- Introduced lazy knowledge base retrieval mode, allowing the main agent to fetch KB content on demand via the `search_knowledge_base` tool, improving performance by skipping expensive pre-injection processes.
- Added cross-thread caching capability, enabling reuse of compiled graphs across different user chats, reducing latency for returning users.
- Updated middleware to support new lazy loading and caching features, ensuring efficient resource utilization and improved response times.
- Enhanced logging for performance tracking during knowledge retrieval and agent interactions.
- Added a new backend URL import to the route file for better configuration.
- Updated the Composer component to use a relative positioning class for improved layout.
- Refactored the ChatExamplePrompts component to enhance the display of active categories and prompts, including a close button for better user interaction.
- Added a new utility function `isLlmOnboardingComplete` to determine if the onboarding process is complete based on the agent LLM ID and the presence of global configurations.
- Updated the onboarding logic in the `OnboardPage` and `DashboardClientLayout` components to utilize the new utility function for improved readability and maintainability.
- Updated the backend URL initialization to use a function that retrieves the URL from environment variables, enhancing configurability for different environments.
- Modified backend URL assignment to ensure it resolves correctly within the internal Docker network, preventing 503 errors for authenticated Zero queries.
- Added comments to clarify the routing behavior and the necessity of using the internal backend URL.
Step results now render from the synced Zero row so the panel ticks
forward as the run progresses. The REST getRun call is gated on the
run reaching a terminal status, since output/artifacts/error are only
written at terminal mark.
- Revised the pricing page title and description to reflect new features including AI workspace, automations, and agents.
- Enhanced the FAQ section with detailed information about AI automations and agents, including scheduling and event-triggered workflows.
- Updated demo plans to include features related to AI automations and agents, ensuring clarity on capabilities and costs.
- Added a new automation illustration to the homepage features grid, emphasizing the automation capabilities of SurfSense.
- Removed the eligibility gate for model selection in the automation creation process, allowing users to choose models directly in the builder.
- Updated the `AutomationBuilderForm` to incorporate model selection logic, ensuring that selected models are validated and preserved during automation creation and editing.
- Simplified the `AutomationsContent` and `AutomationNewContent` components by eliminating unnecessary eligibility checks and alerts.
- Enhanced the user experience by integrating model selection directly into the automation approval process, ensuring that only billable models are used.
- Refactored related tests to cover new model selection behavior and ensure proper validation of user-selected models.
- Improved the layout and readability of the run details panel by restructuring sections and adding collapsible error views.
- Introduced a new `RunErrorSection` component to present run-level errors more clearly, allowing users to toggle raw error details.
- Updated the handling of run outputs, step results, and artifacts for better user experience.
- Refactored duration calculation in `RunRow` to utilize a dedicated `formatDuration` function for consistency.
- Added a new `RunStepResult` interface to improve type safety and clarity in handling step results.
- Added model eligibility checks to ensure automations can only use billable models (premium or BYOK).
- Introduced new API endpoint to report model eligibility status for search spaces.
- Updated frontend components to display eligibility alerts and disable creation options when models are not billable.
- Enhanced automation creation forms to reflect model eligibility, preventing users from submitting invalid configurations.
- Implemented server-side logic to capture and preserve model preferences across automation edits, ensuring consistent behavior during execution.
- 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.
- Replaced the FileJson icon with SquarePen in both AutomationsEmptyState and AutomationsHeader components.
- Updated button label from "Create via JSON" to "Create manually" for clarity in the automation creation process.
- Added support for @-mentions in agent tasks, allowing users to reference documents, folders, and connectors directly in their queries.
- Updated `run_agent_task` to resolve mentions and include them in the context passed to the agent.
- Introduced new parameters in `AgentTaskActionParams` for handling mentioned document and connector IDs.
- Refactored the automation edit and new components to utilize the new `AutomationBuilderForm` for a more streamlined user experience.
- Removed deprecated JSON forms to simplify the automation creation process.
Recent runs card under triggers. Each row expands lazily to fetch the
full run (step results, output, artifacts, error). 20-row cap for now;
real pagination lands if usage demands it.
