diff --git a/README.md b/README.md
index 4d7d5c4..a0c2a67 100644
--- a/README.md
+++ b/README.md
@@ -154,6 +154,11 @@ npm run e2e
Primary references:
+- `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.
diff --git a/docs/ARCHITECTURE.md b/docs/ARCHITECTURE.md
new file mode 100644
index 0000000..91588eb
--- /dev/null
+++ b/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.
diff --git a/docs/CLINICAL_ASSISTANT.md b/docs/CLINICAL_ASSISTANT.md
new file mode 100644
index 0000000..497e888
--- /dev/null
+++ b/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.
diff --git a/docs/DEVELOPMENT.md b/docs/DEVELOPMENT.md
new file mode 100644
index 0000000..043601d
--- /dev/null
+++ b/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, '
');
+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.
diff --git a/docs/MODULE_CONVENTIONS.md b/docs/MODULE_CONVENTIONS.md
new file mode 100644
index 0000000..caa1977
--- /dev/null
+++ b/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, '
');
+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`.
diff --git a/docs/SCALING.md b/docs/SCALING.md
new file mode 100644
index 0000000..28849d5
--- /dev/null
+++ b/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.
diff --git a/public/js/admin.js b/public/js/admin.js
index 8082128..a8ad23f 100644
--- a/public/js/admin.js
+++ b/public/js/admin.js
@@ -4,7 +4,7 @@
function adminEscapeHtml(str) {
if (!str) return '';
- return String(str).replace(/&/g, '&').replace(//g, '>').replace(/"/g, '"');
+ return String(str).replace(/&/g, '&').replace(//g, '>').replace(/"/g, '"').replace(/'/g, ''');
}
function adminTableMessage(colspan, color, text) {
diff --git a/public/js/app.js b/public/js/app.js
index ed92a67..f16f2e4 100644
--- a/public/js/app.js
+++ b/public/js/app.js
@@ -743,8 +743,8 @@ function suggestBillingCodes(outputElementId, noteText, noteType, patientAge, vi
if (data.emLevel) {
html += 'E/M Assessment
';
- html += '
Level ' + data.emLevel.level + '';
- html += '
MDM: ' + data.emLevel.complexity + ' | ' + data.emLevel.diagnosisCount + ' dx | ' + data.emLevel.rosCount + ' ROS | ' + data.emLevel.peCount + ' PE';
+ html += '
Level ' + escHtml(data.emLevel.level) + '';
+ html += '
MDM: ' + escHtml(data.emLevel.complexity) + ' | ' + escHtml(data.emLevel.diagnosisCount) + ' dx | ' + escHtml(data.emLevel.rosCount) + ' ROS | ' + escHtml(data.emLevel.peCount) + ' PE';
html += '