Bump inspect-ai from 0.3.217 to 0.3.218

[dependabot]

Bumps inspect-ai from 0.3.217 to 0.3.218.

Changelog

Sourced from inspect-ai's changelog.

0.3.218 (06 May 2026)

• Google: Support Gemini 3+ native web search and code execution alongside function tools.
• HuggingFace: Add trust_remote_code model argument (defaults to False).
• VLLM: New vllm-completions model provider that uses completions rather than chat endpoint.
• OpenRouter: Coalesce adjacent system messages before request.
• Bedrock: Preserve maxTokens when reasoning effort is less than "high".
• Eval Set: retry_immediate now defaults to True. Pass retry_immediate=False (or --no-retry-immediate) to restore the previous batch-retry behavior.
• Eval Set: max_tasks now defaults to the greater of 10 and the number of models being evaluated (was previously 4).
• Eval Set: Roll forward model_usage and role_usage from previous log when performing retries (matches existing eval-retry behavior).
• Compaction: Account for redacted-reasoning input cost on providers that exclude it from usage.input_tokens (currently OpenAI Responses with store=false + include=["reasoning.encrypted_content"]).
• Bugfix: Fix ToolEvent.message_id to reference the correct ChatMessageTool when multiple tool calls occur in one assistant turn.

Commits

• 0ad4add update changelog for release
• 9452937 Merge branch 'pniranta-add-solver-perplexity'
• 62a39cb update changelog
• 5d2310b Merge branch 'main' into add-solver-perplexity
• 37d49e0 Fix: Bedrock Nova drops maxTokens only for 'high' reasoning effort (#3848)
• 2fda565 Fix ToolEvent.message_id for multiple tool calls in one turn (#3846)
• fd14c73 Bump to latest (#3845)
• dfc9b59 Merge branch 'main' into add-solver-perplexity
• 96f4a81 Move perplexity evaluation from a solver that internally called /v1/completio...
• df75015 petri timeline anchors (#3838)
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)