Repository navigation
Roo Code Test of constitution Command Fails #782
Description
Roo Code Version: 3.28.15 (7734b29c)
VSC Version: 1.104.3 Mac
Test Method
Create a new project using a command similar to specify init sk4 --ai roo --script sh, then select different models to execute /speckit.constitution SOME DESCRIPTION with Roo Code. The situation is confusing:
-
GPT-5-Codex
constitution.md is modified successfully, but at the same time, three templates in .specify/templates are also modified. I'm not sure if the latter should be modified. If they should, it means there's redundant information in the specification file. If not, it indicates that this tool does not provide read-only protection for specific files, and its prompt has factual defects.
Additionally, in my test, I used a Chinese description, so constitution.md was modified to a state mixed with Chinese and English. I'm not sure if the modified language in the section titles will affect subsequent operations.
The process consumed 400k tokens, which was somewhat unexpected. -
Qwen3-Next-80B-A3B-Thinking
constitution.md was modified, with some content deleted, but none of the expected content was written. A total of four files in .specify/templates were modified in a similar manner.
The issue here is the same as with Claude and Qwen3 235B later: the project name and constitution requirements were not passed correctly. Since I had auto-approval enabled, the AI automatically chose to use blank values for replacement. -
Qwen3-Coder-30B-A3B-Instruct
Unable to complete the command -
Grok-Coder-Fast-1
Unable to complete the command -
Claude 4.5
After consuming 120k tokens, the model asked me to provide the project name, core principles, and whether I want to create a new file or update it. -
GPT-OSS-120B
Unable to complete the command -
Qwen3-235B-A22B-Instruct-2507
After consuming 180k tokens, similar to Claude, it asked for the project name and core principles.
Is this tool really adapted for Roo Code?
Furthermore, writing a project's constitution content is not a high-difficulty task. Logically speaking, even relatively weak models should be capable of handling it. I'm not sure if the failure above is due to the model, Roo Code, or Spec Kit itself, but I suggest adding recommended models in the README.
Activity
hiarcs commentedon Oct 8, 2025
GLM4.6, performing similarly to Codex, first updated all 5 template files and then constitution.md, consuming a total of 770k tokens.
During execution, despite explicitly including error handling strategies in constitution.md, when executing the /speckit.specify command, it still asked me what to do if an error was encountered. This is quite absurd. Furthermore, in the output document of the planning task, its designed behavior further deviated from the requirements set forth during the constitution and specification process.
4.5M tokens were consumed before the first source code file was even generated. By the time 7.5M tokens were consumed and the implementation was declared complete, the overall scope and implementation approach had significantly deviated from my original requirements.
clsferguson commentedon Oct 20, 2025
Real quick, the constitution command includes modifications to those 3 templates. So codex did it right. Have a look at the prompt to see.
niklasschaeffer commentedon Dec 8, 2025
@hiarcs Im observing the same pattern. It seems like the commands are very generic and not really tailored towards rooCode. It definetly needs more alignment with how roo actually works. Currently 4 out 5 tries any agent does not follow the instructions given. Best results so far i had was actually with gpt-5-mini weird enough.
SherifMEldeeb commentedon Apr 30, 2026
iam experiencing same behaviour any updates here?
using Clion IDE
mnriem commentedon May 1, 2026
If Roo Code requires more help feel free to create a preset that overloads the core commands to help it out
github-actions commentedon Sep 14, 2026
This issue has been automatically marked as stale because it has not had any activity for 60 days. It will be closed in 30 days if no further activity occurs.
yarcowang commentedon Sep 29, 2026
Hello, any updates?
I see this issue #3167, RooCode support was removed, but it has successor
ZooCodewhich I'm currently using. And I‘m also curious about how to integrate ZooCode with speckit.mnriem commentedon Sep 29, 2026
Thanks for following up. Roo Code support was retired after Roo Code shut down (#3167). ZooCode is a successor, but that doesn't mean the former Roo Code integration has been verified to work with it.
If you'd like to add ZooCode support to Spec Kit, a focused PR demonstrating ZooCode's command format and including tests and documentation would be welcome. We'd be glad to review it. That would be separate from confirming whether ZooCode addresses the constitution-command behavior originally reported here.
Posted on behalf of @mnriem with GitHub Copilot (GPT-6 Sol, interactive agent mode); AI drafted and posted this issue reply at the contributor's request.