Merge branch 'main' into rayhpeng/persistence-scaffold

# Conflicts:
#	backend/tests/test_model_factory.py

backend/app/gateway/routers/runs.py

@@ -51,6 +51,7 @@ async def stateless_stream(body: RunCreateRequest, request: Request) -> Streamin
             "Cache-Control": "no-cache",
             "Connection": "keep-alive",
             "X-Accel-Buffering": "no",
+            "Content-Location": f"/api/threads/{thread_id}/runs/{record.run_id}",
         },
     )
 

backend/app/gateway/routers/thread_runs.py

@@ -119,8 +119,9 @@ async def stream_run(thread_id: str, body: RunCreateRequest, request: Request) -
             "Connection": "keep-alive",
             "X-Accel-Buffering": "no",
             # LangGraph Platform includes run metadata in this header.
-            # The SDK's _get_run_metadata_from_response() parses it.
-            "Content-Location": (f"/api/threads/{thread_id}/runs/{record.run_id}/stream?thread_id={thread_id}&run_id={record.run_id}"),
+            # The SDK uses a greedy regex to extract the run id from this path,
+            # so it must point at the canonical run resource without extra suffixes.
+            "Content-Location": f"/api/threads/{thread_id}/runs/{record.run_id}",
         },
     )
 

backend/app/gateway/services.py

@@ -375,8 +375,9 @@ async def sse_consumer(
     - ``cancel``: abort the background task on client disconnect.
     - ``continue``: let the task run; events are discarded.
     """
+    last_event_id = request.headers.get("Last-Event-ID")
     try:
-        async for entry in bridge.subscribe(record.run_id):
+        async for entry in bridge.subscribe(record.run_id, last_event_id=last_event_id):
             if await request.is_disconnected():
                 break