feat: standard content, IDs, translators, & normalization

[mdrxy]

Warning

• BREAKING: All partner packages must now translate from v1 content blocks to SDK requests and vice versa
• Deprecated: .text() method. .text property on messages is now the recommended usage. .text() will be removed in v2.

Tool Calls

• ToolCall and InvalidToolCall moved to content.py
• index on ToolCall and ToolCallChunk now NotRequired instead of Optional

Standard Content

• WIP

Message & Block IDs

• TL;DR: provider provided > langchain auto-generated > None
• ensure_id(id) now in base.py
• Tests in test_messages.py

Translators

TODO

Normalization

Key Changes:

• Consistent multimodal handling:
  • OpenAI image_url blocks pass through unchanged (broad compatibility) unless convert_all is set in _normalize_messages() (default False)
  • OpenAI input_audio and file blocks convert to v1 standard equivalents
  • Legacy v0 multimodal blocks convert to v1 standard
  • Everything else passes through unchanged
• Partner packages must update content block parsing logic
• Stripping IDs from messages to fix some caching issues: feat: _strip_ids_from_messages #32622

Partner Updates

output_version affects how messages are serialized into .content. _normalize_messages() will now upgrade v0 content to v1, so, all partners now receive v1 format input regardless of output_version.

Migration:

• Partner packages must update to handle v1 input content blocks
• output_version still controls serialization format of responses (unchanged)

TODO

#32694 output version at invoke

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

1 Skipped Deployment

Project	Deployment	Preview	Comments	Updated (UTC)
langchain	Ignored	Preview		Aug 26, 2025 10:04pm

[hntrl]

am confused why we need this subsequent step. isn't the multimodal conversion already happening in the above loop? or are those somehow funneling into non standard blocks?

[ccurme]

we will fix this

[codspeed-hq]

CodSpeed WallTime Performance Report

Merging #32569 will degrade performances by 27.21%

_{Comparing cc/1.0/standard_content (2d450d4) with wip-v1.0 (a2322f6)}

⚠️ Unknown Walltime execution environment detected

Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data.

For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.

Summary

❌ 1 regressions
✅ 12 untouched benchmarks

⚠️ Please fix the performance issues or acknowledge them on CodSpeed.

Benchmarks breakdown

	Benchmark	BASE	HEAD	Change
❌	test_import_time[HumanMessage]	208.3 ms	286.1 ms	-27.21%

[codspeed-hq]

CodSpeed Instrumentation Performance Report

Merging #32569 will not alter performance

_{Comparing cc/1.0/standard_content (2d450d4) with wip-v1.0 (a2322f6)}

Summary

✅ 14 untouched benchmarks