fix

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Fix MTHDS bundles

修复MTHDS包

Automatically fix issues in MTHDS method bundles.

自动修复MTHDS方法包中的问题。

Process

流程

Prerequisite: See CLI Prerequisites

前提条件：查看CLI 前提条件

Step 1: Validate and Identify Errors

步骤1：验证并识别错误

Always use

-L

pointing to the bundle's own directory to avoid namespace collisions:

bash

mthds-agent pipelex validate <file>.mthds -L <bundle-directory>/

Parse the JSON output:

If
```
success: true
```
— nothing to fix, report clean status

error_type: "ValidateBundleError"

— iterate through

validation_errors

array and fix each (Step 2)

If model/config error — see Error Handling Reference (cannot be fixed by editing the .mthds file)

始终使用

-L

指向包自身的目录，以避免命名空间冲突：

bash

mthds-agent pipelex validate <file>.mthds -L <bundle-directory>/

解析JSON输出：

如果
```
success: true
```
— 无需修复，报告状态正常

如果

error_type: "ValidateBundleError"

— 遍历

validation_errors

数组并逐个修复（步骤2）

如果是模型/配置错误 — 查看错误处理参考（无法通过编辑.mthds文件修复）

Step 2: Fix .mthds Validation Errors

步骤2：修复.mthds验证错误

Use the

error_type

field from each validation error to determine the fix:

Error Type	Fix Strategy
`missing_input_variable`	Add the missing variable(s) to the parent pipe's `inputs` line
`extraneous_input_variable`	Remove the unused variable(s) from the pipe's `inputs` line
`input_stuff_spec_mismatch`	Correct the concept type in `inputs` to match what the sub-pipe expects
`inadequate_output_concept`	Change the `output` field to the correct concept type
`inadequate_output_multiplicity`	Add or remove `[]` from the output concept
`circular_dependency_error`	Restructure the method to break the cycle
`llm_output_cannot_be_image`	Use PipeImgGen instead of PipeLLM for image generation
`img_gen_input_not_text_compatible`	Ensure PipeImgGen input is text-based (use `ImgGenPrompt` )
`invalid_pipe_code_syntax`	Rename the pipe to valid snake_case
`unknown_concept`	Add the concept definition to the bundle, or fix the typo
`batch_item_name_collision`	Rename `input_item_name` (or `batch_as` ) to a distinct singular form of the list name. Also update the branch pipe's `inputs` to use the new item name.

For error type descriptions, see Error Handling — Validation Error Types.

使用每个验证错误中的

error_type

字段确定修复方案：

错误类型	修复策略
`missing_input_variable`	将缺失的变量添加到父管道的 `inputs` 行中
`extraneous_input_variable`	从管道的 `inputs` 行中移除未使用的变量
`input_stuff_spec_mismatch`	修正 `inputs` 中的概念类型，使其与子管道的预期一致
`inadequate_output_concept`	将 `output` 字段修改为正确的概念类型
`inadequate_output_multiplicity`	为输出概念添加或移除 `[]`
`circular_dependency_error`	重构方法以打破循环依赖
`llm_output_cannot_be_image`	使用PipeImgGen而非PipeLLM进行图像生成
`img_gen_input_not_text_compatible`	确保PipeImgGen的输入为文本格式（使用 `ImgGenPrompt` ）
`invalid_pipe_code_syntax`	将管道重命名为有效的蛇形命名法（snake_case）
`unknown_concept`	向包中添加概念定义，或修正拼写错误
`batch_item_name_collision`	将 `input_item_name` （或 `batch_as` ）重命名为列表名称的独特单数形式。同时更新分支管道的 `inputs` 以使用新的项名称。

有关错误类型的说明，请查看错误处理 — 验证错误类型。

Step 3: Fix TOML Formatting Issues

步骤3：修复TOML格式问题

These aren't always reported by validation but cause problems:

Multi-line inputs — must be on a single line:

toml

undefined

这些问题并非总会被验证工具报告，但会引发异常：

多行输入 — 必须放在单行中：

toml

undefined

WRONG

错误示例

inputs = { a = "A", b = "B" }

CORRECT

正确示例

inputs = { a = "A", b = "B" }


**Pipe ordering** — controllers before sub-pipes:
```toml

inputs = { a = "A", b = "B" }


**管道顺序** — 控制器管道优先于子管道：
```toml

CORRECT: main pipe first, then sub-pipes in execution order

正确示例：主管道在前，子管道按执行顺序排列

[pipe.main_workflow] type = "PipeSequence" steps = [ { pipe = "step_one", result = "intermediate" }, { pipe = "step_two", result = "final" } ]

[pipe.step_one] ...

[pipe.step_two] ...


**Missing required fields** — add with sensible defaults:
- `description` on every pipe and concept
- `type` on every pipe
- `output` on every pipe

[pipe.main_workflow] type = "PipeSequence" steps = [ { pipe = "step_one", result = "intermediate" }, { pipe = "step_two", result = "final" } ]

[pipe.step_one] ...

[pipe.step_two] ...


**缺失必填字段** — 添加合理的默认值：
- 每个管道和概念都要有`description`
- 每个管道都要有`type`
- 每个管道都要有`output`

Step 4: Re-validate

步骤4：重新验证

After applying fixes, re-validate:

bash

mthds-agent pipelex validate <file>.mthds -L <bundle-directory>/

Continue the fix-validate loop until

success: true

is returned. Some fixes reveal new issues — for example, fixing a

missing_input_variable

may expose an

input_stuff_spec_mismatch

on the newly added input.

If the fix-validate loop gets stuck or errors are unclear, re-run with

--log-level debug

for additional context:

bash

mthds-agent --log-level debug pipelex validate <file>.mthds -L <bundle-directory>/

应用修复后，重新验证：

bash

mthds-agent pipelex validate <file>.mthds -L <bundle-directory>/

重复“修复-验证”循环，直到返回

success: true

。部分修复可能会暴露新问题 — 例如，修复

missing_input_variable

可能会在新添加的输入上暴露

input_stuff_spec_mismatch

。

如果“修复-验证”循环陷入停滞或错误不明确，使用

--log-level debug

重新运行以获取更多上下文：

bash

mthds-agent --log-level debug pipelex validate <file>.mthds -L <bundle-directory>/

Step 5: Report Results

步骤5：报告结果

List all changes made (which pipes were modified and how)
Show the final validation result
Flag any remaining warnings or suggestions

列出所有已做的更改（修改了哪些管道以及修改方式）
展示最终的验证结果
标记任何剩余的警告或建议

Reference

参考资料

CLI Prerequisites — read at skill start to check CLI availability
Error Handling — read when CLI returns an error to determine recovery
MTHDS Agent Guide — read for CLI command syntax or output format details
MTHDS Language Reference — read when writing or modifying .mthds TOML syntax
Native Content Types — read when fixing type mismatches involving native concepts, to verify available attributes

CLI 前提条件 — 技能启动时阅读，检查CLI可用性
错误处理 — 当CLI返回错误时阅读，以确定恢复方案
MTHDS Agent 指南 — 阅读以了解CLI命令语法或输出格式细节
MTHDS 语言参考 — 编写或修改.mthds TOML语法时阅读
原生内容类型 — 修复涉及原生概念的类型不匹配问题时阅读，以验证可用属性