Added model summary and risk assessment for commands that violate sandbox policy (#5536)

This PR adds support for a model-based summary and risk assessment for
commands that violate the sandbox policy and require user approval. This
aids the user in evaluating whether the command should be approved.

The feature works by taking a failed command and passing it back to the
model and asking it to summarize the command, give it a risk level (low,
medium, high) and a risk category (e.g. "data deletion" or "data
exfiltration"). It uses a new conversation thread so the context in the
existing thread doesn't influence the answer. If the call to the model
fails or takes longer than 5 seconds, it falls back to the current
behavior.

For now, this is an experimental feature and is gated by a config key
`experimental_sandbox_command_assessment`.

Here is a screen shot of the approval prompt showing the risk assessment
and summary.

<img width="723" height="282" alt="image"
src="https://github.com/user-attachments/assets/4597dd7c-d5a0-4e9f-9d13-414bd082fd6b"
/>
This commit is contained in:
Eric Traut
2025-10-24 17:23:44 -05:00
committed by GitHub
parent a4be4d78b9
commit f8af4f5c8d
31 changed files with 701 additions and 34 deletions

View File

@@ -1447,6 +1447,7 @@ async fn apply_bespoke_event_handling(
command,
cwd,
reason,
risk,
parsed_cmd,
}) => {
let params = ExecCommandApprovalParams {
@@ -1455,6 +1456,7 @@ async fn apply_bespoke_event_handling(
command,
cwd,
reason,
risk,
parsed_cmd,
};
let rx = outgoing
@@ -1523,6 +1525,7 @@ async fn derive_config_from_params(
include_view_image_tool: None,
show_raw_agent_reasoning: None,
tools_web_search_request: None,
experimental_sandbox_command_assessment: None,
additional_writable_roots: Vec::new(),
};