feat(deepseek): add DeepSeek V4 Flash and V4 Pro model profiles

[neo1027144 (neo1027144-creator)]

Summary

Add model profiles for the new DeepSeek V4 series to \langchain-deepseek.

Models Added

Model	Max Input	Max Output	Reasoning	Tool Calling
\deepseek-v4-flash\	1,000,000	384,000	✅	✅
\deepseek-v4-pro\	1,000,000	384,000	✅	✅

Changes

• **\libs/partners/deepseek/langchain_deepseek/data/_profiles.py**: Added V4 Flash and V4 Pro model profiles

Context

DeepSeek has released its V4 model series. The legacy \deepseek-chat\ and \deepseek-reasoner\ model names are being deprecated, mapping to \deepseek-v4-flash\ non-thinking and thinking modes respectively.

Note

I noticed this file is marked as auto-generated by \langchain-profiles\ CLI. If profiles should only be updated via the CLI tool or upstream \models.dev\ data source, please let me know and I'll adjust the approach.

Source

https://api-docs.deepseek.com/quick_start/pricing

AI Disclosure

This PR was authored with AI assistance.

[github-actions]

This PR has been automatically closed because it does not link to an approved issue.

All external contributions must reference an approved issue or discussion. Please:

1. Find or open an issue describing the change
2. Wait for a maintainer to approve and assign you
3. Add Fixes #<issue_number>, Closes #<issue_number>, or Resolves #<issue_number> to your PR description and the PR will be reopened automatically

Maintainers: reopen this PR or remove the missing-issue-link label to bypass this check.