feat: deprecate deepseek-chat/reasoner, add v4-flash and v4-pro

[kasvith]

DeepSeek has retired deepseek-chat and deepseek-reasoner in favor of the V4 family. Mark the old models as deprecated with replacement pointers, and add deepseek-v4-flash and deepseek-v4-pro with their 1M context, 384K max output limits and published per-million-token pricing.

Description

Brief description of changes.

Type of Change

• Bug fix (non-breaking change fixing an issue)
• New feature (non-breaking change adding functionality)
• Breaking change (fix or feature causing existing functionality to change)
• Documentation update

Breaking Changes

Testing

• Tests pass (mix test)
• Quality checks pass (mix quality)

Checklist

• My code follows the project's style guidelines
• I have updated the documentation accordingly
• I have added tests that prove my fix/feature works
• All new and existing tests pass
• My commits follow conventional commit format
• I have NOT edited CHANGELOG.md (it is auto-generated by git_ops)
• I have NOT directly edited generated snapshot/history artifacts unless this PR intentionally regenerates them (priv/llm_db/snapshot.json, priv/llm_db/history/**)

Related Issues

Closes #