@namzu/sdk 14.0.7 → 15.0.0
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/CHANGELOG.md +81 -0
- package/dist/types/agent/lifecycle-event.d.ts +0 -13
- package/dist/types/agent/lifecycle-event.d.ts.map +1 -1
- package/dist/types/agent/task.d.ts +0 -12
- package/dist/types/agent/task.d.ts.map +1 -1
- package/dist/types/agent/task.js.map +1 -1
- package/package.json +11 -1
- package/src/types/agent/lifecycle-event.ts +0 -9
- package/src/types/agent/task.ts +0 -13
- package/dist/__tests__/default-path-conformance.test.d.ts +0 -2
- package/dist/__tests__/default-path-conformance.test.d.ts.map +0 -1
- package/dist/__tests__/default-path-conformance.test.js +0 -262
- package/dist/__tests__/default-path-conformance.test.js.map +0 -1
- package/dist/__tests__/replay-public-surface.test.d.ts +0 -2
- package/dist/__tests__/replay-public-surface.test.d.ts.map +0 -1
- package/dist/__tests__/replay-public-surface.test.js +0 -45
- package/dist/__tests__/replay-public-surface.test.js.map +0 -1
- package/dist/__tests__/shipped-defaults.test.d.ts +0 -2
- package/dist/__tests__/shipped-defaults.test.d.ts.map +0 -1
- package/dist/__tests__/shipped-defaults.test.js +0 -97
- package/dist/__tests__/shipped-defaults.test.js.map +0 -1
- package/dist/advisory/__tests__/budget-enforcement.test.d.ts +0 -2
- package/dist/advisory/__tests__/budget-enforcement.test.d.ts.map +0 -1
- package/dist/advisory/__tests__/budget-enforcement.test.js +0 -159
- package/dist/advisory/__tests__/budget-enforcement.test.js.map +0 -1
- package/dist/advisory/__tests__/consultation-context.test.d.ts +0 -2
- package/dist/advisory/__tests__/consultation-context.test.d.ts.map +0 -1
- package/dist/advisory/__tests__/consultation-context.test.js +0 -124
- package/dist/advisory/__tests__/consultation-context.test.js.map +0 -1
- package/dist/advisory/__tests__/structured-response.test.d.ts +0 -2
- package/dist/advisory/__tests__/structured-response.test.d.ts.map +0 -1
- package/dist/advisory/__tests__/structured-response.test.js +0 -99
- package/dist/advisory/__tests__/structured-response.test.js.map +0 -1
- package/dist/advisory/context.test.d.ts +0 -16
- package/dist/advisory/context.test.d.ts.map +0 -1
- package/dist/advisory/context.test.js +0 -92
- package/dist/advisory/context.test.js.map +0 -1
- package/dist/advisory/evaluator.test.d.ts +0 -34
- package/dist/advisory/evaluator.test.d.ts.map +0 -1
- package/dist/advisory/evaluator.test.js +0 -172
- package/dist/advisory/evaluator.test.js.map +0 -1
- package/dist/advisory/executor.test.d.ts +0 -38
- package/dist/advisory/executor.test.d.ts.map +0 -1
- package/dist/advisory/executor.test.js +0 -262
- package/dist/advisory/executor.test.js.map +0 -1
- package/dist/advisory/registry.test.d.ts +0 -16
- package/dist/advisory/registry.test.d.ts.map +0 -1
- package/dist/advisory/registry.test.js +0 -62
- package/dist/advisory/registry.test.js.map +0 -1
- package/dist/agents/__tests__/a-policy-nobody-can-select.test.d.ts +0 -2
- package/dist/agents/__tests__/a-policy-nobody-can-select.test.d.ts.map +0 -1
- package/dist/agents/__tests__/a-policy-nobody-can-select.test.js +0 -177
- package/dist/agents/__tests__/a-policy-nobody-can-select.test.js.map +0 -1
- package/dist/agents/__tests__/idempotency-key.test.d.ts +0 -2
- package/dist/agents/__tests__/idempotency-key.test.d.ts.map +0 -1
- package/dist/agents/__tests__/idempotency-key.test.js +0 -149
- package/dist/agents/__tests__/idempotency-key.test.js.map +0 -1
- package/dist/agents/__tests__/invocation-lock.test.d.ts +0 -2
- package/dist/agents/__tests__/invocation-lock.test.d.ts.map +0 -1
- package/dist/agents/__tests__/invocation-lock.test.js +0 -126
- package/dist/agents/__tests__/invocation-lock.test.js.map +0 -1
- package/dist/agents/__tests__/lock.test.d.ts +0 -2
- package/dist/agents/__tests__/lock.test.d.ts.map +0 -1
- package/dist/agents/__tests__/lock.test.js +0 -131
- package/dist/agents/__tests__/lock.test.js.map +0 -1
- package/dist/agents/__tests__/reachability.test.d.ts +0 -2
- package/dist/agents/__tests__/reachability.test.d.ts.map +0 -1
- package/dist/agents/__tests__/reachability.test.js +0 -173
- package/dist/agents/__tests__/reachability.test.js.map +0 -1
- package/dist/agents/__tests__/run-agent-forwarding.test.d.ts +0 -2
- package/dist/agents/__tests__/run-agent-forwarding.test.d.ts.map +0 -1
- package/dist/agents/__tests__/run-agent-forwarding.test.js +0 -76
- package/dist/agents/__tests__/run-agent-forwarding.test.js.map +0 -1
- package/dist/agents/__tests__/run-agent.test.d.ts +0 -2
- package/dist/agents/__tests__/run-agent.test.d.ts.map +0 -1
- package/dist/agents/__tests__/run-agent.test.js +0 -143
- package/dist/agents/__tests__/run-agent.test.js.map +0 -1
- package/dist/agents/__tests__/run-completed-stop-reason.test.d.ts +0 -2
- package/dist/agents/__tests__/run-completed-stop-reason.test.d.ts.map +0 -1
- package/dist/agents/__tests__/run-completed-stop-reason.test.js +0 -50
- package/dist/agents/__tests__/run-completed-stop-reason.test.js.map +0 -1
- package/dist/agents/__tests__/supervisor-coordinator-registration.test.d.ts +0 -2
- package/dist/agents/__tests__/supervisor-coordinator-registration.test.d.ts.map +0 -1
- package/dist/agents/__tests__/supervisor-coordinator-registration.test.js +0 -153
- package/dist/agents/__tests__/supervisor-coordinator-registration.test.js.map +0 -1
- package/dist/agents/__tests__/supervisor-hands-down-hitl.test.d.ts +0 -2
- package/dist/agents/__tests__/supervisor-hands-down-hitl.test.d.ts.map +0 -1
- package/dist/agents/__tests__/supervisor-hands-down-hitl.test.js +0 -112
- package/dist/agents/__tests__/supervisor-hands-down-hitl.test.js.map +0 -1
- package/dist/agents/__tests__/supervisor-inbox-scope.test.d.ts +0 -2
- package/dist/agents/__tests__/supervisor-inbox-scope.test.d.ts.map +0 -1
- package/dist/agents/__tests__/supervisor-inbox-scope.test.js +0 -125
- package/dist/agents/__tests__/supervisor-inbox-scope.test.js.map +0 -1
- package/dist/agents/__tests__/supervisor-ledger.test.d.ts +0 -2
- package/dist/agents/__tests__/supervisor-ledger.test.d.ts.map +0 -1
- package/dist/agents/__tests__/supervisor-ledger.test.js +0 -131
- package/dist/agents/__tests__/supervisor-ledger.test.js.map +0 -1
- package/dist/bridge/a2a/__tests__/project-is-the-a2a-context.test.d.ts +0 -2
- package/dist/bridge/a2a/__tests__/project-is-the-a2a-context.test.d.ts.map +0 -1
- package/dist/bridge/a2a/__tests__/project-is-the-a2a-context.test.js +0 -55
- package/dist/bridge/a2a/__tests__/project-is-the-a2a-context.test.js.map +0 -1
- package/dist/bridge/a2a/agent-card.test.d.ts +0 -24
- package/dist/bridge/a2a/agent-card.test.d.ts.map +0 -1
- package/dist/bridge/a2a/agent-card.test.js +0 -118
- package/dist/bridge/a2a/agent-card.test.js.map +0 -1
- package/dist/bridge/a2a/late-events.test.d.ts +0 -2
- package/dist/bridge/a2a/late-events.test.d.ts.map +0 -1
- package/dist/bridge/a2a/late-events.test.js +0 -70
- package/dist/bridge/a2a/late-events.test.js.map +0 -1
- package/dist/bridge/a2a/mapper.test.d.ts +0 -29
- package/dist/bridge/a2a/mapper.test.d.ts.map +0 -1
- package/dist/bridge/a2a/mapper.test.js +0 -291
- package/dist/bridge/a2a/mapper.test.js.map +0 -1
- package/dist/bridge/a2a/message.test.d.ts +0 -20
- package/dist/bridge/a2a/message.test.d.ts.map +0 -1
- package/dist/bridge/a2a/message.test.js +0 -116
- package/dist/bridge/a2a/message.test.js.map +0 -1
- package/dist/bridge/a2a/task.test.d.ts +0 -29
- package/dist/bridge/a2a/task.test.d.ts.map +0 -1
- package/dist/bridge/a2a/task.test.js +0 -198
- package/dist/bridge/a2a/task.test.js.map +0 -1
- package/dist/bridge/mcp/connector/adapter.test.d.ts +0 -27
- package/dist/bridge/mcp/connector/adapter.test.d.ts.map +0 -1
- package/dist/bridge/mcp/connector/adapter.test.js +0 -203
- package/dist/bridge/mcp/connector/adapter.test.js.map +0 -1
- package/dist/bridge/sse/late-events.test.d.ts +0 -2
- package/dist/bridge/sse/late-events.test.d.ts.map +0 -1
- package/dist/bridge/sse/late-events.test.js +0 -163
- package/dist/bridge/sse/late-events.test.js.map +0 -1
- package/dist/bridge/sse/mapper.test.d.ts +0 -27
- package/dist/bridge/sse/mapper.test.d.ts.map +0 -1
- package/dist/bridge/sse/mapper.test.js +0 -378
- package/dist/bridge/sse/mapper.test.js.map +0 -1
- package/dist/bridge/tools/connector/adapter.test.d.ts +0 -28
- package/dist/bridge/tools/connector/adapter.test.d.ts.map +0 -1
- package/dist/bridge/tools/connector/adapter.test.js +0 -182
- package/dist/bridge/tools/connector/adapter.test.js.map +0 -1
- package/dist/bridge/tools/connector/definitions.test.d.ts +0 -23
- package/dist/bridge/tools/connector/definitions.test.d.ts.map +0 -1
- package/dist/bridge/tools/connector/definitions.test.js +0 -158
- package/dist/bridge/tools/connector/definitions.test.js.map +0 -1
- package/dist/bridge/tools/connector/router.test.d.ts +0 -21
- package/dist/bridge/tools/connector/router.test.d.ts.map +0 -1
- package/dist/bridge/tools/connector/router.test.js +0 -139
- package/dist/bridge/tools/connector/router.test.js.map +0 -1
- package/dist/bus/breaker.test.d.ts +0 -41
- package/dist/bus/breaker.test.d.ts.map +0 -1
- package/dist/bus/breaker.test.js +0 -242
- package/dist/bus/breaker.test.js.map +0 -1
- package/dist/bus/index.test.d.ts +0 -25
- package/dist/bus/index.test.d.ts.map +0 -1
- package/dist/bus/index.test.js +0 -151
- package/dist/bus/index.test.js.map +0 -1
- package/dist/bus/lock.test.d.ts +0 -44
- package/dist/bus/lock.test.d.ts.map +0 -1
- package/dist/bus/lock.test.js +0 -226
- package/dist/bus/lock.test.js.map +0 -1
- package/dist/bus/ownership.test.d.ts +0 -26
- package/dist/bus/ownership.test.d.ts.map +0 -1
- package/dist/bus/ownership.test.js +0 -205
- package/dist/bus/ownership.test.js.map +0 -1
- package/dist/compaction/__tests__/SlidingWindowManager.test.d.ts +0 -2
- package/dist/compaction/__tests__/SlidingWindowManager.test.d.ts.map +0 -1
- package/dist/compaction/__tests__/SlidingWindowManager.test.js +0 -113
- package/dist/compaction/__tests__/SlidingWindowManager.test.js.map +0 -1
- package/dist/compaction/__tests__/cleared-result-recovery.test.d.ts +0 -2
- package/dist/compaction/__tests__/cleared-result-recovery.test.d.ts.map +0 -1
- package/dist/compaction/__tests__/cleared-result-recovery.test.js +0 -101
- package/dist/compaction/__tests__/cleared-result-recovery.test.js.map +0 -1
- package/dist/compaction/__tests__/context-reducer.test.d.ts +0 -2
- package/dist/compaction/__tests__/context-reducer.test.d.ts.map +0 -1
- package/dist/compaction/__tests__/context-reducer.test.js +0 -197
- package/dist/compaction/__tests__/context-reducer.test.js.map +0 -1
- package/dist/compaction/__tests__/context-window.test.d.ts +0 -2
- package/dist/compaction/__tests__/context-window.test.d.ts.map +0 -1
- package/dist/compaction/__tests__/context-window.test.js +0 -62
- package/dist/compaction/__tests__/context-window.test.js.map +0 -1
- package/dist/compaction/__tests__/dangling.test.d.ts +0 -2
- package/dist/compaction/__tests__/dangling.test.d.ts.map +0 -1
- package/dist/compaction/__tests__/dangling.test.js +0 -367
- package/dist/compaction/__tests__/dangling.test.js.map +0 -1
- package/dist/compaction/__tests__/factory.test.d.ts +0 -2
- package/dist/compaction/__tests__/factory.test.d.ts.map +0 -1
- package/dist/compaction/__tests__/factory.test.js +0 -43
- package/dist/compaction/__tests__/factory.test.js.map +0 -1
- package/dist/compaction/__tests__/lossiness.test.d.ts +0 -2
- package/dist/compaction/__tests__/lossiness.test.d.ts.map +0 -1
- package/dist/compaction/__tests__/lossiness.test.js +0 -163
- package/dist/compaction/__tests__/lossiness.test.js.map +0 -1
- package/dist/compaction/__tests__/state-across-resume.test.d.ts +0 -2
- package/dist/compaction/__tests__/state-across-resume.test.d.ts.map +0 -1
- package/dist/compaction/__tests__/state-across-resume.test.js +0 -88
- package/dist/compaction/__tests__/state-across-resume.test.js.map +0 -1
- package/dist/compaction/__tests__/tool-result-editing.test.d.ts +0 -2
- package/dist/compaction/__tests__/tool-result-editing.test.d.ts.map +0 -1
- package/dist/compaction/__tests__/tool-result-editing.test.js +0 -184
- package/dist/compaction/__tests__/tool-result-editing.test.js.map +0 -1
- package/dist/compaction/__tests__/trim-opens-on-user.test.d.ts +0 -2
- package/dist/compaction/__tests__/trim-opens-on-user.test.d.ts.map +0 -1
- package/dist/compaction/__tests__/trim-opens-on-user.test.js +0 -109
- package/dist/compaction/__tests__/trim-opens-on-user.test.js.map +0 -1
- package/dist/compaction/__tests__/verifier-empty-reply.test.d.ts +0 -12
- package/dist/compaction/__tests__/verifier-empty-reply.test.d.ts.map +0 -1
- package/dist/compaction/__tests__/verifier-empty-reply.test.js +0 -73
- package/dist/compaction/__tests__/verifier-empty-reply.test.js.map +0 -1
- package/dist/compaction/__tests__/verifier-model.test.d.ts +0 -2
- package/dist/compaction/__tests__/verifier-model.test.d.ts.map +0 -1
- package/dist/compaction/__tests__/verifier-model.test.js +0 -58
- package/dist/compaction/__tests__/verifier-model.test.js.map +0 -1
- package/dist/config/__tests__/compaction-budget-schema.test.d.ts +0 -18
- package/dist/config/__tests__/compaction-budget-schema.test.d.ts.map +0 -1
- package/dist/config/__tests__/compaction-budget-schema.test.js +0 -96
- package/dist/config/__tests__/compaction-budget-schema.test.js.map +0 -1
- package/dist/connector/BaseConnector.test.d.ts +0 -21
- package/dist/connector/BaseConnector.test.d.ts.map +0 -1
- package/dist/connector/BaseConnector.test.js +0 -108
- package/dist/connector/BaseConnector.test.js.map +0 -1
- package/dist/connector/builtins/__tests__/oauth2-auth.test.d.ts +0 -2
- package/dist/connector/builtins/__tests__/oauth2-auth.test.d.ts.map +0 -1
- package/dist/connector/builtins/__tests__/oauth2-auth.test.js +0 -54
- package/dist/connector/builtins/__tests__/oauth2-auth.test.js.map +0 -1
- package/dist/connector/builtins/http.test.d.ts +0 -30
- package/dist/connector/builtins/http.test.d.ts.map +0 -1
- package/dist/connector/builtins/http.test.js +0 -260
- package/dist/connector/builtins/http.test.js.map +0 -1
- package/dist/connector/builtins/webhook.test.d.ts +0 -20
- package/dist/connector/builtins/webhook.test.d.ts.map +0 -1
- package/dist/connector/builtins/webhook.test.js +0 -130
- package/dist/connector/builtins/webhook.test.js.map +0 -1
- package/dist/connector/execution/factory.test.d.ts +0 -16
- package/dist/connector/execution/factory.test.d.ts.map +0 -1
- package/dist/connector/execution/factory.test.js +0 -64
- package/dist/connector/execution/factory.test.js.map +0 -1
- package/dist/connector/execution/remote.test.d.ts +0 -16
- package/dist/connector/execution/remote.test.d.ts.map +0 -1
- package/dist/connector/execution/remote.test.js +0 -53
- package/dist/connector/execution/remote.test.js.map +0 -1
- package/dist/connector/mcp/__tests__/a-close-that-means-closed.test.d.ts +0 -2
- package/dist/connector/mcp/__tests__/a-close-that-means-closed.test.d.ts.map +0 -1
- package/dist/connector/mcp/__tests__/a-close-that-means-closed.test.js +0 -106
- package/dist/connector/mcp/__tests__/a-close-that-means-closed.test.js.map +0 -1
- package/dist/connector/mcp/__tests__/a-transport-forgets-its-listeners.test.d.ts +0 -2
- package/dist/connector/mcp/__tests__/a-transport-forgets-its-listeners.test.d.ts.map +0 -1
- package/dist/connector/mcp/__tests__/a-transport-forgets-its-listeners.test.js +0 -101
- package/dist/connector/mcp/__tests__/a-transport-forgets-its-listeners.test.js.map +0 -1
- package/dist/connector/mcp/__tests__/discovery-policy.test.d.ts +0 -2
- package/dist/connector/mcp/__tests__/discovery-policy.test.d.ts.map +0 -1
- package/dist/connector/mcp/__tests__/discovery-policy.test.js +0 -109
- package/dist/connector/mcp/__tests__/discovery-policy.test.js.map +0 -1
- package/dist/connector/mcp/__tests__/list-pagination.test.d.ts +0 -2
- package/dist/connector/mcp/__tests__/list-pagination.test.d.ts.map +0 -1
- package/dist/connector/mcp/__tests__/list-pagination.test.js +0 -81
- package/dist/connector/mcp/__tests__/list-pagination.test.js.map +0 -1
- package/dist/connector/mcp/__tests__/policy.test.d.ts +0 -2
- package/dist/connector/mcp/__tests__/policy.test.d.ts.map +0 -1
- package/dist/connector/mcp/__tests__/policy.test.js +0 -86
- package/dist/connector/mcp/__tests__/policy.test.js.map +0 -1
- package/dist/connector/mcp/__tests__/positional-arrays.test.d.ts +0 -2
- package/dist/connector/mcp/__tests__/positional-arrays.test.d.ts.map +0 -1
- package/dist/connector/mcp/__tests__/positional-arrays.test.js +0 -142
- package/dist/connector/mcp/__tests__/positional-arrays.test.js.map +0 -1
- package/dist/connector/mcp/__tests__/prompt-as-tool.test.d.ts +0 -2
- package/dist/connector/mcp/__tests__/prompt-as-tool.test.d.ts.map +0 -1
- package/dist/connector/mcp/__tests__/prompt-as-tool.test.js +0 -122
- package/dist/connector/mcp/__tests__/prompt-as-tool.test.js.map +0 -1
- package/dist/connector/mcp/__tests__/prompts-and-lifecycle.test.d.ts +0 -2
- package/dist/connector/mcp/__tests__/prompts-and-lifecycle.test.d.ts.map +0 -1
- package/dist/connector/mcp/__tests__/prompts-and-lifecycle.test.js +0 -214
- package/dist/connector/mcp/__tests__/prompts-and-lifecycle.test.js.map +0 -1
- package/dist/connector/mcp/__tests__/protocol-negotiation.test.d.ts +0 -2
- package/dist/connector/mcp/__tests__/protocol-negotiation.test.d.ts.map +0 -1
- package/dist/connector/mcp/__tests__/protocol-negotiation.test.js +0 -81
- package/dist/connector/mcp/__tests__/protocol-negotiation.test.js.map +0 -1
- package/dist/connector/mcp/__tests__/schema-fidelity.test.d.ts +0 -2
- package/dist/connector/mcp/__tests__/schema-fidelity.test.d.ts.map +0 -1
- package/dist/connector/mcp/__tests__/schema-fidelity.test.js +0 -206
- package/dist/connector/mcp/__tests__/schema-fidelity.test.js.map +0 -1
- package/dist/connector/mcp/__tests__/structured-result.test.d.ts +0 -2
- package/dist/connector/mcp/__tests__/structured-result.test.d.ts.map +0 -1
- package/dist/connector/mcp/__tests__/structured-result.test.js +0 -112
- package/dist/connector/mcp/__tests__/structured-result.test.js.map +0 -1
- package/dist/connector/mcp/adapter.test.d.ts +0 -34
- package/dist/connector/mcp/adapter.test.d.ts.map +0 -1
- package/dist/connector/mcp/adapter.test.js +0 -199
- package/dist/connector/mcp/adapter.test.js.map +0 -1
- package/dist/connector/mcp/client.test.d.ts +0 -2
- package/dist/connector/mcp/client.test.d.ts.map +0 -1
- package/dist/connector/mcp/client.test.js +0 -105
- package/dist/connector/mcp/client.test.js.map +0 -1
- package/dist/connector/mcp/streamable-http.test.d.ts +0 -2
- package/dist/connector/mcp/streamable-http.test.d.ts.map +0 -1
- package/dist/connector/mcp/streamable-http.test.js +0 -132
- package/dist/connector/mcp/streamable-http.test.js.map +0 -1
- package/dist/constants/tools/__tests__/dangerous-patterns.test.d.ts +0 -2
- package/dist/constants/tools/__tests__/dangerous-patterns.test.d.ts.map +0 -1
- package/dist/constants/tools/__tests__/dangerous-patterns.test.js +0 -54
- package/dist/constants/tools/__tests__/dangerous-patterns.test.js.map +0 -1
- package/dist/contracts/__tests__/an-id-the-sdk-mints-passes-its-own-schema.test.d.ts +0 -2
- package/dist/contracts/__tests__/an-id-the-sdk-mints-passes-its-own-schema.test.d.ts.map +0 -1
- package/dist/contracts/__tests__/an-id-the-sdk-mints-passes-its-own-schema.test.js +0 -73
- package/dist/contracts/__tests__/an-id-the-sdk-mints-passes-its-own-schema.test.js.map +0 -1
- package/dist/directory/__tests__/derive.test.d.ts +0 -2
- package/dist/directory/__tests__/derive.test.d.ts.map +0 -1
- package/dist/directory/__tests__/derive.test.js +0 -111
- package/dist/directory/__tests__/derive.test.js.map +0 -1
- package/dist/directory/__tests__/load-diagnostics.test.d.ts +0 -2
- package/dist/directory/__tests__/load-diagnostics.test.d.ts.map +0 -1
- package/dist/directory/__tests__/load-diagnostics.test.js +0 -106
- package/dist/directory/__tests__/load-diagnostics.test.js.map +0 -1
- package/dist/directory/__tests__/load-directory.test.d.ts +0 -2
- package/dist/directory/__tests__/load-directory.test.d.ts.map +0 -1
- package/dist/directory/__tests__/load-directory.test.js +0 -196
- package/dist/directory/__tests__/load-directory.test.js.map +0 -1
- package/dist/directory/__tests__/subagents.test.d.ts +0 -2
- package/dist/directory/__tests__/subagents.test.d.ts.map +0 -1
- package/dist/directory/__tests__/subagents.test.js +0 -117
- package/dist/directory/__tests__/subagents.test.js.map +0 -1
- package/dist/directory/__tests__/supervisor-budget.test.d.ts +0 -2
- package/dist/directory/__tests__/supervisor-budget.test.d.ts.map +0 -1
- package/dist/directory/__tests__/supervisor-budget.test.js +0 -97
- package/dist/directory/__tests__/supervisor-budget.test.js.map +0 -1
- package/dist/eval/__tests__/case-deadline.test.d.ts +0 -2
- package/dist/eval/__tests__/case-deadline.test.d.ts.map +0 -1
- package/dist/eval/__tests__/case-deadline.test.js +0 -128
- package/dist/eval/__tests__/case-deadline.test.js.map +0 -1
- package/dist/eval/__tests__/end-to-end.test.d.ts +0 -2
- package/dist/eval/__tests__/end-to-end.test.d.ts.map +0 -1
- package/dist/eval/__tests__/end-to-end.test.js +0 -223
- package/dist/eval/__tests__/end-to-end.test.js.map +0 -1
- package/dist/eval/__tests__/harness-honesty.test.d.ts +0 -2
- package/dist/eval/__tests__/harness-honesty.test.d.ts.map +0 -1
- package/dist/eval/__tests__/harness-honesty.test.js +0 -85
- package/dist/eval/__tests__/harness-honesty.test.js.map +0 -1
- package/dist/eval/__tests__/harness.test.d.ts +0 -2
- package/dist/eval/__tests__/harness.test.d.ts.map +0 -1
- package/dist/eval/__tests__/harness.test.js +0 -207
- package/dist/eval/__tests__/harness.test.js.map +0 -1
- package/dist/eval/__tests__/judge.test.d.ts +0 -2
- package/dist/eval/__tests__/judge.test.d.ts.map +0 -1
- package/dist/eval/__tests__/judge.test.js +0 -255
- package/dist/eval/__tests__/judge.test.js.map +0 -1
- package/dist/eval/__tests__/scorer-gates.test.d.ts +0 -2
- package/dist/eval/__tests__/scorer-gates.test.d.ts.map +0 -1
- package/dist/eval/__tests__/scorer-gates.test.js +0 -136
- package/dist/eval/__tests__/scorer-gates.test.js.map +0 -1
- package/dist/execution/local.test.d.ts +0 -2
- package/dist/execution/local.test.d.ts.map +0 -1
- package/dist/execution/local.test.js +0 -37
- package/dist/execution/local.test.js.map +0 -1
- package/dist/gateway/__tests__/a-gateway-that-forgets-the-oldest.test.d.ts +0 -2
- package/dist/gateway/__tests__/a-gateway-that-forgets-the-oldest.test.d.ts.map +0 -1
- package/dist/gateway/__tests__/a-gateway-that-forgets-the-oldest.test.js +0 -96
- package/dist/gateway/__tests__/a-gateway-that-forgets-the-oldest.test.js.map +0 -1
- package/dist/gateway/__tests__/a-knob-nobody-can-turn.test.d.ts +0 -2
- package/dist/gateway/__tests__/a-knob-nobody-can-turn.test.d.ts.map +0 -1
- package/dist/gateway/__tests__/a-knob-nobody-can-turn.test.js +0 -114
- package/dist/gateway/__tests__/a-knob-nobody-can-turn.test.js.map +0 -1
- package/dist/gateway/__tests__/a-progress-tee-cannot-name-a-task-that-does-not-exist.test.d.ts +0 -2
- package/dist/gateway/__tests__/a-progress-tee-cannot-name-a-task-that-does-not-exist.test.d.ts.map +0 -1
- package/dist/gateway/__tests__/a-progress-tee-cannot-name-a-task-that-does-not-exist.test.js +0 -137
- package/dist/gateway/__tests__/a-progress-tee-cannot-name-a-task-that-does-not-exist.test.js.map +0 -1
- package/dist/gateway/__tests__/completion-inbox.test.d.ts +0 -2
- package/dist/gateway/__tests__/completion-inbox.test.d.ts.map +0 -1
- package/dist/gateway/__tests__/completion-inbox.test.js +0 -565
- package/dist/gateway/__tests__/completion-inbox.test.js.map +0 -1
- package/dist/gateway/__tests__/list-survives-eviction.test.d.ts +0 -2
- package/dist/gateway/__tests__/list-survives-eviction.test.d.ts.map +0 -1
- package/dist/gateway/__tests__/list-survives-eviction.test.js +0 -102
- package/dist/gateway/__tests__/list-survives-eviction.test.js.map +0 -1
- package/dist/manager/agent/__tests__/a-fan-out-to-one-agent-id.test.d.ts +0 -2
- package/dist/manager/agent/__tests__/a-fan-out-to-one-agent-id.test.d.ts.map +0 -1
- package/dist/manager/agent/__tests__/a-fan-out-to-one-agent-id.test.js +0 -101
- package/dist/manager/agent/__tests__/a-fan-out-to-one-agent-id.test.js.map +0 -1
- package/dist/manager/agent/__tests__/an-env-reaches-the-child-it-was-set-for.test.d.ts +0 -2
- package/dist/manager/agent/__tests__/an-env-reaches-the-child-it-was-set-for.test.d.ts.map +0 -1
- package/dist/manager/agent/__tests__/an-env-reaches-the-child-it-was-set-for.test.js +0 -159
- package/dist/manager/agent/__tests__/an-env-reaches-the-child-it-was-set-for.test.js.map +0 -1
- package/dist/manager/agent/__tests__/depth-limit-authority.test.d.ts +0 -2
- package/dist/manager/agent/__tests__/depth-limit-authority.test.d.ts.map +0 -1
- package/dist/manager/agent/__tests__/depth-limit-authority.test.js +0 -58
- package/dist/manager/agent/__tests__/depth-limit-authority.test.js.map +0 -1
- package/dist/manager/agent/__tests__/dispose-cancels.test.d.ts +0 -2
- package/dist/manager/agent/__tests__/dispose-cancels.test.d.ts.map +0 -1
- package/dist/manager/agent/__tests__/dispose-cancels.test.js +0 -88
- package/dist/manager/agent/__tests__/dispose-cancels.test.js.map +0 -1
- package/dist/manager/agent/__tests__/hitl-across-spawn.test.d.ts +0 -2
- package/dist/manager/agent/__tests__/hitl-across-spawn.test.d.ts.map +0 -1
- package/dist/manager/agent/__tests__/hitl-across-spawn.test.js +0 -226
- package/dist/manager/agent/__tests__/hitl-across-spawn.test.js.map +0 -1
- package/dist/manager/agent/__tests__/lifecycle.test.d.ts +0 -2
- package/dist/manager/agent/__tests__/lifecycle.test.d.ts.map +0 -1
- package/dist/manager/agent/__tests__/lifecycle.test.js +0 -602
- package/dist/manager/agent/__tests__/lifecycle.test.js.map +0 -1
- package/dist/manager/plan/__tests__/a-plan-that-succeeded-is-not-failed.test.d.ts +0 -2
- package/dist/manager/plan/__tests__/a-plan-that-succeeded-is-not-failed.test.d.ts.map +0 -1
- package/dist/manager/plan/__tests__/a-plan-that-succeeded-is-not-failed.test.js +0 -73
- package/dist/manager/plan/__tests__/a-plan-that-succeeded-is-not-failed.test.js.map +0 -1
- package/dist/manager/project/__tests__/a-closed-workspace-takes-no-work.test.d.ts +0 -2
- package/dist/manager/project/__tests__/a-closed-workspace-takes-no-work.test.d.ts.map +0 -1
- package/dist/manager/project/__tests__/a-closed-workspace-takes-no-work.test.js +0 -248
- package/dist/manager/project/__tests__/a-closed-workspace-takes-no-work.test.js.map +0 -1
- package/dist/manager/thread/__tests__/lifecycle.test.d.ts +0 -2
- package/dist/manager/thread/__tests__/lifecycle.test.d.ts.map +0 -1
- package/dist/manager/thread/__tests__/lifecycle.test.js +0 -216
- package/dist/manager/thread/__tests__/lifecycle.test.js.map +0 -1
- package/dist/plugin/__tests__/discovery-scopes.test.d.ts +0 -2
- package/dist/plugin/__tests__/discovery-scopes.test.d.ts.map +0 -1
- package/dist/plugin/__tests__/discovery-scopes.test.js +0 -97
- package/dist/plugin/__tests__/discovery-scopes.test.js.map +0 -1
- package/dist/plugin/__tests__/enable-contributions.test.d.ts +0 -2
- package/dist/plugin/__tests__/enable-contributions.test.d.ts.map +0 -1
- package/dist/plugin/__tests__/enable-contributions.test.js +0 -269
- package/dist/plugin/__tests__/enable-contributions.test.js.map +0 -1
- package/dist/plugin/__tests__/hook-ordering.test.d.ts +0 -2
- package/dist/plugin/__tests__/hook-ordering.test.d.ts.map +0 -1
- package/dist/plugin/__tests__/hook-ordering.test.js +0 -227
- package/dist/plugin/__tests__/hook-ordering.test.js.map +0 -1
- package/dist/plugin/__tests__/install-time-refusal.test.d.ts +0 -2
- package/dist/plugin/__tests__/install-time-refusal.test.d.ts.map +0 -1
- package/dist/plugin/__tests__/install-time-refusal.test.js +0 -49
- package/dist/plugin/__tests__/install-time-refusal.test.js.map +0 -1
- package/dist/plugin/__tests__/lifecycle.test.d.ts +0 -2
- package/dist/plugin/__tests__/lifecycle.test.d.ts.map +0 -1
- package/dist/plugin/__tests__/lifecycle.test.js +0 -389
- package/dist/plugin/__tests__/lifecycle.test.js.map +0 -1
- package/dist/plugin/__tests__/mcp-admission.test.d.ts +0 -2
- package/dist/plugin/__tests__/mcp-admission.test.d.ts.map +0 -1
- package/dist/plugin/__tests__/mcp-admission.test.js +0 -227
- package/dist/plugin/__tests__/mcp-admission.test.js.map +0 -1
- package/dist/plugin/__tests__/path-containment.test.d.ts +0 -2
- package/dist/plugin/__tests__/path-containment.test.d.ts.map +0 -1
- package/dist/plugin/__tests__/path-containment.test.js +0 -91
- package/dist/plugin/__tests__/path-containment.test.js.map +0 -1
- package/dist/probe/registry.test.d.ts +0 -13
- package/dist/probe/registry.test.d.ts.map +0 -1
- package/dist/probe/registry.test.js +0 -348
- package/dist/probe/registry.test.js.map +0 -1
- package/dist/provider/__tests__/errors.test.d.ts +0 -2
- package/dist/provider/__tests__/errors.test.d.ts.map +0 -1
- package/dist/provider/__tests__/errors.test.js +0 -61
- package/dist/provider/__tests__/errors.test.js.map +0 -1
- package/dist/provider/__tests__/mock-script.test.d.ts +0 -2
- package/dist/provider/__tests__/mock-script.test.d.ts.map +0 -1
- package/dist/provider/__tests__/mock-script.test.js +0 -151
- package/dist/provider/__tests__/mock-script.test.js.map +0 -1
- package/dist/provider/__tests__/model-version.test.d.ts +0 -2
- package/dist/provider/__tests__/model-version.test.d.ts.map +0 -1
- package/dist/provider/__tests__/model-version.test.js +0 -80
- package/dist/provider/__tests__/model-version.test.js.map +0 -1
- package/dist/provider/__tests__/registry.test.d.ts +0 -16
- package/dist/provider/__tests__/registry.test.d.ts.map +0 -1
- package/dist/provider/__tests__/registry.test.js +0 -303
- package/dist/provider/__tests__/registry.test.js.map +0 -1
- package/dist/provider/__tests__/retry-visibility.test.d.ts +0 -2
- package/dist/provider/__tests__/retry-visibility.test.d.ts.map +0 -1
- package/dist/provider/__tests__/retry-visibility.test.js +0 -137
- package/dist/provider/__tests__/retry-visibility.test.js.map +0 -1
- package/dist/provider/__tests__/retry.test.d.ts +0 -2
- package/dist/provider/__tests__/retry.test.d.ts.map +0 -1
- package/dist/provider/__tests__/retry.test.js +0 -259
- package/dist/provider/__tests__/retry.test.js.map +0 -1
- package/dist/provider/__tests__/strict-schema.test.d.ts +0 -2
- package/dist/provider/__tests__/strict-schema.test.d.ts.map +0 -1
- package/dist/provider/__tests__/strict-schema.test.js +0 -157
- package/dist/provider/__tests__/strict-schema.test.js.map +0 -1
- package/dist/provider/__tests__/thinking-support.test.d.ts +0 -2
- package/dist/provider/__tests__/thinking-support.test.d.ts.map +0 -1
- package/dist/provider/__tests__/thinking-support.test.js +0 -47
- package/dist/provider/__tests__/thinking-support.test.js.map +0 -1
- package/dist/provider/__tests__/typed-error-classification.test.d.ts +0 -2
- package/dist/provider/__tests__/typed-error-classification.test.d.ts.map +0 -1
- package/dist/provider/__tests__/typed-error-classification.test.js +0 -123
- package/dist/provider/__tests__/typed-error-classification.test.js.map +0 -1
- package/dist/provider/__tests__/vendor-detail.test.d.ts +0 -2
- package/dist/provider/__tests__/vendor-detail.test.d.ts.map +0 -1
- package/dist/provider/__tests__/vendor-detail.test.js +0 -89
- package/dist/provider/__tests__/vendor-detail.test.js.map +0 -1
- package/dist/provider/collect.test.d.ts +0 -22
- package/dist/provider/collect.test.d.ts.map +0 -1
- package/dist/provider/collect.test.js +0 -123
- package/dist/provider/collect.test.js.map +0 -1
- package/dist/provider/instrumentation.test.d.ts +0 -17
- package/dist/provider/instrumentation.test.d.ts.map +0 -1
- package/dist/provider/instrumentation.test.js +0 -138
- package/dist/provider/instrumentation.test.js.map +0 -1
- package/dist/rag/__tests__/namespace-isolation.test.d.ts +0 -2
- package/dist/rag/__tests__/namespace-isolation.test.d.ts.map +0 -1
- package/dist/rag/__tests__/namespace-isolation.test.js +0 -80
- package/dist/rag/__tests__/namespace-isolation.test.js.map +0 -1
- package/dist/rag/__tests__/retrieval-math.test.d.ts +0 -2
- package/dist/rag/__tests__/retrieval-math.test.d.ts.map +0 -1
- package/dist/rag/__tests__/retrieval-math.test.js +0 -46
- package/dist/rag/__tests__/retrieval-math.test.js.map +0 -1
- package/dist/rag/chunking.test.d.ts +0 -20
- package/dist/rag/chunking.test.d.ts.map +0 -1
- package/dist/rag/chunking.test.js +0 -92
- package/dist/rag/chunking.test.js.map +0 -1
- package/dist/rag/context-assembler.test.d.ts +0 -19
- package/dist/rag/context-assembler.test.d.ts.map +0 -1
- package/dist/rag/context-assembler.test.js +0 -98
- package/dist/rag/context-assembler.test.js.map +0 -1
- package/dist/rag/embedding.test.d.ts +0 -19
- package/dist/rag/embedding.test.d.ts.map +0 -1
- package/dist/rag/embedding.test.js +0 -164
- package/dist/rag/embedding.test.js.map +0 -1
- package/dist/rag/ingestion.test.d.ts +0 -22
- package/dist/rag/ingestion.test.d.ts.map +0 -1
- package/dist/rag/ingestion.test.js +0 -99
- package/dist/rag/ingestion.test.js.map +0 -1
- package/dist/rag/knowledge-base.test.d.ts +0 -17
- package/dist/rag/knowledge-base.test.d.ts.map +0 -1
- package/dist/rag/knowledge-base.test.js +0 -77
- package/dist/rag/knowledge-base.test.js.map +0 -1
- package/dist/rag/rag-tool.test.d.ts +0 -21
- package/dist/rag/rag-tool.test.d.ts.map +0 -1
- package/dist/rag/rag-tool.test.js +0 -149
- package/dist/rag/rag-tool.test.js.map +0 -1
- package/dist/rag/retriever.test.d.ts +0 -26
- package/dist/rag/retriever.test.d.ts.map +0 -1
- package/dist/rag/retriever.test.js +0 -180
- package/dist/rag/retriever.test.js.map +0 -1
- package/dist/rag/vector-store.test.d.ts +0 -38
- package/dist/rag/vector-store.test.d.ts.map +0 -1
- package/dist/rag/vector-store.test.js +0 -175
- package/dist/rag/vector-store.test.js.map +0 -1
- package/dist/registry/ManagedRegistry.test.d.ts +0 -21
- package/dist/registry/ManagedRegistry.test.d.ts.map +0 -1
- package/dist/registry/ManagedRegistry.test.js +0 -98
- package/dist/registry/ManagedRegistry.test.js.map +0 -1
- package/dist/registry/Registry.test.d.ts +0 -18
- package/dist/registry/Registry.test.d.ts.map +0 -1
- package/dist/registry/Registry.test.js +0 -79
- package/dist/registry/Registry.test.js.map +0 -1
- package/dist/registry/agent/definitions.test.d.ts +0 -15
- package/dist/registry/agent/definitions.test.d.ts.map +0 -1
- package/dist/registry/agent/definitions.test.js +0 -84
- package/dist/registry/agent/definitions.test.js.map +0 -1
- package/dist/registry/connector/definitions.test.d.ts +0 -13
- package/dist/registry/connector/definitions.test.d.ts.map +0 -1
- package/dist/registry/connector/definitions.test.js +0 -41
- package/dist/registry/connector/definitions.test.js.map +0 -1
- package/dist/registry/connector/scoped.test.d.ts +0 -21
- package/dist/registry/connector/scoped.test.d.ts.map +0 -1
- package/dist/registry/connector/scoped.test.js +0 -115
- package/dist/registry/connector/scoped.test.js.map +0 -1
- package/dist/registry/plugin/index.test.d.ts +0 -12
- package/dist/registry/plugin/index.test.d.ts.map +0 -1
- package/dist/registry/plugin/index.test.js +0 -69
- package/dist/registry/plugin/index.test.js.map +0 -1
- package/dist/registry/tool/__tests__/dialect.test.d.ts +0 -2
- package/dist/registry/tool/__tests__/dialect.test.d.ts.map +0 -1
- package/dist/registry/tool/__tests__/dialect.test.js +0 -146
- package/dist/registry/tool/__tests__/dialect.test.js.map +0 -1
- package/dist/registry/tool/__tests__/schema.test.d.ts +0 -2
- package/dist/registry/tool/__tests__/schema.test.d.ts.map +0 -1
- package/dist/registry/tool/__tests__/schema.test.js +0 -176
- package/dist/registry/tool/__tests__/schema.test.js.map +0 -1
- package/dist/registry/tool/__tests__/strict-registration.test.d.ts +0 -2
- package/dist/registry/tool/__tests__/strict-registration.test.d.ts.map +0 -1
- package/dist/registry/tool/__tests__/strict-registration.test.js +0 -82
- package/dist/registry/tool/__tests__/strict-registration.test.js.map +0 -1
- package/dist/registry/tool/__tests__/tool-name-validation.test.d.ts +0 -2
- package/dist/registry/tool/__tests__/tool-name-validation.test.d.ts.map +0 -1
- package/dist/registry/tool/__tests__/tool-name-validation.test.js +0 -70
- package/dist/registry/tool/__tests__/tool-name-validation.test.js.map +0 -1
- package/dist/registry/tool/execute.test.d.ts +0 -47
- package/dist/registry/tool/execute.test.d.ts.map +0 -1
- package/dist/registry/tool/execute.test.js +0 -549
- package/dist/registry/tool/execute.test.js.map +0 -1
- package/dist/registry/toolset/catalog.test.d.ts +0 -2
- package/dist/registry/toolset/catalog.test.d.ts.map +0 -1
- package/dist/registry/toolset/catalog.test.js +0 -247
- package/dist/registry/toolset/catalog.test.js.map +0 -1
- package/dist/run/LimitChecker.test.d.ts +0 -2
- package/dist/run/LimitChecker.test.d.ts.map +0 -1
- package/dist/run/LimitChecker.test.js +0 -26
- package/dist/run/LimitChecker.test.js.map +0 -1
- package/dist/runtime/bidi/__tests__/session.test.d.ts +0 -2
- package/dist/runtime/bidi/__tests__/session.test.d.ts.map +0 -1
- package/dist/runtime/bidi/__tests__/session.test.js +0 -201
- package/dist/runtime/bidi/__tests__/session.test.js.map +0 -1
- package/dist/runtime/decision/parser.test.d.ts +0 -2
- package/dist/runtime/decision/parser.test.d.ts.map +0 -1
- package/dist/runtime/decision/parser.test.js +0 -37
- package/dist/runtime/decision/parser.test.js.map +0 -1
- package/dist/runtime/query/__tests__/a-plan-that-succeeded-says-so.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/a-plan-that-succeeded-says-so.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/a-plan-that-succeeded-says-so.test.js +0 -90
- package/dist/runtime/query/__tests__/a-plan-that-succeeded-says-so.test.js.map +0 -1
- package/dist/runtime/query/__tests__/a-settled-plan-reaches-the-host.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/a-settled-plan-reaches-the-host.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/a-settled-plan-reaches-the-host.test.js +0 -97
- package/dist/runtime/query/__tests__/a-settled-plan-reaches-the-host.test.js.map +0 -1
- package/dist/runtime/query/__tests__/answer-review.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/answer-review.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/answer-review.test.js +0 -141
- package/dist/runtime/query/__tests__/answer-review.test.js.map +0 -1
- package/dist/runtime/query/__tests__/capability-negotiation.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/capability-negotiation.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/capability-negotiation.test.js +0 -235
- package/dist/runtime/query/__tests__/capability-negotiation.test.js.map +0 -1
- package/dist/runtime/query/__tests__/checkpoint-store.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/checkpoint-store.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/checkpoint-store.test.js +0 -227
- package/dist/runtime/query/__tests__/checkpoint-store.test.js.map +0 -1
- package/dist/runtime/query/__tests__/checkpoint.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/checkpoint.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/checkpoint.test.js +0 -148
- package/dist/runtime/query/__tests__/checkpoint.test.js.map +0 -1
- package/dist/runtime/query/__tests__/citations.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/citations.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/citations.test.js +0 -85
- package/dist/runtime/query/__tests__/citations.test.js.map +0 -1
- package/dist/runtime/query/__tests__/completion-does-not-erase-the-answer.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/completion-does-not-erase-the-answer.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/completion-does-not-erase-the-answer.test.js +0 -142
- package/dist/runtime/query/__tests__/completion-does-not-erase-the-answer.test.js.map +0 -1
- package/dist/runtime/query/__tests__/completion-notification.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/completion-notification.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/completion-notification.test.js +0 -550
- package/dist/runtime/query/__tests__/completion-notification.test.js.map +0 -1
- package/dist/runtime/query/__tests__/content-budget.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/content-budget.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/content-budget.test.js +0 -69
- package/dist/runtime/query/__tests__/content-budget.test.js.map +0 -1
- package/dist/runtime/query/__tests__/context-size-on-the-wire.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/context-size-on-the-wire.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/context-size-on-the-wire.test.js +0 -100
- package/dist/runtime/query/__tests__/context-size-on-the-wire.test.js.map +0 -1
- package/dist/runtime/query/__tests__/context.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/context.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/context.test.js +0 -104
- package/dist/runtime/query/__tests__/context.test.js.map +0 -1
- package/dist/runtime/query/__tests__/deferred-tools.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/deferred-tools.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/deferred-tools.test.js +0 -176
- package/dist/runtime/query/__tests__/deferred-tools.test.js.map +0 -1
- package/dist/runtime/query/__tests__/delegation-resume.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/delegation-resume.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/delegation-resume.test.js +0 -111
- package/dist/runtime/query/__tests__/delegation-resume.test.js.map +0 -1
- package/dist/runtime/query/__tests__/document-attachments.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/document-attachments.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/document-attachments.test.js +0 -92
- package/dist/runtime/query/__tests__/document-attachments.test.js.map +0 -1
- package/dist/runtime/query/__tests__/durable-park-and-trace.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/durable-park-and-trace.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/durable-park-and-trace.test.js +0 -194
- package/dist/runtime/query/__tests__/durable-park-and-trace.test.js.map +0 -1
- package/dist/runtime/query/__tests__/durable-question-park.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/durable-question-park.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/durable-question-park.test.js +0 -253
- package/dist/runtime/query/__tests__/durable-question-park.test.js.map +0 -1
- package/dist/runtime/query/__tests__/durable-run-state.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/durable-run-state.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/durable-run-state.test.js +0 -158
- package/dist/runtime/query/__tests__/durable-run-state.test.js.map +0 -1
- package/dist/runtime/query/__tests__/effort-reaches-the-wire.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/effort-reaches-the-wire.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/effort-reaches-the-wire.test.js +0 -118
- package/dist/runtime/query/__tests__/effort-reaches-the-wire.test.js.map +0 -1
- package/dist/runtime/query/__tests__/executor-concurrency.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/executor-concurrency.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/executor-concurrency.test.js +0 -98
- package/dist/runtime/query/__tests__/executor-concurrency.test.js.map +0 -1
- package/dist/runtime/query/__tests__/executor-plugin-hooks.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/executor-plugin-hooks.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/executor-plugin-hooks.test.js +0 -275
- package/dist/runtime/query/__tests__/executor-plugin-hooks.test.js.map +0 -1
- package/dist/runtime/query/__tests__/finish-reason-vs-tool-calls.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/finish-reason-vs-tool-calls.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/finish-reason-vs-tool-calls.test.js +0 -187
- package/dist/runtime/query/__tests__/finish-reason-vs-tool-calls.test.js.map +0 -1
- package/dist/runtime/query/__tests__/grant-cannot-overrule-the-gate.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/grant-cannot-overrule-the-gate.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/grant-cannot-overrule-the-gate.test.js +0 -95
- package/dist/runtime/query/__tests__/grant-cannot-overrule-the-gate.test.js.map +0 -1
- package/dist/runtime/query/__tests__/guardrails-e2e.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/guardrails-e2e.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/guardrails-e2e.test.js +0 -132
- package/dist/runtime/query/__tests__/guardrails-e2e.test.js.map +0 -1
- package/dist/runtime/query/__tests__/guardrails.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/guardrails.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/guardrails.test.js +0 -163
- package/dist/runtime/query/__tests__/guardrails.test.js.map +0 -1
- package/dist/runtime/query/__tests__/hook-model-visibility.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/hook-model-visibility.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/hook-model-visibility.test.js +0 -119
- package/dist/runtime/query/__tests__/hook-model-visibility.test.js.map +0 -1
- package/dist/runtime/query/__tests__/long-document-flow.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/long-document-flow.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/long-document-flow.test.js +0 -161
- package/dist/runtime/query/__tests__/long-document-flow.test.js.map +0 -1
- package/dist/runtime/query/__tests__/memory-promotion.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/memory-promotion.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/memory-promotion.test.js +0 -119
- package/dist/runtime/query/__tests__/memory-promotion.test.js.map +0 -1
- package/dist/runtime/query/__tests__/orphan-task-turn-end.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/orphan-task-turn-end.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/orphan-task-turn-end.test.js +0 -88
- package/dist/runtime/query/__tests__/orphan-task-turn-end.test.js.map +0 -1
- package/dist/runtime/query/__tests__/overflow-relief.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/overflow-relief.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/overflow-relief.test.js +0 -119
- package/dist/runtime/query/__tests__/overflow-relief.test.js.map +0 -1
- package/dist/runtime/query/__tests__/partial-batch-resume.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/partial-batch-resume.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/partial-batch-resume.test.js +0 -205
- package/dist/runtime/query/__tests__/partial-batch-resume.test.js.map +0 -1
- package/dist/runtime/query/__tests__/per-step-skills.test.d.ts +0 -10
- package/dist/runtime/query/__tests__/per-step-skills.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/per-step-skills.test.js +0 -122
- package/dist/runtime/query/__tests__/per-step-skills.test.js.map +0 -1
- package/dist/runtime/query/__tests__/per-step-tool-choice.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/per-step-tool-choice.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/per-step-tool-choice.test.js +0 -153
- package/dist/runtime/query/__tests__/per-step-tool-choice.test.js.map +0 -1
- package/dist/runtime/query/__tests__/plugin-hooks.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/plugin-hooks.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/plugin-hooks.test.js +0 -20
- package/dist/runtime/query/__tests__/plugin-hooks.test.js.map +0 -1
- package/dist/runtime/query/__tests__/prepare-step-chain.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/prepare-step-chain.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/prepare-step-chain.test.js +0 -104
- package/dist/runtime/query/__tests__/prepare-step-chain.test.js.map +0 -1
- package/dist/runtime/query/__tests__/prepare-step.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/prepare-step.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/prepare-step.test.js +0 -194
- package/dist/runtime/query/__tests__/prepare-step.test.js.map +0 -1
- package/dist/runtime/query/__tests__/probe-veto-is-error.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/probe-veto-is-error.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/probe-veto-is-error.test.js +0 -111
- package/dist/runtime/query/__tests__/probe-veto-is-error.test.js.map +0 -1
- package/dist/runtime/query/__tests__/prompt.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/prompt.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/prompt.test.js +0 -84
- package/dist/runtime/query/__tests__/prompt.test.js.map +0 -1
- package/dist/runtime/query/__tests__/provider-fault-pauses.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/provider-fault-pauses.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/provider-fault-pauses.test.js +0 -86
- package/dist/runtime/query/__tests__/provider-fault-pauses.test.js.map +0 -1
- package/dist/runtime/query/__tests__/reasoning-stream.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/reasoning-stream.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/reasoning-stream.test.js +0 -146
- package/dist/runtime/query/__tests__/reasoning-stream.test.js.map +0 -1
- package/dist/runtime/query/__tests__/recoverable-settle.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/recoverable-settle.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/recoverable-settle.test.js +0 -119
- package/dist/runtime/query/__tests__/recoverable-settle.test.js.map +0 -1
- package/dist/runtime/query/__tests__/resume-budget.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/resume-budget.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/resume-budget.test.js +0 -130
- package/dist/runtime/query/__tests__/resume-budget.test.js.map +0 -1
- package/dist/runtime/query/__tests__/resume-pending.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/resume-pending.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/resume-pending.test.js +0 -226
- package/dist/runtime/query/__tests__/resume-pending.test.js.map +0 -1
- package/dist/runtime/query/__tests__/resume-run.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/resume-run.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/resume-run.test.js +0 -211
- package/dist/runtime/query/__tests__/resume-run.test.js.map +0 -1
- package/dist/runtime/query/__tests__/rich-content-budget-wiring.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/rich-content-budget-wiring.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/rich-content-budget-wiring.test.js +0 -89
- package/dist/runtime/query/__tests__/rich-content-budget-wiring.test.js.map +0 -1
- package/dist/runtime/query/__tests__/run-survives-its-own-park.proc-test.d.ts +0 -2
- package/dist/runtime/query/__tests__/run-survives-its-own-park.proc-test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/run-survives-its-own-park.proc-test.js +0 -122
- package/dist/runtime/query/__tests__/run-survives-its-own-park.proc-test.js.map +0 -1
- package/dist/runtime/query/__tests__/steering-reaches-the-model.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/steering-reaches-the-model.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/steering-reaches-the-model.test.js +0 -94
- package/dist/runtime/query/__tests__/steering-reaches-the-model.test.js.map +0 -1
- package/dist/runtime/query/__tests__/steering.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/steering.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/steering.test.js +0 -92
- package/dist/runtime/query/__tests__/steering.test.js.map +0 -1
- package/dist/runtime/query/__tests__/step-allow-list.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/step-allow-list.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/step-allow-list.test.js +0 -171
- package/dist/runtime/query/__tests__/step-allow-list.test.js.map +0 -1
- package/dist/runtime/query/__tests__/stop-condition.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/stop-condition.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/stop-condition.test.js +0 -205
- package/dist/runtime/query/__tests__/stop-condition.test.js.map +0 -1
- package/dist/runtime/query/__tests__/stream-recovery.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/stream-recovery.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/stream-recovery.test.js +0 -190
- package/dist/runtime/query/__tests__/stream-recovery.test.js.map +0 -1
- package/dist/runtime/query/__tests__/structured-output.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/structured-output.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/structured-output.test.js +0 -219
- package/dist/runtime/query/__tests__/structured-output.test.js.map +0 -1
- package/dist/runtime/query/__tests__/structured-run-failure.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/structured-run-failure.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/structured-run-failure.test.js +0 -117
- package/dist/runtime/query/__tests__/structured-run-failure.test.js.map +0 -1
- package/dist/runtime/query/__tests__/terminal-tool.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/terminal-tool.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/terminal-tool.test.js +0 -119
- package/dist/runtime/query/__tests__/terminal-tool.test.js.map +0 -1
- package/dist/runtime/query/__tests__/the-other-approval-surface-names-the-agent.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/the-other-approval-surface-names-the-agent.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/the-other-approval-surface-names-the-agent.test.js +0 -81
- package/dist/runtime/query/__tests__/the-other-approval-surface-names-the-agent.test.js.map +0 -1
- package/dist/runtime/query/__tests__/the-plan-graph-reaches-a-host.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/the-plan-graph-reaches-a-host.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/the-plan-graph-reaches-a-host.test.js +0 -62
- package/dist/runtime/query/__tests__/the-plan-graph-reaches-a-host.test.js.map +0 -1
- package/dist/runtime/query/__tests__/tool-grants.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/tool-grants.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/tool-grants.test.js +0 -85
- package/dist/runtime/query/__tests__/tool-grants.test.js.map +0 -1
- package/dist/runtime/query/__tests__/tool-output-budget.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/tool-output-budget.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/tool-output-budget.test.js +0 -0
- package/dist/runtime/query/__tests__/tool-output-budget.test.js.map +0 -1
- package/dist/runtime/query/__tests__/tool-pause.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/tool-pause.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/tool-pause.test.js +0 -165
- package/dist/runtime/query/__tests__/tool-pause.test.js.map +0 -1
- package/dist/runtime/query/__tests__/tool-progress.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/tool-progress.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/tool-progress.test.js +0 -122
- package/dist/runtime/query/__tests__/tool-progress.test.js.map +0 -1
- package/dist/runtime/query/__tests__/tool-repair-retry.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/tool-repair-retry.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/tool-repair-retry.test.js +0 -196
- package/dist/runtime/query/__tests__/tool-repair-retry.test.js.map +0 -1
- package/dist/runtime/query/__tests__/tool-result-wire.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/tool-result-wire.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/tool-result-wire.test.js +0 -106
- package/dist/runtime/query/__tests__/tool-result-wire.test.js.map +0 -1
- package/dist/runtime/query/__tests__/tool-timeout.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/tool-timeout.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/tool-timeout.test.js +0 -218
- package/dist/runtime/query/__tests__/tool-timeout.test.js.map +0 -1
- package/dist/runtime/query/__tests__/trace-parenting.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/trace-parenting.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/trace-parenting.test.js +0 -111
- package/dist/runtime/query/__tests__/trace-parenting.test.js.map +0 -1
- package/dist/runtime/query/__tests__/wiring-seams.test.d.ts +0 -2
- package/dist/runtime/query/__tests__/wiring-seams.test.d.ts.map +0 -1
- package/dist/runtime/query/__tests__/wiring-seams.test.js +0 -237
- package/dist/runtime/query/__tests__/wiring-seams.test.js.map +0 -1
- package/dist/runtime/query/iteration/__tests__/cancel-settles-turn.test.d.ts +0 -2
- package/dist/runtime/query/iteration/__tests__/cancel-settles-turn.test.d.ts.map +0 -1
- package/dist/runtime/query/iteration/__tests__/cancel-settles-turn.test.js +0 -131
- package/dist/runtime/query/iteration/__tests__/cancel-settles-turn.test.js.map +0 -1
- package/dist/runtime/query/iteration/__tests__/settle-grace.test.d.ts +0 -2
- package/dist/runtime/query/iteration/__tests__/settle-grace.test.d.ts.map +0 -1
- package/dist/runtime/query/iteration/__tests__/settle-grace.test.js +0 -226
- package/dist/runtime/query/iteration/__tests__/settle-grace.test.js.map +0 -1
- package/dist/runtime/query/iteration/phases/__tests__/compaction-declined.test.d.ts +0 -2
- package/dist/runtime/query/iteration/phases/__tests__/compaction-declined.test.d.ts.map +0 -1
- package/dist/runtime/query/iteration/phases/__tests__/compaction-declined.test.js +0 -95
- package/dist/runtime/query/iteration/phases/__tests__/compaction-declined.test.js.map +0 -1
- package/dist/runtime/query/iteration/phases/advisory.test.d.ts +0 -42
- package/dist/runtime/query/iteration/phases/advisory.test.d.ts.map +0 -1
- package/dist/runtime/query/iteration/phases/advisory.test.js +0 -337
- package/dist/runtime/query/iteration/phases/advisory.test.js.map +0 -1
- package/dist/runtime/query/iteration/phases/compaction-model-routing.test.d.ts +0 -2
- package/dist/runtime/query/iteration/phases/compaction-model-routing.test.d.ts.map +0 -1
- package/dist/runtime/query/iteration/phases/compaction-model-routing.test.js +0 -96
- package/dist/runtime/query/iteration/phases/compaction-model-routing.test.js.map +0 -1
- package/dist/runtime/query/iteration/phases/compaction-safe-cut.test.d.ts +0 -32
- package/dist/runtime/query/iteration/phases/compaction-safe-cut.test.d.ts.map +0 -1
- package/dist/runtime/query/iteration/phases/compaction-safe-cut.test.js +0 -152
- package/dist/runtime/query/iteration/phases/compaction-safe-cut.test.js.map +0 -1
- package/dist/runtime/query/iteration/phases/context-measurement.test.d.ts +0 -21
- package/dist/runtime/query/iteration/phases/context-measurement.test.d.ts.map +0 -1
- package/dist/runtime/query/iteration/phases/context-measurement.test.js +0 -161
- package/dist/runtime/query/iteration/phases/context-measurement.test.js.map +0 -1
- package/dist/runtime/query/iteration/phases/context-reducer-dispatch.test.d.ts +0 -2
- package/dist/runtime/query/iteration/phases/context-reducer-dispatch.test.d.ts.map +0 -1
- package/dist/runtime/query/iteration/phases/context-reducer-dispatch.test.js +0 -180
- package/dist/runtime/query/iteration/phases/context-reducer-dispatch.test.js.map +0 -1
- package/dist/runtime/query/iteration/phases/hitl-abort-race.test.d.ts +0 -2
- package/dist/runtime/query/iteration/phases/hitl-abort-race.test.d.ts.map +0 -1
- package/dist/runtime/query/iteration/phases/hitl-abort-race.test.js +0 -73
- package/dist/runtime/query/iteration/phases/hitl-abort-race.test.js.map +0 -1
- package/dist/runtime/query/iteration/phases/hitl-answer-question.test.d.ts +0 -2
- package/dist/runtime/query/iteration/phases/hitl-answer-question.test.d.ts.map +0 -1
- package/dist/runtime/query/iteration/phases/hitl-answer-question.test.js +0 -122
- package/dist/runtime/query/iteration/phases/hitl-answer-question.test.js.map +0 -1
- package/dist/runtime/query/iteration/phases/overflow-escalation.test.d.ts +0 -15
- package/dist/runtime/query/iteration/phases/overflow-escalation.test.d.ts.map +0 -1
- package/dist/runtime/query/iteration/phases/overflow-escalation.test.js +0 -130
- package/dist/runtime/query/iteration/phases/overflow-escalation.test.js.map +0 -1
- package/dist/runtime/query/iteration/phases/retained-messages.test.d.ts +0 -2
- package/dist/runtime/query/iteration/phases/retained-messages.test.d.ts.map +0 -1
- package/dist/runtime/query/iteration/phases/retained-messages.test.js +0 -180
- package/dist/runtime/query/iteration/phases/retained-messages.test.js.map +0 -1
- package/dist/runtime/query/iteration/phases/tool-review-denials.test.d.ts +0 -2
- package/dist/runtime/query/iteration/phases/tool-review-denials.test.d.ts.map +0 -1
- package/dist/runtime/query/iteration/phases/tool-review-denials.test.js +0 -224
- package/dist/runtime/query/iteration/phases/tool-review-denials.test.js.map +0 -1
- package/dist/runtime/query/iteration/phases/working-memory-compaction.test.d.ts +0 -19
- package/dist/runtime/query/iteration/phases/working-memory-compaction.test.d.ts.map +0 -1
- package/dist/runtime/query/iteration/phases/working-memory-compaction.test.js +0 -188
- package/dist/runtime/query/iteration/phases/working-memory-compaction.test.js.map +0 -1
- package/dist/runtime/query/replay/__tests__/mutate.test.d.ts +0 -2
- package/dist/runtime/query/replay/__tests__/mutate.test.d.ts.map +0 -1
- package/dist/runtime/query/replay/__tests__/mutate.test.js +0 -123
- package/dist/runtime/query/replay/__tests__/mutate.test.js.map +0 -1
- package/dist/runtime/query/replay/__tests__/prepare.test.d.ts +0 -2
- package/dist/runtime/query/replay/__tests__/prepare.test.d.ts.map +0 -1
- package/dist/runtime/query/replay/__tests__/prepare.test.js +0 -171
- package/dist/runtime/query/replay/__tests__/prepare.test.js.map +0 -1
- package/dist/sandbox/__tests__/exec-cancellation.test.d.ts +0 -2
- package/dist/sandbox/__tests__/exec-cancellation.test.d.ts.map +0 -1
- package/dist/sandbox/__tests__/exec-cancellation.test.js +0 -59
- package/dist/sandbox/__tests__/exec-cancellation.test.js.map +0 -1
- package/dist/sandbox/__tests__/isolation.test.d.ts +0 -2
- package/dist/sandbox/__tests__/isolation.test.d.ts.map +0 -1
- package/dist/sandbox/__tests__/isolation.test.js +0 -139
- package/dist/sandbox/__tests__/isolation.test.js.map +0 -1
- package/dist/sandbox/__tests__/output-truncation.test.d.ts +0 -2
- package/dist/sandbox/__tests__/output-truncation.test.d.ts.map +0 -1
- package/dist/sandbox/__tests__/output-truncation.test.js +0 -88
- package/dist/sandbox/__tests__/output-truncation.test.js.map +0 -1
- package/dist/sandbox/__tests__/resource-limits.test.d.ts +0 -2
- package/dist/sandbox/__tests__/resource-limits.test.d.ts.map +0 -1
- package/dist/sandbox/__tests__/resource-limits.test.js +0 -86
- package/dist/sandbox/__tests__/resource-limits.test.js.map +0 -1
- package/dist/session/__tests__/integration/_fixtures.d.ts +0 -122
- package/dist/session/__tests__/integration/_fixtures.d.ts.map +0 -1
- package/dist/session/__tests__/integration/_fixtures.js +0 -215
- package/dist/session/__tests__/integration/_fixtures.js.map +0 -1
- package/dist/session/__tests__/integration/a-successful-delegation-disposes-its-workspace.test.d.ts +0 -21
- package/dist/session/__tests__/integration/a-successful-delegation-disposes-its-workspace.test.d.ts.map +0 -1
- package/dist/session/__tests__/integration/a-successful-delegation-disposes-its-workspace.test.js +0 -205
- package/dist/session/__tests__/integration/a-successful-delegation-disposes-its-workspace.test.js.map +0 -1
- package/dist/session/__tests__/integration/archive-gate.test.d.ts +0 -15
- package/dist/session/__tests__/integration/archive-gate.test.d.ts.map +0 -1
- package/dist/session/__tests__/integration/archive-gate.test.js +0 -214
- package/dist/session/__tests__/integration/archive-gate.test.js.map +0 -1
- package/dist/session/__tests__/integration/capacity-caps.test.d.ts +0 -13
- package/dist/session/__tests__/integration/capacity-caps.test.d.ts.map +0 -1
- package/dist/session/__tests__/integration/capacity-caps.test.js +0 -123
- package/dist/session/__tests__/integration/capacity-caps.test.js.map +0 -1
- package/dist/session/__tests__/integration/e2e-spawn.test.d.ts +0 -18
- package/dist/session/__tests__/integration/e2e-spawn.test.d.ts.map +0 -1
- package/dist/session/__tests__/integration/e2e-spawn.test.js +0 -238
- package/dist/session/__tests__/integration/e2e-spawn.test.js.map +0 -1
- package/dist/session/__tests__/integration/event-stream-ordering.test.d.ts +0 -15
- package/dist/session/__tests__/integration/event-stream-ordering.test.d.ts.map +0 -1
- package/dist/session/__tests__/integration/event-stream-ordering.test.js +0 -330
- package/dist/session/__tests__/integration/event-stream-ordering.test.js.map +0 -1
- package/dist/session/__tests__/integration/handoff-broadcast-e2e.test.d.ts +0 -12
- package/dist/session/__tests__/integration/handoff-broadcast-e2e.test.d.ts.map +0 -1
- package/dist/session/__tests__/integration/handoff-broadcast-e2e.test.js +0 -182
- package/dist/session/__tests__/integration/handoff-broadcast-e2e.test.js.map +0 -1
- package/dist/session/__tests__/integration/handoff-illegal-transition.test.d.ts +0 -18
- package/dist/session/__tests__/integration/handoff-illegal-transition.test.d.ts.map +0 -1
- package/dist/session/__tests__/integration/handoff-illegal-transition.test.js +0 -156
- package/dist/session/__tests__/integration/handoff-illegal-transition.test.js.map +0 -1
- package/dist/session/__tests__/integration/handoff-single-e2e.test.d.ts +0 -15
- package/dist/session/__tests__/integration/handoff-single-e2e.test.d.ts.map +0 -1
- package/dist/session/__tests__/integration/handoff-single-e2e.test.js +0 -188
- package/dist/session/__tests__/integration/handoff-single-e2e.test.js.map +0 -1
- package/dist/session/__tests__/integration/hierarchy-lifecycle.test.d.ts +0 -12
- package/dist/session/__tests__/integration/hierarchy-lifecycle.test.d.ts.map +0 -1
- package/dist/session/__tests__/integration/hierarchy-lifecycle.test.js +0 -158
- package/dist/session/__tests__/integration/hierarchy-lifecycle.test.js.map +0 -1
- package/dist/session/__tests__/integration/migration-filesystem.test.d.ts +0 -11
- package/dist/session/__tests__/integration/migration-filesystem.test.d.ts.map +0 -1
- package/dist/session/__tests__/integration/migration-filesystem.test.js +0 -140
- package/dist/session/__tests__/integration/migration-filesystem.test.js.map +0 -1
- package/dist/session/__tests__/integration/migration-id-prefix.test.d.ts +0 -13
- package/dist/session/__tests__/integration/migration-id-prefix.test.d.ts.map +0 -1
- package/dist/session/__tests__/integration/migration-id-prefix.test.js +0 -84
- package/dist/session/__tests__/integration/migration-id-prefix.test.js.map +0 -1
- package/dist/session/__tests__/integration/prev-artifact-dag.test.d.ts +0 -14
- package/dist/session/__tests__/integration/prev-artifact-dag.test.d.ts.map +0 -1
- package/dist/session/__tests__/integration/prev-artifact-dag.test.js +0 -242
- package/dist/session/__tests__/integration/prev-artifact-dag.test.js.map +0 -1
- package/dist/session/__tests__/integration/retention-archive.test.d.ts +0 -12
- package/dist/session/__tests__/integration/retention-archive.test.d.ts.map +0 -1
- package/dist/session/__tests__/integration/retention-archive.test.js +0 -187
- package/dist/session/__tests__/integration/retention-archive.test.js.map +0 -1
- package/dist/session/__tests__/integration/spawn-rollback.test.d.ts +0 -26
- package/dist/session/__tests__/integration/spawn-rollback.test.d.ts.map +0 -1
- package/dist/session/__tests__/integration/spawn-rollback.test.js +0 -236
- package/dist/session/__tests__/integration/spawn-rollback.test.js.map +0 -1
- package/dist/session/__tests__/integration/summary-materialization-e2e.test.d.ts +0 -18
- package/dist/session/__tests__/integration/summary-materialization-e2e.test.d.ts.map +0 -1
- package/dist/session/__tests__/integration/summary-materialization-e2e.test.js +0 -201
- package/dist/session/__tests__/integration/summary-materialization-e2e.test.js.map +0 -1
- package/dist/session/__tests__/integration/tenant-isolation.test.d.ts +0 -14
- package/dist/session/__tests__/integration/tenant-isolation.test.d.ts.map +0 -1
- package/dist/session/__tests__/integration/tenant-isolation.test.js +0 -189
- package/dist/session/__tests__/integration/tenant-isolation.test.js.map +0 -1
- package/dist/session/handoff/__tests__/broadcast.test.d.ts +0 -2
- package/dist/session/handoff/__tests__/broadcast.test.d.ts.map +0 -1
- package/dist/session/handoff/__tests__/broadcast.test.js +0 -261
- package/dist/session/handoff/__tests__/broadcast.test.js.map +0 -1
- package/dist/session/handoff/__tests__/capacity.test.d.ts +0 -2
- package/dist/session/handoff/__tests__/capacity.test.d.ts.map +0 -1
- package/dist/session/handoff/__tests__/capacity.test.js +0 -103
- package/dist/session/handoff/__tests__/capacity.test.js.map +0 -1
- package/dist/session/handoff/__tests__/single.test.d.ts +0 -2
- package/dist/session/handoff/__tests__/single.test.d.ts.map +0 -1
- package/dist/session/handoff/__tests__/single.test.js +0 -239
- package/dist/session/handoff/__tests__/single.test.js.map +0 -1
- package/dist/session/intervention/__tests__/prev-artifact.test.d.ts +0 -2
- package/dist/session/intervention/__tests__/prev-artifact.test.d.ts.map +0 -1
- package/dist/session/intervention/__tests__/prev-artifact.test.js +0 -179
- package/dist/session/intervention/__tests__/prev-artifact.test.js.map +0 -1
- package/dist/session/migration/__tests__/a-migrated-project-id-is-an-id.test.d.ts +0 -2
- package/dist/session/migration/__tests__/a-migrated-project-id-is-an-id.test.d.ts.map +0 -1
- package/dist/session/migration/__tests__/a-migrated-project-id-is-an-id.test.js +0 -75
- package/dist/session/migration/__tests__/a-migrated-project-id-is-an-id.test.js.map +0 -1
- package/dist/session/migration/__tests__/filesystem.test.d.ts +0 -2
- package/dist/session/migration/__tests__/filesystem.test.d.ts.map +0 -1
- package/dist/session/migration/__tests__/filesystem.test.js +0 -192
- package/dist/session/migration/__tests__/filesystem.test.js.map +0 -1
- package/dist/session/migration/__tests__/id-prefix.test.d.ts +0 -2
- package/dist/session/migration/__tests__/id-prefix.test.d.ts.map +0 -1
- package/dist/session/migration/__tests__/id-prefix.test.js +0 -83
- package/dist/session/migration/__tests__/id-prefix.test.js.map +0 -1
- package/dist/session/migration/__tests__/marker.test.d.ts +0 -2
- package/dist/session/migration/__tests__/marker.test.d.ts.map +0 -1
- package/dist/session/migration/__tests__/marker.test.js +0 -75
- package/dist/session/migration/__tests__/marker.test.js.map +0 -1
- package/dist/session/retention/__tests__/archive.test.d.ts +0 -2
- package/dist/session/retention/__tests__/archive.test.d.ts.map +0 -1
- package/dist/session/retention/__tests__/archive.test.js +0 -253
- package/dist/session/retention/__tests__/archive.test.js.map +0 -1
- package/dist/session/retention/__tests__/disk-backend.test.d.ts +0 -2
- package/dist/session/retention/__tests__/disk-backend.test.d.ts.map +0 -1
- package/dist/session/retention/__tests__/disk-backend.test.js +0 -154
- package/dist/session/retention/__tests__/disk-backend.test.js.map +0 -1
- package/dist/session/status/__tests__/derive.test.d.ts +0 -2
- package/dist/session/status/__tests__/derive.test.d.ts.map +0 -1
- package/dist/session/status/__tests__/derive.test.js +0 -69
- package/dist/session/status/__tests__/derive.test.js.map +0 -1
- package/dist/session/summary/__tests__/materialize.test.d.ts +0 -2
- package/dist/session/summary/__tests__/materialize.test.d.ts.map +0 -1
- package/dist/session/summary/__tests__/materialize.test.js +0 -271
- package/dist/session/summary/__tests__/materialize.test.js.map +0 -1
- package/dist/session/workspace/__tests__/git-worktree.test.d.ts +0 -2
- package/dist/session/workspace/__tests__/git-worktree.test.d.ts.map +0 -1
- package/dist/session/workspace/__tests__/git-worktree.test.js +0 -248
- package/dist/session/workspace/__tests__/git-worktree.test.js.map +0 -1
- package/dist/session/workspace/__tests__/path-builder.test.d.ts +0 -2
- package/dist/session/workspace/__tests__/path-builder.test.d.ts.map +0 -1
- package/dist/session/workspace/__tests__/path-builder.test.js +0 -37
- package/dist/session/workspace/__tests__/path-builder.test.js.map +0 -1
- package/dist/session/workspace/__tests__/shared-run.test.d.ts +0 -2
- package/dist/session/workspace/__tests__/shared-run.test.d.ts.map +0 -1
- package/dist/session/workspace/__tests__/shared-run.test.js +0 -162
- package/dist/session/workspace/__tests__/shared-run.test.js.map +0 -1
- package/dist/skills/__tests__/frontmatter.test.d.ts +0 -2
- package/dist/skills/__tests__/frontmatter.test.d.ts.map +0 -1
- package/dist/skills/__tests__/frontmatter.test.js +0 -106
- package/dist/skills/__tests__/frontmatter.test.js.map +0 -1
- package/dist/skills/loader.test.d.ts +0 -2
- package/dist/skills/loader.test.d.ts.map +0 -1
- package/dist/skills/loader.test.js +0 -65
- package/dist/skills/loader.test.js.map +0 -1
- package/dist/store/__tests__/checkpoint-integrity.test.d.ts +0 -2
- package/dist/store/__tests__/checkpoint-integrity.test.d.ts.map +0 -1
- package/dist/store/__tests__/checkpoint-integrity.test.js +0 -112
- package/dist/store/__tests__/checkpoint-integrity.test.js.map +0 -1
- package/dist/store/__tests__/checkpoint-versioning.test.d.ts +0 -2
- package/dist/store/__tests__/checkpoint-versioning.test.d.ts.map +0 -1
- package/dist/store/__tests__/checkpoint-versioning.test.js +0 -151
- package/dist/store/__tests__/checkpoint-versioning.test.js.map +0 -1
- package/dist/store/__tests__/schema-adoption.test.d.ts +0 -2
- package/dist/store/__tests__/schema-adoption.test.d.ts.map +0 -1
- package/dist/store/__tests__/schema-adoption.test.js +0 -90
- package/dist/store/__tests__/schema-adoption.test.js.map +0 -1
- package/dist/store/__tests__/schema.test.d.ts +0 -2
- package/dist/store/__tests__/schema.test.d.ts.map +0 -1
- package/dist/store/__tests__/schema.test.js +0 -93
- package/dist/store/__tests__/schema.test.js.map +0 -1
- package/dist/store/session/__tests__/a-session-has-one-writer.test.d.ts +0 -2
- package/dist/store/session/__tests__/a-session-has-one-writer.test.d.ts.map +0 -1
- package/dist/store/session/__tests__/a-session-has-one-writer.test.js +0 -79
- package/dist/store/session/__tests__/a-session-has-one-writer.test.js.map +0 -1
- package/dist/store/session/__tests__/a-workspace-can-be-configured.test.d.ts +0 -2
- package/dist/store/session/__tests__/a-workspace-can-be-configured.test.d.ts.map +0 -1
- package/dist/store/session/__tests__/a-workspace-can-be-configured.test.js +0 -149
- package/dist/store/session/__tests__/a-workspace-can-be-configured.test.js.map +0 -1
- package/dist/store/session/__tests__/disk.test.d.ts +0 -2
- package/dist/store/session/__tests__/disk.test.d.ts.map +0 -1
- package/dist/store/session/__tests__/disk.test.js +0 -267
- package/dist/store/session/__tests__/disk.test.js.map +0 -1
- package/dist/store/session/__tests__/memory.test.d.ts +0 -2
- package/dist/store/session/__tests__/memory.test.d.ts.map +0 -1
- package/dist/store/session/__tests__/memory.test.js +0 -258
- package/dist/store/session/__tests__/memory.test.js.map +0 -1
- package/dist/store/task/__tests__/an-edge-that-already-exists-is-not-news.test.d.ts +0 -2
- package/dist/store/task/__tests__/an-edge-that-already-exists-is-not-news.test.d.ts.map +0 -1
- package/dist/store/task/__tests__/an-edge-that-already-exists-is-not-news.test.js +0 -95
- package/dist/store/task/__tests__/an-edge-that-already-exists-is-not-news.test.js.map +0 -1
- package/dist/store/task/__tests__/disk-concurrency.test.d.ts +0 -2
- package/dist/store/task/__tests__/disk-concurrency.test.d.ts.map +0 -1
- package/dist/store/task/__tests__/disk-concurrency.test.js +0 -91
- package/dist/store/task/__tests__/disk-concurrency.test.js.map +0 -1
- package/dist/store/task/__tests__/lookup-across-runs.test.d.ts +0 -2
- package/dist/store/task/__tests__/lookup-across-runs.test.d.ts.map +0 -1
- package/dist/store/task/__tests__/lookup-across-runs.test.js +0 -60
- package/dist/store/task/__tests__/lookup-across-runs.test.js.map +0 -1
- package/dist/streaming/coalesce.test.d.ts +0 -19
- package/dist/streaming/coalesce.test.d.ts.map +0 -1
- package/dist/streaming/coalesce.test.js +0 -120
- package/dist/streaming/coalesce.test.js.map +0 -1
- package/dist/telemetry/__tests__/latency-instruments.test.d.ts +0 -2
- package/dist/telemetry/__tests__/latency-instruments.test.d.ts.map +0 -1
- package/dist/telemetry/__tests__/latency-instruments.test.js +0 -82
- package/dist/telemetry/__tests__/latency-instruments.test.js.map +0 -1
- package/dist/telemetry/__tests__/metrics.test.d.ts +0 -2
- package/dist/telemetry/__tests__/metrics.test.d.ts.map +0 -1
- package/dist/telemetry/__tests__/metrics.test.js +0 -112
- package/dist/telemetry/__tests__/metrics.test.js.map +0 -1
- package/dist/telemetry/__tests__/model-call-span.test.d.ts +0 -2
- package/dist/telemetry/__tests__/model-call-span.test.d.ts.map +0 -1
- package/dist/telemetry/__tests__/model-call-span.test.js +0 -170
- package/dist/telemetry/__tests__/model-call-span.test.js.map +0 -1
- package/dist/telemetry/__tests__/span-closure.test.d.ts +0 -2
- package/dist/telemetry/__tests__/span-closure.test.d.ts.map +0 -1
- package/dist/telemetry/__tests__/span-closure.test.js +0 -131
- package/dist/telemetry/__tests__/span-closure.test.js.map +0 -1
- package/dist/telemetry/__tests__/span-hierarchy.test.d.ts +0 -2
- package/dist/telemetry/__tests__/span-hierarchy.test.d.ts.map +0 -1
- package/dist/telemetry/__tests__/span-hierarchy.test.js +0 -84
- package/dist/telemetry/__tests__/span-hierarchy.test.js.map +0 -1
- package/dist/test-setup.d.ts +0 -22
- package/dist/test-setup.d.ts.map +0 -1
- package/dist/test-setup.js +0 -23
- package/dist/test-setup.js.map +0 -1
- package/dist/tools/__tests__/file-tool-containment.test.d.ts +0 -2
- package/dist/tools/__tests__/file-tool-containment.test.d.ts.map +0 -1
- package/dist/tools/__tests__/file-tool-containment.test.js +0 -134
- package/dist/tools/__tests__/file-tool-containment.test.js.map +0 -1
- package/dist/tools/__tests__/path-containment.test.d.ts +0 -2
- package/dist/tools/__tests__/path-containment.test.d.ts.map +0 -1
- package/dist/tools/__tests__/path-containment.test.js +0 -133
- package/dist/tools/__tests__/path-containment.test.js.map +0 -1
- package/dist/tools/__tests__/posix-path.test.d.ts +0 -2
- package/dist/tools/__tests__/posix-path.test.d.ts.map +0 -1
- package/dist/tools/__tests__/posix-path.test.js +0 -67
- package/dist/tools/__tests__/posix-path.test.js.map +0 -1
- package/dist/tools/__tests__/sandboxed-search.test.d.ts +0 -2
- package/dist/tools/__tests__/sandboxed-search.test.d.ts.map +0 -1
- package/dist/tools/__tests__/sandboxed-search.test.js +0 -165
- package/dist/tools/__tests__/sandboxed-search.test.js.map +0 -1
- package/dist/tools/__tests__/untrusted-envelope.test.d.ts +0 -2
- package/dist/tools/__tests__/untrusted-envelope.test.d.ts.map +0 -1
- package/dist/tools/__tests__/untrusted-envelope.test.js +0 -71
- package/dist/tools/__tests__/untrusted-envelope.test.js.map +0 -1
- package/dist/tools/builtins/__tests__/bash.proc-test.d.ts +0 -2
- package/dist/tools/builtins/__tests__/bash.proc-test.d.ts.map +0 -1
- package/dist/tools/builtins/__tests__/bash.proc-test.js +0 -115
- package/dist/tools/builtins/__tests__/bash.proc-test.js.map +0 -1
- package/dist/tools/builtins/__tests__/bash.test.d.ts +0 -2
- package/dist/tools/builtins/__tests__/bash.test.d.ts.map +0 -1
- package/dist/tools/builtins/__tests__/bash.test.js +0 -65
- package/dist/tools/builtins/__tests__/bash.test.js.map +0 -1
- package/dist/tools/builtins/__tests__/computer-use.test.d.ts +0 -2
- package/dist/tools/builtins/__tests__/computer-use.test.d.ts.map +0 -1
- package/dist/tools/builtins/__tests__/computer-use.test.js +0 -156
- package/dist/tools/builtins/__tests__/computer-use.test.js.map +0 -1
- package/dist/tools/builtins/__tests__/edit-commits-atomically.test.d.ts +0 -2
- package/dist/tools/builtins/__tests__/edit-commits-atomically.test.d.ts.map +0 -1
- package/dist/tools/builtins/__tests__/edit-commits-atomically.test.js +0 -78
- package/dist/tools/builtins/__tests__/edit-commits-atomically.test.js.map +0 -1
- package/dist/tools/builtins/__tests__/edit-insert-reachable.test.d.ts +0 -2
- package/dist/tools/builtins/__tests__/edit-insert-reachable.test.d.ts.map +0 -1
- package/dist/tools/builtins/__tests__/edit-insert-reachable.test.js +0 -120
- package/dist/tools/builtins/__tests__/edit-insert-reachable.test.js.map +0 -1
- package/dist/tools/builtins/__tests__/edit.test.d.ts +0 -2
- package/dist/tools/builtins/__tests__/edit.test.d.ts.map +0 -1
- package/dist/tools/builtins/__tests__/edit.test.js +0 -286
- package/dist/tools/builtins/__tests__/edit.test.js.map +0 -1
- package/dist/tools/builtins/__tests__/payload-budget.test.d.ts +0 -2
- package/dist/tools/builtins/__tests__/payload-budget.test.d.ts.map +0 -1
- package/dist/tools/builtins/__tests__/payload-budget.test.js +0 -70
- package/dist/tools/builtins/__tests__/payload-budget.test.js.map +0 -1
- package/dist/tools/builtins/__tests__/read-file.test.d.ts +0 -2
- package/dist/tools/builtins/__tests__/read-file.test.d.ts.map +0 -1
- package/dist/tools/builtins/__tests__/read-file.test.js +0 -55
- package/dist/tools/builtins/__tests__/read-file.test.js.map +0 -1
- package/dist/tools/builtins/__tests__/stale-file-refusal.test.d.ts +0 -2
- package/dist/tools/builtins/__tests__/stale-file-refusal.test.d.ts.map +0 -1
- package/dist/tools/builtins/__tests__/stale-file-refusal.test.js +0 -187
- package/dist/tools/builtins/__tests__/stale-file-refusal.test.js.map +0 -1
- package/dist/tools/builtins/__tests__/structuredOutput.test.d.ts +0 -2
- package/dist/tools/builtins/__tests__/structuredOutput.test.d.ts.map +0 -1
- package/dist/tools/builtins/__tests__/structuredOutput.test.js +0 -224
- package/dist/tools/builtins/__tests__/structuredOutput.test.js.map +0 -1
- package/dist/tools/builtins/__tests__/verify-outputs.test.d.ts +0 -2
- package/dist/tools/builtins/__tests__/verify-outputs.test.d.ts.map +0 -1
- package/dist/tools/builtins/__tests__/verify-outputs.test.js +0 -52
- package/dist/tools/builtins/__tests__/verify-outputs.test.js.map +0 -1
- package/dist/tools/builtins/__tests__/write-file.test.d.ts +0 -2
- package/dist/tools/builtins/__tests__/write-file.test.d.ts.map +0 -1
- package/dist/tools/builtins/__tests__/write-file.test.js +0 -133
- package/dist/tools/builtins/__tests__/write-file.test.js.map +0 -1
- package/dist/tools/coordinator/__tests__/a-failed-worker-is-not-an-answer.test.d.ts +0 -2
- package/dist/tools/coordinator/__tests__/a-failed-worker-is-not-an-answer.test.d.ts.map +0 -1
- package/dist/tools/coordinator/__tests__/a-failed-worker-is-not-an-answer.test.js +0 -101
- package/dist/tools/coordinator/__tests__/a-failed-worker-is-not-an-answer.test.js.map +0 -1
- package/dist/tools/coordinator/__tests__/a-listing-is-not-a-back-door.test.d.ts +0 -2
- package/dist/tools/coordinator/__tests__/a-listing-is-not-a-back-door.test.d.ts.map +0 -1
- package/dist/tools/coordinator/__tests__/a-listing-is-not-a-back-door.test.js +0 -139
- package/dist/tools/coordinator/__tests__/a-listing-is-not-a-back-door.test.js.map +0 -1
- package/dist/tools/coordinator/__tests__/a-plan-step-reports-its-own-outcome.test.d.ts +0 -2
- package/dist/tools/coordinator/__tests__/a-plan-step-reports-its-own-outcome.test.d.ts.map +0 -1
- package/dist/tools/coordinator/__tests__/a-plan-step-reports-its-own-outcome.test.js +0 -160
- package/dist/tools/coordinator/__tests__/a-plan-step-reports-its-own-outcome.test.js.map +0 -1
- package/dist/tools/coordinator/__tests__/agent.test.d.ts +0 -15
- package/dist/tools/coordinator/__tests__/agent.test.d.ts.map +0 -1
- package/dist/tools/coordinator/__tests__/agent.test.js +0 -147
- package/dist/tools/coordinator/__tests__/agent.test.js.map +0 -1
- package/dist/tools/coordinator/__tests__/allow-delegation.test.d.ts +0 -2
- package/dist/tools/coordinator/__tests__/allow-delegation.test.d.ts.map +0 -1
- package/dist/tools/coordinator/__tests__/allow-delegation.test.js +0 -94
- package/dist/tools/coordinator/__tests__/allow-delegation.test.js.map +0 -1
- package/dist/tools/coordinator/__tests__/an-approver-is-never-shown-an-impossible-step.test.d.ts +0 -2
- package/dist/tools/coordinator/__tests__/an-approver-is-never-shown-an-impossible-step.test.d.ts.map +0 -1
- package/dist/tools/coordinator/__tests__/an-approver-is-never-shown-an-impossible-step.test.js +0 -115
- package/dist/tools/coordinator/__tests__/an-approver-is-never-shown-an-impossible-step.test.js.map +0 -1
- package/dist/tools/coordinator/__tests__/approve-plan.test.d.ts +0 -2
- package/dist/tools/coordinator/__tests__/approve-plan.test.d.ts.map +0 -1
- package/dist/tools/coordinator/__tests__/approve-plan.test.js +0 -129
- package/dist/tools/coordinator/__tests__/approve-plan.test.js.map +0 -1
- package/dist/tools/coordinator/__tests__/ask-user-question.test.d.ts +0 -2
- package/dist/tools/coordinator/__tests__/ask-user-question.test.d.ts.map +0 -1
- package/dist/tools/coordinator/__tests__/ask-user-question.test.js +0 -411
- package/dist/tools/coordinator/__tests__/ask-user-question.test.js.map +0 -1
- package/dist/tools/coordinator/__tests__/completion-delivery.test.d.ts +0 -2
- package/dist/tools/coordinator/__tests__/completion-delivery.test.d.ts.map +0 -1
- package/dist/tools/coordinator/__tests__/completion-delivery.test.js +0 -376
- package/dist/tools/coordinator/__tests__/completion-delivery.test.js.map +0 -1
- package/dist/tools/coordinator/__tests__/empty-roster.test.d.ts +0 -2
- package/dist/tools/coordinator/__tests__/empty-roster.test.d.ts.map +0 -1
- package/dist/tools/coordinator/__tests__/empty-roster.test.js +0 -97
- package/dist/tools/coordinator/__tests__/empty-roster.test.js.map +0 -1
- package/dist/tools/coordinator/__tests__/plan-dependencies.test.d.ts +0 -2
- package/dist/tools/coordinator/__tests__/plan-dependencies.test.d.ts.map +0 -1
- package/dist/tools/coordinator/__tests__/plan-dependencies.test.js +0 -126
- package/dist/tools/coordinator/__tests__/plan-dependencies.test.js.map +0 -1
- package/dist/tools/coordinator/__tests__/task-list.test.d.ts +0 -13
- package/dist/tools/coordinator/__tests__/task-list.test.d.ts.map +0 -1
- package/dist/tools/coordinator/__tests__/task-list.test.js +0 -268
- package/dist/tools/coordinator/__tests__/task-list.test.js.map +0 -1
- package/dist/tools/coordinator/__tests__/the-plan-a-human-approves.test.d.ts +0 -2
- package/dist/tools/coordinator/__tests__/the-plan-a-human-approves.test.d.ts.map +0 -1
- package/dist/tools/coordinator/__tests__/the-plan-a-human-approves.test.js +0 -99
- package/dist/tools/coordinator/__tests__/the-plan-a-human-approves.test.js.map +0 -1
- package/dist/tools/coordinator/__tests__/wait-with-idle-bound.test.d.ts +0 -2
- package/dist/tools/coordinator/__tests__/wait-with-idle-bound.test.d.ts.map +0 -1
- package/dist/tools/coordinator/__tests__/wait-with-idle-bound.test.js +0 -193
- package/dist/tools/coordinator/__tests__/wait-with-idle-bound.test.js.map +0 -1
- package/dist/types/common/__tests__/numeric-correctness.test.d.ts +0 -2
- package/dist/types/common/__tests__/numeric-correctness.test.d.ts.map +0 -1
- package/dist/types/common/__tests__/numeric-correctness.test.js +0 -108
- package/dist/types/common/__tests__/numeric-correctness.test.js.map +0 -1
- package/dist/types/common/usage-merge.test.d.ts +0 -2
- package/dist/types/common/usage-merge.test.d.ts.map +0 -1
- package/dist/types/common/usage-merge.test.js +0 -48
- package/dist/types/common/usage-merge.test.js.map +0 -1
- package/dist/types/errors/__tests__/catalog.test.d.ts +0 -2
- package/dist/types/errors/__tests__/catalog.test.d.ts.map +0 -1
- package/dist/types/errors/__tests__/catalog.test.js +0 -106
- package/dist/types/errors/__tests__/catalog.test.js.map +0 -1
- package/dist/types/errors/__tests__/errors.test.d.ts +0 -2
- package/dist/types/errors/__tests__/errors.test.d.ts.map +0 -1
- package/dist/types/errors/__tests__/errors.test.js +0 -104
- package/dist/types/errors/__tests__/errors.test.js.map +0 -1
- package/dist/types/invocation/__tests__/state.test.d.ts +0 -2
- package/dist/types/invocation/__tests__/state.test.d.ts.map +0 -1
- package/dist/types/invocation/__tests__/state.test.js +0 -174
- package/dist/types/invocation/__tests__/state.test.js.map +0 -1
- package/dist/types/provider/__tests__/cause-chain.test.d.ts +0 -2
- package/dist/types/provider/__tests__/cause-chain.test.d.ts.map +0 -1
- package/dist/types/provider/__tests__/cause-chain.test.js +0 -108
- package/dist/types/provider/__tests__/cause-chain.test.js.map +0 -1
- package/dist/types/provider/__tests__/declared-retryable.test.d.ts +0 -2
- package/dist/types/provider/__tests__/declared-retryable.test.d.ts.map +0 -1
- package/dist/types/provider/__tests__/declared-retryable.test.js +0 -70
- package/dist/types/provider/__tests__/declared-retryable.test.js.map +0 -1
- package/dist/types/provider/__tests__/overflow-classification.test.d.ts +0 -2
- package/dist/types/provider/__tests__/overflow-classification.test.d.ts.map +0 -1
- package/dist/types/provider/__tests__/overflow-classification.test.js +0 -80
- package/dist/types/provider/__tests__/overflow-classification.test.js.map +0 -1
- package/dist/types/run/__tests__/step.test.d.ts +0 -2
- package/dist/types/run/__tests__/step.test.d.ts.map +0 -1
- package/dist/types/run/__tests__/step.test.js +0 -107
- package/dist/types/run/__tests__/step.test.js.map +0 -1
- package/dist/utils/__tests__/abort-reason.test.d.ts +0 -2
- package/dist/utils/__tests__/abort-reason.test.d.ts.map +0 -1
- package/dist/utils/__tests__/abort-reason.test.js +0 -48
- package/dist/utils/__tests__/abort-reason.test.js.map +0 -1
- package/dist/utils/__tests__/atomic-write.test.d.ts +0 -2
- package/dist/utils/__tests__/atomic-write.test.d.ts.map +0 -1
- package/dist/utils/__tests__/atomic-write.test.js +0 -91
- package/dist/utils/__tests__/atomic-write.test.js.map +0 -1
- package/dist/utils/__tests__/shell-compress.test.d.ts +0 -2
- package/dist/utils/__tests__/shell-compress.test.d.ts.map +0 -1
- package/dist/utils/__tests__/shell-compress.test.js +0 -41
- package/dist/utils/__tests__/shell-compress.test.js.map +0 -1
- package/dist/vault/instrumentation.test.d.ts +0 -2
- package/dist/vault/instrumentation.test.d.ts.map +0 -1
- package/dist/vault/instrumentation.test.js +0 -80
- package/dist/vault/instrumentation.test.js.map +0 -1
- package/dist/verification/__tests__/argument-pattern.test.d.ts +0 -2
- package/dist/verification/__tests__/argument-pattern.test.d.ts.map +0 -1
- package/dist/verification/__tests__/argument-pattern.test.js +0 -122
- package/dist/verification/__tests__/argument-pattern.test.js.map +0 -1
- package/dist/verification/__tests__/rule-order-and-reason.test.d.ts +0 -2
- package/dist/verification/__tests__/rule-order-and-reason.test.d.ts.map +0 -1
- package/dist/verification/__tests__/rule-order-and-reason.test.js +0 -126
- package/dist/verification/__tests__/rule-order-and-reason.test.js.map +0 -1
- package/dist/verification/presets.test.d.ts +0 -16
- package/dist/verification/presets.test.d.ts.map +0 -1
- package/dist/verification/presets.test.js +0 -79
- package/dist/verification/presets.test.js.map +0 -1
- package/src/__tests__/default-path-conformance.test.ts +0 -306
- package/src/__tests__/replay-public-surface.test.ts +0 -54
- package/src/__tests__/shipped-defaults.test.ts +0 -111
- package/src/advisory/__tests__/budget-enforcement.test.ts +0 -208
- package/src/advisory/__tests__/consultation-context.test.ts +0 -191
- package/src/advisory/__tests__/structured-response.test.ts +0 -128
- package/src/advisory/context.test.ts +0 -109
- package/src/advisory/evaluator.test.ts +0 -192
- package/src/advisory/executor.test.ts +0 -301
- package/src/advisory/registry.test.ts +0 -75
- package/src/agents/__tests__/a-policy-nobody-can-select.test.ts +0 -202
- package/src/agents/__tests__/idempotency-key.test.ts +0 -177
- package/src/agents/__tests__/invocation-lock.test.ts +0 -154
- package/src/agents/__tests__/lock.test.ts +0 -158
- package/src/agents/__tests__/reachability.test.ts +0 -224
- package/src/agents/__tests__/run-agent-forwarding.test.ts +0 -85
- package/src/agents/__tests__/run-agent.test.ts +0 -165
- package/src/agents/__tests__/run-completed-stop-reason.test.ts +0 -59
- package/src/agents/__tests__/supervisor-coordinator-registration.test.ts +0 -185
- package/src/agents/__tests__/supervisor-hands-down-hitl.test.ts +0 -131
- package/src/agents/__tests__/supervisor-inbox-scope.test.ts +0 -149
- package/src/agents/__tests__/supervisor-ledger.test.ts +0 -185
- package/src/bridge/a2a/__tests__/project-is-the-a2a-context.test.ts +0 -66
- package/src/bridge/a2a/agent-card.test.ts +0 -140
- package/src/bridge/a2a/late-events.test.ts +0 -84
- package/src/bridge/a2a/mapper.test.ts +0 -319
- package/src/bridge/a2a/message.test.ts +0 -138
- package/src/bridge/a2a/task.test.ts +0 -235
- package/src/bridge/mcp/connector/adapter.test.ts +0 -230
- package/src/bridge/sse/late-events.test.ts +0 -182
- package/src/bridge/sse/mapper.test.ts +0 -550
- package/src/bridge/tools/connector/adapter.test.ts +0 -224
- package/src/bridge/tools/connector/definitions.test.ts +0 -183
- package/src/bridge/tools/connector/router.test.ts +0 -159
- package/src/bus/breaker.test.ts +0 -274
- package/src/bus/index.test.ts +0 -183
- package/src/bus/lock.test.ts +0 -265
- package/src/bus/ownership.test.ts +0 -243
- package/src/compaction/__tests__/SlidingWindowManager.test.ts +0 -139
- package/src/compaction/__tests__/cleared-result-recovery.test.ts +0 -118
- package/src/compaction/__tests__/context-reducer.test.ts +0 -239
- package/src/compaction/__tests__/context-window.test.ts +0 -77
- package/src/compaction/__tests__/dangling.test.ts +0 -457
- package/src/compaction/__tests__/factory.test.ts +0 -53
- package/src/compaction/__tests__/lossiness.test.ts +0 -187
- package/src/compaction/__tests__/state-across-resume.test.ts +0 -99
- package/src/compaction/__tests__/tool-result-editing.test.ts +0 -213
- package/src/compaction/__tests__/trim-opens-on-user.test.ts +0 -118
- package/src/compaction/__tests__/verifier-empty-reply.test.ts +0 -96
- package/src/compaction/__tests__/verifier-model.test.ts +0 -83
- package/src/config/__tests__/compaction-budget-schema.test.ts +0 -114
- package/src/connector/BaseConnector.test.ts +0 -130
- package/src/connector/builtins/__tests__/oauth2-auth.test.ts +0 -73
- package/src/connector/builtins/http.test.ts +0 -329
- package/src/connector/builtins/webhook.test.ts +0 -159
- package/src/connector/execution/factory.test.ts +0 -75
- package/src/connector/execution/remote.test.ts +0 -63
- package/src/connector/mcp/__tests__/a-close-that-means-closed.test.ts +0 -119
- package/src/connector/mcp/__tests__/a-transport-forgets-its-listeners.test.ts +0 -127
- package/src/connector/mcp/__tests__/discovery-policy.test.ts +0 -133
- package/src/connector/mcp/__tests__/list-pagination.test.ts +0 -98
- package/src/connector/mcp/__tests__/policy.test.ts +0 -100
- package/src/connector/mcp/__tests__/positional-arrays.test.ts +0 -183
- package/src/connector/mcp/__tests__/prompt-as-tool.test.ts +0 -157
- package/src/connector/mcp/__tests__/prompts-and-lifecycle.test.ts +0 -286
- package/src/connector/mcp/__tests__/protocol-negotiation.test.ts +0 -105
- package/src/connector/mcp/__tests__/schema-fidelity.test.ts +0 -250
- package/src/connector/mcp/__tests__/structured-result.test.ts +0 -143
- package/src/connector/mcp/adapter.test.ts +0 -249
- package/src/connector/mcp/client.test.ts +0 -159
- package/src/connector/mcp/streamable-http.test.ts +0 -169
- package/src/constants/tools/__tests__/dangerous-patterns.test.ts +0 -62
- package/src/contracts/__tests__/an-id-the-sdk-mints-passes-its-own-schema.test.ts +0 -84
- package/src/directory/__tests__/derive.test.ts +0 -135
- package/src/directory/__tests__/load-diagnostics.test.ts +0 -126
- package/src/directory/__tests__/load-directory.test.ts +0 -243
- package/src/directory/__tests__/subagents.test.ts +0 -155
- package/src/directory/__tests__/supervisor-budget.test.ts +0 -117
- package/src/eval/__tests__/case-deadline.test.ts +0 -147
- package/src/eval/__tests__/end-to-end.test.ts +0 -259
- package/src/eval/__tests__/harness-honesty.test.ts +0 -99
- package/src/eval/__tests__/harness.test.ts +0 -249
- package/src/eval/__tests__/judge.test.ts +0 -306
- package/src/eval/__tests__/scorer-gates.test.ts +0 -156
- package/src/execution/local.test.ts +0 -46
- package/src/gateway/__tests__/a-gateway-that-forgets-the-oldest.test.ts +0 -130
- package/src/gateway/__tests__/a-knob-nobody-can-turn.test.ts +0 -139
- package/src/gateway/__tests__/a-progress-tee-cannot-name-a-task-that-does-not-exist.test.ts +0 -175
- package/src/gateway/__tests__/completion-inbox.test.ts +0 -689
- package/src/gateway/__tests__/list-survives-eviction.test.ts +0 -124
- package/src/manager/agent/__tests__/a-fan-out-to-one-agent-id.test.ts +0 -118
- package/src/manager/agent/__tests__/an-env-reaches-the-child-it-was-set-for.test.ts +0 -196
- package/src/manager/agent/__tests__/depth-limit-authority.test.ts +0 -74
- package/src/manager/agent/__tests__/dispose-cancels.test.ts +0 -104
- package/src/manager/agent/__tests__/hitl-across-spawn.test.ts +0 -273
- package/src/manager/agent/__tests__/lifecycle.test.ts +0 -844
- package/src/manager/plan/__tests__/a-plan-that-succeeded-is-not-failed.test.ts +0 -88
- package/src/manager/project/__tests__/a-closed-workspace-takes-no-work.test.ts +0 -314
- package/src/manager/thread/__tests__/lifecycle.test.ts +0 -286
- package/src/plugin/__tests__/discovery-scopes.test.ts +0 -133
- package/src/plugin/__tests__/enable-contributions.test.ts +0 -299
- package/src/plugin/__tests__/hook-ordering.test.ts +0 -252
- package/src/plugin/__tests__/install-time-refusal.test.ts +0 -68
- package/src/plugin/__tests__/lifecycle.test.ts +0 -496
- package/src/plugin/__tests__/mcp-admission.test.ts +0 -286
- package/src/plugin/__tests__/path-containment.test.ts +0 -107
- package/src/probe/registry.test.ts +0 -523
- package/src/provider/__tests__/errors.test.ts +0 -85
- package/src/provider/__tests__/mock-script.test.ts +0 -179
- package/src/provider/__tests__/model-version.test.ts +0 -93
- package/src/provider/__tests__/registry.test.ts +0 -420
- package/src/provider/__tests__/retry-visibility.test.ts +0 -160
- package/src/provider/__tests__/retry.test.ts +0 -296
- package/src/provider/__tests__/strict-schema.test.ts +0 -189
- package/src/provider/__tests__/thinking-support.test.ts +0 -60
- package/src/provider/__tests__/typed-error-classification.test.ts +0 -143
- package/src/provider/__tests__/vendor-detail.test.ts +0 -107
- package/src/provider/collect.test.ts +0 -142
- package/src/provider/instrumentation.test.ts +0 -173
- package/src/rag/__tests__/namespace-isolation.test.ts +0 -109
- package/src/rag/__tests__/retrieval-math.test.ts +0 -54
- package/src/rag/chunking.test.ts +0 -107
- package/src/rag/context-assembler.test.ts +0 -114
- package/src/rag/embedding.test.ts +0 -185
- package/src/rag/ingestion.test.ts +0 -114
- package/src/rag/knowledge-base.test.ts +0 -106
- package/src/rag/rag-tool.test.ts +0 -167
- package/src/rag/retriever.test.ts +0 -210
- package/src/rag/vector-store.test.ts +0 -196
- package/src/registry/ManagedRegistry.test.ts +0 -118
- package/src/registry/Registry.test.ts +0 -91
- package/src/registry/agent/definitions.test.ts +0 -100
- package/src/registry/connector/definitions.test.ts +0 -51
- package/src/registry/connector/scoped.test.ts +0 -129
- package/src/registry/plugin/index.test.ts +0 -85
- package/src/registry/tool/__tests__/dialect.test.ts +0 -200
- package/src/registry/tool/__tests__/schema.test.ts +0 -208
- package/src/registry/tool/__tests__/strict-registration.test.ts +0 -115
- package/src/registry/tool/__tests__/tool-name-validation.test.ts +0 -88
- package/src/registry/tool/execute.test.ts +0 -648
- package/src/registry/toolset/catalog.test.ts +0 -282
- package/src/run/LimitChecker.test.ts +0 -32
- package/src/runtime/bidi/__tests__/session.test.ts +0 -232
- package/src/runtime/decision/parser.test.ts +0 -46
- package/src/runtime/query/__tests__/a-plan-that-succeeded-says-so.test.ts +0 -109
- package/src/runtime/query/__tests__/a-settled-plan-reaches-the-host.test.ts +0 -122
- package/src/runtime/query/__tests__/answer-review.test.ts +0 -172
- package/src/runtime/query/__tests__/capability-negotiation.test.ts +0 -301
- package/src/runtime/query/__tests__/checkpoint-store.test.ts +0 -285
- package/src/runtime/query/__tests__/checkpoint.test.ts +0 -170
- package/src/runtime/query/__tests__/citations.test.ts +0 -111
- package/src/runtime/query/__tests__/completion-does-not-erase-the-answer.test.ts +0 -163
- package/src/runtime/query/__tests__/completion-notification.test.ts +0 -648
- package/src/runtime/query/__tests__/content-budget.test.ts +0 -83
- package/src/runtime/query/__tests__/context-size-on-the-wire.test.ts +0 -122
- package/src/runtime/query/__tests__/context.test.ts +0 -127
- package/src/runtime/query/__tests__/deferred-tools.test.ts +0 -216
- package/src/runtime/query/__tests__/delegation-resume.test.ts +0 -159
- package/src/runtime/query/__tests__/document-attachments.test.ts +0 -125
- package/src/runtime/query/__tests__/durable-park-and-trace.test.ts +0 -245
- package/src/runtime/query/__tests__/durable-question-park.test.ts +0 -305
- package/src/runtime/query/__tests__/durable-run-state.test.ts +0 -194
- package/src/runtime/query/__tests__/effort-reaches-the-wire.test.ts +0 -135
- package/src/runtime/query/__tests__/executor-concurrency.test.ts +0 -122
- package/src/runtime/query/__tests__/executor-plugin-hooks.test.ts +0 -354
- package/src/runtime/query/__tests__/finish-reason-vs-tool-calls.test.ts +0 -206
- package/src/runtime/query/__tests__/grant-cannot-overrule-the-gate.test.ts +0 -115
- package/src/runtime/query/__tests__/guardrails-e2e.test.ts +0 -164
- package/src/runtime/query/__tests__/guardrails.test.ts +0 -236
- package/src/runtime/query/__tests__/hook-model-visibility.test.ts +0 -143
- package/src/runtime/query/__tests__/long-document-flow.test.ts +0 -187
- package/src/runtime/query/__tests__/memory-promotion.test.ts +0 -148
- package/src/runtime/query/__tests__/orphan-task-turn-end.test.ts +0 -101
- package/src/runtime/query/__tests__/overflow-relief.test.ts +0 -139
- package/src/runtime/query/__tests__/partial-batch-resume.test.ts +0 -264
- package/src/runtime/query/__tests__/per-step-skills.test.ts +0 -154
- package/src/runtime/query/__tests__/per-step-tool-choice.test.ts +0 -180
- package/src/runtime/query/__tests__/plugin-hooks.test.ts +0 -27
- package/src/runtime/query/__tests__/prepare-step-chain.test.ts +0 -127
- package/src/runtime/query/__tests__/prepare-step.test.ts +0 -233
- package/src/runtime/query/__tests__/probe-veto-is-error.test.ts +0 -145
- package/src/runtime/query/__tests__/prompt.test.ts +0 -91
- package/src/runtime/query/__tests__/provider-fault-pauses.test.ts +0 -104
- package/src/runtime/query/__tests__/reasoning-stream.test.ts +0 -177
- package/src/runtime/query/__tests__/recoverable-settle.test.ts +0 -145
- package/src/runtime/query/__tests__/resume-budget.test.ts +0 -158
- package/src/runtime/query/__tests__/resume-pending.test.ts +0 -273
- package/src/runtime/query/__tests__/resume-run.test.ts +0 -262
- package/src/runtime/query/__tests__/rich-content-budget-wiring.test.ts +0 -109
- package/src/runtime/query/__tests__/run-survives-its-own-park.proc-test.ts +0 -127
- package/src/runtime/query/__tests__/steering-reaches-the-model.test.ts +0 -117
- package/src/runtime/query/__tests__/steering.test.ts +0 -121
- package/src/runtime/query/__tests__/step-allow-list.test.ts +0 -205
- package/src/runtime/query/__tests__/stop-condition.test.ts +0 -265
- package/src/runtime/query/__tests__/stream-recovery.test.ts +0 -230
- package/src/runtime/query/__tests__/structured-output.test.ts +0 -268
- package/src/runtime/query/__tests__/structured-run-failure.test.ts +0 -144
- package/src/runtime/query/__tests__/terminal-tool.test.ts +0 -148
- package/src/runtime/query/__tests__/the-other-approval-surface-names-the-agent.test.ts +0 -95
- package/src/runtime/query/__tests__/the-plan-graph-reaches-a-host.test.ts +0 -79
- package/src/runtime/query/__tests__/tool-grants.test.ts +0 -102
- package/src/runtime/query/__tests__/tool-output-budget.test.ts +0 -0
- package/src/runtime/query/__tests__/tool-pause.test.ts +0 -209
- package/src/runtime/query/__tests__/tool-progress.test.ts +0 -154
- package/src/runtime/query/__tests__/tool-repair-retry.test.ts +0 -255
- package/src/runtime/query/__tests__/tool-result-wire.test.ts +0 -135
- package/src/runtime/query/__tests__/tool-timeout.test.ts +0 -268
- package/src/runtime/query/__tests__/trace-parenting.test.ts +0 -128
- package/src/runtime/query/__tests__/wiring-seams.test.ts +0 -288
- package/src/runtime/query/iteration/__tests__/cancel-settles-turn.test.ts +0 -177
- package/src/runtime/query/iteration/__tests__/settle-grace.test.ts +0 -265
- package/src/runtime/query/iteration/phases/__tests__/compaction-declined.test.ts +0 -124
- package/src/runtime/query/iteration/phases/advisory.test.ts +0 -415
- package/src/runtime/query/iteration/phases/compaction-model-routing.test.ts +0 -125
- package/src/runtime/query/iteration/phases/compaction-safe-cut.test.ts +0 -188
- package/src/runtime/query/iteration/phases/context-measurement.test.ts +0 -196
- package/src/runtime/query/iteration/phases/context-reducer-dispatch.test.ts +0 -238
- package/src/runtime/query/iteration/phases/hitl-abort-race.test.ts +0 -86
- package/src/runtime/query/iteration/phases/hitl-answer-question.test.ts +0 -141
- package/src/runtime/query/iteration/phases/overflow-escalation.test.ts +0 -167
- package/src/runtime/query/iteration/phases/retained-messages.test.ts +0 -226
- package/src/runtime/query/iteration/phases/tool-review-denials.test.ts +0 -270
- package/src/runtime/query/iteration/phases/working-memory-compaction.test.ts +0 -227
- package/src/runtime/query/replay/__tests__/mutate.test.ts +0 -134
- package/src/runtime/query/replay/__tests__/prepare.test.ts +0 -207
- package/src/sandbox/__tests__/exec-cancellation.test.ts +0 -72
- package/src/sandbox/__tests__/isolation.test.ts +0 -164
- package/src/sandbox/__tests__/output-truncation.test.ts +0 -106
- package/src/sandbox/__tests__/resource-limits.test.ts +0 -106
- package/src/session/__tests__/integration/_fixtures.ts +0 -310
- package/src/session/__tests__/integration/a-successful-delegation-disposes-its-workspace.test.ts +0 -270
- package/src/session/__tests__/integration/archive-gate.test.ts +0 -288
- package/src/session/__tests__/integration/capacity-caps.test.ts +0 -171
- package/src/session/__tests__/integration/e2e-spawn.test.ts +0 -296
- package/src/session/__tests__/integration/event-stream-ordering.test.ts +0 -410
- package/src/session/__tests__/integration/handoff-broadcast-e2e.test.ts +0 -271
- package/src/session/__tests__/integration/handoff-illegal-transition.test.ts +0 -214
- package/src/session/__tests__/integration/handoff-single-e2e.test.ts +0 -260
- package/src/session/__tests__/integration/hierarchy-lifecycle.test.ts +0 -240
- package/src/session/__tests__/integration/migration-filesystem.test.ts +0 -209
- package/src/session/__tests__/integration/migration-id-prefix.test.ts +0 -101
- package/src/session/__tests__/integration/prev-artifact-dag.test.ts +0 -328
- package/src/session/__tests__/integration/retention-archive.test.ts +0 -233
- package/src/session/__tests__/integration/spawn-rollback.test.ts +0 -313
- package/src/session/__tests__/integration/summary-materialization-e2e.test.ts +0 -239
- package/src/session/__tests__/integration/tenant-isolation.test.ts +0 -292
- package/src/session/handoff/__tests__/broadcast.test.ts +0 -378
- package/src/session/handoff/__tests__/capacity.test.ts +0 -129
- package/src/session/handoff/__tests__/single.test.ts +0 -333
- package/src/session/intervention/__tests__/prev-artifact.test.ts +0 -237
- package/src/session/migration/__tests__/a-migrated-project-id-is-an-id.test.ts +0 -92
- package/src/session/migration/__tests__/filesystem.test.ts +0 -270
- package/src/session/migration/__tests__/id-prefix.test.ts +0 -101
- package/src/session/migration/__tests__/marker.test.ts +0 -84
- package/src/session/retention/__tests__/archive.test.ts +0 -318
- package/src/session/retention/__tests__/disk-backend.test.ts +0 -180
- package/src/session/status/__tests__/derive.test.ts +0 -101
- package/src/session/summary/__tests__/materialize.test.ts +0 -340
- package/src/session/workspace/__tests__/git-worktree.test.ts +0 -262
- package/src/session/workspace/__tests__/path-builder.test.ts +0 -51
- package/src/session/workspace/__tests__/shared-run.test.ts +0 -199
- package/src/skills/__tests__/frontmatter.test.ts +0 -135
- package/src/skills/loader.test.ts +0 -89
- package/src/store/__tests__/checkpoint-integrity.test.ts +0 -134
- package/src/store/__tests__/checkpoint-versioning.test.ts +0 -194
- package/src/store/__tests__/schema-adoption.test.ts +0 -118
- package/src/store/__tests__/schema.test.ts +0 -119
- package/src/store/session/__tests__/a-session-has-one-writer.test.ts +0 -116
- package/src/store/session/__tests__/a-workspace-can-be-configured.test.ts +0 -210
- package/src/store/session/__tests__/disk.test.ts +0 -397
- package/src/store/session/__tests__/memory.test.ts +0 -402
- package/src/store/task/__tests__/an-edge-that-already-exists-is-not-news.test.ts +0 -115
- package/src/store/task/__tests__/disk-concurrency.test.ts +0 -118
- package/src/store/task/__tests__/lookup-across-runs.test.ts +0 -77
- package/src/streaming/coalesce.test.ts +0 -132
- package/src/telemetry/__tests__/latency-instruments.test.ts +0 -120
- package/src/telemetry/__tests__/metrics.test.ts +0 -160
- package/src/telemetry/__tests__/model-call-span.test.ts +0 -212
- package/src/telemetry/__tests__/span-closure.test.ts +0 -160
- package/src/telemetry/__tests__/span-hierarchy.test.ts +0 -94
- package/src/test-setup.ts +0 -24
- package/src/tools/__tests__/file-tool-containment.test.ts +0 -190
- package/src/tools/__tests__/path-containment.test.ts +0 -167
- package/src/tools/__tests__/posix-path.test.ts +0 -83
- package/src/tools/__tests__/sandboxed-search.test.ts +0 -206
- package/src/tools/__tests__/untrusted-envelope.test.ts +0 -105
- package/src/tools/builtins/__tests__/bash.proc-test.ts +0 -142
- package/src/tools/builtins/__tests__/bash.test.ts +0 -79
- package/src/tools/builtins/__tests__/computer-use.test.ts +0 -201
- package/src/tools/builtins/__tests__/edit-commits-atomically.test.ts +0 -103
- package/src/tools/builtins/__tests__/edit-insert-reachable.test.ts +0 -172
- package/src/tools/builtins/__tests__/edit.test.ts +0 -388
- package/src/tools/builtins/__tests__/payload-budget.test.ts +0 -92
- package/src/tools/builtins/__tests__/read-file.test.ts +0 -71
- package/src/tools/builtins/__tests__/stale-file-refusal.test.ts +0 -258
- package/src/tools/builtins/__tests__/structuredOutput.test.ts +0 -275
- package/src/tools/builtins/__tests__/verify-outputs.test.ts +0 -71
- package/src/tools/builtins/__tests__/write-file.test.ts +0 -177
- package/src/tools/coordinator/__tests__/a-failed-worker-is-not-an-answer.test.ts +0 -133
- package/src/tools/coordinator/__tests__/a-listing-is-not-a-back-door.test.ts +0 -171
- package/src/tools/coordinator/__tests__/a-plan-step-reports-its-own-outcome.test.ts +0 -215
- package/src/tools/coordinator/__tests__/agent.test.ts +0 -177
- package/src/tools/coordinator/__tests__/allow-delegation.test.ts +0 -120
- package/src/tools/coordinator/__tests__/an-approver-is-never-shown-an-impossible-step.test.ts +0 -153
- package/src/tools/coordinator/__tests__/approve-plan.test.ts +0 -160
- package/src/tools/coordinator/__tests__/ask-user-question.test.ts +0 -496
- package/src/tools/coordinator/__tests__/completion-delivery.test.ts +0 -501
- package/src/tools/coordinator/__tests__/empty-roster.test.ts +0 -118
- package/src/tools/coordinator/__tests__/plan-dependencies.test.ts +0 -186
- package/src/tools/coordinator/__tests__/task-list.test.ts +0 -303
- package/src/tools/coordinator/__tests__/the-plan-a-human-approves.test.ts +0 -121
- package/src/tools/coordinator/__tests__/wait-with-idle-bound.test.ts +0 -247
- package/src/types/common/__tests__/numeric-correctness.test.ts +0 -123
- package/src/types/common/usage-merge.test.ts +0 -53
- package/src/types/errors/__tests__/catalog.test.ts +0 -130
- package/src/types/errors/__tests__/errors.test.ts +0 -118
- package/src/types/invocation/__tests__/state.test.ts +0 -218
- package/src/types/provider/__tests__/cause-chain.test.ts +0 -132
- package/src/types/provider/__tests__/declared-retryable.test.ts +0 -85
- package/src/types/provider/__tests__/overflow-classification.test.ts +0 -113
- package/src/types/run/__tests__/step.test.ts +0 -123
- package/src/utils/__tests__/abort-reason.test.ts +0 -56
- package/src/utils/__tests__/atomic-write.test.ts +0 -108
- package/src/utils/__tests__/shell-compress.test.ts +0 -49
- package/src/vault/instrumentation.test.ts +0 -98
- package/src/verification/__tests__/argument-pattern.test.ts +0 -158
- package/src/verification/__tests__/rule-order-and-reason.test.ts +0 -149
- package/src/verification/presets.test.ts +0 -112
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"end-to-end.test.js","sourceRoot":"","sources":["../../../src/eval/__tests__/end-to-end.test.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,EAAE,EAAE,EAAE,EAAE,EAAE,MAAM,QAAQ,CAAA;AAEjD,OAAO,EAAE,eAAe,EAAE,MAAM,wBAAwB,CAAA;AACxD,OAAO,EAAE,YAAY,EAAE,MAAM,iCAAiC,CAAA;AAC9D,OAAO,EAAE,qBAAqB,EAAE,MAAM,wCAAwC,CAAA;AAC9E,OAAO,EAAE,aAAa,EAAE,MAAM,gCAAgC,CAAA;AAK9D,OAAO,EAAE,WAAW,EAAE,MAAM,yBAAyB,CAAA;AAGrD,OAAO,EAAE,aAAa,EAAE,MAAM,kBAAkB,CAAA;AAChD,OAAO,EAAE,cAAc,EAAE,MAAM,gBAAgB,CAAA;AAC/C,OAAO,EAAE,gBAAgB,EAAE,gBAAgB,EAAE,MAAM,eAAe,CAAA;AAGlE;;;;;;;;;GASG;AAEH,MAAM,MAAM,GAAG,UAAmB,CAAA;AAElC,SAAS,UAAU;IAClB,MAAM,IAAI,GAAG,EAAE,IAAI,EAAE,EAAE,CAAC,EAAE,EAAE,EAAE,IAAI,EAAE,EAAE,CAAC,EAAE,EAAE,EAAE,KAAK,EAAE,EAAE,CAAC,EAAE,EAAE,EAAE,KAAK,EAAE,EAAE,CAAC,EAAE,EAAE,EAAE,CAAA;IAC7E,OAAO,EAAE,GAAG,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC,EAAE,CAAC,GAAG,EAAE,CAAC,CAAC,EAAE,GAAG,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,EAAuB,CAAA;AAC3F,CAAC;AAED,0EAA0E;AAC1E,KAAK,UAAU,UAAU,CAAC,KAAgB;IACzC,MAAM,QAAQ,GAAc,EAAE,CAAA;IAC9B,IAAI,SAAS,GAAG,CAAC,CAAA;IACjB,IAAI,UAA8B,CAAA;IAClC,MAAM,GAAG,GAAG,UAAU,EAAE,CAAA;IAExB,MAAM,KAAK,GAAG;QACb,GAAG,EAAE,EAAE,CAAC,EAAE,CAAC,CAAC,IAAY,EAAE,EAAE,CAAC,CAAC;YAC7B,IAAI;YACJ,iBAAiB,EAAE,GAAG,EAAE,CAAC,IAAI;YAC7B,UAAU,EAAE,GAAG,EAAE,CAAC,IAAI;YACtB,aAAa,EAAE,GAAG,EAAE,CAAC,KAAK;SAC1B,CAAC,CAAC;QACH,OAAO,EAAE,EAAE,CAAC,EAAE,CAAC,KAAK,EAAE,IAAY,EAAE,EAAE,CAAC,CAAC,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,EAAE,GAAG,IAAI,KAAK,EAAE,CAAC,CAAC;QACjF,GAAG,EAAE,EAAE,CAAC,EAAE,CAAC,GAAG,EAAE,CAAC,IAAI,CAAC;QACtB,SAAS,EAAE,EAAE,CAAC,EAAE,CAAC,GAAG,EAAE,CAAC,EAAE,CAAC;QAC1B,eAAe,EAAE,EAAE,CAAC,EAAE,CAAC,GAAG,EAAE,CAAC,QAAQ,CAAC;QACtC,UAAU,EAAE,EAAE,CAAC,EAAE,CAAC,GAAG,EAAE,CAAC,EAAE,CAAC;QAC3B,QAAQ,EAAE,EAAE,CAAC,EAAE,EAAE;QACjB,UAAU,EAAE,EAAE,CAAC,EAAE,EAAE;KACgB,CAAA;IAEpC,MAAM,aAAa,GAAG,IAAI,aAAa,CAAC,MAAM,EAAE;QAC/C,OAAO,EAAE,KAAK;QACd,cAAc,EAAE,KAAK;QACrB,aAAa,EAAE,KAAK;KACpB,CAAC,CAAA;IAEF,MAAM,MAAM,GAAG;QACd,EAAE,EAAE,MAAM;QACV,QAAQ;QACR,UAAU,EAAE;YACX,YAAY,EAAE,CAAC;YACf,gBAAgB,EAAE,CAAC;YACnB,WAAW,EAAE,CAAC;YACd,YAAY,EAAE,CAAC;YACf,gBAAgB,EAAE,CAAC;SACnB;QACD,QAAQ,EAAE,EAAE,cAAc,EAAE,CAAC,EAAE,eAAe,EAAE,CAAC,EAAE,SAAS,EAAE,CAAC,EAAE,aAAa,EAAE,CAAC,EAAE;QACnF,IAAI,gBAAgB;YACnB,OAAO,SAAS,CAAA;QACjB,CAAC;QACD,kBAAkB,EAAE,GAAG,EAAE,CAAC,EAAE,SAAS;QACrC,WAAW,EAAE,CAAC,CAAU,EAAE,EAAE;YAC3B,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QACjB,CAAC;QACD,eAAe,EAAE,EAAE,CAAC,EAAE,EAAE;QACxB,eAAe,EAAE,EAAE,CAAC,EAAE,EAAE;QACxB,qBAAqB,EAAE,EAAE,CAAC,EAAE,EAAE;QAC9B,gBAAgB,EAAE,SAAS;QAC3B,aAAa,EAAE,CAAC,CAAS,EAAE,EAAE;YAC5B,UAAU,GAAG,CAAC,CAAA;QACf,CAAC;QACD,mBAAmB,EAAE,EAAE,CAAC,EAAE,EAAE;QAC5B,aAAa,EAAE,EAAE,CAAC,EAAE,EAAE;KACtB,CAAA;IAED,MAAM,YAAY,GAAG,IAAI,qBAAqB,CAAC;QAC9C,QAAQ,EAAE,IAAI,eAAe,CAAC,EAAE,KAAK,EAAE,KAAc,EAAE,CAAC;QACxD,SAAS,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,aAAa,EAAE,EAAE,EAAE;QAC/C,KAAK;QACL,MAAM;QACN,YAAY,EAAE,IAAI,YAAY,CAC7B;YACC,KAAK;YACL,KAAK,EAAE,MAAM;YACb,gBAAgB,EAAE,MAAM;YACxB,cAAc,EAAE,MAAM;YACtB,GAAG,EAAE,EAAE;YACP,WAAW,EAAE,IAAI,eAAe,EAAE,CAAC,MAAM;SACzC,EACD,aAAa,EACb,KAAK,IAAI,EAAE,GAAE,CAAC,EACd,GAAG,CACH;QACD,aAAa;QACb,eAAe,EAAE,IAAI,eAAe,EAAE;QACtC,GAAG;QACH,SAAS,EAAE,KAAK,IAAI,EAAE,GAAE,CAAC;QACzB,YAAY,EAAE,QAAQ,CAAC,MAA0B,CAAC;QAClD,aAAa,EAAE,EAAE,MAAM,EAAE,KAAK,IAAI,EAAE,CAAC,CAAC,EAAE,EAAE,EAAE,MAAM,EAAE,CAAC,EAAE;QACvD,WAAW,EAAE,EAAE,MAAM,EAAE,SAAS,EAAE;QAClC,aAAa,EAAE,KAAK,IAAI,EAAE,CAAC,CAAC,EAAE,MAAM,EAAE,eAAe,EAAE,CAAC;QACxD,QAAQ,EAAE,WAAW,CAAC,QAAQ,CAAC;QAC/B,KAAK,EAAE;YACN,eAAe,EAAE,GAAG,EAAE,CAAC,CAAC;gBACvB,UAAU,EAAE,SAAS,IAAI,EAAE;gBAC3B,aAAa,EAAE,KAAK;gBACpB,WAAW,EAAE,KAAK;gBAClB,UAAU,EAAE,gBAAgB;aAC5B,CAAC;SACF;KACQ,CAAC,CAAA;IAEX,MAAM,GAAG,GAAG,YAAY,CAAC,OAAO,EAAE,CAAA;IAClC,IAAI,IAAI,GAAG,MAAM,GAAG,CAAC,IAAI,EAAE,CAAA;IAC3B,OAAO,CAAC,IAAI,CAAC,IAAI;QAAE,IAAI,GAAG,MAAM,GAAG,CAAC,IAAI,EAAE,CAAA;IAE1C,OAAO;QACN,EAAE,EAAE,MAAM;QACV,MAAM,EAAE,WAAW;QACnB,QAAQ;QACR,UAAU,EAAE,MAAM,CAAC,UAAU;QAC7B,QAAQ,EAAE,MAAM,CAAC,QAAQ;QACzB,gBAAgB,EAAE,SAAS;QAC3B,SAAS,EAAE,IAAI,CAAC,GAAG,EAAE,GAAG,EAAE;QAC1B,OAAO,EAAE,IAAI,CAAC,GAAG,EAAE;QACnB,KAAK,EAAE,YAAY,CAAC,QAAQ,EAAE;QAC9B,GAAG,CAAC,UAAU,CAAC,CAAC,CAAC,EAAE,UAAU,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;QACrC,MAAM,EAAE,MAAM;KACI,CAAA;AACpB,CAAC;AAED,0DAA0D;AAC1D,MAAM,MAAM,GAAe;IAC1B;QACC,IAAI,EAAE,qCAAqC;QAC3C,KAAK,EAAE,eAAe;QACtB,aAAa,EAAE,CAAC,MAAM,EAAE,MAAM,EAAE,QAAQ,CAAC;KACzC;CACD,CAAA;AAED,MAAM,OAAO,GAAG;IACf,EAAE,SAAS,EAAE,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,CAAC,EAAE;IACjC,EAAE,SAAS,EAAE,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,CAAC,EAAE;IACjC,EAAE,SAAS,EAAE,CAAC,EAAE,IAAI,EAAE,QAAQ,EAAE,CAAC,EAAE;CACnC,CAAA;AAED,QAAQ,CAAC,+BAA+B,EAAE,GAAG,EAAE;IAC9C,EAAE,CAAC,wDAAwD,EAAE,KAAK,IAAI,EAAE;QACvE,MAAM,GAAG,GAAG,MAAM,UAAU,CAAC,OAAO,CAAC,CAAA;QACrC,MAAM,SAAS,GAAG,cAAc,CAAC,GAAG,CAAC,CAAA;QAErC,MAAM,CAAC,SAAS,CAAC,SAAS,CAAC,CAAC,OAAO,CAAC,CAAC,MAAM,EAAE,MAAM,EAAE,QAAQ,CAAC,CAAC,CAAA;QAC/D,MAAM,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;QACvC,MAAM,CAAC,SAAS,CAAC,UAAU,CAAC,CAAC,IAAI,CAAC,gBAAgB,CAAC,CAAA;IACpD,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,gCAAgC,EAAE,KAAK,IAAI,EAAE;QAC/C,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,IAAI,EAAE,cAAc;YACpB,KAAK,EAAE,MAAM;YACb,OAAO,EAAE,CAAC,gBAAgB,EAAE,EAAE,gBAAgB,CAAC,CAAC,gBAAgB,CAAC,CAAC,CAAC;YACnE,GAAG,EAAE,KAAK,IAAI,EAAE,CAAC,cAAc,CAAC,MAAM,UAAU,CAAC,OAAO,CAAC,CAAC;SAC1D,CAAC,CAAA;QAEF,MAAM,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QAC3B,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IAC9B,CAAC,CAAC,CAAA;AACH,CAAC,CAAC,CAAA;AAEF,QAAQ,CAAC,2CAA2C,EAAE,GAAG,EAAE;IAC1D,EAAE,CAAC,6CAA6C,EAAE,KAAK,IAAI,EAAE;QAC5D,uEAAuE;QACvE,oEAAoE;QACpE,mCAAmC;QACnC,MAAM,SAAS,GAAG,CAAC,EAAE,SAAS,EAAE,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,CAAC,EAAE,EAAE,EAAE,SAAS,EAAE,CAAC,EAAE,IAAI,EAAE,QAAQ,EAAE,CAAC,EAAE,CAAC,CAAA;QAE1F,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,IAAI,EAAE,cAAc;YACpB,KAAK,EAAE,MAAM;YACb,OAAO,EAAE,CAAC,gBAAgB,EAAE,CAAC;YAC7B,GAAG,EAAE,KAAK,IAAI,EAAE,CAAC,cAAc,CAAC,MAAM,UAAU,CAAC,SAAS,CAAC,CAAC;SAC5D,CAAC,CAAA;QAEF,MAAM,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;QACnC,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QAC7B,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,UAAU,EAAE,MAAM,CAAC,CAAC,SAAS,CAAC,MAAM,CAAC,CAAA;IACrE,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,iDAAiD,EAAE,KAAK,IAAI,EAAE;QAChE,uEAAuE;QACvE,sEAAsE;QACtE,OAAO;QACP,MAAM,QAAQ,GAAG;YAChB,EAAE,SAAS,EAAE,CAAC,EAAE,IAAI,EAAE,IAAI,EAAE,CAAC,EAAE;YAC/B,EAAE,SAAS,EAAE,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,CAAC,EAAE;YACjC,EAAE,SAAS,EAAE,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,CAAC,EAAE;YACjC,EAAE,SAAS,EAAE,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,CAAC,EAAE;YACjC,EAAE,SAAS,EAAE,CAAC,EAAE,IAAI,EAAE,QAAQ,EAAE,CAAC,EAAE;SACnC,CAAA;QAED,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,IAAI,EAAE,cAAc;YACpB,KAAK,EAAE,MAAM;YACb,OAAO,EAAE,CAAC,gBAAgB,EAAE,CAAC;YAC7B,GAAG,EAAE,KAAK,IAAI,EAAE,CAAC,cAAc,CAAC,MAAM,UAAU,CAAC,QAAQ,CAAC,CAAC;SAC3D,CAAC,CAAA;QAEF,MAAM,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;QACnC,sEAAsE;QACtE,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,UAAU,EAAE,OAAO,EAAE,MAAM,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QACnE,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,UAAU,EAAE,OAAO,EAAE,SAAS,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;IAC/E,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,mEAAmE,EAAE,KAAK,IAAI,EAAE;QAClF,MAAM,KAAK,GAAG,KAAK,EAAE,KAAgB,EAAE,EAAE;YACxC,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;gBAClC,IAAI,EAAE,GAAG;gBACT,KAAK,EAAE,MAAM;gBACb,OAAO,EAAE,CAAC,gBAAgB,EAAE,CAAC;gBAC7B,GAAG,EAAE,KAAK,IAAI,EAAE,CAAC,cAAc,CAAC,MAAM,UAAU,CAAC,KAAK,CAAC,CAAC;aACxD,CAAC,CAAA;YACF,OAAO,MAAM,CAAC,IAAI,CAAA;QACnB,CAAC,CAAA;QAED,MAAM,OAAO,GAAG,MAAM,KAAK,CAAC;YAC3B,EAAE,SAAS,EAAE,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,CAAC,EAAE;YACjC,EAAE,SAAS,EAAE,CAAC,EAAE,IAAI,EAAE,QAAQ,EAAE,CAAC,EAAE;SACnC,CAAC,CAAA;QACF,MAAM,QAAQ,GAAG,MAAM,KAAK,CAAC;YAC5B,EAAE,SAAS,EAAE,CAAC,EAAE,IAAI,EAAE,IAAI,EAAE,CAAC,EAAE;YAC/B,EAAE,SAAS,EAAE,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,CAAC,EAAE;YACjC,EAAE,SAAS,EAAE,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,CAAC,EAAE;YACjC,EAAE,SAAS,EAAE,CAAC,EAAE,IAAI,EAAE,QAAQ,EAAE,CAAC,EAAE;SACnC,CAAC,CAAA;QAEF,MAAM,CAAC,OAAO,CAAC,CAAC,GAAG,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAA;QAClC,+DAA+D;QAC/D,MAAM,CAAC,OAAO,CAAC,CAAC,YAAY,CAAC,QAAQ,CAAC,CAAA;IACvC,CAAC,CAAC,CAAA;AACH,CAAC,CAAC,CAAA"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"harness-honesty.test.d.ts","sourceRoot":"","sources":["../../../src/eval/__tests__/harness-honesty.test.ts"],"names":[],"mappings":""}
|
|
@@ -1,85 +0,0 @@
|
|
|
1
|
-
import { describe, expect, it } from 'vitest';
|
|
2
|
-
import { runExperiment } from '../experiment.js';
|
|
3
|
-
import { containsScorer, stepBudgetScorer, trajectoryScorer } from '../scorers.js';
|
|
4
|
-
/**
|
|
5
|
-
* An eval harness that reports green on a broken suite is worse than no
|
|
6
|
-
* harness: it converts "we do not know" into "we checked". Both defects
|
|
7
|
-
* here did exactly that.
|
|
8
|
-
*/
|
|
9
|
-
const emptyRun = () => ({
|
|
10
|
-
output: 'ok',
|
|
11
|
-
steps: [],
|
|
12
|
-
toolCalls: [],
|
|
13
|
-
totalTokens: 0,
|
|
14
|
-
totalCostUsd: 0,
|
|
15
|
-
durationMs: 0,
|
|
16
|
-
});
|
|
17
|
-
describe('a case whose run THREW cannot score above zero', () => {
|
|
18
|
-
it('scores 0 instead of a perfect step budget', async () => {
|
|
19
|
-
// `executeCase` catches the throw and returns an empty run, and an
|
|
20
|
-
// empty run walks into every scorer's happy path: 0 steps is within
|
|
21
|
-
// any allowance, and "no tools expected, none called" is a match. The
|
|
22
|
-
// suite reported 1.0 for a case that never ran.
|
|
23
|
-
const report = await runExperiment({
|
|
24
|
-
name: 'crash',
|
|
25
|
-
cases: [{ name: 'boom', input: 'x' }],
|
|
26
|
-
scorers: [stepBudgetScorer(5), trajectoryScorer()],
|
|
27
|
-
run: () => {
|
|
28
|
-
throw new Error('provider exploded');
|
|
29
|
-
},
|
|
30
|
-
});
|
|
31
|
-
expect(report.cases[0]?.scores['step-budget']?.score).toBe(0);
|
|
32
|
-
expect(report.cases[0]?.scores.trajectory?.score).toBe(0);
|
|
33
|
-
expect(report.mean).toBe(0);
|
|
34
|
-
});
|
|
35
|
-
it('says why, so the green-to-red change is diagnosable', async () => {
|
|
36
|
-
const report = await runExperiment({
|
|
37
|
-
name: 'crash',
|
|
38
|
-
cases: [{ name: 'boom', input: 'x' }],
|
|
39
|
-
scorers: [stepBudgetScorer(5)],
|
|
40
|
-
run: () => {
|
|
41
|
-
throw new Error('provider exploded');
|
|
42
|
-
},
|
|
43
|
-
});
|
|
44
|
-
expect(report.cases[0]?.scores['step-budget']?.reason).toContain('provider exploded');
|
|
45
|
-
});
|
|
46
|
-
it('still scores a healthy run normally', async () => {
|
|
47
|
-
const report = await runExperiment({
|
|
48
|
-
name: 'fine',
|
|
49
|
-
cases: [{ name: 'ok', input: 'x' }],
|
|
50
|
-
scorers: [stepBudgetScorer(5)],
|
|
51
|
-
run: () => Promise.resolve(emptyRun()),
|
|
52
|
-
});
|
|
53
|
-
expect(report.cases[0]?.scores['step-budget']?.score).toBe(1);
|
|
54
|
-
});
|
|
55
|
-
});
|
|
56
|
-
describe('two scorers cannot silently collapse into one', () => {
|
|
57
|
-
it('refuses a duplicate scorer name rather than overwriting', async () => {
|
|
58
|
-
// Scores are keyed by name, so two `containsScorer(...)` instances —
|
|
59
|
-
// both called 'contains' — meant the second overwrote the first and
|
|
60
|
-
// the case mean was computed over the wrong denominator. With 'a'
|
|
61
|
-
// scoring 0 and 'b' scoring 1 the suite reported 1.0 where the honest
|
|
62
|
-
// answer is 0.5.
|
|
63
|
-
await expect(runExperiment({
|
|
64
|
-
name: 'dupe',
|
|
65
|
-
cases: [{ name: 'c', input: 'x' }],
|
|
66
|
-
scorers: [containsScorer('a'), containsScorer('b')],
|
|
67
|
-
run: () => Promise.resolve({ ...emptyRun(), output: 'b' }),
|
|
68
|
-
})).rejects.toThrow(/Duplicate scorer name "contains"/);
|
|
69
|
-
});
|
|
70
|
-
it('accepts distinct names', async () => {
|
|
71
|
-
const report = await runExperiment({
|
|
72
|
-
name: 'ok',
|
|
73
|
-
cases: [{ name: 'c', input: 'x' }],
|
|
74
|
-
scorers: [
|
|
75
|
-
{ ...containsScorer('a'), name: 'contains-a' },
|
|
76
|
-
{ ...containsScorer('b'), name: 'contains-b' },
|
|
77
|
-
],
|
|
78
|
-
run: () => Promise.resolve({ ...emptyRun(), output: 'b' }),
|
|
79
|
-
});
|
|
80
|
-
expect(report.cases[0]?.scores['contains-a']?.score).toBe(0);
|
|
81
|
-
expect(report.cases[0]?.scores['contains-b']?.score).toBe(1);
|
|
82
|
-
expect(report.cases[0]?.mean).toBe(0.5);
|
|
83
|
-
});
|
|
84
|
-
});
|
|
85
|
-
//# sourceMappingURL=harness-honesty.test.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"harness-honesty.test.js","sourceRoot":"","sources":["../../../src/eval/__tests__/harness-honesty.test.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,EAAE,EAAE,EAAE,MAAM,QAAQ,CAAA;AAE7C,OAAO,EAAE,aAAa,EAAE,MAAM,kBAAkB,CAAA;AAChD,OAAO,EAAE,cAAc,EAAE,gBAAgB,EAAE,gBAAgB,EAAE,MAAM,eAAe,CAAA;AAGlF;;;;GAIG;AAEH,MAAM,QAAQ,GAAG,GAAY,EAAE,CAAC,CAAC;IAChC,MAAM,EAAE,IAAI;IACZ,KAAK,EAAE,EAAE;IACT,SAAS,EAAE,EAAE;IACb,WAAW,EAAE,CAAC;IACd,YAAY,EAAE,CAAC;IACf,UAAU,EAAE,CAAC;CACb,CAAC,CAAA;AAEF,QAAQ,CAAC,gDAAgD,EAAE,GAAG,EAAE;IAC/D,EAAE,CAAC,2CAA2C,EAAE,KAAK,IAAI,EAAE;QAC1D,mEAAmE;QACnE,oEAAoE;QACpE,sEAAsE;QACtE,gDAAgD;QAChD,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,IAAI,EAAE,OAAO;YACb,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,GAAG,EAAE,CAAC;YACrC,OAAO,EAAE,CAAC,gBAAgB,CAAC,CAAC,CAAC,EAAE,gBAAgB,EAAE,CAAC;YAClD,GAAG,EAAE,GAAG,EAAE;gBACT,MAAM,IAAI,KAAK,CAAC,mBAAmB,CAAC,CAAA;YACrC,CAAC;SACD,CAAC,CAAA;QAEF,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,aAAa,CAAC,EAAE,KAAK,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QAC7D,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,UAAU,EAAE,KAAK,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QACzD,MAAM,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IAC5B,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,qDAAqD,EAAE,KAAK,IAAI,EAAE;QACpE,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,IAAI,EAAE,OAAO;YACb,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,GAAG,EAAE,CAAC;YACrC,OAAO,EAAE,CAAC,gBAAgB,CAAC,CAAC,CAAC,CAAC;YAC9B,GAAG,EAAE,GAAG,EAAE;gBACT,MAAM,IAAI,KAAK,CAAC,mBAAmB,CAAC,CAAA;YACrC,CAAC;SACD,CAAC,CAAA;QAEF,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,aAAa,CAAC,EAAE,MAAM,CAAC,CAAC,SAAS,CAAC,mBAAmB,CAAC,CAAA;IACtF,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,qCAAqC,EAAE,KAAK,IAAI,EAAE;QACpD,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,IAAI,EAAE,MAAM;YACZ,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,IAAI,EAAE,KAAK,EAAE,GAAG,EAAE,CAAC;YACnC,OAAO,EAAE,CAAC,gBAAgB,CAAC,CAAC,CAAC,CAAC;YAC9B,GAAG,EAAE,GAAG,EAAE,CAAC,OAAO,CAAC,OAAO,CAAC,QAAQ,EAAE,CAAC;SACtC,CAAC,CAAA;QAEF,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,aAAa,CAAC,EAAE,KAAK,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IAC9D,CAAC,CAAC,CAAA;AACH,CAAC,CAAC,CAAA;AAEF,QAAQ,CAAC,+CAA+C,EAAE,GAAG,EAAE;IAC9D,EAAE,CAAC,yDAAyD,EAAE,KAAK,IAAI,EAAE;QACxE,qEAAqE;QACrE,oEAAoE;QACpE,kEAAkE;QAClE,sEAAsE;QACtE,iBAAiB;QACjB,MAAM,MAAM,CACX,aAAa,CAAC;YACb,IAAI,EAAE,MAAM;YACZ,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,GAAG,EAAE,KAAK,EAAE,GAAG,EAAE,CAAC;YAClC,OAAO,EAAE,CAAC,cAAc,CAAC,GAAG,CAAC,EAAE,cAAc,CAAC,GAAG,CAAC,CAAC;YACnD,GAAG,EAAE,GAAG,EAAE,CAAC,OAAO,CAAC,OAAO,CAAC,EAAE,GAAG,QAAQ,EAAE,EAAE,MAAM,EAAE,GAAG,EAAE,CAAC;SAC1D,CAAC,CACF,CAAC,OAAO,CAAC,OAAO,CAAC,kCAAkC,CAAC,CAAA;IACtD,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,wBAAwB,EAAE,KAAK,IAAI,EAAE;QACvC,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,IAAI,EAAE,IAAI;YACV,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,GAAG,EAAE,KAAK,EAAE,GAAG,EAAE,CAAC;YAClC,OAAO,EAAE;gBACR,EAAE,GAAG,cAAc,CAAC,GAAG,CAAC,EAAE,IAAI,EAAE,YAAY,EAAE;gBAC9C,EAAE,GAAG,cAAc,CAAC,GAAG,CAAC,EAAE,IAAI,EAAE,YAAY,EAAE;aAC9C;YACD,GAAG,EAAE,GAAG,EAAE,CAAC,OAAO,CAAC,OAAO,CAAC,EAAE,GAAG,QAAQ,EAAE,EAAE,MAAM,EAAE,GAAG,EAAE,CAAC;SAC1D,CAAC,CAAA;QAEF,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,YAAY,CAAC,EAAE,KAAK,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QAC5D,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,YAAY,CAAC,EAAE,KAAK,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QAC5D,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;IACxC,CAAC,CAAC,CAAA;AACH,CAAC,CAAC,CAAA"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"harness.test.d.ts","sourceRoot":"","sources":["../../../src/eval/__tests__/harness.test.ts"],"names":[],"mappings":""}
|
|
@@ -1,207 +0,0 @@
|
|
|
1
|
-
import { describe, expect, it } from 'vitest';
|
|
2
|
-
import { formatReport, runExperiment } from '../experiment.js';
|
|
3
|
-
import { completionScorer, containsScorer, customScorer, stepBudgetScorer, trajectoryScorer, } from '../scorers.js';
|
|
4
|
-
/**
|
|
5
|
-
* There was no evaluation harness of any kind — no dataset, no scorer, no
|
|
6
|
-
* judge, no trajectory assertion. So the constants that govern namzu's
|
|
7
|
-
* most load-bearing behavior (`search_tools` top-k, the compaction
|
|
8
|
-
* threshold, six state-list caps, every builtin tool description) were
|
|
9
|
-
* tunable but not measurable: change one and the only way to learn the
|
|
10
|
-
* agent now takes four tool calls where it took one was for a user to
|
|
11
|
-
* hit it.
|
|
12
|
-
*/
|
|
13
|
-
function run(overrides = {}) {
|
|
14
|
-
return {
|
|
15
|
-
output: 'done',
|
|
16
|
-
steps: [],
|
|
17
|
-
toolCalls: [],
|
|
18
|
-
stopReason: 'end_turn',
|
|
19
|
-
totalTokens: 0,
|
|
20
|
-
totalCostUsd: 0,
|
|
21
|
-
durationMs: 0,
|
|
22
|
-
...overrides,
|
|
23
|
-
};
|
|
24
|
-
}
|
|
25
|
-
const CASE = { name: 'c', input: null };
|
|
26
|
-
describe('trajectoryScorer', () => {
|
|
27
|
-
// `Scorer.score` may be async (a model-graded judge is just an async
|
|
28
|
-
// predicate), so every call site awaits even when the built-in is sync.
|
|
29
|
-
const score = async (expectedTools, toolCalls) => await trajectoryScorer().score(run({ toolCalls }), { ...CASE, expectedTools });
|
|
30
|
-
it('scores an exact trajectory 1', async () => {
|
|
31
|
-
expect((await score(['read', 'edit'], ['read', 'edit'])).score).toBe(1);
|
|
32
|
-
});
|
|
33
|
-
it('distinguishes ORDER — a set-based score could not', async () => {
|
|
34
|
-
// Reading before editing is not the same run as editing then reading.
|
|
35
|
-
const reversed = await score(['read', 'edit'], ['edit', 'read']);
|
|
36
|
-
expect(reversed.score).toBeLessThan(1);
|
|
37
|
-
expect(reversed.score).toBeGreaterThan(0);
|
|
38
|
-
});
|
|
39
|
-
it('penalises an extra call through precision', async () => {
|
|
40
|
-
const wasteful = await score(['read'], ['read', 'read', 'read']);
|
|
41
|
-
expect(wasteful.score).toBeLessThan(1);
|
|
42
|
-
expect(wasteful.details?.recall).toBe(1);
|
|
43
|
-
expect(wasteful.details?.precision).toBeLessThan(1);
|
|
44
|
-
});
|
|
45
|
-
it('penalises a missing call through recall', async () => {
|
|
46
|
-
const lazy = await score(['read', 'edit', 'bash'], ['read']);
|
|
47
|
-
expect(lazy.details?.precision).toBe(1);
|
|
48
|
-
expect(lazy.details?.recall).toBeLessThan(1);
|
|
49
|
-
});
|
|
50
|
-
it('separates "wasteful" from "skipped" — a final-answer score collapses them', async () => {
|
|
51
|
-
const wasteful = await score(['read', 'edit'], ['read', 'ls', 'edit']);
|
|
52
|
-
const skipped = await score(['read', 'edit'], ['read']);
|
|
53
|
-
expect(wasteful.score).not.toBe(skipped.score);
|
|
54
|
-
});
|
|
55
|
-
it('scores 1 when no tools were expected and none ran', async () => {
|
|
56
|
-
expect((await score([], [])).score).toBe(1);
|
|
57
|
-
});
|
|
58
|
-
it('scores 0 when tools were expected and none ran', async () => {
|
|
59
|
-
const s = await score(['read'], []);
|
|
60
|
-
expect(s.score).toBe(0);
|
|
61
|
-
expect(s.reason).toContain('no tools were called');
|
|
62
|
-
});
|
|
63
|
-
it('scores 0 when none were expected and some ran', async () => {
|
|
64
|
-
expect((await score([], ['bash'])).score).toBe(0);
|
|
65
|
-
});
|
|
66
|
-
it('always explains itself', async () => {
|
|
67
|
-
expect((await score(['read'], ['edit'])).reason.length).toBeGreaterThan(0);
|
|
68
|
-
});
|
|
69
|
-
});
|
|
70
|
-
describe('completionScorer', () => {
|
|
71
|
-
it('accepts a clean settle', async () => {
|
|
72
|
-
expect((await completionScorer().score(run({ stopReason: 'end_turn' }), CASE)).score).toBe(1);
|
|
73
|
-
});
|
|
74
|
-
it('rejects a budget-forced stop', async () => {
|
|
75
|
-
const s = await completionScorer().score(run({ stopReason: 'max_iterations' }), CASE);
|
|
76
|
-
expect(s.score).toBe(0);
|
|
77
|
-
expect(s.reason).toContain('max_iterations');
|
|
78
|
-
});
|
|
79
|
-
it('reports the error when the run threw', async () => {
|
|
80
|
-
const s = await completionScorer().score(run({ error: 'boom' }), CASE);
|
|
81
|
-
expect(s.score).toBe(0);
|
|
82
|
-
expect(s.reason).toContain('boom');
|
|
83
|
-
});
|
|
84
|
-
});
|
|
85
|
-
describe('stepBudgetScorer', () => {
|
|
86
|
-
const withSteps = (n) => run({ steps: Array.from({ length: n }, () => ({})) });
|
|
87
|
-
it('passes within budget', async () => {
|
|
88
|
-
expect((await stepBudgetScorer(5).score(withSteps(3), CASE)).score).toBe(1);
|
|
89
|
-
});
|
|
90
|
-
it('degrades proportionally past it, rather than snapping to zero', async () => {
|
|
91
|
-
// A run that took 6 steps against a 5 allowance is worse than one
|
|
92
|
-
// that took 20; a binary score cannot say so.
|
|
93
|
-
const slight = (await stepBudgetScorer(5).score(withSteps(6), CASE)).score;
|
|
94
|
-
const severe = (await stepBudgetScorer(5).score(withSteps(20), CASE)).score;
|
|
95
|
-
expect(slight).toBeGreaterThan(severe);
|
|
96
|
-
expect(slight).toBeLessThan(1);
|
|
97
|
-
});
|
|
98
|
-
});
|
|
99
|
-
describe('containsScorer', () => {
|
|
100
|
-
it('scores the fraction found and names what is missing', async () => {
|
|
101
|
-
const s = await containsScorer('alpha', 'beta').score(run({ output: 'alpha only' }), CASE);
|
|
102
|
-
expect(s.score).toBe(0.5);
|
|
103
|
-
expect(s.reason).toContain('beta');
|
|
104
|
-
});
|
|
105
|
-
});
|
|
106
|
-
describe('runExperiment', () => {
|
|
107
|
-
const cases = [
|
|
108
|
-
{ name: 'good', input: 'a', expectedTools: ['read'] },
|
|
109
|
-
{ name: 'bad', input: 'b', expectedTools: ['read', 'edit'] },
|
|
110
|
-
];
|
|
111
|
-
it('scores every case and aggregates', async () => {
|
|
112
|
-
const report = await runExperiment({
|
|
113
|
-
name: 'demo',
|
|
114
|
-
cases,
|
|
115
|
-
scorers: [trajectoryScorer()],
|
|
116
|
-
run: async (input) => run({ toolCalls: input === 'a' ? ['read'] : ['bash'] }),
|
|
117
|
-
});
|
|
118
|
-
expect(report.cases).toHaveLength(2);
|
|
119
|
-
expect(report.passed).toBe(1);
|
|
120
|
-
expect(report.failed).toBe(1);
|
|
121
|
-
expect(report.byScorer.trajectory).toBeCloseTo(0.5, 5);
|
|
122
|
-
});
|
|
123
|
-
it('a throwing case is a RESULT, not a crash', async () => {
|
|
124
|
-
// A suite whose first broken case aborts tells you nothing about the
|
|
125
|
-
// other forty.
|
|
126
|
-
const report = await runExperiment({
|
|
127
|
-
name: 'demo',
|
|
128
|
-
cases,
|
|
129
|
-
scorers: [completionScorer()],
|
|
130
|
-
run: async (input) => {
|
|
131
|
-
if (input === 'a')
|
|
132
|
-
throw new Error('exploded');
|
|
133
|
-
return run();
|
|
134
|
-
},
|
|
135
|
-
});
|
|
136
|
-
expect(report.cases).toHaveLength(2);
|
|
137
|
-
expect(report.cases[0]?.run.error).toBe('exploded');
|
|
138
|
-
expect(report.cases[1]?.passed).toBe(true);
|
|
139
|
-
});
|
|
140
|
-
it('a throwing scorer scores zero with the throw as its reason', async () => {
|
|
141
|
-
const report = await runExperiment({
|
|
142
|
-
name: 'demo',
|
|
143
|
-
cases: [cases[0]],
|
|
144
|
-
scorers: [
|
|
145
|
-
customScorer('boom', () => {
|
|
146
|
-
throw new Error('scorer broke');
|
|
147
|
-
}),
|
|
148
|
-
],
|
|
149
|
-
run: async () => run(),
|
|
150
|
-
});
|
|
151
|
-
expect(report.cases[0]?.scores.boom?.score).toBe(0);
|
|
152
|
-
expect(report.cases[0]?.scores.boom?.reason).toContain('scorer broke');
|
|
153
|
-
});
|
|
154
|
-
it('preserves case order under concurrency', async () => {
|
|
155
|
-
const many = Array.from({ length: 8 }, (_, i) => ({
|
|
156
|
-
name: `case-${i}`,
|
|
157
|
-
input: i,
|
|
158
|
-
}));
|
|
159
|
-
const report = await runExperiment({
|
|
160
|
-
name: 'demo',
|
|
161
|
-
cases: many,
|
|
162
|
-
concurrency: 4,
|
|
163
|
-
scorers: [completionScorer()],
|
|
164
|
-
run: async (input) => {
|
|
165
|
-
await new Promise((r) => setTimeout(r, (8 - input) * 2));
|
|
166
|
-
return run();
|
|
167
|
-
},
|
|
168
|
-
});
|
|
169
|
-
expect(report.cases.map((c) => c.case)).toEqual(many.map((c) => c.name));
|
|
170
|
-
});
|
|
171
|
-
it('honours a per-case scorer override', async () => {
|
|
172
|
-
const report = await runExperiment({
|
|
173
|
-
name: 'demo',
|
|
174
|
-
cases: [{ name: 'special', input: null, scorers: [containsScorer('xyz')] }],
|
|
175
|
-
scorers: [completionScorer()],
|
|
176
|
-
run: async () => run({ output: 'no match here' }),
|
|
177
|
-
});
|
|
178
|
-
expect(Object.keys(report.cases[0]?.scores ?? {})).toEqual(['contains']);
|
|
179
|
-
});
|
|
180
|
-
it('respects a partial pass threshold', async () => {
|
|
181
|
-
const report = await runExperiment({
|
|
182
|
-
name: 'demo',
|
|
183
|
-
cases: [{ name: 'partial', input: null, expectedTools: ['read', 'edit'] }],
|
|
184
|
-
scorers: [trajectoryScorer()],
|
|
185
|
-
passThreshold: 0.5,
|
|
186
|
-
run: async () => run({ toolCalls: ['read'] }),
|
|
187
|
-
});
|
|
188
|
-
expect(report.passed).toBe(1);
|
|
189
|
-
});
|
|
190
|
-
});
|
|
191
|
-
describe('formatReport', () => {
|
|
192
|
-
it('prints scorer reasons for failures, not just numbers', async () => {
|
|
193
|
-
// A CI log that says "0.62" sends someone back to reproduce it by hand.
|
|
194
|
-
const report = await runExperiment({
|
|
195
|
-
name: 'demo',
|
|
196
|
-
cases: [{ name: 'bad', input: null, expectedTools: ['read', 'edit'] }],
|
|
197
|
-
scorers: [trajectoryScorer()],
|
|
198
|
-
run: async () => run({ toolCalls: ['bash'] }),
|
|
199
|
-
});
|
|
200
|
-
const text = formatReport(report);
|
|
201
|
-
expect(text).toContain('0/1 passed');
|
|
202
|
-
expect(text).toContain('✗ bad');
|
|
203
|
-
expect(text).toContain('trajectory:');
|
|
204
|
-
expect(text).toContain('expected read → edit');
|
|
205
|
-
});
|
|
206
|
-
});
|
|
207
|
-
//# sourceMappingURL=harness.test.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"harness.test.js","sourceRoot":"","sources":["../../../src/eval/__tests__/harness.test.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,EAAE,EAAE,EAAE,MAAM,QAAQ,CAAA;AAE7C,OAAO,EAAE,YAAY,EAAE,aAAa,EAAE,MAAM,kBAAkB,CAAA;AAC9D,OAAO,EACN,gBAAgB,EAChB,cAAc,EACd,YAAY,EACZ,gBAAgB,EAChB,gBAAgB,GAChB,MAAM,eAAe,CAAA;AAGtB;;;;;;;;GAQG;AAEH,SAAS,GAAG,CAAC,YAA8B,EAAE;IAC5C,OAAO;QACN,MAAM,EAAE,MAAM;QACd,KAAK,EAAE,EAAE;QACT,SAAS,EAAE,EAAE;QACb,UAAU,EAAE,UAAU;QACtB,WAAW,EAAE,CAAC;QACd,YAAY,EAAE,CAAC;QACf,UAAU,EAAE,CAAC;QACb,GAAG,SAAS;KACZ,CAAA;AACF,CAAC;AAED,MAAM,IAAI,GAAa,EAAE,IAAI,EAAE,GAAG,EAAE,KAAK,EAAE,IAAI,EAAE,CAAA;AAEjD,QAAQ,CAAC,kBAAkB,EAAE,GAAG,EAAE;IACjC,qEAAqE;IACrE,wEAAwE;IACxE,MAAM,KAAK,GAAG,KAAK,EAAE,aAAuB,EAAE,SAAmB,EAAE,EAAE,CACpE,MAAM,gBAAgB,EAAE,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,SAAS,EAAE,CAAC,EAAE,EAAE,GAAG,IAAI,EAAE,aAAa,EAAE,CAAC,CAAA;IAE/E,EAAE,CAAC,8BAA8B,EAAE,KAAK,IAAI,EAAE;QAC7C,MAAM,CAAC,CAAC,MAAM,KAAK,CAAC,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IACxE,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,mDAAmD,EAAE,KAAK,IAAI,EAAE;QAClE,sEAAsE;QACtE,MAAM,QAAQ,GAAG,MAAM,KAAK,CAAC,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC,CAAA;QAChE,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;QACtC,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,CAAA;IAC1C,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,2CAA2C,EAAE,KAAK,IAAI,EAAE;QAC1D,MAAM,QAAQ,GAAG,MAAM,KAAK,CAAC,CAAC,MAAM,CAAC,EAAE,CAAC,MAAM,EAAE,MAAM,EAAE,MAAM,CAAC,CAAC,CAAA;QAChE,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;QACtC,MAAM,CAAC,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QACxC,MAAM,CAAC,QAAQ,CAAC,OAAO,EAAE,SAAS,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;IACpD,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,yCAAyC,EAAE,KAAK,IAAI,EAAE;QACxD,MAAM,IAAI,GAAG,MAAM,KAAK,CAAC,CAAC,MAAM,EAAE,MAAM,EAAE,MAAM,CAAC,EAAE,CAAC,MAAM,CAAC,CAAC,CAAA;QAC5D,MAAM,CAAC,IAAI,CAAC,OAAO,EAAE,SAAS,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QACvC,MAAM,CAAC,IAAI,CAAC,OAAO,EAAE,MAAM,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;IAC7C,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,2EAA2E,EAAE,KAAK,IAAI,EAAE;QAC1F,MAAM,QAAQ,GAAG,MAAM,KAAK,CAAC,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,CAAC,MAAM,EAAE,IAAI,EAAE,MAAM,CAAC,CAAC,CAAA;QACtE,MAAM,OAAO,GAAG,MAAM,KAAK,CAAC,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,CAAC,MAAM,CAAC,CAAC,CAAA;QACvD,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,IAAI,CAAC,OAAO,CAAC,KAAK,CAAC,CAAA;IAC/C,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,mDAAmD,EAAE,KAAK,IAAI,EAAE;QAClE,MAAM,CAAC,CAAC,MAAM,KAAK,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IAC5C,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,gDAAgD,EAAE,KAAK,IAAI,EAAE;QAC/D,MAAM,CAAC,GAAG,MAAM,KAAK,CAAC,CAAC,MAAM,CAAC,EAAE,EAAE,CAAC,CAAA;QACnC,MAAM,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QACvB,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,SAAS,CAAC,sBAAsB,CAAC,CAAA;IACnD,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,+CAA+C,EAAE,KAAK,IAAI,EAAE;QAC9D,MAAM,CAAC,CAAC,MAAM,KAAK,CAAC,EAAE,EAAE,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IAClD,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,wBAAwB,EAAE,KAAK,IAAI,EAAE;QACvC,MAAM,CAAC,CAAC,MAAM,KAAK,CAAC,CAAC,MAAM,CAAC,EAAE,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,CAAA;IAC3E,CAAC,CAAC,CAAA;AACH,CAAC,CAAC,CAAA;AAEF,QAAQ,CAAC,kBAAkB,EAAE,GAAG,EAAE;IACjC,EAAE,CAAC,wBAAwB,EAAE,KAAK,IAAI,EAAE;QACvC,MAAM,CAAC,CAAC,MAAM,gBAAgB,EAAE,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,UAAU,EAAE,UAAU,EAAE,CAAC,EAAE,IAAI,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IAC9F,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,8BAA8B,EAAE,KAAK,IAAI,EAAE;QAC7C,MAAM,CAAC,GAAG,MAAM,gBAAgB,EAAE,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,UAAU,EAAE,gBAAgB,EAAE,CAAC,EAAE,IAAI,CAAC,CAAA;QACrF,MAAM,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QACvB,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,SAAS,CAAC,gBAAgB,CAAC,CAAA;IAC7C,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,sCAAsC,EAAE,KAAK,IAAI,EAAE;QACrD,MAAM,CAAC,GAAG,MAAM,gBAAgB,EAAE,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,KAAK,EAAE,MAAM,EAAE,CAAC,EAAE,IAAI,CAAC,CAAA;QACtE,MAAM,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QACvB,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,SAAS,CAAC,MAAM,CAAC,CAAA;IACnC,CAAC,CAAC,CAAA;AACH,CAAC,CAAC,CAAA;AAEF,QAAQ,CAAC,kBAAkB,EAAE,GAAG,EAAE;IACjC,MAAM,SAAS,GAAG,CAAC,CAAS,EAAE,EAAE,CAAC,GAAG,CAAC,EAAE,KAAK,EAAE,KAAK,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,EAAE,GAAG,EAAE,CAAC,CAAC,EAAE,CAAU,CAAC,EAAE,CAAC,CAAA;IAE/F,EAAE,CAAC,sBAAsB,EAAE,KAAK,IAAI,EAAE;QACrC,MAAM,CAAC,CAAC,MAAM,gBAAgB,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,SAAS,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IAC5E,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,+DAA+D,EAAE,KAAK,IAAI,EAAE;QAC9E,kEAAkE;QAClE,8CAA8C;QAC9C,MAAM,MAAM,GAAG,CAAC,MAAM,gBAAgB,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,SAAS,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,CAAC,KAAK,CAAA;QAC1E,MAAM,MAAM,GAAG,CAAC,MAAM,gBAAgB,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,SAAS,CAAC,EAAE,CAAC,EAAE,IAAI,CAAC,CAAC,CAAC,KAAK,CAAA;QAC3E,MAAM,CAAC,MAAM,CAAC,CAAC,eAAe,CAAC,MAAM,CAAC,CAAA;QACtC,MAAM,CAAC,MAAM,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;IAC/B,CAAC,CAAC,CAAA;AACH,CAAC,CAAC,CAAA;AAEF,QAAQ,CAAC,gBAAgB,EAAE,GAAG,EAAE;IAC/B,EAAE,CAAC,qDAAqD,EAAE,KAAK,IAAI,EAAE;QACpE,MAAM,CAAC,GAAG,MAAM,cAAc,CAAC,OAAO,EAAE,MAAM,CAAC,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,MAAM,EAAE,YAAY,EAAE,CAAC,EAAE,IAAI,CAAC,CAAA;QAC1F,MAAM,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;QACzB,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,SAAS,CAAC,MAAM,CAAC,CAAA;IACnC,CAAC,CAAC,CAAA;AACH,CAAC,CAAC,CAAA;AAEF,QAAQ,CAAC,eAAe,EAAE,GAAG,EAAE;IAC9B,MAAM,KAAK,GAAe;QACzB,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,GAAG,EAAE,aAAa,EAAE,CAAC,MAAM,CAAC,EAAE;QACrD,EAAE,IAAI,EAAE,KAAK,EAAE,KAAK,EAAE,GAAG,EAAE,aAAa,EAAE,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE;KAC5D,CAAA;IAED,EAAE,CAAC,kCAAkC,EAAE,KAAK,IAAI,EAAE;QACjD,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,IAAI,EAAE,MAAM;YACZ,KAAK;YACL,OAAO,EAAE,CAAC,gBAAgB,EAAE,CAAC;YAC7B,GAAG,EAAE,KAAK,EAAE,KAAK,EAAE,EAAE,CAAC,GAAG,CAAC,EAAE,SAAS,EAAE,KAAK,KAAK,GAAG,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,EAAE,CAAC;SAC7E,CAAC,CAAA;QAEF,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;QACpC,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QAC7B,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QAC7B,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,UAAU,CAAC,CAAC,WAAW,CAAC,GAAG,EAAE,CAAC,CAAC,CAAA;IACvD,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,0CAA0C,EAAE,KAAK,IAAI,EAAE;QACzD,qEAAqE;QACrE,eAAe;QACf,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,IAAI,EAAE,MAAM;YACZ,KAAK;YACL,OAAO,EAAE,CAAC,gBAAgB,EAAE,CAAC;YAC7B,GAAG,EAAE,KAAK,EAAE,KAAK,EAAE,EAAE;gBACpB,IAAI,KAAK,KAAK,GAAG;oBAAE,MAAM,IAAI,KAAK,CAAC,UAAU,CAAC,CAAA;gBAC9C,OAAO,GAAG,EAAE,CAAA;YACb,CAAC;SACD,CAAC,CAAA;QAEF,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,CAAA;QACpC,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,GAAG,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,UAAU,CAAC,CAAA;QACnD,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;IAC3C,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,4DAA4D,EAAE,KAAK,IAAI,EAAE;QAC3E,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,IAAI,EAAE,MAAM;YACZ,KAAK,EAAE,CAAC,KAAK,CAAC,CAAC,CAAa,CAAC;YAC7B,OAAO,EAAE;gBACR,YAAY,CAAC,MAAM,EAAE,GAAG,EAAE;oBACzB,MAAM,IAAI,KAAK,CAAC,cAAc,CAAC,CAAA;gBAChC,CAAC,CAAC;aACF;YACD,GAAG,EAAE,KAAK,IAAI,EAAE,CAAC,GAAG,EAAE;SACtB,CAAC,CAAA;QAEF,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,IAAI,EAAE,KAAK,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QACnD,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,IAAI,EAAE,MAAM,CAAC,CAAC,SAAS,CAAC,cAAc,CAAC,CAAA;IACvE,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,wCAAwC,EAAE,KAAK,IAAI,EAAE;QACvD,MAAM,IAAI,GAAe,KAAK,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC;YAC7D,IAAI,EAAE,QAAQ,CAAC,EAAE;YACjB,KAAK,EAAE,CAAC;SACR,CAAC,CAAC,CAAA;QACH,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,IAAI,EAAE,MAAM;YACZ,KAAK,EAAE,IAAI;YACX,WAAW,EAAE,CAAC;YACd,OAAO,EAAE,CAAC,gBAAgB,EAAE,CAAC;YAC7B,GAAG,EAAE,KAAK,EAAE,KAAK,EAAE,EAAE;gBACpB,MAAM,IAAI,OAAO,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,UAAU,CAAC,CAAC,EAAE,CAAC,CAAC,GAAI,KAAgB,CAAC,GAAG,CAAC,CAAC,CAAC,CAAA;gBACpE,OAAO,GAAG,EAAE,CAAA;YACb,CAAC;SACD,CAAC,CAAA;QAEF,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,OAAO,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAA;IACzE,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,oCAAoC,EAAE,KAAK,IAAI,EAAE;QACnD,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,IAAI,EAAE,MAAM;YACZ,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,SAAS,EAAE,KAAK,EAAE,IAAI,EAAE,OAAO,EAAE,CAAC,cAAc,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC;YAC3E,OAAO,EAAE,CAAC,gBAAgB,EAAE,CAAC;YAC7B,GAAG,EAAE,KAAK,IAAI,EAAE,CAAC,GAAG,CAAC,EAAE,MAAM,EAAE,eAAe,EAAE,CAAC;SACjD,CAAC,CAAA;QAEF,MAAM,CAAC,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,IAAI,EAAE,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,UAAU,CAAC,CAAC,CAAA;IACzE,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,mCAAmC,EAAE,KAAK,IAAI,EAAE;QAClD,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,IAAI,EAAE,MAAM;YACZ,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,SAAS,EAAE,KAAK,EAAE,IAAI,EAAE,aAAa,EAAE,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,CAAC;YAC1E,OAAO,EAAE,CAAC,gBAAgB,EAAE,CAAC;YAC7B,aAAa,EAAE,GAAG;YAClB,GAAG,EAAE,KAAK,IAAI,EAAE,CAAC,GAAG,CAAC,EAAE,SAAS,EAAE,CAAC,MAAM,CAAC,EAAE,CAAC;SAC7C,CAAC,CAAA;QAEF,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IAC9B,CAAC,CAAC,CAAA;AACH,CAAC,CAAC,CAAA;AAEF,QAAQ,CAAC,cAAc,EAAE,GAAG,EAAE;IAC7B,EAAE,CAAC,sDAAsD,EAAE,KAAK,IAAI,EAAE;QACrE,wEAAwE;QACxE,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,IAAI,EAAE,MAAM;YACZ,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,KAAK,EAAE,KAAK,EAAE,IAAI,EAAE,aAAa,EAAE,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,CAAC;YACtE,OAAO,EAAE,CAAC,gBAAgB,EAAE,CAAC;YAC7B,GAAG,EAAE,KAAK,IAAI,EAAE,CAAC,GAAG,CAAC,EAAE,SAAS,EAAE,CAAC,MAAM,CAAC,EAAE,CAAC;SAC7C,CAAC,CAAA;QAEF,MAAM,IAAI,GAAG,YAAY,CAAC,MAAM,CAAC,CAAA;QACjC,MAAM,CAAC,IAAI,CAAC,CAAC,SAAS,CAAC,YAAY,CAAC,CAAA;QACpC,MAAM,CAAC,IAAI,CAAC,CAAC,SAAS,CAAC,OAAO,CAAC,CAAA;QAC/B,MAAM,CAAC,IAAI,CAAC,CAAC,SAAS,CAAC,aAAa,CAAC,CAAA;QACrC,MAAM,CAAC,IAAI,CAAC,CAAC,SAAS,CAAC,sBAAsB,CAAC,CAAA;IAC/C,CAAC,CAAC,CAAA;AACH,CAAC,CAAC,CAAA"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"judge.test.d.ts","sourceRoot":"","sources":["../../../src/eval/__tests__/judge.test.ts"],"names":[],"mappings":""}
|
|
@@ -1,255 +0,0 @@
|
|
|
1
|
-
import { describe, expect, it } from 'vitest';
|
|
2
|
-
import { runExperiment } from '../experiment.js';
|
|
3
|
-
import { judgeScorer } from '../judge.js';
|
|
4
|
-
/**
|
|
5
|
-
* Every other scorer is a pure function over the run, which is what makes
|
|
6
|
-
* them reproducible and what makes them unable to say whether an answer is
|
|
7
|
-
* GOOD. A judge closes that, and brings a failure mode none of the others
|
|
8
|
-
* have: it can fail to answer at all. A failed measurement scored zero
|
|
9
|
-
* reads exactly like a regression, so the distinction is what most of this
|
|
10
|
-
* file is about.
|
|
11
|
-
*/
|
|
12
|
-
function fakeProvider(reply, tokens = 42) {
|
|
13
|
-
const seen = [];
|
|
14
|
-
const provider = {
|
|
15
|
-
id: 'fake',
|
|
16
|
-
name: 'fake',
|
|
17
|
-
capabilities: {
|
|
18
|
-
supportsTools: false,
|
|
19
|
-
supportsStreaming: true,
|
|
20
|
-
supportsFunctionCalling: false,
|
|
21
|
-
},
|
|
22
|
-
seen,
|
|
23
|
-
async *chatStream(params) {
|
|
24
|
-
seen.push(params);
|
|
25
|
-
if (typeof reply !== 'string')
|
|
26
|
-
reply();
|
|
27
|
-
yield { id: 'j', delta: { content: reply } };
|
|
28
|
-
yield {
|
|
29
|
-
id: 'j',
|
|
30
|
-
delta: {},
|
|
31
|
-
finishReason: 'stop',
|
|
32
|
-
usage: {
|
|
33
|
-
promptTokens: tokens,
|
|
34
|
-
completionTokens: 0,
|
|
35
|
-
totalTokens: tokens,
|
|
36
|
-
cachedTokens: 0,
|
|
37
|
-
cacheWriteTokens: 0,
|
|
38
|
-
},
|
|
39
|
-
};
|
|
40
|
-
},
|
|
41
|
-
async listModels() {
|
|
42
|
-
return [];
|
|
43
|
-
},
|
|
44
|
-
async healthCheck() {
|
|
45
|
-
return true;
|
|
46
|
-
},
|
|
47
|
-
};
|
|
48
|
-
return provider;
|
|
49
|
-
}
|
|
50
|
-
const RUN = {
|
|
51
|
-
output: 'The capital of France is Paris.',
|
|
52
|
-
steps: [],
|
|
53
|
-
toolCalls: ['search'],
|
|
54
|
-
stopReason: 'end_turn',
|
|
55
|
-
totalTokens: 100,
|
|
56
|
-
totalCostUsd: 0,
|
|
57
|
-
durationMs: 10,
|
|
58
|
-
};
|
|
59
|
-
const CASE = { name: 'capital', input: 'What is the capital of France?' };
|
|
60
|
-
const RUBRIC = 'The answer names the correct city.';
|
|
61
|
-
describe('grading', () => {
|
|
62
|
-
it('normalises the grade onto 0..1 against the scale it asked for', async () => {
|
|
63
|
-
const scorer = judgeScorer({
|
|
64
|
-
provider: fakeProvider('{"grade": 3, "reason": "names the right city"}'),
|
|
65
|
-
model: 'm',
|
|
66
|
-
rubric: RUBRIC,
|
|
67
|
-
scale: 4,
|
|
68
|
-
});
|
|
69
|
-
const score = await scorer.score(RUN, CASE);
|
|
70
|
-
expect(score.score).toBe(0.75);
|
|
71
|
-
expect(score.reason).toBe('names the right city');
|
|
72
|
-
expect(score.details?.grade).toBe(3);
|
|
73
|
-
});
|
|
74
|
-
it('reads a verdict wrapped in prose or fences', async () => {
|
|
75
|
-
const scorer = judgeScorer({
|
|
76
|
-
provider: fakeProvider('Here is my grade:\n```json\n{"grade": 4, "reason": "correct"}\n```'),
|
|
77
|
-
model: 'm',
|
|
78
|
-
rubric: RUBRIC,
|
|
79
|
-
});
|
|
80
|
-
expect((await scorer.score(RUN, CASE)).score).toBe(1);
|
|
81
|
-
});
|
|
82
|
-
it('handles a brace inside the reason string', async () => {
|
|
83
|
-
const scorer = judgeScorer({
|
|
84
|
-
provider: fakeProvider('{"grade": 2, "reason": "mentions {city} placeholder"}'),
|
|
85
|
-
model: 'm',
|
|
86
|
-
rubric: RUBRIC,
|
|
87
|
-
scale: 4,
|
|
88
|
-
});
|
|
89
|
-
// A naive scan to the first `}` would cut the object in half here.
|
|
90
|
-
expect((await scorer.score(RUN, CASE)).score).toBe(0.5);
|
|
91
|
-
});
|
|
92
|
-
it('carries what the judging itself cost', async () => {
|
|
93
|
-
const scorer = judgeScorer({
|
|
94
|
-
provider: fakeProvider('{"grade": 4, "reason": "ok"}', 1234),
|
|
95
|
-
model: 'm',
|
|
96
|
-
rubric: RUBRIC,
|
|
97
|
-
});
|
|
98
|
-
// A judge is the most expensive scorer there is; a bill nobody can
|
|
99
|
-
// attribute is a bill nobody controls.
|
|
100
|
-
expect((await scorer.score(RUN, CASE)).details?.judgeTokens).toBe(1234);
|
|
101
|
-
});
|
|
102
|
-
it('grades the same run the same way twice', async () => {
|
|
103
|
-
const provider = fakeProvider('{"grade": 4, "reason": "ok"}');
|
|
104
|
-
await judgeScorer({ provider, model: 'm', rubric: RUBRIC }).score(RUN, CASE);
|
|
105
|
-
// Sampling noise is indistinguishable from a regression, so the
|
|
106
|
-
// judge does not sample.
|
|
107
|
-
expect(provider.seen[0]?.temperature).toBe(0);
|
|
108
|
-
});
|
|
109
|
-
});
|
|
110
|
-
describe('what the judge is shown', () => {
|
|
111
|
-
const promptOf = (provider) => String(provider.seen[0]?.messages[0]?.content);
|
|
112
|
-
it('shows the rubric, the task and the answer', async () => {
|
|
113
|
-
const provider = fakeProvider('{"grade": 4, "reason": "ok"}');
|
|
114
|
-
await judgeScorer({ provider, model: 'm', rubric: RUBRIC }).score(RUN, CASE);
|
|
115
|
-
const prompt = promptOf(provider);
|
|
116
|
-
expect(prompt).toContain(RUBRIC);
|
|
117
|
-
expect(prompt).toContain('What is the capital of France?');
|
|
118
|
-
expect(prompt).toContain('The capital of France is Paris.');
|
|
119
|
-
});
|
|
120
|
-
it('withholds the trajectory unless asked', async () => {
|
|
121
|
-
const off = fakeProvider('{"grade": 4, "reason": "ok"}');
|
|
122
|
-
await judgeScorer({ provider: off, model: 'm', rubric: RUBRIC }).score(RUN, CASE);
|
|
123
|
-
expect(promptOf(off)).not.toContain('TOOLS CALLED');
|
|
124
|
-
const on = fakeProvider('{"grade": 4, "reason": "ok"}');
|
|
125
|
-
await judgeScorer({
|
|
126
|
-
provider: on,
|
|
127
|
-
model: 'm',
|
|
128
|
-
rubric: RUBRIC,
|
|
129
|
-
includeTrajectory: true,
|
|
130
|
-
}).score(RUN, CASE);
|
|
131
|
-
expect(promptOf(on)).toContain('search');
|
|
132
|
-
});
|
|
133
|
-
it('says when it truncated the answer', async () => {
|
|
134
|
-
const provider = fakeProvider('{"grade": 4, "reason": "ok"}');
|
|
135
|
-
await judgeScorer({
|
|
136
|
-
provider,
|
|
137
|
-
model: 'm',
|
|
138
|
-
rubric: RUBRIC,
|
|
139
|
-
maxOutputChars: 10,
|
|
140
|
-
}).score({ ...RUN, output: 'x'.repeat(500) }, CASE);
|
|
141
|
-
// A judge shown a silently cut answer marks it down for stopping
|
|
142
|
-
// mid-sentence, which scores our truncation rather than the run.
|
|
143
|
-
expect(promptOf(provider)).toContain('cut at 10 characters by the harness');
|
|
144
|
-
});
|
|
145
|
-
it('offers the reference answer when the case has one', async () => {
|
|
146
|
-
const provider = fakeProvider('{"grade": 4, "reason": "ok"}');
|
|
147
|
-
await judgeScorer({ provider, model: 'm', rubric: RUBRIC }).score(RUN, {
|
|
148
|
-
...CASE,
|
|
149
|
-
expected: 'Paris',
|
|
150
|
-
});
|
|
151
|
-
expect(promptOf(provider)).toContain('Paris');
|
|
152
|
-
});
|
|
153
|
-
});
|
|
154
|
-
describe('a judge that cannot judge', () => {
|
|
155
|
-
const failing = (reply) => judgeScorer({ provider: fakeProvider(reply), model: 'm', rubric: RUBRIC, scale: 4 });
|
|
156
|
-
it('throws on a reply with no JSON at all', async () => {
|
|
157
|
-
await expect(failing('I think it was pretty good!').score(RUN, CASE)).rejects.toThrow(/no JSON/);
|
|
158
|
-
});
|
|
159
|
-
it('throws on a grade outside the scale it was given', async () => {
|
|
160
|
-
// Clamping would turn a judge that misread the scale into a
|
|
161
|
-
// confident score, and a judge that misread the scale did not apply
|
|
162
|
-
// the rubric either.
|
|
163
|
-
await expect(failing('{"grade": 9, "reason": "great"}').score(RUN, CASE)).rejects.toThrow(/outside the 0\.\.4 scale/);
|
|
164
|
-
});
|
|
165
|
-
it('throws on a non-numeric grade', async () => {
|
|
166
|
-
await expect(failing('{"grade": "good", "reason": "x"}').score(RUN, CASE)).rejects.toThrow(/no numeric grade/);
|
|
167
|
-
});
|
|
168
|
-
it('throws on an unterminated object', async () => {
|
|
169
|
-
await expect(failing('{"grade": 3, "reason": "cut off').score(RUN, CASE)).rejects.toThrow(/unterminated/);
|
|
170
|
-
});
|
|
171
|
-
it('refuses to exist without a rubric', () => {
|
|
172
|
-
expect(() => judgeScorer({ provider: fakeProvider('{}'), model: 'm', rubric: ' ' })).toThrow(/rubric is required/);
|
|
173
|
-
});
|
|
174
|
-
it('refuses a nonsense scale', () => {
|
|
175
|
-
expect(() => judgeScorer({ provider: fakeProvider('{}'), model: 'm', rubric: RUBRIC, scale: 0 })).toThrow(/positive integer/);
|
|
176
|
-
});
|
|
177
|
-
});
|
|
178
|
-
describe('a broken judge is not a bad run', () => {
|
|
179
|
-
const dataset = {
|
|
180
|
-
name: 'suite',
|
|
181
|
-
cases: [CASE],
|
|
182
|
-
run: async () => RUN,
|
|
183
|
-
};
|
|
184
|
-
it('reports the case as inconclusive rather than failed', async () => {
|
|
185
|
-
const report = await runExperiment({
|
|
186
|
-
...dataset,
|
|
187
|
-
scorers: [
|
|
188
|
-
judgeScorer({
|
|
189
|
-
provider: fakeProvider(() => {
|
|
190
|
-
throw new Error('429 rate limited');
|
|
191
|
-
}),
|
|
192
|
-
model: 'm',
|
|
193
|
-
rubric: RUBRIC,
|
|
194
|
-
}),
|
|
195
|
-
],
|
|
196
|
-
});
|
|
197
|
-
expect(report.inconclusive).toBe(1);
|
|
198
|
-
expect(report.failed).toBe(0);
|
|
199
|
-
expect(report.passed).toBe(0);
|
|
200
|
-
expect(report.cases[0]?.scores.judge?.unavailable).toBe(true);
|
|
201
|
-
expect(report.cases[0]?.scores.judge?.reason).toContain('429');
|
|
202
|
-
});
|
|
203
|
-
it('keeps an unavailable score out of the mean entirely', async () => {
|
|
204
|
-
const report = await runExperiment({
|
|
205
|
-
...dataset,
|
|
206
|
-
scorers: [
|
|
207
|
-
{ name: 'always-one', score: () => ({ score: 1, reason: 'fine' }) },
|
|
208
|
-
judgeScorer({
|
|
209
|
-
provider: fakeProvider(() => {
|
|
210
|
-
throw new Error('down');
|
|
211
|
-
}),
|
|
212
|
-
model: 'm',
|
|
213
|
-
rubric: RUBRIC,
|
|
214
|
-
}),
|
|
215
|
-
],
|
|
216
|
-
});
|
|
217
|
-
// Not 0.5. A measurement that never happened is not a zero, and
|
|
218
|
-
// averaging it in would report a regression the harness caused.
|
|
219
|
-
expect(report.cases[0]?.mean).toBe(1);
|
|
220
|
-
expect(report.cases[0]?.status).toBe('passed');
|
|
221
|
-
expect(report.mean).toBe(1);
|
|
222
|
-
});
|
|
223
|
-
it('omits a scorer that was never available from the per-dimension means', async () => {
|
|
224
|
-
const report = await runExperiment({
|
|
225
|
-
...dataset,
|
|
226
|
-
scorers: [
|
|
227
|
-
judgeScorer({
|
|
228
|
-
provider: fakeProvider(() => {
|
|
229
|
-
throw new Error('down');
|
|
230
|
-
}),
|
|
231
|
-
model: 'm',
|
|
232
|
-
rubric: RUBRIC,
|
|
233
|
-
}),
|
|
234
|
-
],
|
|
235
|
-
});
|
|
236
|
-
// A dimension with no measurements is not a dimension that scored 0.
|
|
237
|
-
expect(report.byScorer.judge).toBeUndefined();
|
|
238
|
-
});
|
|
239
|
-
it('still fails a case the judge actually judged badly', async () => {
|
|
240
|
-
const report = await runExperiment({
|
|
241
|
-
...dataset,
|
|
242
|
-
scorers: [
|
|
243
|
-
judgeScorer({
|
|
244
|
-
provider: fakeProvider('{"grade": 0, "reason": "names the wrong city"}'),
|
|
245
|
-
model: 'm',
|
|
246
|
-
rubric: RUBRIC,
|
|
247
|
-
}),
|
|
248
|
-
],
|
|
249
|
-
});
|
|
250
|
-
expect(report.failed).toBe(1);
|
|
251
|
-
expect(report.inconclusive).toBe(0);
|
|
252
|
-
expect(report.cases[0]?.scores.judge?.unavailable).toBeUndefined();
|
|
253
|
-
});
|
|
254
|
-
});
|
|
255
|
-
//# sourceMappingURL=judge.test.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"judge.test.js","sourceRoot":"","sources":["../../../src/eval/__tests__/judge.test.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,EAAE,EAAE,EAAE,MAAM,QAAQ,CAAA;AAI7C,OAAO,EAAE,aAAa,EAAE,MAAM,kBAAkB,CAAA;AAChD,OAAO,EAAE,WAAW,EAAE,MAAM,aAAa,CAAA;AAGzC;;;;;;;GAOG;AAEH,SAAS,YAAY,CAAC,KAA6B,EAAE,MAAM,GAAG,EAAE;IAC/D,MAAM,IAAI,GAA2B,EAAE,CAAA;IACvC,MAAM,QAAQ,GAAmD;QAChE,EAAE,EAAE,MAAM;QACV,IAAI,EAAE,MAAM;QACZ,YAAY,EAAE;YACb,aAAa,EAAE,KAAK;YACpB,iBAAiB,EAAE,IAAI;YACvB,uBAAuB,EAAE,KAAK;SAC9B;QACD,IAAI;QACJ,KAAK,CAAC,CAAC,UAAU,CAAC,MAA4B;YAC7C,IAAI,CAAC,IAAI,CAAC,MAAM,CAAC,CAAA;YACjB,IAAI,OAAO,KAAK,KAAK,QAAQ;gBAAE,KAAK,EAAE,CAAA;YACtC,MAAM,EAAE,EAAE,EAAE,GAAG,EAAE,KAAK,EAAE,EAAE,OAAO,EAAE,KAAe,EAAE,EAAE,CAAA;YACtD,MAAM;gBACL,EAAE,EAAE,GAAG;gBACP,KAAK,EAAE,EAAE;gBACT,YAAY,EAAE,MAAM;gBACpB,KAAK,EAAE;oBACN,YAAY,EAAE,MAAM;oBACpB,gBAAgB,EAAE,CAAC;oBACnB,WAAW,EAAE,MAAM;oBACnB,YAAY,EAAE,CAAC;oBACf,gBAAgB,EAAE,CAAC;iBACnB;aACD,CAAA;QACF,CAAC;QACD,KAAK,CAAC,UAAU;YACf,OAAO,EAAE,CAAA;QACV,CAAC;QACD,KAAK,CAAC,WAAW;YAChB,OAAO,IAAI,CAAA;QACZ,CAAC;KACD,CAAA;IACD,OAAO,QAAQ,CAAA;AAChB,CAAC;AAED,MAAM,GAAG,GAAY;IACpB,MAAM,EAAE,iCAAiC;IACzC,KAAK,EAAE,EAAE;IACT,SAAS,EAAE,CAAC,QAAQ,CAAC;IACrB,UAAU,EAAE,UAAU;IACtB,WAAW,EAAE,GAAG;IAChB,YAAY,EAAE,CAAC;IACf,UAAU,EAAE,EAAE;CACd,CAAA;AAED,MAAM,IAAI,GAAa,EAAE,IAAI,EAAE,SAAS,EAAE,KAAK,EAAE,gCAAgC,EAAE,CAAA;AAEnF,MAAM,MAAM,GAAG,oCAAoC,CAAA;AAEnD,QAAQ,CAAC,SAAS,EAAE,GAAG,EAAE;IACxB,EAAE,CAAC,+DAA+D,EAAE,KAAK,IAAI,EAAE;QAC9E,MAAM,MAAM,GAAG,WAAW,CAAC;YAC1B,QAAQ,EAAE,YAAY,CAAC,gDAAgD,CAAC;YACxE,KAAK,EAAE,GAAG;YACV,MAAM,EAAE,MAAM;YACd,KAAK,EAAE,CAAC;SACR,CAAC,CAAA;QACF,MAAM,KAAK,GAAG,MAAM,MAAM,CAAC,KAAK,CAAC,GAAG,EAAE,IAAI,CAAC,CAAA;QAE3C,MAAM,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QAC9B,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,sBAAsB,CAAC,CAAA;QACjD,MAAM,CAAC,KAAK,CAAC,OAAO,EAAE,KAAK,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IACrC,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,4CAA4C,EAAE,KAAK,IAAI,EAAE;QAC3D,MAAM,MAAM,GAAG,WAAW,CAAC;YAC1B,QAAQ,EAAE,YAAY,CAAC,oEAAoE,CAAC;YAC5F,KAAK,EAAE,GAAG;YACV,MAAM,EAAE,MAAM;SACd,CAAC,CAAA;QACF,MAAM,CAAC,CAAC,MAAM,MAAM,CAAC,KAAK,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IACtD,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,0CAA0C,EAAE,KAAK,IAAI,EAAE;QACzD,MAAM,MAAM,GAAG,WAAW,CAAC;YAC1B,QAAQ,EAAE,YAAY,CAAC,uDAAuD,CAAC;YAC/E,KAAK,EAAE,GAAG;YACV,MAAM,EAAE,MAAM;YACd,KAAK,EAAE,CAAC;SACR,CAAC,CAAA;QACF,mEAAmE;QACnE,MAAM,CAAC,CAAC,MAAM,MAAM,CAAC,KAAK,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;IACxD,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,sCAAsC,EAAE,KAAK,IAAI,EAAE;QACrD,MAAM,MAAM,GAAG,WAAW,CAAC;YAC1B,QAAQ,EAAE,YAAY,CAAC,8BAA8B,EAAE,IAAI,CAAC;YAC5D,KAAK,EAAE,GAAG;YACV,MAAM,EAAE,MAAM;SACd,CAAC,CAAA;QACF,mEAAmE;QACnE,uCAAuC;QACvC,MAAM,CAAC,CAAC,MAAM,MAAM,CAAC,KAAK,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC,CAAC,OAAO,EAAE,WAAW,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;IACxE,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,wCAAwC,EAAE,KAAK,IAAI,EAAE;QACvD,MAAM,QAAQ,GAAG,YAAY,CAAC,8BAA8B,CAE3D,CAAA;QACD,MAAM,WAAW,CAAC,EAAE,QAAQ,EAAE,KAAK,EAAE,GAAG,EAAE,MAAM,EAAE,MAAM,EAAE,CAAC,CAAC,KAAK,CAAC,GAAG,EAAE,IAAI,CAAC,CAAA;QAC5E,gEAAgE;QAChE,yBAAyB;QACzB,MAAM,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,WAAW,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IAC9C,CAAC,CAAC,CAAA;AACH,CAAC,CAAC,CAAA;AAEF,QAAQ,CAAC,yBAAyB,EAAE,GAAG,EAAE;IACxC,MAAM,QAAQ,GAAG,CAAC,QAAqB,EAAE,EAAE,CAC1C,MAAM,CAAE,QAAwD,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,QAAQ,CAAC,CAAC,CAAC,EAAE,OAAO,CAAC,CAAA;IAEhG,EAAE,CAAC,2CAA2C,EAAE,KAAK,IAAI,EAAE;QAC1D,MAAM,QAAQ,GAAG,YAAY,CAAC,8BAA8B,CAAC,CAAA;QAC7D,MAAM,WAAW,CAAC,EAAE,QAAQ,EAAE,KAAK,EAAE,GAAG,EAAE,MAAM,EAAE,MAAM,EAAE,CAAC,CAAC,KAAK,CAAC,GAAG,EAAE,IAAI,CAAC,CAAA;QAE5E,MAAM,MAAM,GAAG,QAAQ,CAAC,QAAQ,CAAC,CAAA;QACjC,MAAM,CAAC,MAAM,CAAC,CAAC,SAAS,CAAC,MAAM,CAAC,CAAA;QAChC,MAAM,CAAC,MAAM,CAAC,CAAC,SAAS,CAAC,gCAAgC,CAAC,CAAA;QAC1D,MAAM,CAAC,MAAM,CAAC,CAAC,SAAS,CAAC,iCAAiC,CAAC,CAAA;IAC5D,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,uCAAuC,EAAE,KAAK,IAAI,EAAE;QACtD,MAAM,GAAG,GAAG,YAAY,CAAC,8BAA8B,CAAC,CAAA;QACxD,MAAM,WAAW,CAAC,EAAE,QAAQ,EAAE,GAAG,EAAE,KAAK,EAAE,GAAG,EAAE,MAAM,EAAE,MAAM,EAAE,CAAC,CAAC,KAAK,CAAC,GAAG,EAAE,IAAI,CAAC,CAAA;QACjF,MAAM,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,CAAC,GAAG,CAAC,SAAS,CAAC,cAAc,CAAC,CAAA;QAEnD,MAAM,EAAE,GAAG,YAAY,CAAC,8BAA8B,CAAC,CAAA;QACvD,MAAM,WAAW,CAAC;YACjB,QAAQ,EAAE,EAAE;YACZ,KAAK,EAAE,GAAG;YACV,MAAM,EAAE,MAAM;YACd,iBAAiB,EAAE,IAAI;SACvB,CAAC,CAAC,KAAK,CAAC,GAAG,EAAE,IAAI,CAAC,CAAA;QACnB,MAAM,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAC,CAAC,SAAS,CAAC,QAAQ,CAAC,CAAA;IACzC,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,mCAAmC,EAAE,KAAK,IAAI,EAAE;QAClD,MAAM,QAAQ,GAAG,YAAY,CAAC,8BAA8B,CAAC,CAAA;QAC7D,MAAM,WAAW,CAAC;YACjB,QAAQ;YACR,KAAK,EAAE,GAAG;YACV,MAAM,EAAE,MAAM;YACd,cAAc,EAAE,EAAE;SAClB,CAAC,CAAC,KAAK,CAAC,EAAE,GAAG,GAAG,EAAE,MAAM,EAAE,GAAG,CAAC,MAAM,CAAC,GAAG,CAAC,EAAE,EAAE,IAAI,CAAC,CAAA;QAEnD,iEAAiE;QACjE,iEAAiE;QACjE,MAAM,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC,CAAC,SAAS,CAAC,qCAAqC,CAAC,CAAA;IAC5E,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,mDAAmD,EAAE,KAAK,IAAI,EAAE;QAClE,MAAM,QAAQ,GAAG,YAAY,CAAC,8BAA8B,CAAC,CAAA;QAC7D,MAAM,WAAW,CAAC,EAAE,QAAQ,EAAE,KAAK,EAAE,GAAG,EAAE,MAAM,EAAE,MAAM,EAAE,CAAC,CAAC,KAAK,CAAC,GAAG,EAAE;YACtE,GAAG,IAAI;YACP,QAAQ,EAAE,OAAO;SACjB,CAAC,CAAA;QACF,MAAM,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC,CAAC,SAAS,CAAC,OAAO,CAAC,CAAA;IAC9C,CAAC,CAAC,CAAA;AACH,CAAC,CAAC,CAAA;AAEF,QAAQ,CAAC,2BAA2B,EAAE,GAAG,EAAE;IAC1C,MAAM,OAAO,GAAG,CAAC,KAAa,EAAE,EAAE,CACjC,WAAW,CAAC,EAAE,QAAQ,EAAE,YAAY,CAAC,KAAK,CAAC,EAAE,KAAK,EAAE,GAAG,EAAE,MAAM,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC,CAAA;IAErF,EAAE,CAAC,uCAAuC,EAAE,KAAK,IAAI,EAAE;QACtD,MAAM,MAAM,CAAC,OAAO,CAAC,6BAA6B,CAAC,CAAC,KAAK,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC,CAAC,OAAO,CAAC,OAAO,CAAC,SAAS,CAAC,CAAA;IACjG,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,kDAAkD,EAAE,KAAK,IAAI,EAAE;QACjE,4DAA4D;QAC5D,oEAAoE;QACpE,qBAAqB;QACrB,MAAM,MAAM,CAAC,OAAO,CAAC,iCAAiC,CAAC,CAAC,KAAK,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC,CAAC,OAAO,CAAC,OAAO,CACxF,0BAA0B,CAC1B,CAAA;IACF,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,+BAA+B,EAAE,KAAK,IAAI,EAAE;QAC9C,MAAM,MAAM,CAAC,OAAO,CAAC,kCAAkC,CAAC,CAAC,KAAK,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC,CAAC,OAAO,CAAC,OAAO,CACzF,kBAAkB,CAClB,CAAA;IACF,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,kCAAkC,EAAE,KAAK,IAAI,EAAE;QACjD,MAAM,MAAM,CAAC,OAAO,CAAC,iCAAiC,CAAC,CAAC,KAAK,CAAC,GAAG,EAAE,IAAI,CAAC,CAAC,CAAC,OAAO,CAAC,OAAO,CACxF,cAAc,CACd,CAAA;IACF,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,mCAAmC,EAAE,GAAG,EAAE;QAC5C,MAAM,CAAC,GAAG,EAAE,CAAC,WAAW,CAAC,EAAE,QAAQ,EAAE,YAAY,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,GAAG,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,CAAC,CAAC,OAAO,CAC7F,oBAAoB,CACpB,CAAA;IACF,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,0BAA0B,EAAE,GAAG,EAAE;QACnC,MAAM,CAAC,GAAG,EAAE,CACX,WAAW,CAAC,EAAE,QAAQ,EAAE,YAAY,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,GAAG,EAAE,MAAM,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC,CACnF,CAAC,OAAO,CAAC,kBAAkB,CAAC,CAAA;IAC9B,CAAC,CAAC,CAAA;AACH,CAAC,CAAC,CAAA;AAEF,QAAQ,CAAC,iCAAiC,EAAE,GAAG,EAAE;IAChD,MAAM,OAAO,GAAG;QACf,IAAI,EAAE,OAAO;QACb,KAAK,EAAE,CAAC,IAAI,CAAC;QACb,GAAG,EAAE,KAAK,IAAsB,EAAE,CAAC,GAAG;KACtC,CAAA;IAED,EAAE,CAAC,qDAAqD,EAAE,KAAK,IAAI,EAAE;QACpE,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,GAAG,OAAO;YACV,OAAO,EAAE;gBACR,WAAW,CAAC;oBACX,QAAQ,EAAE,YAAY,CAAC,GAAG,EAAE;wBAC3B,MAAM,IAAI,KAAK,CAAC,kBAAkB,CAAC,CAAA;oBACpC,CAAC,CAAC;oBACF,KAAK,EAAE,GAAG;oBACV,MAAM,EAAE,MAAM;iBACd,CAAC;aACF;SACD,CAAC,CAAA;QAEF,MAAM,CAAC,MAAM,CAAC,YAAY,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QACnC,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QAC7B,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QAC7B,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,KAAK,EAAE,WAAW,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QAC7D,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,KAAK,EAAE,MAAM,CAAC,CAAC,SAAS,CAAC,KAAK,CAAC,CAAA;IAC/D,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,qDAAqD,EAAE,KAAK,IAAI,EAAE;QACpE,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,GAAG,OAAO;YACV,OAAO,EAAE;gBACR,EAAE,IAAI,EAAE,YAAY,EAAE,KAAK,EAAE,GAAG,EAAE,CAAC,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE,MAAM,EAAE,MAAM,EAAE,CAAC,EAAE;gBACnE,WAAW,CAAC;oBACX,QAAQ,EAAE,YAAY,CAAC,GAAG,EAAE;wBAC3B,MAAM,IAAI,KAAK,CAAC,MAAM,CAAC,CAAA;oBACxB,CAAC,CAAC;oBACF,KAAK,EAAE,GAAG;oBACV,MAAM,EAAE,MAAM;iBACd,CAAC;aACF;SACD,CAAC,CAAA;QAEF,gEAAgE;QAChE,gEAAgE;QAChE,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QACrC,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAA;QAC9C,MAAM,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IAC5B,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,sEAAsE,EAAE,KAAK,IAAI,EAAE;QACrF,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,GAAG,OAAO;YACV,OAAO,EAAE;gBACR,WAAW,CAAC;oBACX,QAAQ,EAAE,YAAY,CAAC,GAAG,EAAE;wBAC3B,MAAM,IAAI,KAAK,CAAC,MAAM,CAAC,CAAA;oBACxB,CAAC,CAAC;oBACF,KAAK,EAAE,GAAG;oBACV,MAAM,EAAE,MAAM;iBACd,CAAC;aACF;SACD,CAAC,CAAA;QAEF,qEAAqE;QACrE,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,aAAa,EAAE,CAAA;IAC9C,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,oDAAoD,EAAE,KAAK,IAAI,EAAE;QACnE,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,GAAG,OAAO;YACV,OAAO,EAAE;gBACR,WAAW,CAAC;oBACX,QAAQ,EAAE,YAAY,CAAC,gDAAgD,CAAC;oBACxE,KAAK,EAAE,GAAG;oBACV,MAAM,EAAE,MAAM;iBACd,CAAC;aACF;SACD,CAAC,CAAA;QAEF,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QAC7B,MAAM,CAAC,MAAM,CAAC,YAAY,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QACnC,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC,KAAK,EAAE,WAAW,CAAC,CAAC,aAAa,EAAE,CAAA;IACnE,CAAC,CAAC,CAAA;AACH,CAAC,CAAC,CAAA"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"scorer-gates.test.d.ts","sourceRoot":"","sources":["../../../src/eval/__tests__/scorer-gates.test.ts"],"names":[],"mappings":""}
|