v0.2.2 Campaign

Objective

Stabilize and deepen comparative campaign execution by improving reporting, observability, browser evidence realism, and a minimal real MCP path.

Scope

• campaign report quality
• campaign semantic summaries
• runtime observability
• richer BrowserEvidence fixtures and browser-oriented rubrics
• partial real MCP via stdio subprocess path
• docs and capability classification alignment

Non-goals

• remote/IDE-hosted MCP integrations
• dashboards
• cloud orchestration
• changing default offline CI behavior

Exit criteria

• campaign docs are aligned
• campaign reporting artifacts validate
• browser evidence fixtures validate
• MCP stdio path is tested and documented as partial
• uv run just ci passes

Verification

• uv run just ci
• uv run pytest tests/ --ignore=tests/integration
• uv run alwm validate examples/campaign_runs/multi_suite/manifest.json campaign_manifest
• uv run alwm validate examples/campaign_runs/multi_suite/campaign-summary.json campaign_summary
• uv run alwm validate examples/campaign_runs/multi_suite/campaign-semantic-summary.json campaign_semantic_summary

Next milestone

v0.2.3 shipped: docs/releases/v0.2.3.md. v0.2.4 shipped: docs/releases/v0.2.4.md. v0.2.5 shipped: docs/releases/v0.2.5.md.