Aoyang Fang

I find that this version can not be used in RL training now. For example, there are reward returned in my LitAgent, however, the reward is always None: `Warning: Reward...

I return the float reward in the rollout function, the following is an example ```python async def rollout_async( self, task: dict, resources: agl.NamedResources, rollout: agl.Rollout, ) -> agl.RolloutRawResult: sample =...

When I replace `return 1 if judged_sample.correct else 0.0001` with `agl.emit_reward(0.01)`, nothing happened: ``` (TaskRunner pid=2686400) Warning: Reward is None for rollout ro-3896968001ed, will be auto-set to 0.0. (TaskRunner pid=2686400)...

Yes, it generated. In previous logs, it has: ``` reward span is _Span(name="agentlightning.reward", context=SpanContext(trace_id=0xe044bacfc66f1abd64e32a50fec889ad, span_id=0x66cb1b78abf3689c, trace_flags=0x01, trace_state=[], is_remote=False)) ===============trace_spans: [, , , ] getting span reward: _Span(name="agentlightning.reward", context=SpanContext(trace_id=0xe044bacfc66f1abd64e32a50fec889ad, span_id=0x66cb1b78abf3689c, trace_flags=0x01,...

Actually, when I use the default Agentops tracer, I also found that the token ids are missing. There are only rewards here. ``` (TaskRunner pid=2810103) Warning: Rollout ro-9bbacebcded8 contains empty...

Is this because the agent I implemented is not instrumented? I am using youtu-agent (https://github.com/TencentCloudADP/youtu-agent), which is a wrapper of openai-agents. I think by default, AgentOps can instrument it.

Switched to the latest main, the issue remains ``` (TaskRunner pid=2885675) Warning: Rollout ro-34788af75c53 contains empty response: [Triplet(prompt={'token_ids': []}, response={'token_ids': []}, reward=None, metadata={'response_id': 'chatcmpl-5e22b526f0324d0698df20396f5552b2', 'agent_name': '*'}), Triplet(prompt={'token_ids': []}, response={'token_ids': []},...

I tried, but the token_ids are also missing. The code snippets are shown below. I think it is simple. But both AgentOpsTracer and OtelTracer does not output the Triplelet. ```python...

This is Otel Tracer ```bash (rcagent-rl) root@iv-ye5ro8ne9s5i3z3p14l4 ~/RCAgent-RL (main)# uv run python ./training_agl/rcagent/rcagent.py --mode runner 2025-11-02 16:01:23,359[utu.eval.data.data_manager] - WARNING - data_manager.py:45 - exp_id rcabench_evaluation already exists in db 2025-11-02 16:01:23,362...

I encounter the same issue