Skip to content

v0.96: first useful reconstruction without new capture - #100

Merged
KAVentures merged 16 commits into
mainfrom
feat/first-value-activation-v096
Sep 28, 2026
Merged

KAVentures merged 16 commits into
mainfrom
feat/first-value-activation-v096

Conversation

@KAVentures

Copy link
Copy Markdown
Owner

Summary

This adds a thin first-run activation layer on top of the existing v0.95 evidence stack so a user can understand OpenWorkGraph during the first real work session without weakening or replacing existing functionality.

  • Overview gets a dismissible See what OpenWorkGraph understands card.
  • Progress is evidence-driven (observed events, work surfaces, transitions, agent runs), not a countdown.
  • Once enough current-session evidence exists, Your last few minutes renders a deterministic reconstruction from existing privacy-hardened dashboard evidence and existing structural agent-run reports.
  • Focus-only workflows can still become useful: existing observed surface transitions are used as a factual fallback when interaction-level rows are sparse.
  • Conditional CTAs point to the already-existing Connect AI, browser-sensor and agent-telemetry setup surfaces; nothing is auto-enabled.
  • The stale timeline placeholder and empty repeated-workflows card are suppressed until useful, without removing their underlying DOM/data paths.
  • Small time-to-first-value milestones are stored only in local browser storage for dogfooding; they are not transmitted.

Strict compatibility/privacy boundary

This PR adds no new capture sensor, screenshots, filesystem watcher, browser/OS permission, prompt/response capture, typed-text capture, clipboard-content capture, database schema, retention rule, saved-history lease, Gateway behavior, organization-sharing behavior, agent-ingest capability, export format, or MCP tool.

The activation layer performs GET requests only against existing authenticated local endpoints. It cannot write canonical evidence, enable AI access, retain history, or synchronize evidence.

Polling is intentionally lightweight: it runs only while the Overview first-value guide is relevant/visible, summary refresh is every 15s, and the more expensive agent-trace read is cached for 30s. Dismissing the guide stops activation polling.

Release

Version sources are aligned to 0.96.0. Existing macOS/Windows/Claude/custom-agent SDK release jobs remain unchanged except for release notes. Please gate merge on the full Python matrix, browser JS, Gateway/Postgres, macOS/Windows packages, Claude MCPB, and SDK packaging.

@KAVentures
KAVentures merged commit 8226792 into main Sep 28, 2026
10 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant