feat(cohere): support reasoning

[njbrake]

• Updated the CohereProvider to support reasoning in completion responses.
• Modified the response conversion methods to handle V2ChatResponse and reasoning content.

Description

PR Type

🆕 New Feature ## Relevant issues

Checklist

• I have added unit tests that prove my fix/feature works
• New and existing tests pass locally
• Documentation was updated where necessary
• I have read and followed the contribution guidelines```

[codecov]

Codecov Report

❌ Patch coverage is 80.00000% with 4 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
src/any_llm/providers/cohere/utils.py	75.00%	0 Missing and 4 partials ⚠️

Files with missing lines	Coverage Δ
src/any_llm/providers/cohere/cohere.py	91.46% <100.00%> (+0.10%)	⬆️
src/any_llm/providers/cohere/utils.py	77.92% <75.00%> (-0.87%)	⬇️

... and 31 files with indirect coverage changes

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[daavoo]

Integration tests: https://github.com/mozilla-ai/any-llm/actions/runs/18554330010/job/52888075644#step:6:75

Not as part of this PR, but I think we should handle reasoning_effort in cohere similar to how we handle it in gemini, by mapping to token_budget values:

https://docs.cohere.com/reference/chat#request.body.thinking