Closes the create loop in chat: the agent describes user intent → the
drafter sub-LLM produces an AutomationCreate JSON → this card surfaces
a structured preview → approve persists; reject cancels. Edits flow
through chat refinement (re-call with a refined intent), not in-card,
so the card stays simple and the multi-turn checkpointer carries the
context.
Tool UI (components/tool-ui/automation/):
- create-automation.tsx — entry dispatcher + ApprovalCard chrome
(pending/processing/complete/rejected via useHitlPhase) + SavedCard
(links to the detail page) + InvalidCard (lists drafter validation
issues) + ErrorCard (verbatim message). Rejection result is hidden
because the approval card itself shows the rejected phase inline.
- automation-draft-preview.tsx — structured preview body: name +
description + goal, triggers (humanised cron + tz + static-input
keys), plan steps (step_id → action), and a collapsible raw JSON
for power users.
Wiring:
- components/tool-ui/index.ts — re-export.
- features/chat-messages/timeline/tool-registry/registry.ts —
register create_automation → CreateAutomationToolUI (dynamic import,
same pattern as other connector tools).
- contracts/enums/toolIcons.tsx — Workflow icon + "Create automation"
display name so fallback chrome (and timeline headers) are honest.
Shared util:
- lib/automations/describe-cron.ts — lifted from the route slice's
lib/ folder since both the dashboard slice and the new approval card
now render schedule descriptions. Slice imports updated; the now-
empty slice lib/ folder is gone.
Backend prompt fragments:
- main_agent/system_prompt/.../create_automation/description.md and
the tool's docstring no longer promise in-card edits. They make the
refinement path explicit: if the user wants changes after seeing the
draft, they reply in chat and the agent calls the tool again with a
refined intent.
v1 deliberately excludes:
- In-card edit form / right-side edit panel — defer until we see real
demand. The chat refinement loop covers the common case.
- approve_always / persistent allow rules — automations are a single
artifact, not a repeated mutation, so the "trust this kind of call"
affordance doesn't apply.
- Added a new tool for generating structured Markdown reports based on user input.
- Implemented routes for creating, reading, exporting, and deleting reports.
- Integrated report generation into the chat flow, allowing users to generate reports inline.
- Updated schemas to support report data structures and responses.
- Enhanced frontend components to handle report generation and display results.
- Create CreateNotionPageToolUI component with approval card (approve/reject)
- Handle data-interrupt-request SSE event in page.tsx
- Add handleResume callback to POST decisions and stream continuation
- Skip message persistence for interrupted messages (handleResume persists)
- Stamp __decided__ on tool results for immutable post-decision state
- Sync pendingInterrupt ID after message persistence rename
- Removed the write_todos tool as it is now included by default through TodoListMiddleware in the deep agent.
- Updated the system prompt and documentation to reflect the integration of TodoListMiddleware, clarifying its capabilities for managing planning and todo lists.
- Enhanced the chat handling logic to extract todos directly from the deep agent's command output, ensuring seamless user experience.
- Refactored UI components to align with the new data structure and improve rendering of todo items, including updates to the Plan and TodoItem components.
- Cleaned up code for better maintainability and readability, following recent refactoring efforts.
- Refactored the write_todos tool to enhance argument and result schemas using Zod for better validation and type safety.
- Updated the WriteTodosToolUI to streamline the rendering logic and improve loading states, ensuring a smoother user experience.
- Enhanced the Plan and TodoItem components to better handle streaming states and display progress, providing clearer feedback during task management.
- Cleaned up code formatting and structure for improved readability and maintainability.
- Added a new write_todos tool to facilitate the creation and management of planning lists within the chat interface.
- Updated system prompt with detailed instructions on using the write_todos tool, including usage patterns and restrictions.
- Enhanced the chat message handling to support the new tool, ensuring proper integration and user experience.
- Implemented UI components for displaying and interacting with the planning lists, including progress tracking and status indicators.
