Logic
+
+This is the long-form companion to [`../architecture.md`](../architecture.md).
+Older versions of this file tried to document every source line and frontend
+wrapper pattern; that became stale as Ped-AI moved selected areas to ES modules,
+added cookie-based web auth, migrations, Redis, metrics, patient education, and
+mobile support.
+
+## Current Shape
+
+- Runtime: Node.js 20 + Express 4 in Docker.
+- Data: PostgreSQL 16 with pgvector, plus Redis for operational cache/prompt
+  suggestion groundwork.
+- Schema: idempotent baseline init in `src/db/database.js` plus versioned
+  migrations in `migrations/` through `node-pg-migrate`.
+- Frontend: vanilla JS SPA. Many files are still classic deferred scripts;
+  isolated newer areas use ES modules. There is no frontend bundler.
+- Auth: web uses the `ped_auth` httpOnly cookie; mobile uses secure token
+  storage and `Authorization: Bearer` headers. `user_sessions` is authoritative.
+- AI: `src/utils/ai.js` routes to OpenRouter, Bedrock, Azure, Vertex, or
+  LiteLLM based on startup configuration and server-side model allowlists.
+- Speech: server-side STT providers plus explicit opt-in browser Web Speech
+  preview. Browser Whisper/browser-local model downloads are not part of the
+  runtime.
+- Observability: `/metrics`, structured JSONL logs, Postgres audit/API/access
+  logs, and optional direct Loki push.
+
+## Composition Root
+
+`server.js` owns the boot and routing order:
+
+1. Load environment and core middleware.
+2. Apply Helmet/CSP, CORS, cookie parsing, metrics, JSON limits, rate limiters,
+   static file serving, and logging.
+3. Mount auth, admin, Learning Hub, clinical workflow, storage, user data,
+   metrics, and utility routers.
+4. Serve the SPA fallback for non-API paths.
+5. Drain audit queues and close Postgres on shutdown.
+
+For exact current route mounts, read `server.js` and `src/routes/*.js`.
+
+## Frontend Pattern
+
+- `public/index.html` is the SPA shell.
+- `public/components/*.html` contains lazy-loaded tab fragments.
+- `public/js/app.js` handles tab activation and dispatches
+  `CustomEvent('tabChanged', { detail: { tab } })`.
+- Feature scripts initialize their DOM only when the relevant tab is active.
+- Shared browser helpers are still exposed through `window.*` where needed.
+- New isolated frontend work should prefer small ES modules where the existing
+  page load order supports it, but do not rewrite unrelated clinical flows just
+  for style.
+
+## Data And PHI
+
+- Sensitive fields use `src/utils/crypto.js` AES-256-GCM helpers.
+- `user_memories.name` and `user_memories.content` are encrypted for new rows.
+- `audio_backups.audio_data` is gzipped and encrypted, then deleted after its
+  short expiry window.
+- `saved_encounters` expire by `site.auto_delete_days`.
+- Audit details are PHI-redacted before database insert.
+
+## Operational Boundaries
+
+- Ped-AI owns the clinical UI, prompts, provider selection, note helpers,
+  patient education, and local user data.
+- External MCP/Nextcloud services own retrieval/indexing when used by clinical
+  assistant features.
+- Clinical answer response caching is intentionally avoided; Redis is for
+  operational metadata and prompt suggestions, not answer reuse.
+
+## High-Risk Areas
+
+Treat these as small-diff zones unless you are deliberately testing a broader
+refactor:
+
+- Auth/session/crypto: `src/middleware/auth.js`, `src/routes/auth.js`,
+  `src/routes/oidc.js`, `src/utils/crypto.js`, `src/utils/sessions.js`.
+- Recording/STT plumbing: `AudioRecorder` in `public/js/app.js`,
+  `public/js/audioBackup.js`, `public/js/speechRecognition.js`,
+  `src/routes/transcribe.js`.
+- Encounter persistence: `src/routes/encounters.js` and
+  `public/js/encounters.js`.
+- Validated calculators/reference data: `public/js/calc-math.js`,
+  `public/js/calculators.js`, `public/data/**`, bedside calculator modules,
+  and tests under `test/`.
+- ED MDM/finalization prompts and billing-related helpers.
+
+## Keep Current
+
+Do not add file-line citations here unless a test locks them down. Prefer
+describing responsibilities and pointing to file paths. If implementation moves,
+update this doc in the same commit.

docs/logic/auth-admin-learning.md

@@ -0,0 +1,62 @@
+# Auth, Admin, And Learning Hub Logic
+
+This doc summarizes the current auth/admin/Learning Hub responsibilities. The
+source of truth is `server.js`, `src/routes/*.js`, and the focused top-level
+docs.
+
+## Auth
+
+- Local auth uses argon2id for new password hashes and bcrypt fallback/rehash
+  for legacy rows.
+- Web sessions use the `ped_auth` httpOnly cookie.
+- Mobile sessions use secure token storage and `Authorization: Bearer`.
+- `user_sessions` is the authoritative session registry.
+- OIDC uses Authorization Code + PKCE through `src/routes/oidc.js`.
+- 2FA uses TOTP plus one-time backup codes.
+
+See [`../authentication.md`](../authentication.md) for details.
+
+## Admin Panel
+
+Admin routes live under `/api/admin` and require admin middleware unless the
+specific route is explicitly public (for example public config reads used by the
+login screen). Admin responsibilities include:
+
+- user management and role changes
+- settings and feature flags
+- model allowlist/defaults/custom models
+- prompt overrides
+- SMTP/OIDC/security settings
+- health/log views
+- milestone management
+- admin docs browser
+
+## Learning Hub
+
+Learning Hub has two surfaces:
+
+- learner/user-facing routes under `/api/learning`
+- moderator/admin CMS routes under `/api/admin/learning`
+
+Content types include articles, pearls, quizzes, and presentations. AI content
+generation can use topic text, uploaded files, or connected Nextcloud/WebDAV
+sources. Semantic search uses pgvector embeddings on `learning_content` when an
+embedding provider is configured.
+
+See [`../learning-hub.md`](../learning-hub.md) and
+[`../embeddings-setup.md`](../embeddings-setup.md).
+
+## Security Rules
+
+- Never expose raw secrets in admin health/config responses.
+- Keep OIDC issuer validation and SSRF protections intact.
+- Keep login, password reset, 2FA, and session endpoints rate-limited.
+- Treat Learning Hub uploads as untrusted input and keep file-type checks.
+- Sanitize rendered Learning Hub content.
+
+## Change Checklist
+
+1. Check the relevant route and frontend module together.
+2. Preserve role middleware order.
+3. Run `node --check` on touched JS files.
+4. Run `npm test`.

docs/logic/bedside-and-calculators.md

@@ -0,0 +1,71 @@
+# Bedside Tools And Calculators
+
+This doc describes the current responsibilities of the bedside/reference area
+without hardcoded line numbers. The source of truth is the code plus the
+calculator test suite.
+
+## Areas
+
+| Area | Files | Notes |
+|---|---|---|
+| Bedside emergencies | `public/js/bedside/*` | ES-module pocket for emergency reference sections. |
+| Core calculators | `public/js/calc-math.js`, `public/js/calculators.js`, `public/js/drugs-loader.js` | `calc-math.js` keeps a dual browser/CommonJS wrapper so tests can `require()` the same formulas used in browser. |
+| Drug data | `public/data/drugs.json` | Loaded by `drugs-loader.js`; fallback constants remain in some UI modules for resilience. |
+| PE Guide | `public/js/peGuide.js`, `src/routes/peGuide.js`, `public/components/pe-guide.html` | Structured PE reference plus AI narrative endpoint. |
+| Well-visit schedule | `public/js/wellVisit/scheduleData.js`, `public/data/well-visit/schedule.json`, `public/js/wellVisit.js` | Schedule JSON is loaded and applied to legacy globals used by the UI. |
+| Milestones | `public/js/milestonesData.js`, `public/js/milestones.js`, `src/routes/milestones.js`, `src/routes/adminMilestones.js` | DB-backed milestone data with static fallback. |
+
+## Calculator Accuracy Rule
+
+Do not change clinical formulas or reference data without tests. Add or update
+test vectors first, then change data/code, then run `npm test`.
+
+Protected examples include:
+
+- APLS and Best Guess weights.
+- Maintenance fluids.
+- Parkland burn fluids and Lund-Browder TBSA.
+- PRAM, Westley croup, GCS, Apgar, bilirubin, BMI, BP, growth, Fenton, and
+  equipment sizing.
+- Emergency medication dosing in resuscitation, anaphylaxis, seizure,
+  sedation, agitation, emesis, trauma, and NRP modules.
+
+## Schedule Data
+
+Well-visit schedule data now lives in JSON:
+
+- `public/data/well-visit/schedule.json`
+- loader: `public/js/wellVisit/scheduleData.js`
+- consumer: `public/js/wellVisit.js`
+- server enrichment: `src/routes/wellVisit.js`
+
+The loader exposes the legacy names expected by the existing UI, including
+`VISIT_AGES`, `PERIODICITY`, `CATCH_UP_SCHEDULE`, `GROWTH_REFERENCE`, and BMI
+classification data.
+
+## Bedside ES Modules
+
+The bedside tab is intentionally split by emergency/reference topic. Keep new
+sections small and self-contained. Shared formatting/helpers should stay in the
+bedside support modules rather than growing `calculators.js` again.
+
+## PE Guide
+
+The PE Guide is partly deterministic reference UI and partly AI-assisted
+narrative generation:
+
+- Browser code collects assessed systems, selected normals/abnormals, and
+  clinician notes.
+- `POST /api/generate-pe-narrative` wraps user-derived text with
+  `wrapUserText` and applies `INJECTION_GUARD` before `callAI`.
+- The route returns a generated narrative plus summary metadata.
+
+## Extension Checklist
+
+When adding or changing a bedside/calculator feature:
+
+1. Add test vectors for any clinical formula or reference boundary.
+2. Keep UI state local unless persistence is explicitly required.
+3. Avoid PHI storage in reference/calculator-only areas.
+4. Prefer small files for new bedside sections.
+5. Run `node --check` on touched scripts and `npm test` before deploy.

docs/logic/clinical-notes.md

@@ -0,0 +1,65 @@
+# Clinical Note Workflows
+
+Clinical note workflows share the same broad lifecycle:
+
+1. User enters text or records audio.
+2. Audio, when used, is transcribed by the configured server-side STT provider.
+3. The frontend gathers demographics, structured form data, and optional user
+   template context.
+4. The route wraps user-derived text with `wrapUserText` and appends
+   `INJECTION_GUARD` before calling `callAI`.
+5. The generated note is inserted as safe text/sanitized output.
+6. Post-note helpers can offer refine/shorten/clarify, billing suggestions,
+   don't-miss review, and parent-facing patient handouts.
+7. Users can save/load encounter drafts through the shared encounter system.
+
+## Main Workflows
+
+| Workflow | Frontend | Route | Notes |
+|---|---|---|---|
+| Live Encounter HPI | `public/js/liveEncounter.js` | `POST /api/generate-hpi-encounter` | Recording/transcript to HPI. |
+| Dictation | `public/js/voiceDictation.js` | `POST /api/generate-hpi-dictation` or `POST /api/generate-soap` | Dictated summary to HPI or SOAP. |
+| SOAP | `public/js/soap.js` | `POST /api/generate-soap` | Transcript/dictation to SOAP. |
+| Sick Visit | `public/js/sickVisit.js` | `POST /api/sick-visit/note` | Chief complaint, transcript/dictation, ROS/PE, diagnosis context. |
+| Well Visit | `public/js/wellVisit.js`, `public/js/shadess.js` | `POST /api/well-visit/note`, `POST /api/well-visit/shadess` | Schedule data, ROS/PE, SSHADESS, milestones, vaccines/screenings. |
+| Hospital Course | `public/js/hospitalCourse.js` | `POST /api/generate-hospital-course` | Pasted notes/labs to course summary. |
+| Chart Review | `public/js/chartReview.js` | `POST /api/generate-chart-review` | Pasted chart content to outpatient review. |
+| ED Encounter | `public/js/ed-encounters.js` | `src/routes/edEncounters.js` | Multi-stage ED workflow; see `ed-encounters.md`. |
+| Milestones | `public/js/milestones.js` | `POST /api/generate-milestone-narrative`, `POST /api/generate-milestone-summary` | Developmental milestone narratives. |
+
+## User Templates
+
+Settings saves templates/preferences in `user_memories`. The frontend calls
+`getUserMemoryContext()` before generation and passes the result as
+`physicianMemories`. Server routes wrap that context as low-priority
+style/template guidance. `custom` memories and legacy `correction_*` rows are
+not injected into prompts.
+
+## Encounter Persistence
+
+Shared save/load behavior lives in `public/js/encounters.js` and
+`src/routes/encounters.js`.
+
+- Encounters are scoped by `user_id`.
+- Rows expire by `site.auto_delete_days`.
+- `idempotency_key` prevents duplicate creates.
+- `version` supports optimistic locking when clients send `expected_version`.
+- Text fields are encrypted at rest for new writes.
+
+## Patient Education
+
+`attachPatientEducation` adds a Handout panel beside supported note outputs.
+`POST /api/patient-education` generates a parent-facing plain-text draft from
+the edited clinician note plus optional diagnosis, medication, age, language,
+and reading-level context. The clinician remains responsible for review before
+sharing.
+
+## Safety Rules
+
+- Do not insert generated clinical output with raw `innerHTML` unless it is
+  intentionally sanitized.
+- Do not add browser-native `prompt`, `alert`, or `confirm` workflows.
+- Do not add inline DOM event handlers.
+- Do not reintroduce browser Whisper/browser-local model downloads.
+- Do not cache clinical answer text in Redis.
+- Keep source transcript/context available for refine actions where relevant.

docs/logic/ed-encounters.md

@@ -0,0 +1,45 @@
+# ED Encounters
+
+The ED encounter workflow is a multi-stage clinical documentation flow for
+emergency visits.
+
+## Shape
+
+- Frontend: `public/js/ed-encounters.js`.
+- Backend: `src/routes/edEncounters.js`.
+- Prompts: ED-specific entries in `src/utils/prompts.js`.
+- Helpers: billing suggestions and don't-miss review can run after generated
+  ED output.
+
+## Typical Flow
+
+1. Capture initial ED context and generate an initial note/stage output.
+2. Add interval updates as the encounter evolves.
+3. Consolidate relevant stages into the final ED note.
+4. Generate MDM/final documentation using the ED finalize prompt.
+5. Optionally run billing and don't-miss helpers.
+6. Save or reload the encounter through the shared encounter system.
+
+## Design Constraints
+
+- Later stages should not silently overwrite earlier clinical text.
+- Regeneration should make it clear which stage is being updated.
+- MDM/finalization prompt changes should be conservative and coding-aware.
+- Don't-miss output is clinician-facing safety support, not a replacement for
+  clinical judgment.
+
+## User Templates
+
+Templates saved under ED-relevant categories can be included through
+`/api/memories/context` and passed as `physicianMemories`. Legacy
+`correction_*` rows are filtered out.
+
+## Testing Checklist
+
+When changing ED behavior:
+
+1. Run syntax checks for `public/js/ed-encounters.js` and
+   `src/routes/edEncounters.js`.
+2. Run `npm test`.
+3. Manually test stage generation, finalization, save/load, and helper panels
+   in an authenticated session when possible.

docs/mobile-build.md

@@ -1,7 +1,8 @@
-# Mobile build & release
+# Mobile Build And Release
 
-Capacitor 6 wrapper. Android only today; iOS project exists but requires macOS
-+ Xcode to produce an `.ipa`.
+Capacitor 6 wrapper around the hosted Ped-AI web app. The launcher defaults to `https://app.pedshub.com`, lets the user change the server URL, and stores that URL locally. Android is buildable on Linux. The iOS project exists but requires macOS and Xcode to produce an `.ipa`.
+
+This is not a separate native clinical app. The native shell provides WebView hosting, microphone permission plumbing, secure storage, and mobile packaging for the same authenticated web app.
 
 ## One-time setup
 
@@ -25,8 +26,12 @@ npx cap open android
 
 ## CI build (preferred)
 
-Tag-triggered. Push any `vX.Y.Z` tag → `.github/workflows/android-release.yml`
-builds a signed APK on a GitHub runner and attaches it to the matching release.
+Push-triggered. Any push to `main`/feature branches and any `vX.Y.Z` tag push
+→ `.forgejo/workflows/android-apk.yml` builds a signed APK on the Forgejo
+runner.
+
+Tagged builds additionally publish the artifact to the matching Forgejo release
+as `pedscribe-<tag>.apk` so Obtainium can track updates.
 
 Required repo secrets (set once, via Settings → Secrets and variables → Actions
 or `gh secret set`):
@@ -35,6 +40,14 @@ or `gh secret set`):
 - `ANDROID_KEYSTORE_PASSWORD`
 - `ANDROID_KEY_ALIAS` — `pedscribe`
 - `ANDROID_KEY_PASSWORD`
+- `GOOGLE_PLAY_SERVICE_ACCOUNT_JSON_B64` — base64 of your Google Play service
+  account JSON (optional). If present, the same tag build also runs `bundleRelease`
+  and uploads the AAB to Play's `internal` track.
+
+Optional Play Store flow:
+- Service account must have permissions to edit releases on the app in Play.
+- Build task is `bundleRelease`, tracked as `com.pedshub.scribe`.
+- Upload lane is `fastlane/android publish_internal` (under `mobile/android/fastlane`).
 
 Tag a release:
 
@@ -44,12 +57,13 @@ git commit -m "feat: ..."  && git push      # auto-version workflow bumps minor
 git commit -m "fix: ..."   && git push      # auto-version workflow bumps patch
 
 # or force an exact version
-scripts/release.sh 6.2.0 --push
+scripts/release.sh X.Y.Z --push
 ```
 
-APK lands at the GitHub release; `/releases/latest` link in the login page
-resolves to it automatically. Obtanium subscribers (`github.com/<owner>/<repo>`)
-pick up the update on next poll.
+APK lands on the Forgejo release. Obtainium can still track
+`git.danvics.com/danvics/pediatric-ai-scribe-v3` releases automatically.
+Play Store upload is handled automatically for tagged builds only when
+`GOOGLE_PLAY_SERVICE_ACCOUNT_JSON_B64` is configured.
 
 ## Local build (fallback / debugging)
 
@@ -69,6 +83,8 @@ Output: `android/app/build/outputs/apk/release/app-release.apk`
 For Play Store, swap `assembleRelease` → `bundleRelease`; output: `.aab` under
 `bundle/release/`.
 
+If web assets or Capacitor config changed, run `npx cap sync android` from `mobile/` before building.
+
 ### Single-quote the password
 
 Keystore passwords with shell metacharacters (`)`, `$`, `!`, space, etc.) must
@@ -109,8 +125,9 @@ user to uninstall + reinstall.
 | Path | Purpose |
 |---|---|
 | `mobile/capacitor.config.json` | appId, name, WebView config, plugin opts |
-| `mobile/src/` | launcher HTML (server URL entry) |
+| `mobile/src/` | launcher HTML and server URL entry, defaulting to `https://app.pedshub.com` |
 | `mobile/android/app/src/main/java/com/pedshub/scribe/MainActivity.java` | JS bridge + WebView mic permission |
 | `mobile/android/app/src/main/java/com/pedshub/scribe/AudioRecordingService.java` | foreground service for background recording |
 | `mobile/android/app/src/main/AndroidManifest.xml` | permissions, intents, backup rules |
-| `.github/workflows/android-release.yml` | CI build |
+| `.forgejo/workflows/android-apk.yml` | CI build |
+| `mobile/android/fastlane/Fastfile` | internal Play track upload lane |

docs/speech.md

@@ -1,83 +1,38 @@
-# Speech: STT, TTS, audio backup
+# Speech: STT, TTS, Audio Backup
 
-## Transcription (speech-to-text)
+## Transcription
 
-### Overview
+`POST /api/transcribe` accepts `multipart/form-data` with one audio file up to 25 MB. Server STT is routed through LiteLLM.
 
-`POST /api/transcribe` accepts `multipart/form-data` with a single audio
-file (≤ 25 MB). Provider is `TRANSCRIBE_PROVIDER` env var, or auto-detected
-(`google > aws > openai`) from available credentials. Each user may override
-via `users.stt_model`; admin-wide default via `stt.model` in `app_settings`.
+Set `TRANSCRIBE_PROVIDER=litellm`, `LITELLM_API_BASE`, and `LITELLM_STT_MODEL`. Auto mode also uses LiteLLM when the gateway is configured.
 
-### Providers
-
-| Provider | Transport | HIPAA (with BAA) |
+| Provider | Notes | HIPAA posture |
 |---|---|---|
-| **Google Gemini** | Inline audio in `generateContent` call. Default model `gemini-2.0-flash`. | Yes |
-| **Amazon Transcribe** | Streaming. `AWS_TRANSCRIBE_MEDICAL=true` + `AWS_TRANSCRIBE_SPECIALTY` switches to Transcribe Medical. Specialties: `PRIMARYCARE`, `CARDIOLOGY`, `NEUROLOGY`, `ONCOLOGY`, `RADIOLOGY`, `UROLOGY`. | Yes |
-| **Local Whisper** | Spawns `whisper.cpp` or `faster-whisper` via `WHISPER_BINARY`. Fully offline. Model sizes `tiny`/`base`/`small`/`medium`/`large`. | N/A (nothing leaves host) |
-| **OpenAI Whisper** | `whisper-1` via `/v1/audio/transcriptions`. Medical-context prompt prepended: `"Medical patient encounter. Pediatric."` | No |
-| **LiteLLM** | Inline audio via LiteLLM's `chat.completions` endpoint (not the `/audio/transcriptions` path). Model from `LITELLM_STT_MODEL`. | Depends on LiteLLM backend |
+| LiteLLM | Sends audio through the configured LiteLLM `/audio/transcriptions` backend. | Depends on the selected upstream. |
 
-## Browser Whisper (fully offline)
+Browser Whisper and browser-local Whisper workers are not part of the runtime. Do not add browser model downloads or Transformers.js STT back into the public app.
 
-Runs entirely in the browser via WebAssembly. Zero network. Suitable when
-no external transcription is acceptable.
+## Web Speech Preview
 
-- Runtime: `@xenova/transformers` (WASM).
-- Models (bundled in the Docker image, no CDN fetch):
-  - `whisper-tiny.en` — 39 MB
-  - `whisper-base.en` — 74 MB
-  - `whisper-small.en` — 244 MB
-- Executes in a dedicated Web Worker; UI thread is never blocked.
-- Models cached in IndexedDB after first load.
-- Per-user toggle. On browser transcription failure, the client falls back to
-  server-side transcription without user intervention.
+Browser-native Web Speech can show interim text when the user explicitly enables it. It is browser/vendor dependent, may send audio to browser-provider cloud services, and should not be treated as the final clinical transcript.
 
-## Live speech preview
+## Text To Speech
 
-Chrome / Edge `webkitSpeechRecognition` streams interim text to the UI during
-recording. Used for real-time preview only — **not** for final transcription.
-The actual transcript comes from the configured STT provider after recording
-ends.
-
-## Text-to-speech
-
-### Overview
-
-`POST /api/text-to-speech`. Returns `audio/mpeg`. `X-TTS-Provider` response
-header identifies the provider used. 5000-character limit per request. Each
-user may override via `users.tts_voice`; admin-wide default via `tts.voice`.
-
-### Providers
+`POST /api/text-to-speech` returns audio from LiteLLM `/audio/speech`. The `X-TTS-Provider` response header identifies the LiteLLM model used. Requests are limited to 5000 characters.
 
 | Provider | Notes |
 |---|---|
-| **Google Cloud TTS** | `@google-cloud/text-to-speech`. Voice families: Journey, Studio, Neural2. |
-| **LiteLLM** | Configured via `LITELLM_TTS_MODEL` + `LITELLM_TTS_VOICE`. Backend-agnostic. |
-| **ElevenLabs** | `eleven_turbo_v2_5`. **Not HIPAA-compliant**. |
+| LiteLLM | Uses `LITELLM_TTS_MODEL` and `LITELLM_TTS_VOICE`. |
 
-## Audio backup
+The admin/user voice pickers read available LiteLLM-compatible voices from `LITELLM_TTS_VOICES`.
 
-Raw audio is saved to Postgres **only when transcription fails**, providing a
-retry window without persisting every recording.
+## Audio Backup
 
-### Storage
+Failed transcription submissions can be stored for retry instead of being silently lost.
 
-- Gzip-compressed, then AES-256-GCM encrypted (0x01 version byte prefix).
-- `BYTEA` column in `audio_backups`.
-- 24-hour `expires_at`, swept hourly.
-- Legacy rows (gzip magic `0x1F` as first byte, no encryption envelope)
-  decompress as-is — detection is deterministic because `0x1F ≠ 0x01`.
+- Audio backups are compressed and encrypted before storage.
+- Backups expire automatically.
+- The Settings audio backup UI can retry or delete saved items.
+- Browser fallback storage is used only when the server cannot save the failed audio.
 
-### Retry UI
-
-Settings → Audio Backups:
-- List: module, size, created, expiry.
-- **Retry** — resubmits to `POST /api/transcribe`.
-- **Delete** — purge now.
-
-### Browser fallback
-
-If the server-side save fails (network, 500, etc.), the client stores the audio
-in IndexedDB so it can retry later. Cleared after successful submission.
+Treat audio backups as sensitive clinical data even when encrypted.

docs/transcription-options.md

@@ -0,0 +1,40 @@
+# Transcription Options
+
+Ped-AI currently supports server-side transcription through LiteLLM plus an explicit browser Web Speech preview option. Browser Whisper was removed and should not be offered in settings, documentation, public workers, or model download scripts.
+
+## Recommended Clinical Setup
+
+Route STT through LiteLLM and configure the compliant upstream in LiteLLM.
+
+| Need | Recommended provider |
+|---|---|
+| Server STT | LiteLLM with a compliant upstream. |
+| Real-time draft preview | Browser Web Speech only with explicit user opt-in and privacy warning. |
+
+Auto-detect uses LiteLLM when `LITELLM_API_BASE` is configured. Direct Google, AWS, local Whisper, and OpenAI Whisper branches are not part of the app runtime.
+
+## Configuration
+
+```env
+TRANSCRIBE_PROVIDER=litellm
+LITELLM_API_BASE=https://your-litellm.example/v1
+LITELLM_API_KEY=<key>
+LITELLM_STT_MODEL=local-parakeet-v3
+```
+
+## Failure Handling
+
+- Server transcription failures can create encrypted audio backups for retry.
+- Users can retry or delete failed backups from Settings.
+- Web Speech interim text is not a substitute for a server transcription response.
+
+## Removed Paths
+
+These should remain absent unless the project intentionally reintroduces browser-local STT with a new design review:
+
+- `public/js/browserWhisper.js`
+- `public/js/whisperWorker.js`
+- `public/js/whisperWorkerV2.js`
+- `public/models/Xenova/*`
+- Browser Whisper setup/troubleshooting docs
+- Whisper model download scripts for public browser models

e2e/fixtures.js

@@ -0,0 +1,166 @@
+// ============================================================
+// SHARED PLAYWRIGHT FIXTURES
+// ============================================================
+// Provides:
+//   - `test` — augmented @playwright/test with auto-applied uncaught-error
+//     guards on every page (pageerror + console.error → test fail)
+//   - `authedPage` fixture — a logged-in page, ready to drive
+//   - `mockAI(page, overrides)` — installs page.route() handlers that
+//     intercept AI endpoints and return canned JSON. Pass `{ real: true }`
+//     or set E2E_USE_REAL_AI=1 to bypass mocking and call real backend.
+// ============================================================
+
+const base = require('@playwright/test');
+
+// ── Environment ──────────────────────────────────────────────
+const E2E_BASE_INTERNAL = 'http://pediatric-ai-scribe-e2e:3000';
+const E2E_BASE_EXTERNAL = 'http://host.docker.internal:3553';
+const E2E_BASE = process.env.E2E_AUTH_BASE_URL || E2E_BASE_INTERNAL;
+
+const TEST_EMAIL = process.env.E2E_TEST_EMAIL || 'e2e-user@ped-ai.test';
+const TEST_PASSWORD = process.env.E2E_TEST_PASSWORD || 'E2E-testPassword123!';
+
+const USE_REAL_AI = process.env.E2E_USE_REAL_AI === '1' || process.env.E2E_USE_REAL_AI === 'true';
+
+// ── Console-error allowlist ─────────────────────────────────
+// Some console messages are expected / noise (e.g. favicon 404). If a
+// message matches one of these patterns it does NOT fail the test.
+const CONSOLE_ERROR_ALLOWLIST = [
+  /favicon/i,
+  /\/api\/models/i,                                  // When no AI provider configured yet
+  /Cross-Origin-Opener-Policy/i,                     // Chrome warning on non-HTTPS e2e server
+  /Failed to load resource.*(400|401|403|404|500|502|503)/i,  // Any HTTP error on subsidiary fetches — smoke tests only verify UI renders, deeper integration tests validate endpoint contracts separately
+  /net::ERR_BLOCKED_BY_CLIENT/i,                     // Adblocker etc.
+  /Cloudflare Turnstile.*110200/i,                   // Expected on e2e: site key hard-coded in index.html but e2e uses different host → domain mismatch error
+  /challenges\.cloudflare\.com\/turnstile/i,         // Turnstile script errors from same root cause
+];
+function isAllowedConsoleNoise(text) {
+  return CONSOLE_ERROR_ALLOWLIST.some(re => re.test(text));
+}
+
+// ── Auth — module-scoped token cache ────────────────────────
+// Keeps one login per worker to avoid the 10/15-min login rate-limiter.
+let _tokenCache = null;
+async function getAuthToken(request) {
+  if (_tokenCache) return _tokenCache;
+  const r = await request.post(E2E_BASE + '/api/auth/login', {
+    data: { email: TEST_EMAIL, password: TEST_PASSWORD },
+  });
+  if (!r.ok()) {
+    const text = await r.text();
+    throw new Error(`E2E login failed (status ${r.status()}): ${text}`);
+  }
+  const body = await r.json();
+  if (!body.token) throw new Error('Login response missing token: ' + JSON.stringify(body));
+  _tokenCache = body.token;
+  return _tokenCache;
+}
+
+async function loginAs(context, request) {
+  const token = await getAuthToken(request);
+  const url = new URL(E2E_BASE);
+  await context.addCookies([{
+    name: 'ped_auth',
+    value: token,
+    domain: url.hostname,
+    path: '/',
+    httpOnly: true,
+    secure: false,
+    sameSite: 'Lax',
+  }]);
+}
+
+// ── AI mock — intercepts generation endpoints ──────────────
+// Canned response shape matches what each route's frontend expects.
+// Override per-test by passing {pattern: responseFn} in overrides.
+async function mockAI(page, overrides = {}) {
+  if (USE_REAL_AI || overrides.real) return; // opt-out to hit real backend
+
+  const routes = [
+    { pattern: '**/api/generate-soap',                  response: { success: true, soap: 'MOCK SOAP NOTE.\nSubjective: ...\nObjective: ...\nAssessment: ...\nPlan: ...', model: 'mock-gpt' } },
+    { pattern: '**/api/generate-hpi-encounter',         response: { success: true, hpi: 'MOCK HPI from encounter.', model: 'mock-gpt' } },
+    { pattern: '**/api/generate-hpi-dictation',         response: { success: true, hpi: 'MOCK HPI from dictation.', model: 'mock-gpt' } },
+    { pattern: '**/api/sick-visit/note',                response: { success: true, note: 'MOCK sick visit note.', model: 'mock-gpt' } },
+    { pattern: '**/api/well-visit/note',                response: { success: true, note: 'MOCK well visit note.', model: 'mock-gpt' } },
+    { pattern: '**/api/generate-hospital-course',       response: { success: true, hospitalCourse: 'MOCK hospital course narrative.', format: 'auto', model: 'mock-gpt' } },
+    { pattern: '**/api/generate-milestone-narrative',   response: { success: true, narrative: 'MOCK developmental narrative.', model: 'mock-gpt', summary: { achieved: 3, notAchieved: 0, notAssessed: 0 } } },
+    { pattern: '**/api/generate-milestone-summary',     response: { success: true, summary: 'MOCK 3-sentence summary.', model: 'mock-gpt' } },
+    { pattern: '**/api/generate-pe-narrative',          response: { success: true, narrative: 'Technique:\nMOCK technique.\n\nFindings:\nMOCK findings.', model: 'mock-gpt', summary: { normal: 2, abnormal: 0, notAssessed: 0 } } },
+    { pattern: '**/api/generate-chart-review',          response: { success: true, review: 'MOCK chart review.', model: 'mock-gpt' } },
+    { pattern: '**/api/well-visit/shadess',             response: { success: true, assessment: 'MOCK SSHADESS assessment.', model: 'mock-gpt' } },
+    { pattern: '**/api/refine',                         response: { success: true, refined: 'MOCK refined content.', model: 'mock-gpt' } },
+    { pattern: '**/api/suggest-billing-codes',          response: { success: true, icd10: [], cpt: [], model: 'mock-gpt' } },
+    { pattern: '**/api/transcribe',                     response: { success: true, transcript: 'MOCK transcribed text.' } },
+    { pattern: '**/api/tts',                            response: { success: true, audioBase64: '' } },
+  ];
+
+  for (const { pattern, response } of routes) {
+    const override = overrides[pattern];
+    await page.route(pattern, async route => {
+      const resp = typeof override === 'function' ? await override(route.request()) : (override || response);
+      await route.fulfill({ status: 200, contentType: 'application/json', body: JSON.stringify(resp) });
+    });
+  }
+}
+
+// ── Error guards — auto-applied via extended test ──────────
+// Any uncaught page JS error or unhandled console.error fails the test.
+// This is the safety net for bugs like the SSO ReferenceError.
+const test = base.test.extend({
+  // Replace the default `page` with one that has listeners wired before
+  // any navigation happens.
+  page: async ({ page }, use) => {
+    const errors = [];
+    const consoleErrors = [];
+
+    page.on('pageerror', err => {
+      // Same allowlist applies to pageerror — third-party scripts (Turnstile)
+      // can throw uncaught errors that are expected on the e2e host.
+      const msg = err && (err.message || String(err));
+      if (isAllowedConsoleNoise(msg)) return;
+      errors.push(err);
+    });
+    page.on('console', msg => {
+      if (msg.type() !== 'error') return;
+      const text = msg.text();
+      if (isAllowedConsoleNoise(text)) return;
+      consoleErrors.push(text);
+    });
+
+    await use(page);
+
+    // After the test finishes, fail if any uncaught errors accumulated.
+    if (errors.length > 0) {
+      throw new Error(
+        'Uncaught page error(s) during test:\n' +
+        errors.map(e => '  - ' + e.message + '\n    ' + (e.stack || '').split('\n').slice(0, 3).join('\n    ')).join('\n')
+      );
+    }
+    if (consoleErrors.length > 0) {
+      throw new Error(
+        'console.error() during test:\n' +
+        consoleErrors.map(t => '  - ' + t).join('\n')
+      );
+    }
+  },
+
+  // Pre-authed page — login before use.
+  authedPage: async ({ page, context, request }, use) => {
+    await loginAs(context, request);
+    await use(page);
+  },
+});
+
+const expect = base.expect;
+
+module.exports = {
+  test,
+  expect,
+  E2E_BASE,
+  TEST_EMAIL,
+  TEST_PASSWORD,
+  loginAs,
+  getAuthToken,
+  mockAI,
+  USE_REAL_AI,
+};

e2e/tests/ai-endpoints-contract.spec.js

@@ -0,0 +1,114 @@
+// ============================================================
+// AI ENDPOINT CONTRACT TESTS — hit the REAL server handlers
+// ============================================================
+// The UI smoke tests mock AI responses via page.route() so they never
+// exercise the server-side handler. That meant a route whose require()
+// statement was wrong (undefined PROMPTS → 500) shipped to prod without
+// any test failing. This spec calls each AI generation endpoint
+// through the Playwright request fixture (bypasses page.route) with a
+// minimal valid payload and only checks the server didn't crash with a
+// ReferenceError / TypeError. A mock model is installed on the server
+// side via MOCK_AI=1 env var (if configured) so we don't spend API
+// credits; otherwise the server still processes the request and returns
+// a structured error (which is fine — we're guarding against 500s from
+// bad imports, not end-to-end AI generation).
+//
+// A non-500 response (200 OK or 4xx with structured JSON) means the
+// handler at least ran — that's the contract we're verifying.
+// ============================================================
+
+const { test, expect, E2E_BASE, getAuthToken } = require('../fixtures');
+
+test.describe('AI endpoint contracts — handler loads + accepts POST', () => {
+  let token;
+
+  test.beforeAll(async ({ request }) => {
+    token = await getAuthToken(request);
+  });
+
+  // Each entry: path, minimal body that should make the handler run past
+  // its import statements. We don't need a valid AI key — a 500 from
+  // a require() bug will still fail, but a 4xx from "missing API key"
+  // is acceptable because it proves the route loaded.
+  const endpoints = [
+    {
+      path: '/api/generate-pe-narrative',
+      body: {
+        steps: [{ component: 'Inspection', label: 'General', method: 'Observed', status: 'normal' }],
+        ageGroup: 'School-Age (6-11 yr)',
+        system: 'neuro',
+        patientAge: '8 years',
+        patientGender: 'male',
+        format: 'narrative',
+      },
+    },
+    {
+      path: '/api/generate-milestone-narrative',
+      body: {
+        milestones: [{ domain: 'Motor', label: 'Walks', status: 'achieved' }],
+        ageGroup: '12 months',
+        patientAge: '12 months',
+        patientGender: 'male',
+      },
+    },
+    {
+      path: '/api/generate-hpi-encounter',
+      body: { transcript: 'Patient with cough for 3 days.', setting: 'outpatient' },
+    },
+    {
+      path: '/api/sick-visit/note',
+      body: { chiefComplaint: 'Cough', transcript: 'Cough x 3 days.' },
+    },
+    {
+      path: '/api/generate-soap',
+      body: { transcript: 'Patient with cough x 3 days.' },
+    },
+    {
+      path: '/api/generate-chart-review',
+      body: { pmh: 'None', outpatientVisits: [], edVisits: [], subspecialtyVisits: [], labs: [] },
+    },
+    {
+      path: '/api/refine',
+      body: { currentDocument: 'MOCK doc', instructions: 'Add severity.' },
+    },
+    {
+      path: '/api/well-visit/shadess',
+      body: { answers: { home: 'lives with parents' } },
+    },
+  ];
+
+  // Signatures of runtime bugs that mean the handler crashed before it
+  // could reach its try/catch (i.e. the exact class of bug being guarded).
+  const CRASH_SIGNATURES = [
+    /Cannot read properties of undefined/i,
+    /is not a function/i,
+    /is not defined/i,
+    /ReferenceError/i,
+    /TypeError/i,
+  ];
+
+  for (const { path, body } of endpoints) {
+    test(`${path} — handler loads, returns structured JSON, no import-bug crash`, async ({ request }) => {
+      const r = await request.post(E2E_BASE + path, {
+        headers: { Authorization: 'Bearer ' + token },
+        data: body,
+      });
+      // Must always be JSON — a 500 HTML page means the express error handler
+      // caught an unhandled exception (our bug class).
+      let json = null;
+      try { json = await r.json(); } catch (_) { /* remains null */ }
+      expect(json, `${path} did not return JSON (HTTP ${r.status()})`).toBeTruthy();
+
+      // If the response leaked a JS error message through to the client,
+      // that's the import/destructure-bug signature we want to catch.
+      const errText = (json && (json.error || json.message)) || '';
+      for (const sig of CRASH_SIGNATURES) {
+        expect(errText, `${path} leaked a runtime error: ${errText}`).not.toMatch(sig);
+      }
+      // Errors should be plain strings — never raw error objects.
+      if (json && json.success === false) {
+        expect(typeof json.error).toBe('string');
+      }
+    });
+  }
+});

e2e/tests/auth-gated-smoke.spec.js

@@ -6,50 +6,10 @@
 // Each test logs in via the API (no UI interaction needed) and injects the
 // session cookie into the browser context.
 
-const { test, expect } = require('@playwright/test');
-
-const E2E_BASE_INTERNAL = 'http://pediatric-ai-scribe-e2e:3000';
-const E2E_BASE_EXTERNAL = 'http://host.docker.internal:3553'; // only used when running Playwright on host
-const E2E_BASE = process.env.E2E_AUTH_BASE_URL || E2E_BASE_INTERNAL;
-
-const TEST_EMAIL = 'e2e-user@ped-ai.test';
-const TEST_PASSWORD = 'E2E-testPassword123!';
-
-// Module-scoped token cache — one login per Playwright worker (config uses
-// workers:1, so effectively one login for the whole run). Without this we
-// hit the 10/15min login rate-limit on the first pass.
-let _tokenCache = null;
-
-async function getAuthToken(request) {
-  if (_tokenCache) return _tokenCache;
-  const r = await request.post(E2E_BASE + '/api/auth/login', {
-    data: { email: TEST_EMAIL, password: TEST_PASSWORD },
-  });
-  if (!r.ok()) {
-    const text = await r.text();
-    throw new Error(`Login failed (status ${r.status()}): ${text}`);
-  }
-  const body = await r.json();
-  if (!body.token) throw new Error('Login response missing token: ' + JSON.stringify(body));
-  _tokenCache = body.token;
-  return _tokenCache;
-}
-
-async function loginAs(context, request) {
-  const token = await getAuthToken(request);
-  const url = new URL(E2E_BASE);
-  await context.addCookies([
-    {
-      name: 'ped_auth',
-      value: token,
-      domain: url.hostname,
-      path: '/',
-      httpOnly: true,
-      secure: false,
-      sameSite: 'Lax',
-    },
-  ]);
-}
+// Uses the shared fixture so the token cache is unified across every spec
+// — each Playwright worker does ONE login for the whole run, staying under
+// the 10/15min login rate-limit.
+const { test, expect, E2E_BASE, loginAs } = require('../fixtures');
 
 // ── Tests ────────────────────────────────────────────────────────────
 

e2e/tests/auth-screen.spec.js

@@ -0,0 +1,70 @@
+// ============================================================
+// AUTH SCREEN — unauthenticated landing page structure.
+// These tests do NOT use the `authedPage` fixture; they visit the
+// app with a fresh context (no cookie) and assert the sign-in
+// form + register + forgot-password transitions render correctly.
+// ============================================================
+
+const { test, expect, E2E_BASE } = require('../fixtures');
+
+test.describe('Unauthenticated auth screen', () => {
+
+  // Use the base test that doesn't auto-login.
+  test('landing shows login form with email + password fields', async ({ page }) => {
+    await page.goto(E2E_BASE + '/');
+    await expect(page.locator('#auth-screen')).toBeVisible({ timeout: 10000 });
+    await expect(page.locator('#login-email')).toBeVisible();
+    await expect(page.locator('#login-password')).toBeVisible();
+    await expect(page.locator('#btn-local-login')).toBeVisible();
+    // main app body must be hidden while unauthenticated
+    await expect(page.locator('#main-app')).toBeHidden();
+  });
+
+  test('register link is present but currently disabled (display:none)', async ({ page }) => {
+    // Invite-only registration hides the link while keeping the form in the DOM.
+    await page.goto(E2E_BASE + '/');
+    await page.waitForSelector('#auth-screen', { timeout: 10000 });
+    const display = await page.locator('#show-register').evaluate(el => el.style.display);
+    expect(display).toBe('none');
+    // The register form element still exists in the DOM for programmatic access
+    await expect(page.locator('#register-form')).toHaveCount(1);
+  });
+
+  test('register form DOM is wired correctly if manually unhidden', async ({ page }) => {
+    await page.goto(E2E_BASE + '/');
+    await page.waitForSelector('#auth-screen', { timeout: 10000 });
+    // Force the link visible so we can exercise the swap path — useful for
+    // future tests that want to validate the full register flow.
+    await page.locator('#show-register').evaluate(el => { el.style.display = ''; });
+    await page.click('#show-register');
+    await expect(page.locator('#register-form')).toBeVisible();
+    await expect(page.locator('#reg-name')).toBeVisible();
+    await expect(page.locator('#reg-email')).toBeVisible();
+    await expect(page.locator('#reg-password')).toBeVisible();
+    await page.click('#show-login');
+    await expect(page.locator('#login-form')).toBeVisible();
+    await expect(page.locator('#register-form')).toBeHidden();
+  });
+
+  test('clicking "Forgot password?" swaps to forgot form', async ({ page }) => {
+    await page.goto(E2E_BASE + '/');
+    await page.waitForSelector('#auth-screen', { timeout: 10000 });
+    await page.click('#show-forgot');
+    await expect(page.locator('#forgot-form')).toBeVisible();
+    await expect(page.locator('#forgot-email')).toBeVisible();
+    await expect(page.locator('#login-form')).toBeHidden();
+    // Back link returns to login
+    await page.click('#show-login-2');
+    await expect(page.locator('#login-form')).toBeVisible();
+    await expect(page.locator('#forgot-form')).toBeHidden();
+  });
+
+  test('password minlength enforces 8 chars in register form', async ({ page }) => {
+    await page.goto(E2E_BASE + '/');
+    await page.waitForSelector('#auth-screen', { timeout: 10000 });
+    // Attribute check doesn't require the element to be visible.
+    const pw = page.locator('#reg-password');
+    await expect(pw).toHaveAttribute('minlength', '8');
+    await expect(pw).toHaveAttribute('type', 'password');
+  });
+});

e2e/tests/bedside-smoke.spec.js

@@ -1,21 +1,22 @@
 // Bedside module smoke tests.
-// Each test navigates to the Calculators tab, opens Bedside, clicks the target
-// sub-pill, and asserts a known string is rendered. Catches "button doesn't
-// fire / section goes blank" regressions.
+// The harness renders the Calculators + Bedside components side-by-side, so
+// each test selects the target sub-pill (if any) and asserts a known string
+// is rendered. Bedside was promoted to a top-level tab, so there is no longer
+// a calc-nav-pill[data-calc="bedside"] — the panel is always visible in the
+// harness and always the full tab in the live app.
 
 const { test, expect } = require('@playwright/test');
 
-// Helper — open Calculators tab + Bedside panel + (optionally) a sub-pill
 async function openCalculators(page) {
   await page.goto('/e2e-harness.html');
   await page.waitForFunction(() => window.__harnessReady === true);
-  // Give the async innerHTML injection + JS init one more microtask tick
-  await page.waitForSelector('button.calc-nav-pill[data-calc="bedside"]');
+  // Wait for the bedside component to finish injecting — #bedside-age is the
+  // first input in the shared age→weight estimator at the top of the tab.
+  await page.waitForSelector('#bedside-age');
 }
 
 async function openBedside(page, subPill) {
   await openCalculators(page);
-  await page.click('button.calc-nav-pill[data-calc="bedside"]');
   if (subPill) {
     await page.click(`button.calc-pill[data-em="${subPill}"]`);
   }
@@ -128,10 +129,23 @@ test.describe('Bedside — dose calculators fire', () => {
 });
 
 test.describe('Bedside — interactive widgets', () => {
-  test('Lightbox: View pathway image button opens modal', async ({ page }) => {
+  test('Lightbox: seizure pathway image opens and closes', async ({ page }) => {
     await openBedside(page, 'seizure');
     await page.click('button[data-img-src="/img/epilepsy_eiic_pathway.png"]');
     await expect(page.locator('#img-lightbox')).toBeVisible();
+    await expect(page.locator('#img-lightbox-img')).toHaveAttribute('src', /epilepsy_eiic_pathway/);
+    await page.click('#img-lightbox-close');
+    await expect(page.locator('#img-lightbox')).toBeHidden();
+  });
+
+  test('Lightbox: NRP pathway image opens on neonatal sub-pill', async ({ page }) => {
+    await openBedside(page, 'neonatal');
+    // The "View pathway image" button sits inside a collapsed <details>
+    // titled "NRP Resuscitation Pathway" — expand it first.
+    await page.getByText('NRP Resuscitation Pathway').click();
+    await page.click('button[data-img-src="/img/nrp_pathway.png"]');
+    await expect(page.locator('#img-lightbox')).toBeVisible();
+    await expect(page.locator('#img-lightbox-img')).toHaveAttribute('src', /nrp_pathway/);
     await page.click('#img-lightbox-close');
     await expect(page.locator('#img-lightbox')).toBeHidden();
   });

e2e/tests/chart-review-workflow.spec.js

@@ -0,0 +1,54 @@
+// ============================================================
+// CHART REVIEW — fill the form → generate → verify mocked output.
+// ============================================================
+
+const { test, expect, E2E_BASE, mockAI } = require('../fixtures');
+
+async function openTab(page) {
+  await page.goto(E2E_BASE + '/');
+  await page.waitForSelector('button.tab-btn', { timeout: 15000 });
+  const vp = page.viewportSize();
+  if (vp && vp.width <= 768) {
+    await page.click('#btn-menu-toggle').catch(() => {});
+  }
+  await page.click('button.tab-btn[data-tab="chart"]');
+  await page.waitForFunction(() => {
+    const el = document.getElementById('chart-tab');
+    return el && el.classList.contains('active') && el.innerHTML.trim().length > 100;
+  }, { timeout: 15000 });
+}
+
+test.describe('Chart Review — generation workflow', () => {
+
+  test('minimum form → generate → mocked analysis renders in output card', async ({ authedPage: _, page }) => {
+    await mockAI(page);
+    await openTab(page);
+
+    await page.fill('#cr-age', '8 years');
+    await page.selectOption('#cr-gender', 'Male');
+    await page.fill('#cr-pmh', 'Hypothyroidism, asthma');
+
+    // The chart template already renders one visit row with a .visit-content
+    // contenteditable. Fill it so the client-side "at least one visit" guard
+    // doesn't block the generate call.
+    const firstVisit = page.locator('.visit-content').first();
+    await firstVisit.click();
+    await page.keyboard.type('Annual well visit. Growth stable. No acute concerns.');
+
+    const [resp] = await Promise.all([
+      page.waitForResponse('**/api/generate-chart-review', { timeout: 15000 }),
+      page.click('#cr-generate-btn'),
+    ]);
+    expect(resp.status()).toBe(200);
+    await expect(page.locator('#cr-output')).toBeVisible({ timeout: 10000 });
+    await expect(page.locator('#cr-review-text')).toContainText('MOCK chart review');
+  });
+
+  test('load popover opens/closes when its buttons are clicked', async ({ authedPage: _, page }) => {
+    await openTab(page);
+    await page.click('#btn-chart-load');
+    await expect(page.locator('#chart-load-popover')).not.toHaveClass(/hidden/, { timeout: 3000 });
+    await page.locator('#chart-load-popover .enc-pop-close').click();
+    await expect(page.locator('#chart-load-popover')).toHaveClass(/hidden/);
+  });
+});

e2e/tests/encounter-save-load.spec.js

@@ -0,0 +1,83 @@
+// ============================================================
+// ENCOUNTER SAVE/LOAD — save an encounter draft, then load it back
+// and verify the transcript + label repopulate.
+// ============================================================
+
+const { test, expect, E2E_BASE, mockAI, getAuthToken } = require('../fixtures');
+
+async function openTab(page) {
+  await page.goto(E2E_BASE + '/');
+  await page.waitForSelector('button.tab-btn', { timeout: 15000 });
+  const vp = page.viewportSize();
+  if (vp && vp.width <= 768) {
+    await page.click('#btn-menu-toggle').catch(() => {});
+  }
+  await page.click('button.tab-btn[data-tab="encounter"]');
+  await page.waitForFunction(() => {
+    const el = document.getElementById('encounter-tab');
+    return el && el.classList.contains('active') && el.innerHTML.trim().length > 100;
+  }, { timeout: 15000 });
+}
+
+// Purge all saved encounters for the test user so each run starts clean.
+async function wipeSaved(request) {
+  const token = await getAuthToken(request);
+  const auth = { Authorization: 'Bearer ' + token };
+  const r = await request.get(E2E_BASE + '/api/encounters', { headers: auth });
+  if (!r.ok()) return;
+  const d = await r.json().catch(() => ({ items: [] }));
+  for (const it of (d.items || d.encounters || [])) {
+    await request.delete(E2E_BASE + '/api/encounters/' + it.id, { headers: auth }).catch(() => {});
+  }
+}
+
+test.describe('Encounter — save + load saved drafts', () => {
+  test.beforeEach(async ({ request }) => {
+    await wipeSaved(request);
+  });
+
+  test.afterAll(async ({ request }) => {
+    await wipeSaved(request);
+  });
+
+  test('save → load popover lists the saved draft → loading repopulates transcript', async ({ authedPage: _, page }) => {
+    await mockAI(page);
+    await openTab(page);
+
+    // Build a distinct transcript + label so we can verify round-trip
+    const label = 'TEST-ENC-' + Date.now();
+    const transcript = 'Unique transcript content: acute pharyngitis with fever.';
+
+    await page.fill('#enc-age', '7 years');
+    await page.selectOption('#enc-gender', 'Male');
+    await page.locator('#enc-transcript').click();
+    await page.keyboard.type(transcript);
+    await page.fill('#enc-label', label);
+
+    await page.click('#btn-enc-save');
+    // Wait for save toast / API round-trip — watch for a save request
+    await page.waitForResponse(res =>
+      /\/api\/encounters/.test(res.url()) && res.request().method() === 'POST',
+      { timeout: 10000 }
+    );
+
+    // Clear the form and open load popover
+    await page.click('#btn-enc-new');
+    // Transcript should now be empty after 'new'
+    await expect.poll(async () =>
+      (await page.locator('#enc-transcript').innerText()).trim(),
+    { timeout: 3000 }).toBe('');
+
+    await page.click('#btn-enc-load');
+    await expect(page.locator('#enc-load-popover')).not.toHaveClass(/hidden/, { timeout: 5000 });
+    // The saved label appears in the popover list
+    await expect(page.locator('#enc-load-popover')).toContainText(label, { timeout: 5000 });
+
+    // Click the row for this encounter
+    await page.locator('#enc-load-popover').getByText(label).first().click();
+    // Wait for the transcript contenteditable to repopulate
+    await expect.poll(async () =>
+      (await page.locator('#enc-transcript').innerText()),
+    { timeout: 5000 }).toContain('acute pharyngitis');
+  });
+});

e2e/tests/encounter-workflow.spec.js

@@ -0,0 +1,80 @@
+// ============================================================
+// ENCOUNTER TAB — detailed workflow: transcript → generate HPI →
+// refine → shorten. Uses mocked AI so tests don't burn API credits.
+// ============================================================
+
+const { test, expect, E2E_BASE, mockAI } = require('../fixtures');
+
+async function openTab(page) {
+  await page.goto(E2E_BASE + '/');
+  await page.waitForSelector('button.tab-btn', { timeout: 15000 });
+  const vp = page.viewportSize();
+  if (vp && vp.width <= 768) {
+    await page.click('#btn-menu-toggle').catch(() => {});
+  }
+  await page.click('button.tab-btn[data-tab="encounter"]');
+  await page.waitForFunction(() => {
+    const el = document.getElementById('encounter-tab');
+    return el && el.classList.contains('active') && el.innerHTML.trim().length > 100;
+  }, { timeout: 15000 });
+}
+
+test.describe('Encounter — HPI generation workflow', () => {
+
+  test('fill transcript + generate → mocked HPI renders in output pane', async ({ authedPage: _, page }) => {
+    await mockAI(page);
+    await openTab(page);
+
+    // Fill age + setting; transcript is a contenteditable div, not a textarea
+    await page.fill('#enc-age', '8 years');
+    await page.selectOption('#enc-gender', 'Male');
+    await page.locator('#enc-transcript').click();
+    await page.keyboard.type('Chief complaint: 3-day history of fever and cough.');
+
+    // Click generate — wait for the mocked /api/generate-hpi-encounter response
+    const [hpiResp] = await Promise.all([
+      page.waitForResponse('**/api/generate-hpi-encounter'),
+      page.click('#enc-generate-btn'),
+    ]);
+    expect(hpiResp.status()).toBe(200);
+
+    // Output container un-hides and shows the mocked text
+    await expect(page.locator('#enc-output')).toBeVisible();
+    await expect(page.locator('#enc-hpi-text')).toContainText('MOCK HPI from encounter');
+  });
+
+  test('refine action → fetches /api/refine and updates the rendered HPI', async ({ authedPage: _, page }) => {
+    // Override /api/refine to return a recognisable marker so we can tell the refined
+    // content replaced the original.
+    await mockAI(page, {
+      '**/api/refine': { success: true, refined: 'REFINED-MARKER: now a longer narrative.', model: 'mock-gpt' },
+    });
+    await openTab(page);
+
+    await page.fill('#enc-age', '8 years');
+    await page.locator('#enc-transcript').click();
+    await page.keyboard.type('Fever and cough 3 days.');
+    await page.click('#enc-generate-btn');
+    await expect(page.locator('#enc-hpi-text')).toContainText('MOCK HPI', { timeout: 10000 });
+
+    // Type an instruction and hit refine
+    await page.fill('#enc-refine-input', 'Make it longer.');
+    const [refineResp] = await Promise.all([
+      page.waitForResponse('**/api/refine'),
+      page.click('#enc-refine-btn'),
+    ]);
+    expect(refineResp.status()).toBe(200);
+    await expect(page.locator('#enc-hpi-text')).toContainText('REFINED-MARKER', { timeout: 10000 });
+  });
+
+  test('clear transcript button empties the contenteditable', async ({ authedPage: _, page }) => {
+    await mockAI(page);
+    await openTab(page);
+    await page.locator('#enc-transcript').click();
+    await page.keyboard.type('Some content.');
+    await expect(page.locator('#enc-transcript')).toContainText('Some content.');
+    await page.click('#enc-clear');
+    const text = await page.locator('#enc-transcript').innerText();
+    expect(text.trim()).toBe('');
+  });
+});

e2e/tests/extensions-crud.spec.js

@@ -0,0 +1,240 @@
+// ============================================================
+// EXTENSIONS TAB — full CRUD + soft-delete + restore + search
+// ============================================================
+// Uses the shared fixture which logs in + wires pageerror/console-error
+// listeners. No AI mocking needed — Extensions is pure CRUD.
+//
+// Tests against the e2e container (port 3553 on host, 3000 internal).
+// Each test cleans up its own rows to stay isolated.
+// ============================================================
+
+const { test, expect, E2E_BASE, getAuthToken } = require('../fixtures');
+
+// Helper — purge everything in trash, then soft-delete every active row.
+// Leaves the table empty for the next test.
+async function wipeAll(request) {
+  const token = await getAuthToken(request);
+  const auth = { Authorization: 'Bearer ' + token };
+
+  async function purgeTrash() {
+    const r = await request.get(E2E_BASE + '/api/extensions?trash=1', { headers: auth });
+    const d = await r.json();
+    for (const item of (d.items || [])) {
+      await request.delete(E2E_BASE + '/api/extensions/' + item.id + '/purge', { headers: auth });
+    }
+  }
+
+  await purgeTrash(); // first purge anything already in trash
+  const r = await request.get(E2E_BASE + '/api/extensions', { headers: auth });
+  const d = await r.json();
+  for (const item of (d.items || [])) {
+    await request.delete(E2E_BASE + '/api/extensions/' + item.id, { headers: auth });
+  }
+  await purgeTrash(); // now purge the freshly-trashed rows
+}
+
+test.describe('Extensions — CRUD', () => {
+  test.beforeEach(async ({ request }) => {
+    await wipeAll(request);
+  });
+
+  test.afterAll(async ({ request }) => {
+    await wipeAll(request);
+  });
+
+  async function openTab(page) {
+    await page.goto(E2E_BASE + '/');
+    await page.waitForSelector('button.tab-btn', { timeout: 15000 });
+    const vp = page.viewportSize();
+    if (vp && vp.width <= 768) {
+      await page.click('#btn-menu-toggle').catch(() => {});
+    }
+    await page.click('button.tab-btn[data-tab="extensions"]');
+    // Wait for component to load
+    await page.waitForFunction(() => {
+      const el = document.getElementById('extensions-tab');
+      return el && el.classList.contains('active') && el.innerHTML.trim().length > 100;
+    }, { timeout: 15000 });
+    // Wait for first load to resolve (spinner text goes away)
+    await page.waitForFunction(() => {
+      const list = document.getElementById('ext-list');
+      return list && !list.innerHTML.includes('Loading');
+    }, { timeout: 10000 });
+  }
+
+  async function fillForm(page, { location, name, number, type = 'extension', notes = '' }) {
+    await page.click('#ext-add-btn');
+    await page.fill('#ext-location', location);
+    await page.fill('#ext-name', name);
+    await page.fill('#ext-number', number);
+    await page.selectOption('#ext-type', type);
+    if (notes) await page.fill('#ext-notes', notes);
+    await page.click('#ext-save-btn');
+    // Form hides after save
+    await expect(page.locator('#ext-form-wrap')).toHaveClass(/hidden/, { timeout: 5000 });
+  }
+
+  test('empty state shown before any entries', async ({ authedPage: _, page }) => {
+    await openTab(page);
+    await expect(page.locator('#ext-list')).toContainText(/No entries yet|click Add/i);
+  });
+
+  test('add an extension — appears in list grouped by location + type', async ({ authedPage: _, page }) => {
+    await openTab(page);
+    await fillForm(page, { location: 'Main Hospital', name: 'Nursery', number: '5866', type: 'extension' });
+
+    // Location group header
+    await expect(page.locator('#ext-list')).toContainText('Main Hospital');
+    // Type subheader
+    await expect(page.locator('#ext-list')).toContainText(/Extensions/i);
+    // Card content
+    await expect(page.locator('.ext-card')).toContainText('5866');
+    await expect(page.locator('.ext-card')).toContainText('Nursery');
+  });
+
+  test('add a pager — routed to pagers subsection', async ({ authedPage: _, page }) => {
+    await openTab(page);
+    await fillForm(page, { location: 'Clinic A', name: 'On-call', number: '1234', type: 'pager' });
+
+    await expect(page.locator('#ext-list')).toContainText('Clinic A');
+    await expect(page.locator('#ext-list')).toContainText(/Pagers/i);
+    await expect(page.locator('.ext-card')).toContainText('1234');
+  });
+
+  test('edit an extension — changes persist', async ({ authedPage: _, page }) => {
+    await openTab(page);
+    await fillForm(page, { location: 'Main Hospital', name: 'Old Name', number: '1111', type: 'extension' });
+
+    await page.locator('.ext-card button[data-ext-action="edit"]').first().click();
+    await expect(page.locator('#ext-form-wrap')).not.toHaveClass(/hidden/);
+    await page.fill('#ext-name', 'New Name');
+    await page.fill('#ext-number', '2222');
+    await page.click('#ext-save-btn');
+    await expect(page.locator('#ext-form-wrap')).toHaveClass(/hidden/, { timeout: 5000 });
+
+    await expect(page.locator('.ext-card')).toContainText('New Name');
+    await expect(page.locator('.ext-card')).toContainText('2222');
+    await expect(page.locator('.ext-card')).not.toContainText('Old Name');
+  });
+
+  test('search — filter by location', async ({ authedPage: _, page }) => {
+    await openTab(page);
+    await fillForm(page, { location: 'Main Hospital', name: 'Dept A', number: '1001', type: 'extension' });
+    await fillForm(page, { location: 'Clinic B',     name: 'Dept B', number: '2002', type: 'extension' });
+
+    // Initially both visible
+    await expect(page.locator('.ext-card')).toHaveCount(2);
+
+    // Search by substring of first location
+    await page.fill('#ext-search', 'Main');
+    // Debounce is 200ms; wait for the filter to apply
+    await page.waitForTimeout(400);
+    await expect(page.locator('.ext-card')).toHaveCount(1);
+    await expect(page.locator('.ext-card')).toContainText('Dept A');
+
+    // Clear search — both visible again
+    await page.fill('#ext-search', '');
+    await page.waitForTimeout(400);
+    await expect(page.locator('.ext-card')).toHaveCount(2);
+  });
+
+  test('search — filter by number', async ({ authedPage: _, page }) => {
+    await openTab(page);
+    await fillForm(page, { location: 'Loc', name: 'A', number: '5866', type: 'extension' });
+    await fillForm(page, { location: 'Loc', name: 'B', number: '1234', type: 'pager' });
+
+    await page.fill('#ext-search', '586');
+    await page.waitForTimeout(400);
+    await expect(page.locator('.ext-card')).toHaveCount(1);
+    await expect(page.locator('.ext-card')).toContainText('5866');
+  });
+
+  test('soft-delete — moves to trash, confirm dialog required', async ({ authedPage: _, page }) => {
+    await openTab(page);
+    await fillForm(page, { location: 'Loc', name: 'To delete', number: '9999', type: 'extension' });
+
+    await page.locator('.ext-card button[data-ext-action="delete"]').first().click();
+    // In-app modal — click confirm
+    await page.click('#confirm-modal-ok');
+
+    // Gone from active list
+    await expect(page.locator('#ext-list')).toContainText(/No entries yet/i, { timeout: 5000 });
+
+    // Visible in trash view
+    await page.click('#ext-trash-btn');
+    await expect(page.locator('#ext-mode-banner')).not.toHaveClass(/hidden/);
+    await expect(page.locator('.ext-card')).toContainText('To delete');
+  });
+
+  test('restore from trash — reappears in active', async ({ authedPage: _, page }) => {
+    await openTab(page);
+    await fillForm(page, { location: 'Loc', name: 'Bounceback', number: '5555', type: 'extension' });
+
+    await page.locator('.ext-card button[data-ext-action="delete"]').first().click();
+    await page.click('#confirm-modal-ok');
+
+    await page.click('#ext-trash-btn');
+    await expect(page.locator('.ext-card')).toContainText('Bounceback');
+    await page.locator('.ext-card button[data-ext-action="restore"]').first().click();
+
+    // Back-to-active button
+    await page.click('#ext-back-active');
+    await expect(page.locator('.ext-card')).toContainText('Bounceback');
+  });
+
+  test('purge from trash — permanent, second confirm', async ({ authedPage: _, page }) => {
+    await openTab(page);
+    await fillForm(page, { location: 'Loc', name: 'Gone forever', number: '7777', type: 'extension' });
+
+    await page.locator('.ext-card button[data-ext-action="delete"]').first().click();
+    await page.click('#confirm-modal-ok');
+
+    await page.click('#ext-trash-btn');
+    await expect(page.locator('.ext-card')).toContainText('Gone forever');
+
+    await page.locator('.ext-card button[data-ext-action="purge"]').first().click();
+    await page.click('#confirm-modal-ok');
+
+    // Trash is empty
+    await expect(page.locator('#ext-list')).toContainText(/Trash is empty/i, { timeout: 5000 });
+
+    // Not recoverable — back-to-active view has nothing
+    await page.click('#ext-back-active');
+    await expect(page.locator('#ext-list')).toContainText(/No entries yet/i);
+  });
+
+  test('cancel dialog — keeps item (not deleted)', async ({ authedPage: _, page }) => {
+    await openTab(page);
+    await fillForm(page, { location: 'Loc', name: 'Stays', number: '8888', type: 'extension' });
+
+    // User cancels the modal
+    await page.locator('.ext-card button[data-ext-action="delete"]').first().click();
+    await page.click('#confirm-modal-cancel');
+
+    // Still there
+    await expect(page.locator('.ext-card')).toContainText('Stays');
+  });
+
+  test('cancel button closes form without saving', async ({ authedPage: _, page }) => {
+    await openTab(page);
+    await page.click('#ext-add-btn');
+    await page.fill('#ext-location', 'Should not save');
+    await page.fill('#ext-name', 'x');
+    await page.fill('#ext-number', '0');
+    await page.click('#ext-cancel-btn');
+    await expect(page.locator('#ext-form-wrap')).toHaveClass(/hidden/);
+
+    // Nothing was created
+    await expect(page.locator('#ext-list')).toContainText(/No entries yet/i);
+  });
+
+  test('form validates required fields', async ({ authedPage: _, page }) => {
+    await openTab(page);
+    await page.click('#ext-add-btn');
+    // Click save with empty fields
+    await page.click('#ext-save-btn');
+    await expect(page.locator('#ext-form-status')).toContainText(/required/i);
+    // Form stays open
+    await expect(page.locator('#ext-form-wrap')).not.toHaveClass(/hidden/);
+  });
+});

e2e/tests/hospitalcourse-workflow.spec.js

@@ -0,0 +1,76 @@
+// ============================================================
+// HOSPITAL COURSE — full workflow: fill inputs → generate → verify
+// mocked narrative renders → refine → verify rendered replaces.
+// The older soap-hospital-workflow.spec.js only smokes the save bar;
+// this one drives the actual AI generate path.
+// ============================================================
+
+const { test, expect, E2E_BASE, mockAI } = require('../fixtures');
+
+async function openTab(page) {
+  await page.goto(E2E_BASE + '/');
+  await page.waitForSelector('button.tab-btn', { timeout: 15000 });
+  const vp = page.viewportSize();
+  if (vp && vp.width <= 768) {
+    await page.click('#btn-menu-toggle').catch(() => {});
+  }
+  await page.click('button.tab-btn[data-tab="hospital"]');
+  await page.waitForFunction(() => {
+    const el = document.getElementById('hospital-tab');
+    return el && el.classList.contains('active') && el.innerHTML.trim().length > 100;
+  }, { timeout: 15000 });
+}
+
+test.describe('Hospital Course — generate + refine', () => {
+
+  test('minimum inputs → generate → mocked narrative renders', async ({ authedPage: _, page }) => {
+    await mockAI(page);
+    await openTab(page);
+
+    await page.fill('#hc-age', '9 years');
+    await page.selectOption('#hc-gender', 'Male');
+    await page.fill('#hc-pmh', 'Asthma, mild intermittent');
+    // H&P is the minimum "some note" the route needs so it doesn't reject
+    await page.locator('#hc-hp-content').click();
+    await page.keyboard.type('Admitted for status asthmaticus. Started on continuous albuterol and steroids.');
+
+    const [resp] = await Promise.all([
+      page.waitForResponse('**/api/generate-hospital-course', { timeout: 15000 }),
+      page.click('#hc-generate-btn'),
+    ]);
+    expect(resp.status()).toBe(200);
+    await expect(page.locator('#hc-output')).toBeVisible({ timeout: 10000 });
+    await expect(page.locator('#hc-course-text')).toContainText('MOCK hospital course narrative');
+  });
+
+  test('refine button on generated course fires /api/refine + updates text', async ({ authedPage: _, page }) => {
+    await mockAI(page, {
+      '**/api/refine': { success: true, refined: 'REFINED-HC course — emphasised hospital day 1 events.', model: 'mock-gpt' },
+    });
+    await openTab(page);
+
+    await page.fill('#hc-age', '5 years');
+    await page.locator('#hc-hp-content').click();
+    await page.keyboard.type('Admission for pneumonia, improving on IV cefriaxone.');
+    await page.click('#hc-generate-btn');
+    await expect(page.locator('#hc-course-text')).toContainText('MOCK hospital course', { timeout: 10000 });
+
+    // Refine with an instruction
+    const refineInput = page.locator('#hc-refine-input, [id*="hc-refine"]').first();
+    await refineInput.fill('Tighten the prose.');
+    const [resp] = await Promise.all([
+      page.waitForResponse('**/api/refine'),
+      page.click('#hc-refine-btn'),
+    ]);
+    expect(resp.status()).toBe(200);
+    await expect(page.locator('#hc-course-text')).toContainText('REFINED-HC course', { timeout: 10000 });
+  });
+
+  test('load popover: opens and closes from both triggers', async ({ authedPage: _, page }) => {
+    await openTab(page);
+    await page.click('#btn-hosp-load');
+    await expect(page.locator('#hosp-load-popover')).not.toHaveClass(/hidden/, { timeout: 3000 });
+    await page.locator('#hosp-load-popover .enc-pop-close').click();
+    await expect(page.locator('#hosp-load-popover')).toHaveClass(/hidden/);
+  });
+});

e2e/tests/learning-tab.spec.js

@@ -0,0 +1,57 @@
+// ============================================================
+// LEARNING HUB — search, category pills, feed rendering.
+// Quiz flow is gated by having quiz content; just verify the UI
+// scaffolding works without requiring a specific topic to exist.
+// ============================================================
+
+const { test, expect, E2E_BASE } = require('../fixtures');
+
+async function openTab(page) {
+  await page.goto(E2E_BASE + '/');
+  await page.waitForSelector('button.tab-btn', { timeout: 15000 });
+  const vp = page.viewportSize();
+  if (vp && vp.width <= 768) {
+    await page.click('#btn-menu-toggle').catch(() => {});
+  }
+  await page.click('button.tab-btn[data-tab="learning"]');
+  await page.waitForFunction(() => {
+    const el = document.getElementById('learning-tab');
+    return el && el.classList.contains('active') && el.innerHTML.trim().length > 100;
+  }, { timeout: 15000 });
+}
+
+test.describe('Learning Hub — navigation + search', () => {
+
+  test('search input + categories + feed all render', async ({ authedPage: _, page }) => {
+    await openTab(page);
+    await expect(page.locator('#lh-search')).toBeVisible();
+    await expect(page.locator('#lh-categories')).toBeVisible();
+    await expect(page.locator('#lh-feed')).toBeVisible();
+  });
+
+  test('typing in search filters the feed (even if zero matches)', async ({ authedPage: _, page }) => {
+    await openTab(page);
+    // Wait for feed to render some content or be flagged as empty
+    await expect.poll(async () =>
+      (await page.locator('#lh-feed').innerText()).trim().length,
+    { timeout: 10000 }).toBeGreaterThan(0);
+    const initialHtml = await page.locator('#lh-feed').innerHTML();
+
+    // Type a very specific string that likely won't match any topic
+    await page.fill('#lh-search', 'xyzzy-unlikely-topic-name');
+    // Feed should update — either to empty state or different filtered list
+    await expect.poll(async () =>
+      (await page.locator('#lh-feed').innerHTML()) !== initialHtml,
+    { timeout: 3000 }).toBe(true);
+  });
+
+  test('clicking a category pill (if present) does not crash the UI', async ({ authedPage: _, page }) => {
+    await openTab(page);
+    const pills = page.locator('#lh-categories button, #lh-categories .category-pill');
+    const count = await pills.count();
+    test.skip(count === 0, 'No category pills rendered — nothing to test');
+    await pills.first().click();
+    // Feed must still be visible and have some content after filtering
+    await expect(page.locator('#lh-feed')).toBeVisible();
+  });
+});

e2e/tests/model-selector.spec.js

@@ -0,0 +1,43 @@
+// ============================================================
+// MODEL SELECTOR — each tab has its own <select.tab-model-select>
+// populated by window._buildModelOptions. Verify the dropdowns
+// render across tabs that should have one.
+// ============================================================
+
+const { test, expect, E2E_BASE } = require('../fixtures');
+
+async function openTab(page, name) {
+  await page.goto(E2E_BASE + '/');
+  await page.waitForSelector('button.tab-btn', { timeout: 15000 });
+  const vp = page.viewportSize();
+  if (vp && vp.width <= 768) {
+    await page.click('#btn-menu-toggle').catch(() => {});
+  }
+  await page.click(`button.tab-btn[data-tab="${name}"]`);
+  await page.waitForFunction((t) => {
+    const el = document.getElementById(t + '-tab');
+    return el && el.classList.contains('active') && el.innerHTML.trim().length > 100;
+  }, name, { timeout: 15000 });
+}
+
+test.describe('Per-tab model selector', () => {
+  const tabsWithModelPicker = ['encounter', 'dictation', 'chart', 'soap', 'hospital', 'sickvisit', 'wellvisit'];
+
+  for (const tab of tabsWithModelPicker) {
+    test(`${tab}: model picker renders and has at least one option`, async ({ authedPage: _, page }) => {
+      await openTab(page, tab);
+      // Well Visit has four sub-panels each with their own picker; three of
+      // them are hidden until you switch to that sub-tab, so visibility is
+      // unreliable. Instead: require that the active tab contains at least
+      // one picker AND that at least one picker inside the tab has >0
+      // options populated by window._buildModelOptions.
+      const pickers = page.locator(`#${tab}-tab select.tab-model-select`);
+      await expect.poll(async () => pickers.count(), { timeout: 10000 })
+        .toBeGreaterThan(0);
+      await expect.poll(async () => {
+        return await pickers.evaluateAll(list => list.reduce((max, el) =>
+          Math.max(max, el.options ? el.options.length : 0), 0));
+      }, { timeout: 10000 }).toBeGreaterThan(0);
+    });
+  }
+});

e2e/tests/pe-guide-smoke.spec.js

@@ -0,0 +1,176 @@
+// ============================================================
+// PE GUIDE — smoke tests for the Physical Exam Guide tab
+// ============================================================
+// Exercises the full rendering path: tab load → age group selection →
+// system switching (msk / neuro / resp / cv) → expected per-system
+// cards (scales, sounds library for resp, APTM image + innocent
+// murmur panel for cv) → step toggle interaction.
+//
+// Uses the shared fixture so any uncaught JS error or console.error
+// fails the test automatically (catches a repeat of the SSO-bug
+// class on this page).
+// ============================================================
+
+const { test, expect, E2E_BASE } = require('../fixtures');
+
+async function openPEGuide(page) {
+  await page.goto(E2E_BASE + '/');
+  await page.waitForSelector('button.tab-btn', { timeout: 15000 });
+  // On mobile the sidebar collapses behind a hamburger. Open it so the
+  // tab button is actually in the viewport before we click it.
+  const vp = page.viewportSize();
+  if (vp && vp.width <= 768) {
+    await page.click('#btn-menu-toggle').catch(() => {});
+  }
+  await page.click('button.tab-btn[data-tab="peguide"]');
+  await page.waitForFunction(() => {
+    const el = document.getElementById('peguide-tab');
+    return el && el.classList.contains('active') && el.innerHTML.trim().length > 100;
+  }, { timeout: 15000 });
+}
+
+async function selectAge(page, value) {
+  await page.selectOption('#pe-age-group', value);
+  // Wait for components to render (at least one card with a step)
+  await page.waitForFunction(() => {
+    return document.querySelectorAll('#pe-content .pe-step').length > 0;
+  }, { timeout: 5000 });
+}
+
+async function switchSystem(page, sys) {
+  await page.click('button.wv-subtab-btn[data-pesystem="' + sys + '"]');
+  // Either steps are there, or the resp/cv cards are (which have no .pe-step)
+  await page.waitForFunction((s) => {
+    const content = document.getElementById('pe-content');
+    if (!content) return false;
+    if (s === 'resp') return content.innerHTML.includes('Respiratory sounds library');
+    if (s === 'cv')   return content.innerHTML.includes('Auscultation landmarks');
+    return content.querySelectorAll('.pe-step').length > 0;
+  }, sys, { timeout: 5000 });
+}
+
+test.describe('PE Guide — smoke', () => {
+
+  test('tab loads with empty-state message before age group selected', async ({ authedPage: _, page }) => {
+    await openPEGuide(page);
+    await expect(page.locator('#pe-content')).toContainText(/Select an age group/i);
+  });
+
+  test('MSK (default) renders with overview and grading scales for adolescent', async ({ authedPage: _, page }) => {
+    await openPEGuide(page);
+    await selectAge(page, 'adolescent');
+    await expect(page.locator('#pe-content')).toContainText('Musculoskeletal');
+    await expect(page.locator('#pe-content')).toContainText(/Scoliometer|Beighton/);
+    // At least one step card present
+    await expect(page.locator('.pe-step').first()).toBeVisible();
+  });
+
+  test('switches to Neuro and shows MRC scale + teaching pearl', async ({ authedPage: _, page }) => {
+    await openPEGuide(page);
+    await selectAge(page, 'adolescent');
+    await switchSystem(page, 'neuro');
+    await expect(page.locator('#pe-content')).toContainText('Neurologic');
+    await expect(page.locator('#pe-content')).toContainText(/MRC strength/i);
+    // Teaching pearl rendered (amber block)
+    await expect(page.locator('#pe-content')).toContainText(/Pronator drift/i);
+  });
+
+  test('Respiratory system shows the 7-sound library, all with real audio players', async ({ authedPage: _, page }) => {
+    await openPEGuide(page);
+    await selectAge(page, 'adolescent');
+    await switchSystem(page, 'resp');
+    await expect(page.locator('#pe-content')).toContainText('Respiratory sounds library');
+    // All 7 sounds must render as native <audio controls> elements (pause/seek available)
+    const audioPlayers = page.locator('#pe-content .pe-audio');
+    await expect(audioPlayers).toHaveCount(7);
+    // Every one has a src attribute pointing at /audio/respiratory/*.ogg (no synth fallbacks)
+    const srcs = await audioPlayers.evaluateAll(els => els.map(e => e.getAttribute('src')));
+    for (const src of srcs) {
+      expect(src, 'respiratory audio src').toMatch(/^\/audio\/respiratory\/.+\.ogg$/);
+    }
+    // Grunting entry must NOT appear in the SOUND LIBRARY (removed — no openly-licensed
+    // recording). The phrase "expiratory grunting" still appears in clinical teaching
+    // steps, which is fine; just assert the sounds library has no grunting card.
+    const libraryText = await page
+      .locator('#pe-content .card')
+      .filter({ hasText: /Respiratory sounds library/i })
+      .innerText();
+    expect(libraryText).not.toMatch(/Grunting/i);
+    // RR scale renders
+    await expect(page.locator('#pe-content')).toContainText(/Respiratory rate/i);
+    // Observation-first inspection card present
+    await expect(page.locator('#pe-content')).toContainText(/Inspection/i);
+  });
+
+  test('Cardiovascular system shows APTM image + all 5 landmarks + innocent murmur panel', async ({ authedPage: _, page }) => {
+    await openPEGuide(page);
+    await selectAge(page, 'adolescent');
+    await switchSystem(page, 'cv');
+    // APTM diagram image loaded
+    const aptmImg = page.locator('img[src*="aptm.png"]');
+    await expect(aptmImg).toBeVisible();
+    // Wait for it to actually have painted pixels (naturalWidth > 0 = fetched successfully)
+    await expect.poll(async () => {
+      return await aptmImg.evaluate(el => el.naturalWidth);
+    }, { timeout: 10000 }).toBeGreaterThan(0);
+    // All 5 landmark letters in the legend
+    for (const letter of ['A', 'P', 'E', 'T', 'M']) {
+      await expect(page.locator('#pe-content')).toContainText(letter);
+    }
+    // Innocent murmur panel
+    await expect(page.locator('#pe-content')).toContainText(/Innocent murmurs/i);
+    await expect(page.locator('#pe-content')).toContainText(/Still.s/i);
+    await expect(page.locator('#pe-content')).toContainText(/Venous hum/i);
+    // 7 "S" criteria footer
+    await expect(page.locator('#pe-content')).toContainText(/7.*S/);
+  });
+
+  test('each age group has resp + cv data (no "no data" empty state)', async ({ authedPage: _, page }) => {
+    await openPEGuide(page);
+    const ages = ['newborn', 'infant', 'toddler', 'preschool', 'school', 'adolescent'];
+    for (const age of ages) {
+      await selectAge(page, age);
+      for (const sys of ['resp', 'cv']) {
+        await switchSystem(page, sys);
+        // Must NOT show the "no data" placeholder
+        const content = await page.locator('#pe-content').innerText();
+        expect(content, `${age}/${sys} should have data`).not.toMatch(/No data for this combination/i);
+        // Should have at least one component card with at least one step
+        const stepCount = await page.locator('.pe-step').count();
+        expect(stepCount, `${age}/${sys} should have at least 1 step`).toBeGreaterThan(0);
+      }
+    }
+  });
+
+  test('step toggle cycles Normal → Abnormal → Skip and updates visual state', async ({ authedPage: _, page }) => {
+    await openPEGuide(page);
+    await selectAge(page, 'adolescent');
+    await switchSystem(page, 'neuro');
+    const firstStep = page.locator('.pe-step').first();
+    // Click Normal (✓) button
+    await firstStep.locator('button[data-pe-status="normal"]').click();
+    // Background should turn green (#ecfdf5)
+    await expect.poll(async () => {
+      return await firstStep.evaluate(el => el.style.background);
+    }).toMatch(/rgb\(236, 253, 245\)|#ecfdf5/);
+    // Click Abnormal (✗) — note field should appear
+    await firstStep.locator('button[data-pe-status="abnormal"]').click();
+    await expect(firstStep.locator('.pe-note')).toBeVisible();
+    // Click Skip (—) — note field hides
+    await firstStep.locator('button[data-pe-status="skip"]').click();
+    await expect(firstStep.locator('.pe-note')).toBeHidden();
+  });
+
+  test('grading scales card is collapsible and expands on click', async ({ authedPage: _, page }) => {
+    await openPEGuide(page);
+    await selectAge(page, 'adolescent');
+    await switchSystem(page, 'neuro');
+    // <details> element with "Grading scales" summary
+    const details = page.locator('details').filter({ hasText: /Grading scales/ });
+    await expect(details).toBeVisible();
+    // Open it
+    await details.locator('summary').click();
+    // Should now see at least one scale title
+    await expect(details).toContainText(/MRC strength/);
+  });
+});

e2e/tests/session-persistence.spec.js

@@ -0,0 +1,87 @@
+// ============================================================
+// SESSION PERSISTENCE — full logout → login → still on the same
+// tab + same sub-pill.
+//
+// The test does a programmatic logout (clear the ped_auth cookie,
+// same effect server-side as clicking Logout) followed by a fresh
+// programmatic login. This exercises the same localStorage
+// persistence path a real logout/login would.
+//
+// (Historically this was a workaround for the Turnstile challenge on
+// the login form, which could not be completed in the e2e container.
+// Login is no longer gated, but driving it programmatically keeps
+// the test focused on persistence rather than form mechanics.)
+// ============================================================
+
+const { test, expect, E2E_BASE, loginAs } = require('../fixtures');
+
+async function openDesktopTab(page, name) {
+  const vp = page.viewportSize();
+  if (vp && vp.width <= 768) {
+    await page.click('#btn-menu-toggle').catch(() => {});
+  }
+  await page.click(`button.tab-btn[data-tab="${name}"]`);
+  await page.waitForFunction((t) => {
+    const el = document.getElementById(t + '-tab');
+    return el && el.classList.contains('active') && el.innerHTML.trim().length > 100;
+  }, name, { timeout: 15000 });
+}
+
+async function logoutClearsCookie(context) {
+  // Remove the ped_auth cookie — identical server-side to hitting /logout.
+  const cookies = await context.cookies();
+  const keep = cookies.filter(c => c.name !== 'ped_auth');
+  await context.clearCookies();
+  if (keep.length) await context.addCookies(keep);
+}
+
+test.describe('Logout → login restores last tab + sub-pill', () => {
+
+  test('tab choice + calc pill survive a full logout/login cycle', async ({ context, request, page }) => {
+    await loginAs(context, request);
+    await page.goto(E2E_BASE + '/');
+    await page.waitForSelector('button.tab-btn', { timeout: 15000 });
+    await openDesktopTab(page, 'calculators');
+    await page.click('button.calc-nav-pill[data-calc="bili"]');
+    await expect(page.locator('button.calc-nav-pill[data-calc="bili"].active')).toBeVisible();
+
+    // Simulate logout (clear session cookie)
+    await logoutClearsCookie(context);
+    // Visiting the app with no cookie lands on the auth screen
+    await page.goto(E2E_BASE + '/');
+    await expect(page.locator('#auth-screen')).toBeVisible({ timeout: 10000 });
+
+    // Log back in (fresh cookie) and revisit the app
+    await loginAs(context, request);
+    await page.goto(E2E_BASE + '/');
+    await page.waitForSelector('button.tab-btn', { timeout: 15000 });
+
+    // Restore must put us back on Calculators / Bilirubin pill
+    await expect(page.locator('#calculators-tab.active')).toHaveCount(1, { timeout: 10000 });
+    await expect(page.locator('button.calc-nav-pill[data-calc="bili"].active')).toBeVisible({ timeout: 10000 });
+    await expect(page.locator('#calc-bili')).not.toHaveClass(/hidden/);
+  });
+
+  test('bedside sub-pill survives logout/login', async ({ context, request, page }) => {
+    await loginAs(context, request);
+    await page.goto(E2E_BASE + '/');
+    await page.waitForSelector('button.tab-btn', { timeout: 15000 });
+    await openDesktopTab(page, 'bedside');
+    await page.click('button.calc-pill[data-em="sepsis"]');
+    await expect(page.locator('button.calc-pill[data-em="sepsis"].active')).toBeVisible();
+
+    await logoutClearsCookie(context);
+    await page.goto(E2E_BASE + '/');
+    await expect(page.locator('#auth-screen')).toBeVisible({ timeout: 10000 });
+
+    await loginAs(context, request);
+    await page.goto(E2E_BASE + '/');
+    await page.waitForSelector('button.tab-btn', { timeout: 15000 });
+
+    await expect(page.locator('#bedside-tab.active')).toHaveCount(1, { timeout: 10000 });
+    await expect(page.locator('button.calc-pill[data-em="sepsis"].active')).toBeVisible({ timeout: 10000 });
+    await expect.poll(async () =>
+      await page.locator('#em-sepsis').evaluate(el => el.style.display),
+    { timeout: 5000 }).not.toBe('none');
+  });
+});

e2e/tests/settings-faq-dictation.spec.js

@@ -0,0 +1,115 @@
+// ============================================================
+// SETTINGS + FAQ + DICTATION — detailed UI exercises that
+// don't depend on real AI / recording permissions.
+// ============================================================
+
+const { test, expect, E2E_BASE, mockAI } = require('../fixtures');
+
+async function openTab(page, name) {
+  await page.goto(E2E_BASE + '/');
+  await page.waitForSelector('button.tab-btn', { timeout: 15000 });
+  const vp = page.viewportSize();
+  if (vp && vp.width <= 768) {
+    await page.click('#btn-menu-toggle').catch(() => {});
+  }
+  await page.click(`button.tab-btn[data-tab="${name}"]`);
+  await page.waitForFunction((t) => {
+    const el = document.getElementById(t + '-tab');
+    return el && el.classList.contains('active') && el.innerHTML.trim().length > 100;
+  }, name, { timeout: 15000 });
+}
+
+test.describe('Settings — voice, password, nextcloud sections render', () => {
+
+  test('voice-preferences inputs + save button exist', async ({ authedPage: _, page }) => {
+    await openTab(page, 'settings');
+    // STT and TTS dropdowns populate; save button exists
+    await expect(page.locator('#stt-model-select')).toBeVisible();
+    await expect(page.locator('#tts-voice-select')).toBeVisible();
+    await expect(page.locator('#btn-save-voice-prefs')).toBeVisible();
+  });
+
+  test('change-password form: all three fields + submit button present', async ({ authedPage: _, page }) => {
+    await openTab(page, 'settings');
+    await expect(page.locator('#pw-current')).toBeVisible();
+    await expect(page.locator('#pw-new')).toBeVisible();
+    await expect(page.locator('#pw-confirm')).toBeVisible();
+    await expect(page.locator('#btn-change-password')).toBeVisible();
+  });
+
+  test('2FA setup panel has QR container + verify input', async ({ authedPage: _, page }) => {
+    await openTab(page, 'settings');
+    // At least one of the 2FA buttons should be present
+    const setupCount = await page.locator('#btn-setup-2fa').count();
+    const disableCount = await page.locator('#btn-disable-2fa').count();
+    expect(setupCount + disableCount).toBeGreaterThan(0);
+  });
+
+  test('Nextcloud section: URL/user/pass fields render', async ({ authedPage: _, page }) => {
+    await openTab(page, 'settings');
+    await expect(page.locator('#nc-url')).toBeVisible();
+    await expect(page.locator('#nc-user')).toBeVisible();
+    await expect(page.locator('#nc-pass')).toBeVisible();
+  });
+});
+
+test.describe('FAQ — questions expand + collapse on click', () => {
+
+  test('clicking a FAQ question reveals its answer panel', async ({ authedPage: _, page }) => {
+    await openTab(page, 'faq');
+    const questions = page.locator('.faq-question');
+    const count = await questions.count();
+    expect(count).toBeGreaterThan(0);
+    const first = questions.first();
+    await first.click();
+    // The corresponding answer should become visible — either via class toggle or
+    // inline style. Grab the sibling / next matching answer element and check.
+    const ariaControls = await first.getAttribute('aria-controls');
+    if (ariaControls) {
+      await expect(page.locator('#' + ariaControls)).toBeVisible();
+    } else {
+      // Fallback: any .faq-answer becomes visible
+      await expect(page.locator('.faq-answer').first()).toBeVisible();
+    }
+  });
+});
+
+test.describe('Dictation — UI loads, transcript editable, clear works', () => {
+
+  test('age/gender/setting inputs + generate + clear all render', async ({ authedPage: _, page }) => {
+    await mockAI(page);
+    await openTab(page, 'dictation');
+    await expect(page.locator('#dict-age')).toBeVisible();
+    await expect(page.locator('#dict-gender')).toBeVisible();
+    await expect(page.locator('#dict-setting')).toBeVisible();
+    await expect(page.locator('#dict-transcript')).toBeVisible();
+    await expect(page.locator('#dict-generate-btn')).toBeVisible();
+  });
+
+  test('typing into transcript + clear empties it', async ({ authedPage: _, page }) => {
+    await mockAI(page);
+    await openTab(page, 'dictation');
+    await page.locator('#dict-transcript').click();
+    await page.keyboard.type('Chief complaint: sore throat.');
+    await expect(page.locator('#dict-transcript')).toContainText('sore throat');
+    await page.click('#dict-clear');
+    const text = await page.locator('#dict-transcript').innerText();
+    expect(text.trim()).toBe('');
+  });
+
+  test('generate with short transcript → mocked HPI renders', async ({ authedPage: _, page }) => {
+    await mockAI(page);
+    await openTab(page, 'dictation');
+    await page.fill('#dict-age', '6 years');
+    await page.locator('#dict-transcript').click();
+    await page.keyboard.type('Patient with cough and congestion for 2 days.');
+    // Default output type is HPI — should call /api/generate-hpi-dictation
+    const [resp] = await Promise.all([
+      page.waitForResponse('**/api/generate-hpi-dictation'),
+      page.click('#dict-generate-btn'),
+    ]);
+    expect(resp.status()).toBe(200);
+    await expect(page.locator('#dict-output')).toBeVisible();
+    await expect(page.locator('#dict-hpi-text')).toContainText('MOCK HPI from dictation');
+  });
+});

e2e/tests/sickvisit-workflow.spec.js

@@ -0,0 +1,89 @@
+// ============================================================
+// SICK VISIT — detailed workflow tests
+// Fills the form, generates a mocked note, verifies output render
+// and the refine + clear flows.
+// ============================================================
+
+const { test, expect, E2E_BASE, mockAI } = require('../fixtures');
+
+async function openTab(page) {
+  await page.goto(E2E_BASE + '/');
+  await page.waitForSelector('button.tab-btn', { timeout: 15000 });
+  const vp = page.viewportSize();
+  if (vp && vp.width <= 768) {
+    await page.click('#btn-menu-toggle').catch(() => {});
+  }
+  await page.click('button.tab-btn[data-tab="sickvisit"]');
+  await page.waitForFunction(() => {
+    const el = document.getElementById('sickvisit-tab');
+    return el && el.classList.contains('active') && el.innerHTML.trim().length > 100;
+  }, { timeout: 15000 });
+}
+
+test.describe('Sick Visit — generate workflow', () => {
+
+  test('fill demographics + CC + transcript → mocked note renders', async ({ authedPage: _, page }) => {
+    await mockAI(page);
+    await openTab(page);
+
+    await page.fill('#sick-age', '6 years');
+    await page.selectOption('#sick-gender', 'Male');
+    await page.fill('#sick-cc', 'Sore throat x 3 days');
+    await page.locator('#sick-transcript').click();
+    await page.keyboard.type('6yo with 3 days sore throat, fever, fatigue. No rash.');
+
+    const [resp] = await Promise.all([
+      page.waitForResponse('**/api/sick-visit/note', { timeout: 15000 }),
+      page.click('#btn-sick-generate'),
+    ]);
+    expect(resp.status()).toBe(200);
+    await expect(page.locator('#sick-note-output')).toBeVisible({ timeout: 10000 });
+    await expect(page.locator('#sick-note-text')).toContainText('MOCK sick visit note');
+  });
+
+  test('refine button fires /api/refine and updates the rendered note', async ({ authedPage: _, page }) => {
+    await mockAI(page, {
+      '**/api/refine': { success: true, refined: 'REFINED sick-visit note — added return precautions.', model: 'mock-gpt' },
+    });
+    await openTab(page);
+    await page.fill('#sick-age', '4 years');
+    await page.fill('#sick-cc', 'Cough');
+    await page.locator('#sick-transcript').click();
+    await page.keyboard.type('Cough x 2 days, no fever, hydrating OK.');
+    await page.click('#btn-sick-generate');
+    await expect(page.locator('#sick-note-text')).toContainText('MOCK sick visit note', { timeout: 10000 });
+
+    await page.fill('#sick-refine-input', 'Add return precautions.');
+    const [resp] = await Promise.all([
+      page.waitForResponse('**/api/refine'),
+      page.click('#sick-refine-btn'),
+    ]);
+    expect(resp.status()).toBe(200);
+    await expect(page.locator('#sick-note-text')).toContainText('REFINED sick-visit note', { timeout: 10000 });
+  });
+
+  test('load popover opens and closes', async ({ authedPage: _, page }) => {
+    await openTab(page);
+    await page.click('#btn-sick-load');
+    await expect(page.locator('#sick-load-popover')).not.toHaveClass(/hidden/, { timeout: 3000 });
+    // Close by clicking the close button inside the popover
+    await page.locator('#sick-load-popover .enc-pop-close').click();
+    await expect(page.locator('#sick-load-popover')).toHaveClass(/hidden/);
+  });
+
+  test('New button clears demographics + transcript for a new patient', async ({ authedPage: _, page }) => {
+    await mockAI(page);
+    await openTab(page);
+    await page.fill('#sick-age', '5 years');
+    await page.selectOption('#sick-gender', 'Male');
+    await page.locator('#sick-transcript').click();
+    await page.keyboard.type('Temporary transcript');
+    await page.click('#btn-sick-new');
+    // clearTab() resets demographics + transcript (chief complaint is left so a
+    // rapid "next patient with same complaint" doesn't have to retype it).
+    await expect(page.locator('#sick-age')).toHaveValue('');
+    await expect(page.locator('#sick-gender')).toHaveValue('');
+    const txt = await page.locator('#sick-transcript').innerText();
+    expect(txt.trim()).toBe('');
+  });
+});

e2e/tests/soap-hospital-workflow.spec.js

@@ -0,0 +1,75 @@
+// ============================================================
+// SOAP + HOSPITAL COURSE — detailed workflow for the two notes
+// tabs that previously only had smoke coverage.
+// ============================================================
+
+const { test, expect, E2E_BASE, mockAI } = require('../fixtures');
+
+async function openTab(page, name) {
+  await page.goto(E2E_BASE + '/');
+  await page.waitForSelector('button.tab-btn', { timeout: 15000 });
+  const vp = page.viewportSize();
+  if (vp && vp.width <= 768) {
+    await page.click('#btn-menu-toggle').catch(() => {});
+  }
+  await page.click(`button.tab-btn[data-tab="${name}"]`);
+  await page.waitForFunction((t) => {
+    const el = document.getElementById(t + '-tab');
+    return el && el.classList.contains('active') && el.innerHTML.trim().length > 100;
+  }, name, { timeout: 15000 });
+}
+
+test.describe('SOAP Note — generate + refine', () => {
+
+  test('fill transcript + generate → mocked SOAP renders', async ({ authedPage: _, page }) => {
+    await mockAI(page);
+    await openTab(page, 'soap');
+
+    await page.fill('#soap-age', '5 years');
+    await page.selectOption('#soap-gender', 'Male');
+    await page.locator('#soap-transcript').click();
+    await page.keyboard.type('Patient presents with 3 days of fever, cough, and runny nose.');
+
+    const [resp] = await Promise.all([
+      page.waitForResponse('**/api/generate-soap', { timeout: 15000 }),
+      page.click('#soap-generate-btn'),
+    ]);
+    expect(resp.status()).toBe(200);
+    await expect(page.locator('#soap-output')).toBeVisible({ timeout: 10000 });
+    await expect(page.locator('#soap-text')).toContainText('MOCK SOAP NOTE');
+  });
+
+  test('clear transcript button empties the contenteditable', async ({ authedPage: _, page }) => {
+    await mockAI(page);
+    await openTab(page, 'soap');
+    await page.locator('#soap-transcript').click();
+    await page.keyboard.type('some transcript');
+    await expect(page.locator('#soap-transcript')).toContainText('some transcript');
+    await page.click('#soap-clear');
+    const text = await page.locator('#soap-transcript').innerText();
+    expect(text.trim()).toBe('');
+  });
+
+  test('load popover opens and closes', async ({ authedPage: _, page }) => {
+    await openTab(page, 'soap');
+    await page.click('#btn-soap-load').catch(() => page.click('button[id*="soap-load"]'));
+    await expect(page.locator('#soap-load-popover')).not.toHaveClass(/hidden/, { timeout: 3000 });
+  });
+});
+
+test.describe('Hospital Course — tab loads with save/load bar', () => {
+
+  test('tab renders with label input + save/load/new buttons', async ({ authedPage: _, page }) => {
+    await openTab(page, 'hospital');
+    await expect(page.locator('#hosp-label')).toBeVisible();
+    await expect(page.locator('#hosp-save-bar')).toBeVisible();
+  });
+
+  test('load popover opens and closes', async ({ authedPage: _, page }) => {
+    await openTab(page, 'hospital');
+    // Any button with id that looks like load
+    const loadBtn = page.locator('button[id*="hosp-load"], button[id*="btn-hosp-load"]').first();
+    await loadBtn.click();
+    await expect(page.locator('#hosp-load-popover')).not.toHaveClass(/hidden/, { timeout: 3000 });
+  });
+});

e2e/tests/ui-state-persistence.spec.js

@@ -0,0 +1,89 @@
+// ============================================================
+// UI STATE PERSISTENCE — sub-pill / sub-tab choices survive a
+// full page reload (simulating sign-out / sign-in or browser
+// restart). Guards against regressions in the ui-state.js +
+// localStorage wiring.
+// ============================================================
+
+const { test, expect, E2E_BASE } = require('../fixtures');
+
+async function gotoHome(page) {
+  await page.goto(E2E_BASE + '/');
+  await page.waitForSelector('button.tab-btn', { timeout: 15000 });
+}
+
+async function openDesktopTab(page, name) {
+  const vp = page.viewportSize();
+  if (vp && vp.width <= 768) {
+    await page.click('#btn-menu-toggle').catch(() => {});
+  }
+  await page.click(`button.tab-btn[data-tab="${name}"]`);
+  await page.waitForFunction((t) => {
+    const el = document.getElementById(t + '-tab');
+    return el && el.classList.contains('active') && el.innerHTML.trim().length > 100;
+  }, name, { timeout: 15000 });
+}
+
+test.describe('UI state survives page reload', () => {
+
+  test('ped_last_tab → user lands on last-active tab after reload', async ({ authedPage: _, page }) => {
+    await gotoHome(page);
+    await openDesktopTab(page, 'calculators');
+    // Reload (keeps cookie, clears _componentCache + in-memory DOM state)
+    await page.reload();
+    await page.waitForSelector('button.tab-btn', { timeout: 15000 });
+    await expect.poll(async () => {
+      return await page.locator('#calculators-tab.active').count();
+    }, { timeout: 5000 }).toBe(1);
+  });
+
+  test('calculators nav pill persists across reload', async ({ authedPage: _, page }) => {
+    await gotoHome(page);
+    await openDesktopTab(page, 'calculators');
+    // Switch to GCS
+    await page.click('button.calc-nav-pill[data-calc="gcs"]');
+    await expect(page.locator('button.calc-nav-pill[data-calc="gcs"].active')).toBeVisible();
+    await page.reload();
+    await page.waitForSelector('button.calc-nav-pill[data-calc="gcs"]', { timeout: 15000 });
+    // Same pill should be active after reload
+    await expect(page.locator('button.calc-nav-pill[data-calc="gcs"].active')).toBeVisible({ timeout: 5000 });
+    // And the corresponding panel should be un-hidden
+    await expect(page.locator('#calc-gcs')).not.toHaveClass(/hidden/);
+  });
+
+  test('bedside sub-pill persists across reload', async ({ authedPage: _, page }) => {
+    await gotoHome(page);
+    await openDesktopTab(page, 'bedside');
+    await page.click('button.calc-pill[data-em="anaphylaxis"]');
+    await expect(page.locator('button.calc-pill[data-em="anaphylaxis"].active')).toBeVisible();
+    await page.reload();
+    await page.waitForSelector('button.calc-pill[data-em="anaphylaxis"]', { timeout: 15000 });
+    await expect(page.locator('button.calc-pill[data-em="anaphylaxis"].active')).toBeVisible({ timeout: 5000 });
+    // The anaphylaxis em-section should be the visible one
+    await expect.poll(async () => {
+      return await page.locator('#em-anaphylaxis').evaluate(el => el.style.display);
+    }, { timeout: 5000 }).not.toBe('none');
+  });
+
+  test('well-visit sub-tab persists across reload', async ({ authedPage: _, page }) => {
+    await gotoHome(page);
+    await openDesktopTab(page, 'wellvisit');
+    await page.click('button.wv-subtab-btn[data-subtab="milestones"]');
+    await expect(page.locator('#wv-panel-milestones')).not.toHaveClass(/hidden/);
+    await page.reload();
+    await page.waitForSelector('button.wv-subtab-btn[data-subtab="milestones"]', { timeout: 15000 });
+    await expect(page.locator('#wv-panel-milestones')).not.toHaveClass(/hidden/, { timeout: 5000 });
+  });
+
+  test('PE guide age group + system persist across reload', async ({ authedPage: _, page }) => {
+    await gotoHome(page);
+    await openDesktopTab(page, 'peguide');
+    await page.selectOption('#pe-age-group', 'adolescent');
+    await page.click('button[data-pesystem="neuro"]');
+    await expect(page.locator('button[data-pesystem="neuro"].active')).toBeVisible();
+    await page.reload();
+    await page.waitForSelector('#pe-age-group', { timeout: 15000 });
+    await expect(page.locator('#pe-age-group')).toHaveValue('adolescent', { timeout: 5000 });
+    await expect(page.locator('button[data-pesystem="neuro"].active')).toBeVisible({ timeout: 5000 });
+  });
+});

e2e/tests/vaxschedule-content.spec.js

@@ -0,0 +1,52 @@
+// ============================================================
+// VAX SCHEDULE + CATCH-UP — content renders into the stub panels.
+// These tabs have no inputs; they just display the AAP/ACIP tables.
+// Verify: real content (not just "Loading") + at least a few
+// recognisable vaccine abbreviations show up.
+// ============================================================
+
+const { test, expect, E2E_BASE } = require('../fixtures');
+
+async function openTab(page, name) {
+  await page.goto(E2E_BASE + '/');
+  await page.waitForSelector('button.tab-btn', { timeout: 15000 });
+  const vp = page.viewportSize();
+  if (vp && vp.width <= 768) {
+    await page.click('#btn-menu-toggle').catch(() => {});
+  }
+  await page.click(`button.tab-btn[data-tab="${name}"]`);
+  await page.waitForFunction((t) => {
+    const el = document.getElementById(t + '-tab');
+    return el && el.classList.contains('active') && el.innerHTML.trim().length > 100;
+  }, name, { timeout: 15000 });
+}
+
+test.describe('Vaccine schedules — content loaded', () => {
+
+  test('vaxschedule: panel populates beyond the loading placeholder', async ({ authedPage: _, page }) => {
+    await openTab(page, 'vaxschedule');
+    await expect.poll(async () => {
+      const text = await page.locator('#wv-panel-schedule').innerText();
+      return text;
+    }, { timeout: 10000 }).not.toMatch(/^Loading schedule/i);
+
+    // Must mention at least a couple of the core childhood vaccines
+    const text = await page.locator('#wv-panel-schedule').innerText();
+    expect(text).toMatch(/HepB|Hep B/i);
+    expect(text).toMatch(/MMR/i);
+    expect(text).toMatch(/DTaP|Tdap/i);
+  });
+
+  test('catchup: panel populates with the catch-up schedule', async ({ authedPage: _, page }) => {
+    await openTab(page, 'catchup');
+    await expect.poll(async () => {
+      const text = await page.locator('#wv-panel-catchup').innerText();
+      return text;
+    }, { timeout: 10000 }).not.toMatch(/^Loading catch-up/i);
+
+    const text = await page.locator('#wv-panel-catchup').innerText();
+    expect(text.trim().length).toBeGreaterThan(200);
+    // Should mention interval guidance in some form
+    expect(text).toMatch(/interval|month|week/i);
+  });
+});

e2e/tests/wellvisit-workflow.spec.js

@@ -0,0 +1,133 @@
+// ============================================================
+// WELL VISIT — detailed workflow across the 4 sub-tabs:
+//   1. By Visit Age (reference display)
+//   2. Milestones — generate narrative from toggles
+//   3. SSHADESS — generate psychosocial assessment
+//   4. Visit Note — end-to-end generate a well-child note
+// All AI calls are mocked.
+// ============================================================
+
+const { test, expect, E2E_BASE, mockAI } = require('../fixtures');
+
+async function openTab(page) {
+  await page.goto(E2E_BASE + '/');
+  await page.waitForSelector('button.tab-btn', { timeout: 15000 });
+  const vp = page.viewportSize();
+  if (vp && vp.width <= 768) {
+    await page.click('#btn-menu-toggle').catch(() => {});
+  }
+  await page.click('button.tab-btn[data-tab="wellvisit"]');
+  await page.waitForFunction(() => {
+    const el = document.getElementById('wellvisit-tab');
+    return el && el.classList.contains('active') && el.innerHTML.trim().length > 100;
+  }, { timeout: 15000 });
+}
+
+async function openSubtab(page, key) {
+  await page.click(`button.wv-subtab-btn[data-subtab="${key}"]`);
+  await page.waitForFunction(
+    (k) => !document.getElementById('wv-panel-' + k).classList.contains('hidden'),
+    key,
+    { timeout: 5000 }
+  );
+}
+
+test.describe('Well Visit — detailed workflows', () => {
+
+  test('By Visit Age — selecting a visit age renders content detail', async ({ authedPage: _, page }) => {
+    await openTab(page);
+    await openSubtab(page, 'byvisit');
+    // Dropdown must exist and be non-empty
+    const options = await page.locator('#wv-visit-select option').count();
+    expect(options).toBeGreaterThan(1);
+    // Pick the 2nd option (skip placeholder). Detail container should populate.
+    await page.selectOption('#wv-visit-select', { index: 1 });
+    await expect.poll(async () =>
+      (await page.locator('#wv-visit-detail').innerText()).trim().length,
+    { timeout: 5000 }).toBeGreaterThan(0);
+  });
+
+  test('Milestones — toggle "All yes" then generate → narrative renders', async ({ authedPage: _, page }) => {
+    await mockAI(page);
+    await openTab(page);
+    await openSubtab(page, 'milestones');
+
+    await page.fill('#ms-age', '12 months');
+    await page.selectOption('#ms-gender', 'Male');
+    // Age group picker — pick the first real option if there is a placeholder
+    const optCount = await page.locator('#ms-age-group option').count();
+    if (optCount > 1) await page.selectOption('#ms-age-group', { index: 1 });
+
+    // Mark everything achieved (the "All yes" action), wait for checklist to have at least one item
+    await page.waitForFunction(() => document.querySelectorAll('#milestone-checklist .milestone-row').length > 0, null, { timeout: 5000 }).catch(() => {});
+    await page.click('#ms-all-yes').catch(() => {});
+
+    const [resp] = await Promise.all([
+      page.waitForResponse('**/api/generate-milestone-narrative'),
+      page.click('#ms-generate-btn'),
+    ]);
+    expect(resp.status()).toBe(200);
+    await expect(page.locator('#ms-narrative-text')).toContainText('MOCK developmental narrative', { timeout: 10000 });
+  });
+
+  test('SSHADESS — domain list renders + generate fires /api/well-visit/shadess', async ({ authedPage: _, page }) => {
+    await mockAI(page);
+    await openTab(page);
+    // The SSHADESS subtab button is display:none until the user picks a 12+
+    // visit in byvisit. Iterate the visit dropdown options and pick one whose
+    // value looks like a 12+ year visit.
+    await openSubtab(page, 'byvisit');
+    await page.waitForFunction(() => document.querySelectorAll('#wv-visit-select option').length > 2, null, { timeout: 5000 });
+    const adolescentOpt = await page.locator('#wv-visit-select option').evaluateAll((opts) => {
+      const match = opts.find(o => /1[2-8].*(year|yr)/i.test(o.textContent || '') || /1[2-8].*year/i.test(o.value || ''));
+      return match ? match.value : null;
+    });
+    if (!adolescentOpt) test.skip(true, 'No 12+ visit option in dropdown — cannot expose SSHADESS subtab');
+    await page.selectOption('#wv-visit-select', adolescentOpt);
+    // Now the shadess subtab button becomes visible
+    await expect(page.locator('button.wv-subtab-btn[data-subtab="shadess"]')).toBeVisible({ timeout: 5000 });
+    await openSubtab(page, 'shadess');
+
+    // Age 14 — should surface SSHADESS (12+ only)
+    await page.fill('#shadess-age', '14 years');
+    await page.selectOption('#shadess-gender', 'Female');
+
+    // Wait for domains to render — JS populates after age/gender are set
+    await expect.poll(async () =>
+      (await page.locator('#shadess-domains').innerText()).trim().length,
+    { timeout: 5000 }).toBeGreaterThan(0);
+
+    // Generate refuses with a toast if no domain has data. Fill the first
+    // domain's free-text comment so hasData is true.
+    await page.locator('.shadess-comment').first().fill('Lives at home with parents, supportive environment.');
+
+    const [resp] = await Promise.all([
+      page.waitForResponse('**/api/well-visit/shadess', { timeout: 10000 }),
+      page.click('#btn-shadess-generate'),
+    ]);
+    expect(resp.status()).toBe(200);
+    await expect(page.locator('#shadess-result-text')).toContainText('MOCK SSHADESS', { timeout: 10000 });
+  });
+
+  test('Visit Note — minimal generate → mocked well-visit note in output', async ({ authedPage: _, page }) => {
+    await mockAI(page);
+    await openTab(page);
+    await openSubtab(page, 'note');
+
+    await page.fill('#wv-note-age', '5 years');
+    await page.selectOption('#wv-note-gender', 'Male');
+    // Provide a vitals string so the request body has something
+    await page.fill('#wv-vitals', 'T 37.0, HR 95, RR 22, BP 95/60, SpO2 99% RA');
+    // Use the transcript area for content
+    await page.locator('#wv-transcript').click();
+    await page.keyboard.type('Parent reports child is doing well; no concerns.');
+
+    const [resp] = await Promise.all([
+      page.waitForResponse('**/api/well-visit/note', { timeout: 15000 }),
+      page.click('#btn-wv-generate'),
+    ]);
+    expect(resp.status()).toBe(200);
+    await expect(page.locator('#wv-note-output')).toBeVisible({ timeout: 10000 });
+    await expect(page.locator('#wv-note-text')).toContainText('MOCK well visit note', { timeout: 10000 });
+  });
+});

migrations/1777003849000_add-personal-notes.js

@@ -0,0 +1,25 @@
+/**
+ * Personal Notes — lightweight per-user scratchpad living under
+ * Clinical Tools. Distinct from user_memories (which feed AI
+ * prompts as style hints / templates): personal_notes are pure
+ * clinician notes, never injected into an AI call. Title + rich-
+ * text body, encrypted at rest like memories so row dumps are
+ * useless without the app crypto key.
+ */
+
+exports.up = (pgm) => {
+  pgm.createTable('personal_notes', {
+    id:         { type: 'serial', primaryKey: true },
+    user_id:    { type: 'integer', notNull: true, references: 'users(id)', onDelete: 'CASCADE' },
+    title:      { type: 'text', notNull: true },
+    body:       { type: 'text', notNull: true, default: '' },
+    created_at: { type: 'timestamptz', notNull: true, default: pgm.func('NOW()') },
+    updated_at: { type: 'timestamptz', notNull: true, default: pgm.func('NOW()') },
+  });
+  pgm.createIndex('personal_notes', 'user_id');
+  pgm.createIndex('personal_notes', ['user_id', 'updated_at']);
+};
+
+exports.down = (pgm) => {
+  pgm.dropTable('personal_notes');
+};

migrations/1777090000000_notes-trash.js

@@ -0,0 +1,13 @@
+// Adds soft-delete support for personal_notes via deleted_at.
+
+exports.up = (pgm) => {
+  pgm.addColumn('personal_notes', {
+    deleted_at: { type: 'timestamptz', notNull: false, default: null },
+  });
+  pgm.createIndex('personal_notes', ['user_id', 'deleted_at']);
+};
+
+exports.down = (pgm) => {
+  pgm.dropIndex('personal_notes', ['user_id', 'deleted_at']);
+  pgm.dropColumn('personal_notes', 'deleted_at');
+};

migrations/1777507197626_add-mermaid-diagrams.js

@@ -0,0 +1,24 @@
+/**
+ * Mermaid Diagrams — per-user clinical pathway / algorithm diagrams.
+ * Source is plain Mermaid text; rendered to SVG client-side. Source
+ * encrypted at rest like personal_notes so a row dump stays useless
+ * without the app key.
+ */
+
+exports.up = (pgm) => {
+  pgm.createTable('mermaid_diagrams', {
+    id:         { type: 'serial', primaryKey: true },
+    user_id:    { type: 'integer', notNull: true, references: 'users(id)', onDelete: 'CASCADE' },
+    title:      { type: 'text', notNull: true },
+    source:     { type: 'text', notNull: true, default: '' },
+    notes:      { type: 'text', notNull: true, default: '' },
+    created_at: { type: 'timestamptz', notNull: true, default: pgm.func('NOW()') },
+    updated_at: { type: 'timestamptz', notNull: true, default: pgm.func('NOW()') },
+  });
+  pgm.createIndex('mermaid_diagrams', 'user_id');
+  pgm.createIndex('mermaid_diagrams', ['user_id', 'updated_at']);
+};
+
+exports.down = (pgm) => {
+  pgm.dropTable('mermaid_diagrams');
+};

migrations/1777600000000_add-clinical-assistant-chats.js

@@ -0,0 +1,21 @@
+/**
+ * Optional saved clinical assistant chats. These are user-triggered saves,
+ * encrypted at rest like personal_notes because answers may contain PHI.
+ */
+
+exports.up = (pgm) => {
+  pgm.createTable('clinical_assistant_chats', {
+    id:         { type: 'serial', primaryKey: true },
+    user_id:    { type: 'integer', notNull: true, references: 'users(id)', onDelete: 'CASCADE' },
+    title:      { type: 'text', notNull: true },
+    payload:    { type: 'text', notNull: true, default: '{}' },
+    created_at: { type: 'timestamptz', notNull: true, default: pgm.func('NOW()') },
+    updated_at: { type: 'timestamptz', notNull: true, default: pgm.func('NOW()') },
+  });
+  pgm.createIndex('clinical_assistant_chats', 'user_id');
+  pgm.createIndex('clinical_assistant_chats', ['user_id', 'updated_at']);
+};
+
+exports.down = (pgm) => {
+  pgm.dropTable('clinical_assistant_chats');
+};

mobile/README.md

@@ -1,17 +1,21 @@
 # PedScribe Mobile App
 
-Native mobile wrapper for Pediatric AI Scribe using Capacitor. Provides background audio recording, push notifications, haptic feedback, deep linking, and share intent support on both iOS and Android.
+Capacitor mobile wrapper for the hosted Ped-AI web app. The app defaults to `https://app.pedshub.com`, lets users choose a self-hosted server URL, and keeps clinical workflows API-backed through the same Express service as the browser app.
 
 ## Features
 
-- Background recording that survives screen lock (foreground service on Android, background audio on iOS)
+- Hosted web workflow inside a native WebView; server updates reach mobile clients without app-store releases
 - Configurable server URL (supports self-hosted instances)
 - Haptic feedback on recording start/stop
 - Keep screen awake during recording
 - Deep linking (pedscribe:// and https://app.pedshub.com)
 - Share intent (receive text/PDFs from other apps)
 - Push notification support
-- App Store and Play Store ready
+- **Biometric sign-in** (Face ID / Touch ID / fingerprint) — credentials
+  stored in iOS Keychain / Android Keystore, gated by OS biometric.
+  Enrolled on first password sign-in (opt-in prompt). 2FA still applies
+  on top — biometric replaces the password step only.
+- Android and iOS project scaffolds for store builds
 
 ## Prerequisites
 

mobile/android/app/build.gradle

@@ -9,8 +9,8 @@ android {
         targetSdkVersion rootProject.ext.targetSdkVersion
         // Version values below are overwritten by scripts/release.sh from
         // the root package.json. versionCode auto-increments per release.
-        versionCode 610002
-        versionName "6.10.2"
+        versionCode 714016
+        versionName "7.14.16"
         testInstrumentationRunner "androidx.test.runner.AndroidJUnitRunner"
         aaptOptions {
              // Files and dirs to omit from the packaged assets dir, modified to accommodate modern web apps.

mobile/android/app/src/main/AndroidManifest.xml

@@ -1,6 +1,11 @@
 <?xml version="1.0" encoding="utf-8"?>
 <manifest xmlns:android="http://schemas.android.com/apk/res/android">
 
+    <!-- Biometric login (capacitor-native-biometric). USE_BIOMETRIC is the
+         API 28+ permission; older devices ignore it. No legacy FINGERPRINT
+         entry needed because capacitor-native-biometric targets API 23+. -->
+    <uses-permission android:name="android.permission.USE_BIOMETRIC" />
+
     <application
         android:allowBackup="false"
         android:fullBackupContent="false"

mobile/android/app/src/main/java/com/pedshub/scribe/MainActivity.java

@@ -1,11 +1,25 @@
 package com.pedshub.scribe;
 
 import android.Manifest;
+import android.content.ContentResolver;
+import android.content.ContentValues;
+import android.content.Context;
 import android.content.Intent;
 import android.content.pm.PackageManager;
+import android.net.Uri;
+import android.os.Build;
 import android.os.Bundle;
+import android.os.Environment;
+import android.print.PrintAttributes;
+import android.print.PrintDocumentAdapter;
+import android.print.PrintManager;
+import android.provider.MediaStore;
+import android.util.Base64;
+import android.view.WindowManager;
+import android.webkit.CookieManager;
 import android.webkit.PermissionRequest;
 import android.webkit.WebChromeClient;
+import android.webkit.WebViewClient;
 import android.webkit.WebView;
 
 import androidx.annotation.NonNull;
@@ -14,10 +28,20 @@ import androidx.core.content.ContextCompat;
 
 import com.getcapacitor.BridgeActivity;
 
+import java.io.File;
+import java.io.FileOutputStream;
+import java.io.OutputStream;
+
 public class MainActivity extends BridgeActivity {
 
     private static final int MIC_PERMISSION_CODE = 1001;
     private PermissionRequest pendingPermissionRequest;
+    private WebView printWebView;
+
+    // True between startForegroundService() and stopForegroundService(), i.e.
+    // while the web app has an active MediaRecorder. Drives the keep-screen-on
+    // flag and the timer-throttling workaround below.
+    private volatile boolean recordingActive = false;
 
     @Override
     protected void onCreate(Bundle savedInstanceState) {
@@ -30,11 +54,93 @@ public class MainActivity extends BridgeActivity {
                     new String[]{ Manifest.permission.RECORD_AUDIO }, MIC_PERMISSION_CODE);
         }
 
+        // Allow the Cloudflare Turnstile iframe to use storage.
+        setupThirdPartyCookies();
+
         // Setup WebView mic permission granting
         setupWebViewPermissions();
 
         // Register JS interface for foreground service control
         setupRecordingBridge();
+
+        // Register JS interface for Android's print / Save as PDF flow.
+        setupPrintBridge();
+
+        // Register JS interface for saving generated visuals to Photos.
+        setupFileBridge();
+    }
+
+    // ── Recording Lifecycle ────────────────────────────────────
+    //
+    // Recording happens in the WebView (MediaRecorder), not in native code,
+    // so keeping the foreground service alive is necessary but not sufficient
+    // — the WebView also has to keep executing JS. Two things protect that:
+    //
+    //  1. FLAG_KEEP_SCREEN_ON while recording, so the device does not
+    //     auto-lock mid-encounter. This is the case that actually bites
+    //     clinicians: a long pause in conversation and the screen times out.
+    //
+    //  2. resumeTimers() if the activity is paused anyway (user presses the
+    //     power button, or a call comes in). Chromium throttles timers hard
+    //     for hidden WebViews, which starves MediaRecorder's chunk delivery.
+    //     Capacitor never calls webView.onPause(), so the WebView itself is
+    //     still live — it is only the timers that need rescuing.
+    //
+    // Note resumeTimers()/pauseTimers() are process-global in WebView, not
+    // per-instance; calling resume here is safe because this app has no other
+    // WebView that wants throttling (printWebView is transient).
+
+    void setKeepScreenOn(final boolean on) {
+        runOnUiThread(() -> {
+            if (on) {
+                getWindow().addFlags(WindowManager.LayoutParams.FLAG_KEEP_SCREEN_ON);
+            } else {
+                getWindow().clearFlags(WindowManager.LayoutParams.FLAG_KEEP_SCREEN_ON);
+            }
+        });
+    }
+
+    void setRecordingActive(boolean active) {
+        recordingActive = active;
+        setKeepScreenOn(active);
+    }
+
+    // NB: BridgeActivity declares these public — narrowing to protected would
+    // not compile.
+    @Override
+    public void onPause() {
+        super.onPause();
+        if (recordingActive && this.bridge != null && this.bridge.getWebView() != null) {
+            this.bridge.getWebView().resumeTimers();
+        }
+    }
+
+    @Override
+    public void onResume() {
+        super.onResume();
+        if (this.bridge != null && this.bridge.getWebView() != null) {
+            this.bridge.getWebView().resumeTimers();
+        }
+    }
+
+    // ── Third-Party Cookies ────────────────────────────────────
+    //
+    // Android WebView blocks third-party cookies by default (unlike Chrome,
+    // which still allows them for now). Cloudflare Turnstile runs inside a
+    // cross-origin iframe from challenges.cloudflare.com and needs its own
+    // storage to run and persist a challenge — without this the widget
+    // silently stalls or errors and never emits a token, so registration and
+    // password reset are impossible from inside the app.
+    //
+    // This is scoped to our own WebView, which only ever loads the PedScribe
+    // origin (see allowNavigation in capacitor.config.json), so it is not a
+    // general relaxation of the app's cookie policy.
+
+    private void setupThirdPartyCookies() {
+        WebView webView = this.bridge.getWebView();
+        CookieManager cookieManager = CookieManager.getInstance();
+        cookieManager.setAcceptCookie(true);
+        cookieManager.setAcceptThirdPartyCookies(webView, true);
     }
 
     // ── WebView Microphone Permission ──────────────────────────
@@ -80,6 +186,16 @@ public class MainActivity extends BridgeActivity {
         webView.addJavascriptInterface(new RecordingBridge(this), "NativeRecording");
     }
 
+    private void setupPrintBridge() {
+        WebView webView = this.bridge.getWebView();
+        webView.addJavascriptInterface(new PrintBridge(this), "NativePrint");
+    }
+
+    private void setupFileBridge() {
+        WebView webView = this.bridge.getWebView();
+        webView.addJavascriptInterface(new FileBridge(this), "NativeFiles");
+    }
+
     public static class RecordingBridge {
         private final MainActivity activity;
 
@@ -91,6 +207,7 @@ public class MainActivity extends BridgeActivity {
         public void startForegroundService() {
             Intent intent = new Intent(activity, AudioRecordingService.class);
             ContextCompat.startForegroundService(activity, intent);
+            activity.setRecordingActive(true);
         }
 
         @android.webkit.JavascriptInterface
@@ -98,6 +215,108 @@ public class MainActivity extends BridgeActivity {
             Intent intent = new Intent(activity, AudioRecordingService.class);
             intent.setAction(AudioRecordingService.ACTION_STOP);
             activity.startService(intent);
+            activity.setRecordingActive(false);
+        }
+
+        // Standalone keep-awake, exposed so the web app can hold the screen on
+        // for non-recording work too. window.nativeKeepAwake() previously
+        // called Capacitor's KeepAwake plugin, which is not installed in this
+        // project — so it silently did nothing and the screen slept during
+        // recordings.
+        @android.webkit.JavascriptInterface
+        public void keepAwake(boolean on) {
+            activity.setKeepScreenOn(on);
         }
     }
+
+    public static class PrintBridge {
+        private final MainActivity activity;
+
+        PrintBridge(MainActivity activity) {
+            this.activity = activity;
+        }
+
+        @android.webkit.JavascriptInterface
+        public void printHtml(String title, String base64Html) {
+            activity.runOnUiThread(() -> activity.printHtmlFromBase64(title, base64Html));
+        }
+    }
+
+    public static class FileBridge {
+        private final MainActivity activity;
+
+        FileBridge(MainActivity activity) {
+            this.activity = activity;
+        }
+
+        @android.webkit.JavascriptInterface
+        public String saveImage(String filename, String base64Png) {
+            return activity.saveImageToPictures(filename, base64Png);
+        }
+    }
+
+    private void printHtmlFromBase64(String title, String base64Html) {
+        try {
+            byte[] decoded = Base64.decode(base64Html, Base64.DEFAULT);
+            String html = new String(decoded, java.nio.charset.StandardCharsets.UTF_8);
+            printWebView = new WebView(this);
+            printWebView.setWebViewClient(new WebViewClient() {
+                @Override
+                public void onPageFinished(WebView view, String url) {
+                    PrintManager printManager = (PrintManager) getSystemService(Context.PRINT_SERVICE);
+                    PrintDocumentAdapter adapter = view.createPrintDocumentAdapter(title != null && !title.isEmpty() ? title : "Clinical Assistant Export");
+                    printManager.print(title != null && !title.isEmpty() ? title : "Clinical Assistant Export", adapter, new PrintAttributes.Builder().build());
+                }
+            });
+            printWebView.loadDataWithBaseURL(null, html, "text/html", "UTF-8", null);
+        } catch (Exception e) {
+            android.util.Log.e("PedScribe", "Native print failed", e);
+        }
+    }
+
+    private String saveImageToPictures(String filename, String base64Png) {
+        String safeName = sanitizeFilename(filename, "clinical-visual.png");
+        try {
+            byte[] imageBytes = Base64.decode(base64Png, Base64.DEFAULT);
+            Uri uri;
+            if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.Q) {
+                ContentResolver resolver = getContentResolver();
+                ContentValues values = new ContentValues();
+                values.put(MediaStore.Images.Media.DISPLAY_NAME, safeName);
+                values.put(MediaStore.Images.Media.MIME_TYPE, "image/png");
+                values.put(MediaStore.Images.Media.RELATIVE_PATH, Environment.DIRECTORY_PICTURES + "/PedScribe");
+                values.put(MediaStore.Images.Media.IS_PENDING, 1);
+                uri = resolver.insert(MediaStore.Images.Media.EXTERNAL_CONTENT_URI, values);
+                if (uri == null) return "error:Could not create image file";
+                try (OutputStream out = resolver.openOutputStream(uri)) {
+                    if (out == null) return "error:Could not open image file";
+                    out.write(imageBytes);
+                }
+                values.clear();
+                values.put(MediaStore.Images.Media.IS_PENDING, 0);
+                resolver.update(uri, values, null, null);
+            } else {
+                File dir = new File(Environment.getExternalStoragePublicDirectory(Environment.DIRECTORY_PICTURES), "PedScribe");
+                if (!dir.exists() && !dir.mkdirs()) return "error:Could not create Pictures/PedScribe";
+                File file = new File(dir, safeName);
+                try (OutputStream out = new FileOutputStream(file)) {
+                    out.write(imageBytes);
+                }
+                uri = Uri.fromFile(file);
+                sendBroadcast(new Intent(Intent.ACTION_MEDIA_SCANNER_SCAN_FILE, uri));
+            }
+            return "saved:" + uri.toString();
+        } catch (Exception e) {
+            android.util.Log.e("PedScribe", "Native image save failed", e);
+            return "error:" + (e.getMessage() != null ? e.getMessage() : "Image save failed");
+        }
+    }
+
+    private String sanitizeFilename(String filename, String fallback) {
+        String value = filename != null ? filename : fallback;
+        value = value.replaceAll("[^A-Za-z0-9._-]", "-");
+        if (value.length() == 0) value = fallback;
+        if (!value.toLowerCase(java.util.Locale.US).endsWith(".png")) value = value + ".png";
+        return value;
+    }
 }

mobile/android/app/src/main/res/values/styles.xml

@@ -13,7 +13,7 @@
     <style name="AppTheme.NoActionBar" parent="Theme.AppCompat.DayNight.NoActionBar">
         <item name="windowActionBar">false</item>
         <item name="windowNoTitle">true</item>
-        <item name="android:background">@null</item>
+        <item name="android:background">@color/colorPrimary</item>
         <item name="android:statusBarColor">@color/colorPrimaryDark</item>
         <item name="android:navigationBarColor">@color/colorPrimaryDark</item>
     </style>
@@ -22,4 +22,4 @@
     <style name="AppTheme.NoActionBarLaunch" parent="Theme.SplashScreen">
         <item name="android:background">@drawable/splash</item>
     </style>
-</resources>
+</resources>

mobile/android/app/src/main/res/xml/file_paths.xml

@@ -2,4 +2,6 @@
 <paths xmlns:android="http://schemas.android.com/apk/res/android">
     <external-path name="my_images" path="." />
     <cache-path name="my_cache_images" path="." />
-</paths>
+    <files-path name="my_files" path="." />
+    <external-files-path name="my_external_files" path="." />
+</paths>

mobile/android/fastlane/Appfile

@@ -0,0 +1,2 @@
+json_key_file('fastlane/google-play-service-account.json')
+package_name('com.pedshub.scribe')

mobile/android/fastlane/Fastfile

@@ -0,0 +1,18 @@
+default_platform(:android)
+
+platform :android do
+  desc "Upload a signed release AAB to Google Play internal track"
+  lane :publish_internal do
+    upload_to_play_store(
+      package_name: 'com.pedshub.scribe',
+      json_key: 'fastlane/google-play-service-account.json',
+      aab: ENV['AAB_PATH'] || 'app/build/outputs/bundle/release/app-release.aab',
+      track: ENV['PLAY_TRACK'] || 'internal',
+      skip_upload_changelogs: true,
+      skip_upload_metadata: true,
+      skip_upload_images: true,
+      skip_upload_screenshots: true,
+      release_status: 'completed',
+    )
+  end
+end

mobile/android/fastlane/Gemfile

@@ -0,0 +1,3 @@
+source 'https://rubygems.org'
+
+gem 'fastlane'

mobile/ios/App/App/Info.plist

@@ -6,6 +6,8 @@
 	<string>en</string>
 	<key>CFBundleDisplayName</key>
         <string>PedScribe</string>
+	<key>NSFaceIDUsageDescription</key>
+	<string>PedScribe uses Face ID to securely sign you in without re-entering your password.</string>
 	<key>CFBundleExecutable</key>
 	<string>$(EXECUTABLE_NAME)</string>
 	<key>CFBundleIdentifier</key>

mobile/package-lock.json

@@ -1,18 +1,19 @@
 {
   "name": "pedscribe-mobile",
-  "version": "1.0.0",
+  "version": "7.14.14",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "pedscribe-mobile",
-      "version": "1.0.0",
+      "version": "7.14.14",
       "dependencies": {
         "@aparajita/capacitor-biometric-auth": "^8.0.0",
         "@capacitor/android": "^6.0.0",
         "@capacitor/app": "^6.0.0",
         "@capacitor/cli": "^6.0.0",
         "@capacitor/core": "^6.0.0",
+        "@capacitor/filesystem": "^6.0.4",
         "@capacitor/haptics": "^6.0.0",
         "@capacitor/ios": "^6.0.0",
         "@capacitor/keyboard": "^6.0.0",
@@ -20,7 +21,8 @@
         "@capacitor/screen-orientation": "^6.0.0",
         "@capacitor/share": "^6.0.0",
         "@capacitor/splash-screen": "^6.0.0",
-        "@capacitor/status-bar": "^6.0.0"
+        "@capacitor/status-bar": "^6.0.0",
+        "capacitor-secure-storage-plugin": "^0.10.0"
       }
     },
     "node_modules/@aparajita/capacitor-biometric-auth": {
@@ -97,6 +99,15 @@
         "tslib": "^2.1.0"
       }
     },
+    "node_modules/@capacitor/filesystem": {
+      "version": "6.0.4",
+      "resolved": "https://registry.npmjs.org/@capacitor/filesystem/-/filesystem-6.0.4.tgz",
+      "integrity": "sha512-eFlg/ZrwYA4Y6ClLRRikudVu2XvuZxfX/XC0ky9MgfbC9dyqTnVkkEoWM6vr1xR89YNY4mB0EeVTet1m1Jcumw==",
+      "license": "MIT",
+      "peerDependencies": {
+        "@capacitor/core": "^6.0.0"
+      }
+    },
     "node_modules/@capacitor/haptics": {
       "version": "6.0.3",
       "resolved": "https://registry.npmjs.org/@capacitor/haptics/-/haptics-6.0.3.tgz",
@@ -488,6 +499,15 @@
         "node": "*"
       }
     },
+    "node_modules/capacitor-secure-storage-plugin": {
+      "version": "0.10.0",
+      "resolved": "https://registry.npmjs.org/capacitor-secure-storage-plugin/-/capacitor-secure-storage-plugin-0.10.0.tgz",
+      "integrity": "sha512-dV4E+HTZAJWC3gef7sBXaAkkb6wvcZHyXjJIHXNb3yz9gRQ/5VMLqCxa0khqpwgWh5oIbo4XFxg3g5tEkfaNMg==",
+      "license": "MIT",
+      "peerDependencies": {
+        "@capacitor/core": "^6.0.0"
+      }
+    },
     "node_modules/chownr": {
       "version": "2.0.0",
       "resolved": "https://registry.npmjs.org/chownr/-/chownr-2.0.0.tgz",

mobile/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pedscribe-mobile",
-  "version": "6.10.2",
+  "version": "7.14.16",
   "description": "PedScribe native mobile app — Capacitor wrapper for Pediatric AI Scribe",
   "private": true,
   "scripts": {
@@ -11,12 +11,14 @@
     "build:ios": "npx cap sync ios"
   },
   "dependencies": {
+    "@aparajita/capacitor-biometric-auth": "^8.0.0",
     "@capacitor/android": "^6.0.0",
     "@capacitor/app": "^6.0.0",
     "@capacitor/cli": "^6.0.0",
     "@capacitor/core": "^6.0.0",
-    "@capacitor/ios": "^6.0.0",
+    "@capacitor/filesystem": "^6.0.4",
     "@capacitor/haptics": "^6.0.0",
+    "@capacitor/ios": "^6.0.0",
     "@capacitor/keyboard": "^6.0.0",
     "@capacitor/push-notifications": "^6.0.0",
     "@capacitor/screen-orientation": "^6.0.0",

package.json

@@ -1,11 +1,11 @@
 {
   "name": "pediatric-ai-scribe",
-  "version": "6.10.2",
+  "version": "7.14.16",
   "description": "AI-powered pediatric clinical documentation platform",
   "main": "server.js",
   "scripts": {
     "start": "node server.js",
-    "test": "node --test test/",
+    "test": "node --test test/*.test.js",
     "e2e": "./scripts/e2e.sh",
     "maint:check": "node scripts/maintenance.js check",
     "maint:reindex": "node scripts/maintenance.js reindex",
@@ -25,8 +25,8 @@
     "@tiptap/extension-text-style": "^3.20.4",
     "@tiptap/extension-underline": "^3.20.4",
     "@tiptap/starter-kit": "^3.20.4",
-    "axios": "^1.7.7",
     "argon2": "^0.41.1",
+    "axios": "^1.7.7",
     "bcryptjs": "^2.4.3",
     "cookie-parser": "^1.4.7",
     "cors": "^2.8.5",
@@ -36,6 +36,8 @@
     "helmet": "^8.0.0",
     "jsonwebtoken": "^9.0.2",
     "mammoth": "^1.8.0",
+    "markdown-it": "^14.1.1",
+    "marked": "^18.0.2",
     "multer": "^1.4.5-lts.1",
     "node-pg-migrate": "^7.7.0",
     "nodemailer": "^8.0.5",
@@ -44,7 +46,9 @@
     "pdf-parse": "^1.1.1",
     "pg": "^8.13.0",
     "pptxgenjs": "^4.0.1",
+    "prom-client": "^15.1.3",
     "qrcode": "^1.5.4",
+    "redis": "^4.7.1",
     "speakeasy": "^2.0.0"
   },
   "optionalDependencies": {
@@ -54,5 +58,9 @@
     "@aws-sdk/client-transcribe-streaming": "^3.1017.0",
     "@aws-sdk/s3-request-presigner": "^3.700.0",
     "@google-cloud/vertexai": "^1.9.0"
+  },
+  "devDependencies": {
+    "dompurify": "^3.4.1",
+    "jsdom": "^29.0.2"
   }
 }

public/404.html

@@ -3,7 +3,7 @@
 <head>
   <meta charset="UTF-8">
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
-  <title>404 – Page Not Found | Pediatric AI Scribe</title>
+  <title>404 – Page Not Found | Pediatric Clinical Tools</title>
   <link rel="preconnect" href="https://fonts.googleapis.com">
   <link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700;800&display=swap" rel="stylesheet">
   <style>
@@ -162,14 +162,14 @@
     </div>
 
     <h1>This page doesn't exist</h1>
-    <p>The URL you visited isn't part of Pediatric AI Scribe.<br>It may have been mistyped or the link is outdated.</p>
+    <p>The URL you visited isn't part of Pediatric Clinical Tools.<br>It may have been mistyped or the link is outdated.</p>
 
     <a href="/" class="btn">
       <svg viewBox="0 0 20 20" fill="currentColor"><path d="M10.707 2.293a1 1 0 0 0-1.414 0l-7 7a1 1 0 0 0 1.414 1.414L4 10.414V17a1 1 0 0 0 1 1h4a1 1 0 0 0 1-1v-3h2v3a1 1 0 0 0 1 1h4a1 1 0 0 0 1-1v-6.586l.293.293a1 1 0 0 0 1.414-1.414l-7-7z"/></svg>
       Back to the app
     </a>
 
-    <div class="footer-note">Pediatric AI Scribe &mdash; Clinical Documentation Platform</div>
+    <div class="footer-note">Pediatric Clinical Tools &mdash; Clinical Documentation Platform</div>
   </div>
 </body>
 </html>