[Feat]: Automations / Event-driven trigger type with document.entered_folder #3
Closed
CREDO23 wants to merge 1188 commits into
Closed
[Feat]: Automations / Event-driven trigger type with document.entered_folder #3CREDO23 wants to merge 1188 commits into
CREDO23 wants to merge 1188 commits into
Conversation
LiteLLM normalizes every provider's cache fields onto usage.prompt_tokens_details (cached_tokens + cache_creation_tokens). The earlier fallback to usage.cache_read_input_tokens / usage.cache_creation_input_tokens was wrong: Anthropic-shaped fields only live there via a trailing setattr loop, and the canonical field name on the wrapper is cache_creation_tokens (not _input_tokens).
embed_texts holds a threading.Lock and runs a sync embedding call inside search_knowledge_base, an async coroutine on the KB priority middleware critical path. Blocking the event loop here stalls every other coroutine on the worker (SSE keepalives, concurrent chat requests, background tasks). Wrap in asyncio.to_thread so the embed runs on the default executor pool while the loop keeps serving.
_create_document and _update_document run on the chat critical path when the filesystem subagent writes via the user's chat turn. Both called embed_texts synchronously inside an async coroutine, blocking the event loop for the duration of the embed.
generate_document_summary and create_document_chunks are async helpers called from the chat path and from many connector indexers. Both wrapped embed_text/embed_texts directly inside the coroutine, blocking the event loop for the full duration of the embedding call.
_restore_in_place_document and _reinsert_document_from_revision are async helpers invoked by the synchronous-feeling POST /api/threads/.../revert route; both ran embed_texts inline, blocking the event loop while the HTTP client waited.
…orkers Connector kb_sync_services (gmail, onedrive, google_calendar, jira), streaming indexers (discord, luma, teams) and the file-processor save path all called embed_text inside async coroutines, blocking the background worker's event loop for the duration of the embed. Wrap each call site in asyncio.to_thread so concurrent indexing tasks stop serialising on the embed.
…ile-hook fix: use shared useIsMobile (768px) in SidebarSlideOutPanel (MODSetter#1359)
…rom the new chat agent
…tive 429 recovery
The preflight pattern probed the LLM with a 1-token ping before each
cold turn (when requested_llm_config_id==0, llm_config_id<0, and the
45s healthy TTL had expired) to detect 429s before fanning out into
planner/classifier/title-gen. To absorb its ~1-5s RTT cost we built the
agent speculatively in parallel; on 429 we discarded the build and
repinned.
Three problems with that design:
1. False security. Provider rate limits are token-bucket. A 1-token
ping consumes ~5 tokens; the real request consumes 10-50K. The
probe can return 200 while the real call still 429s.
2. Pure overhead in the common case. On warm-agent-cache turns the
probe dominates wall time: ~2.5s of TTFT pure tax for ~99% of users
who never see a 429.
3. The in-stream recovery loop (catch of _is_provider_rate_limited
gated by not _first_event_logged) already does the right thing
reactively: mark_runtime_cooldown -> resolve_or_get_pinned_llm_config_id
with exclude_config_ids={previous} -> rebuild agent -> retry the
stream. Preflight was never the only safety net; it was a redundant
probe in front of one.
Changes:
- Delete _preflight_llm, _settle_speculative_agent_build, and the
_PREFLIGHT_TIMEOUT_SEC / _PREFLIGHT_MAX_TOKENS constants.
- Drop the parallel agent_build_task / preflight_task plumbing in
both stream_new_chat and stream_resume_chat; build the agent inline
with await _build_main_agent_for_thread(...).
- Drop the unused is_recently_healthy / mark_healthy imports here
(still exported from auto_model_pin_service since OpenRouter
catalogue refresh and a few tests reference clear_healthy).
- Remove the obsolete preflight + settle-speculative tests from
test_stream_new_chat_contract.py.
Net: -447 LOC. ~2.5s removed from TTFT on every cold preflight-eligible
turn. 429 recovery path is unchanged - same repin/rebuild/retry, just
not paid in advance on the healthy path.
…responding unit tests
…t LLM Adds an optional planner LLM role wired through KnowledgePriorityMiddleware so KB query rewriting, date extraction, and recency classification run on a cheap model (e.g. gpt-4o-mini, Haiku, Azure nano) instead of the user's chat LLM. Operators opt in by setting is_planner: true on exactly one global config; without it, behavior is unchanged.
Splits the OpenAI-family gate into per-param predicates so AZURE and AZURE_OPENAI configs now receive prompt_cache_key for backend routing affinity (Microsoft auto-caches GPT-4o+ deployments at >=1024 tokens; the key clusters same-prefix requests on the same GPU pool and raises hit rate on turn 2+). prompt_cache_retention stays opted out for Azure because litellm 1.83.14's Azure transformer would drop it silently; revisit when Azure's supported params list is updated.
Release v0.0.24: UI revamp, multi-agent parallelization, citations & HITL improvements
Skip the ~1-3s MCP initialize + list_tools handshake on every cache miss by reading tool definitions from the connector row we already load. Lazy populate on first miss, self-heal on corrupt cache, zero schema migration.
…ection and job dependencies
…n job and simplifying test conditions
- Deleted the `search_surfsense_docs` tool and its associated files, streamlining the agent's toolset. - Updated various components and prompts to remove references to the now-removed tool, ensuring consistency across the codebase. - Adjusted documentation to direct users to the SurfSense documentation link for product-related queries instead.
feat: added basic UI for automations and removed surfsense docs in chat related code.
A standalone, domain-agnostic pub/sub seam: an EventBus that owns its subscriber registry and streams Event values from producers to listeners in process. Boundary-crossing (Celery/DB/workers) is left to subscribers, keeping the bus single-responsibility. Includes the immutable Event value object and full unit coverage.
…ered_folder events
CREDO23
changed the title
CREDO23
changed the title
CREDO23
force-pushed
the
feature-automations-v2
branch
2 times, most recently
from
b0f08f8 to
38b7385
Compare
Owner
Author
|
Closing — opened by mistake on the wrong repo. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
EventBus(app/event_bus/) with a typedEventCatalogand class-based pub/sub — decoupled from Celery (SRP)document.entered_folderas the first built-in event type, published via SQLAlchemyafter_commithooks (ORM-level CDC, no pg_notify daemon)eventtrigger type for automations, mirroring thescheduletrigger pattern (source → selector → inputs → dispatch)bulk_move_documentsto use ORM objects so session hooks fire correctlyeventtrigger typeTest plan
{{ inputs.folder_id }}in the query)uv run pytest tests/unit/