History

Commits on fix-threads-db-sqlite-locking to crates/language_model/src35+

cloud_api_client: Send the organization ID in LLM token requests (#50517)Tom Houlé committed 8 months agoa1d4037
Add fast mode toggle in agent panel (#49714)Tom Houlé committed 8 months ago6a74938
agent: Implement streaming for edit file tool (#50004)Bennet Bo Fenner committed 8 months agoa2e34cb
Sign out upon receiving an Unauthorized response when acquiring an LLM token (#49673)Marshall Bowers committed 8 months ago42202ed
Revert "Sign out upon receiving an Unauthorized response when acquiring an LLM token (#49661) (#49669)Marshall Bowers committed 8 months ago94b9628
Sign out upon receiving an Unauthorized response when acquiring an LLM token (#49661)Marshall Bowers committed 8 months ago2f9350b
cloud_llm_client: Delete unused variants of CompletionRequestStatus (#49516)Tom Houlé committed 8 months ago1702a05
copilot: Display cost multiplier for Github Copilot models (#44800)Sathiyaraman M committed 9 months ago6e33d83
cloud_llm_client: Add StreamEnded and Unknown variants to CompletionRequestStatus (#49121)Tom Houlé committed 9 months ago93ead96
Strip broken thinking blocks from Anthropic requests (#48548)Mikayla Maki committed 9 months ago8529406
agent: Highlight latest models available through the Zed provider (#48614)Marshall Bowers committed 9 months agoafafb66
agent: Add support for setting thinking effort for Zed provider (#48545)Marshall Bowers committed 9 months ago9860106
language_model: Add `supported_effort_levels` method to `LanguageModel` (#48523)Marshall Bowers committed 9 months agoa2ca075
Add support for refreshing outdated LLM tokens (#47512)Marshall Bowers committed 9 months ago25904f6
Add helper method for checking if the LLM token needs to be refreshed (#47511)Marshall Bowers committed 9 months ago097cfae
Fix rate limiter holding permits during tool execution (#47494)Richard Feldman committed 9 months ago29cf14e
agent: Add thinking toggle for Zed provider (#47407)Marshall Bowers committed 9 months agoec981b8
Fix nested request rate limiting deadlock for subagent edit_file (#47232)Richard Feldman committed 9 months ago21050e2
agent: Patch image format bug (#45978)Mason Palmer committed 9 months agoc1da016
Remove Burn Mode code (#46950)Marshall Bowers committed 10 months agoa92df1e
Remove legacy billing code (#46927)Marshall Bowers committed 10 months ago6fcc5e9
Split token display for OpenAI (#46829)Mikayla Maki committed 10 months ago9c5fc6e
Enforce 5MB per-image limit when converting images for language models (#45313)Nathan Sobo committed 11 months agob091cc4
Add support for provider extensions (but no extensions yet) (#45277)Richard Feldman committed 11 months ago6055b45
agent: Allow LanguageModelImage size to be optional (#44956)Xiaobo Liu committed 11 months agoa176a8c
Finish inline telemetry changes (#44842)Mikayla Maki committed 11 months agod7da5d3
Streaming tool use for inline assistant (#44751)Michael Benfield committed 11 months ago488fa02
Enable configuring edit prediction providers through the settings UI (#44505)Danilo Leal committed 11 months ago0283bfb
inline assistant: Use tools and remove insertion mode (#44248)Michael Benfield committed 11 months ago5cd30e5
ai: Add an eval for the inline assistant (#43291)Michael Benfield committed 11 months ago290a155
Fix Gemini 3 on OpenRouter (#43416)Richard Feldman committed 11 months ago6631d8b
Simplify error management in stream_completion (#43035)Mikayla Maki committed 11 months ago898c133
Thought signatures (#42915)Richard Feldman committed 12 months agoc0fadae
agent_ui: Render error descriptions as markdown in thread view callouts (#42732)Danilo Leal committed 1 year agoc1096d8
Add retry support for OpenAI-compatible LLM providers (#37891)Tim McLean committed 1 year agofb90b12