zed/crates/eval
Marshall Bowers 9860106b8e
agent: Add support for setting thinking effort for Zed provider (#48545)
This PR adds the ability to set the thinking effort of a model.

Right now this only applies to Opus 4.6 through the Zed provider.

This is gated behind the `cloud-thinking-toggle` feature flag.

UI is still rough; needs a design pass:

<img width="639" height="163" alt="Screenshot 2026-02-05 at 7 45 54 PM"
src="https://github.com/user-attachments/assets/2b5a9ef8-74cd-498e-9c81-b92666572409"
/>

<img width="263" height="148" alt="Screenshot 2026-02-05 at 7 45 58 PM"
src="https://github.com/user-attachments/assets/40232cb0-1743-443b-b04c-5cd33065513d"
/>

Release Notes:

- N/A
2026-02-06 01:04:53 +00:00
..
docs
src agent: Add support for setting thinking effort for Zed provider (#48545) 2026-02-06 01:04:53 +00:00
.gitignore
build.rs Use distinct user agents in agent eval and zeta-cli (#35897) 2025-08-08 23:26:38 +00:00
Cargo.toml eval: Port to agent2 (#40704) 2025-10-22 17:55:26 +00:00
LICENSE-GPL
README.md eval: Add support for reading from a .env file (#29426) 2025-04-25 15:53:02 +00:00
runner_settings.json eval: Port to agent2 (#40704) 2025-10-22 17:55:26 +00:00

Eval

This eval assumes the working directory is the root of the repository. Run it with:

cargo run -p eval

The eval will optionally read a .env file in crates/eval if you need it to set environment variables, such as API keys.

Explorer Tool

The explorer tool generates a self-contained HTML view from one or more thread JSON file. It provides a visual interface to explore the agent thread, including tool calls and results. See ./docs/explorer.md for more details.

Usage

cargo run -p eval --bin explorer -- --input <path-to-json-files> --output <output-html-path>

Example:

cargo run -p eval --bin explorer -- --input ./runs/2025-04-23_15-53-30/fastmcp_bugifx/*/last.messages.json --output /tmp/explorer.html