Expose invocation sources to extension tools (#40382)

## What changed

- Add `ToolCallSource` to extension `ToolCall`s and propagate direct or Code Mode
  invocation metadata, including the runtime cell and nested tool-call IDs.
- Add `ToolCall::response_byte_budget` so extension tools can bound direct-call
  responses by the host truncation policy while allowing Code Mode responses up
  to the tool's own limit.
- Share the skills extension's response-size limit between its `list` and `read`
  tools.

## Testing

- Verify that Code Mode source metadata is preserved when core constructs an
  extension tool call.

GitOrigin-RevId: b10aef01be30d35b67bee3af24a1a4175c9ee112

codex-rs/ext/history-notes/tests/history_notes_extension.rs

@@ -11,6 +11,7 @@ use codex_extension_api::ExtensionRegistryBuilder;
 use codex_extension_api::NoopTurnItemEmitter;
 use codex_extension_api::ThreadStartInput;
 use codex_extension_api::ToolCall;
+use codex_extension_api::ToolCallSource;
 use codex_extension_api::ToolExecutor;
 use codex_extension_api::ToolName;
 use codex_extension_api::ToolPayload;
@@ -235,6 +236,7 @@ fn tool_call(tool_name: ToolName, arguments: serde_json::Value) -> ToolCall {
         model: "gpt-test".to_string(),
         codex_turn_metadata: None,
         truncation_policy: TruncationPolicy::Bytes(1024),
+        source: ToolCallSource::Direct,
         conversation_history: ConversationHistory::default(),
         turn_item_emitter: Arc::new(NoopTurnItemEmitter),
         environments: Vec::new(),