fix(checkpointer): use AsyncConnectionPool for postgres to prevent stale connection errors (#3223) (#3226)

* fix(checkpointer): use AsyncConnectionPool for postgres to prevent stale connection errors (#3223)

  Replace AsyncPostgresSaver.from_conn_string() with an explicit
  AsyncConnectionPool that has check_connection enabled, so dead idle
  connections are detected and replaced on checkout instead of raising
  OperationalError.

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* Fixed the unit test error and lint error

* fix(checkpointer): add TCP keepalive to postgres connection pool (#3254)

  Enable TCP keepalive probes on the AsyncConnectionPool to prevent
  idle postgres connections from being dropped by the server or network
  middleware. Combined with the existing check_connection callback, this
  provides defense-in-depth against stale connection errors.

  Fixes #3254

* Changed the code as review suggestion

---------

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

backend/packages/harness/deerflow/runtime/checkpointer/async_provider.py

@@ -47,6 +47,41 @@ def _prepare_database_sqlite_checkpointer_path(db_config) -> str:
     return conn_str
 
 
+def _build_postgres_pool(conn_string: str):
+    """Build an AsyncConnectionPool with TCP keepalive and connection checking."""
+    from psycopg.rows import dict_row
+    from psycopg_pool import AsyncConnectionPool
+
+    return AsyncConnectionPool(
+        conn_string,
+        kwargs={
+            "autocommit": True,
+            "prepare_threshold": 0,
+            "row_factory": dict_row,
+            "keepalives": 1,
+            "keepalives_idle": 60,
+            "keepalives_interval": 10,
+            "keepalives_count": 6,
+        },
+        check=AsyncConnectionPool.check_connection,
+    )
+
+
+def _ensure_postgres_imports():
+    """Import and return (AsyncPostgresSaver, AsyncConnectionPool), raising ImportError on failure."""
+    try:
+        from langgraph.checkpoint.postgres.aio import AsyncPostgresSaver
+    except ImportError as exc:
+        raise ImportError(POSTGRES_INSTALL) from exc
+
+    try:
+        from psycopg_pool import AsyncConnectionPool
+    except ImportError as exc:
+        raise ImportError(POSTGRES_INSTALL) from exc
+
+    return AsyncPostgresSaver, AsyncConnectionPool
+
+
 # ---------------------------------------------------------------------------
 # Async factory
 # ---------------------------------------------------------------------------
@@ -74,15 +109,13 @@ async def _async_checkpointer(config) -> AsyncIterator[Checkpointer]:
         return
 
     if config.type == "postgres":
-        try:
-            from langgraph.checkpoint.postgres.aio import AsyncPostgresSaver
-        except ImportError as exc:
-            raise ImportError(POSTGRES_INSTALL) from exc
-
         if not config.connection_string:
             raise ValueError(POSTGRES_CONN_REQUIRED)
 
-        async with AsyncPostgresSaver.from_conn_string(config.connection_string) as saver:
+        AsyncPostgresSaver, _ = _ensure_postgres_imports()
+        pool = _build_postgres_pool(config.connection_string)
+        async with pool:
+            saver = AsyncPostgresSaver(conn=pool)
             await saver.setup()
             yield saver
         return
@@ -117,15 +150,13 @@ async def _async_checkpointer_from_database(db_config) -> AsyncIterator[Checkpoi
         return
 
     if db_config.backend == "postgres":
-        try:
-            from langgraph.checkpoint.postgres.aio import AsyncPostgresSaver
-        except ImportError as exc:
-            raise ImportError(POSTGRES_INSTALL) from exc
-
         if not db_config.postgres_url:
             raise ValueError("database.postgres_url is required for the postgres backend")
 
-        async with AsyncPostgresSaver.from_conn_string(db_config.postgres_url) as saver:
+        AsyncPostgresSaver, _ = _ensure_postgres_imports()
+        pool = _build_postgres_pool(db_config.postgres_url)
+        async with pool:
+            saver = AsyncPostgresSaver(conn=pool)
             await saver.setup()
             yield saver
         return