[GitHub Dev Team Sample] Revisit Flow of working with dozens of Issues in GitHub
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 25/100
- Issue type
- Feature
- Clarity
- Needs clarification
- Activity status
- Stale
- Tech stack
- csharp, github
- Domain
- developer-experience, tooling
Research direction
The issue does not name files, tests, or entry points to change. Start by tracing how the repository currently creates and updates GitHub Issues, comments, labels, branches, and pull requests, then compare that behavior with the proposed workflow; done would require an agreed design and implementation scope.
Written by the indexing model from the issue text.
Description
Is a Project Manager and Software Engineer, I find the flow of opening dozens of GitHub Issues for the single tasks of the agent very unintuitive and confusing. Especially, as it does not reflect what humans would do. In addition, I think it's weird that the agents post the code they want to generate as comments to a GitHub issue instead of opening a Pull Request, where code can be properly discussed. Lastly, closing issues before the actual work on them is done also looks like a bad practice to me.
Here is, how an ideal flow would look like to me:
- Human Project Manager opens a GitHub issue with a description of what to achieve
- Human Project Manager labels the issue with
dev-agentslabel, to trigger the AI work - First Agents starts the work and describes the project plan in Markdown as a comment to the issue
- Human Project Manager can give feedback and iterate on it in the comments.
- Once satisfied, the issue get labeled differently (e.g.
coding-plan), which triggers another Agent to plan the coding work - An Agent generates the step-by-step plan (To Do List) and posts it as a comment to the issue
- Human Project Manager can give feedback and iterate on it in the comments.
- Once satisfied, the issue gets labeled again (e.g.
start-coding), which triggers another Agent to start the coding work - An Agent creates a new branch, commits code and creates a Pull Request, with the code changes and links the PR to the issue
- Human Developer can give feedback on the code and iterate on it in the PR comment.
- Once satisfied, the PR gets merged and the Issue automatically gets closed
Am I missing anything, why the flow is not like this but happens across so many issues?
Am I misunderstanding anything, which makes my suggested flow not possible?
- Dominant language
- C#
- Stars
- 307
- Forks
- 61
- Avg merge
- 19h 26m
- Merged PRs (30d)
- 1
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from microsoft/project-oagents
-
Difficulty 1/5 Under an hour Newbie friendliness 45/100
microsoft/project-oagents#101 ·
-
Difficulty 1/5 Under an hour Newbie friendliness 35/100
microsoft/project-oagents#100 ·
-
microsoft/project-oagents#76 · 1 comment · 1 assignee ·
-
microsoft/project-oagents#72 · 1 reaction · 1 assignee ·
-
Difficulty 5/5 Over a week Newbie friendliness 25/100
microsoft/project-oagents#69 ·
All issues in microsoft/project-oagents
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 86/100
-
:watch: Not Triaged 11.0 fundamentals/subsvc
Difficulty 2/5 1-3 hours Newbie friendliness 92/100
dotnet/AspNetCore.Docs#37699 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
SubtitleEdit/subtitleedit#15108 · 1 comment ·
-
area/docs-content Bug pulumi/docs
Difficulty 1/5 1-3 hours Newbie friendliness 94/100
-
agentic-workflows untriaged
Difficulty 2/5 1-3 hours Newbie friendliness 76/100