docs: update for PR #1723 — async scheduler migration + contextvars singleton replacement by MervinPraison · Pull Request #456 · MervinPraison/PraisonAIDocs

MervinPraison · 2026-05-30T06:24:27Z

Summary

Updates documentation to reflect the architectural changes introduced in PraisonAI PR #1723 which eliminated wrapper layer gaps through:

Async scheduler migration to canonical praisonai.scheduler package
Global singleton replacement with contextvars for multi-agent safety
Import path updates and deprecation status changes

Changes Made

📝 Documentation Updates

async-agent-scheduler.mdx: Updated all import paths from deprecated praisonai.async_agent_scheduler to canonical praisonai.scheduler import AsyncAgentScheduler
async-scheduler.mdx: Removed duplicate page and docs.json entry (consolidated into async-agent-scheduler.mdx)
tool-resolver.mdx: Added per-context resolver documentation with reset_default_resolver() function
thread-safety.mdx: Added multi-agent context safety section covering PR #1723 contextvars changes
multi-agent-context-safety.mdx: New comprehensive guide for contextvars-based multi-agent patterns

🔧 Technical Changes

Updated deprecation warnings from PendingDeprecationWarning to DeprecationWarning
Documented context-local default resolver behavior (eliminates first-caller-CWD-wins bug)
Added reset_default_resolver() documentation for daemon/IDE plugin use cases
Updated docs.json navigation structure

Verification

All verification checklist items from issue #443 completed:

✅ All from praisonai.async_agent_scheduler import updated to canonical imports
✅ Deprecation status changed from "pending" to active
✅ tool-resolver.mdx updated to reflect per-context behavior
✅ reset_default_resolver() documented with import path and examples
✅ thread-safety.mdx mentions PR #1723's contextvars switch
✅ docs.json validated as valid JSON
✅ Removed async-scheduler.mdx and its docs.json entry
✅ New page added to docs/features/ (not docs/concepts/)

…ingleton replacement - Update async-agent-scheduler.mdx with canonical import paths (praisonai.scheduler) - Update deprecation status from PendingDeprecationWarning to DeprecationWarning - Remove duplicate async-scheduler.mdx and docs.json entry (consolidation) - Add per-context resolver documentation to tool-resolver.mdx with reset_default_resolver() - Add multi-agent context safety section to thread-safety.mdx covering PR #1723 changes - Create new multi-agent-context-safety.mdx with comprehensive contextvars guidance - Update docs.json navigation to include new page in Safety & Control section All import paths updated from deprecated praisonai.async_agent_scheduler to canonical praisonai.scheduler imports. Documentation now reflects contextvars-based per-context runtime and resolver state for safe concurrent agent operations. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>

qodo-code-review · 2026-05-30T06:24:30Z

Qodo reviews are paused for this user.

Troubleshooting steps vary by plan Learn more →

On a Teams plan?
Reviews resume once this user has a paid seat and their Git account is linked in Qodo.
Link Git account →

Using GitHub Enterprise Server, GitLab Self-Managed, or Bitbucket Data Center?
These require an Enterprise plan - Contact us
Contact us →

coderabbitai · 2026-05-30T06:24:33Z

Warning

Review limit reached

@MervinPraison, we couldn't start this review because you've reached your PR review rate limit.

More reviews will be available in 41 minutes and 59 seconds. Learn how PR review limits work.

Your organization has run out of usage credits. Purchase more in the billing tab.

⌛ How to resolve this issue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

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 include higher PR review limits than trial, open-source, and free plans. In all cases, reviews become available again over time. During sustained high-volume PR review activity, CodeRabbit may temporarily slow when the next review becomes available.

Please see our Fair Usage Limits Policy for further information.

ℹ️ Review info

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: 1a96e9db-e8a6-4a1f-b8e9-11d6e20fd514

📥 Commits

Reviewing files that changed from the base of the PR and between ad3daba and 3723c33.

📒 Files selected for processing (6)

docs.json
docs/features/async-agent-scheduler.mdx
docs/features/async-scheduler.mdx
docs/features/multi-agent-context-safety.mdx
docs/features/thread-safety.mdx
docs/features/tool-resolver.mdx

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Commit unit tests in branch claude/issue-443-20260530-0617

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.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

gemini-code-assist

Code Review

This pull request updates the documentation to introduce multi-agent context safety, per-context tool resolvers, and updated import paths for the async agent scheduler. However, the review feedback highlights critical discrepancies where the documented features—such as reset_default_resolver, context-local _get_shared_runtime(), _get_default_resolver(), and cleanup_runtime()—are not yet implemented in the codebase, which would result in import errors and state-sharing bugs.

gemini-code-assist · 2026-05-30T06:25:49Z

+### `reset_default_resolver()`
+
+| | |
+|---|---|
+| **When to call** | Daemons or IDE plugins that switch the working directory between projects |
+| **What it does** | Clears the cached `ToolResolver` in the current context so the next call re-anchors to the new CWD |
+| **Import** | `from praisonai.tool_resolver import reset_default_resolver` |


The function reset_default_resolver is documented here as being imported from praisonai.tool_resolver, but it is currently missing from praisonai/tool_resolver.py in the codebase. This will cause an ImportError when users attempt to import and call it. Please ensure the implementation in praisonai/tool_resolver.py is updated to export this function.

gemini-code-assist · 2026-05-30T06:25:49Z

+### Multi-agent context safety (PR #1723)
+
+`praisonai.cli.features.interactive_tools._get_shared_runtime()` and `praisonai.tool_resolver._get_default_resolver()` were previously process-wide singletons. They are now **per-context** via `contextvars.ContextVar`:
+
+- Concurrent agents in the same process no longer share an `InteractiveRuntime` (no LSP/ACP config bleed).
+- Resolvers anchor to each agent's CWD, not whichever agent ran first.
+- For long-lived daemons that switch projects, call `praisonai.tool_resolver.reset_default_resolver()` to force re-anchoring.


The documentation states that _get_shared_runtime() and _get_default_resolver() are now per-context via contextvars.ContextVar. However, in the codebase (praisonai/cli/features/interactive_tools.py and praisonai/tool_resolver.py), these are still implemented as process-wide singletons using global variables. The implementation needs to be updated to use contextvars.ContextVar to match this documentation.

gemini-code-assist · 2026-05-30T06:25:49Z

+<Accordion title="Use context-local cleanup functions">
+When cleaning up resources, use the context-local versions that only affect the current agent's context.
+
+```python
+from praisonai.cli.features.interactive_tools import cleanup_runtime
+
+async def agent_task():
+    agent = Agent(name="TempAgent", instructions="Temporary task")
+    try:
+        result = await agent.astart("Do something")
+        return result
+    finally:
+        cleanup_runtime()  # Only cleans up this context's runtime
+```


The documentation describes cleanup_runtime() as context-local, only cleaning up the current context's runtime. However, the implementation in praisonai/cli/features/interactive_tools.py uses global variables (_shared_runtime and _shared_agent_tools) and shuts down the shared runtime globally. If concurrent agents are running, calling cleanup_runtime() in one agent will prematurely terminate the runtime for all other agents. The implementation should be updated to use contextvars to ensure context-local safety as documented.

Copilot

Copilot encountered an error and was unable to review this pull request. You can try again by re-requesting a review.

Copilot AI review requested due to automatic review settings May 30, 2026 06:24

Copilot started reviewing on behalf of MervinPraison May 30, 2026 06:24 View session

MervinPraison mentioned this pull request May 30, 2026

docs: update for PR #1723 — async scheduler migration + contextvars singleton replacement #443

Open

8 tasks

gemini-code-assist Bot reviewed May 30, 2026

View reviewed changes

Copilot AI reviewed May 30, 2026

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

docs: update for PR #1723 — async scheduler migration + contextvars singleton replacement#456

docs: update for PR #1723 — async scheduler migration + contextvars singleton replacement#456
MervinPraison wants to merge 1 commit into
mainfrom
claude/issue-443-20260530-0617

MervinPraison commented May 30, 2026

Uh oh!

qodo-code-review Bot commented May 30, 2026

Uh oh!

coderabbitai Bot commented May 30, 2026

Review limit reached

Uh oh!

gemini-code-assist Bot left a comment

Uh oh!

gemini-code-assist Bot May 30, 2026

Uh oh!

gemini-code-assist Bot May 30, 2026

Uh oh!

gemini-code-assist Bot May 30, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

MervinPraison commented May 30, 2026

Summary

Changes Made

📝 Documentation Updates

🔧 Technical Changes

Verification

Related

Uh oh!

qodo-code-review Bot commented May 30, 2026

Qodo reviews are paused for this user.

Uh oh!

coderabbitai Bot commented May 30, 2026

Review limit reached

Uh oh!

gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

gemini-code-assist Bot May 30, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist Bot May 30, 2026

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist Bot May 30, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants