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-protocol/src/protocol/thread_history.rs

@@ -604,6 +604,7 @@ impl ThreadHistoryBuilder {
         let should_upsert = match item {
             codex_protocol::items::TurnItem::Plan(plan) => !plan.text.is_empty(),
             codex_protocol::items::TurnItem::HookPrompt(_)
+            | codex_protocol::items::TurnItem::FunctionCallOutput(_)
             | codex_protocol::items::TurnItem::CommandExecution(_)
             | codex_protocol::items::TurnItem::DynamicToolCall(_)
             | codex_protocol::items::TurnItem::CollabAgentToolCall(_)