History

Commits on codex to crates/language_model/src35+

Handle `upstream_http_error` completion responses (#34573)Richard Feldman committed 1 year agob4c2ae5
agent: Disable thinking when using inline assistant/edit file tool (#34141)Bennet Bo Fenner committed 1 year ago41fe2a2
agent: Fix max token count mismatch when not using burn mode (#34025)Bennet Bo Fenner committed 1 year ago66a1c35
agent: Add component preview for Zed AI configuration (#33704)Bennet Bo Fenner committed 1 year ago782fbfa
agent: Improve error handling and retry for zed-provided models (#33565)Michael Sloan committed 1 year agod497f52
Cleanup remaining references to max mode (#33509)Ben Brandt committed 1 year ago6c46e11
agent: Fix issue with Anthropic thinking models (#33317)Bennet Bo Fenner committed 1 year ago7be57ba
Thread Anthropic errors into LanguageModelKnownError (#33261)Richard Feldman committed 1 year agoc610ebf
agent: Fix issues with usage display sometimes showing initially fetched usage (#33125)Michael Sloan committed 1 year ago7e801dc
Standardize on u64 for token counts (#32869)Richard Feldman committed 1 year ago5405c2c
Don't spawn Anthropic telemetry event when API key is missing (#32813)Richard Feldman committed 1 year agocfbc2d0
Distinguish between missing models and registries in error messages (#32678)Ben Brandt committed 1 year ago9427833
More resilient eval (#32257)Ben Brandt committed 1 year agoe4bd115
Remove unused load_model method from LanguageModelProvider (#32070)Ben Brandt committed 1 year ago4304521
Pass up intent with completion requests (#31710)Marshall Bowers committed 1 year agoa23ee61
Rename Max Mode to Burn Mode throughout code and docs (#31668)Umesh Yadav committed 1 year ago703ee29
Make language model deserialization more resilient (#31311)Richard Feldman committed 1 year ago00fd045
Show progress as the agent locates which range it needs to edit (#31582)Antonio Scandurra committed 1 year ago4f78165
Default to fast model first for commit messages (#31385)Abdelhakim Qbaich committed 1 year agoe42cf21
language_model: Remove `CloudModel` enum (#31322)Marshall Bowers committed 1 year ago7fb9569
language_models: Fetch Zed models from the server (#31316)Marshall Bowers committed 1 year ago685933b
Handle new `refusal` stop reason from Claude 4 models (#31217)Marshall Bowers committed 1 year ago5c0b161
language_model: Allow Max Mode for Claude 4 models (#31207)Marshall Bowers committed 1 year agofc78408
anthropic: Add support for Claude 4 (#31203)Marshall Bowers committed 1 year ago1475ace
Use `anyhow` more idiomatically (#31052)Kirill Bulatov committed 1 year ago16366cf
Accept wrapped text content from LLM providers (#31048)Richard Feldman committed 1 year ago4bb04ce
evals: Make LLMs configurable in edit_agent evals (#30813)Oleksiy Syvokon committed 1 year ago5112fce
agent: Remove unused max monthly spend reached error (#30615)Marshall Bowers committed 1 year ago7cad943
Have read_file support images (#30435)Richard Feldman committed 1 year ago8fdf309
language_models: Add vision support for Copilot Chat models (#30155)Umesh Yadav committed 1 year agoa6c3d49
Reuse conversation cache when streaming edits (#30245)Antonio Scandurra committed 1 year ago9f6809a
Restore tool cards on thread deserialization (#30053)Mikayla Maki committed 1 year ago0cdd8bd
Change cloud language model provider JSON protocol to surface errors and usage information (#29830)Max Brunsfeld committed 1 year agoc3d9cde
agent: Show a notice when reaching consecutive tool use limits (#29833)Marshall Bowers committed 1 year agof0515d1
Add support for queuing status updates in cloud language model provider (#29818)Max Brunsfeld committed 1 year ago04772bf