The previous commit hard-coded a BoxUnavailableNotice banner above the
``local-agent`` stage card. That works, but it shouts at the user about
every field in that stage when in reality only one field —
``box-session-id-template`` — depends on the sandbox.
Use the dynamic-form schema's existing variable-injection mechanism
(``__system.*`` references via ``systemContext``) and add a sibling to
``show_if``: ``disable_if`` + ``disabled_tooltip``. The field stays
visible, becomes inert, and an info icon next to its label exposes the
reason on hover. The rest of the AI tab is left untouched.
- entities/form/dynamic.ts: extend IDynamicFormItemSchema with
``disable_if: IShowIfCondition`` and ``disabled_tooltip: I18nObject``
- DynamicFormComponent: evaluate disable_if with the same resolver as
show_if; OR the result into isFieldDisabled; render an Info tooltip
trigger next to the label when the condition matches
- ai.yaml metadata: attach disable_if (__system.box_available eq false)
and a localized disabled_tooltip to box-session-id-template
- PipelineFormComponent: drop the BoxUnavailableNotice import and the
per-stage banner; pass ``systemContext={ box_available: boxAvailable }``
only for the local-agent stage so other stages aren't paying the
re-render cost
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Make the Box sandbox runtime optional. When ``box.enabled`` is false in
config (or when an enabled Box fails to connect), every dependent feature
degrades to the same disabled-state UX rather than crashing or silently
falling back to less safe code paths.
Backend:
- config.yaml: new top-level ``box.enabled: true`` flag (default true)
- BoxService:
- Read box.enabled on construction
- initialize() short-circuits when disabled — no remote WS connect, no
stdio subprocess fork
- _on_runtime_disconnect is a no-op when disabled (no reconnect loop
on a deliberately-off service)
- get_status() now exposes ``enabled`` so the frontend can tell
"disabled in config" from "configured but failed"
- MCP stdio loader (mcp_stdio.uses_box_stdio): requires box_service to
be available, not just installed
- MCP _init_stdio_python_server: when ap.box_service exists but is
unavailable, refuse the stdio server with an actionable error instead
of silently falling through to host-stdio (which bypasses the sandbox
the operator asked for). Setups without ap.box_service installed at
all keep the legacy host-stdio fallback for pre-Box dev mode
- SkillService._require_box_for_write: refuses create/update/install/
write_skill_file when ap.box_service is installed but unavailable.
Distinguishes disabled vs failed in the error message so the UI can
surface the right hint. Legacy setups (no ap.box_service) keep the
local fallback path — that distinction is what keeps the existing
local-skills tests valid
Tests:
- Box disabled-state behavior (4 cases)
- Skill write refusal in disabled & failed states (7 cases)
- MCP stdio runtime info policy updated to match new refuse-when-down
behavior
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Replace text marker activation with `activate` tool (Tool Call mechanism)
- Replace 7 authoring tools with 2: `activate` + `register_skill`
- Add builtin skills loading from templates/skills/
- Add create-skill as first builtin skill
- Remove SKILL_ACTIVATION_MARKER and text detection methods
- Tool Result returns SKILL.md content (protects KV Cache)
This aligns with Claude Code's progressive disclosure pattern:
- Metadata (name+description) always visible in tool description
- SKILL.md body loaded on activate via Tool Call
- Bundled resources accessible through virtual path mapping
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Add 'image' field to box config section. When set, it overrides the
profile default image (python:3.11-slim) for all sandbox containers.
Priority: caller-specified > config.yaml image > profile default.
Remove the separate langbot_box_runtime Docker service. Box Runtime
now always launches as a local stdio subprocess, regardless of whether
LangBot runs in Docker or not. The WebSocket transport path is kept
only for explicit runtime_url configuration (remote deployment).
This simplifies deployment by eliminating cross-container path mapping
and network hops. Box Runtime is a pure scheduling process (talks to
Docker socket / nsjail), it does not execute user code or touch the
filesystem, so container isolation is unnecessary — unlike Plugin
Runtime.
* feat(skills): add Agent Skills management system
Implement comprehensive skills management feature inspired by agentskills spec:
Backend:
- Add Skill and SkillPipelineBinding database entities
- Add database migration (dbm018) for skills tables
- Implement SkillManager for skill loading, matching, and resolution
- Implement SkillService for CRUD operations
- Add skills API endpoints for skill and pipeline binding management
- Integrate skill index injection into pipeline preprocessor
- Add skill activation detection in LocalAgentRunner
Frontend:
- Add Skills page with listing, search, and type filter
- Add SkillDetailDialog for create/edit with preview
- Add SkillCard and SkillForm components
- Add skills API methods to BackendClient
- Add skills entry to sidebar navigation
- Add i18n translations (en-US, zh-Hans)
Features:
- Support skill and workflow types
- Sub-skill composition via {{INVOKE_SKILL: name}} syntax
- Progressive disclosure (index in prompt, full instructions on activation)
- Pipeline-specific skill bindings with priority
* fix: resolve cherry-pick conflicts for agentskills onto sandbox
- Remove non-existent external_kb service import
- Add skill_mgr mock to localagent sandbox_exec tests
- Keep database version at 24 (sandbox branch's latest)
* feat(skills): upgrade to package-backed skills with sandbox execution
Evolve the skills system from pure prompt-based to package-backed with
sandbox tool execution support:
- Add source_type/package_root/entry_file/skill_tools fields to Skill entity
- SkillManager loads SKILL.md from local package directories
- SkillToolLoader as 4th dispatch layer in ToolManager (query-scoped)
- LocalAgent injects skill tools into use_funcs on skill activation
- BoxService.execute_skill_tool() runs scripts in sandbox (ro mount, env params)
- Skill tool names auto-namespaced as skill__{skill}__{tool}
- API validation for package_root allowlist and entry path traversal
- Frontend source_type toggle, package_root input, skill_tools editor
- Migration renumbered to 025 with ALTER TABLE fallback for existing DBs
- Fix unclosed limitation section in i18n files
- Fix skills API methods misplaced outside BackendClient class
* fix: test info
* feat(skills): switch skills to package-backed storage and add import tooling
- skills 从 inline/package 双轨收敛成 package-first
- instructions 改为写入并读取 SKILL.md
- 新增本地目录扫描和 GitHub 安装 skill
- 前端把 skills 整合进 plugins 页，新增 SkillsComponent 和 GitHub 导入弹窗
- skill form 去掉 source_type / type 筛选，改成目录扫描驱动
- Box skill tool 挂载模式从 ro 改成 rw
- 测试和中英文文案同步更新
* feat: simplify langbot skill create and import
* refactor(skills): clean up legacy skill API and harden activation flow
* refactor(skills): remove skill dependency expansion and add skill_get
* fix: lint
* fix: delete
* fix(skills): align tool manager loader initialization
* refactor: remove sandbox execute skill
* fix(skills): hide activation markers and isolate skill activation flow
* refactor(skills): switch skill model to filesystem-backed packages
* refactor(skills): switch skill model to filesystem-backed packages
* refactor(skills): unify runtime skill access around filesystem paths
* refactor(skills): unify runtime skill access around filesystem paths
* feat(skills): align rw package design and fix skill activation, visibility, and lint issues
* refactor(skills): replace rich authoring API with import/reload flow and update
Box design doc
* feat(box): add sandbox_exec tool loop for local-agent calculations
* feat(box): add host workspace mounting and sandbox_exec guidance
* feat(box): add BoxProfile with resource limits and improved output truncation
- Implement head+tail output truncation (60/40 split) so LLM sees both
beginning and final results; add streaming byte-limited reads in backend
to prevent unbounded memory usage (_MAX_RAW_OUTPUT_BYTES = 1MB)
- Define BoxProfile model with locked fields and max_timeout_sec clamping
- Add four built-in profiles: default, offline_readonly, network_basic,
network_extended with differentiated resource and security constraints
- Add resource limit fields to BoxSpec (cpus, memory_mb, pids_limit,
read_only_rootfs) and pass corresponding container CLI flags
(--cpus, --memory, --pids-limit, --read-only, --tmpfs)
- Profile loaded from config (box.profile), applied in service layer
before BoxSpec validation; locked fields cannot be overridden by
tool-call parameters
* feat(box): add obs
* refactor(box): unify box service lifecycle and local runtime
management
* refactor(box): remove legacy in-process runtime code and clean up smells
After the architecture settled on always using an independent Box Runtime
service, several pieces of compatibility code and design shortcuts were
left behind. This commit cleans them up:
- Remove `LocalBoxRuntimeClient` and `create_box_runtime_client` from
production code (moved to test-only helper).
- Remove unused `_clip_bytes` method from backend.
- Remove `__langbot_session_placeholder__` hack by making `BoxSpec.cmd`
default to empty and validating non-empty only in `runtime.execute()`.
- Extract `get_box_config()` helper to eliminate 5× duplicated config
access boilerplate.
- Remove `session_id`/`host_path`/`host_path_mode` from the LLM-facing
tool schema to enforce request-scoped session isolation.
- Fix dual shutdown path: `NativeToolLoader.shutdown()` no longer calls
`box_service.shutdown()` (handled by `Application.dispose()`).
- Simplify `_assert_session_compatible` with a loop.
- Inline client creation in `BoxRuntimeConnector`.
- Remove redundant `BOX__RUNTIME_URL` env var from docker-compose
(auto-detected by code).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(box/mcp): integrate MCP stdio with Box sandbox — auto-isolation, dep install, security
## Summary
When Podman/Docker is available, all stdio-mode MCP servers now automatically
run inside Box containers with dependency installation, path rewriting, and
lifecycle management. When no container runtime exists, LangBot starts normally
and stdio MCP falls back to host-direct execution.
## What changed
### MCP stdio → Box integration (mcp.py)
- Add `MCPServerBoxConfig` pydantic model for structured box configuration
with validation and defaults (network, host_path_mode, timeouts, resources)
- Auto-infer `host_path` from command/args with venv detection: recognizes
`.venv/bin/python` patterns and walks up to the project root
- Rewrite host paths to container `/workspace` paths transparently
- Replace venv python commands with container-native `python`
- Auto-detect `pyproject.toml`/`setup.py`/`requirements.txt` and run
`pip install` inside the container before starting the MCP server
- Copy project to `/tmp` before install to handle read-only mounts
- Add retry with exponential backoff (3 retries, 2s/4s/8s delays)
- Add Box managed process health monitoring (poll every 5s)
- Fix session leak: `_cleanup_box_stdio_session()` now runs in `finally`
block of `_lifecycle_loop`, covering all exit paths
- Fix retry logic: `_ready_event` is only set after all retries exhaust
or on success, not on first failure
- Enhance `get_runtime_info_dict()` with `box_session_id` and `box_enabled`
### Box security (security.py — new)
- `validate_sandbox_security()` blocks dangerous host paths:
`/etc`, `/proc`, `/sys`, `/dev`, `/root`, `/boot`, `/run`,
docker.sock, podman socket
- Called at the start of `CLISandboxBackend.start_session()`
### Box models (models.py)
- Add `BoxHostMountMode.NONE` — skips volume mount entirely
- Adjust `validate_host_mount_consistency` to allow arbitrary workdir
when `host_path_mode=NONE`
### Box backend (backend.py)
- Add `validate_sandbox_security()` call in `start_session()`
- Add `langbot.box.config_hash` label on containers for drift detection
- Handle `BoxHostMountMode.NONE` — skip `-v` mount arg
- Add `cleanup_orphaned_containers()` to base class (no-op default) and
CLI implementation (single batched `rm -f` command)
### Box runtime (runtime.py)
- Call `cleanup_orphaned_containers()` during `initialize()` to remove
lingering containers from previous runs
### Box service (service.py)
- Graceful degradation: `initialize()` catches runtime errors and sets
`available=False` instead of crashing LangBot startup
- Add `available` property and guard on `execute_sandbox_tool()`
- Add `skip_host_mount_validation` parameter to `build_spec()` and
`create_session()` — MCP paths are admin-configured and trusted,
bypassing `allowed_host_mount_roots` restrictions meant for
LLM-generated sandbox_exec commands
### Default behavior
- stdio MCP servers automatically use Box when `box_service.available`
is True (Podman/Docker detected); no explicit `box` config needed
- When no container runtime exists, falls back to host-direct stdio
- MCP Box defaults: `network=on` (for pip install), `read_only_rootfs=false`
(for site-packages), `host_path_mode=ro`, `startup_timeout=120s`
### Tests
- `test_box_security.py`: blocked paths, safe paths, subpath rejection
- `test_mcp_box_integration.py`: config model, path rewriting, venv
unwrap, host_path inference, payload building, runtime info, box
availability check
- `test_box_service.py`: `BoxHostMountMode.NONE` validation tests
* feat(box/mcp): instance-based orphan cleanup, error classification, session API, and integration tests
## Changes
### Precise orphan container cleanup
- Runtime generates a unique instance_id on startup
- Every container gets a `langbot.box.instance_id` label
- `cleanup_orphaned_containers()` only removes containers from
previous instances, preserving containers owned by the current one
- Containers from older versions (no label) are also cleaned up
- `cleanup_orphaned_containers` added to `BaseSandboxBackend` as
a no-op default method, removing hasattr duck-typing
### Fine-grained MCP error classification
- New `MCPSessionErrorPhase` enum with 7 phases: session_create,
dep_install, process_start, relay_connect, mcp_init, runtime,
tool_call
- Each phase in `_init_box_stdio_server()` sets the error phase
before re-raising, enabling precise failure diagnosis
- `retry_count` tracked across retry attempts
- `get_runtime_info_dict()` exposes `error_phase` and `retry_count`
### GET /v1/sessions/{id} API
- `BoxRuntime.get_session()` returns session details including
managed process info when present
- `handle_get_session` HTTP handler + route in server.py
- `BoxRuntimeClient.get_session()` abstract method + remote impl
### stdio defaults to Box when runtime is available
- `_uses_box_stdio()` checks `box_service.available` instead of
requiring explicit `box` key in server_config
- `BoxService.initialize()` catches runtime errors gracefully,
sets `available=False` instead of crashing LangBot startup
- When no container runtime exists, stdio MCP falls back to
host-direct execution
### Code quality (from /simplify review)
- Extracted `_VENV_DIRS` / `_VENV_BIN_DIRS` module-level constants
- Removed dead `_box_network_mode()` method and unused `bc` variable
- Fixed broken import `from ....box.models` → `from ...box.models`
- Cached `_resolve_host_path()` result — computed once, passed through
- Config hash now includes `host_path` field
- Batched orphan cleanup into single `rm -f` command
### Session leak fix
- `_cleanup_box_stdio_session()` now runs in `_lifecycle_loop`'s
finally block, covering all exit paths (normal shutdown, error,
retry, final failure)
### Integration tests
- 6 end-to-end tests covering managed process lifecycle, WebSocket
stdio bidirectional IO, session cleanup verification, single
session query, process exit detection, and orphan cleanup safety
* refactor: use rpc
* fix: import
* refactor(box): clean up sandbox subsystem code quality and efficiency
- Fix O(n²) stderr trimming in runtime.py with running length tracker
- Remove dead code: RESERVED_CONTAINER_PATHS, _subprocess_wait_task,
unused config_hash computation, unused imports
- Deduplicate connection callback in BoxRuntimeConnector, parse URL once
- Use enum comparison instead of stringly-typed spec.network.value check
- Replace manual _result_to_dict/_session_to_dict with model_dump()
- Cache NativeToolLoader tool definition and sandbox system guidance
- Extract _is_path_under() helper to eliminate duplicated path checks
- Import SANDBOX_EXEC_TOOL_NAME from native.py instead of redefining
- Add JSON startswith guard in logging_utils to skip futile json.loads
- Fix ruff lint errors (F401 unused imports, F841 unused variables)
* fix: ruff
* refactor(sandbox): keep box logic out of pipeline and localagent
- Move sandbox system-prompt guidance from LocalAgentRunner into
BoxService.get_system_guidance() so all box domain knowledge stays
in the box module.
- Remove standalone logging_utils.py; merge format_result_log() into
MessageHandler base class alongside cut_str().
- Strip sandbox-specific JSON parsing from log formatting; tool
results now use generic truncation.
- Revert TYPE_CHECKING changes in stage.py and runner.py that were
unrelated to this feature.
- Skip two test files affected by a pre-existing circular import
(runner ↔ app) until the import cycle is resolved in a separate PR.
* refactor(box): move box runtime to langbot-plugin-sdk
Extract self-contained box runtime modules (actions, backend, client,
errors, models, runtime, security, server) to langbot-plugin-sdk and
update all imports to use `langbot_plugin.box.*`. Keep only service
and
connector in LangBot core as they depend on the Application context.
- Update docker-compose to use `langbot_plugin.box.server` entry
point
- Update pyproject.toml to use local SDK via `tool.uv.sources`
- Remove migrated source files and their unit/integration tests
- Update remaining test imports to match new module paths
* fix: ruff
* fix(box): tighten sandbox exposure and restore box integration coverage
* refactor(types): remove quoted annotations under postponed evaluation
* chore(sandbox): move MCP loader changes to follow-up branch
* refactor(plugins): simplify GitHub install flow to default master archive
* revert(api): restore plugin GitHub import flow in plugins controller
* Improve data-root handling and skill install previews
* Add managed skill authoring tools for local agents
* Refactor the skills UI around sidebar detail pages
* Document why managed skill authoring tools bypass box
* fix: lint
* feat(web): refactor plugin/skill install flows and fix skills page
- Fix sidebar skill icon
- Add skills route and error page component
- Refactor plugin GitHub install from dialog modal to inline card
- Add skill install dropdown menu (create/upload/github) in sidebar
- Wire sidebar → skills page communication via pendingSkillInstallAction context
- Add i18n keys for error page and skill install actions
* fix(web): persist sidebar collapsible section open state on navigation
Sections opened via sub-item navigation now retain their expanded state
when the user switches to a different section, instead of collapsing
because the isActive fallback becomes false.
---------
Co-authored-by: youhuanghe <1051233107@qq.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Junyan Qin <rockchinq@gmail.com>
- Implement head+tail output truncation (60/40 split) so LLM sees both
beginning and final results; add streaming byte-limited reads in backend
to prevent unbounded memory usage (_MAX_RAW_OUTPUT_BYTES = 1MB)
- Define BoxProfile model with locked fields and max_timeout_sec clamping
- Add four built-in profiles: default, offline_readonly, network_basic,
network_extended with differentiated resource and security constraints
- Add resource limit fields to BoxSpec (cpus, memory_mb, pids_limit,
read_only_rootfs) and pass corresponding container CLI flags
(--cpus, --memory, --pids-limit, --read-only, --tmpfs)
- Profile loaded from config (box.profile), applied in service layer
before BoxSpec validation; locked fields cannot be overridden by
tool-call parameters
* add conversation expire config
* add user query text to card
* fix(pipeline): move session limit to AI config
* test(pipeline): cover AI session limit config
* refactor(pipeline): merge session expire-time into AI runner stage
Move the session validity duration field out of the standalone
session-limit stage into the runner stage so it actually renders in the
AI tab (the tab only shows the runner stage and the stage matching the
selected runner — any other stage is filtered out). Read path, default
config, metadata description, and tests updated accordingly.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(pipeline): expire conversations from last update time
* fix(n8n): sync generated conversation id into payload
---------
Co-authored-by: RockChinQ <rockchinq@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat: add web_page_bot adapter and embed widget
- Implemented a new `web_page_bot` adapter for embedding chat widgets on websites.
- Created a new YAML configuration file for `web_page_bot` with necessary metadata and execution details.
- Developed the `WebPageBotAdapter` class to handle message events and manage listeners.
- Added a JavaScript widget for embedding the chat interface, including styles and functionality for user interaction.
- Updated WebSocket handling to support the new bot adapter and manage connections.
- Enhanced the bot form to include pipeline UUID and adapter configuration in the system context.
- Introduced a new dynamic form item type for embed code in the form entity.
* feat(embed): add feedback submission and image upload functionality to embed widget
* feat(embed): add reset session endpoint for embed widget and improve WebSocket image handling
* feat(widget): remove typing indicator display logic from message handling
* fix(embed): security hardening for embed widget
- Add UUID format validation for pipeline_uuid parameters
- Add Cloudflare Turnstile integration for bot protection (optional)
- Add HMAC-signed session tokens for /messages, /reset, /feedback endpoints
- Sanitize error responses (remove internal exception details)
- Sanitize base_url before JS injection
- Fix XSS in markdown link rendering (only allow http/https protocols)
- Fix XSS in image URL extraction (only allow http/https/data protocols)
- Escape widget title in embed code snippet (HTML entity encoding)
- Remove class-level mutable default in WebPageBotAdapter
- Remove duplicate config line and console.log in widget.js
- Add turnstile_site_key and turnstile_secret_key config fields
* style: fix prettier formatting for chained replace calls
* fix(embed): declare listeners as Pydantic field in WebPageBotAdapter
The base class is a Pydantic BaseModel, so listeners must be declared
as a field (with default_factory) rather than assigned in __init__.
Also keep the __init__ to convert positional args to keyword args for
Pydantic compatibility with botmgr's calling convention.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor(embed): use bot_uuid instead of pipeline_uuid in all embed URLs
Replace pipeline_uuid with bot_uuid in all user-facing embed widget
URLs so internal pipeline identifiers are never exposed. The server
resolves bot_uuid to the owning web_page_bot, validates it is enabled
and has a pipeline bound, then routes internally using pipeline_uuid.
Add a dedicated WebSocket endpoint at /api/v1/embed/<bot_uuid>/ws/connect
instead of reusing the pipeline debug path. Wire WebPageBotAdapter to
proxy reply_message calls through the WebSocket adapter so dashboard
shows the correct adapter name while replies are still delivered.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs(embed): improve Turnstile config field descriptions
Add guidance on where to obtain the keys (Cloudflare dashboard) and
clarify that leaving them empty disables the feature.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(embed): add multi-language support for embed widget
Add a language selector to the web_page_bot config with 8 locales
(en, zh-Hans, zh-Hant, ja, es, ru, th, vi). The backend injects the
locale into widget.js which uses a built-in i18n dictionary for all
user-facing strings (welcome message, placeholder, aria labels, error
messages, powered-by footer).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(embed): use correct select option format for language selector
Options must use name/label (i18n object) format, not value/label
(plain string), to match the dynamic form renderer.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* style(embed): adjust footer padding and link to langbot.app
Increase footer padding for more breathing room from the bottom edge.
Change powered-by link from GitHub repo to langbot.app.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(embed): ignore Enter key during IME composition
Check e.isComposing before treating Enter as send, so confirming
an IME candidate (e.g. Chinese/Japanese input) does not also fire
the message.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(embed): center bubble icon and fill entire circle
Make .lb-chat-icon span fill the full bubble area so the logo image
covers the circle completely without exposing the blue background.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(embed): add bubble icon presets selector
Add 6 bubble icon options (LangBot logo, chat bubble, robot, headset,
sparkle, message) configurable in the bot settings. Icons are inline
SVGs in widget.js, selected via a config field injected by the backend.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: RockChinQ <rockchinq@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(provider): add rerank model management as a core model type
* feat(provider): add rerank support to existing requesters and new rerank providers
* feat(web): add rerank model management UI and pipeline config
* fix(provider): correct rerank support_type after verification
- Add rerank to OpenRouter (confirmed /api/v1/rerank endpoint)
- Remove rerank from Ollama (no native support, PR #7219 unmerged)
- Remove rerank from JiekouAI (no rerank docs found, URL path mismatch)
* fix(provider): remove alru_cache from model getters and add rerank param hints
* fix: resolve lint errors
- Remove unused alru_cache import from modelmgr.py
- Remove unused error_message variable in invoke_rerank
- Fix prettier formatting in frontend files
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix: remove unused exception variable
- Change `except Exception as e:` to `except Exception:` since e is not used
- Fix prettier formatting in ProviderCard.tsx
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix: apply ruff format
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* feat(template): add rerank config fields to default pipeline config
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* chore: remove PR.md
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* fix(ui): remove duplicate rerank model form in AddModelPopover
The form was being rendered twice: once in TabsContent manual mode
and again in a separate conditional block for rerank tab.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Adds 'system.disabled_adapters' config option (list of adapter names).
Disabled adapters are excluded from both the adapter registry and API
responses, preventing users from creating bots with those adapters.
Example config:
system:
disabled_adapters:
- aiocqhttp
- dingtalk
- Add zh_Hant (Traditional Chinese) to all 17 adapter YAML metadata and config fields
- Add ja_JP translations to global adapters (Telegram, Discord, Slack, Lark, LINE)
- Fix buggy zh_Hant in line.yaml and slack.yaml (contained simplified Chinese)
- Add zh_Hant field to backend I18nString model
- Add adapter category grouping with locale-aware ordering
- Add webhook Cloud CTA for community edition users
- Fix wizard progress not clearing on skip/complete
* feat(web): add onboarding wizard for guided bot creation
Implement a full-screen 4-step wizard at /wizard that guides users
through selecting a platform, configuring a bot, choosing an AI engine,
and completing setup. The wizard uses DynamicFormComponent for adapter
and pipeline configuration, embeds BotLogListComponent for real-time
debugging, persists state to localStorage, and integrates with Space
OAuth flow. Also fixes a prompt-editor crash in DynamicFormComponent
when value is undefined.
* feat(wizard): redesign step 0/1 flow, add skip dialog, auto-expand log images
- Step 0: Remove bot name/description fields; auto-derive name from adapter
label; create disabled bot on confirm; advance to Step 1 automatically
- Step 1: Replace 'Create Bot' with 'Save & Enable Bot'; update adapter
config and enable bot; disable form fields after saving
- Add skip confirmation AlertDialog with i18n message
- Add LanguageSelector to wizard header
- Move wizard sidebar entry to last position to prevent fallback redirect loop
- Add defaultExpanded prop to BotLogCard; auto-expand entries with images
in wizard via autoExpandImages prop on BotLogListComponent
- Remove automatic default pipeline creation (write_default_pipeline) from
backend persistence manager since the wizard now handles pipeline creation
- Update all 4 locale files (en-US, zh-Hans, zh-Hant, ja-JP)
* fix(wizard): hide detailed logs link in wizard, allow re-editing bot config after save
- Add hideDetailedLogsLink prop to BotLogListComponent; pass it in wizard
- Remove isEditing on DynamicFormComponent so form stays editable after save
- Always show save button; label changes to 'Re-save' after first save
- Add resaveBot i18n key to all 4 locale files
* style(wizard): move save button into config card header
* fix(wizard): initialize userInfo/systemInfo so model selector works
The wizard runs outside /home layout, so userInfo was null. This caused
the model-fallback-selector to filter out all Space models, showing an
empty dropdown. Fix by calling initializeUserInfo() and
initializeSystemInfo() before fetching wizard data.
Also:
- Hide log toolbar in wizard via hideToolbar prop on BotLogListComponent
- Add empty state message for bot logs (noLogs i18n key, all 4 locales)
* feat(wizard): redesign AI Engine step with left-right split layout
Before selecting a runner: centered grid of runner cards.
After selecting: left panel shows compact runner list for switching,
right panel shows runner config form with slide-in animations.
Also fix prompt field default: add default value to prompt-editor field
in ai.yaml metadata so the prompt is pre-populated with
'You are a helpful assistant.' instead of being empty.
* feat(pipeline): add default values to ai.yaml runner configs and show_if for n8n auth fields
- Sync default values from default-pipeline-config.json to all runner
config fields in ai.yaml so wizard forms are pre-populated
- Add show_if conditions to n8n-service-api auth fields so only the
relevant credentials appear based on selected auth-type
- Fix prompt-editor crash in DynamicFormItemComponent when field.value
is undefined (Array.isArray guard + fallback)
- Improve wizard Step 2 split layout with fixed column widths,
independent scroll, ring clipping fix, and mobile responsiveness
- Use key={selected} on DynamicFormComponent to force remount on
runner switch
- Improve pipeline creation flow: create → fetch defaults → merge AI
section → update (preserves trigger/safety/output defaults)
* feat(dynamic-form): add systemContext prop with __system.* namespace for show_if conditions
- Add systemContext prop to DynamicFormComponent for injecting external
variables accessible via __system.* prefix in show_if conditions
- Extract resolveShowIfValue() helper for cleaner field resolution
- Pass { is_wizard: true } from wizard to hide knowledge-bases field
- Remove bot config save toast in wizard (keep inline indicator)
* feat(sidebar): render wizard as standalone item before Home group with fallback redirect fix
* fix(wizard): remove unused setBotDescription to fix lint error
Add instance_id field to system section in config.yaml.
Can be set via SYSTEM__INSTANCE_ID env var (auto-mapped).
Falls back to data/labels/instance_id.json if not set.
- Added checks for maximum allowed extensions, bots, and pipelines in the backend services (PluginsRouterGroup, BotService, MCPService, PipelineService).
- Updated system configuration to include limitation settings for max_bots, max_pipelines, and max_extensions.
- Enhanced frontend components to handle limitations, providing user feedback when limits are reached.
- Added internationalization support for limitation messages in English, Japanese, Simplified Chinese, and Traditional Chinese.
- Add Milvus db_name configuration and client parameter support.
- change kb_data uuid for Milvus. 3. add MAX_BATCH_SIZE for openai.
- support more vector_size.
* feat: add telemetry support for query execution tracking and configuration
* feat: integrate telemetry manager and enable telemetry data sending
* feat: integrate telemetry manager and enhance error handling for telemetry sending
* feat: update telemetry configuration to use 'space' instead of 'telemetry' and adjust related parameters
* feat: integrate telemetry manager and enable telemetry data sending
* feat: integrate telemetry manager and enhance error handling for telemetry sending
* feat: add instance id
* feat: enhance telemetry management with asynchronous task handling and improve model retrieval caching
---------
Co-authored-by: Junyan Qin <rockchinq@gmail.com>
* feat: add SeekDB vector database support for knowledge bases
This commit adds complete integration of OceanBase's SeekDB as a vector
database option for LangBot's knowledge base feature.
## Changes
### Core Implementation
- Add SeekDB adapter implementing VectorDatabase interface
- Support both embedded and server deployment modes
- HNSW indexing with cosine similarity
- Async operations with error handling
- Comprehensive logging
### System Integration
- Register SeekDB in VectorDBManager
- Add pyseekdb>=0.1.0 dependency
- Add SeekDB configuration template
- Update README with vector database section
### Documentation
- Complete integration guide with platform compatibility warnings
- Configuration examples for all deployment modes
- Troubleshooting guide for common issues
- Code examples demonstrating usage patterns
- Comprehensive test reports and status documentation
## Testing
Architecture validated end-to-end using ChromaDB:
- File upload → parsing → chunking → embedding → storage
- 828 bytes → 3 chunks → 3 vectors stored successfully
- BGE-M3 model (384 dimensions)
- Status: Completed ✅
## Platform Compatibility
### Embedded Mode
- ✅ Linux: Fully supported
- ❌ macOS: Not supported (pylibseekdb is Linux-only)
- ❌ Windows: Not supported (pylibseekdb is Linux-only)
### Server Mode
- ✅ Linux: Fully supported
- ⚠️ macOS: Known issue (oceanbase/seekdb#36)
- ⚠️ Windows: Untested
### Remote Connection
- ✅ All platforms supported
## Known Issues
macOS Docker server mode affected by upstream bug:
https://github.com/oceanbase/seekdb/issues/36
Workaround: Use ChromaDB/Qdrant or connect to remote SeekDB server.
## Files Added
- src/langbot/pkg/vector/vdbs/seekdb.py
- docs/SEEKDB_INTEGRATION.md
- examples/seekdb_example.py
- SEEKDB_INTEGRATION_SUMMARY.md
- SEEKDB_INTEGRATION_COMPLETE.md
- SEEKDB_TEST_STATUS.md
- SEEKDB_FINAL_SUMMARY.md
- SEEKDB_INTEGRATION_DONE.md
- GITHUB_ISSUE_36_COMMENT.md
## Files Modified
- src/langbot/pkg/vector/mgr.py
- src/langbot/pkg/vector/vdbs/__init__.py
- pyproject.toml
- src/langbot/templates/config.yaml
- README.md
- README_EN.md
🤖 Generated with [Claude Code](https://claude.com/claude-code)
via [Happy](https://happy.engineering)
Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
* chore: remove unused docs
* feature: minimal seekdb change (#1866)
* feat: add SeekDB embedding requester and configuration
This commit introduces a new SeekDB embedding requester, which utilizes the local embedding function from pyseekdb. It includes the necessary Python implementation and a corresponding YAML configuration file for integration. Additionally, a new SVG icon for SeekDB is added to enhance the visual representation in the UI.
* fix: update EmbeddingForm to conditionally render URL field based on model provider
This commit modifies the EmbeddingForm component to conditionally display the URL input field only when the current model provider is not 'seekdb-embedding'. Additionally, it updates the condition for rendering the API key field to exclude both 'ollama-chat' and 'seekdb-embedding' providers.
* chore: update Python version requirement in pyproject.toml to support Python 3.11
* fix: add config default value, when it makes fronted not show spec
* fix: seekdb.py clean metadata. change api
* fix: enhance error handling in SeekDB embedding initialization
This commit adds improved error handling to the SeekDB embedding function. It ensures that a RuntimeError is raised if the embedding function fails to initialize, and wraps the embedding call in a try-except block to catch and raise a RequesterError with a descriptive message in case of failure.
* refactor: update SeekDB database management to use AdminClient
This commit refactors the SeekDB database management logic to utilize the AdminClient for database operations. It replaces the previous temp_client with admin_client for listing and creating databases, ensuring a more robust interaction with the SeekDB API.
* refactor: update SeekDB embedding model initialization to use task manager
This commit refactors the SeekDB embedding model initialization by replacing the direct asyncio task creation with the task manager's create_task method. This change enhances task management and provides a clearer naming convention for the embedding model initialization task.
* perf: integration
* chore: remove unnecessary files
* fix: linter errors
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Happy <yesreply@happy.engineering>
Co-authored-by: 名为a的全局变量 <1051233107@qq.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>
