Guess

你可以试试用[增量开发功能](https://docs.deepwisdom.ai/main/en/guide/in_depth_guides/incremental_development.html)来修这个bug。 不过我更推荐你使用[Data Interpreter模式](https://docs.deepwisdom.ai/main/en/guide/use_cases/agent/interpreter/intro.html)来解决这种非SOP场景。软件公司SOP是一个用来展示MetaGPT框架能力的示例，但实际上软件开发流程并不是一个SOP场景。

Sorry, I don't quite understand what the `SoftwareDev dataset` is used for. To avoid any misunderstanding, could you please describe it in detail?

The SoftwareDev related to the MetaGPT paper is not open to the public. After the release of MetaGPT 1.0 and MGX, we will open an open-source version similar to SoftwareDev.

qianfan模型代码是这个`metagpt/provider/qianfan_api.py`。 是模型调不通还是说扣费结算问题？ 如果是扣费结算问题，可以在`metagpt/utils/token_counter.py`中添加： ```python """ QianFan Token Price https://cloud.baidu.com/doc/WENXINWORKSHOP/s/hlrk4akp7#tokens%E5%90%8E%E4%BB%98%E8%B4%B9 Due to QianFan has multi price strategies, we unify `Tokens post-payment` as a statistical method. """ QIANFAN_MODEL_TOKEN_COSTS = { "ERNIE-Bot-4": {"prompt":...

The code you submitted needs a modification in one place：[#37](https://github.com/xiaoxiaoimg/MetaGPT/pull/37)

I've consolidated all the incremental development-related issues into #1498 to make it easier to follow up. Any new issues will be discussed in this newly opened issue, and the old...

```python class Action(SerializationMixin, ContextMixin, BaseModel): model_config = ConfigDict(arbitrary_types_allowed=True) name: str = "" i_context: Union[ dict, CodingContext, CodeSummarizeContext, TestingContext, RunCodeContext, CodePlanAndChangeContext, str, None ] = "" prefix: str = "" #...

[https://docs.deepwisdom.ai/](https://docs.deepwisdom.ai/), not `https://www.deepwisdom.ai/` You can visit it from [README](https://github.com/geekan/MetaGPT)

MetaGPT has two modes: SOP and Data Interpreter mode. SOP is a kind of waterfall model. The software company you use is an example of SOP. The applicable scenario for...

你应该传`prompt`，而不是那两个参数。 整个MetaGPT框架，agent之间、action之间都是传message。