feat: Add extra_content field to ToolCall for provider-specific metadata

[loadchange]

• Add optional extra_content field to ToolCall TypedDict
• Preserve extra_content in parse_tool_call()
• Include extra_content in OpenAI format conversion

Enables support for Google Gemini's thought_signature and other provider-specific metadata while maintaining backward compatibility.

---

Cloudflare's AI Gateway offers an OpenAI-style calling method for Google AI Studio and Google Vertex AI. OpenRouter also adopts this style. However, Google's Gemini 3 series models currently require the thought_signature field to be passed. Therefore, this modification is essential for the above scenarios.

https://ai.google.dev/gemini-api/docs/thought-signatures#openai

[codspeed-hq]

CodSpeed Performance Report

Merging #34111 will not alter performance

_{Comparing loadchange:feat/tool-call-extra-content (7c47dd6) with master (0a6d01e)¹}

⚠️ Unknown Walltime execution environment detected

Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data.

For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.

Summary

✅ 19 untouched
⏩ 15 skipped²

Footnotes

1. No successful run was found on master (65ee43c) during the generation of this report, so 0a6d01e was used instead as the comparison base. There might be some changes unrelated to this pull request in this report. ↩

2. 15 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩

[loadchange]

@mdrxy Please help me troubleshoot the reason, I didn't modify the file for which the test failed; tests/unit_tests/tracers/test_memory_stream.py

Force-push code retry, CI passed