v1.17.9

denizsafak/abogenv1.17.9Jun 21, 2026by opencode-agent[bot]

AI Summary

Core and TUI updates focusing on bug fixes for agent step limits, Devstral model detection, and prompt caching. New thinking variants for the GLM-5.2 model are also added.

Key Highlights

Fixed Devstral model detection when provider IDs use different casing.
Added 'high' and 'max' thinking variants for GLM-5.2.
Improved prompt caching by stopping steering reminders on follow-up messages.
Fixed Honor configured agent step limits by forcing a final response.

New Features

High and Max thinking variants for GLM-5.2
Pass configured custom headers to Copilot model requests

Full Release Notes

## Core

### Bugfixes

- Honor configured agent step limits by forcing a final text response instead of failing mid-run.
- Fix Devstral model detection when provider IDs use different casing. (@Robin1987China)
- Pass configured custom headers to Copilot model requests.

### Improvements

- Add `high` and `max` thinking variants for GLM-5.2 across supported providers. (@imranshaiedi-byte)
- Stop wrapping follow-up user messages in a steering reminder so prompt caching stays effective.

## TUI

### Bugfixes

- Only show the background subagent shortcut when the server supports it.

**Thank you to 4 community contributors:**
- @Grantmartin2002:
  - fix(core): fix command docs in customize-opencode skill (#32718)
- @Robin1987China:
  - fix(opencode): use toLowerCase for Devstral model detection (#33109)
- @kimnamu:
  - fix(experimental llm pkg): forward topK to Converse via additionalModelRequestFields (#33030)
- @imranshaiedi-byte:
  - feat(opencode): expose High/Max thinking variants for GLM-5.2 (#32446)