@bjoernrochel/sevro 0.1.0-rc.8 → 1.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CONTRIBUTING.md +52 -6
- package/README.md +12 -7
- package/dist/examples/basic/graded.json +13 -0
- package/dist/examples/basic/host.js +9 -0
- package/dist/examples/basic/host.js.map +1 -0
- package/dist/examples/basic/prompt-only.json +7 -0
- package/dist/examples/recipes/candidate.js +23 -0
- package/dist/examples/recipes/candidate.js.map +1 -0
- package/dist/examples/recipes/cases/coding-change.json +21 -0
- package/dist/examples/recipes/cases/host-tools.json +21 -0
- package/dist/examples/recipes/cases/mise.json +21 -0
- package/dist/examples/recipes/cases/node.json +21 -0
- package/dist/examples/recipes/cases/python-uv.json +21 -0
- package/dist/examples/recipes/cases/semantic.json +17 -0
- package/dist/examples/recipes/coding-change/check.js +16 -0
- package/dist/examples/recipes/coding-change/check.js.map +1 -0
- package/dist/examples/recipes/executable.js +20 -0
- package/dist/examples/recipes/executable.js.map +1 -0
- package/dist/examples/recipes/extension-artifacts.js +56 -0
- package/dist/examples/recipes/extension-artifacts.js.map +1 -0
- package/dist/examples/recipes/extension-methods.js +167 -0
- package/dist/examples/recipes/extension-methods.js.map +1 -0
- package/dist/examples/recipes/extension.js +28 -0
- package/dist/examples/recipes/extension.js.map +1 -0
- package/dist/examples/recipes/modules.js +9 -0
- package/dist/examples/recipes/modules.js.map +1 -0
- package/dist/examples/recipes/repository-skill/.agents/skills/startup-guide/SKILL.md +7 -0
- package/dist/examples/recipes/repository-skill/.claude/skills/startup-guide/SKILL.md +7 -0
- package/dist/examples/recipes/repository-skill/README.md +3 -0
- package/dist/examples/recipes/run-inputs.js +144 -0
- package/dist/examples/recipes/run-inputs.js.map +1 -0
- package/dist/examples/recipes/run-options.js +103 -0
- package/dist/examples/recipes/run-options.js.map +1 -0
- package/dist/examples/recipes/run.js +62 -0
- package/dist/examples/recipes/run.js.map +1 -0
- package/dist/examples/recipes/runtime/empty.json +1 -0
- package/dist/examples/recipes/runtime/goals.json +1 -0
- package/dist/examples/recipes/runtime/mise.json +6 -0
- package/dist/examples/recipes/runtime/path.json +1 -0
- package/dist/examples/recipes/runtime/plugins.json +4 -0
- package/dist/examples/recipes/runtime/python-uv.json +10 -0
- package/dist/examples/recipes/semantic-judge.js +27 -0
- package/dist/examples/recipes/semantic-judge.js.map +1 -0
- package/dist/examples/templates/coding/adapter.js +14 -0
- package/dist/examples/templates/coding/adapter.js.map +1 -0
- package/dist/examples/templates/coding/case.json +15 -0
- package/dist/examples/templates/repository-skill/.agents/skills/startup-guide/SKILL.md +6 -0
- package/dist/examples/templates/repository-skill/extension-data.js +61 -0
- package/dist/examples/templates/repository-skill/extension-data.js.map +1 -0
- package/dist/examples/templates/repository-skill/extension.js +29 -0
- package/dist/examples/templates/repository-skill/extension.js.map +1 -0
- package/dist/examples/templates/response/adapter.js +13 -0
- package/dist/examples/templates/response/adapter.js.map +1 -0
- package/dist/examples/templates/response/case.json +13 -0
- package/dist/src/advisory.js +86 -0
- package/dist/src/advisory.js.map +1 -0
- package/dist/src/candidate-artifacts.js +139 -0
- package/dist/src/candidate-artifacts.js.map +1 -0
- package/dist/src/candidate-codex-state.js +110 -0
- package/dist/src/candidate-codex-state.js.map +1 -0
- package/dist/src/case-validation.js +92 -0
- package/dist/src/case-validation.js.map +1 -0
- package/dist/src/cli/cancellation.js +21 -0
- package/dist/src/cli/cancellation.js.map +1 -0
- package/dist/src/cli/command.js +60 -0
- package/dist/src/cli/command.js.map +1 -0
- package/dist/src/cli/completion.js +14 -0
- package/dist/src/cli/completion.js.map +1 -0
- package/dist/src/cli/demo.js +45 -0
- package/dist/src/cli/demo.js.map +1 -0
- package/dist/src/cli/evaluation.js +40 -0
- package/dist/src/cli/evaluation.js.map +1 -0
- package/dist/src/cli/extension.js +54 -0
- package/dist/src/cli/extension.js.map +1 -0
- package/dist/src/cli/help.js +190 -0
- package/dist/src/cli/help.js.map +1 -0
- package/dist/src/cli/hosts.js +33 -0
- package/dist/src/cli/hosts.js.map +1 -0
- package/dist/src/cli/init-settings.js +29 -0
- package/dist/src/cli/init-settings.js.map +1 -0
- package/dist/src/cli/init.js +82 -0
- package/dist/src/cli/init.js.map +1 -0
- package/dist/src/cli/invocation.js +431 -0
- package/dist/src/cli/invocation.js.map +1 -0
- package/dist/src/cli/loading.js +110 -0
- package/dist/src/cli/loading.js.map +1 -0
- package/dist/src/cli/preparation.js +88 -0
- package/dist/src/cli/preparation.js.map +1 -0
- package/dist/src/cli/presentation.js +61 -0
- package/dist/src/cli/presentation.js.map +1 -0
- package/dist/src/cli/progress.js +5 -0
- package/dist/src/cli/progress.js.map +1 -0
- package/dist/src/cli/run-manifest.js +108 -0
- package/dist/src/cli/run-manifest.js.map +1 -0
- package/dist/src/cli/run-options.js +367 -0
- package/dist/src/cli/run-options.js.map +1 -0
- package/dist/src/cli/run-overrides.js +51 -0
- package/dist/src/cli/run-overrides.js.map +1 -0
- package/dist/src/cli/settings.js +127 -0
- package/dist/src/cli/settings.js.map +1 -0
- package/dist/src/cli/summary.js +28 -0
- package/dist/src/cli/summary.js.map +1 -0
- package/dist/src/cli.js +20 -0
- package/dist/src/cli.js.map +1 -0
- package/dist/src/contract-types.js +2 -0
- package/dist/src/contract-types.js.map +1 -0
- package/dist/src/engine.js +4 -0
- package/dist/src/engine.js.map +1 -0
- package/dist/src/evaluation/advisory.js +85 -0
- package/dist/src/evaluation/advisory.js.map +1 -0
- package/dist/src/evaluation/check-plan.js +292 -0
- package/dist/src/evaluation/check-plan.js.map +1 -0
- package/dist/src/evaluation/collection.js +61 -0
- package/dist/src/evaluation/collection.js.map +1 -0
- package/dist/src/evaluation/context.js +2 -0
- package/dist/src/evaluation/context.js.map +1 -0
- package/dist/src/evaluation/grading-host.js +28 -0
- package/dist/src/evaluation/grading-host.js.map +1 -0
- package/dist/src/evaluation/grading.js +154 -0
- package/dist/src/evaluation/grading.js.map +1 -0
- package/dist/src/evaluation/invocation-plan.js +312 -0
- package/dist/src/evaluation/invocation-plan.js.map +1 -0
- package/dist/src/evaluation/plan.js +376 -0
- package/dist/src/evaluation/plan.js.map +1 -0
- package/dist/src/evaluation/progress.js +14 -0
- package/dist/src/evaluation/progress.js.map +1 -0
- package/dist/src/evaluation/resources.js +159 -0
- package/dist/src/evaluation/resources.js.map +1 -0
- package/dist/src/evaluation/run.js +148 -0
- package/dist/src/evaluation/run.js.map +1 -0
- package/dist/src/evaluation/scheduler.js +27 -0
- package/dist/src/evaluation/scheduler.js.map +1 -0
- package/dist/src/evaluation/semantic.js +183 -0
- package/dist/src/evaluation/semantic.js.map +1 -0
- package/dist/src/evaluation/trial.js +593 -0
- package/dist/src/evaluation/trial.js.map +1 -0
- package/dist/src/evaluation/types.js +20 -0
- package/dist/src/evaluation/types.js.map +1 -0
- package/dist/src/evidence/host-results.js +67 -0
- package/dist/src/evidence/host-results.js.map +1 -0
- package/dist/src/evidence/retained-artifacts.js +17 -0
- package/dist/src/evidence/retained-artifacts.js.map +1 -0
- package/dist/src/evidence/trial-writer.js +131 -0
- package/dist/src/evidence/trial-writer.js.map +1 -0
- package/dist/src/evidence/usage.js +14 -0
- package/dist/src/evidence/usage.js.map +1 -0
- package/dist/src/executable.js +20 -0
- package/dist/src/executable.js.map +1 -0
- package/dist/src/extension-client.js +212 -0
- package/dist/src/extension-client.js.map +1 -0
- package/dist/src/extension-session.js +236 -0
- package/dist/src/extension-session.js.map +1 -0
- package/dist/src/fixtures/advisory.js +206 -0
- package/dist/src/fixtures/advisory.js.map +1 -0
- package/dist/src/fixtures/bin.js +41 -0
- package/dist/src/fixtures/bin.js.map +1 -0
- package/dist/src/fixtures/cleanup.js +43 -0
- package/dist/src/fixtures/cleanup.js.map +1 -0
- package/dist/src/fixtures/create.js +94 -0
- package/dist/src/fixtures/create.js.map +1 -0
- package/dist/src/fixtures/generated.js +181 -0
- package/dist/src/fixtures/generated.js.map +1 -0
- package/dist/src/fixtures/git-hooks.js +16 -0
- package/dist/src/fixtures/git-hooks.js.map +1 -0
- package/dist/src/fixtures/preparation.js +201 -0
- package/dist/src/fixtures/preparation.js.map +1 -0
- package/dist/src/fixtures/repository.js +255 -0
- package/dist/src/fixtures/repository.js.map +1 -0
- package/dist/src/fixtures/setup.js +175 -0
- package/dist/src/fixtures/setup.js.map +1 -0
- package/dist/src/fixtures/tools.js +57 -0
- package/dist/src/fixtures/tools.js.map +1 -0
- package/dist/src/fixtures/workspace-state.js +155 -0
- package/dist/src/fixtures/workspace-state.js.map +1 -0
- package/dist/src/generated/cli-result.cjs +2 -0
- package/dist/src/generated/extension.cjs +2 -0
- package/dist/src/generated/report.cjs +2 -0
- package/dist/src/generated/run-evidence.cjs +2 -0
- package/dist/src/generated/runtime.cjs +2 -0
- package/dist/src/git.js +72 -0
- package/dist/src/git.js.map +1 -0
- package/dist/src/graders/artifact.js +68 -0
- package/dist/src/graders/artifact.js.map +1 -0
- package/dist/src/graders/git-head.js +112 -0
- package/dist/src/graders/git-head.js.map +1 -0
- package/dist/src/graders/output.js +345 -0
- package/dist/src/graders/output.js.map +1 -0
- package/dist/src/graders/semantic.js +132 -0
- package/dist/src/graders/semantic.js.map +1 -0
- package/dist/src/graders/shell.js +321 -0
- package/dist/src/graders/shell.js.map +1 -0
- package/dist/src/host-diagnostic-redaction.js +52 -0
- package/dist/src/host-diagnostic-redaction.js.map +1 -0
- package/dist/src/host-diagnostics.js +248 -0
- package/dist/src/host-diagnostics.js.map +1 -0
- package/dist/src/hosts/claude-continuation.js +89 -0
- package/dist/src/hosts/claude-continuation.js.map +1 -0
- package/dist/src/hosts/claude-credential.js +121 -0
- package/dist/src/hosts/claude-credential.js.map +1 -0
- package/dist/src/hosts/claude-events.js +136 -0
- package/dist/src/hosts/claude-events.js.map +1 -0
- package/dist/src/hosts/claude-keychain.js +100 -0
- package/dist/src/hosts/claude-keychain.js.map +1 -0
- package/dist/src/hosts/claude-login-recovery.js +67 -0
- package/dist/src/hosts/claude-login-recovery.js.map +1 -0
- package/dist/src/hosts/claude-login-refresh.js +146 -0
- package/dist/src/hosts/claude-login-refresh.js.map +1 -0
- package/dist/src/hosts/claude-login-store.js +124 -0
- package/dist/src/hosts/claude-login-store.js.map +1 -0
- package/dist/src/hosts/claude-login.js +74 -0
- package/dist/src/hosts/claude-login.js.map +1 -0
- package/dist/src/hosts/claude-native-goal.js +138 -0
- package/dist/src/hosts/claude-native-goal.js.map +1 -0
- package/dist/src/hosts/claude-process.js +10 -0
- package/dist/src/hosts/claude-process.js.map +1 -0
- package/dist/src/hosts/claude-refresh-lock.js +76 -0
- package/dist/src/hosts/claude-refresh-lock.js.map +1 -0
- package/dist/src/hosts/claude-repository-invocation.js +229 -0
- package/dist/src/hosts/claude-repository-invocation.js.map +1 -0
- package/dist/src/hosts/claude-settings.js +156 -0
- package/dist/src/hosts/claude-settings.js.map +1 -0
- package/dist/src/hosts/claude-skill-activations.js +131 -0
- package/dist/src/hosts/claude-skill-activations.js.map +1 -0
- package/dist/src/hosts/claude-state.js +237 -0
- package/dist/src/hosts/claude-state.js.map +1 -0
- package/dist/src/hosts/claude-tool-calls.js +150 -0
- package/dist/src/hosts/claude-tool-calls.js.map +1 -0
- package/dist/src/hosts/claude.js +373 -0
- package/dist/src/hosts/claude.js.map +1 -0
- package/dist/src/hosts/codex-app-server.js +764 -0
- package/dist/src/hosts/codex-app-server.js.map +1 -0
- package/dist/src/hosts/codex-configuration.js +91 -0
- package/dist/src/hosts/codex-configuration.js.map +1 -0
- package/dist/src/hosts/codex-events.js +104 -0
- package/dist/src/hosts/codex-events.js.map +1 -0
- package/dist/src/hosts/codex-exec-controls.js +434 -0
- package/dist/src/hosts/codex-exec-controls.js.map +1 -0
- package/dist/src/hosts/codex-invocation.js +54 -0
- package/dist/src/hosts/codex-invocation.js.map +1 -0
- package/dist/src/hosts/codex-marketplace.js +185 -0
- package/dist/src/hosts/codex-marketplace.js.map +1 -0
- package/dist/src/hosts/codex-native-calls.js +516 -0
- package/dist/src/hosts/codex-native-calls.js.map +1 -0
- package/dist/src/hosts/codex-process.js +10 -0
- package/dist/src/hosts/codex-process.js.map +1 -0
- package/dist/src/hosts/codex-profile.js +206 -0
- package/dist/src/hosts/codex-profile.js.map +1 -0
- package/dist/src/hosts/codex-session-files.js +89 -0
- package/dist/src/hosts/codex-session-files.js.map +1 -0
- package/dist/src/hosts/codex-state.js +310 -0
- package/dist/src/hosts/codex-state.js.map +1 -0
- package/dist/src/hosts/codex.js +527 -0
- package/dist/src/hosts/codex.js.map +1 -0
- package/dist/src/hosts/isolation-common.js +43 -0
- package/dist/src/hosts/isolation-common.js.map +1 -0
- package/dist/src/hosts/isolation-roots.js +64 -0
- package/dist/src/hosts/isolation-roots.js.map +1 -0
- package/dist/src/hosts/isolation.js +12 -0
- package/dist/src/hosts/isolation.js.map +1 -0
- package/dist/src/hosts/linux-sandbox.js +127 -0
- package/dist/src/hosts/linux-sandbox.js.map +1 -0
- package/dist/src/hosts/mac-sandbox.js +137 -0
- package/dist/src/hosts/mac-sandbox.js.map +1 -0
- package/dist/src/hosts/native-controls.js +151 -0
- package/dist/src/hosts/native-controls.js.map +1 -0
- package/dist/src/hosts/native-request.js +33 -0
- package/dist/src/hosts/native-request.js.map +1 -0
- package/dist/src/hosts/process-lifecycle.js +167 -0
- package/dist/src/hosts/process-lifecycle.js.map +1 -0
- package/dist/src/hosts/protected-worktrees.js +81 -0
- package/dist/src/hosts/protected-worktrees.js.map +1 -0
- package/dist/src/hosts/skill-hook-catalog.js +100 -0
- package/dist/src/hosts/skill-hook-catalog.js.map +1 -0
- package/dist/src/hosts/skill-hook-handler.js +228 -0
- package/dist/src/hosts/skill-hook-handler.js.map +1 -0
- package/dist/src/hosts/skill-hooks.js +423 -0
- package/dist/src/hosts/skill-hooks.js.map +1 -0
- package/dist/src/hosts/workspace-fingerprint.js +72 -0
- package/dist/src/hosts/workspace-fingerprint.js.map +1 -0
- package/dist/src/identity.js +167 -0
- package/dist/src/identity.js.map +1 -0
- package/dist/src/instrumentation.js +83 -0
- package/dist/src/instrumentation.js.map +1 -0
- package/dist/src/native-transcript-state.js +85 -0
- package/dist/src/native-transcript-state.js.map +1 -0
- package/dist/src/native-transcript-view.js +65 -0
- package/dist/src/native-transcript-view.js.map +1 -0
- package/dist/src/native-transcripts.js +208 -0
- package/dist/src/native-transcripts.js.map +1 -0
- package/dist/src/paths.js +13 -0
- package/dist/src/paths.js.map +1 -0
- package/dist/src/process-lifecycle.js +101 -0
- package/dist/src/process-lifecycle.js.map +1 -0
- package/dist/src/provenance.js +263 -0
- package/dist/src/provenance.js.map +1 -0
- package/dist/src/prune.js +228 -0
- package/dist/src/prune.js.map +1 -0
- package/dist/src/report.js +276 -0
- package/dist/src/report.js.map +1 -0
- package/dist/src/resolved-case.js +29 -0
- package/dist/src/resolved-case.js.map +1 -0
- package/dist/src/results-lock.js +40 -0
- package/dist/src/results-lock.js.map +1 -0
- package/dist/src/results.js +127 -0
- package/dist/src/results.js.map +1 -0
- package/dist/src/run-owner.js +283 -0
- package/dist/src/run-owner.js.map +1 -0
- package/dist/src/runner-paths.js +11 -0
- package/dist/src/runner-paths.js.map +1 -0
- package/dist/src/runtime/config.js +323 -0
- package/dist/src/runtime/config.js.map +1 -0
- package/dist/src/runtime/discovery-apple.js +65 -0
- package/dist/src/runtime/discovery-apple.js.map +1 -0
- package/dist/src/runtime/discovery-providers.js +37 -0
- package/dist/src/runtime/discovery-providers.js.map +1 -0
- package/dist/src/runtime/discovery.js +40 -0
- package/dist/src/runtime/discovery.js.map +1 -0
- package/dist/src/runtime/hook-processes.js +81 -0
- package/dist/src/runtime/hook-processes.js.map +1 -0
- package/dist/src/runtime/hooks.js +304 -0
- package/dist/src/runtime/hooks.js.map +1 -0
- package/dist/src/runtime/paths.js +244 -0
- package/dist/src/runtime/paths.js.map +1 -0
- package/dist/src/runtime/query.js +76 -0
- package/dist/src/runtime/query.js.map +1 -0
- package/dist/src/runtime/seeds.js +98 -0
- package/dist/src/runtime/seeds.js.map +1 -0
- package/dist/src/runtime/shared-cache.js +81 -0
- package/dist/src/runtime/shared-cache.js.map +1 -0
- package/dist/src/runtime/state.js +106 -0
- package/dist/src/runtime/state.js.map +1 -0
- package/dist/src/runtime-process.js +148 -0
- package/dist/src/runtime-process.js.map +1 -0
- package/dist/src/schema-types.js +2 -0
- package/dist/src/schema-types.js.map +1 -0
- package/dist/src/schema.js +16 -0
- package/dist/src/schema.js.map +1 -0
- package/dist/src/shell.js +5 -0
- package/dist/src/shell.js.map +1 -0
- package/dist/src/sqlite-lock.js +18 -0
- package/dist/src/sqlite-lock.js.map +1 -0
- package/dist/src/storage.js +21 -0
- package/dist/src/storage.js.map +1 -0
- package/dist/src/transcript-retention.js +109 -0
- package/dist/src/transcript-retention.js.map +1 -0
- package/dist/src/value-guards.js +26 -0
- package/dist/src/value-guards.js.map +1 -0
- package/docs/README.md +19 -15
- package/docs/architecture.md +141 -17
- package/docs/assets/README.md +5 -4
- package/docs/builtin-graders-v1.md +9 -2
- package/docs/codex-host.md +155 -57
- package/docs/contracts.md +2 -1
- package/docs/creating-cases.md +10 -4
- package/docs/development-cli.md +197 -24
- package/docs/documentation-quality.md +16 -5
- package/docs/evaluation-workflow.md +110 -0
- package/docs/extension-protocol-v1.md +26 -3
- package/docs/getting-started.md +29 -7
- package/docs/guide-evaluation.md +34 -2
- package/docs/identity-v1.md +29 -3
- package/docs/installing.md +35 -17
- package/docs/licensing.md +2 -2
- package/docs/native-controls.md +76 -5
- package/docs/native-hosts.md +197 -8
- package/docs/reading-results.md +102 -0
- package/docs/recipes.md +490 -0
- package/docs/releases.md +48 -13
- package/docs/report-v1.md +29 -1
- package/docs/results-v1.md +122 -4
- package/docs/run-settings-v1.md +147 -0
- package/docs/runtime-v1.md +255 -22
- package/docs/specs/repository-guide.md +1 -1
- package/docs/troubleshooting.md +12 -12
- package/docs/typescript-quality.md +106 -26
- package/examples/recipes/candidate.ts +26 -0
- package/examples/recipes/cases/coding-change.json +21 -0
- package/examples/recipes/cases/host-tools.json +21 -0
- package/examples/recipes/cases/mise.json +21 -0
- package/examples/recipes/cases/node.json +21 -0
- package/examples/recipes/cases/python-uv.json +21 -0
- package/examples/recipes/cases/semantic.json +17 -0
- package/examples/recipes/coding-change/check.ts +23 -0
- package/examples/recipes/executable.ts +19 -0
- package/examples/recipes/extension-artifacts.ts +65 -0
- package/examples/recipes/extension-methods.ts +174 -0
- package/examples/recipes/extension.ts +38 -0
- package/examples/recipes/modules.ts +9 -0
- package/examples/recipes/repository-skill/.agents/skills/startup-guide/SKILL.md +7 -0
- package/examples/recipes/repository-skill/.claude/skills/startup-guide/SKILL.md +7 -0
- package/examples/recipes/repository-skill/README.md +3 -0
- package/examples/recipes/run-inputs.ts +183 -0
- package/examples/recipes/run-options.ts +132 -0
- package/examples/recipes/run.ts +77 -0
- package/examples/recipes/runtime/empty.json +1 -0
- package/examples/recipes/runtime/goals.json +1 -0
- package/examples/recipes/runtime/mise.json +6 -0
- package/examples/recipes/runtime/path.json +1 -0
- package/examples/recipes/runtime/plugins.json +4 -0
- package/examples/recipes/runtime/python-uv.json +10 -0
- package/examples/recipes/semantic-judge.ts +29 -0
- package/examples/templates/coding/adapter.ts +17 -0
- package/examples/templates/coding/case.json +15 -0
- package/examples/templates/repository-skill/.agents/skills/startup-guide/SKILL.md +6 -0
- package/examples/templates/repository-skill/extension-data.ts +64 -0
- package/examples/templates/repository-skill/extension.ts +32 -0
- package/examples/templates/response/adapter.ts +12 -0
- package/examples/templates/response/case.json +13 -0
- package/package.json +23 -9
- package/schemas/report-v1.schema.json +9 -0
- package/schemas/run-evidence-v1.schema.json +2 -1
- package/schemas/runtime-v1.schema.json +43 -7
- package/src/advisory.ts +2 -2
- package/src/candidate-artifacts.ts +42 -11
- package/src/candidate-codex-state.ts +185 -0
- package/src/case-validation.ts +73 -50
- package/src/cli/cancellation.ts +20 -0
- package/src/cli/command.ts +87 -0
- package/src/cli/completion.ts +15 -0
- package/src/cli/demo.ts +61 -0
- package/src/cli/evaluation.ts +55 -0
- package/src/cli/extension.ts +79 -0
- package/src/cli/help.ts +199 -0
- package/src/cli/hosts.ts +55 -0
- package/src/cli/init-settings.ts +31 -0
- package/src/cli/init.ts +112 -0
- package/src/{cli-invocation.ts → cli/invocation.ts} +215 -218
- package/src/cli/loading.ts +151 -0
- package/src/cli/preparation.ts +154 -0
- package/src/cli/presentation.ts +93 -0
- package/src/cli/progress.ts +6 -0
- package/src/cli/run-manifest.ts +128 -0
- package/src/cli/run-options.ts +403 -0
- package/src/cli/run-overrides.ts +69 -0
- package/src/cli/settings.ts +154 -0
- package/src/cli/summary.ts +43 -0
- package/src/cli.ts +14 -592
- package/src/contract-types.ts +94 -0
- package/src/engine.ts +9 -5
- package/src/evaluation/advisory.ts +150 -0
- package/src/{evaluation-check-plan.ts → evaluation/check-plan.ts} +103 -67
- package/src/evaluation/collection.ts +88 -0
- package/src/evaluation/context.ts +10 -0
- package/src/{evaluation-grading-host.ts → evaluation/grading-host.ts} +5 -5
- package/src/evaluation/grading.ts +235 -0
- package/src/{evaluation-invocation-plan.ts → evaluation/invocation-plan.ts} +147 -58
- package/src/{evaluation-plan.ts → evaluation/plan.ts} +208 -141
- package/src/evaluation/progress.ts +19 -0
- package/src/evaluation/resources.ts +241 -0
- package/src/evaluation/run.ts +206 -0
- package/src/{evaluation-semantic.ts → evaluation/semantic.ts} +77 -87
- package/src/evaluation/trial.ts +800 -0
- package/src/{evaluation-types.ts → evaluation/types.ts} +79 -29
- package/src/evidence/host-results.ts +85 -0
- package/src/evidence/retained-artifacts.ts +18 -0
- package/src/evidence/trial-writer.ts +203 -0
- package/src/evidence/usage.ts +17 -0
- package/src/executable.ts +19 -0
- package/src/extension-client.ts +40 -108
- package/src/extension-session.ts +24 -48
- package/src/{advisory-fixture.ts → fixtures/advisory.ts} +12 -72
- package/src/{fixture-bin.ts → fixtures/bin.ts} +1 -1
- package/src/{fixture-cleanup.ts → fixtures/cleanup.ts} +13 -7
- package/src/fixtures/create.ts +183 -0
- package/src/{generated-fixture.ts → fixtures/generated.ts} +10 -53
- package/src/{git-hooks.ts → fixtures/git-hooks.ts} +1 -1
- package/src/{preparation.ts → fixtures/preparation.ts} +6 -16
- package/src/{repository-fixture.ts → fixtures/repository.ts} +30 -64
- package/src/{fixture-setup.ts → fixtures/setup.ts} +36 -53
- package/src/{fixture-tools.ts → fixtures/tools.ts} +1 -1
- package/src/{workspace-state.ts → fixtures/workspace-state.ts} +5 -5
- package/src/generated/cli-result.d.cts +2 -1
- package/src/generated/extension.d.cts +2 -1
- package/src/generated/report.cjs +1 -1
- package/src/generated/report.d.cts +2 -1
- package/src/generated/run-evidence.cjs +1 -1
- package/src/generated/run-evidence.d.cts +2 -1
- package/src/generated/runtime.cjs +1 -1
- package/src/generated/runtime.d.cts +2 -1
- package/src/git.ts +94 -0
- package/src/graders/git-head.ts +31 -85
- package/src/graders/shell.ts +54 -71
- package/src/host-diagnostic-redaction.ts +52 -0
- package/src/host-diagnostics.ts +331 -0
- package/src/hosts/claude-continuation.ts +57 -40
- package/src/hosts/claude-credential.ts +160 -63
- package/src/hosts/claude-events.ts +34 -18
- package/src/hosts/claude-keychain.ts +79 -21
- package/src/hosts/claude-login-recovery.ts +85 -0
- package/src/hosts/claude-login-refresh.ts +179 -0
- package/src/hosts/claude-login-store.ts +162 -0
- package/src/hosts/claude-login.ts +107 -0
- package/src/hosts/claude-native-goal.ts +15 -12
- package/src/hosts/claude-process.ts +10 -50
- package/src/hosts/claude-refresh-lock.ts +82 -0
- package/src/hosts/claude-repository-invocation.ts +9 -34
- package/src/hosts/claude-settings.ts +46 -9
- package/src/hosts/claude-skill-activations.ts +169 -0
- package/src/hosts/claude-state.ts +28 -15
- package/src/hosts/claude-tool-calls.ts +13 -10
- package/src/hosts/claude.ts +121 -81
- package/src/hosts/codex-app-server.ts +78 -52
- package/src/hosts/codex-configuration.ts +5 -10
- package/src/hosts/codex-exec-controls.ts +516 -0
- package/src/hosts/codex-marketplace.ts +12 -10
- package/src/hosts/codex-native-calls.ts +15 -122
- package/src/hosts/codex-process.ts +10 -183
- package/src/hosts/codex-profile.ts +36 -21
- package/src/hosts/codex-session-files.ts +1 -9
- package/src/hosts/codex-state.ts +134 -18
- package/src/hosts/codex.ts +210 -183
- package/src/hosts/isolation-common.ts +8 -11
- package/src/hosts/isolation-roots.ts +5 -4
- package/src/hosts/linux-sandbox.ts +15 -2
- package/src/hosts/mac-sandbox.ts +87 -18
- package/src/hosts/native-controls.ts +72 -22
- package/src/hosts/native-request.ts +55 -0
- package/src/hosts/process-lifecycle.ts +215 -49
- package/src/hosts/protected-worktrees.ts +3 -2
- package/src/hosts/skill-hook-catalog.ts +131 -0
- package/src/hosts/skill-hook-handler.ts +374 -0
- package/src/hosts/skill-hooks.ts +585 -0
- package/src/instrumentation.ts +7 -8
- package/src/native-transcript-state.ts +22 -3
- package/src/native-transcript-view.ts +52 -13
- package/src/native-transcripts.ts +26 -11
- package/src/paths.ts +22 -0
- package/src/process-lifecycle.ts +150 -0
- package/src/provenance.ts +34 -13
- package/src/prune.ts +300 -0
- package/src/report.ts +63 -36
- package/src/resolved-case.ts +1 -1
- package/src/results-lock.ts +42 -0
- package/src/results.ts +14 -18
- package/src/run-owner.ts +15 -9
- package/src/runner-paths.ts +21 -0
- package/src/{runtime-config.ts → runtime/config.ts} +160 -46
- package/src/{runtime-discovery-apple.ts → runtime/discovery-apple.ts} +3 -3
- package/src/{runtime-discovery-providers.ts → runtime/discovery-providers.ts} +3 -9
- package/src/{runtime-discovery.ts → runtime/discovery.ts} +4 -4
- package/src/{runtime-hook-processes.ts → runtime/hook-processes.ts} +3 -2
- package/src/{runtime-hooks.ts → runtime/hooks.ts} +40 -28
- package/src/{runtime-paths.ts → runtime/paths.ts} +5 -19
- package/src/{runtime-query.ts → runtime/query.ts} +5 -5
- package/src/{runtime-seeds.ts → runtime/seeds.ts} +3 -3
- package/src/runtime/shared-cache.ts +130 -0
- package/src/{runtime-state.ts → runtime/state.ts} +28 -11
- package/src/runtime-process.ts +194 -0
- package/src/schema-types.ts +73 -161
- package/src/shell.ts +4 -0
- package/src/sqlite-lock.ts +25 -0
- package/src/transcript-retention.ts +146 -0
- package/src/value-guards.ts +22 -0
- package/docs/assets/sevro-logo.png +0 -0
- package/docs/assets/sevro-symbol.svg +0 -1
- package/docs/assets/sevro-wordmark.svg +0 -1
- package/docs/cache-ownership-validation.md +0 -49
- package/docs/claude-continuation-validation.md +0 -47
- package/docs/concurrency-validation.md +0 -86
- package/docs/configuration-root-validation.md +0 -70
- package/docs/engine-slice.md +0 -114
- package/docs/evidence/runtime-startup-30/README.md +0 -185
- package/docs/evidence/runtime-startup-30/after.json +0 -319
- package/docs/evidence/runtime-startup-30/baseline-timeout.jsonl +0 -2
- package/docs/evidence/runtime-startup-30/before.json +0 -403
- package/docs/evidence/runtime-startup-30/consumer-smoke.json +0 -63
- package/docs/evidence/runtime-startup-30/full-policy-diagnostic.jsonl +0 -3
- package/docs/evidence/runtime-startup-30/minimal-policy-diagnostic.jsonl +0 -3
- package/docs/evidence/runtime-startup-30/plugin-template-assessment.json +0 -20
- package/docs/evidence/runtime-startup-30/seedless-timeout.jsonl +0 -2
- package/docs/evidence.md +0 -17
- package/docs/fixture-cleanup-validation.md +0 -73
- package/docs/guide-verification.json +0 -239
- package/src/evaluation-context.ts +0 -259
- package/src/evaluation-fixture.ts +0 -302
- package/src/evaluation-run.ts +0 -200
- package/src/evaluation-trial.ts +0 -1016
- package/src/hosts/claude-nested-skills.ts +0 -272
- package/src/hosts/codex-command-output.ts +0 -510
- package/src/hosts/codex-executor-command.ts +0 -291
- package/src/hosts/codex-skill-reads.ts +0 -783
- /package/src/{trial-scheduler.ts → evaluation/scheduler.ts} +0 -0
package/src/cli/init.ts
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
1
|
+
import { examplePath, sourceRuntime } from "../runner-paths";
|
|
2
|
+
import { cp, mkdir, rm, writeFile } from "node:fs/promises";
|
|
3
|
+
import { dirname, join, resolve } from "node:path";
|
|
4
|
+
import { parseArgs } from "node:util";
|
|
5
|
+
import {
|
|
6
|
+
nativeReadme,
|
|
7
|
+
templateCommand,
|
|
8
|
+
templateSettings,
|
|
9
|
+
} from "./init-settings";
|
|
10
|
+
|
|
11
|
+
function initOptions(argv: string[]) {
|
|
12
|
+
const { values, positionals } = parseArgs({
|
|
13
|
+
args: argv,
|
|
14
|
+
strict: true,
|
|
15
|
+
allowPositionals: true,
|
|
16
|
+
options: {
|
|
17
|
+
template: { type: "string", default: "response" },
|
|
18
|
+
directory: { type: "string", default: "sevro-evaluation" },
|
|
19
|
+
},
|
|
20
|
+
});
|
|
21
|
+
if (
|
|
22
|
+
positionals.length ||
|
|
23
|
+
!["response", "coding", "repository-skill"].includes(values.template)
|
|
24
|
+
)
|
|
25
|
+
throw new Error(
|
|
26
|
+
"use --template response, coding or repository-skill; run sevro init --help",
|
|
27
|
+
);
|
|
28
|
+
if (!values.directory.trim())
|
|
29
|
+
throw new Error("--directory must name a new directory");
|
|
30
|
+
return { template: values.template, destination: resolve(values.directory) };
|
|
31
|
+
}
|
|
32
|
+
|
|
33
|
+
async function reserveDirectory(destination: string): Promise<void> {
|
|
34
|
+
await mkdir(dirname(destination), { recursive: true });
|
|
35
|
+
try {
|
|
36
|
+
await mkdir(destination);
|
|
37
|
+
} catch (cause) {
|
|
38
|
+
throw new Error(
|
|
39
|
+
`init destination already exists or cannot be created: ${destination}; choose a new --directory`,
|
|
40
|
+
{ cause },
|
|
41
|
+
);
|
|
42
|
+
}
|
|
43
|
+
}
|
|
44
|
+
|
|
45
|
+
function starterReadme(template: string) {
|
|
46
|
+
if (template === "repository-skill") return nativeReadme();
|
|
47
|
+
const assertion =
|
|
48
|
+
template === "coding"
|
|
49
|
+
? "positive, negative and zero addition assertions against edited add.sh"
|
|
50
|
+
: "an exact response assertion";
|
|
51
|
+
const prerequisites =
|
|
52
|
+
template === "coding"
|
|
53
|
+
? "Node.js 24.13.0 or newer, or Bun 1.3.13, plus sandbox-exec on macOS or bubblewrap/socat on Linux"
|
|
54
|
+
: "Node.js 24.13.0 or newer, or Bun 1.3.13";
|
|
55
|
+
return `# ${template} evaluation\n\nThis deterministic adapter exercises ${assertion}, without model credentials. Prerequisites: ${prerequisites}.\n\n\`\`\`sh\nsevro run --run-manifest-file run.json --dry\nsevro run --run-manifest-file run.json\nsevro report --latest\nSEVRO_TEMPLATE_FAIL=1 sevro run --run-manifest-file run.json\n\`\`\`\n\nThe negative control must report task=failed and exit 1. Dry preparation is not an assessment.\nEdit case.json and ${sourceRuntime ? "adapter.ts" : "adapter.js"}, prepare, then run again. Keep private .sevro evidence out of Git.\nFor a native model, replace the adapter route explicitly with --host, --model and --effort; Codex also requires --codex-auth-file. No model execution or native skill dispatch is established by this adapter.\n`;
|
|
56
|
+
}
|
|
57
|
+
|
|
58
|
+
async function initialize(template: string, destination: string) {
|
|
59
|
+
await reserveDirectory(destination);
|
|
60
|
+
try {
|
|
61
|
+
await cp(examplePath("templates", template), destination, {
|
|
62
|
+
recursive: true,
|
|
63
|
+
errorOnExist: true,
|
|
64
|
+
force: false,
|
|
65
|
+
});
|
|
66
|
+
await writeFile(
|
|
67
|
+
join(destination, "run.json"),
|
|
68
|
+
JSON.stringify(
|
|
69
|
+
{ format: "sevro.run.v1", settings: templateSettings(template) },
|
|
70
|
+
null,
|
|
71
|
+
2,
|
|
72
|
+
) + "\n",
|
|
73
|
+
{ flag: "wx" },
|
|
74
|
+
);
|
|
75
|
+
if (template === "repository-skill")
|
|
76
|
+
await writeFile(
|
|
77
|
+
join(destination, "command.json"),
|
|
78
|
+
JSON.stringify(templateCommand(destination)) + "\n",
|
|
79
|
+
{ flag: "wx" },
|
|
80
|
+
);
|
|
81
|
+
await writeFile(join(destination, ".gitignore"), ".sevro/\n", {
|
|
82
|
+
flag: "wx",
|
|
83
|
+
});
|
|
84
|
+
await writeFile(join(destination, "README.md"), starterReadme(template), {
|
|
85
|
+
flag: "wx",
|
|
86
|
+
});
|
|
87
|
+
} catch (cause) {
|
|
88
|
+
await rm(destination, { recursive: true, force: true });
|
|
89
|
+
throw cause;
|
|
90
|
+
}
|
|
91
|
+
}
|
|
92
|
+
|
|
93
|
+
export async function initCommand(argv: string[]): Promise<number> {
|
|
94
|
+
try {
|
|
95
|
+
const { template, destination } = initOptions(argv);
|
|
96
|
+
await initialize(template, destination);
|
|
97
|
+
const quoted = `'${destination.replaceAll("'", "'\\''")}'`;
|
|
98
|
+
const native =
|
|
99
|
+
template === "repository-skill"
|
|
100
|
+
? " --model YOUR_MODEL --effort YOUR_EFFORT --codex-auth-file /absolute/auth.json"
|
|
101
|
+
: "";
|
|
102
|
+
process.stdout.write(
|
|
103
|
+
`Created ${template} evaluation at ${destination}\nOpen README.md, then:\n cd ${quoted}\n sevro run --run-manifest-file run.json${native} --dry\n sevro run --run-manifest-file run.json${native}\n`,
|
|
104
|
+
);
|
|
105
|
+
return 0;
|
|
106
|
+
} catch (error) {
|
|
107
|
+
process.stderr.write(
|
|
108
|
+
`sevro: ${error instanceof Error ? error.message : "initialization failed"}\n`,
|
|
109
|
+
);
|
|
110
|
+
return 64;
|
|
111
|
+
}
|
|
112
|
+
}
|