Commit Graph

18 Commits

Author SHA1 Message Date
fdc310 d1ee5f931a chore(deps): update dashscope version to 1.25.10 in pyproject.toml (#1951)
feat: enable thinking feature in DashScopeAPIRunner for improved conversation handling
2026-01-31 20:31:37 +08:00
fdc310 2f06321ebf fix: Fix the file URL processing logic to support complete URLs (#1950) 2026-01-31 20:30:46 +08:00
Guanchao Wang 5d9f6ec763 Feat/monitor (#1928)
* feat: add monitor

* feat: fix tab

* feat: work

* feat: not reliable monitor

* feat: enhance monitoring page layout with integrated filters and refresh button

* feat: add support for runner recording

* feat: add jump button & alignment

* feat: new

* fix: not show query variables in local agent

* fix: pnpm lint and python ruff check

* fix: ruff fromat

* chore: remove unnecessary migration

* style: optimize monitoring page layout and fix sticky filter issues

- Enhanced metric cards with gradient backgrounds and hover effects
- Increased traffic chart height from 200px to 300px
- Adjusted grid layout and spacing for better visual appeal
- Fixed sticky filter area to properly cover parent padding without transparent gaps
- Used negative margins and positioning to eliminate scrolling artifacts
- Matched padding/margins with other pages (pipelines, bots) for consistency
- Removed duplicate title/subtitle from page content
- Added cursor-pointer styling to tab triggers
- Removed border between tab list and tab content

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

* fix: apply prettier formatting to monitoring components

- Fixed indentation and spacing in MetricCard.tsx
- Fixed formatting in TrafficChart.tsx
- Applied prettier formatting to page.tsx

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

* feat: update HomeSidebar to trigger action on child selection and localize monitoring titles

* refactor: streamline LLM and embedding invocation methods

* feat: add embedding model monitor

* fix: database version

* chore: simplify pnpm-lock.yaml formatting

---------

Co-authored-by: Junyan Qin <rockchinq@gmail.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-01-26 21:08:23 +08:00
Junyan Qin (Chin) fc6e414be4 feat: add GitHub Actions workflow for linting with Ruff (#1929)
* feat: add GitHub Actions workflow for linting with Ruff

* refactor: rename lint job and add formatting step to Ruff workflow

* chore: run ruff format

* chore: rename Ruff lint job to 'Lint' and add frontend linting workflow
2026-01-23 13:43:12 +08:00
Tiankai Ma 604cc53973 fix(localagent): allow empty func arg (#1921) 2026-01-19 23:42:47 +08:00
Tiankai Ma 1fc5e75f93 feat(mcp): add streamable HTTP and stdio (#1911)
* feat(mcp): add streamable HTTP

alongside with frontend UI change, w/ support for stdio

* fix(mcp): address copilot reviews

* Update src/langbot/pkg/provider/tools/loaders/mcp.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* fix: resolve copilot reviews

* fix: Message -> MessageChunk

* feat: upgrade mcp module

* feat: add i18n

* feat(mcp): enhance MCPCardComponent with mode badge and reorder select items in MCPFormDialog

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: WangCham <651122857@qq.com>
Co-authored-by: Junyan Qin (Chin) <rockchinq@gmail.com>
2026-01-13 13:50:06 +08:00
fdc310 a332206ba3 fix: When the deletion of the thinking chain is activated, since the "continue" is triggered as soon as the thinking begins, it causes a bug in the subsequent judgment that breaks out of the loop impression. (#1913) 2026-01-12 00:14:39 +08:00
Junyan Qin 4528000fc4 refactor: model management 2026-01-01 02:00:24 +08:00
fdc310 60ca688bcb Fix/Incomplete JSON data returned by N8N streaming data causes the loss of chunks. (#1880)
* fix: Incomplete JSON data returned by N8N streaming data causes the loss of chunks.
2025-12-23 09:42:26 +08:00
fdc310 854b291c5a fix: n8n streaming no sequence bug (#1873) 2025-12-20 00:03:05 +08:00
Copilot 82e2123fe7 Fix Dify v1.11.0 conversation_id UUID validation error (#1860)
* Initial plan

* Fix Dify v1.11.0 conversation_id UUID validation error

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>
2025-12-12 18:35:47 +08:00
Junyan Qin (Chin) 6421a6f5cb Feat/complete adapter features (#1849)
* feat: add voice and file supports for wecom

* feat: add   and  in query variables

* feat: supports for lark recv file message

* feat: kook recv voice msg

* feat: supports for Voice and File in discord

* chore: remove debug msg

* perf: remove unnecessary bot logs

* feat: implement bot log filtering and per label color (#1839)

* feat: add sender_name and group_name in query variables
2025-12-06 21:11:01 +08:00
Yaguang.Wang cb7c9af25c feat: Expanded WeCom message parsing to capture msgtype, inline voice/video… (#1843)
* Expanded WeCom message parsing to capture msgtype, inline voice/video/file/link data, bounded base64 downloads, and richer mixed-message attachments (src/langbot/libs/wecom_ai_bot_api/api.py); added event accessors for new fields (src/langbot/libs/wecom_ai_bot_api/wecombotevent.py).
Converter now maps richer WeCom payloads (text, images, files, voice, video, links) into platform message chain with fallbacks when nothing parsable is present (src/langbot/pkg/platform/sources/wecombot.py).
Preprocessor now turns voice inputs into file URLs for downstream runners (src/langbot/pkg/pipeline/preproc/preproc.py).
Dify runner uploads all incoming files (images/audio/video/docs) after downloading or decoding data URLs, infers MIME types, and passes typed file descriptors into chat/workflow calls (src/langbot/pkg/provider/runners/difysvapi.py).

* Update src/langbot/pkg/platform/sources/wecombot.py

Fixed the issue of duplicate text in the comments.

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update src/langbot/libs/wecom_ai_bot_api/api.py

Modify the way you approach challenges.

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update src/langbot/pkg/platform/sources/wecombot.py

Changing the variable names makes more sense.

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* feat: use from_base64 for the voice file converting

---------

Co-authored-by: tabriswang <tabriswang@finecomn.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Junyan Qin <rockchinq@gmail.com>
2025-12-05 22:33:15 +08:00
Junyan Qin (Chin) b5d192425e perf: advanced web chat (#1811)
* perf: supports for quoting message

* feat: add supports for Voice and File

* perf: reply button
2025-11-28 22:25:06 +08:00
Copilot a8481e43f0 feat: external knowledge bases (#1783)
* Initial plan

* Add backend support for external knowledge bases

Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>

* Add frontend support for external knowledge bases with tabs UI

Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>

* Add i18n translations for all languages (Traditional Chinese and Japanese)

Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>

* Update knowledge base tab list styling to match plugins page

Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>

* perf: margin-top for kb page

* refactor: switch RetrievalResultEntry to langbot_plugin pkg ones

* feat: knowledge retriever listing and creating

* stash

* refactor: unify sync mechanism for polymorphic components

* feat: use unified retireval result struct in retrieval test page

* chore: remove unused methods

* feat: retriever icon displaying

* feat: localagent retrieval with external kbs

* chore: bump version of langbot-plugin to 0.2.0b1

* fix: i18n

---------

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>
2025-11-27 23:19:43 +08:00
wrj97 31b483509c fix: fix n8n streaming support issue (#1787)
* 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>
2025-11-22 14:17:46 +08:00
Junyan Qin 2bf593fa6b feat: pass session and query_id to tool call 2025-11-20 21:17:47 +08:00
Copilot e642ffa5b3 chore: Add PyPI package support for uvx/pip installation (#1764)
* 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>
2025-11-16 19:53:01 +08:00