round compass
I have the following skill that I use as an example and has been running just fine until upgrading.
---
name: test-prod
description: Use when the user invokes test_prod or asks to test Prod agent routing. The expected behavior is to spawn the prod agent and return exactly the child result.
---
++ Usage
When this skill is invoked:
1. Call `agents_list` if needed to confirm the exact Prod agent id.
2. Call `sessions_spawn` with `runtime: "subagent"`, `agentId: "prod"`, `mode: "run"`, and task: `Reply with exactly prod-ok`.
3. Wait for the spawned run completion if the tool/runtime requires it.
4. Reply with the resulting text. The expected final reply is exactly: `prod-ok`.
If `sessions_spawn` or the Prod agent id is unavailable, explain that instead of replying NO_REPLY.
I would see the tool calls for the session spawning/yielding to the Prod agent before receiving the response of prod-ok as expected. However, after upgrade I do not see any tool calls and the response, while varying each time, seems to be addressing internal system messages rather than the skill prompt. For example:
This appears to be a log entry or a record of an action taken at a specific time and location (implied by the format).
Since there is no explicit question, I need more context to provide a helpful response. Could you please tell me:
1. **What do you want me to do with this information?** (e.g., interpret it, explain what it means, continue a conversation, analyze it?)
2. **What does this format represent?** (e.g., a chat transcript, a system log, a personal note?)
If you can provide context, I will do my best to assist you!
Logs are attached.
odd heart