feat: summarize conversations in the background after each turn

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V57jSQPqwkGG8BuAXg59X5

Claude outputs/main.py

@@ -783,6 +783,41 @@ async def run_chat_completion(claude_messages: list, conversation_id: int):
     )
 
 
+SUMMARY_SYSTEM_PROMPT = (
+    "Fasse das folgende Gespraech in 2-3 Saetzen auf Deutsch zusammen, damit "
+    "ein spaeterer Chat den Kontext wiedererkennt. Gib nur die Zusammenfassung "
+    "aus, ohne Einleitung."
+)
+
+
+async def update_conversation_summary(conversation_id: int):
+    try:
+        history = await get_messages(conversation_id)
+        claude_messages = [{"role": m["role"], "content": m["content"]} for m in history]
+        completion = await asyncio.to_thread(
+            claude_client.messages.create,
+            model=CLAUDE_MODEL,
+            max_tokens=200,
+            system=SUMMARY_SYSTEM_PROMPT,
+            messages=claude_messages,
+        )
+        summary_text = "".join(b.text for b in completion.content if b.type == "text")
+        embedding = await get_embedding(summary_text)
+        await upsert_conversation_summary(conversation_id, summary_text, embedding)
+    except Exception as e:
+        logger.error(f"Conversation summary update failed for conversation {conversation_id}: {e}")
+
+
+_background_tasks: set = set()
+
+
+def _spawn_background_task(coro):
+    task = asyncio.create_task(coro)
+    _background_tasks.add(task)
+    task.add_done_callback(_background_tasks.discard)
+    return task
+
+
 # ============ MODELS ============
 class ChatRequest(BaseModel):
     conversation_id: Optional[int] = None
@@ -910,6 +945,8 @@ async def chat(request: ChatRequest):
 
         await save_message(conversation_id, DEFAULT_USER_ID, "assistant", response_text, output_tokens)
 
+        _spawn_background_task(update_conversation_summary(conversation_id))
+
         return ChatResponse(
             conversation_id=conversation_id,
             response=response_text,

Claude outputs/tests/test_memory.py

@@ -212,3 +212,49 @@ async def test_run_chat_completion_includes_memory_context_in_system_prompt():
     _, kwargs = main.claude_client.messages.create.call_args
     assert "Hund heisst Bruno" in kwargs["system"]
     assert kwargs["tools"] == main.CALENDAR_TOOLS + main.MEMORY_TOOLS
+
+
+@pytest.mark.asyncio
+async def test_update_conversation_summary_upserts_summary_and_embedding():
+    history = [
+        {"role": "user", "content": "Wie geht es meinem Hund?", "tokens_used": None, "created_at": None},
+        {"role": "assistant", "content": "Bruno geht es gut.", "tokens_used": 5, "created_at": None},
+    ]
+    completion = MagicMock()
+    text_block = MagicMock()
+    text_block.type = "text"
+    text_block.text = "Nutzer fragte nach seinem Hund Bruno."
+    completion.content = [text_block]
+
+    main.claude_client = MagicMock()
+    main.claude_client.messages.create.return_value = completion
+
+    with patch.object(main, "get_messages", new=AsyncMock(return_value=history)), patch.object(
+        main, "get_embedding", new=AsyncMock(return_value=[0.1, 0.2])
+    ), patch.object(main, "upsert_conversation_summary", new=AsyncMock()) as mock_upsert:
+        await main.update_conversation_summary(conversation_id=3)
+
+    mock_upsert.assert_called_once_with(3, "Nutzer fragte nach seinem Hund Bruno.", [0.1, 0.2])
+
+
+@pytest.mark.asyncio
+async def test_update_conversation_summary_swallows_exceptions():
+    with patch.object(main, "get_messages", new=AsyncMock(side_effect=RuntimeError("DB down"))):
+        await main.update_conversation_summary(conversation_id=3)
+    # kein Raise - das ist der Test
+
+
+def test_spawn_background_task_tracks_and_releases_task():
+    import asyncio as aio
+
+    async def _run():
+        async def noop():
+            return "done"
+
+        task = main._spawn_background_task(noop())
+        assert task in main._background_tasks
+        result = await task
+        assert result == "done"
+        assert task not in main._background_tasks
+
+    aio.run(_run())