Core no longer assembles a whole trace locally. Every workflow node is uploaded
the moment it completes as its own `execution_node` record, and each execution
closes with exactly one `execution_chain` record; all records of one execution
carry the same `event_id`, so Space groups them back into a single chain.
- every execution starts at an inbound event: event-less Pipeline lanes and
WebUI/API debug runs synthesize their virtual inbound event at the boundary
and are marked debug=true, so a Runner is never a trace origin
- sampling is decided once per event from a stable hash of the event id (the
previous `int(id[:8], 16)` raised on every `platform:`-prefixed id and so
dropped every successful inbound-event chain) and is reported on each record
as sample{mode,denominator}; the default mode is now `all`
- the local trace buffer, the 120s TTL, the per-process trace cap and the shared
open-node mirror are gone, which also removes the truncated-chain upload and
the re-buffered-closed-trace leak they caused
- a broken chain is always uploaded, and its reason falls back to the first
failed node so the chain explains itself
- flush keeps records until the sender accepts them and counts what it drops;
telemetry health replaces the unused send-task queue
- heartbeat reports bound Agent / plugin-processor / event-binding counts
- bound Pipeline and Agent resources (plugins, MCP servers, knowledge bases,
tools with their Host source, skills, models and the Runner schema selectors
that picked them) are reported on the chain record
- failure text is bounded and redacted instead of passing exception text through
- the dead per-query feature counters and their call sites are removed
Wire contract: schema 2 (`execution_node` / `execution_chain`).
Every host step now opens a stage scope, so observations recorded inside it (including cross-task plugin/RPC calls resolved through the execution registry) carry the owning step as parent; the pipeline lane records its own pipeline/run node so acks and replies issued outside the runner still hang off a node.
Execution telemetry already reported window counters. This adds one bounded,
content-free chain per inbound platform event, so a single event can be
followed from its source platform through routing and processing to the
platform API calls it caused.
- telemetry/trace.py: ContextVar trace identity with route and run scopes, and
a 32-stage bound per chain.
- telemetry/execution.py: keeps at most 64 chains for 120s, decides sampling
from the observed outcome, and sends one payload per chain keyed by
query_id = trace_id, so Space fetches a chain by primary identity. Window
counters are unchanged and remain the source of coverage statistics.
- botmgr / pipelinemgr / orchestrator: bind the trace at the ingress boundary,
scope routing identity per dispatch, and attach the run identity, so nested
lanes (event -> route -> pipeline/runner -> platform API) reuse one chain. A
run reached without an ingress (WebUI debug, service API) owns its own chain.
- space.execution_trace selects off | failures | sampled | all (default
sampled: failures, WebUI debug runs and every N-th success).
Chains carry only code-defined identifiers (adapter and runner types, route
identity as type:uuid, run id); never message content, tool arguments or
platform user identifiers.
A saved pipeline may carry the post-migration shape
{'ai': {'runner': {'id': ''}, 'runner_config': {}}} while no runner has been
selected yet. The planner matched the empty id against the certified
'plugin:author/name/component' form, failed, and returned a malformed-id
blocker, so the whole 'migrate all' batch stopped with both pipelines reported
as blocked even though there was no legacy section and nothing to convert.
A blank id with no legacy runner section now reports not_legacy: no work is
needed and no target is synthesized. A blank id that still coexists with a
legacy section remains an explicit invalid_runner_id blocker, because that
ambiguous state must be resolved by the operator rather than guessed.
* fix(pipeline): stop emitting empty final assistant messages
An empty final streaming chunk was appended as an empty message chain when no sandbox outbox attachment was present, so platforms received an empty reply. Only append the chain when attachments were actually collected, and gate the "Call ..." tool notice behind output.misc.track-function-calls so it no longer becomes the final chunk of a stream.
* fix(wecombot): do not close stream on a blank final snapshot
A blank final snapshot closed the WeCom stream with an empty bubble and pushed the real answer into a separate reply_text message. Skip blank final snapshots and keep the session open so the following non-blank chunk can finalize it. Covered by new regression tests.
- Add MediaCache using xxHash3-128 (with sha256 fallback) content-addressable storage
- Externalize message chain image payloads before recording monitoring and discarded messages
- Strip base64 payloads to null in SQLite monitoring_messages, dropping row size from megabytes to hundreds of bytes
- Add GET /api/v1/files/media/<filename> route with immutable HTTP cache headers to serve cached media
- Integrate age-based retention (default 30 days) and configurable disk quota with MaintenanceService cleanup loop
- Add defensive sanitizer in MonitoringService.record_message against oversized raw base64 payloads
- Add comprehensive unit tests and end-to-end verification covering CAS deduplication, route serving, and LRU pruning
* fix(runner): align SDK pin and workspace-aware integration fixtures
* fix(ci): format sources and resolve current migration head
* test(persistence): align standalone migration fixtures with current models
* test(web): align smoke fixtures with current processor UI
---------
Co-authored-by: dadachann <[email protected]>
* fix(cntfilter): allow legacy sensitive-word lists over 64 patterns
Legacy sensitive-words.json files shipped ~70 rules. After v4.10.7,
BanWordFilter treated the 64-pattern safe_regex cap as a hard failure
and blocked every message. Raise the cap only on the sensitive-word
path, keep the 50ms CPU budget, and truncate oversized lists with a
one-time warning.
Fixes#2443
* fix(cntfilter): reject oversized sensitive-word lists
---------
Co-authored-by: dadachann <[email protected]>
* fix(wecombot): align media upload protocol
* fix(wecombot): deliver outbox media in reply and fix tool call recording
- Integrate _send_media into reply_message and reply_message_chunk so
sandbox outbox images/voices/files are uploaded and sent instead of
being silently dropped.
- Add missing import base64 that caused _send_media to fail with a
NameError swallowed by its except clause.
- Change yiri2target to return component dicts (text/image/voice/file)
so callers can distinguish text from media.
- Fix _get_message_for_tool_context using result.first()/row[0] which
returned a raw string instead of the ORM object, causing
"'str' object has no attribute 'pipeline_id'" in tool call recording.
Use result.scalars().first() per SQLAlchemy 2.0 convention.
* fix(pipeline): collect outbox attachments on final chunk with empty content
When the last streaming chunk has is_final=True but empty content
(e.g. the LLM sends all text in earlier chunks), the 'if result.content'
branch is skipped entirely, so _append_outbound_attachments never runs
and sandbox outbox images are silently dropped.
Add an elif branch for _is_final_assistant_message that creates an
empty MessageChain and still collects outbox attachments, so images
are delivered even when the final chunk carries no text.
* fix(box): bypass stdout truncation when reading outbox via exec
_read_outbox_via_exec used execute_tool which returns _serialize_result
where stdout is truncated to output_limit_chars (4000). A 7KB JPEG
encodes to ~9400 base64 chars, so the JSON payload was truncated and
json.loads failed silently, returning an empty list.
Call client.execute directly to get the raw BoxExecutionResult with
untruncated stdout, so base64 file data is preserved.
* fix(tests): adapt box and wrapper tests for client.execute and strict is_final check
- wrapper.py: restrict outbox collection on empty-content chunks to
actual MessageChunk instances with is_final=True, not generic Mock
objects that happen to have role='assistant'
- test_box_service.py: update _read_outbox_via_exec tests to mock
client.execute (returning BoxExecutionResult) instead of
execute_tool, matching the implementation change
* chore(wecombot): remove temporary upload log
* test(box): preserve direct outbox read and cleanup coverage
---------
Co-authored-by: fdc310 <[email protected]>
Co-authored-by: dadachann <[email protected]>
The local-agent runner's system prompt is a static string with no
template-variable support, so the model had no anchor for "today" and
resolved relative time references (e.g. "this quarter", "latest")
against whichever period was best represented in training data instead
of the real date, sometimes confidently answering with stale
information for time-sensitive questions.
PreProcessor now appends a short, deterministically-computed
"Current date: ..." note to the system prompt on every request for
local-agent pipelines, alongside guidance to verify time-sensitive
facts with a search tool rather than answering from memory. The
existing skill-awareness prompt injection is refactored to share the
same append-to-system-prompt helper.
Expose skill tools (activate/register_skill/native exec) like native tools
instead of gating them behind the skill_authoring capability:
- toolmgr.get_all_tools drops include_skill_authoring; SkillToolLoader
self-gates on sandbox + skill_mgr
- preproc drops the include_skill_authoring branch; pipeline-bound skills
and the skills resource gate on skill_mgr presence
Persist activated skills into host.activated_skills conversation state so
they survive across runs (host writes at activate; last-write-wins); drop
the dead restore_activated_skills helper.
Prefill ToolResource.parameters host-side (tool_mgr.get_tool_schema) so
runners build LLM tools without per-tool get_tool_detail round-trips.
Align agent-runner-pluginization design docs to the all-tool model.
* feat: Implement workflow form handling for paused workflows
- Added module-level storage for pending forms to manage state across sessions.
- Introduced functions to set, get, and clear pending forms with expiration handling.
- Enhanced DifyServiceAPIRunner to support resuming paused workflows via form actions.
- Implemented logic to yield human input requests and display appropriate messages.
- Updated workflow submission methods to handle paused states and resume actions.
- Ensured proper merging of pending form actions with user inputs for seamless interaction.
* feat: Add '_routed_by_rule' variable to form action in Lark and Telegram adapters
* feat: Enhance Lark and Telegram adapters with new form handling for paused workflows
* feat: Enhance TelegramAdapter to handle form action buttons and message threading
* feat: Improve TelegramAdapter message handling with enhanced error management and draft message support
* feat: Add the function for formatting human input text to support adapters without rich UI.
* feat(dingtalk): implement human input card support and card action handling
- Add a new module `card_callback.py` to handle card action button clicks from DingTalk.
- Introduce `DingTalkCardActionHandler` to process card action callbacks and extract parameters.
- Update `DingTalkAdapter` to manage card state and handle form input through a single card template.
- Add configuration for `human_input_card_template_id` in `dingtalk.yaml` to specify the template for human input.
- Create a new card template `dingtalk_human_input_card.json` for rendering human input prompts and buttons.
* feat(dingtalk): enhance human input card functionality with streaming support and active turn management
- Updated the DingTalk card template to enable streaming mode and multi-update configuration.
- Removed the obsolete delete_card method from DingTalkClient to streamline card management.
- Enhanced DingTalkAdapter to manage active turn cards and accumulated streaming text, ensuring a seamless user experience during human input prompts.
- Modified the create_message_card method to utilize existing active cards for resumed workflows, preventing duplication.
- Improved the _paint_form_on_card method to update existing cards with human input prompts and buttons dynamically.
- Updated the dingtalk_human_input_card.json template to reflect the new streaming capabilities and configuration options.
* feat(wecom): implement Dify human input pause handling with button interaction support
* feat(qqofficial): implement Dify human input button interaction handling and markdown keyboard support
* feat(qqofficial): implement one-click QR binding and enhance localization support
* feat(discord): implement Discord form view with button interactions for Dify actions
* fix(telegram): correct group chat type check and handle oversized callback data for Telegram actions
fix(difysvapi): ensure safe access to remove-think configuration in pipeline settings
* feat(dify): add support for chatflow app type and enhance human input handling
* feat(telegram): add action title feedback for user selections in Telegram messages
* feat(lark): enhance LarkAdapter to store form content for resume notices
* feat(dingtalk): update display formatting for card content with HTML line breaks
* feat(dingtalk): add feedback functionality to cards with 👍/👎 buttons
- Implemented feedback state management for cards, allowing users to provide feedback via thumbs up/down buttons.
- Enhanced card rendering to include feedback buttons when appropriate.
- Registered feedback listeners to handle feedback events and update card states accordingly.
- Updated the card template to support dynamic button rendering for feedback actions.
- Improved error handling and logging for feedback actions and card updates.
* fix: add Avatar component to dingtalk_human_input_card.json for enhanced user interaction
* feat(wecom): add optional source block to interactive template cards for enhanced branding
* feat(wecom): add functions for template card action extraction and update, enhance button interaction handling
* feat(qqofficial): synchronize passive-reply counter with inbound message sequence
* feat(qqofficial): add method to identify invisible form placeholder chunks in messages
* feat(dingtalk): add download link for human input card template and enhance dynamic form configuration
* feat(telegram): enhance message handling with group stream deletion and form placeholder detection
* Add unit tests for DingTalk, Lark, WeComBot, and Dify service API runners
- Implement tests for DingTalk adapter helper functions including form content cleaning, input extraction, and completed input lines.
- Create unit tests for Lark adapter helper functions focusing on input extraction and completed input lines.
- Add tests for WeComBot template card functionalities, including event extraction and payload building for human input.
- Enhance Dify service API runner tests to cover human input forms, including input collection, action handling, and form snapshot extraction.
* feat: Enhance Telegram and QQ Official adapters with select field handling and form action processing
- Added support for select fields in Telegram adapter, including option extraction and callback handling.
- Implemented form action processing for Telegram callbacks, improving user interaction feedback.
- Introduced new helper functions for building keyboards and resolving select button actions in QQ Official adapter.
- Enhanced DifyServiceAPIRunner to handle cumulative streaming responses and improve error handling during workflow resumes.
- Added unit tests for new functionalities in Telegram and QQ Official adapters, ensuring robust behavior for select fields and form actions.
* feat(lark): add functions for current input definitions and visible form content handling
feat(qqofficial): update fallback text handling for non-streaming scenarios
feat(difysvapi): enhance form content processing for interactive fields and actions
test: add unit tests for Lark and QQ Official adapter functionalities
* Add tests for DingTalk adapter content processing and markdown formatting
- Updated the assertion in `test_dingtalk_completed_input_lines_include_text_and_select_values` to remove unnecessary markdown formatting.
- Added new tests to verify that `_dingtalk_clean_form_content` maintains the order of prompts and completed values in various scenarios.
- Introduced `test_dingtalk_card_markdown_preserves_internal_line_breaks` to ensure internal line breaks are correctly converted to HTML line breaks.
* feat: Refactor input handling and feedback messages across multiple adapters
* feat: Update the human-computer interaction template cards, and optimize the prompt information and content display.
* feat: Refactor pending form handling to isolate by bot and pipeline
* feat: Enhance error handling and caching for Dify and WeCom interactions
* feat: Enhance select input handling and validation in Dify API runner and Telegram adapter
* feat: Add missing completed input lines handling in DingTalk adapter
* feat: Add pipeline_uuid handling across multiple adapters and update related tests
* feat(box): bidirectional attachment transfer for sandbox
Materialize inbound attachments into the sandbox workspace so agents can
process user-sent files, and collect agent-produced files from the outbox
to attach them back to the reply.
- box(service): add materialize_inbound_attachments / collect_outbound
attachments. Prefer direct host-filesystem read/write on the bind-mounted
workspace (no size limit), falling back to chunked exec only for
non-shared backends (e2b/remote). Clear per-query inbox/outbox dirs at
turn start to avoid query_id-reuse collisions.
- provider(localagent): inject inbound attachment descriptors into the
sandbox and append a system note telling the agent the inbox/outbox paths.
- pipeline(wrapper): collect outbox files on the final stream chunk and
append them as attachment components to the response chain.
- web(debug-dialog): render File components with a download link when
base64/url is present; add base64/path fields to the File entity.
- tests: cover inbound/outbound, large-file transfer without truncation,
and stale-dir clearing (86 passing).
* feat(box): support voice/file attachment round-trip end-to-end
Extends the bidirectional attachment transfer to audio and arbitrary files
through the real webchat UI, and fixes the model-payload errors that
non-image attachments triggered.
- platform(websocket_adapter): resolve Voice/File component storage keys to
base64 (previously only Image), so audio/documents reach the sandbox inbox.
- web(debug-dialog): accept audio/* and any file in the uploader (was
image-only), classify by mimetype, upload Voice/File via the documents
endpoint, and render non-image staged attachments as a chip.
- provider(litellmchat): drop non-image file parts (file_base64 / file_url)
when building the OpenAI/LiteLLM payload. These come from Voice/File
attachments — including ones replayed from conversation history — and the
agent reads their bytes from the sandbox, not the model. Without this the
provider rejects the request: 'invalid content type=file_base64'.
- provider(localagent): also strip those parts from the current user message
alongside the sandbox-path note (model-facing clarity; the requester is the
real safety net for history).
- tests: cover the requester strip/keep behavior (file dropped, image kept and
reshaped to image_url, mixed history, plain-string content).
* test(box): cover inbound/outbound attachment helpers; fix ruff format
- ruff format localagent.py (CI ruff format --check was failing)
- add unit tests for ResponseWrapper outbound-attachment helpers (wrapper.py 78%->98%)
- add unit tests for LocalAgentRunner._inject_inbound_attachments
- add unit tests for WebSocketAdapter._process_image_components (0%->covered)
Lifts PR patch coverage from 68.97% to ~88% (>75% target).
* refactor(provider): use LiteLLM as unified LLM requester backend
- Replace 23+ individual requester implementations with unified litellmchat.py
- Add litellm_provider field to 27 YAML manifests for provider routing
- Delete redundant requester subclasses
- Add unit tests for LiteLLMRequester (29 tests)
- Fix num_retries parameter name (was max_retries)
- Fix exception handling order for subclass exceptions
LiteLLM provides unified API for 100+ providers, eliminating need for
provider-specific requesters.
* fix: ruff format provider.py
Co-Authored-By: Claude Opus 4.7 <[email protected]>
* refactor(provider): simplify LiteLLM requester usage handling
- Remove unused Anthropic-specific tool schema generation
- Share completion argument construction between normal and streaming calls
- Use LiteLLM/OpenAI native usage fields for monitoring
- Collect stream token usage from LiteLLM stream_options
- Update LiteLLM requester tests for unified usage fields
* restore: restore deleted provider requester files
Restore individual provider requester implementations that were
removed in de61b5d3. These files coexist with the unified
litellmchat.py backend.
Co-Authored-By: Claude Opus 4.7 <[email protected]>
* feat: update requesters and improve provider selection UI
- Added `litellm_provider` field to various requesters' YAML configurations.
- Removed obsolete Python requester files for OpenRouter, PPIO, QHAIGC, ShengSuanYun, SiliconFlow, Space, TokenPony, VolcArk, and Xai.
- Introduced new requesters for Tencent and Together AI with corresponding YAML configurations and SVG icons.
- Enhanced the ProviderForm component to include a searchable dropdown for selecting providers, improving user experience.
- Updated localization files to include search provider text for both English and Chinese.
* fix(provider): align litellm rebase with master
* fix(provider): capture streaming token usage; add token observability
The LiteLLM streaming requester only captured usage when a chunk had an
empty `choices` list. Many OpenAI-compatible gateways (e.g. new-api) and
providers send the final usage payload in a chunk that still carries an
empty-delta choice, so streamed calls always recorded 0 tokens in the
monitoring logs/dashboard (non-streaming worked).
- Capture stream usage whenever a chunk carries it, regardless of choices
- Add robust _normalize_usage (dict/obj shapes, derive missing total_tokens)
- Register litellm in bootutils/deps.py (was in pyproject only)
- Add MonitoringService.get_token_statistics + /monitoring/token-statistics
endpoint: summary, per-model breakdown, token timeseries, and a
zero-token-success data-quality signal
- Add TokenMonitoring dashboard tab (summary tiles, stacked token chart,
per-model table) + i18n (en/zh)
- Regression tests for stream usage capture and usage normalization
Verified end-to-end against a real OpenAI-compatible endpoint with
gpt-5.5 and claude-opus-4-8: tokens now recorded non-zero for both
streaming and non-streaming paths.
* refactor(provider): simplify litellm capabilities
* style: simplify wrapped expressions
* feat(models): persist context metadata
* fix(provider): handle dict embeddings and openai-compatible rerank in LiteLLMRequester
- invoke_embedding: support both object- and dict-shaped response.data
entries (OpenAI-compatible gateways like new-api return dicts)
- invoke_rerank: litellm.arerank rejects the 'openai' provider, so for
openai-compatible (or unspecified) providers call the standard
Jina/Cohere-style POST /v1/rerank endpoint directly over HTTP
- accept both 'relevance_score' and 'score' fields in rerank results
- add unit tests for the openai-compatible HTTP rerank path
* feat(provider): enforce requester support_type when adding models
- frontend: AddModelPopover only shows model-type tabs (llm/embedding/
rerank) that the provider's requester declares in its manifest
support_type; ModelsDialog fetches requester manifests and maps
requester -> support_type, passed down through ProviderCard
- backend: add _validate_provider_supports guard in create_llm_model /
create_embedding_model / create_rerank_model so a model cannot be
attached to a provider whose requester does not support that type,
even if the frontend restriction is bypassed (manifests without
support_type are allowed for backward compatibility)
- manifests: correct support_type for providers that do not offer all
three model types:
- llm only: anthropic, deepseek, groq, moonshot, openrouter, xai
- llm + text-embedding: openai, gemini, mistral
- add rerank to new-api (verified working via /v1/rerank)
- set llm + text-embedding + rerank for aggregator/unknown gateways
* feat(provider): add searchable alias to requester manifests
- add a free-text 'alias' field to every requester manifest spec,
containing the vendor's English/Chinese names, pinyin, common
nicknames and flagship model-series names (e.g. moonshot -> kimi,
月之暗面; zhipu -> glm, 智谱清言)
- frontend: ProviderForm requester search now also matches against
alias (substring/contains), so searching 'kimi' surfaces Moonshot,
'硅基' surfaces SiliconFlow, etc.
- also fix support_type: openrouter (relay) supports embedding+rerank;
LangBot Space gains rerank (coming soon)
* fix(provider): make support_type guard defensive against incomplete model_mgr
- _validate_provider_supports now uses getattr to gracefully skip when
model_mgr / provider_dict / manifest lookup is unavailable, instead of
raising AttributeError (fixes unit tests that mock ap.model_mgr as a
bare SimpleNamespace)
- add TestValidateProviderSupports covering: allow supported type,
reject unsupported type, allow when support_type missing, allow when
provider unknown, degrade safely when model_mgr is incomplete
* fix(persistence): guard 0004 migration against missing llm_models table
The 0004_add_llm_model_context_length migration called
inspector.get_columns('llm_models') unconditionally, raising
NoSuchTableError when the table does not exist (e.g. migrating a
fresh/empty DB, as exercised by the integration tests where
create_all() registers no tables because the ORM models are not
imported). Every other migration guards with a table-existence check
first; add the same guard here for both upgrade and downgrade.
Also restore the test head assertion to 0004 (it had been lowered to
0003 to mask this failure).
* Merge branch 'master' into feat/litellm
Resolve conflicts:
- uv.lock: regenerated via 'uv lock' to reconcile litellm/fastuuid
(ours) with openai bump (master).
- Alembic migrations: master added 0004_add_mcp_readme while this
branch added 0004_add_llm_model_context_length, both as children of
0003 (would create multiple heads). Re-chain the litellm migration as
0005_add_llm_model_context_length with down_revision=0004_add_mcp_readme
for a single linear head. Update test head assertion accordingly.
* fix(persistence): shorten migration revision id to fit varchar(32)
PostgreSQL stores alembic_version.version_num as varchar(32).
'0005_add_llm_model_context_length' (33 chars) overflowed it, raising
StringDataRightTruncationError in the PG migration tests. Rename the
revision (and file) to '0005_add_llm_context_length' (27 chars) and
update the head assertions in both SQLite and PostgreSQL migration
tests.
---------
Co-authored-by: Claude Opus 4.7 <[email protected]>
Co-authored-by: fdc310 <[email protected]>
Co-authored-by: RockChinQ <[email protected]>
Counts successful non-WebSocket bot responses (persisted in the metadata
table as survey_bot_response_count, survives restarts) and fires the
bot_response_success_100 survey event once the instance reaches 100
responses. Counting stops after the milestone has been triggered.
Existing first_bot_response_success behavior unchanged. 6 new unit tests.
Hyu