Commit Graph

3 Commits

Author SHA1 Message Date
bellman bfc507895b fix: trust user-configured multimodal-looker model for vision (#4209)
When a user explicitly configures a model for the multimodal-looker
agent (e.g. zhipuai-coding-plan/glm-5.1), treat that model as
vision-capable even when its provider config does not declare
modalities.input or capabilities.input.image. This unblocks
vision-capable models that the provider config does not advertise.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-24 02:04:48 +09:00
YeonGyu-Kim 612b9c163d fix(config): clear stale context limit cache on provider updates
Rebuilding provider model limits prevents removed entries from leaking into later compaction decisions after config changes.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-03-16 10:38:55 +09:00
YeonGyu-Kim dd680357ae fix(plugin-handlers): cache vision-capable provider models
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-03-08 02:20:34 +09:00