Repository navigation
Update Wally to 0.0.4: model catalog - #3519
Merged
Merged
Conversation
crazywoola
approved these changes
Oct 27, 2026
crazywoola
left a comment
Member
There was a problem hiding this comment.
Pre Check Plugin and PR Risk Label passed for this revision. Inspected the submitted package, documentation, and relevant source; this is a non-draft plugin submission with no Web3 functionality identified. This is an eligibility review, not a comprehensive security audit.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Plugin Submission
Plugin information
Submission type
What changed
Updates the model list to what Wally serves today. Removes MiMo V2.6 Flash (
mimo-v2.6-flash) and adds Kimi K3 (kimi-k3), DeepSeek V4.1 Flash (Fast) (deepseek-v4.1-flash-fast), GLM-5.3 (Fast) (glm-5.3-fast), DeepSeek V4 Pro (Fast) (deepseek-v4-pro-fast), DeepSeek V4 Flash 0731 (deepseek-v4-flash-0731) and MiniMax M3 (minimax-m3), for eight models. Context, max output, image input and prices now followGET /v1/models: GLM-5.3 Flash is text only, and GLM-5.3 Flash and DeepSeek V4.1 Flash have new prices. The thinking toggle is replaced by a per-model Reasoning effort select with the levels each model accepts;none(thinking off) is offered only on models that can turn thinking off. The endpoint and the icon are unchanged.Breaking changes: apps that use
mimo-v2.6-flashneed another model, and apps that had the Thinking mode toggle off should set Reasoning effort tonone.Risk level
Required checks
.envfiles,.gitdirectories, virtual environments, caches, logs, or IDE files.PRIVACY.mdor a hosted privacy policy, andmanifest.yamlreferences it.Security and privacy notes
None of the listed sensitive capabilities.
The plugin sends prompts, messages, tool definitions and results, and attached images to one fixed endpoint,
https://inference.runanywhere.ai/v1, authenticated with the user's Wally API key. That is why this is marked Medium risk. The plugin stores and logs nothing itself. This update adds no new external service or capability.Local validation
dify plugin package(dify-plugin-daemon CLI v0.6.10): packaged successfully, 22 files.python3 validator/validate-difypkg.py wally-0.0.4.difypkg --pr-body-file <this body>(dify-marketplace-toolkit): 0 blocking failures.validator/test-plugin-install.pyagainst the unpacked package (serverless mode):Plugin test result: success.Reviewer notes
Limitation: not run end to end inside a Dify Community Edition or Dify Cloud instance. The plugin's model class was run against the live API for all eight models.