public/galaxy
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
178 Commits 1 Branch 0 Tags
b3f3a72435d3d29d51e493f5f331f7ac62eb7c74
Commit Graph
4 Commits
Author SHA1 Message Date
rkw6086 b3f3a72435 Fix provider tool history handling 2026-08-12 14:19:51 -05:00
Ryan Ward 345057a147 Fix: Ensure OpenAI requests end with user message for Bedrock/LiteLLM compatibility 
When LiteLLM routes OpenAI-format requests to AWS Bedrock, the provider
rejects conversations ending with an assistant message with:
'This model does not support assistant message prefill.'

Add ensure_ends_with_user_message() as the final sanitization step in
sanitize_messages_for_openai(). If the conversation ends with an assistant
message, a minimal 'Continue.' user message is appended.

Updated tests to reflect the new behavior and added dedicated tests for
the new function.
 2026-07-16 09:55:38 -05:00
Ryan Ward 40bd86f662 Adding logging when we crash in bedrock, adding open AI request translator changes and AI page settings cleanup 2026-07-08 15:19:51 -05:00
Ryan Ward 5ea378a38d Add OpenAI/LiteLLM provider support with settings UI 
- Add openai/ provider module with translator, client, convert, request/response translators
- Add shared provider/ types (ConversationMessage, MessageRole, ProviderConfig enum)
- Wire OpenAI-compatible provider dispatch alongside Bedrock in response_stream.rs
- Add ai.openai.* settings (enabled, base_url, api_key, model, models)
- Add OpenAI/LiteLLM settings page with model fetch, picker, and config UI
- Extend model menu items and llms.rs to surface LiteLLM models
- Update WARP.md with OpenAI provider architecture docs
 2026-06-17 14:14:40 -05:00