eval: Fix stalling on tool confirmation (#28786)
The `always_allow_tool_actions` setting would get overridden with the default when we loaded each example project, leading to examples stalling when they run a tool that needed confirmation. There's now a separate `runner_settings.json` file where we can configure the environment for the eval. Release Notes: - N/A --------- Co-authored-by: Oleksiy <oleksiy@zed.dev>
This commit is contained in:
parent
b1e4e6048a
commit
ff4334efc7
5 changed files with 36 additions and 13 deletions
1
Cargo.lock
generated
1
Cargo.lock
generated
|
@ -4877,7 +4877,6 @@ version = "0.1.0"
|
|||
dependencies = [
|
||||
"agent",
|
||||
"anyhow",
|
||||
"assistant_settings",
|
||||
"assistant_tool",
|
||||
"assistant_tools",
|
||||
"async-watch",
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue