starred/aryx
1
0
Fork 0
mirror of https://github.com/davidkaya/aryx.git synced 2026-08-25 12:23:57 +02:00
Code Issues 3 Packages Projects Releases 10 Wiki Activity

feat: show sub-workflow agents and lifecycle in the Activity panel

Browse Source 
Deep agent resolution in the sidecar now walks sub-workflow nodes so
nested agents carry subworkflowNodeId and subworkflowName on activity
events. New subworkflow-started / subworkflow-completed activity types
let the frontend track sub-workflow lifecycle.

The Activity panel groups nested agents under collapsible sub-workflow
cards with status badges, accent-colored left borders, and smooth
expand/collapse transitions. Cards auto-expand when a sub-workflow
starts running. Workflows without sub-workflow nodes render identically
to before.

Extracted AgentRow, SubWorkflowGroup, and shared accent constants to
a new components/activity/ feature directory. Added
resolveWorkflowAgentHierarchy and buildGroupedActivityRows for
hierarchical activity grouping with dynamic fallback for unresolved
sub-workflow agents.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
David Kaya
2026-04-08 18:57:23 +02:00
co-authored by Copilot
parent fa8f6ef4b3
commit c70a5c6612
24 changed files with 2063 additions and 240 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ARCHITECTURE.md
+4 -2
View File
@@ -220,6 +220,8 @@ This protocol boundary keeps the AI execution runtime replaceable and prevents t
The protocol also carries **turn-scoped lifecycle events** alongside output deltas. These events let the UI visualize execution internals without the main process having to interpret AI workflow semantics:
- **Workflow activity events**: agent activity records preserve agent, tool, and optional sub-workflow context (`subworkflowNodeId`, `subworkflowName`) so the UI can distinguish root-level activity from nested execution without rebuilding workflow ancestry in Electron
- **Sub-workflow lifecycle events**: `subworkflow-started` and `subworkflow-completed` are emitted when nested workflow executors begin and finish, so the Activity panel can surface sub-workflow groups as first-class runtime activity
- **Sub-agent events**: started, completed, failed, selected, deselected — surfaced when custom agents are defined
- **Skill invocation events**: emitted when an agent-side skill is triggered
- **Message reclassification events**: let the sidecar retroactively mark a streamed assistant message as `thinking` once the SDK confirms that message requested tool work, so the UI can separate intermediate planning chatter from the final response without sacrificing live streaming
@@ -318,8 +320,8 @@ For git-backed projects, the renderer surfaces three specialized components. `Ru
The architecture treats execution as observable by design:
- partial output is streamed
- agent activity is surfaced
- turn-scoped lifecycle events (sub-agent, hook, skill, compaction, usage) are streamed
- agent activity is surfaced with optional sub-workflow context
- turn-scoped lifecycle events (sub-agent, sub-workflow, hook, skill, compaction, usage) are streamed
- runs are surfaced inline as collapsible turn activity panels
- failures are represented explicitly