Repository navigation
Failed to get response from the AI model; retried 5 times; Last error: Unknown error #1627
Description
Describe the bug
On 2026-02-23, Copilot CLI repeatedly failed during normal chat turns with automatic retries, burning premium requests without returning usable output.
I observed two failure modes in the same incident window:
Failed to get response from the AI model; retried 5 times; Last error: Unknown errorCAPIError: 400 400 Bad Request(with Request-ID), also retried repeatedly
Example failure:
The issue persisted after exiting Copilot CLI and resuming the session with /resume.
Switching models did not resolve it (Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3 Pro Preview).
This issue exhausted my premium requests today due to repeated automatic retries and re-sends of context during failure loops.
Affected version
GitHub Copilot CLI 0.0.414
Steps to reproduce the behavior
- Start Copilot CLI in an existing session with prior context.
- Run normal prompts, then continue with retry/continue style prompts after a failure.
- Observe repeated retry loops and eventual query failure.
- Switch model (Sonnet -> Haiku -> Gemini) and retry.
- Exit Copilot CLI, then resume session using
/resume. - Observe failures continue, including repeated
400 Bad Requeston later attempts.
Expected behavior
Copilot CLI should either:
- recover and return a response after transient backend errors, or
- fail fast with a clear actionable reason and avoid repeated paid retries for the same invalid/unserviceable request path.
Switching model or resuming session should not keep replaying a failing pattern indefinitely.
Additional context
- OS: Linux
- Shell: bash
- Incident date: 2026-02-23
- Models attempted: Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3 Pro Preview
- Session behavior: persisted across exit +
/resume
Observed errors:
Failed to get response from the AI model; retried 5 times; Last error: Unknown errorCAPIError: 400 400 Bad Request
Request-IDs captured from logs:
9BE4:71AB1:11F1B88:1569739:699C1D4F9BE4:71AB1:11F45BA:156C643:699C1D539BE4:71AB1:11F757D:156FB2A:699C1D5C9BE4:71AB1:11FB120:1573D46:699C1D689BE4:71AB1:12008C3:1579E68:699C1D759BE4:71AB1:120678E:1580847:699C1D889BE4:71AB1:1212A42:158E05B:699C1DC59BE4:71AB1:12153DB:1590E66:699C1DC89BE4:71AB1:12181A3:1594130:699C1DD29BE4:71AB1:121B746:1597C52:699C1DDC9BE4:71AB1:121F978:159C676:699C1DE79BE4:71AB1:122550A:15A2C11:699C1DF6
Reacted by Justin Chu and Zhuoren Ye
Activity
dereklegenzoff commentedon Feb 24, 2026
We shipped a fix in version 0.0.416 that should prevent the
Response was interrupted due to a server errorerrors from happening frequently in autopilot mode.Regarding the 400s, it looks like those errors are predominantly caused by the
chrome-devtool-emulateMCP tool. We will look into this issue but in the interim, the best bet might be to disable that MCP tool temporarily.dereklegenzoff commentedon Feb 24, 2026
Thanks for providing the request IDs!
doughgle commentedon Feb 24, 2026
@dereklegenzoff thank you. I'll try those suggestions. If it helps, Copilot chat worked smoothly at the same time, same model, same mcp tools.
borcherspm commentedon Feb 25, 2026
I have this too still with 0.0.418. it just started showing up, unfortunately I dont know which version i was on before I updated today.
I do not have the chrome-devtool-emulate tool.
MCP_DOCKER is using the docker desktop mcp toolkit and it has context7 and confluence/jira mcp server.
patniko commentedon Oct 26, 2026
Thanks for the report. We've shipped fixes in this area since this was filed (most recently in Copilot CLI v0.0.422), and we believe this may now be resolved. Could you retest on the latest release (Copilot CLI v1.0.103) and let us know whether you still see it? If we don't hear back in a couple of weeks, we may close this issue — you can always reopen it.
Triaged as part of a Copilot SDK backlog review, with help from GitHub Copilot.