2517bc112c
- Add OpenAI provider implementation using @ai-sdk/openai.\n- Update `models` command/tool to display API key status for configured providers.\n- Implement model-specific `maxTokens` override logic in `config-manager.js` using `supported-models.json`.\n- Improve AI error message parsing in `ai-services-unified.js` for better clarity.
12 lines
1.8 KiB
Plaintext
12 lines
1.8 KiB
Plaintext
# Task ID: 70
|
|
# Title: Implement 'diagram' command for Mermaid diagram generation
|
|
# Status: pending
|
|
# Dependencies: None
|
|
# Priority: medium
|
|
# Description: Develop a CLI command named 'diagram' that generates Mermaid diagrams to visualize task dependencies and workflows, with options to target specific tasks or generate comprehensive diagrams for all tasks.
|
|
# Details:
|
|
The task involves implementing a new command that accepts an optional '--id' parameter: if provided, the command generates a diagram illustrating the chosen task and its dependencies; if omitted, it produces a diagram that includes all tasks. The diagrams should use color coding to reflect task status and arrows to denote dependencies. In addition to CLI rendering, the command should offer an option to save the output as a Markdown (.md) file. Consider integrating with the existing task management system to pull task details and status. Pay attention to formatting consistency and error handling for invalid or missing task IDs. Comments should be added to the code to improve maintainability, and unit tests should cover edge cases such as cyclic dependencies, missing tasks, and invalid input formats.
|
|
|
|
# Test Strategy:
|
|
Verify the command functionality by testing with both specific task IDs and general invocation: 1) Run the command with a valid '--id' and ensure the resulting diagram accurately depicts the specified task's dependencies with correct color codings for statuses. 2) Execute the command without '--id' to ensure a complete workflow diagram is generated for all tasks. 3) Check that arrows correctly represent dependency relationships. 4) Validate the Markdown (.md) file export option by confirming the file format and content after saving. 5) Test error responses for non-existent task IDs and malformed inputs.
|