fix(transform): inject reasoning_content for ALL assistant msgs to fix DeepSeek thinking mode

[fkyah3]

Issue for this PR

Closes #24104

Type of change

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

What does this PR do?

DeepSeek thinking mode requires
easoning_content on every assistant message, even empty ones. The current code only injects it for interleaved-capable models and skips when
easoningText is empty.

This fails for:

• Models with capabilities.reasoning but no interleaved config (e.g., DeepSeek via @ai-sdk/openai-compatible)
• Old DB-replayed messages without reasoning parts
• String-content assistant messages (legacy format)

The fix broadens the trigger condition, defaults the providerOptions field to "reasoning_content", removes the if (reasoningText) guard, and handles string-content messages.

Note: PR #24146 by @heimoshuiyu addresses the same symptom (empty reasoning_content) but only for interleaved-configured models. This PR covers a broader set of scenarios including non-interleaved models and legacy message formats.

How did you verify your code works?

Applied the same logic to local fork, ran for multiple sessions with DeepSeek reasoning model — no more
easoning_content must be passed back errors.

Screenshots / recordings

N/A

Checklist

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

[github-actions]

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

Based on my search, I found 2 related open PRs that are potential duplicates or closely related:

1. PR fix: preserve empty reasoning_content for DeepSeek V4 thinking mode #24146 - "fix: preserve empty reasoning_content for DeepSeek V4 thinking mode"

   • fix: preserve empty reasoning_content for DeepSeek V4 thinking mode #24146
   • Why related: Directly addresses the same issue of preserving reasoning_content for DeepSeek V4 thinking mode, likely overlapping with the current PR's solution.

2. PR fix(opencode): Error 400 missing reasoning_content – transform reasoning according to DeepSeek API and aditional test cases #17529 - "fix(opencode): Error 400 missing reasoning_content – transform reasoning according to DeepSeek API and aditional test cases"

   • fix(opencode): Error 400 missing reasoning_content – transform reasoning according to DeepSeek API and aditional test cases #17529
   • Why related: The current PR explicitly states it "Closes fix(opencode): Error 400 missing reasoning_content – transform reasoning according to DeepSeek API and aditional test cases #17529 (supersedes with broader fix)", indicating this is a related prior fix that the current PR is meant to replace with a more comprehensive solution.

Recommendation: Check PR #24146 for overlap with the current PR #24150, as both appear to be recent fixes addressing the same DeepSeek reasoning content issue.

[github-actions]

Thanks for updating your PR! It now meets our contributing guidelines. 👍

[fkyah3]

Our more comprehensive fix is available in our fork (commit b5b6ad05d). The simpler fix #24146 covers the common case. Closing as superseded.

[fkyah3]

Re-evaluated the approach — a smaller provider-level default config fix (<10 lines) is safer for upstream than modifying normalizeMessages core logic. Closing in favor of a targeted fix for @ai-sdk/openai-compatible provider.

[fkyah3]

Followed your suggestion — opened a minimal 1-line PR at #24218. Different approach: defaults interleaved to { field: "reasoning_content" } when reasoning: true is set, instead of false. Closes the same gap without touching normalizeMessages.