feat: add Azure OpenAI / MS Foundry support for /api/ask

- Add LLM_API_VERSION config for Azure api-version query param
- Detect Azure endpoints and use api-key header instead of Bearer
- Handle base URLs that already include /chat/completions path
- Update .env.example with Azure OpenAI guidance

backend/routes/ask.py

@@ -5,7 +5,7 @@ from datetime import UTC, datetime, timedelta
 import httpx
 import structlog
 from auth import require_auth
-from config import LLM_API_KEY, LLM_BASE_URL, LLM_MAX_EVENTS, LLM_MODEL, LLM_TIMEOUT_SECONDS
+from config import LLM_API_KEY, LLM_API_VERSION, LLM_BASE_URL, LLM_MAX_EVENTS, LLM_MODEL, LLM_TIMEOUT_SECONDS
 from database import events_collection
 from fastapi import APIRouter, Depends, HTTPException
 from models.api import AskRequest, AskResponse
@@ -172,6 +172,15 @@ def _format_events_for_llm(events: list[dict]) -> str:
     return "\n".join(lines)
 
 
+def _build_chat_url(base_url: str, api_version: str) -> str:
+    """Construct the chat completions URL, handling Azure OpenAI endpoints."""
+    base = base_url.rstrip("/")
+    url = base if base.endswith("/chat/completions") else f"{base}/chat/completions"
+    if api_version:
+        url = f"{url}?api-version={api_version}"
+    return url
+
+
 async def _call_llm(question: str, events: list[dict]) -> str:
     if not LLM_API_KEY:
         raise RuntimeError("LLM_API_KEY not configured")
@@ -185,13 +194,20 @@ async def _call_llm(question: str, events: list[dict]) -> str:
         },
     ]
 
+    url = _build_chat_url(LLM_BASE_URL, LLM_API_VERSION)
+    headers = {
+        "Content-Type": "application/json",
+    }
+    # Azure OpenAI uses api-key header; standard OpenAI uses Bearer token
+    if "azure" in LLM_BASE_URL.lower() or "cognitiveservices" in LLM_BASE_URL.lower():
+        headers["api-key"] = LLM_API_KEY
+    else:
+        headers["Authorization"] = f"Bearer {LLM_API_KEY}"
+
     async with httpx.AsyncClient(timeout=LLM_TIMEOUT_SECONDS) as client:
         resp = await client.post(
-            f"{LLM_BASE_URL.rstrip('/')}/chat/completions",
-            headers={
-                "Authorization": f"Bearer {LLM_API_KEY}",
-                "Content-Type": "application/json",
-            },
+            url,
+            headers=headers,
             json={
                 "model": LLM_MODEL,
                 "messages": messages,