Compaction fails with "CAPIError: 400 Tool choice must be auto" on custom models

Describe the bug

Session compaction (manual /compact and automatic compaction at the context threshold) fails with:

Compaction failed. CAPIError: 400 Tool choice must be auto

whenever the session is running a custom model (e.g. ~z-ai/glm-latest registered through a custom OpenRouter-compatible provider). The compaction summary request appears to force a tool call, and CAPI rejects non-auto tool choice for custom models, so compaction can never succeed on them.

Switching the same session to a first-party model (e.g. GPT-5.6 Luna or Claude Sonnet 4.6) and running /compact succeeds, confirming the failure is tied to the custom model's tool-choice capability, not the session contents.

Affected version

GitHub Copilot CLI 1.0.80 (also confirmed still present in the 1.0.81-14 prerelease)

Steps to reproduce the behavior

1. Register a custom model via an OpenRouter-compatible provider (e.g. ~z-ai/glm-latest)
2. Start a session on that model and work until auto-compaction triggers (or run /compact manually)
3. Observe: Compaction failed. CAPIError: 400 Tool choice must be auto
4. Switch the session to a first-party model and run /compact — it succeeds

Expected behavior

Compaction should succeed on custom models, e.g. by falling back to tool_choice: auto with a prompt-based summary when the selected model does not support forced tool choice.

Additional context

• Reproducible across multiple sessions and repositories whenever the session model is a custom one; first-party models (GPT/Claude/Gemini) compact fine.
• After the failed compaction the session keeps growing and eventually hits context/size failures, since auto-compaction can never complete on custom models.

Start by reproducing the failure with /compact on a custom OpenRouter-compatible model, then compare it with a first-party model. No source file or test is named in the report, so trace the compaction request from the /compact entry point and inspect the tool-choice handling. Done means both manual and automatic compaction complete successfully for custom models without the CAPI error.