Expose MCP provenance to tool lifecycle extensions (#40976)

## What changed

- Add optional `McpToolContext` metadata to `ToolStartInput`, exposing the
  model-visible MCP tool details and its source classification without exposing
  the executable client.
- Classify MCP calls as connectors, configured servers, plugin servers,
  executor-selected plugins, or other registrations based on the prepared call.
- Prepare each MCP call before notifying tool lifecycle contributors and reuse
  that same call for execution so the callback describes the call that runs.

## Testing

- Cover host-owned connector calls and extension-owned Apps server calls,
  including their distinct provenance and executed tool names.

GitOrigin-RevId: efd23f511b1045ffdd96349d621ad62365569b2b

codex-rs/ext/extension-api/src/lib.rs

@@ -17,6 +17,7 @@ pub use capabilities::NoopResponseItemInjector;
 pub use capabilities::ResponseItemInjectionFuture;
 pub use capabilities::ResponseItemInjector;
 pub use codex_context_fragments::ContextualUserFragment;
+pub use codex_mcp::ToolInfo as McpToolInfo;
 pub use codex_protocol::models::ContentItemKind;
 pub use codex_protocol::models::ResponseItem;
 pub use codex_protocol::security_risk::SecurityRiskScore;
@@ -49,6 +50,8 @@ pub use contributors::ExtensionFuture;
 pub use contributors::McpServerContribution;
 pub use contributors::McpServerContributionContext;
 pub use contributors::McpServerContributor;
+pub use contributors::McpToolContext;
+pub use contributors::McpToolSource;
 pub use contributors::PreviousWorldStateSection;
 pub use contributors::PromptFragment;
 pub use contributors::PromptSlot;