mirror of
https://github.com/openai/codex.git
synced 2026-11-17 14:58:36 +00:00
Add bounded tool-result metadata support to executed tool calls (#44336)
## What changed - Add host-recorded `tool_result_metadata` snapshots with size limits, redacted debug output, and protection against deserialization from untrusted input. MCP capture remains disabled. - Preserve accepted metadata across retries and delayed Code Mode results. Shed raw metadata before source evidence, calls, or completion markers when the request budget is exceeded. - Send raw metadata only to allowed OpenAI and ChatGPT HTTPS endpoints, filtering by the resolved destination for HTTP and WebSocket requests. - Encode source parse failures as an array entry with type `parse_failed` and an empty ID. ## Testing Add coverage for metadata bounds and redaction, retained-call updates, budget shedding, disabled MCP capture, and HTTP/WebSocket destination filtering. GitOrigin-RevId: b1a396323ad0623167cdd9e20ff9453f0d01bbf7
This commit is contained in:
1 parent
b5544d5732
commit
0df6366a87
18 files changed
+1198
-120
No files matched your search
@@ -44,6 +44,7 @@ pub use executed_tool_calls::ExecutedToolCall;
|
||||
pub use executed_tool_calls::ExecutedToolCallArguments;
|
||||
pub use executed_tool_calls::ExecutedToolCallTruncation;
|
||||
pub use executed_tool_calls::MAX_TOOL_RESULT_SOURCE_FIELD_BYTES;
|
||||
pub use executed_tool_calls::ToolResultMetadata;
|
||||
pub use executed_tool_calls::ToolResultSource;
|
||||
pub use executed_tool_calls::ToolResultSources;
|
||||
pub use executed_tool_calls::bound_executed_tool_calls_for_prompt;
|
||||
|
||||
Reference in new issue
Block a user