mirror of
https://github.com/openai/codex.git
synced 2026-11-13 14:46:14 +00:00
Add batched executor capability discovery (#33852)
## Why Selected capability roots can contribute plugins, MCP servers, connectors, and skills. Discovering each contribution separately requires repeated access to the executor filesystem. ## What changed - Add the `capabilityRoots/discoverV1` exec-server RPC to scan selected roots and materialize recognized plugin manifests, configuration files, skill instructions, and skill metadata in one bounded request. - Add the opt-in `executor_capability_discovery` feature, with a thread-scoped cache and per-step snapshot shared by MCP and skill discovery. - Parse MCP, connector, and skill contributions from the materialized snapshot, including serving cached skill instructions without another filesystem read. ## Testing - Cover discovery limits, manifest precedence, root-local failures, cache reuse, plugin contributions, and parity with the existing environment skill loader. GitOrigin-RevId: f98fd2321cafb58c596db02da1f83c09d8eb375d
This commit is contained in:
1 parent
caa6e554d6
commit
08e30a2e4e
47 files changed
+1957
-47
No files matched your search
@@ -28,6 +28,7 @@ async fn hosted_plugin_runtime_forwards_thread_originator() -> Result<(), Box<dy
|
||||
&thread_store,
|
||||
"codex_work_desktop",
|
||||
/*ready_selected_capability_roots*/ &[],
|
||||
/*executor_capability_discovery*/ None,
|
||||
))
|
||||
.await;
|
||||
let [McpServerContribution::Set { config: server, .. }] = contributions.as_slice() else {
|
||||
|
||||
Reference in new issue
Block a user