v0.2.4

Changelog

• f81609a: ci: bump actions/upload-artifact from 5 to 7 (@dependabot[bot])
• 57e5715: ci: bump golangci/golangci-lint-action from 8 to 9 (@dependabot[bot])
• 5fa437a: feat(evaluator): collect_artifacts glob to download workspace files on any outcome (#85) (@zpzjzj)
• 653ae83: feat: add Custom Engine with local transport (#24) (@zpzjzj)
• a54597b: fix(runner): report skill name from SKILL.md frontmatter, not dir basename (@zpzjzj)
• 03bce5e: refactor(agent,runtime): unify PATH/env handling via command prelude (#63) (@zpzjzj)

v0.2.3

Changelog

• af7a2ca: ci: bump actions/deploy-pages from 4 to 5 (@dependabot[bot])
• cd41d6d: ci: make revive violations actually fail the Lint job (@zpzjzj)
• 11d5ca4: feat(agent): DEBUG-log unknown engine.kwargs keys to catch typos (@zpzjzj)
• e237098: feat(engine): add engine.kwargs (CLI --engine-kwarg/--ek); codex honors bypass_sandbox (@zpzjzj)
• bf519ad: test: improve unit coverage (#71) (@lbfsc)

v0.2.2

Changelog

• c80f11e: ci: bump actions/download-artifact from 5 to 8 (@dependabot[bot])
• 449215f: ci: bump actions/setup-go from 5 to 6 (@dependabot[bot])
• cdcb0af: feat(runtime): add docker runtime for local container-isolated evals (#56) (@zpzjzj)
• a6e284b: fix(ci): publish coverage badge from badges branch (#64) (@lbfsc)
• dcdb5d8: fix(codex): synthesize provider override when ModelProvider is empty but BaseURL is set (@zpzjzj)
• ba1b06d: fix(config): apply documented defaults when loading eval.yaml (@zpzjzj)
• d04fe13: fix(evaluator): exclude parent-supplied deadlines from case-timeout label (@zpzjzj)
• c7bfb5a: fix(evaluator): gate case-timeout annotation on case ctx actually expiring (@zpzjzj)
• 5eb811e: fix(runtime): surface stdout when runtime.exec exits non-zero (@zpzjzj)
• 9fc85b5: fix(timeout): strict case-timeout budget, judge knob for agent_judge, named errors (@zpzjzj)
• 87fa0b2: refactor(timeout): hoist annotate-gate decisions to caller (fix revive lint) (@zpzjzj)
• b9f6d9f: test(judge): check type assertion in agent_judge timeout test (@zpzjzj)

v0.2.1

Changelog

• b4f8f57: Revert "fix(claude_code): preserve provider prefix in --model for custom proxies" (@zpzjzj)
• 3d020a3: fix(claude_code): also write ANTHROPIC_AUTH_TOKEN for Bearer-auth proxies (@zpzjzj)
• 632abc3: fix(claude_code): preserve provider prefix in --model for custom proxies (@zpzjzj)
• c670ff9: fix(cli): gate --model provider/name split on provider being configured (@zpzjzj)
• 26239e0: fix(cli): honour --api-key, eval.yaml base_url, and framework-default providers (@zpzjzj)
• 1836d12: fix(cli): let opaque slashed model ids pass through with --api-key (@zpzjzj)
• 724ae51: fix(cli): scope collapse to CLI splits, honour --api-key and Qoder PAT (@zpzjzj)
• a046966: fix(credential): qoder PAT probe is qoder-specific, not a generic suffix (@zpzjzj)
• 1e9d9ed: fix(runner): generate report.json when --format json is specified for run subcommand (#58) (@lbfsc)
• f684a9f: fix: gofmt credential.go after adding EnvAnthropicAuthToken (@zpzjzj)
• 7f7a3c7: refactor(credential): extract ResolveModelRef + Resolver.HasProvider (@zpzjzj)
• 2a9c7ce: refactor(credential): pass CLI hints into ResolveModelRef predicate (@zpzjzj)
• b3cb00f: test(cli): consolidate preserves-split cases into table-driven test (@zpzjzj)

v0.2.0

Changelog

v0.1.2

Changelog

• 58a3c5f: ci: bump actions/configure-pages from 5 to 6 (@dependabot[bot])
• 86a77e9: ci: bump actions/setup-node from 4 to 6 (@dependabot[bot])
• cde9b39: ci: bump actions/upload-artifact from 5 to 7 (@dependabot[bot])
• 7b2f584: feat(mcp): support mocked MCP servers (#15) (@zpzjzj)
• f7afc7d: feat(skill-upper): provide skill-upper to use skill-up (#17) (@lijunfeng722)
• 279183b: feat: add --runtime flag to override environment.type (#25) (@zpzjzj)
• e18366c: feat: add network_policy support for sandbox egress isolation (#16) (@zpzjzj)
• 2d1331c: fix(agent): decouple post-run session lookup from canceled run ctx (@zpzjzj)
• f78280b: fix(cli): make init --config read a source file, not a write target (#37) (@zpzjzj)
• 69b754d: fix(credential): load default credentials file in run path (#29) (@zpzjzj)
• d8f6187: fix(evaluator): implement context.git.checkout in fixture loader (#30) (@zpzjzj)
• 4cc6064: fix(runner): place default eval workspace alongside skill directory (#27) (@zpzjzj)
• d0ec760: fix(runtime/none): distinguish ctx-killed processes from real non-zero exits (@zpzjzj)
• 903e3fa: fix(runtime/opensandbox): distinguish SDK failure from non-zero remote exit (@zpzjzj)
• 653bf20: refactor(runtime): use SDK batch UploadFiles for directory upload (#23) (@zpzjzj)
• 09b03f8: test(e2e): verify opensandbox runtime with codex via CI sidecar (#12) (@zpzjzj)

v0.1.1

Changelog

• c8d7fed: Revert "test(agent/codex): dump run artifacts on codex non-zero exit" (@zpzjzj)
• 7a06c1c: build(goreleaser): drop deprecated v2 fields (@zpzjzj)
• 3cecd4b: ci(e2e): force ANTHROPIC_MODEL=qwen3.6-plus to avoid real Claude billing (@zpzjzj)
• 2c69670: ci(e2e): install claude / codex / qodercli to exercise none runtime (@zpzjzj)
• 768eda1: ci(e2e): point codex at DashScope qwen via OPENAI_MODEL override (@zpzjzj)
• 2129d45: ci(e2e): unlock SKILL_UP_FULL_E2E with DashScope + Qoder secrets (@zpzjzj)
• 99a6b0a: ci: add e2e quick-mode job (@zpzjzj)
• 2eadb0a: ci: add revive lint and goreleaser dry-run jobs (@zpzjzj)
• 54334cb: ci: bump actions/checkout from 4 to 6 (@dependabot[bot])
• 97bf0e3: ci: bump actions/setup-go from 5 to 6 (@dependabot[bot])
• a4da26f: ci: bump actions/upload-pages-artifact from 3 to 5 (@dependabot[bot])
• 13a74e8: ci: bump goreleaser/goreleaser-action from 6 to 7 (@dependabot[bot])
• ff6d6d2: ci: skip Go CI on docs-only changes (@zpzjzj)
• 9b38025: feat(config): support engine type in eval config (@jwx0925)
• 30953e9: fix(agent): skip nvm bootstrap when claude/codex is already on PATH (@zpzjzj)
• 51b1474: fix(agent/codex): emit openai BaseURL override under a distinct provider key (@zpzjzj)
• 7662082: fix(agent/codex): honor OPENAI_BASE_URL when provider=openai (@zpzjzj)
• 57a7363: revert(config): keep engine name in eval schema (@jwx0925)
• abb7cc8: test(agent/codex): dump run artifacts on codex non-zero exit (@zpzjzj)
• 84776c1: test(agent/codex): vary instruction in new build-cmd test to silence unparam (@zpzjzj)
• 0dad099: test(e2e): align RunAutoWithExamples assertion with actual auto-detect (@zpzjzj)
• 443eef6: test(e2e): preserve workspaces under SKILL_UP_E2E_ARTIFACT_DIR; upload from CI (@zpzjzj)

v0.1.0

Changelog