* fix(terminal): reconnect to running executions after page refresh
* fix(terminal): use ExecutionEvent type instead of any in reconnection stream
* fix(execution): type event buffer with ExecutionEvent instead of Record<string, unknown>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(execution): validate fromEventId query param in reconnection endpoint
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* Fix some bugs
* fix(variables): fix tag dropdown and cursor alignment in variables block (#3199)
* feat(confluence): added list space labels, delete label, delete page prop (#3201)
* updated route
* ack comments
* fix(execution): reset execution state in reconnection cleanup to unblock re-entry
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(execution): restore running entries when reconnection is interrupted by navigation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* done
* remove cast in ioredis types
* ack PR comments
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Siddharth Ganesan <siddharthganesan@gmail.com>
* feat(providers): add Gemini Deep Research via Interactions API
* fix(providers): hide memory UI for deep research models
* feat(providers): add multi-turn support and token logging for deep research
* fix(providers): only collect user messages as deep research input
* fix(providers): forward previousInteractionId to provider request
* fix(blocks): hide memory child fields for deep research models
* remove memory params from models that don't support it in provider requests
* update blog
* fix(execution): scope execution state per workflow to prevent cross-workflow bleed
* fix(execution): use validated workflowId param instead of non-null assertion in handleRunUntilBlock
* improvement(execution): use individual selectors to avoid unnecessary re-renders from unselectored store hook
* improvement(execution): use useShallow selector in workflow.tsx to avoid re-renders from lastRunPath/lastRunEdges changes
Adds the AgentSkillsIcon to trace spans in logs when displaying the
load_skill tool. Previously, skills appeared with a default gray color.
Now they display with the proper skill icon and a purple (#8B5CF6)
background color, consistent with the skills icon used in the settings
modal and skill input components.
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Emir Karabeg <emir-karabeg@users.noreply.github.com>
* improvement(preview): added trigger mode context for deploy preview
* use existing helper
* enhance disabled mode for subblocks
* update
* update all subblocks to allow scrolling in read only mode
* updated short and long input to match others, reverted triggerutils change
* fix(mcp): harden notification system against race conditions
- Guard concurrent connect() calls in connection manager with connectingServers Set
- Suppress post-disconnect notification handler firing in MCP client
- Clean up Redis event listeners in pub/sub dispose()
- Add tests for all three hardening fixes (11 new tests)
* updated tests
* plugged in new mcp event based system and create sse route to publish notifs
* ack commetns
* fix reconnect timer
* cleanup when running onClose
* fixed spacing on mcp settings tab
* keep error listeners before quiet in redis
* feat(models): updated model configs, updated anthropic provider to propagate errors back to user if any
* moved max tokens to advanced
* updated model configs and testesd
* removed default in max config for output tokens
* moved more stuff to advanced mode in the agent block
* stronger typing
* move api key under model, update mistral and groq
* update openrouter, fixed serializer to allow ollama/vllm models without api key
* removed ollama handling
* improvement(preview): nested workflow snapshots/preview when not executed
* improvements to resolve nested subblock values
* few more things
* add try catch
* fix fallback case
* deps
* fix(logs): execution files should always use our internal route
* correct degree of access control
* fix tests
* fix tag defs flag
* fix type check
* fix mcp tools
* make webhooks consistent
* fix ollama and vllm visibility
* remove dup test
* feat(icons): add Airweave icon and update registry with Airweave block and tool
* feat(icons): add Airweave icon and update icon mapping and metadata
* fix(search): update API key header from Authorization to X-API-Key for Airweave search tool
* refactor(icon-mapping): reorder icon imports for consistency and formatting improvements; update airweave block retrieval strategy description formatting; add newline at end of meta.json
* refactor(search): update visibility settings for retrieval strategy and query options to allow access for both users and LLMs
