The contributor's original PR (#1917) appended an ``Available Skills``
index to the system prompt before the LLM saw the user message, so the
LLM could decide whether to activate a skill. ``7145447b`` removed the
text-marker activation flow and, together with it, the entire system
prompt injection — but the Tool Call replacement only put the available
skills inside the ``activate`` tool's description. In practice the LLM
ignores tool descriptions for selection and goes straight to native
tools, so user-visible skill activation silently broke.
Restore the injection, adapted for the Tool Call era:
- SkillManager regains ``get_skill_index(bound_skills)`` and
``build_skill_aware_prompt_addition(bound_skills)``. The addendum
carries only ``name (display_name): description`` for each
pipeline-visible skill plus one instruction line pointing at the
``activate`` tool. No SKILL.md contents — KV cache stays clean
- PreProcessor appends the addendum to the first system message (or
inserts a new one) of ``query.prompt.messages`` for the local-agent
runner. Handles plain-string and ContentElement[] bodies. Skips
cleanly when no skills are visible
- 3 new test_preproc cases: injection happens, bound-skills subset
honoured, empty addendum touches nothing. 280 passed
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>
* 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>
- 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.
* 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>
File messages from platforms like Telegram carry base64 data with an
empty url. The unconditional from_file_url(me.url) call passed an empty
string downstream, causing httpx to fail with "Request URL is missing
an 'http://' or 'https://' protocol" when uploading to Dify.
Mirror the existing Voice handling pattern: check base64 first, fall
back to url. Applied in both the main message chain and the Quote path.
Closes#2079
Co-authored-by: Junyan Qin <rockchinq@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(monitoring): link feedback to LangBot message ID and add feedback export
- Add pipeline→adapter notification hook so monitoring message ID is
passed back to WecomBotAdapter after creation
- Store stream_id→monitoring_message_id mapping with 10-min TTL cleanup
- Replace feedback record stream_id with LangBot monitoring message ID
so feedback can be linked to actual message records
- Rename streamId label to "Related Query ID" in all 7 i18n locales
- Remove non-functional message ID jump button from FeedbackList
- Add feedback export option to ExportDropdown (backend already implemented)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat(monitoring): add combined refresh handler for monitoring and feedback data
* fix(wecombot): improve stream ID mapping and error logging in WecomBotAdapter
* feat(lark): add monitoring message ID mapping for feedback correlation
* feat(lark): rename monitoring message ID mappings for clarity and consistency
feat(feedback): add button to view conversation for feedback items
* feat(bot-session-monitor): add feedback handling for bot messages with visual indicators
* feat(bot-session-monitor): enhance feedback display with hover content for like/dislike indicators
* fix(dingtalk): use voice recognition text instead of raw audio binary
When DingTalk sends a voice message to the bot, the callback JSON contains
a 'recognition' field with the speech-to-text result (powered by Qwen).
Previously, LangBot only extracted the 'downloadCode' to download the raw
audio binary and passed it as 'file_base64' to LLM APIs, which caused
400 errors since most models don't support this content type.
This patch:
- Extracts the 'recognition' field from DingTalk audio message content
- Uses it as plain text input to the LLM instead of raw audio
- Falls back to audio binary only when no recognition text is available
- Fixes duplicate text issue for audio messages with recognition
Fixes voice messages returning 'Request failed' on all LLM models.
* fix: add filereader for dingtalk,lark (#2122)
* fix: add filereader for dingtalk
* feat: add lark
* feat: update uv.lock
* chore: update version to 4.9.6 in pyproject.toml, __init__.py, and uv.lock
* fix: update langbot-plugin version to 0.3.8
* fix: update langbot-plugin version to 0.3.8
* fix(wecombot): extend StreamSession TTL for feedback sessions to prevent context data loss
StreamSessionManager.cleanup() removes sessions after 60s TTL, but feedback
events (like → cancel → dislike) can arrive later. When the session expires
before the dislike event, all context fields (session_id, user_id, message_id,
stream_id) are lost because get_session_by_feedback_id() returns None.
Fix: Sessions with registered feedback_ids now use a 10-minute TTL, aligned
with the adapter's _stream_to_monitoring_msg TTL in wecombot.py.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: 6mvp6 <13727783693@163.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: fdc310 <2213070223@qq.com>
Co-authored-by: haiyangbg <zhouhaiyangaa@gmail.com>
Co-authored-by: Guanchao Wang <wangcham233@gmail.com>
Co-authored-by: Rock Chin <1010553892@qq.com>
* refactor: pipeline routing rules - add routed_by_rule bypass and diagnostic logging
- Add routing rules editor (RoutingRulesEditor component)
- Add routed_by_rule bypass logic in response rules
- Add diagnostic logging for pipeline routing
- Database migration for bot pipeline routing rules
- Extract RoutingRulesEditor component from BotForm
- Revert log levels to debug
* feat: add message_has_element routing rule type
Support routing by message element type (Image, Voice, File, Forward,
Face, At, AtAll, Quote) with eq/neq operators.
* test: add unit tests for pipeline routing rules
20 tests covering _match_operator (eq/neq/contains/not_contains/
starts_with/regex/invalid) and resolve_pipeline_uuid (launcher_type/
launcher_id/message_content/message_has_element/first-match-wins/
skip-invalid/default-operator).
* fix(web): add missing 'message_has_element' to routing rule type validation
The Zod schema and TypeScript type for PipelineRoutingRule.type were
missing the 'message_has_element' variant, causing silent form validation
failure when saving routing rules with this type.
* feat: add pipeline discard functionality and localization support
* feat(web): improve drag-and-drop with DragOverlay, add discard monitoring and pipeline icons
- Add DragOverlay for smooth cursor-following drag in routing rules editor
- Remove transition to eliminate redundant swap animation on drop
- Record discarded messages in monitoring system via _record_discarded_message
- Display pipeline name (Workflow icon) and runner name (Play icon) on session monitor messages
- Show discard badge on discarded messages in session monitor
- Add i18n translations for discarded/userMessage/botMessage
* fix: ensure discarded messages appear in session monitor and improve icons
- Create/update monitoring session for discarded messages so they show in
the bot session monitor (was only inserting message rows, not sessions)
- Use human-readable 'Discarded' as pipeline_name instead of '__discard__'
- Change runner icon from Play to Bot for better AI Agent semantics
* fix: merge discarded messages into same session and remove session-level pipeline name
- Use LauncherTypes enum for session_id in discarded messages to match
the format used by monitoring_helper (fixes duplicate sessions)
- Don't overwrite session pipeline info on discard — a session can have
messages from multiple pipelines
- Remove pipeline_name from session list and chat header since it's
now shown per-message and a session is no longer single-pipeline
* fix(web): only show save button on config tab in bot detail page
* fix(web): scroll to bottom after messages render in session monitor
---------
Co-authored-by: RockChinQ <rockchinq@gmail.com>
Extract knowledge base UUID list into query.variables['_knowledge_base_uuids']
in PreProcessor so plugins can modify it during PromptPreProcessing. Runner now
reads from variables instead of pipeline_config. Also pass session_name,
bot_uuid, and sender_id to kb.retrieve() in the RETRIEVE_KNOWLEDGE_BASE handler
so knowledge engines receive proper session context.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: coerce pipeline config types at load time using metadata definitions
Pipeline configs stored in SQLAlchemy JSON columns can have values turned
into strings after UI edits (e.g. "120" instead of 120), causing runtime
arithmetic/logic errors. Add centralized type coercion in load_pipeline()
that leverages existing metadata YAML type definitions (integer, number,
float, boolean) to convert values before they reach downstream stages.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: address review - defensive getattr + add unit tests for config_coercion
- Use getattr with defaults for pipeline_config_meta_* attributes to
avoid AttributeError when MockApplication lacks these fields
- Add 18 unit tests for config_coercion module covering all code paths
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add dynamic form stage tracking and snapshot management
* fix: standardize string formatting in config coercion and improve logging messages
---------
Co-authored-by: KPC <kpc@kpc.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Junyan Qin <rockchinq@gmail.com>
* feat(chat): add runner_url to payload for telemetry tracking
* feat(telemetry): add runner_url to sanitized fields in telemetry payload
* feat(telemetry): replace runner_url with runner_category in telemetry payload and add runner utility functions
* fix:ruff
* perf: reduce memory usage by ~200MB+ at startup
Two key optimizations:
1. Use importlib.util.find_spec() instead of __import__() in dependency
checking. find_spec() only locates modules without executing them,
avoiding loading all 36 dependencies (~222MB) into memory at startup.
2. Introduce shared aiohttp.ClientSession via httpclient module.
Previously, every HTTP request created a new ClientSession, which
creates a new TCPConnector and SSL context, loading system root
certificates each time (~270MB total allocations observed via memray).
Now all HTTP client code reuses shared sessions.
- satori.py and coze_server_api/client.py are left unchanged as they
create one session per adapter lifecycle (not per-request).
Profiling data (memray):
- Peak memory: 403MB
- SSL context creation: 270MB / 6.7M allocations (67% of total)
- Dependency import: 222MB (55% of peak)
- Expected reduction: 150-350MB at startup
* fix: remove unused aiohttp imports (ruff F401)
* style: ruff format
* feat: add in-product survey system
- SurveyManager: event-based trigger, Space API communication
- Trigger on first successful non-WebSocket response
- Backend API: /api/v1/survey/{pending,respond,dismiss}
- Frontend: floating survey widget with progressive questions
- Flat radio/checkbox style (not dropdown Select)
* fix: persist triggered survey events to disk across restarts
Store triggered events in data/survey_triggered_events.json so that
restarting the process doesn't re-query Space for already-triggered events.
* fix: use metadata table for survey event persistence instead of file
Store triggered events in the existing metadata KV table
(key='survey_triggered_events') instead of a standalone JSON file.
* fix: ruff format and prettier fixes
* feat: add session message monitoring tab to bot detail dialog
Add a new "Sessions" tab in the bot detail dialog that displays
sent & received messages grouped by sessions. Users can select
any session to view its messages in a chat-bubble style layout.
Backend changes:
- Add sessionId filter to monitoring messages endpoint
- Add role column to MonitoringMessage (user/assistant)
- Record bot responses in monitoring via record_query_response()
- Add DB migration (dbm019) for the new role column
Frontend changes:
- New BotSessionMonitor component with session list + message viewer
- Add Sessions sidebar tab to BotDetailDialog
- Add getBotSessions/getSessionMessages API methods to BackendClient
- Add i18n translations (en-US, zh-Hans, zh-Hant, ja-JP)
Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)
Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
* refactor: remove outdated version comment from PipelineManager class
* fix: bump required_database_version to 19 to trigger monitoring_messages.role migration
* fix: prevent session message auto-scroll from pushing dialog content out of view
Replace scrollIntoView (which scrolls all ancestor containers) with
direct scrollTop manipulation on the ScrollArea viewport. This keeps
the scroll contained within the messages panel only.
* ui: redesign BotSessionMonitor with polished chat UI
- Wider session list (w-72) with avatar circles and cleaner layout
- Richer chat header with avatar, platform info, and active indicator
- User messages now use blue-500 (solid) instead of blue-100 for
clear visual distinction
- Metadata (time, runner) shown on hover below bubbles, not inside
- Proper empty state illustrations for both panels
- Better spacing, rounded corners, and shadow treatment
- Consistent dark mode styling
* fix: infinite re-render loop in DynamicFormComponent
The useEffect depended on onSubmit which was a new closure every
parent render. Calling onSubmit inside the effect triggered parent
state update → re-render → new onSubmit ref → effect re-runs → loop.
Fix: use useRef to hold a stable reference to onSubmit, removing it
from the useEffect dependency array.
Also add DialogDescription to BotDetailDialog to suppress Radix
aria-describedby warning.
* fix: remove .html suffix from docs.langbot.app links (Mintlify migration)
* style: fix prettier and ruff formatting
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Happy <yesreply@happy.engineering>
* 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>
* 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>
* 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>
Junyan Qin