Add ralph-claude-code integration and agent documentation #131
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Reviewer's GuideAdds the ralph-claude-code integration to the project configuration and introduces comprehensive autonomous agent documentation and workflow standards, along with ignoring agent-related state/config files in version control. Flow diagram for Ralph status and EXIT_SIGNAL decision logicflowchart TD
A["Start end_of_loop_evaluation"] --> B["All tasks in fix_plan complete?"]
B -->|Yes| C["All requirements from specs implemented?"]
B -->|No| D["Any blocker detected (external dependency or recurring error)?"]
C -->|Yes| E["All tests passing or legitimately absent?"]
C -->|No| D
E -->|Yes| F["Set STATUS COMPLETE"]
E -->|No| G["Set STATUS IN_PROGRESS and TESTS_STATUS FAILING"]
F --> H["Set EXIT_SIGNAL true"]
H --> I["Emit RALPH_STATUS block with recommendation project ready for review"]
G --> J["Set EXIT_SIGNAL false"]
J --> K["Emit RALPH_STATUS block with recommendation continue fixing tests"]
D -->|Yes| L["Set STATUS BLOCKED"]
D -->|No| M["Set STATUS IN_PROGRESS"]
L --> N["Set EXIT_SIGNAL false"]
N --> O["Emit RALPH_STATUS with recommendation human intervention or wait for dependency"]
M --> P["Evaluate recent_loops_for_test_only_pattern"]
P -->|Test_only_pattern_detected| Q["Set WORK_TYPE TESTING and recommendation no implementation needed"]
P -->|Normal_progress| R["Set WORK_TYPE IMPLEMENTATION and recommendation continue next task"]
Q --> S["Set EXIT_SIGNAL false"]
R --> S
S --> T["Emit RALPH_STATUS block for ongoing work"]
File-Level Changes
Tips and commandsInteracting with Sourcery
Customizing Your ExperienceAccess your dashboard to:
Getting Help
|
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
There was a problem hiding this comment.
Hey - I've found 1 issue, and left some high level feedback:
- Consider whether
ralph-claude-codeshould be a dev-only or optional extra dependency rather than a mandatory runtime dependency inpyproject.toml, so that consumers of the template aren't forced to install agent tooling if they don't need it. - The agent instructions currently hard-code paths and assumptions like
/workspaces/pythontemplate; it may be more robust to parameterize or generalize these so the template remains accurate when cloned under different project names or directory structures.
Prompt for AI Agents
Please address the comments from this code review:
## Overall Comments
- Consider whether `ralph-claude-code` should be a dev-only or optional extra dependency rather than a mandatory runtime dependency in `pyproject.toml`, so that consumers of the template aren't forced to install agent tooling if they don't need it.
- The agent instructions currently hard-code paths and assumptions like `/workspaces/pythontemplate`; it may be more robust to parameterize or generalize these so the template remains accurate when cloned under different project names or directory structures.
## Individual Comments
### Comment 1
<location> `PROMPT.md:284` </location>
<code_context>
+## Existing Infrastructure
+- **Package manager**: pixi (conda-forge based)
+- **Testing**: pytest with coverage
+- **Linting**: ruff, pylint, ty
+- **CI/CD**: GitHub Actions
+- **Dev environment**: devcontainer support
</code_context>
<issue_to_address>
**question (typo):** Clarify or correct the `ty` tool name in the linting list.
The list currently says `ruff, pylint, ty`, but `ty` isn’t a standard Python linting or type-checking tool. If this is a typo (e.g., you meant `mypy` or `pyright`), please correct it; otherwise, add a brief note explaining what `ty` is.
Suggested implementation:
```
- **Linting/typing**: ruff, pylint, mypy
```
1. Confirm that `mypy` is indeed the tool used for type checking in this project (e.g., in `pyproject.toml`, `pixi` tasks, or CI workflows).
2. If a different tool is used (e.g., `pyright` or another checker), replace `mypy` in the updated line with the actual tool name to keep the documentation accurate.
</issue_to_address>Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.
- Clarify that ty is a type checker (not a typo) in PROMPT.md - Remove hardcoded path from @AGENT.md for template portability Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
ralph-claude-codedependency to pyproject.toml for autonomous agent capabilitiesTest plan
pixi installcompletes successfully with the new dependency🤖 Generated with Claude Code
Summary by Sourcery
Add autonomous AI agent support and guidance to the Python template project.
New Features:
Enhancements:
Build:
Chores: