Adds an Electron install check that repairs incomplete or wrong-architecture binaries
Runs the check during root postinstall and before electron dev startup
Adds tests and docs for the new ensure:electron workflow
Expands when screenshots, recordings, or measurements are required
Adds evidence-gap as a distinct review classification
Aligns CONTRIBUTING guidance with the updated review policy
Removes the separate review check and relies on review labels/comments instead
Marks workflow/tooling failures with review:automation-failed
Updates review guidance to reflect the advisory verdict model
Require reading .github/PULL_REQUEST_TEMPLATE.md alongside AGENTS.md and CONTRIBUTING.md
Tighten guidance for loading matching skills and task-required references before editing
Add PR handoff expectations for concrete evidence and rollback considerations
* docs(agents): add step-by-step workflows with posting and label procedures
Add numbered step-by-step workflows to all four automation agents
(pr-review, reproduce-issue, summarize, triage), each with an explicit
comment-posting sub-procedure: draft once, post via gh, capture result,
verify by reading comments back only, and retry once on failure.
pr-review also gains a Labels section that applies confidence:* and
risk:* labels matching the review scores, removing stale labels first
to avoid stacking. merge-conflict:true is left to its dedicated action.
triage renames its label-selection steps to Category 1-5 to avoid
colliding with the new workflow step numbering.
* fix(agents): avoid duplicate comments after ambiguous posts
---------
Co-authored-by: Bohdan Triapitsyn <artmore@protonmail.com>
Adds safe PR review automation for pull requests and /oc-review comments
Supports fork PR review without checking out or executing untrusted code
Defines a dedicated read-only PR review agent
Electron updater now uses Electron release metadata only
Removed legacy Tauri package and migration workflow
Replaced Tauri shim usage with the desktop bridge
Bohdan Triapitsyn