Track byte sizes of inline-uploaded files during PreprocessInlineFileInputs and convert them to conservative token estimates (bytes/3). RefFileTokens is threaded through StandardRequest into all OpenAI chat/responses usage builders so returned prompt_tokens/input_tokens reflect the full upstream context cost including attached files.
Move OpenAI chat and responses usage accounting onto the shared tokenizer-aware counters so prompt and output usage stay model-aware and conservatively sized.
- Add support for multiple keywords: tool_calls, function.name:, [tool_call_history]
- Add OOM protection with search limits in extractToolCallObjects
- Add max scan length limit in extractJSONObject to prevent OOM on unclosed objects
- Update tool_sieve to handle more tool call patterns
- Add loose JSON repair in parseToolCallPayload for better error recovery
This improves DeepSeek tool call parsing robustness.
