 Sami Jawhar
|
db32bad004
|
fix(look-at): respect configured multimodal-looker model instead of overriding via dynamic fallback
|
2026-03-23 01:12:24 +00:00 |
|
|
YeonGyu-Kim
|
85151f7dfd
|
fix(look-at): preserve variant metadata in fallback chain and block non-vision models
- fallback-chain.ts: cache-derived entries inherit variant from matching hardcoded entries
- agent-metadata.ts: new isVisionCapableAgentModel() guard blocks non-vision registered models
- tools.ts: early vision-capability check before session creation
- Added regression tests for variant preservation and non-vision model rejection
|
2026-03-11 21:45:49 +09:00 |
|
|
YeonGyu-Kim
|
5d31bf46fa
|
fix(look-at): resolve multimodal models from vision-capable providers
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
|
2026-03-08 02:20:48 +09:00 |
|
|
YeonGyu-Kim
|
480dcff420
|
refactor(look-at): split tools.ts into argument parsing and extraction modules
Extract multimodal look-at tool internals:
- look-at-arguments.ts: argument validation and parsing
- assistant-message-extractor.ts: response extraction
- mime-type-inference.ts: file type detection
- multimodal-agent-metadata.ts: agent metadata constants
|
2026-02-08 16:24:21 +09:00 |
|