v0.25.0
What's New in v0.25.0
Bug Fixes
-
SKILL.md content injection restored (#190) — The copilot-sdk executor now injects SKILL.md content into the model's system prompt via
SystemMessage. The target skill's full body is injected, with compact summaries for all discovered skills. This was a regression from PR #140 which removed explicit injection. -
Trigger tests now receive fixture files (#186) — Trigger test runner loads fixture files from
context_dironce at init and passes them to every trigger execution request. Previously, trigger tests ran with an empty workspace. -
MCP servers config now passed to copilot session (#180) — The
mcp_serverssection in eval YAML is now properly forwarded to the copilot SDK session, making MCP tools available to the agent during evals.
Features
- Eval coverage grid generator (#82) — New
waza coveragecommand generates a coverage matrix showing which eval tasks exercise which graders and skill capabilities.
Documentation
- Updated CLI reference, README, and site docs for v0.23+ features (#167)
Release
- Includes all changes from v0.24.0 release prep (#161)
Full Changelog: azd-ext-microsoft-azd-waza_0.23.0...v0.25.0