open-swe/agent/webhooks
Adam Moussa ea7da4220a
fix(webhooks): fall back to vision model for Slack/Linear image threads
Re-land upstream #1626 onto the modular webhook structure. When a
Slack mention or Linear issue carries images but the resolved model is
text-only, fall back to a vision-capable model instead of dropping the
images. Re-points default_vision_model_pair at the fork's image-capable
models (Opus 4.8 default, else any supports_images model) rather than
upstream's openai:/anthropic: provider filter.

Refs #80, upstream #1626
2026-07-08 16:41:51 -04:00
..
__init__.py refactor: adopt modular webhook architecture (#1621) + port fork customizations (#85) 2026-06-30 18:46:46 -04:00
github.py refactor: adopt modular webhook architecture (#1621) + port fork customizations (#85) 2026-06-30 18:46:46 -04:00
linear.py fix(webhooks): fall back to vision model for Slack/Linear image threads 2026-07-08 16:41:51 -04:00
slack.py fix(webhooks): fall back to vision model for Slack/Linear image threads 2026-07-08 16:41:51 -04:00