feat(delivery): add POST /delivery/parsePDF SSE route

- Accepts multipart/form-data PDF, streams LLM extraction via SSE
- Uses libllmorbiter (OpenRouterProvider) with API key from companysetting keys.openrouter
- Extracts manifest basedata, notes, and line items from invoices/delivery notes
- Events: status, llm_call, tool_call, usage, progress, result, error
- Extends generateApiDocs.js: multipart field table + x-sse-events table support
- Docs: docs/api/routes/delivery/parsePDF.md (auto-generated)

docs/api/routes/delivery/parsePDF.md

@@ -0,0 +1,85 @@
+# `POST /delivery/parsePDF`
+
+Protected. Requires a valid session cookie (`credentials: 'include'`).
+
+Parse PDF (SSE)
+
+Accepts a PDF invoice or delivery note (`multipart/form-data`, field `pdf`)
+and streams extraction results as Server-Sent Events until parsing is complete.
+
+The PDF is read via `pdftotext -layout` and fed page-by-page to an LLM
+(OpenRouter) which fills a structured manifest of header data and line items.
+The OpenRouter API key is read from the authenticated user's company setting
+`keys.openrouter`; the endpoint returns `400` if the key is not configured.
+
+The stream ends after the final `result` event (or an `error` event on failure).
+
+
+## Body (`multipart/form-data`)
+
+| Field | Required | Type | Description |
+|-------|----------|------|-------------|
+| `pdf` | yes | file | PDF file to parse (max 50 MB, application/pdf) |
+
+## SSE Events
+
+The response is a `text/event-stream`. Events are emitted in order until the stream closes.
+
+| Event | Description | Payload |
+|-------|-------------|---------|
+| `status` | PDF parse confirmation and LLM status messages | `{ "message": "…" }` |
+| `llm_call` | Fired before each LLM request | `{ "model": "…", "promptSize": 0, "messages": 0 }` |
+| `tool_call` | Fired when the output_manifest tool is invoked | `{ "name": "output_manifest" }` |
+| `usage` | Token usage after each LLM response | `{ "input": 0, "cached": 0, "output": 0, "cost": 0 }` |
+| `progress` | Intermediate accumulated extraction state (basedata / notes / items) | `ManifestResult` |
+| `result` | Final accumulated extraction — emitted just before the stream closes | `ManifestResult` |
+| `error` | Emitted on PDF parse or LLM failure; stream closes immediately after | `{ "message": "…" }` |
+
+## Response `200`
+
+`text/event-stream` — emits `status`, `llm_call`, `tool_call`, `usage`,
+`progress`, `result` (and `error` on failure). See SSE Events table below.
+
+**ManifestResult shape** (used by `progress` and `result`):
+
+```json
+{
+  "basedata": {
+    "date": "2026-01-15",
+    "kLieferant": 42,
+    "lieferantName": "Muster GmbH",
+    "manifestNr": "LS-2026-001",
+    "manifestType": "lieferschein"
+  },
+  "notes": ["Pos. 3: VPE-Angabe fehlte, Standardwert 1 angenommen."],
+  "items": {
+    "pagesFrom": 1,
+    "pagesTo": 2,
+    "items": [
+      {
+        "position": 1,
+        "count": 10,
+        "vpe": 1,
+        "unit": "Stk.",
+        "articleName": "Einhängesieb Stahl",
+        "liefArtNr": "ES-100",
+        "mwst": "19",
+        "eknetto": 450,
+        "page": 1
+      }
+    ]
+  }
+}
+```
+
+
+## Errors
+
+| Status | Description |
+|--------|-------------|
+| 400 | No PDF uploaded or OpenRouter key not configured — `{"error":"…"}` |
+| 401 | Unauthorized — `{"error":"…"}` |
+
+---
+
+_Generated from `@openapi` JSDoc. Do not edit by hand — run `npm run docs:api`._