Add generic LLM worker

README.md

@@ -22,6 +22,26 @@ The service is intentionally domain-agnostic:
 This keeps AI service as shared infrastructure rather than a telephony-specific
 service.
 
+## Built-in workers
+
+The first built-in worker processes `llm_chat` and `chat_completion` jobs whose
+`model_profile` equals `LLM_MODEL`.
+
+Input can be either explicit messages:
+
+```json
+{
+  "messages": [
+    {"role": "system", "content": "Answer as JSON."},
+    {"role": "user", "content": "Classify this text"}
+  ],
+  "max_tokens": 256
+}
+```
+
+or compact `system` / `user` fields. The completed job result contains
+`content`, `model`, `usage` and `duration_ms`.
+
 ## API
 
 - `POST /api/v1/jobs` creates one job.
@@ -48,6 +68,9 @@ service.
 - `LLM_MODEL`, default `qwen2.5-14b`
 - `LLM_TIMEOUT`, default `5m`
 - `WHISPERX_URL`, WhisperX endpoint for transcription jobs
+- `WORKER_ID`, default hostname
+- `WORKER_POLL_INTERVAL`, default `2s`
+- `WORKER_CLAIM_LIMIT`, default `4`
 
 ## Next integration step