Skip to content

reasoning_effort binding to claude-haiku-4.5 model fails on sub-agent invocation #4941

Description

@Jon-Tindel-Sonova

Describe the bug

My custom build-agent, which worked up through yesterday, (and likely any custom subagent whose  /subagents  config pins model  claude-haiku-4.5 ) fails every invocation with:  Reasoning effort 'low' is not supported for model 'claude-haiku-4.5' . Reproduced regardless of whether  reasoning_effort  is omitted or explicitly set ( low / medium / minimal ) in the  task  tool call — the runtime appears to always inject a  reasoning_effort  value for this model, which the model doesn't support at all. First seen 2026-09-22; sessions from 2026-09-14 through 2026-09-21 using the same  build-agent  config succeeded without this error, so it looks like a recent regression. Session:  e8b4c267-83c7-431f-9a10-ede4dd88f8cf .

Affected version

GitHub Copilot CLI 1.0.87

Steps to reproduce the behavior

  1. Invoke the sub-agent whose model is set to claude-haiku-4.5
  2. Fails as described above

Expected behavior

Sub-agent invocation succeeds.

Additional context

windows 11, x86_64

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    area:agentsSub-agents, fleet, autopilot, plan mode, background agents, and custom agentsarea:modelsModel selection, availability, switching, rate limits, and model-specific behavior

    Type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions