fix(api): report checkpoint deletion failures and classify SSE errors

Delete checkpoints before removing business fields. Suppress only an
explicit CheckpointNotFoundError; propagate storage failures and
cancellation so the endpoint cannot report false success. Prefer async
checkpoint deletion and fail clearly when cleanup is unsupported.

Classify SSE error events as 401 for authentication, 429 for rate limits,
and 500 for other failures, using the same fixed messages as non-stream
responses. Errors terminate the stream without a success done event or
provider exception text in the response.

Validation: 286 offline tests passed (19 added), including failed-delete
HTTP retry with preserved business/checkpoint state, explicit missing
threads, cancellation, missing cleanup capability, and HTTP SSE errors
before and after text output.

test/services/test_app_service.py

@@ -211,8 +211,10 @@ async def test_delete_clears_business_state_and_is_idempotent():
 
 @pytest.mark.asyncio
 async def test_delete_tolerates_missing_checkpoint():
+    from src.services.repository import CheckpointNotFoundError
+
     async def missing(_session_id):
-        raise RuntimeError("no such thread")
+        raise CheckpointNotFoundError("no such thread")
 
     service, _ = make_service()
     await service.set_info("s1", "xm1", "王五")