* Initial plan
* feat: add model_config parameter support for Dify assistant type
- Add model_config parameter to AsyncDifyServiceClient.chat_messages method
- Add _get_model_config helper method to DifyServiceAPIRunner
- Pass model_config from pipeline configuration to all chat_messages calls
- Add model-config configuration field to dify-service-api schema in ai.yaml
- Support optional model configuration for assistant type apps in open-source Dify
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
* refactor: improve model_config implementation based on code review
- Simplify _get_model_config method logic
- Add more descriptive comment about model_config usage
- Clarify when model_config is used (assistant type apps)
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
* feat: only modify client.py
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
Co-authored-by: Junyan Qin <rockchinq@gmail.com>
* fix: fix n8n streaming support issue
Add streaming support detection and proper message type handling for
n8n service API runner. Previously, when streaming was enabled, n8n
integration would fail due to incorrect message type usage.
1. Added streaming capability detection by checking adapter's
is_stream_output_supported method
2. Implemented conditional message generation using MessageChunk for
streaming mode and Message for non-streaming mode
3. Added proper error handling for adapters that don't support streaming
detection
* fix: add n8n webhook streaming model ,Optimized the streaming output when calling n8n.
---------
Co-authored-by: Dong_master <2213070223@qq.com>
- Replace plugin detail dialog with hover buttons interaction
- Add "Install" and "View Details" hover buttons on plugin cards
- Remove PluginDetailDialog component
- Update plugin marketplace URL format to /market/{author}/{plugin}
- Redirect all plugin detail views to LangBot Space
- Add i18n support for 4 languages (zh-Hans, en-US, zh-Hant, ja-JP)
- Optimize hover overlay styles for light/dark theme
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Initial plan
* Add package structure and resource path utilities
- Created langbot/ package with __init__.py and __main__.py entry point
- Added paths utility to find frontend and resource files from package installation
- Updated config loading to use resource paths
- Updated frontend serving to use resource paths
- Added MANIFEST.in for package data inclusion
- Updated pyproject.toml with build system and entry points
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
* Add PyPI publishing workflow and update license
- Created GitHub Actions workflow to build frontend and publish to PyPI
- Added license field to pyproject.toml to fix deprecation warning
- Updated .gitignore to exclude build artifacts
- Tested package building successfully
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
* Add PyPI installation documentation
- Created PYPI_INSTALLATION.md with detailed installation and usage instructions
- Updated README.md to feature uvx/pip installation as recommended method
- Updated README_EN.md with same changes for English documentation
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
* Address code review feedback
- Made package-data configuration more specific to langbot package only
- Improved path detection with caching to avoid repeated file I/O
- Removed sys.path searching which was incorrect for package data
- Removed interactive input() call for non-interactive environment compatibility
- Simplified error messages for version check
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
* Fix code review issues
- Use specific exception types instead of bare except
- Fix misleading comments about directory levels
- Remove redundant existence check before makedirs with exist_ok=True
- Use context manager for file opening to ensure proper cleanup
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
* Simplify package configuration and document behavioral differences
- Removed redundant package-data configuration, relying on MANIFEST.in
- Added documentation about behavioral differences between package and source installation
- Clarified that include-package-data=true uses MANIFEST.in for data files
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
* chore: update pyproject.toml
* chore: try pack templates in langbot/
* chore: update
* chore: update
* chore: update
* chore: update
* chore: update
* chore: adjust dir structure
* chore: fix imports
* fix: read default-pipeline-config.json
* fix: read default-pipeline-config.json
* fix: tests
* ci: publish pypi
* chore: bump version 4.6.0-beta.1 for testing
* chore: add templates/**
* fix: send adapters and requesters icons
* chore: bump version 4.6.0b2 for testing
* chore: add platform field for docker-compose.yaml
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
Co-authored-by: Junyan Qin <rockchinq@gmail.com>
* Initial plan
* feat: Add hover card with model details to embedding model selector in KB form
- Updated KBForm.tsx to fetch full EmbeddingModel objects instead of simplified entities
- Added HoverCard component to show model details (icon, description, base URL, extra args) when hovering over embedding model options
- Removed unused IEmbeddingModelEntity import and embeddingModelNameList state
- Made the embedding model selector consistent with LLM model selector behavior
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
* fix:Fixed the issue where the rich text processing in the DingTalk API did not account for multiple texts and images, as well as the presence of default line breaks. Also resolved the error in Dify caused by sending only images, which resulted in an empty query.
* fix:Considering the various possible scenarios, there are cases where plan_text is empty when there is file content, and there is no file (the message could not be parsed) and the content is empty.
* fix:Add the default modifiable prompt input for didify in the ai.yaml file to ensure that the error of query being empty occurs when receiving data.
* add: The config migration of Dify
* fix:Migration issue
* perf: minor fix
* chore: minor fix
---------
Co-authored-by: Junyan Qin <rockchinq@gmail.com>
