5 Commits

Author SHA1 Message Date
YeonGyu-Kim
0c59d2dbe7 refactor(ultrawork): remove thinking config injection from model override
Delegate thinking config control to the provider layer rather than
injecting it manually in ultrawork model override.

🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-02-26 20:08:44 +09:00
YeonGyu-Kim
565ab8c13a fix(ultrawork-model-override): set thinking config object instead of variant string
Fixes #2049
2026-02-25 14:01:03 +09:00
YeonGyu-Kim
eb0931ed6d fix(ultrawork): use session agent fallback and skip same-model override 2026-02-19 18:40:42 +09:00
YeonGyu-Kim
7c71a2dbbf fix(ultrawork): respect variant-only schema overrides
Allow ultrawork overrides configured with only variant to apply at message time so thinking level is honored even without model replacement.
2026-02-19 18:40:42 +09:00
YeonGyu-Kim
64b2d69036 feat(ultrawork): implement per-message model override with deferred DB retry strategy
- Add per-message ultrawork mode detection via keyword matching
- Implement deferred DB override strategy using microtask retry loop
- Fall back to setTimeout after 10 microtask retries for robustness
- Update agent configuration schema with ultrawork model/variant fields
- Integrate with chat.message hook to apply overrides on detection
- Add comprehensive tests for all override scenarios
- Generated schema includes ultrawork configuration

🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
2026-02-19 18:40:42 +09:00