mirror of
https://github.com/openai/codex.git
synced 2026-11-07 20:30:33 +00:00
Support per-tool MCP output limits (#41421)
## What changed - Add a positive `output_token_limit` setting to each entry under an MCP server's `tools` configuration. - Apply the most restrictive limit when plugin and user policies overlap, while keeping approval policy independent. - Carry the effective MCP output budget in conversation history so tool output, post-tool hook responses, and resumed sessions use the same truncation limit. ## Testing - Cover configuration parsing, serialization, schema validation, and plugin policy merging. - Cover MCP output below and above the configured limit, post-tool hook responses, and session resume. GitOrigin-RevId: d0beb4fca9ba6055d9e1d31c137373b465d50d61
This commit is contained in:
@@ -401,6 +401,7 @@ mod tests {
|
||||
item: ResponseItem::Other,
|
||||
metadata: Some(CodexHarnessMetadata {
|
||||
client_authored: true,
|
||||
..Default::default()
|
||||
}),
|
||||
});
|
||||
assert!(serde_json::to_value(annotated).is_err());
|
||||
|
||||
Reference in New Issue
Block a user