Inspect-ai

- Bugfix: Correct handling of backward compatiblity for inspect-web-browser-tool image.
- Bugfix: Eval now properly exits when `max_tasks` is greater than total tasks

- Requirements: Temporarily upper-bound `rich` to < 14.0.0 to workaround issue.

- Google: Compatibility with httpx client in `google-genai` >= 1.8.0 (which is now required).
- Mistral: Compatibility with tool call schema for `mistralai` >= v1.6.0 (which is now required).
- Inspect View: Correctly parse NaN values (use JSON5 for all JSON parsing)

- Google: Compatibility with v1.7 of google-genai package (create client per-generate request)
- Bugfix: Properly record scorer and metrics when there are multiple tasks run in an eval.

- OpenAI: Ensure that assistant messages always have the `msg_` prefix in responses API.

- New [think()](https://inspect.aisi.org.uk/tools-standard.html#sec-think) tool that provides models with the ability to include an additional thinking step.
- OpenAI: Support for the new [Responses API](https://inspect.ai-safety-institute.org.uk/providers.html#responses-api) and [o1-pro](https://platform.openai.com/docs/models/o1-pro) models.
- OpenAI: Remove base64-encoded audio content from API call JSON in ModelEvent.
- AzureAI: Support for use of native [OpenAI](https://inspect.ai-safety-institute.org.uk/providers.html#openai-on-azure) and [Mistral](https://inspect.ai-safety-institute.org.uk/providers.html#mistral-on-azure-ai) clients using service qualifiers (e.g. `openai/azure/gpt-4o-mini` or `mistral/azure/Mistral-Large-2411`).
- OpenRouter: Handle "error" field in response object and retry for empty responses.
- Added `--metadata` option to eval for associating metadata with eval runs.
- Task display: Show reasoning tokens for models that report them.
- Anthropic: Include reasoning tokens in computation of total tokens
- Inspect View: Properly wrap tool input for non-code inputs like `think`.