[PR #31689] refactor(model): Refactor plugin model schema cache to be process-global to prevent redundant Daemon API calls #33353

Closed
opened 2026-02-21 20:53:08 -05:00 by yindo · 0 comments
Owner

Original Pull Request: https://github.com/langgenius/dify/pull/31689

State: closed
Merged: Yes


Important

  1. Make sure you have read our contribution guidelines
  2. Ensure there is an associated issue and you have been assigned to it
  3. Use the correct syntax to link this PR: Fixes #<issue number>.

Summary

Currently, plugin_model_schemas is implemented using RecyclableContextVar. This causes the cache to be reset with every request (or thread recycle), rendering it ineffective for cross-request caching. As a result, the system re-fetches the model schema from the Plugin Daemon for every single API request, leading to unnecessary network overhead and latency.

This refactor transitions the plugin_model_schemas caching mechanism to a distributed Redis-based storage. By leveraging Redis, model schemas are now cached across multiple processes and instances, persisting according to a configurable Time-To-Live (TTL) which defaults to 24 hours. This significantly reduces redundant internal Plugin Daemon API calls and enhances the system's scalability.

Screenshots

Before After
Clipboard_Screenshot_1769569761 Clipboard_Screenshot_1769570075

Checklist

  • This change requires a documentation update, included: Dify Document
  • I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
  • I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
  • I've updated the documentation accordingly.
  • I ran make lint and make type-check (backend) and cd web && npx lint-staged (frontend) to appease the lint gods

#31627

**Original Pull Request:** https://github.com/langgenius/dify/pull/31689 **State:** closed **Merged:** Yes --- > [!IMPORTANT] > > 1. Make sure you have read our [contribution guidelines](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) > 1. Ensure there is an associated issue and you have been assigned to it > 1. Use the correct syntax to link this PR: `Fixes #<issue number>`. ## Summary Currently, `plugin_model_schemas` is implemented using `RecyclableContextVar`. This causes the cache to be reset with every request (or thread recycle), rendering it ineffective for cross-request caching. As a result, the system re-fetches the model schema from the Plugin Daemon for every single API request, leading to unnecessary network overhead and latency. This refactor transitions the plugin_model_schemas caching mechanism to a distributed Redis-based storage. By leveraging Redis, model schemas are now cached across multiple processes and instances, persisting according to a configurable Time-To-Live (TTL) which defaults to 24 hours. This significantly reduces redundant internal Plugin Daemon API calls and enhances the system's scalability. ## Screenshots | Before | After | |--------|-------| | <img width="400" height="200" alt="Clipboard_Screenshot_1769569761" src="https://github.com/user-attachments/assets/83babe77-9b9c-4fe9-a6c9-aa65c44765c4" /> | <img width="400" height="200" alt="Clipboard_Screenshot_1769570075" src="https://github.com/user-attachments/assets/630118da-9187-4a7c-be19-6b6bffcfb023" />| ## Checklist - [ ] This change requires a documentation update, included: [Dify Document](https://github.com/langgenius/dify-docs) - [x] I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!) - [x] I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change. - [x] I've updated the documentation accordingly. - [x] I ran `make lint` and `make type-check` (backend) and `cd web && npx lint-staged` (frontend) to appease the lint gods #31627
yindo added the pull-request label 2026-02-21 20:53:08 -05:00
yindo closed this issue 2026-02-21 20:53:08 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#33353