feat(hooks): add thinking_budget hook for extended thinking management

[nmarasoiu]

Note: Not sure if this is useful.

In case of Claude Code, using keywords like think, think hard & ultrathink go a long way of setting a thinking budget.
For non Claude thinking models, the http parameters might be different so not sure this would work beyond Anthropic.

Add a new hook that manages Claude's extended thinking budget_tokens parameter:

• Inject default budget_tokens when thinking is enabled but budget is missing
• Override budget_tokens when below configurable minimum threshold
• Ensure budget < max_tokens (API constraint)
• Optionally inject thinking configuration for thinking-capable models

Key design decisions:

• Trust caller: if request has thinking, adjust budget regardless of model
• Model filter only applies to inject_if_missing mode
• Anthropic-specific: non-Anthropic providers will ignore thinking field
• Simple config via hook params (no env var complexity)

Configuration:

• budget_default: Default budget (10000)
• budget_min: Minimum threshold (1024)
• inject_if_missing: Auto-inject thinking (false)
• log_modifications: Log changes (true)

[starbaser]

Thanks for the PR, and another thank you for your patience. After looking through this, I kind of see where you're going with it, but first thing I'd want from you is a more focused value proposition.

Some things to note:

• LiteLLM provides a unified reasoning support check via supports_reasoning(model)
• You can configure params for thinking, max tokens, etc. per model in the litellm config
• LiteLLM already supports some transformations between providers, i.e. gemini and anthropic thinking params are basically interchangeable between each other, reasoning_effort for some is converted to a token budget, other times it's dropped.