Skip to content

release(v0.0.5): sync TokenHub language model catalog and remove offline models - #2827

Open
lws123321 wants to merge 6 commits into
langgenius:mainfrom
lws123321:main
Open

release(v0.0.5): sync TokenHub language model catalog and remove offline models#2827
lws123321 wants to merge 6 commits into
langgenius:mainfrom
lws123321:main

Conversation

@lws123321

Copy link
Copy Markdown
Contributor

Plugin Submission

Plugin information

Submission type

  • New plugin
  • Version update

What changed

This release realigns predefined language models with the official TokenHub model list.

Added

  • hy3 (with thinking toggle and reasoning effort)
  • hy-mt2-pro / hy-mt2-plus / hy-mt2-lite
  • hy-role
  • glm-5.2
  • kimi-k3, kimi-k2.7-code, kimi-k2.7-code-highspeed
  • qwen3.5-flash, qwen3.5-plus
  • mimo-v2.5-pro

Removed

  • Offline models: hy3-preview, minimax-m2.5
  • Delisted models: hunyuan-2.0-thinking-20251109, hunyuan-2.0-instruct-20251111, deepseek-v3.2, deepseek-v3.1-terminus, deepseek-r1-0528, deepseek-v3-0324

Also updated

  • _position.yaml order, thinking / reasoning-effort allowlists
  • Provider credential probe model (deepseek-v4-flash)
  • README / CHANGELOG for v0.0.5

No breaking API changes to existing model invocation behavior.

Risk level

  • Low risk
  • Medium risk
  • High risk

Low risk: the plugin only calls the fixed, documented Tencent TokenHub HTTPS OpenAI-compatible API and does not execute user-controlled code, commands, or SQL.

Required checks

  • I have read and followed the Marketplace submission requirements.
  • I have read and comply with the Plugin Developer Agreement.
  • I tested this plugin on Dify Community Edition and Dify Cloud, or documented any limitation below.
  • The package contains only files needed at runtime.
  • The package does not contain secrets, local credentials, .env files, .git directories, virtual environments, caches, logs, or IDE files.
  • The package does not contain executables or bundled binaries, or I explained why they are required below.
  • The plugin README includes setup steps, usage instructions, required APIs or credentials, connection requirements, and the source repository link.
  • The plugin includes PRIVACY.md or a hosted privacy policy, and manifest.yaml references it.
  • All user-facing text is primarily in English, with any localized README files following the i18n guidance.

Security and privacy notes

No new data collection. Requests are sent to Tencent TokenHub for inference. See PRIVACY.md.

Local validation

  • Packaged with dify plugin package as tencent-tokenhub-0.0.5.difypkg
  • Plugin starts in Dify without schema validation errors
  • Model list matches the new catalog; offline / delisted models are absent
  • Smoke-tested streaming chat on representative new models (hy3, glm-5.2, kimi-k3, qwen3.5-flash)
  • Verified thinking / reasoning_effort forwarding for supported models
  • Provider credential validation works with probe model deepseek-v4-flash
  • Customizable-model flow still works

Reviewer notes

Version update PR contains only the new .difypkg package for lws123321/tencent-tokenhub v0.0.5.

lws123321 added 4 commits June 3, 2026 11:42
Align predefined LLMs with the official TokenHub catalog: add Hy3/Qwen/Kimi/GLM/MiMo models, remove offline and delisted ones, and update allowlists/docs.
@github-actions github-actions Bot added the risk: low Low-risk Marketplace submission label Aug 6, 2026

@crazywoola crazywoola left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

❌ Request Changes

Decision: Request changes

Failed Checks

Check Status Detail Required action
README language ❌ Fail README.md CJK ratio=0.4% (zh=11, en=2586, allowed_zh<=0); Chinese characters are not allowed. Use multilingual README guidance: https://docs.dify.ai/en/develop-plugin/features-and-specs/plugin-types/multilingual-readme#multilingual-readme Remove Chinese characters from README.md and use the multilingual README pattern: https://docs.dify.ai/en/develop-plugin/features-and-specs/plugin-types/multilingual-readme#multilingual-readme

Full Check Results

Check Status Detail Required action
PR content language ✅ Pass PR title/body CJK ratio=0.0% (zh=0, en=2401, ignored_zh=0, allowed_zh<=0) None.
Project structure ✅ Pass All expected files present: manifest.yaml, README.md, PRIVACY.md. _assets/: yes. None.
Manifest author ✅ Pass author is valid. None.
Icon validation ✅ Pass icon exists: _assets/icon_s_en.svg None.
Version check ✅ Pass version 0.0.5 is available. None.
README language ❌ Fail README.md CJK ratio=0.4% (zh=11, en=2586, allowed_zh<=0); Chinese characters are not allowed. Use multilingual README guidance: https://docs.dify.ai/en/develop-plugin/features-and-specs/plugin-types/multilingual-readme#multilingual-readme Remove Chinese characters from README.md and use the multilingual README pattern: https://docs.dify.ai/en/develop-plugin/features-and-specs/plugin-types/multilingual-readme#multilingual-readme
PRIVACY.md ✅ Pass PRIVACY.md exists and is non-empty. None.
Dependency install ✅ Pass requirements installed successfully. None.
dify_plugin version ✅ Pass dify_plugin version 0.10.1 satisfies >= 0.9.0. None.
Install test ✅ Pass plugin install test passed. None.
Packaging test ✅ Pass packaging check passed. None.

Next steps

Please address these issues and push an update.

@lws123321
lws123321 requested a review from crazywoola August 7, 2026 01:55
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

risk: low Low-risk Marketplace submission

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants