v0.96: first useful reconstruction without new capture - #100
Merged
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
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.
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.