fix: preserve thinking/redacted_thinking blocks in Anthropic message transforms

[bbartels]

Issue for this PR

Closes #14332

Type of change

• Bug fix
• New feature
• Refactor / code improvement
• Documentation

What does this PR do?

Fixes the Anthropic API error: messages.X.content.Y: 'thinking' or 'redacted_thinking' blocks in the latest assistant message cannot be modified.
The Anthropic API requires that thinking and redacted_thinking blocks in assistant messages are sent back byte-for-byte identical in subsequent requests. Three code paths in normalizeMessages / applyCaching in src/provider/transform.ts were inadvertently modifying these blocks:

1. Empty content filtering removed redacted_thinking blocks. The AI SDK represents these as { type: "reasoning", text: "", providerOptions: { anthropic: { redactedData: "..." } } } — the empty text caused them to be filtered out. Fix: only filter reasoning parts that have no providerOptions.
2. Tool-use reordering split assistant messages containing [thinking, tool_call, text] into two separate messages, changing which message the thinking blocks belong to. Fix: skip the reorder when reasoning blocks are present.
3. Cache control hints could be applied to a reasoning block if it was the last content block in the message. Fix: find the last non-reasoning block for cache annotations instead.

How did you verify your code works?

Added tests covering all three fixes to test/provider/transform.test.ts. All 143 tests pass (130 existing + 13 new).
bun test test/provider/transform.test.ts
143 pass, 0 fail

Screenshots / recordings

N/A - not a UI change.

Checklist

• I have tested my changes locally
• I have not included unrelated changes in this PR

[github-actions]

This PR doesn't fully meet our contributing guidelines and PR template.

What needs to be fixed:

• No issue referenced. Please add Closes #<number> linking to the relevant issue.

Please edit this PR description to address the above within 2 hours, or it will be automatically closed.

If you believe this was flagged incorrectly, please let a maintainer know.

[github-actions]

The following comment was made by an LLM, it may be inaccurate:

Based on my search, here are potentially related PRs that address similar issues with Anthropic thinking/redacted_thinking blocks:

Potentially Related PRs:

1. PR fix(opencode): preserve reasoning providerMetadata across model switches #23104 - "fix(opencode): preserve reasoning providerMetadata across model switches"

   • Relates to preserving reasoning blocks across transformations

2. PR fix(provider): skip empty-text filtering for assistant messages in normalizeMessages (#16748) #16750 - "fix(provider): skip empty-text filtering for assistant messages in normalizeMessages (normalizeMessages() removes empty text parts between reasoning blocks, invalidating Anthropic thinking block signatures #16748)"

   • Directly addresses the empty-text filtering issue mentioned in your PR as one of the three fixes

3. PR fix(provider): preserve assistant message content when reasoning blocks present #21370 - "fix(provider): preserve assistant message content when reasoning blocks present"

   • Also deals with preserving reasoning blocks during message transformations

4. PR fix: replace empty text in reasoning messages to preserve thinking block positions #21860 - "fix: replace empty text in reasoning messages to preserve thinking block positions"

   • Addresses similar empty text handling in reasoning messages

5. PR fix: preserve thinking block signatures and fix compaction headroom asymmetry #14393 - "fix: preserve thinking block signatures and fix compaction headroom asymmetry"

   • Related to thinking block preservation

These PRs appear to be addressing similar or overlapping issues with Anthropic thinking/reasoning block preservation. I'd recommend reviewing them to check if any address the same issues or if this PR supersedes any of them.

[github-actions]

Thanks for your contribution!

This PR doesn't have a linked issue. All PRs must reference an existing issue.

Please:

1. Open an issue describing the bug/feature (if one doesn't exist)
2. Add Fixes #<number> or Closes #<number> to this PR description

See CONTRIBUTING.md for details.

[bbartels]

@rekram1-node should be a fairly straightforward set of changes. Runtime changes are small, tests make up main part of the changes

[github-actions]

This pull request has been automatically closed because it was not updated to meet our contributing guidelines within the 2-hour window.

Feel free to open a new pull request that follows our guidelines.

[bainos]

@bbartels would you mind reopening? Closes #14332 has been added to the description? The fix looks correct and is needed — see related discussion in #23104.

[bbartels]

@bbartels would you mind reopening? Closes #14332 has been added to the description? The fix looks correct and is needed — see related discussion in #23104.

Already created another one #23755