@agentclientprotocol/codex-acp 1.1.2 → 1.1.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +1 -0
- package/dist/index.js +722 -92
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -12,6 +12,7 @@ Use [OpenAI Codex](https://github.com/openai/codex) from [Agent Client Protocol]
|
|
|
12
12
|
- Model, reasoning effort, fast mode, approval, and sandbox mode configuration.
|
|
13
13
|
- Text prompts, embedded context, images, resource links, and additional workspace directories.
|
|
14
14
|
- Shell command, file change, permission request, MCP tool call, terminal output, reasoning, plan, web search, image generation, image view, token usage, and review events.
|
|
15
|
+
- Subagent launches as standard ACP tool calls, with Codex thread identity and activity details in namespaced `_meta.codex.subagent` metadata.
|
|
15
16
|
- Client-provided MCP servers over command-based stdio config and HTTP transport.
|
|
16
17
|
- Slash commands: `/status`, `/mcp`, `/skills`, `/review`, `/review-branch`, `/review-commit`, `/compact`, and `/logout`, as well as configured skills.
|
|
17
18
|
|