Inspect-ai

- Add `interactive` option to `web_browser()` for disabling interactive tools (clicking, typing, and submitting forms).
- Provide token usage and raw model API calls for OpenAI o1-preview.
- Add support for reading CSV files of dialect 'excel-tab'.
- Improve prompting for Python tool to emphasise the need to print output.
- For `basic_agent()`, defer to task `max_messages` if none is specified for the agent (default to 50 is the task does not specify `max_messages`).
- Add optional `content` parameter to `ModelOutput.for_tool_call()`.
- Display total samples in Inspect View
- Prune `sample_reductions` when returning eval logs with `header_only=True`.
- Improved error message for undecorated solvers.
- For simple matching scorers, only include explanation if it differs from answer.

- The sample transcript will now display the target for scoring in the Score Event (for newly run evaluations).
- Provide setter for `max_messages` on `TaskState`.
- Provide `max_messages` option for `basic_agent()` (defaulting to 50) and use it rather than any task `max_messages` defined.
- Improved implementation of disabling parallel tool calling (also fixes a transcript issue introduced by the original implementation).
- Improve quality of error messages when a model API key environment variable is missing.
- Improve prompting around letting the model know it should not attempt parallel web browser calls.

- Rename `web_browser_tools()` to `web_browser()`, and don't export individual web browsing tools.
- Add `parallel` option to `tool` decorator and specify `parallel=False` for web browsing tools.
- Improve prompting for web browser tools using more explicit examples.
- Improve prompting for `</tool_call>` end sequence for Llama models.
- Fix issue with failure to execute sample setup scripts.

- Move evals into [inspect_evals](https://github.com/UKGovernmentBEIS/inspect_evals) package.

- [Web Browser](https://inspect.aisi.org.uk/tools-standard.html#sec-web-browser) tool which provides a headless Chromium browser that supports navigation, history, and mouse/keyboard interactions.
- `auto_id` option for dataset readers to assign an auto-incrementing ID to records.
- Task args: don't attempt to serialise registry objects that don't have captured parameters.

- Catch o1-preview "invalid_prompt" exception and convert to normal content_filter refusal.
- Terminate timed out subprocesses.
- Support 'anthropoic/bedrock/' service prefix for Anthropic models hosted on AWS Bedrock.
- Change score reducer behavior to always reduce score metadata to the value of the `metadata` field in the first epoch
- Improve task termination message (provide eval-retry prompt for tasks published in packages)
- Preserve type for functions decorated with `task`.
- Various improvements to layout and display for Inspect View transcript.