5 Commits
Author SHA1 Message Date
Maksim Totmin 338bd80a95 fix: use provider block's own vision model on legacy fallback
When falling back to a provider block (providerID / legacy ludmila-ai),
prefer the model flagged attachment:true in that block instead of the
Google-default options.model. Prevents sending 'gemini-2.5-flash' to the
ludmila endpoint which expects 'gemini/gemini-2.5-flash'.
2026-08-04 20:44:14 +07:00
Maksim Totmin 04e3eb8dda feat: use Google Gemini as default vision backend, make provider configurable
- Plugin options: baseURL, apiKey, model, providerID, visionModels
- Default: Google Gemini OpenAI-compatible endpoint, gemini-2.5-flash
- Support {env:VAR} templates and GEMINI_API_KEY fallback
- Legacy fallback to ludmila-ai provider block for existing setups
- vision.md subagent now uses google/gemini-2.5-flash
2026-08-04 20:37:40 +07:00
Maksim Totmin 5e24763323 docs: use git+https spec for plugin install 2026-08-04 20:34:17 +07:00
Maksim Totmin 2beadf7ff7 chore: add package.json, README, example config and gitignore 2026-08-04 20:30:36 +07:00
Maksim Totmin b0699f2f07 feat: Initial commit of vision-bridge plugin and agent 2026-08-04 20:25:11 +07:00