v0.4.3

Full Changelog: v0.4.2...v0.4.3

v0.4.2

Full Changelog: v0.4.1...v0.4.2

v0.4.1

Full Changelog: v0.4.0...v0.4.1

v0.4.0

What's Changed

• refactor: use MCP protocol to access mcp.run via SSE/stdio by @zshipko in #14

Full Changelog: v0.3.0...v0.4.0

v0.3.0

What's Changed

• cleanup: rename ignore-tools -> ignored-tools by @zshipko in #10
• docs: add mcp.run setup by @zshipko in #12
• chore(docs): small typo by @nilslice in #13
• feat: Evals for pre-existing task runs by @zshipko in #11

New Contributors

• @nilslice made their first contribution in #13

Full Changelog: v0.2.1...v0.3.0

v0.2.1

What's Changed

• cleanup: more tests, improve output of multiple results by @zshipko in #8

Full Changelog: v0.2.0...v0.2.1

v0.2.0

What's Changed

• chore: update to mcp-run client with oauth support by @zshipko in #7

Full Changelog: v0.1.4...v0.2.0

v0.1.4

What's Changed

• fix: improve separation of judge and test profiles by @zshipko in #6

Full Changelog: v0.1.3...v0.1.4

v0.1.3

What's Changed

• fix: judge profile by @zshipko in #5

Full Changelog: v0.1.2...v0.1.3

v0.1.2

What's Changed

• fix: use judge model for judge analysis by @zshipko in #3

Full Changelog: v0.1.1...v0.1.2