Skip to content

Fix AI provider exclusivity, provider-aware models, and Gemini streaming#50

Open
shettydev wants to merge 1 commit intomainfrom
codex/fix-ai-provider-streaming
Open

Fix AI provider exclusivity, provider-aware models, and Gemini streaming#50
shettydev wants to merge 1 commit intomainfrom
codex/fix-ai-provider-streaming

Conversation

@shettydev
Copy link
Copy Markdown
Owner

@shettydev shettydev commented Feb 11, 2026

Summary

  • Persist preferences.activeProvider (openrouter/gemini) and enforce a single active provider by clearing the other BYOK key on save.
  • Make models/settings provider-aware and route the conversation send + queue processing through the active provider (adds Gemini model support).
  • Improve streaming reliability: align Gemini SSE events with OpenRouter, add a Redis-backed stream fanout bridge, and add a best-effort web polling fallback.

Tests

  • bun run test -- src/modules/ai/__tests__/ai.controller.spec.ts src/modules/conversations/services/__tests__/queue.gemini-stream.spec.ts src/modules/conversations/services/__tests__/queue.service.spec.ts src/modules/conversations/__tests__/conversation.controller.spec.ts (in packages/mukti-api)
  • bun run test -- src/lib/hooks/__tests__/use-conversations.spec.ts (in packages/mukti-web)

@shettydev shettydev self-assigned this Feb 28, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant