Fix extended thinking bug by reordering tool messages

[habema]

Resolves #1797

This fixes the issue where conversation histories with extended thinking could have tool_result messages appearing before their corresponding tool_use messages, causing Anthropic API rejections.

What was happening:

• Reasoning blocks between tool calls caused the converter to create malformed message sequences
• Multiple consecutive assistant messages with tool calls weren't getting paired with their results properly
• Anthropic API requires strict tool_use → tool_result ordering

The fix:

• Added _fix_tool_message_ordering() method that only activates when preserve_thinking_blocks=True
• Analyzes the entire conversation to identify tool call/result pairs
• Reconstructs messages ensuring proper tool_use → tool_result sequencing
• Handles edge cases like consecutive tool calls and misplaced results
• Non-breaking - only affects extended thinking scenarios

Repro script available in the original issue.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

[chatgpt-codex-connector]

Preserve unmatched tool_result messages

In _fix_tool_message_ordering() the role == "tool" branch simply marks the index as used and skips emitting the message. When a tool message has no matching tool_call_id or the corresponding tool call is absent from the trimmed history, this logic drops the tool result entirely. Previously those messages were forwarded to the provider; now they silently disappear, which removes tool outputs from the conversation and can change agent behaviour. Consider emitting unmatched tool messages (or raising) rather than discarding them.

Useful? React with 👍 / 👎.

[seratch]

Thanks!