docs: Document workspace sandboxing, self-improving skills, and expanded bot default tools#234
docs: Document workspace sandboxing, self-improving skills, and expanded bot default tools#234MervinPraison wants to merge 1 commit intomainfrom
Conversation
…ded bot default tools (fixes #232) - Add comprehensive documentation for workspace sandboxing with security by construction - Document self-improving skill management with runtime creation/editing capabilities - Cover 20+ auto-injected bot default tools and smart filtering - Add todo planning tools for multi-step task management - Document file editing tools with fuzzy find-and-replace - Update existing skills.mdx with runtime skill management section - All pages follow AGENTS.md standards with agent-centric examples and Mermaid diagrams 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
|
Warning Rate limit exceeded
Your organization is not enrolled in usage-based pricing. Contact your admin to enable usage-based pricing to continue reviews beyond the rate limit, or try again in 42 minutes and 41 seconds. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (7)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces documentation for several new features, including workspace sandboxing, bot default tools, file editing, todo planning, and runtime skill management. Feedback highlights a spelling inconsistency in the skill management guide, missing methods in the documented SkillManager API, and a type mismatch for todo IDs in the planning examples.
| tools=["skill_manage", "skills_list", "skill_view"] # auto-injected in bots | ||
| ) | ||
|
|
||
| agent.start("Create a skill called 'weekly-summary' that summarises the week's work.") |
There was a problem hiding this comment.
The documentation uses British spelling ("summarises") here, but American spelling ("summarize") is used consistently throughout the rest of the documentation (e.g., lines 156, 159, 178). It is recommended to use American spelling for consistency.
agent.start("Create a skill called 'weekly-summary' that summarizes the week's work.")
| result = mgr.create_skill("weekly-summary", "# Weekly Summary\nSteps...", category="reporting") | ||
|
|
||
| # Edit existing skills | ||
| result = mgr.edit_skill("weekly-summary", "# Weekly Summary v2\n...") | ||
|
|
||
| # Apply targeted patches | ||
| result = mgr.patch_skill("weekly-summary", old_string="v2", new_string="v3") | ||
|
|
||
| # Manage skill files | ||
| result = mgr.write_skill_file("weekly-summary", "scripts/report.py", "print('Weekly report')") | ||
| result = mgr.remove_skill_file("weekly-summary", "scripts/report.py") | ||
|
|
||
| # Delete skills | ||
| result = mgr.delete_skill("weekly-summary") |
There was a problem hiding this comment.
The Python API examples for SkillManager refer to several methods that are not present in the implementation provided in praisonaiagents/skills/manager.py. Specifically, create_skill, edit_skill, patch_skill, write_skill_file, remove_skill_file, and delete_skill are missing from the class definition. This will cause runtime errors for users attempting to use these methods.
| todo_update(1, status="pending") # Default state | ||
| todo_update(2, status="completed") # Task finished | ||
| todo_update(3, status="cancelled") # Task abandoned |
There was a problem hiding this comment.
The examples use integers (e.g., 1, 2, 3) as todo_id values. However, the TodoItem class in praisonaiagents/planning/todo.py (line 43) defines the id as a string (a truncated UUID). The documentation should be updated to use string IDs to match the implementation.
todo_update("1", status="pending") # Default state
todo_update("2", status="completed") # Task finished
todo_update("3", status="cancelled") # Task abandoned
Fixes #232
This PR implements comprehensive documentation for the major features introduced in PraisonAI PR #1503:
All documentation follows AGENTS.md standards with agent-centric examples, Mermaid diagrams, and Mintlify components.
Generated with Claude Code