Track blocks are YAML-fenced sections embedded in markdown notes whose output
is rewritten by a background agent. Three trigger types: manual (Run button or
Copilot), scheduled (cron / window / once with a 2 min grace window), and
event-driven (Gmail/Calendar sync events routed via an LLM classifier with a
second-pass agent decision). Output lives between <!--track-target:ID-->
comment markers that render as editable content in the Tiptap editor so users
can read and extend AI-generated content inline.
Core:
- Schedule and event pipelines run as independent polling loops (15s / 5s),
both calling the same triggerTrackUpdate orchestrator. Events are FIFO via
monotonic IDs; a per-track Set guards against duplicate runs.
- Track-run agent builds three message variants (manual/timed/event) — the
event variant includes a Pass 2 directive to skip updates on false positives
flagged by the liberal Pass 1 router.
- IPC surface: track:run/get/update/replaceYaml/delete plus tracks:events
forward of the pub-sub bus to the renderer.
- Gmail emits per-thread events; Calendar bundles a digest per sync.
Copilot:
- New `tracks` skill (auto-generated canonical schema from Zod via
z.toJSONSchema) teaches block creation, editing, and proactive suggestion.
- `run-track-block` tool with optional `context` parameter for backfills
(e.g. seeding a new email-tracking block from existing synced emails).
Renderer:
- Tiptap chip (display-only) opens a rich modal with tabs, toggle, schedule
details, raw YAML editor, and confirm-to-delete. All mutations go through
IPC so the backend stays the single writer.
- Target regions use two atom marker nodes (open/close) around real editable
content — custom blocks render natively, users can add their own notes.
- "Edit with Copilot" seeds a chat session with the note attached.
Docs: apps/x/TRACKS.md covers product flows, technical pipeline, and a
catalog of every LLM prompt involved with file+line pointers.
Added blocks to notes and updated assistant skill with this.
Image blocks — images with alt text and captions
Embed blocks — inline YouTube videos, Figma designs, or link cards
Chart blocks — line, bar, and pie charts from inline data or JSON files
Table blocks — styled data tables with named columns
connected-accounts UI
This refactor simplifies OAuth storage/IPC and updates the Electron UI
to use the new client-facing contract. OAuth state is now persisted per
provider with tokens, optional clientId, and an error string. A new oauth:getState
IPC returns only client-facing state (connected + error), and the UI renders
error/reconnect flow based on that.
Core changes
- Replace OAuth config with providers { tokens, clientId?, error? }
and add zod-based migration from legacy token maps.
- Persist Google clientId after successful OAuth and keep error state
in repo.
- Surface provider errors from refresh/credential failures in Google +
Fireflies.
- Add oauth:getState in IPC, returning client-facing config; remove
old status wiring in the UI.
UI changes
- Switch renderer status checks to oauth:getState and derive connected/error
from config.
- Add alert dialog for account issues and update copy to “Connected
accounts”.
- Provide “View connected accounts” CTA that opens the Connectors popover.
- Add shadcn alert-dialog component and Radix dependency.
Notes
- Adds @radix-ui/react-alert-dialog and shadcn wrapper.
- pnpm-lock updated accordingly.
- Add background task scheduling system with cron-based triggers
- Add background-task-detail component for viewing agent status
- Add agent schedule repo and state management
- Update sidebar to show background agents section
- Remove old workflow-authoring and workflow-run-ops skills
- Add IPC handlers for agent schedule operations
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Allow users to ask copilot to use Slack on their behalf via Composio integration.
Adds composio client, OAuth flow, slack skill with tool catalog, and UI for
connecting Slack in onboarding and connectors popover.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Move the presentation implementation out of the skill string into real
TypeScript files (types.ts, presentation-generator.tsx) and add a
generatePresentation builtin tool so the agent calls it directly instead
of writing code. Rewrite the skill to guidance-only with content limits,
preference gathering, and JSON examples for each slide type.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
