Type: Bug
Copilot CLI Version: 1.0.84-5 (also observed on 1.0.81-0 and 1.0.79-9)
OS Version: Windows 11 x64
Model: gpt-6-astra (also observed on an Anthropic model)
Summary
When a model stream ends early, the CLI reports five retries with 5-6 seconds of total retry wait, then stops the background sub-agent's turn. The parent receives a normal completion/idle notification without a failure status.
Found five occurrences in local session history, all on background sub-agent turns.
Steps to Reproduce
No deterministic standalone reproducer yet. The observed workflow was:
- Start a background sub-agent on a long, tool-heavy task.
- A model response stream terminates early.
- Compare the
session.error with the following completion/idle notification.
Actual Behaviour
The failing turn reports:
Execution failed: Failed to get response from the AI model; retried 5 times (total retry wait time: 5.00 seconds) Last error: Responses stream ended without a completed response (request ...)
| Path |
Last error |
Reported total retry wait |
| Responses |
Responses stream ended without a completed response |
5.00 s |
| Anthropic messages |
stream ended without producing a Message with role=assistant |
6.00 s |
| Native HTTP |
unexpected EOF during chunk size line |
5.00 s |
The wait figure is not the total request duration.
The inspected subagent.completed event contains usage and timing fields, but no success/error field. In one case it arrived 14 seconds after the error, following 57 minutes and 231 tool calls. In another, the agent went idle less than a second after the error.
Expected Behaviour
- Propagate the failure and its error through the sub-agent completion path.
- Use configurable backoff for retryable stream failures, without replaying already completed tool actions.
Notes
Impact
Long background work can stop without a usable final response while the parent receives an ordinary completion/idle signal.
Type: Bug
Copilot CLI Version:
1.0.84-5(also observed on1.0.81-0and1.0.79-9)OS Version: Windows 11 x64
Model:
gpt-6-astra(also observed on an Anthropic model)Summary
When a model stream ends early, the CLI reports five retries with 5-6 seconds of total retry wait, then stops the background sub-agent's turn. The parent receives a normal completion/idle notification without a failure status.
Found five occurrences in local session history, all on background sub-agent turns.
Steps to Reproduce
No deterministic standalone reproducer yet. The observed workflow was:
session.errorwith the following completion/idle notification.Actual Behaviour
The failing turn reports:
Responses stream ended without a completed responsestream ended without producing a Message with role=assistantunexpected EOF during chunk size lineThe wait figure is not the total request duration.
The inspected
subagent.completedevent contains usage and timing fields, but no success/error field. In one case it arrived 14 seconds after the error, following 57 minutes and 231 tool calls. In another, the agent went idle less than a second after the error.Expected Behaviour
Notes
1.0.86-2. Finding the same error strings in that binary does not establish that the behaviour is unchanged.Impact
Long background work can stop without a usable final response while the parent receives an ordinary completion/idle signal.