core-agent-ide/codex-rs/mcp-server/src
zhao-oai 3d35cb4619
Refactor execpolicy fallback evaluation (#7544)
## Refactor of the `execpolicy` crate

To illustrate why we need this refactor, consider an agent attempting to
run `apple | rm -rf ./`. Suppose `apple` is allowed by `execpolicy`.
Before this PR, `execpolicy` would consider `apple` and `pear` and only
render one rule match: `Allow`. We would skip any heuristics checks on
`rm -rf ./` and immediately approve `apple | rm -rf ./` to run.

To fix this, we now thread a `fallback` evaluation function into
`execpolicy` that runs when no `execpolicy` rules match a given command.
In our example, we would run `fallback` on `rm -rf ./` and prevent
`apple | rm -rf ./` from being run without approval.
2025-12-03 23:39:48 -08:00
..
tool_handlers remove mcp-server/src/mcp_protocol.rs and the code that depends on it (#2360) 2025-08-18 00:29:18 -07:00
codex_tool_config.rs [Hygiene] Remove include_view_image_tool config (#5976) 2025-10-30 13:23:24 -07:00
codex_tool_runner.rs Refactor execpolicy fallback evaluation (#7544) 2025-12-03 23:39:48 -08:00
error_code.rs fix: update OutgoingMessageSender::send_response() to take Serialize (#2263) 2025-08-13 14:29:13 -07:00
exec_approval.rs Added model summary and risk assessment for commands that violate sandbox policy (#5536) 2025-10-24 15:23:44 -07:00
lib.rs add(core): managed config (#3868) 2025-10-03 13:02:26 -07:00
main.rs Added new auth-related methods and events to mcp server (#2496) 2025-08-20 20:36:34 -07:00
message_processor.rs [Auth] Choose which auth storage to use based on config (#5792) 2025-10-27 19:41:49 -07:00
outgoing_message.rs Migrate model preset (#7542) 2025-12-03 20:30:43 +00:00
patch_approval.rs chore: introduce ConversationManager as a clearinghouse for all conversations (#2240) 2025-08-13 13:38:18 -07:00