v4.24.1

What's Changed

• fix: remove before_session hook startup color by @christso in #1193
• feat: add check-grader-scores post-processor by @christso in #1191
• fix: resolve self-update package manager command by @christso in #1195
• fix: use Studio threshold as Run Eval default by @christso in #1197
• fix(core): normalize rubric grader name to rubrics by @christso in #1196

Full Changelog: v4.24.0...v4.24.1

v4.24.1-next.1

What's Changed

• fix: remove before_session hook startup color by @christso in #1193
• feat: add check-grader-scores post-processor by @christso in #1191
• fix: resolve self-update package manager command by @christso in #1195
• fix: use Studio threshold as Run Eval default by @christso in #1197
• fix(core): normalize rubric grader name to rubrics by @christso in #1196

Full Changelog: v4.24.0...v4.24.1-next.1

v4.24.0

What's Changed

• fix(agentv-bench): fix grader subagent pipeline bugs by @jozsurf in #1148
• fix(pipeline): align subagent-mode suite fallback with CLI mode by @christso in #1151
• feat(core): optional governance metadata on EvalMetadata and EvalTest by @christso in #1165
• docs(examples): AI system register convention (.ai-register.yaml) + aggregator Action template by @christso in #1167
• feat(examples): scenario-based red-team suites for coding and customer-facing agent archetypes by @christso in #1168
• feat(examples): OWASP LLM Top 10 / MITRE ATLAS-aligned red-team eval pack by @christso in #1166
• fix(test): raise pipeline-e2e timeout to 30s (#1169) by @christso in #1170
• fix(docs): correct contains* case-sensitivity in grader.md by @christso in #1171
• fix(core): unwrap YAML merge keys (<<:) in eval loader by @christso in #1174
• fix(examples): use tool-trajectory not contains for destructive-git negative assertions by @christso in #1175
• fix(test): raise input.test.ts pipeline timeouts to 30s by @christso in #1176
• fix(test): bump e2e/integration test timeouts to 30s (#1173) by @christso in #1177
• feat(skill): add agentv-compliance skill for governance block authoring and lint (Phase 1 of #1172) by @christso in #1178
• refactor(core): remove typed governance schema, generalize metadata merge (Phase 2 of #1172) by @christso in #1179
• feat(examples): add compliance-lint GitHub Action reference (Phase 3 of #1172) by @christso in #1180
• chore: rename agentv-compliance skill to agentv-governance by @christso in #1181
• docs: fix risk_tier vocabulary mismatch and add eval-level governance docs by @christso in #1183
• docs(examples): align ai-register manifest with EU AI Act, NIST RMF, ISO 42001 by @christso in #1184
• feat(studio): add targets tab drilldown by @christso in #1189
• feat(red-team): screenshot PII upload eval for coding agents by @christso in #1185
• feat(cli): show eval progress durations in ms by @christso in #1187

New Contributors

• @jozsurf made their first contribution in #1148

Full Changelog: v4.22.0...v4.24.0

v4.24.0-next.1

What's Changed

• docs(examples): align ai-register manifest with EU AI Act, NIST RMF, ISO 42001 by @christso in #1184
• feat(studio): add targets tab drilldown by @christso in #1189
• feat(red-team): screenshot PII upload eval for coding agents by @christso in #1185
• feat(cli): show eval progress durations in ms by @christso in #1187

Full Changelog: v4.23.0-next.1...v4.24.0-next.1

v4.23.0-next.1

What's Changed

• fix(agentv-bench): fix grader subagent pipeline bugs by @jozsurf in #1148
• fix(pipeline): align subagent-mode suite fallback with CLI mode by @christso in #1151
• feat(core): optional governance metadata on EvalMetadata and EvalTest by @christso in #1165
• docs(examples): AI system register convention (.ai-register.yaml) + aggregator Action template by @christso in #1167
• feat(examples): scenario-based red-team suites for coding and customer-facing agent archetypes by @christso in #1168
• feat(examples): OWASP LLM Top 10 / MITRE ATLAS-aligned red-team eval pack by @christso in #1166
• fix(test): raise pipeline-e2e timeout to 30s (#1169) by @christso in #1170
• fix(docs): correct contains* case-sensitivity in grader.md by @christso in #1171
• fix(core): unwrap YAML merge keys (<<:) in eval loader by @christso in #1174
• fix(examples): use tool-trajectory not contains for destructive-git negative assertions by @christso in #1175
• fix(test): raise input.test.ts pipeline timeouts to 30s by @christso in #1176
• fix(test): bump e2e/integration test timeouts to 30s (#1173) by @christso in #1177
• feat(skill): add agentv-compliance skill for governance block authoring and lint (Phase 1 of #1172) by @christso in #1178
• refactor(core): remove typed governance schema, generalize metadata merge (Phase 2 of #1172) by @christso in #1179
• feat(examples): add compliance-lint GitHub Action reference (Phase 3 of #1172) by @christso in #1180
• chore: rename agentv-compliance skill to agentv-governance by @christso in #1181
• docs: fix risk_tier vocabulary mismatch and add eval-level governance docs by @christso in #1183

New Contributors

• @jozsurf made their first contribution in #1148

Full Changelog: v4.22.0...v4.23.0-next.1

v4.22.0

What's Changed

• fix(cli): drop outputFormat from interactive wizard rawOptions by @christso in #1147
• feat(config): add hooks.pre_run for pre-eval environment injection by @christso in #1150

Full Changelog: v4.21.0...v4.22.0

v4.22.0-next.1

What's Changed

• fix(cli): drop outputFormat from interactive wizard rawOptions by @christso in #1147
• feat(config): add hooks.pre_run for pre-eval environment injection by @christso in #1150

Full Changelog: v4.21.0...v4.22.0-next.1

v4.21.0

What's Changed

• feat(cli): auto-update when version mismatch detected by @christso in #1126
• feat(cli): skip self-update when already on latest version by @christso in #1130
• feat(cli): add version check to studio/serve commands by @christso in #1131
• feat(cli): self update preserves install scope (local vs global) by @christso in #1132
• docs(AGENTS.md): add design principle #3 — maximize feature surface through composition by @christso in #1138
• feat(core): auto-discover test cases from directory structure by @christso in #1142
• feat(studio)!: benchmarks.yaml as single source of truth, live-reloaded by @christso in #1145
• docs(targets): add CLI Provider page + oracle-validation pattern by @christso in #1146

Full Changelog: v4.20.0...v4.21.0

v4.21.0-next.1

What's Changed

• feat(cli): auto-update when version mismatch detected by @christso in #1126
• feat(cli): skip self-update when already on latest version by @christso in #1130
• feat(cli): add version check to studio/serve commands by @christso in #1131
• feat(cli): self update preserves install scope (local vs global) by @christso in #1132
• docs(AGENTS.md): add design principle #3 — maximize feature surface through composition by @christso in #1138
• feat(core): auto-discover test cases from directory structure by @christso in #1142
• feat(studio)!: benchmarks.yaml as single source of truth, live-reloaded by @christso in #1145
• docs(targets): add CLI Provider page + oracle-validation pattern by @christso in #1146

Full Changelog: v4.20.0...v4.21.0-next.1

v4.20.0

What's Changed

• feat(cli): add --budget-usd run-level cost cap by @christso in #1118
• feat(bench): autoresearch optimization loop (#958, #746, #748) by @christso in #1112
• refactor(bench): extract autoresearch to reference file by @christso in #1124
• feat(core): expose {{ tool_calls }} template variable for LLM graders by @christso in #1123

Full Changelog: v4.19.0...v4.20.0