History

Commits on example2 to crates/agent/src/thread.rs35+

Polish agent checkpoints (#29265)Antonio Scandurra committed 1 year agoe515b2c
Restore file to original content when rejecting file recreated by agent (#29264)Antonio Scandurra committed 1 year ago55ea481
eval: Fine-grained assertions (#29246)Agus Zubiaga committed 1 year agoce1a674
agent: Support inserting selections as context via `@selection` (#29045)Bennet Bo Fenner committed 1 year agoa5852d4
agent: Support pasting images as context (#29177)Bennet Bo Fenner committed 1 year agoeca6d5a
Add new action to run agent eval (#29158)Nathan Sobo committed 1 year ago458ffaa
agent: Do not add `<using_tool>` placeholder (#29194)Agus Zubiaga committed 1 year agob14356d
Streaming tool calls (#29179)Richard Feldman committed 1 year ago4f2f9ff
Add ability to attach rules as context (#29109)Michael Sloan committed 1 year ago7aa0fa1
agent: Add additional fields to `Agent Tool Finished` telemetry event (#29163)Marshall Bowers committed 1 year ago942d4eb
Default to fast model for thread summaries and titles + don't include system prompt / context / thinking segments (#29102)Michael Sloan committed 1 year agofbf7caf
Don't send dummy user text with tool results (#29099)Nathan Sobo committed 1 year agod48152d
agent: Preserve thinking blocks between requests (#29055)Bennet Bo Fenner committed 1 year agobafc086
Systematically optimize agentic editing performance (#28961)Nathan Sobo committed 1 year agobab2856
agent: Attach thread ID and prompt ID to telemetry events (#29069)Marshall Bowers committed 1 year ago7abe2c9
agent: Use default prompts from prompt library in system prompt (#28915)Michael Sloan committed 1 year ago502a0f6
agent: Report usage from thread summarization requests (#29012)Marshall Bowers committed 1 year ago676cc10
agent: Show request usage in the panel (#29006)Marshall Bowers committed 1 year agoc2cd4fd
agent: Extract usage information from response headers (#29002)Marshall Bowers committed 1 year agod93141b
agent: Support adding selection as context (#28964)Bennet Bo Fenner committed 1 year ago002235d
agent: Fix conversation token usage and estimate unsent message (#28878)Agus Zubiaga committed 1 year ago0286b8a
agent: Add websearch tool (#28621)Bennet Bo Fenner committed 1 year ago456e54b
agent: Show an error when the model requests limit has been reached (#28868)Marshall Bowers committed 1 year agocb79420
Fix rejecting multiple hunks in `AgentDiff` (#28806)Antonio Scandurra committed 1 year ago06ad45c
agent: Return `ToolResult` from `run` inside `Tool` (#28763)Bennet Bo Fenner committed 1 year ago5e09455
agent: Make `ToolWorkingSet` an `Entity` (#28757)Bennet Bo Fenner committed 1 year agoe26f0a3
Add judge to new eval + provide LSP diagnostics (#28713)Michael Sloan committed 1 year ago6b80eb5
agent: Improve compatibility when using MCP servers with Gemini models (#28700)Bennet Bo Fenner committed 1 year ago2603f36
agent: Handle context window exceeded errors from Anthropic (#28688)Agus Zubiaga committed 1 year agob452307
agent: Clean up thread auto-capturing (#28550)Marshall Bowers committed 1 year ago5ebac7e
Actually run the eval and fix a hang when retrieving outline (#28547)Antonio Scandurra committed 1 year ago2440faf
agent: Auto-capture telemetry feature flag (#28271)Thomas Mickley-Doyle committed 1 year ago46b1df2
agent: Add selected tool names to agent panel telemetry (#28247)Thomas Mickley-Doyle committed 1 year agocb1ee01
Lay the groundwork for a Rust-based eval (#28488)Antonio Scandurra committed 1 year ago8ac378b
Revert "Add reminder message about system prompt" (#28482)Antonio Scandurra committed 1 year ago9dfb907