Release Trinity-RFT 0.3.2 (#369)

Author: pan-x-c

README.md

@@ -83,7 +83,7 @@ Trinity-RFT is a flexible, general-purpose framework for reinforcement fine-tuni
 ## 🚀 News
 
 * [2025-11] Introducing [BOTS](https://github.com/modelscope/Trinity-RFT/tree/main/examples/bots): online RL task selection for efficient LLM fine-tuning ([paper](https://arxiv.org/pdf/2510.26374)).
-* [2025-10] [[Release Notes](https://github.com/modelscope/Trinity-RFT/releases/tag/v0.3.2)] Trinity-RFT v0.3.2 released: bug fixes and advanced task selection & scheduling.
+* [2025-11] [[Release Notes](https://github.com/modelscope/Trinity-RFT/releases/tag/v0.3.2)] Trinity-RFT v0.3.2 released: bug fixes and advanced task selection & scheduling.
 * [2025-10] [[Release Notes](https://github.com/modelscope/Trinity-RFT/releases/tag/v0.3.1)] Trinity-RFT v0.3.1 released: multi-stage training support, improved agentic RL examples, LoRA support, debug mode and new RL algorithms.
 * [2025-09] [[Release Notes](https://github.com/modelscope/Trinity-RFT/releases/tag/v0.3.0)] Trinity-RFT v0.3.0 released: enhanced Buffer, FSDP2 & Megatron support, multi-modal models, and new RL algorithms/examples.
 * [2025-08] Introducing [CHORD](https://github.com/modelscope/Trinity-RFT/tree/main/examples/mix_chord): dynamic SFT + RL integration for advanced LLM fine-tuning ([paper](https://arxiv.org/pdf/2508.11408)).

README_zh.md

@@ -83,8 +83,8 @@ Trinity-RFT 是一个灵活、通用的大语言模型（LLM）强化微调（RF
 
 ## 🚀 新闻
 
-* [2025-11] 推出 [BOTS](https://github.com/modelscope/Trinity-RFT/tree/main/examples/bots)：在线RL任务选择，实现高效LLM微调（[论文](https://arxiv.org/pdf/2510.26374)）。
-* [2025-10] [[发布说明](https://github.com/modelscope/Trinity-RFT/releases/tag/v0.3.2)] Trinity-RFT v0.3.2 发布：修复若干 Bug 并支持进阶的任务选择和调度。
+* [2025-11] 推出 [BOTS](https://github.com/modelscope/Trinity-RFT/tree/main/examples/bots)：在线 RL 任务选择，实现高效 LLM 微调（[论文](https://arxiv.org/pdf/2510.26374)）。
+* [2025-11] [[发布说明](https://github.com/modelscope/Trinity-RFT/releases/tag/v0.3.2)] Trinity-RFT v0.3.2 发布：修复若干 Bug 并支持进阶的任务选择和调度。
 * [2025-10] [[发布说明](https://github.com/modelscope/Trinity-RFT/releases/tag/v0.3.1)] Trinity-RFT v0.3.1 发布：多阶段训练支持、改进的智能体 RL 示例、LoRA 支持、调试模式和全新 RL 算法。
 * [2025-09] [[发布说明](https://github.com/modelscope/Trinity-RFT/releases/tag/v0.3.0)] Trinity-RFT v0.3.0 发布：增强的 Buffer、FSDP2 & Megatron 支持，多模态模型，以及全新 RL 算法/示例。
 * [2025-08] 推出 [CHORD](https://github.com/modelscope/Trinity-RFT/tree/main/examples/mix_chord)：动态 SFT + RL 集成，实现进阶 LLM 微调（[论文](https://arxiv.org/pdf/2508.11408)）。

examples/bots/workflow/bots_math_boxed_workflow.py

@@ -19,12 +19,12 @@ def format_messages(self):
         return self.task_desc
 
     @property
-    def task_desc(self) -> Union[str, None]:
+    def task_desc(self) -> Union[str, None]:  # type: ignore [override]
         prompt_key = self.format_args.prompt_key
         return nested_query(prompt_key, self.raw_task)  # type: ignore
 
     @property
-    def truth(self) -> Union[str, None]:
+    def truth(self) -> Union[str, None]:  # type: ignore [override]
         response_key = self.format_args.response_key
         return nested_query(response_key, self.raw_task)
 

trinity/common/workflows/workflow.py

@@ -60,6 +60,18 @@ def to_workflow(
             auxiliary_models=auxiliary_models,
         )
 
+    # Deprecated property, will be removed in the future
+    @property
+    def task_desc(self) -> Union[str, None]:
+        prompt_key = self.format_args.prompt_key
+        return self.raw_task[prompt_key] if prompt_key in self.raw_task else None  # type: ignore
+
+    # Deprecated property, will be removed in the future
+    @property
+    def truth(self) -> Union[str, None]:
+        response_key = self.format_args.response_key
+        return self.raw_task[response_key] if response_key in self.raw_task else None  # type: ignore
+
     def to_dict(self) -> dict:
         return self.raw_task  # type: ignore