mirrors/codex
1
0
Fork 0
mirror of https://github.com/openai/codex.git synced 2026-05-03 04:42:20 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add append-only clear context operation

Browse Source
This commit is contained in:
Ahmed Ibrahim
2026-01-26 00:56:15 -08:00
parent d27f2533a9
commit 1aea5ff6c1
18 changed files with 327 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
codex-rs/docs/protocol_v1.md
View File

@@ -68,6 +68,7 @@ For complete documentation of the `Op` and `EventMsg` variants, refer to [protoc
- `Op::UserTurn` – Any input from the user to kick off a `Turn`
- `Op::UserInput` – Legacy form of user input
- `Op::Interrupt` – Interrupts a running turn
- `Op::ClearContext` – Reset the conversation back to the initial context boundary
- `Op::ExecApproval` – Approve or deny code execution
- `Op::UserInputAnswer` – Provide answers for a `request_user_input` tool call
- `Op::ListSkills` – Request skills for one or more cwd values (optionally `force_reload`)
@@ -76,6 +77,7 @@ For complete documentation of the `Op` and `EventMsg` variants, refer to [protoc
- `EventMsg::AgentMessage` – Messages from the `Model`
- `EventMsg::ExecApprovalRequest` – Request approval from user to execute a command
- `EventMsg::RequestUserInput` – Request user input for a tool call
- `EventMsg::ContextCleared` – Signals that prior conversation history should be cleared
- `EventMsg::TurnComplete` – A turn completed successfully
- `EventMsg::Error` – A turn stopped with an error
- `EventMsg::Warning` – A non-fatal warning that the client should surface to the user