fix(data): wrap MiniMax-M2 tool calls in <minimax:tool_call> tags#10586
Open
he-yufeng wants to merge 1 commit into
Open
fix(data): wrap MiniMax-M2 tool calls in <minimax:tool_call> tags#10586he-yufeng wants to merge 1 commit into
he-yufeng wants to merge 1 commit into
Conversation
Contributor
There was a problem hiding this comment.
Code Review
This pull request updates the function_formatter in src/llamafactory/data/tool_utils.py to wrap tool calls with <minimax:tool_call> tags. It also adds comprehensive unit tests in tests/data/test_formatter.py to verify the formatting, extraction, and round-trip behavior for the minimax2 tool format. There are no review comments, and I have no feedback to provide.
Important
The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.
2 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do?
MiniMaxM2ToolUtils.function_formatteremits the<invoke>...</invoke>blocks but never wraps them in the<minimax:tool_call>...</minimax:tool_call>tags. That is the wrapper the tool prompt (MINIMAX_M2_TOOL_PROMPT) tells the model to produce, and the same wrappertool_extractorrequires:So the assistant tool-call targets built during training don't match the format the model is taught to emit, and a round trip through
function_formatter->tool_extractorreturns the raw string instead of the parsed calls.Repro on current main:
The fix wraps the joined invoke blocks in the tags, matching both the prompt spec and the extractor:
After the fix the round trip returns
[FunctionCall(name='get_weather', arguments='{"city": "NYC"}')]for both single and parallel calls.How I tested
Added regression tests in
tests/data/test_formatter.py(single, parallel, extractor, round trip), mirroring the existing qwen/lfm2 cases.Before submitting