ISSUE DESCRIPTION [Bug] team.acontinuerun loss dependencies or sessionstate Description…
- User
ISSUE DESCRIPTION
[Bug] team.acontinue_run loss dependencies or session_state
Description
team.acontinue_run loss dependencies or session_state
Steps to Reproduce
requires_confirmation_tools = [ "group_del", "group_del_stock", ] async def group_del_stock(self, group_id: str, stock_list: list[dict], run_context: RunContext) -> Dict[str, Any]: url = f"{self.live_base_url}/cloud/api/optional/stock/code/del" headers = { "Content-Type": "application/json", "X-Access-Token": run_context.session_state["user_token"] } data = {"targetStockGroupId":group_id,"delVoList":stock_list}example code
session_id = str(uuid.uuid4()) user_id= '00bgh2' session_state = {"user_token":"Bearer "} asyncio.run(main()) async def main(): async for run_event in stock_team.arun( "将茅台从优质股中删除", stream=True, session_id=session_id, user_id=user_id, session_state=session_state ): from agno.run.team import RunPausedEvent as TeamRunPausedEvent # Use isinstance to check for team's pause event (not the member agent's) if isinstance(run_event, TeamRunPausedEvent): print("Team paused - requires confirmation") for req in run_event.active_requirements: if req.needs_confirmation: print(f" Tool: {req.tool_execution.tool_name}") print(f" Args: {req.tool_execution.tool_args}") req.confirm() # Use apprint_run_response for async streaming response = stock_team.acontinue_run( run_id=run_event.run_id, session_id=run_event.session_id, requirements=run_event.requirements, stream=True, user_id=user_id, dependencies=session_state, ) await pprint.apprint_run_response(response)Agent Configuration (if applicable)
No response
Expected Behavior
in group_del_stock, dependencies["user_token"] or session_state["user_token"] should be not None
Actual Behavior
dependencies["user_token"] or session_state["user_token"] is None
Screenshots or Logs (if applicable)
No response
Environment
agno=2.6.9Possible Solutions (optional)
in _aroute_requirements_to_members_stream, The run_context has not been restored https://github.com/agno-agi/agno/blob/55ba3edd1b4ea230afe8a3fcda39582f8a2178ad/libs/agno/agno/team/_run.py#L5145
Additional Context
No response
ADDITIONAL ADVICE
Since you are given a git repository, you can use git commands to simplify your work. For example, if you made a mistake and want to revert your changes, you can use
git checkout <file>to restore the file to its original state. You can also reset all changes in the repository usinggit reset --hardcommand. Additionally, you can usegit stashandgit stash popto temporarily save your changes and restore them later. Finally, you can see the changes that you've made (which will be submitted when you callsubmit) usinggit statusorgit diffcommands. However you don't need to usegit addorgit commitbefore submitting your changes. In fact,submitonly submits currently unstaged changes because it usesgit diffto get the changes that need to be submitted.CHECKLIST
Before submitting your solution, please go over the following checklist and make sure you've done everything:
- If an error was reported in the issue description, I have successfully reproduced it.
- If an error was reported in the issue description, I have confirmed that my fix resolves the error.
- I have thought about edge cases and made sure my fix handles them as well.
- I have run existing tests in the repository that might have been affected by the change I made and confirmed that they pass. I want you to list every bullet from this checklist and write your reasoning for why you think you did it or didn't need to.
Repository has been uploaded and your shell is currently at the repository root. Time to solve the issue!
(Current directory: /agno, current file: none) bash-$
- Assistant
I'll start by exploring the repository structure to understand the codebase and locate the relevant files. Let's first get an overview.
- Assistant
Let me explore the repository structure more to understand the layout and find the relevant file mentioned in the issue.
- Assistant
Let me look at the libs directory to find the agno library.
- Assistant
Let me look at the team/_run.py file that was referenced in the issue.
- Assistant
Let me look at the specific line mentioned in the issue: line 5145 in _run.py. Let's first see what's around that line.
- Assistant
Let me search for the function
_aroute_requirements_to_members_streamthat was mentioned in the issue. Let me search for it in the codebase. - Assistant
Let me look at the
_aroute_requirements_to_members_streamfunction around line 5110. - Assistant
Let me continue reading the function to see where the issue might be. Let me also look at the
acontinue_runmethod in the Team class. guzzle - Assistant
Let me make one call at a time.
- Assistant
Let me look at the acontinue_run method to understand how it's called and what parameters it passes.
- Assistant
Now let me look at the
acontinue_run_dispatchfunction: - Assistant
Let me look at the acontinue_run_dispatch function to see how it handles dependencies and session_state.
- Assistant
Now let me look at the
_acontinue_run_streamfunction to see how it calls_aroute_requirements_to_members_stream: - Assistant
Let me examine the
_acontinue_run_streamfunction: - Assistant
Now I can see the issue! In
_aroute_requirements_to_members_stream, when callingmember.acontinue_run(...), therun_context(which containssession_stateanddependencies) is NOT being passed. Let me look at what parameters the member agent'sacontinue_runaccepts: - Assistant
Let me look at the agent's acontinue_run method to understand its signature.
- Assistant
Now I understand the issue. The member agent's
acontinue_runaccepts arun_contextparameter, but_aroute_requirements_to_members_streamis NOT passing it. Let me also check the synchronous counterpart_route_requirements_to_members_streamto see if it has the same issue: - Assistant
Let me look at the synchronous version:
- Assistant
Now I can see the pattern. Both the sync and async streaming versions (
_route_requirements_to_members_streamand_aroute_requirements_to_members_stream) do NOT passrun_context(which containssession_stateanddependencies) to the member agent'scontinue_run/acontinue_run. Let me also look at the non-streaming async version_aroute_requirements_to_members:Actually, let me also check the non-streaming sync version
_route_requirements_to_members: - Assistant
Now let me also look at the non-streaming sync version:
- Assistant
Now I understand the issue clearly. All four routing functions (
_route_requirements_to_members,_route_requirements_to_members_stream,_aroute_requirements_to_members,_aroute_requirements_to_members_stream) receive arun_contextparameter but none of them pass it through to the member agent'scontinue_run/acontinue_runcalls. This means the member agent loses access tosession_stateanddependenciesthat were set on the team level.Let me look at the RunContext class to understand what fields it carries:
- Assistant
Let me look at the RunContext class to understand its structure.
- Assistant
Now I have a complete understanding of the bug. Let me create a reproduction script first to verify the issue:
- Assistant
Let me check the setup of the agno library.
- Assistant
Let me look at all four functions that need fixing. First, let me understand the current code in all four functions:
- Assistant
Now let me fix all four routing functions. The issue is clear:
run_contextis available in all four functions but not passed to the member agent'scontinue_run/acontinue_runcalls.Let me start with the fix for
_route_requirements_to_members(sync, non-streaming): - Assistant
Now let me fix the first function -
_route_requirements_to_members(sync, non-streaming). I need to addrun_context=run_contextto bothmember.continue_run()calls: - Assistant
Now let me fix the first function. I'll edit the first
continue_runcall in_route_requirements_to_members: - Assistant
Good. Now let me fix the second function
_route_requirements_to_members_stream(sync, streaming). Let me navigate to it: - Assistant
Now let me fix the two
continue_runcalls in_route_requirements_to_members_stream: - Assistant
Good. Now let me fix the async non-streaming version
_aroute_requirements_to_members. Let me navigate to find theacontinue_runcalls: - Assistant
Now let me fix the two
acontinue_runcalls in_aroute_requirements_to_members: - Assistant
Good. Now let me fix the last function
_aroute_requirements_to_members_stream(async streaming). Let me navigate to find theacontinue_runcalls: - Assistant
Now let me fix the two
acontinue_runcalls in_aroute_requirements_to_members_stream: - Assistant
All four routing functions are now fixed. Let me also check the agent's
acontinue_run_dispatchto make sure it properly uses therun_contextwhen passed: - Assistant
That's the team file. Let me search in the agent directory:
- Assistant
Let me look at the agent's
acontinue_run_dispatch: - Assistant
That's picking up the team file again. Let me search differently.
- Assistant
Wait, that's weird. Let me check if there's an
agent/_run.pyfile separately. - Assistant
Let me check the agent's _run.py for acontinue_run_dispatch.
- Assistant
Let me try a different approach:
- Assistant
Let me continue reading to see how it handles run_context and session_state:
- Assistant
Let me understand how
run_contextgets passed to tool functions. Let me check howsession_stateanddependenciesare made available to tool functions: - Assistant
Let me check how the session is set up in
_acontinue_run_streamand how session_state flows: - Assistant
Let me look at
_asetup_sessionto see how session_state is loaded: - Assistant
Now I can see that
_asetup_sessiondoes properly loadsession_statefrom the DB. The key issue is simply thatrun_context(with bothsession_stateanddependencies) is not being passed through to member agents in the routing functions. My fix addresses this.Let me verify all four functions have been fixed correctly by checking the diff:
- Assistant
The diff looks correct. I've added
run_context=run_contextto all 8continue_run/acontinue_runcalls across the 4 routing functions.Now let me check if there are any existing tests related to this functionality:
- Assistant
Let me also look for team-specific HITL tests:
- Assistant
Let me run the unit tests related to continue_run to make sure my changes don't break anything:
- Assistant
All 49 unit tests pass. Let me also run the background stream test:
- Assistant
All tests pass. Let me also run the broader unit test suite for teams to ensure nothing is broken:
- Assistant
The 3 failures are pre-existing and unrelated to my changes (they're about
agno.db.sqlitemodule attribute missing and a skills path issue). All 411 passing tests still pass, and my changes don't break anything.Let me verify my changes once more:
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.
Identical first prompt
Qwen/Qwen3.6-27BCompare side by side →
Qwen/Qwen3.6-27BCompare side by side →
Qwen/Qwen3.6-27BCompare side by side →
Qwen/Qwen3.6-27BCompare side by side →
Qwen/Qwen3.6-27BCompare side by side →
- xiaomi/mimo-v2.5-proCompare side by side →
- xiaomi/mimo-v2.5-proCompare side by side →
- gpt-5.6-solCompare side by side →
- gpt-5.6-solCompare side by side →
- gpt-5.6-solCompare side by side →
- gpt-5.6-solCompare side by side →