## 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)