chore: release 2.5.13 (agno-agi#7258)

## Improvements:

- **ReliabilityEval**: Add subset matching, argument validation, and
missing tool call tracking with multi-round tool call collection fixes.
- **AgentOS**: Enhance /sessions list API to return additional fields
(user_id, agent_id, team_id, workflow_id, session_summary, metrics,
total_tokens, metadata).
- **AgentOS**: Add /info API endpoint to return agent, team, and
workflow count as lightweight, unauthenticated instance metadata.
- **ChromaDB**: Implement dynamic batch splitting for large upsert/query
operations.
- **Reader**: Propagate chunk_size to default chunking strategies in
reader classes.
- **Slack** **Interface**: Add show_member_tool_calls param and
automatic card overflow rotation — rotates to a new message when text
exceeds a threshold

## Bug Fixes:

- **VertexAI/Bedrock Claude**: Support `messages` parameter in
`_prepare_request_kwargs` for Claude sub classes
- **Workflows**: Fix continue_run to correctly pause at Condition, Loop,
and Router HITL steps — previously only Step instances were checked.
- **AgentOS**: Exclude interface routes (Slack, Telegram, WhatsApp, A2A)
from JWT middleware so webhook deliveries are not rejected with 401.
- **Tracing**: Fix trace session stats grouping to use session_id only,
preventing duplicate rows when a session has runs from different users.
- **SurrealDB**: Fix trace session stats to use array::first() instead
of math::max() for string fields.
- **ReliabilityEval**: Fix multi-round tool call extraction so all
rounds are collected; fix mutation bug modifying original
RunOutput.messages;
fix arun() using wrong ID for file save.

Author: ysolanky

libs/agno/tests/integration/agent/human_in_the_loop/test_multi_round_user_input.py

@@ -32,6 +32,7 @@ def ask_question(question: str, answer: str = ""):
     )
 
     session_id = "test_multi_round_decorator"
+    answers = ["John", "25", "NYC"]
 
     # Round 1
     response = agent.run("Start the survey", session_id=session_id)
@@ -40,44 +41,24 @@ def ask_question(question: str, answer: str = ""):
     assert len(response.active_requirements) == 1, "Should have 1 active requirement"
     assert response.active_requirements[0].needs_user_input
 
-    # Fill in first answer
-    response.active_requirements[0].user_input_schema[0].value = "John"  # type: ignore
-
-    # Round 2
-    response = agent.continue_run(
-        run_id=response.run_id,
-        requirements=response.requirements,
-        session_id=session_id,
-    )
-
-    if response.is_paused:
-        # Verify we have a NEW active requirement
-        assert len(response.active_requirements) >= 1, "Should have at least 1 active requirement for the new question"
-        assert response.active_requirements[0].needs_user_input
+    round_num = 0
+    max_rounds = 6  # Safety limit
 
-        # Fill in second answer
-        response.active_requirements[0].user_input_schema[0].value = "25"  # type: ignore
+    while response.is_paused and round_num < max_rounds:
+        # Fill in the answer for the active requirement
+        answer = answers[min(round_num, len(answers) - 1)]
+        response.active_requirements[0].user_input_schema[0].value = answer  # type: ignore
 
-        # Round 3
         response = agent.continue_run(
             run_id=response.run_id,
             requirements=response.requirements,
             session_id=session_id,
         )
-
-        if response.is_paused:
-            assert len(response.active_requirements) >= 1
-            response.active_requirements[0].user_input_schema[0].value = "NYC"  # type: ignore
-
-            # Final round
-            response = agent.continue_run(
-                run_id=response.run_id,
-                requirements=response.requirements,
-                session_id=session_id,
-            )
+        round_num += 1
 
     # Final response should not be paused
     assert not response.is_paused, "Final response should not be paused"
+    assert round_num <= max_rounds, f"Test didn't complete within {max_rounds} rounds"
 
 
 def test_multi_round_user_control_flow_tools(shared_db):

libs/agno/tests/integration/agent/test_tool_hooks.py

@@ -94,7 +94,7 @@ def test_confirmation_hook_allows_mul_tool():
 
 
 def test_logger_hook_invocation_add_tool():
-    agent = Agent(tools=[add], tool_hooks=[logger_hook])
+    agent = Agent(tools=[add], tool_hooks=[logger_hook], instructions="Always use the add tool to compute sums.")
 
     with patch.object(type(logger), "info", wraps=logger.info) as mock_info:
         response: RunOutput = agent.run("Compute 4 + 5")

libs/agno/tests/integration/teams/test_event_streaming.py

@@ -833,7 +833,7 @@ def test_intermediate_steps_with_member_agents():
         RunEvent.reasoning_started,
         RunEvent.reasoning_step,
         RunEvent.reasoning_completed,
-        RunEvent.run_content,
+        TeamRunEvent.run_intermediate_content,
         RunEvent.run_content_completed,
         RunEvent.run_completed,
         TeamRunEvent.tool_call_completed,
@@ -870,7 +870,7 @@ def test_intermediate_steps_with_member_agents():
     assert len(events[RunEvent.reasoning_started]) == 1
     assert len(events[RunEvent.reasoning_completed]) == 1
     assert len(events[RunEvent.reasoning_step]) > 1
-    assert len(events[RunEvent.run_content]) > 1
+    assert len(events[TeamRunEvent.run_intermediate_content]) > 1
     assert len(events[RunEvent.run_content_completed]) >= 1
 
 
@@ -906,7 +906,7 @@ def test_intermediate_steps_with_member_agents_only_member_events():
         RunEvent.model_request_completed,
         RunEvent.tool_call_started,
         RunEvent.tool_call_completed,
-        RunEvent.run_content,
+        TeamRunEvent.run_intermediate_content,
         RunEvent.run_content_completed,
         RunEvent.run_completed,
         TeamRunEvent.run_content,
@@ -929,7 +929,7 @@ def test_intermediate_steps_with_member_agents_only_member_events():
     # Lots of member tool calls
     assert len(events[RunEvent.tool_call_started]) == 1
     assert len(events[RunEvent.tool_call_completed]) == 1
-    assert len(events[RunEvent.run_content]) > 1
+    assert len(events[TeamRunEvent.run_intermediate_content]) > 1
     assert len(events[RunEvent.run_content_completed]) == 1
 
 
@@ -972,7 +972,7 @@ def test_intermediate_steps_with_member_agents_nested_team():
         RunEvent.run_started.value,
         RunEvent.model_request_started.value,
         RunEvent.model_request_completed.value,
-        RunEvent.run_content.value,
+        TeamRunEvent.run_intermediate_content.value,
         RunEvent.run_content_completed.value,
         RunEvent.run_completed.value,
         TeamRunEvent.run_content.value,
@@ -1114,7 +1114,7 @@ def get_news_from_duckduckgo(query: str):
     # Assert expected events from members
     assert len(events[RunEvent.run_started]) == 2
     assert len(events[RunEvent.run_completed]) == 2
-    assert len(events[RunEvent.run_content]) > 1
+    assert len(events[TeamRunEvent.run_intermediate_content]) > 1
 
 
 def test_tool_parent_run_id():