Centralize thread MCP state in McpRuntime (#34930)

## What changed

- Make `McpRuntime` own the published MCP configuration, connections, elicitation routing, and selected capability roots for a thread.
- Capture immutable MCP bindings for model steps and tool calls so in-flight work keeps a consistent connection set and approval authority while refreshed state is published atomically.
- Mark MCP state dirty when relevant configuration, plugins, environments, authentication, or elicitation capabilities change, then rebuild it before the next sampling request or out-of-band MCP operation.
- Separate config reloads from server invalidation: `ReloadMcpConfig` applies resolved MCP inputs, while `RefreshMcpServers` requests reinitialization from the thread's latest state.

## Testing

- Cover refreshed state visibility for existing turns, stable step bindings, current approval authority, cancelled refresh retries, resource-client reconciliation, and Apps recovery between sampling requests.

GitOrigin-RevId: 59eabb1aa8dc083426bd18ef4d3630508f376401
This commit is contained in:
jif authored and copyberry committed 2026-07-23 11:27:34 +00:00
1 parent 39a2438d16
commit e497325a6a
54 files changed
+1792 -2038

No files matched your search

-13
View File
@@ -478,19 +478,6 @@ impl AsyncManagedClient {
),
)
});
if codex_apps_tools_cache_context
.as_ref()
.is_some_and(ConnectorRuntimeContext::has_current_tools)
|| tool_catalog_cache_context
.as_ref()
.is_some_and(McpToolCatalogCacheContext::has_tools)
{
let startup_task = client.clone();
tokio::spawn(async move {
let _ = startup_task.await;
});
}
Self {
client,
is_codex_apps_mcp_server,