Problem (one or two sentences)
Hi, I am wondering if the main task and subtask share the same context_size but are calculated separately?
I set the context_size in Zoo to 128k, and was using Orchestrator mode. When the conversation went into the subtask, there was another context progress bar showing another 128k context_size. The conversation stopped with a context_size exceeding error when the sum of the main task and the subtask exceeded 100% (47%+60% ish).
Context (who is affected and when)
When the user is using Orchestrator mode and entering a subtask.
Reproduction steps
- Use Orchestrator mode
- Enter subtask
- Run until the context_size exceeds
Expected result
run normally without context_size error
Actual result
context_size exceeding error with (main+subtask)
Variations tried (optional)
No response
App Version
3.60.0
API Provider (optional)
OpenAI Compatible
Model Used (optional)
Qwen3.6-27B
Zoo Code Task Links (optional)
No response
Relevant logs or errors (optional)
Problem (one or two sentences)
Hi, I am wondering if the main task and subtask share the same context_size but are calculated separately?
I set the context_size in Zoo to 128k, and was using Orchestrator mode. When the conversation went into the subtask, there was another context progress bar showing another 128k context_size. The conversation stopped with a context_size exceeding error when the sum of the main task and the subtask exceeded 100% (47%+60% ish).
Context (who is affected and when)
When the user is using Orchestrator mode and entering a subtask.
Reproduction steps
Expected result
run normally without context_size error
Actual result
context_size exceeding error with (main+subtask)
Variations tried (optional)
No response
App Version
3.60.0
API Provider (optional)
OpenAI Compatible
Model Used (optional)
Qwen3.6-27B
Zoo Code Task Links (optional)
No response
Relevant logs or errors (optional)