fix(openai): mark truncated/filtered responses as incomplete and avoid finalizing partial tool calls

- Update OpenAI Responses conversion to map finish reasons (`length`/`max_tokens`/`content_filter`) to `response.incomplete` with proper `incomplete_details`.
- Propagate `incomplete` status to response, message, and function/custom tool items in both streaming and non-stream paths.
- Prevent premature completion of tool-call items when a stream ends without a terminal finish reason or with incomplete/partial tool arguments.

Closes: #4873