yenru0/zed

0 Fork 0

Files

T

Richard FeldmanandZed Zippy 2f949d14a7 Replace always_allow_tool_actions with tool_permissions.default (#48553 )

<img width="1275" height="154" alt="Screenshot 2026-02-10 at 6 55 03 PM"
src="https://github.com/user-attachments/assets/db87fe3f-274b-4bca-b342-b72e651ce57c"
/>
<img width="1275" height="176" alt="Screenshot 2026-02-10 at 6 55 15 PM"
src="https://github.com/user-attachments/assets/4b9a0e70-4897-4736-8cc1-8d1415508f58"
/>

Replaces the boolean `always_allow_tool_actions` setting with a
three-valued `tool_permissions.default` field (`"allow"` / `"confirm"` /
`"deny"`).

Release Notes:

- Introduced per-tool permission settings, including regexes for
controlling when tools may be auto-allowed, auto-denied, or always
require confirmation.
- Replaced the `always_allow_tool_actions` setting with
`tool_permissions.default`.

---------

Co-authored-by: Zed Zippy <234243425+zed-zippy[bot]@users.noreply.github.com>

2026-02-10 18:57:31 -05:00

docs

eval: Add HTML overview for evaluation runs (#29413 )

2025-04-25 17:49:05 +03:00

src

agent: Move subagent spawning to ThreadEnvironment (#48381 )

2026-02-10 11:26:01 +00:00

.gitignore

Add judge to new eval + provide LSP diagnostics (#28713 )

2025-04-14 20:18:47 +00:00

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

Lay the groundwork for a Rust-based eval (#28488 )

2025-04-10 04:45:27 +00:00

README.md

eval: Add support for reading from a .env file (#29426 )

2025-04-25 15:53:02 +00:00

runner_settings.json

Replace always_allow_tool_actions with tool_permissions.default (#48553 )

2026-02-10 18:57:31 -05:00

README.md

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