This pull request introduces a new tool for streaming edits. The short-term goal is for this tool to replace the existing `EditFileTool`, but we want to get this out the door as soon as possible so that we can start testing it. `StreamingEditFileTool` is mutually exclusive with `EditFileTool`. It will be enabled by default for anyone who has the `agent-stream-edits` feature flag, as well as people that set `assistant.stream_edits` to `true` in their settings. ### Implementation Streaming is achieved by requesting a completion while the `edit_file` tool gets called. We invoke the model by taking the existing conversation with the agent and appending a prompt specifically tailored for editing. In that prompt, we ask the model to produce a stream of `<old_text>`/`<new_text>` tags. As the model streams text in, we incrementally parse it and start editing as soon as we can. ### Evals Note that, as part of this pull request, I also defined some new evals that I used to drive the behavior of the recursive LLM call. To run them, use this command: ```bash cargo test --package=assistant_tools --features eval -- eval_extract_handle_command_output ``` Or comment out the `#[cfg_attr(not(feature = "eval"), ignore)]` macro. I recommend running them one at a time, because right now we don't really have a way of orchestrating of all these evals. I think we should invest into that effort once the new agent panel goes live. Release Notes: - N/A --------- Co-authored-by: Nathan Sobo <nathan@zed.dev> Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de> Co-authored-by: Oleksiy Syvokon <oleksiy.syvokon@gmail.com>
24 lines
681 B
Handlebars
24 lines
681 B
Handlebars
You are an expert coder, and have been tasked with looking at the following diff:
|
|
|
|
<diff>
|
|
{{diff}}
|
|
</diff>
|
|
|
|
Evaluate the following assertions:
|
|
|
|
<assertions>
|
|
{{assertions}}
|
|
</assertions>
|
|
|
|
You must respond with a short analysis and a score between 0 and 100, where:
|
|
- 0 means no assertions pass
|
|
- 100 means all the assertions pass perfectly
|
|
|
|
<analysis>
|
|
- Assertion 1: one line describing why the first assertion passes or fails (even partially)
|
|
- Assertion 2: one line describing why the second assertion passes or fails (even partially)
|
|
- ...
|
|
- Assertion N: one line describing why the Nth assertion passes or fails (even partially)
|
|
</analysis>
|
|
<score>YOUR FINAL SCORE HERE</score>
|