Support standalone tool outputs in turn/start (#41002)

## What changed

- Add an optional `toolOutput` to `turn/start` for starting or steering a turn with a named function-call output instead of user input.
- Emit standalone outputs as `functionCallOutput` thread items, persist them in durable history, and include them in resumed threads.
- Validate that tool outputs have a name, are not combined with nonempty `input`, satisfy the text-size limit, and use supported image URLs.

## Testing

- Cover standalone tool-output notifications, model input, and resumed history in both legacy and paginated history modes.
- Cover the text-size limit for structured tool output.

GitOrigin-RevId: a1eeec7b9b7de67b1a1c5e829a54552b85ec118b

codex-rs/app-server/src/message_processor_tracing_tests.rs

@@ -664,6 +664,7 @@ async fn turn_start_jsonrpc_span_parents_core_turn_spans() -> Result<()> {
                         text_elements: Vec::new(),
                     }],
                     turn_trigger: None,
+                    tool_output: None,
                     responsesapi_client_metadata: None,
                     additional_context: None,
                     cwd: None,