diff options
| author | Adam Malczewski <[email protected]> | 2026-06-28 21:24:18 +0900 |
|---|---|---|
| committer | Adam Malczewski <[email protected]> | 2026-06-28 21:24:18 +0900 |
| commit | 6dd9ea9b935e5011c16faed6c869c976cf5ff172 (patch) | |
| tree | 4702e1ba6a58cbf630831deb24bcd1d6d261a75c /docker/cs | |
| parent | 7f1381c4452846e5a2689d868ab0ee2bc90042c9 (diff) | |
| download | dispatch-6dd9ea9b935e5011c16faed6c869c976cf5ff172.tar.gz dispatch-6dd9ea9b935e5011c16faed6c869c976cf5ff172.zip | |
fix(vision): tell vision agents not to use tools, just describe images directly
Kimi was trying to use Python tools to analyze images rather than just
describing them. Updated both vision system prompts (consult_vision and
image compaction) to explicitly instruct: do not use any tools unless
specifically asked to — just use your vision to see the image and describe
it directly.
Diffstat (limited to 'docker/cs')
0 files changed, 0 insertions, 0 deletions