feat(portkey): completion reasoning

[njbrake]

Description

Portkey docs show that it supports returning:

https://portkey.ai/docs/product/ai-gateway/multimodal-capabilities/thinking-mode#understanding-response-format

I need to make some changes to support and test this but I'm waiting for our portkey account to support a model that outputs thinking, that way I can edit the portkey response as needed.

PR Type

🆕 New Feature 🐛 Bug Fix 💅 Refactor 📚 Documentation 🚦 Infrastructure ## 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 80.82192% with 14 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
src/any_llm/providers/portkey/portkey.py	82.60%	6 Missing and 2 partials ⚠️
src/any_llm/providers/portkey/utils.py	77.77%	1 Missing and 5 partials ⚠️

Files with missing lines	Coverage Δ
src/any_llm/providers/portkey/utils.py	77.77% <77.77%> (ø)
src/any_llm/providers/portkey/portkey.py	86.20% <82.60%> (-13.80%)	⬇️

... and 34 files with indirect coverage changes

🚀 New features to boost your workflow:

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

[njbrake]

Integration tests: https://github.com/mozilla-ai/any-llm/actions/runs/18651581278/job/53170623544