@namzu/sdk 2.0.0 → 3.0.0
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 +2265 -0
- package/README.md +49 -53
- package/dist/__tests__/default-path-conformance.test.d.ts +2 -0
- package/dist/__tests__/default-path-conformance.test.d.ts.map +1 -0
- package/dist/__tests__/default-path-conformance.test.js +262 -0
- package/dist/__tests__/default-path-conformance.test.js.map +1 -0
- package/dist/__tests__/shipped-defaults.test.d.ts +2 -0
- package/dist/__tests__/shipped-defaults.test.d.ts.map +1 -0
- package/dist/__tests__/shipped-defaults.test.js +97 -0
- package/dist/__tests__/shipped-defaults.test.js.map +1 -0
- package/dist/advisory/__tests__/budget-enforcement.test.d.ts +2 -0
- package/dist/advisory/__tests__/budget-enforcement.test.d.ts.map +1 -0
- package/dist/advisory/__tests__/budget-enforcement.test.js +159 -0
- package/dist/advisory/__tests__/budget-enforcement.test.js.map +1 -0
- package/dist/advisory/__tests__/structured-response.test.d.ts +2 -0
- package/dist/advisory/__tests__/structured-response.test.d.ts.map +1 -0
- package/dist/advisory/__tests__/structured-response.test.js +99 -0
- package/dist/advisory/__tests__/structured-response.test.js.map +1 -0
- package/dist/advisory/budget.d.ts +15 -0
- package/dist/advisory/budget.d.ts.map +1 -0
- package/dist/advisory/budget.js +21 -0
- package/dist/advisory/budget.js.map +1 -0
- package/dist/advisory/context.d.ts +2 -0
- package/dist/advisory/context.d.ts.map +1 -1
- package/dist/advisory/context.js +16 -0
- package/dist/advisory/context.js.map +1 -1
- package/dist/advisory/executor.d.ts +14 -11
- package/dist/advisory/executor.d.ts.map +1 -1
- package/dist/advisory/executor.js +36 -24
- package/dist/advisory/executor.js.map +1 -1
- package/dist/advisory/executor.test.d.ts +8 -6
- package/dist/advisory/executor.test.d.ts.map +1 -1
- package/dist/advisory/executor.test.js +12 -8
- package/dist/advisory/executor.test.js.map +1 -1
- package/dist/advisory/index.d.ts +2 -0
- package/dist/advisory/index.d.ts.map +1 -1
- package/dist/advisory/index.js +2 -0
- package/dist/advisory/index.js.map +1 -1
- package/dist/advisory/parse.d.ts +23 -0
- package/dist/advisory/parse.d.ts.map +1 -0
- package/dist/advisory/parse.js +56 -0
- package/dist/advisory/parse.js.map +1 -0
- package/dist/agents/AbstractAgent.d.ts +48 -0
- package/dist/agents/AbstractAgent.d.ts.map +1 -1
- package/dist/agents/AbstractAgent.js +77 -0
- package/dist/agents/AbstractAgent.js.map +1 -1
- package/dist/agents/PipelineAgent.d.ts +10 -0
- package/dist/agents/PipelineAgent.d.ts.map +1 -1
- package/dist/agents/PipelineAgent.js +12 -0
- package/dist/agents/PipelineAgent.js.map +1 -1
- package/dist/agents/ReactiveAgent.d.ts +10 -0
- package/dist/agents/ReactiveAgent.d.ts.map +1 -1
- package/dist/agents/ReactiveAgent.js +40 -0
- package/dist/agents/ReactiveAgent.js.map +1 -1
- package/dist/agents/RouterAgent.d.ts +10 -0
- package/dist/agents/RouterAgent.d.ts.map +1 -1
- package/dist/agents/RouterAgent.js +23 -2
- package/dist/agents/RouterAgent.js.map +1 -1
- package/dist/agents/SupervisorAgent.d.ts +11 -1
- package/dist/agents/SupervisorAgent.d.ts.map +1 -1
- package/dist/agents/SupervisorAgent.js +23 -1
- package/dist/agents/SupervisorAgent.js.map +1 -1
- package/dist/agents/__tests__/idempotency-key.test.d.ts +2 -0
- package/dist/agents/__tests__/idempotency-key.test.d.ts.map +1 -0
- package/dist/agents/__tests__/idempotency-key.test.js +149 -0
- package/dist/agents/__tests__/idempotency-key.test.js.map +1 -0
- package/dist/agents/__tests__/invocation-lock.test.d.ts +2 -0
- package/dist/agents/__tests__/invocation-lock.test.d.ts.map +1 -0
- package/dist/agents/__tests__/invocation-lock.test.js +126 -0
- package/dist/agents/__tests__/invocation-lock.test.js.map +1 -0
- package/dist/agents/__tests__/reachability.test.d.ts +2 -0
- package/dist/agents/__tests__/reachability.test.d.ts.map +1 -0
- package/dist/agents/__tests__/reachability.test.js +173 -0
- package/dist/agents/__tests__/reachability.test.js.map +1 -0
- package/dist/agents/__tests__/supervisor-ledger.test.js +1 -1
- package/dist/agents/__tests__/supervisor-ledger.test.js.map +1 -1
- package/dist/agents/index.d.ts +1 -1
- package/dist/agents/index.d.ts.map +1 -1
- package/dist/agents/lock.d.ts +0 -1
- package/dist/agents/lock.d.ts.map +1 -1
- package/dist/agents/lock.js.map +1 -1
- package/dist/bridge/a2a/late-events.test.d.ts +2 -0
- package/dist/bridge/a2a/late-events.test.d.ts.map +1 -0
- package/dist/bridge/a2a/late-events.test.js +70 -0
- package/dist/bridge/a2a/late-events.test.js.map +1 -0
- package/dist/bridge/a2a/mapper.d.ts.map +1 -1
- package/dist/bridge/a2a/mapper.js +55 -3
- package/dist/bridge/a2a/mapper.js.map +1 -1
- package/dist/bridge/a2a/mapper.test.js +1 -1
- package/dist/bridge/a2a/mapper.test.js.map +1 -1
- package/dist/bridge/a2a/message.d.ts.map +1 -1
- package/dist/bridge/a2a/message.js +5 -1
- package/dist/bridge/a2a/message.js.map +1 -1
- package/dist/bridge/sse/late-events.test.d.ts +2 -0
- package/dist/bridge/sse/late-events.test.d.ts.map +1 -0
- package/dist/bridge/sse/late-events.test.js +163 -0
- package/dist/bridge/sse/late-events.test.js.map +1 -0
- package/dist/bridge/sse/mapper.d.ts.map +1 -1
- package/dist/bridge/sse/mapper.js +100 -0
- package/dist/bridge/sse/mapper.js.map +1 -1
- package/dist/compaction/__tests__/cleared-result-recovery.test.d.ts +2 -0
- package/dist/compaction/__tests__/cleared-result-recovery.test.d.ts.map +1 -0
- package/dist/compaction/__tests__/cleared-result-recovery.test.js +101 -0
- package/dist/compaction/__tests__/cleared-result-recovery.test.js.map +1 -0
- package/dist/compaction/__tests__/context-window.test.d.ts +2 -0
- package/dist/compaction/__tests__/context-window.test.d.ts.map +1 -0
- package/dist/compaction/__tests__/context-window.test.js +62 -0
- package/dist/compaction/__tests__/context-window.test.js.map +1 -0
- package/dist/compaction/__tests__/dangling.test.js +16 -5
- package/dist/compaction/__tests__/dangling.test.js.map +1 -1
- package/dist/compaction/__tests__/lossiness.test.d.ts +2 -0
- package/dist/compaction/__tests__/lossiness.test.d.ts.map +1 -0
- package/dist/compaction/__tests__/lossiness.test.js +163 -0
- package/dist/compaction/__tests__/lossiness.test.js.map +1 -0
- package/dist/compaction/__tests__/state-across-resume.test.d.ts +2 -0
- package/dist/compaction/__tests__/state-across-resume.test.d.ts.map +1 -0
- package/dist/compaction/__tests__/state-across-resume.test.js +88 -0
- package/dist/compaction/__tests__/state-across-resume.test.js.map +1 -0
- package/dist/compaction/__tests__/tool-result-editing.test.d.ts +2 -0
- package/dist/compaction/__tests__/tool-result-editing.test.d.ts.map +1 -0
- package/dist/compaction/__tests__/tool-result-editing.test.js +184 -0
- package/dist/compaction/__tests__/tool-result-editing.test.js.map +1 -0
- package/dist/compaction/__tests__/trim-opens-on-user.test.d.ts +2 -0
- package/dist/compaction/__tests__/trim-opens-on-user.test.d.ts.map +1 -0
- package/dist/compaction/__tests__/trim-opens-on-user.test.js +109 -0
- package/dist/compaction/__tests__/trim-opens-on-user.test.js.map +1 -0
- package/dist/compaction/__tests__/verifier-model.test.d.ts +2 -0
- package/dist/compaction/__tests__/verifier-model.test.d.ts.map +1 -0
- package/dist/compaction/__tests__/verifier-model.test.js +58 -0
- package/dist/compaction/__tests__/verifier-model.test.js.map +1 -0
- package/dist/compaction/context-window.d.ts +44 -0
- package/dist/compaction/context-window.d.ts.map +1 -0
- package/dist/compaction/context-window.js +97 -0
- package/dist/compaction/context-window.js.map +1 -0
- package/dist/compaction/dangling.js +48 -1
- package/dist/compaction/dangling.js.map +1 -1
- package/dist/compaction/extractor.d.ts.map +1 -1
- package/dist/compaction/extractor.js +55 -1
- package/dist/compaction/extractor.js.map +1 -1
- package/dist/compaction/index.d.ts +5 -0
- package/dist/compaction/index.d.ts.map +1 -1
- package/dist/compaction/index.js +3 -0
- package/dist/compaction/index.js.map +1 -1
- package/dist/compaction/manager.d.ts +25 -0
- package/dist/compaction/manager.d.ts.map +1 -1
- package/dist/compaction/manager.js +42 -8
- package/dist/compaction/manager.js.map +1 -1
- package/dist/compaction/managers/structured.d.ts.map +1 -1
- package/dist/compaction/managers/structured.js +7 -3
- package/dist/compaction/managers/structured.js.map +1 -1
- package/dist/compaction/retention.d.ts +15 -0
- package/dist/compaction/retention.d.ts.map +1 -0
- package/dist/compaction/retention.js +89 -0
- package/dist/compaction/retention.js.map +1 -0
- package/dist/compaction/serializer.d.ts.map +1 -1
- package/dist/compaction/serializer.js +28 -11
- package/dist/compaction/serializer.js.map +1 -1
- package/dist/compaction/tool-result-editing.d.ts +54 -0
- package/dist/compaction/tool-result-editing.d.ts.map +1 -0
- package/dist/compaction/tool-result-editing.js +164 -0
- package/dist/compaction/tool-result-editing.js.map +1 -0
- package/dist/compaction/types.d.ts +10 -0
- package/dist/compaction/types.d.ts.map +1 -1
- package/dist/compaction/verifier.d.ts +20 -1
- package/dist/compaction/verifier.d.ts.map +1 -1
- package/dist/compaction/verifier.js +11 -2
- package/dist/compaction/verifier.js.map +1 -1
- package/dist/compaction/wire.d.ts +54 -0
- package/dist/compaction/wire.d.ts.map +1 -0
- package/dist/compaction/wire.js +45 -0
- package/dist/compaction/wire.js.map +1 -0
- package/dist/config/runtime.d.ts +161 -45
- package/dist/config/runtime.d.ts.map +1 -1
- package/dist/config/runtime.js +61 -19
- package/dist/config/runtime.js.map +1 -1
- package/dist/connector/builtins/http.d.ts.map +1 -1
- package/dist/connector/builtins/http.js +14 -1
- package/dist/connector/builtins/http.js.map +1 -1
- package/dist/connector/builtins/http.test.js +12 -0
- package/dist/connector/builtins/http.test.js.map +1 -1
- package/dist/connector/mcp/__tests__/discovery-policy.test.d.ts +2 -0
- package/dist/connector/mcp/__tests__/discovery-policy.test.d.ts.map +1 -0
- package/dist/connector/mcp/__tests__/discovery-policy.test.js +109 -0
- package/dist/connector/mcp/__tests__/discovery-policy.test.js.map +1 -0
- package/dist/connector/mcp/__tests__/list-pagination.test.d.ts +2 -0
- package/dist/connector/mcp/__tests__/list-pagination.test.d.ts.map +1 -0
- package/dist/connector/mcp/__tests__/list-pagination.test.js +81 -0
- package/dist/connector/mcp/__tests__/list-pagination.test.js.map +1 -0
- package/dist/connector/mcp/__tests__/policy.test.d.ts +2 -0
- package/dist/connector/mcp/__tests__/policy.test.d.ts.map +1 -0
- package/dist/connector/mcp/__tests__/policy.test.js +86 -0
- package/dist/connector/mcp/__tests__/policy.test.js.map +1 -0
- package/dist/connector/mcp/__tests__/protocol-negotiation.test.d.ts +2 -0
- package/dist/connector/mcp/__tests__/protocol-negotiation.test.d.ts.map +1 -0
- package/dist/connector/mcp/__tests__/protocol-negotiation.test.js +81 -0
- package/dist/connector/mcp/__tests__/protocol-negotiation.test.js.map +1 -0
- package/dist/connector/mcp/__tests__/schema-fidelity.test.d.ts +2 -0
- package/dist/connector/mcp/__tests__/schema-fidelity.test.d.ts.map +1 -0
- package/dist/connector/mcp/__tests__/schema-fidelity.test.js +206 -0
- package/dist/connector/mcp/__tests__/schema-fidelity.test.js.map +1 -0
- package/dist/connector/mcp/__tests__/structured-result.test.d.ts +2 -0
- package/dist/connector/mcp/__tests__/structured-result.test.d.ts.map +1 -0
- package/dist/connector/mcp/__tests__/structured-result.test.js +112 -0
- package/dist/connector/mcp/__tests__/structured-result.test.js.map +1 -0
- package/dist/connector/mcp/adapter.d.ts +14 -0
- package/dist/connector/mcp/adapter.d.ts.map +1 -1
- package/dist/connector/mcp/adapter.js +292 -18
- package/dist/connector/mcp/adapter.js.map +1 -1
- package/dist/connector/mcp/client.d.ts +38 -0
- package/dist/connector/mcp/client.d.ts.map +1 -1
- package/dist/connector/mcp/client.js +138 -12
- package/dist/connector/mcp/client.js.map +1 -1
- package/dist/connector/mcp/client.test.d.ts +2 -0
- package/dist/connector/mcp/client.test.d.ts.map +1 -0
- package/dist/connector/mcp/client.test.js +105 -0
- package/dist/connector/mcp/client.test.js.map +1 -0
- package/dist/connector/mcp/discovery.d.ts +32 -1
- package/dist/connector/mcp/discovery.d.ts.map +1 -1
- package/dist/connector/mcp/discovery.js +41 -4
- package/dist/connector/mcp/discovery.js.map +1 -1
- package/dist/connector/mcp/http-sse.d.ts.map +1 -1
- package/dist/connector/mcp/http-sse.js +15 -1
- package/dist/connector/mcp/http-sse.js.map +1 -1
- package/dist/connector/mcp/index.d.ts +3 -0
- package/dist/connector/mcp/index.d.ts.map +1 -1
- package/dist/connector/mcp/index.js +1 -0
- package/dist/connector/mcp/index.js.map +1 -1
- package/dist/connector/mcp/policy.d.ts +57 -0
- package/dist/connector/mcp/policy.d.ts.map +1 -0
- package/dist/connector/mcp/policy.js +84 -0
- package/dist/connector/mcp/policy.js.map +1 -0
- package/dist/connector/mcp/schema-refs.d.ts +26 -0
- package/dist/connector/mcp/schema-refs.d.ts.map +1 -0
- package/dist/connector/mcp/schema-refs.js +111 -0
- package/dist/connector/mcp/schema-refs.js.map +1 -0
- package/dist/constants/agent/index.d.ts.map +1 -1
- package/dist/constants/agent/index.js +3 -0
- package/dist/constants/agent/index.js.map +1 -1
- package/dist/constants/compaction/index.js +1 -1
- package/dist/constants/compaction/index.js.map +1 -1
- package/dist/constants/continuation.d.ts +4 -4
- package/dist/constants/continuation.js +4 -4
- package/dist/constants/mcp/index.d.ts +31 -0
- package/dist/constants/mcp/index.d.ts.map +1 -1
- package/dist/constants/mcp/index.js +31 -0
- package/dist/constants/mcp/index.js.map +1 -1
- package/dist/constants/plugin/index.d.ts +23 -2
- package/dist/constants/plugin/index.d.ts.map +1 -1
- package/dist/constants/plugin/index.js +23 -2
- package/dist/constants/plugin/index.js.map +1 -1
- package/dist/constants/sandbox/index.d.ts +2 -3
- package/dist/constants/sandbox/index.d.ts.map +1 -1
- package/dist/constants/sandbox/index.js +6 -5
- package/dist/constants/sandbox/index.js.map +1 -1
- package/dist/constants/telemetry/index.d.ts +7 -0
- package/dist/constants/telemetry/index.d.ts.map +1 -1
- package/dist/constants/telemetry/index.js +7 -0
- package/dist/constants/telemetry/index.js.map +1 -1
- package/dist/constants/tools/index.d.ts +16 -0
- package/dist/constants/tools/index.d.ts.map +1 -1
- package/dist/constants/tools/index.js +16 -0
- package/dist/constants/tools/index.js.map +1 -1
- package/dist/contracts/a2a.d.ts +94 -94
- package/dist/contracts/api.d.ts +40 -2
- package/dist/contracts/api.d.ts.map +1 -1
- package/dist/contracts/run-status.d.ts +17 -0
- package/dist/contracts/run-status.d.ts.map +1 -0
- package/dist/contracts/run-status.js +41 -0
- package/dist/contracts/run-status.js.map +1 -0
- package/dist/contracts/schemas.d.ts +6 -6
- package/dist/eval/__tests__/case-deadline.test.d.ts +2 -0
- package/dist/eval/__tests__/case-deadline.test.d.ts.map +1 -0
- package/dist/eval/__tests__/case-deadline.test.js +128 -0
- package/dist/eval/__tests__/case-deadline.test.js.map +1 -0
- package/dist/eval/__tests__/end-to-end.test.d.ts +2 -0
- package/dist/eval/__tests__/end-to-end.test.d.ts.map +1 -0
- package/dist/eval/__tests__/end-to-end.test.js +223 -0
- package/dist/eval/__tests__/end-to-end.test.js.map +1 -0
- package/dist/eval/__tests__/harness-honesty.test.d.ts +2 -0
- package/dist/eval/__tests__/harness-honesty.test.d.ts.map +1 -0
- package/dist/eval/__tests__/harness-honesty.test.js +85 -0
- package/dist/eval/__tests__/harness-honesty.test.js.map +1 -0
- package/dist/eval/__tests__/harness.test.d.ts +2 -0
- package/dist/eval/__tests__/harness.test.d.ts.map +1 -0
- package/dist/eval/__tests__/harness.test.js +207 -0
- package/dist/eval/__tests__/harness.test.js.map +1 -0
- package/dist/eval/__tests__/judge.test.d.ts +2 -0
- package/dist/eval/__tests__/judge.test.d.ts.map +1 -0
- package/dist/eval/__tests__/judge.test.js +255 -0
- package/dist/eval/__tests__/judge.test.js.map +1 -0
- package/dist/eval/__tests__/scorer-gates.test.d.ts +2 -0
- package/dist/eval/__tests__/scorer-gates.test.d.ts.map +1 -0
- package/dist/eval/__tests__/scorer-gates.test.js +136 -0
- package/dist/eval/__tests__/scorer-gates.test.js.map +1 -0
- package/dist/eval/experiment.d.ts +54 -0
- package/dist/eval/experiment.d.ts.map +1 -0
- package/dist/eval/experiment.js +263 -0
- package/dist/eval/experiment.js.map +1 -0
- package/dist/eval/from-run.d.ts +30 -0
- package/dist/eval/from-run.d.ts.map +1 -0
- package/dist/eval/from-run.js +46 -0
- package/dist/eval/from-run.js.map +1 -0
- package/dist/eval/index.d.ts +8 -0
- package/dist/eval/index.d.ts.map +1 -0
- package/dist/eval/index.js +5 -0
- package/dist/eval/index.js.map +1 -0
- package/dist/eval/judge.d.ts +63 -0
- package/dist/eval/judge.d.ts.map +1 -0
- package/dist/eval/judge.js +136 -0
- package/dist/eval/judge.js.map +1 -0
- package/dist/eval/scorers.d.ts +40 -0
- package/dist/eval/scorers.d.ts.map +1 -0
- package/dist/eval/scorers.js +151 -0
- package/dist/eval/scorers.js.map +1 -0
- package/dist/eval/types.d.ts +150 -0
- package/dist/eval/types.d.ts.map +1 -0
- package/dist/eval/types.js +2 -0
- package/dist/eval/types.js.map +1 -0
- package/dist/execution/local.d.ts.map +1 -1
- package/dist/execution/local.js +6 -1
- package/dist/execution/local.js.map +1 -1
- package/dist/execution/local.test.d.ts +2 -0
- package/dist/execution/local.test.d.ts.map +1 -0
- package/dist/execution/local.test.js +37 -0
- package/dist/execution/local.test.js.map +1 -0
- package/dist/gateway/__tests__/list-survives-eviction.test.d.ts +2 -0
- package/dist/gateway/__tests__/list-survives-eviction.test.d.ts.map +1 -0
- package/dist/gateway/__tests__/list-survives-eviction.test.js +102 -0
- package/dist/gateway/__tests__/list-survives-eviction.test.js.map +1 -0
- package/dist/gateway/local.d.ts +42 -2
- package/dist/gateway/local.d.ts.map +1 -1
- package/dist/gateway/local.js +110 -3
- package/dist/gateway/local.js.map +1 -1
- package/dist/manager/agent/__tests__/dispose-cancels.test.d.ts +2 -0
- package/dist/manager/agent/__tests__/dispose-cancels.test.d.ts.map +1 -0
- package/dist/manager/agent/__tests__/dispose-cancels.test.js +88 -0
- package/dist/manager/agent/__tests__/dispose-cancels.test.js.map +1 -0
- package/dist/manager/agent/__tests__/lifecycle.test.js +230 -0
- package/dist/manager/agent/__tests__/lifecycle.test.js.map +1 -1
- package/dist/manager/agent/lifecycle.d.ts +35 -0
- package/dist/manager/agent/lifecycle.d.ts.map +1 -1
- package/dist/manager/agent/lifecycle.js +117 -7
- package/dist/manager/agent/lifecycle.js.map +1 -1
- package/dist/manager/run/persistence.d.ts +90 -1
- package/dist/manager/run/persistence.d.ts.map +1 -1
- package/dist/manager/run/persistence.js +120 -0
- package/dist/manager/run/persistence.js.map +1 -1
- package/dist/plugin/__tests__/enable-contributions.test.js +3 -3
- package/dist/plugin/__tests__/enable-contributions.test.js.map +1 -1
- package/dist/plugin/__tests__/hook-ordering.test.d.ts +2 -0
- package/dist/plugin/__tests__/hook-ordering.test.d.ts.map +1 -0
- package/dist/plugin/__tests__/hook-ordering.test.js +227 -0
- package/dist/plugin/__tests__/hook-ordering.test.js.map +1 -0
- package/dist/plugin/__tests__/install-time-refusal.test.d.ts +2 -0
- package/dist/plugin/__tests__/install-time-refusal.test.d.ts.map +1 -0
- package/dist/plugin/__tests__/install-time-refusal.test.js +49 -0
- package/dist/plugin/__tests__/install-time-refusal.test.js.map +1 -0
- package/dist/plugin/__tests__/lifecycle.test.js +95 -68
- package/dist/plugin/__tests__/lifecycle.test.js.map +1 -1
- package/dist/plugin/lifecycle.d.ts +15 -1
- package/dist/plugin/lifecycle.d.ts.map +1 -1
- package/dist/plugin/lifecycle.js +67 -20
- package/dist/plugin/lifecycle.js.map +1 -1
- package/dist/plugin/loader.d.ts +15 -0
- package/dist/plugin/loader.d.ts.map +1 -1
- package/dist/plugin/loader.js +33 -1
- package/dist/plugin/loader.js.map +1 -1
- package/dist/probe/registry.d.ts.map +1 -1
- package/dist/probe/registry.js +19 -1
- package/dist/probe/registry.js.map +1 -1
- package/dist/probe/registry.test.d.ts +9 -3
- package/dist/probe/registry.test.d.ts.map +1 -1
- package/dist/probe/registry.test.js +44 -6
- package/dist/probe/registry.test.js.map +1 -1
- package/dist/provider/__tests__/mock-script.test.d.ts +2 -0
- package/dist/provider/__tests__/mock-script.test.d.ts.map +1 -0
- package/dist/provider/__tests__/mock-script.test.js +151 -0
- package/dist/provider/__tests__/mock-script.test.js.map +1 -0
- package/dist/provider/__tests__/retry-visibility.test.d.ts +2 -0
- package/dist/provider/__tests__/retry-visibility.test.d.ts.map +1 -0
- package/dist/provider/__tests__/retry-visibility.test.js +137 -0
- package/dist/provider/__tests__/retry-visibility.test.js.map +1 -0
- package/dist/provider/__tests__/retry.test.d.ts +2 -0
- package/dist/provider/__tests__/retry.test.d.ts.map +1 -0
- package/dist/provider/__tests__/retry.test.js +259 -0
- package/dist/provider/__tests__/retry.test.js.map +1 -0
- package/dist/provider/capabilities.d.ts +1 -0
- package/dist/provider/capabilities.d.ts.map +1 -1
- package/dist/provider/capabilities.js +2 -0
- package/dist/provider/capabilities.js.map +1 -1
- package/dist/provider/collect.d.ts +1 -1
- package/dist/provider/collect.js +1 -1
- package/dist/provider/collect.test.d.ts +1 -1
- package/dist/provider/collect.test.js +1 -1
- package/dist/provider/index.d.ts +3 -0
- package/dist/provider/index.d.ts.map +1 -1
- package/dist/provider/index.js +2 -0
- package/dist/provider/index.js.map +1 -1
- package/dist/provider/mock-register.d.ts.map +1 -1
- package/dist/provider/mock-register.js +5 -2
- package/dist/provider/mock-register.js.map +1 -1
- package/dist/provider/mock.d.ts +35 -5
- package/dist/provider/mock.d.ts.map +1 -1
- package/dist/provider/mock.js +104 -32
- package/dist/provider/mock.js.map +1 -1
- package/dist/provider/retry.d.ts +42 -0
- package/dist/provider/retry.d.ts.map +1 -0
- package/dist/provider/retry.js +161 -0
- package/dist/provider/retry.js.map +1 -0
- package/dist/public-runtime.d.ts +26 -7
- package/dist/public-runtime.d.ts.map +1 -1
- package/dist/public-runtime.js +50 -7
- package/dist/public-runtime.js.map +1 -1
- package/dist/public-types.d.ts +5 -1
- package/dist/public-types.d.ts.map +1 -1
- package/dist/rag/__tests__/retrieval-math.test.d.ts +2 -0
- package/dist/rag/__tests__/retrieval-math.test.d.ts.map +1 -0
- package/dist/rag/__tests__/retrieval-math.test.js +46 -0
- package/dist/rag/__tests__/retrieval-math.test.js.map +1 -0
- package/dist/rag/chunking.d.ts +12 -0
- package/dist/rag/chunking.d.ts.map +1 -1
- package/dist/rag/chunking.js +32 -1
- package/dist/rag/chunking.js.map +1 -1
- package/dist/rag/embedding.d.ts +4 -4
- package/dist/rag/embedding.d.ts.map +1 -1
- package/dist/rag/embedding.js +23 -3
- package/dist/rag/embedding.js.map +1 -1
- package/dist/rag/embedding.test.d.ts +1 -1
- package/dist/rag/embedding.test.js +59 -10
- package/dist/rag/embedding.test.js.map +1 -1
- package/dist/rag/index.d.ts +1 -1
- package/dist/rag/index.d.ts.map +1 -1
- package/dist/rag/index.js +1 -1
- package/dist/rag/index.js.map +1 -1
- package/dist/rag/retriever.d.ts +0 -1
- package/dist/rag/retriever.d.ts.map +1 -1
- package/dist/rag/retriever.js +75 -22
- package/dist/rag/retriever.js.map +1 -1
- package/dist/rag/vector-store.test.d.ts +1 -1
- package/dist/rag/vector-store.test.js +2 -2
- package/dist/rag/vector-store.test.js.map +1 -1
- package/dist/registry/ManagedRegistry.test.d.ts +1 -1
- package/dist/registry/ManagedRegistry.test.js +1 -1
- package/dist/registry/Registry.test.d.ts +1 -1
- package/dist/registry/Registry.test.js +1 -1
- package/dist/registry/connector/definitions.test.d.ts +1 -1
- package/dist/registry/connector/definitions.test.js +1 -1
- package/dist/registry/tool/__tests__/schema.test.d.ts +2 -0
- package/dist/registry/tool/__tests__/schema.test.d.ts.map +1 -0
- package/dist/registry/tool/__tests__/schema.test.js +176 -0
- package/dist/registry/tool/__tests__/schema.test.js.map +1 -0
- package/dist/registry/tool/__tests__/tool-name-validation.test.d.ts +2 -0
- package/dist/registry/tool/__tests__/tool-name-validation.test.d.ts.map +1 -0
- package/dist/registry/tool/__tests__/tool-name-validation.test.js +70 -0
- package/dist/registry/tool/__tests__/tool-name-validation.test.js.map +1 -0
- package/dist/registry/tool/execute.d.ts +37 -0
- package/dist/registry/tool/execute.d.ts.map +1 -1
- package/dist/registry/tool/execute.js +91 -21
- package/dist/registry/tool/execute.js.map +1 -1
- package/dist/registry/tool/schema.d.ts +26 -0
- package/dist/registry/tool/schema.d.ts.map +1 -0
- package/dist/registry/tool/schema.js +77 -0
- package/dist/registry/tool/schema.js.map +1 -0
- package/dist/registry/toolset/catalog.d.ts.map +1 -1
- package/dist/registry/toolset/catalog.js +0 -1
- package/dist/registry/toolset/catalog.js.map +1 -1
- package/dist/registry/toolset/catalog.test.js +0 -1
- package/dist/registry/toolset/catalog.test.js.map +1 -1
- package/dist/run/reporter.d.ts.map +1 -1
- package/dist/run/reporter.js +76 -0
- package/dist/run/reporter.js.map +1 -1
- package/dist/runtime/bidi/__tests__/session.test.d.ts +2 -0
- package/dist/runtime/bidi/__tests__/session.test.d.ts.map +1 -0
- package/dist/runtime/bidi/__tests__/session.test.js +201 -0
- package/dist/runtime/bidi/__tests__/session.test.js.map +1 -0
- package/dist/runtime/bidi/index.d.ts +5 -0
- package/dist/runtime/bidi/index.d.ts.map +1 -0
- package/dist/runtime/bidi/index.js +3 -0
- package/dist/runtime/bidi/index.js.map +1 -0
- package/dist/runtime/bidi/mock.d.ts +34 -0
- package/dist/runtime/bidi/mock.d.ts.map +1 -0
- package/dist/runtime/bidi/mock.js +60 -0
- package/dist/runtime/bidi/mock.js.map +1 -0
- package/dist/runtime/bidi/session.d.ts +44 -0
- package/dist/runtime/bidi/session.d.ts.map +1 -0
- package/dist/runtime/bidi/session.js +154 -0
- package/dist/runtime/bidi/session.js.map +1 -0
- package/dist/runtime/decision/parser.d.ts.map +1 -1
- package/dist/runtime/decision/parser.js +8 -1
- package/dist/runtime/decision/parser.js.map +1 -1
- package/dist/runtime/decision/parser.test.d.ts +2 -0
- package/dist/runtime/decision/parser.test.d.ts.map +1 -0
- package/dist/runtime/decision/parser.test.js +37 -0
- package/dist/runtime/decision/parser.test.js.map +1 -0
- package/dist/runtime/query/__tests__/answer-review.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/answer-review.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/answer-review.test.js +141 -0
- package/dist/runtime/query/__tests__/answer-review.test.js.map +1 -0
- package/dist/runtime/query/__tests__/capability-negotiation.test.js +24 -111
- package/dist/runtime/query/__tests__/capability-negotiation.test.js.map +1 -1
- package/dist/runtime/query/__tests__/checkpoint-store.test.js +12 -44
- package/dist/runtime/query/__tests__/checkpoint-store.test.js.map +1 -1
- package/dist/runtime/query/__tests__/checkpoint.test.js +2 -10
- package/dist/runtime/query/__tests__/checkpoint.test.js.map +1 -1
- package/dist/runtime/query/__tests__/citations.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/citations.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/citations.test.js +85 -0
- package/dist/runtime/query/__tests__/citations.test.js.map +1 -0
- package/dist/runtime/query/__tests__/content-budget.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/content-budget.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/content-budget.test.js +69 -0
- package/dist/runtime/query/__tests__/content-budget.test.js.map +1 -0
- package/dist/runtime/query/__tests__/context.test.js +3 -2
- package/dist/runtime/query/__tests__/context.test.js.map +1 -1
- package/dist/runtime/query/__tests__/deferred-tools.test.js +21 -130
- package/dist/runtime/query/__tests__/deferred-tools.test.js.map +1 -1
- package/dist/runtime/query/__tests__/delegation-resume.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/delegation-resume.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/delegation-resume.test.js +111 -0
- package/dist/runtime/query/__tests__/delegation-resume.test.js.map +1 -0
- package/dist/runtime/query/__tests__/document-attachments.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/document-attachments.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/document-attachments.test.js +92 -0
- package/dist/runtime/query/__tests__/document-attachments.test.js.map +1 -0
- package/dist/runtime/query/__tests__/durable-park-and-trace.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/durable-park-and-trace.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/durable-park-and-trace.test.js +194 -0
- package/dist/runtime/query/__tests__/durable-park-and-trace.test.js.map +1 -0
- package/dist/runtime/query/__tests__/durable-question-park.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/durable-question-park.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/durable-question-park.test.js +253 -0
- package/dist/runtime/query/__tests__/durable-question-park.test.js.map +1 -0
- package/dist/runtime/query/__tests__/durable-run-state.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/durable-run-state.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/durable-run-state.test.js +158 -0
- package/dist/runtime/query/__tests__/durable-run-state.test.js.map +1 -0
- package/dist/runtime/query/__tests__/executor-plugin-hooks.test.js +24 -20
- package/dist/runtime/query/__tests__/executor-plugin-hooks.test.js.map +1 -1
- package/dist/runtime/query/__tests__/finish-reason-vs-tool-calls.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/finish-reason-vs-tool-calls.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/finish-reason-vs-tool-calls.test.js +187 -0
- package/dist/runtime/query/__tests__/finish-reason-vs-tool-calls.test.js.map +1 -0
- package/dist/runtime/query/__tests__/grant-cannot-overrule-the-gate.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/grant-cannot-overrule-the-gate.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/grant-cannot-overrule-the-gate.test.js +95 -0
- package/dist/runtime/query/__tests__/grant-cannot-overrule-the-gate.test.js.map +1 -0
- package/dist/runtime/query/__tests__/guardrails-e2e.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/guardrails-e2e.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/guardrails-e2e.test.js +132 -0
- package/dist/runtime/query/__tests__/guardrails-e2e.test.js.map +1 -0
- package/dist/runtime/query/__tests__/guardrails.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/guardrails.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/guardrails.test.js +163 -0
- package/dist/runtime/query/__tests__/guardrails.test.js.map +1 -0
- package/dist/runtime/query/__tests__/hook-model-visibility.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/hook-model-visibility.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/hook-model-visibility.test.js +119 -0
- package/dist/runtime/query/__tests__/hook-model-visibility.test.js.map +1 -0
- package/dist/runtime/query/__tests__/long-document-flow.test.js +9 -2
- package/dist/runtime/query/__tests__/long-document-flow.test.js.map +1 -1
- package/dist/runtime/query/__tests__/memory-promotion.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/memory-promotion.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/memory-promotion.test.js +119 -0
- package/dist/runtime/query/__tests__/memory-promotion.test.js.map +1 -0
- package/dist/runtime/query/__tests__/orphan-task-turn-end.test.js +5 -27
- package/dist/runtime/query/__tests__/orphan-task-turn-end.test.js.map +1 -1
- package/dist/runtime/query/__tests__/overflow-relief.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/overflow-relief.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/overflow-relief.test.js +119 -0
- package/dist/runtime/query/__tests__/overflow-relief.test.js.map +1 -0
- package/dist/runtime/query/__tests__/partial-batch-resume.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/partial-batch-resume.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/partial-batch-resume.test.js +205 -0
- package/dist/runtime/query/__tests__/partial-batch-resume.test.js.map +1 -0
- package/dist/runtime/query/__tests__/plugin-hooks.test.js +0 -1
- package/dist/runtime/query/__tests__/plugin-hooks.test.js.map +1 -1
- package/dist/runtime/query/__tests__/prepare-step-chain.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/prepare-step-chain.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/prepare-step-chain.test.js +104 -0
- package/dist/runtime/query/__tests__/prepare-step-chain.test.js.map +1 -0
- package/dist/runtime/query/__tests__/prepare-step.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/prepare-step.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/prepare-step.test.js +194 -0
- package/dist/runtime/query/__tests__/prepare-step.test.js.map +1 -0
- package/dist/runtime/query/__tests__/probe-veto-is-error.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/probe-veto-is-error.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/probe-veto-is-error.test.js +111 -0
- package/dist/runtime/query/__tests__/probe-veto-is-error.test.js.map +1 -0
- package/dist/runtime/query/__tests__/prompt.test.js +1 -1
- package/dist/runtime/query/__tests__/prompt.test.js.map +1 -1
- package/dist/runtime/query/__tests__/provider-fault-pauses.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/provider-fault-pauses.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/provider-fault-pauses.test.js +86 -0
- package/dist/runtime/query/__tests__/provider-fault-pauses.test.js.map +1 -0
- package/dist/runtime/query/__tests__/reasoning-stream.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/reasoning-stream.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/reasoning-stream.test.js +146 -0
- package/dist/runtime/query/__tests__/reasoning-stream.test.js.map +1 -0
- package/dist/runtime/query/__tests__/recoverable-settle.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/recoverable-settle.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/recoverable-settle.test.js +119 -0
- package/dist/runtime/query/__tests__/recoverable-settle.test.js.map +1 -0
- package/dist/runtime/query/__tests__/resume-budget.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/resume-budget.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/resume-budget.test.js +130 -0
- package/dist/runtime/query/__tests__/resume-budget.test.js.map +1 -0
- package/dist/runtime/query/__tests__/resume-pending.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/resume-pending.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/resume-pending.test.js +226 -0
- package/dist/runtime/query/__tests__/resume-pending.test.js.map +1 -0
- package/dist/runtime/query/__tests__/rich-content-budget-wiring.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/rich-content-budget-wiring.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/rich-content-budget-wiring.test.js +89 -0
- package/dist/runtime/query/__tests__/rich-content-budget-wiring.test.js.map +1 -0
- package/dist/runtime/query/__tests__/stop-condition.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/stop-condition.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/stop-condition.test.js +205 -0
- package/dist/runtime/query/__tests__/stop-condition.test.js.map +1 -0
- package/dist/runtime/query/__tests__/structured-output.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/structured-output.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/structured-output.test.js +219 -0
- package/dist/runtime/query/__tests__/structured-output.test.js.map +1 -0
- package/dist/runtime/query/__tests__/structured-run-failure.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/structured-run-failure.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/structured-run-failure.test.js +117 -0
- package/dist/runtime/query/__tests__/structured-run-failure.test.js.map +1 -0
- package/dist/runtime/query/__tests__/terminal-tool.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/terminal-tool.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/terminal-tool.test.js +119 -0
- package/dist/runtime/query/__tests__/terminal-tool.test.js.map +1 -0
- package/dist/runtime/query/__tests__/tool-grants.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/tool-grants.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/tool-grants.test.js +85 -0
- package/dist/runtime/query/__tests__/tool-grants.test.js.map +1 -0
- package/dist/runtime/query/__tests__/tool-output-budget.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/tool-output-budget.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/tool-output-budget.test.js +0 -0
- package/dist/runtime/query/__tests__/tool-output-budget.test.js.map +1 -0
- package/dist/runtime/query/__tests__/tool-pause.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/tool-pause.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/tool-pause.test.js +165 -0
- package/dist/runtime/query/__tests__/tool-pause.test.js.map +1 -0
- package/dist/runtime/query/__tests__/tool-progress.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/tool-progress.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/tool-progress.test.js +122 -0
- package/dist/runtime/query/__tests__/tool-progress.test.js.map +1 -0
- package/dist/runtime/query/__tests__/tool-repair-retry.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/tool-repair-retry.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/tool-repair-retry.test.js +196 -0
- package/dist/runtime/query/__tests__/tool-repair-retry.test.js.map +1 -0
- package/dist/runtime/query/__tests__/tool-result-wire.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/tool-result-wire.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/tool-result-wire.test.js +106 -0
- package/dist/runtime/query/__tests__/tool-result-wire.test.js.map +1 -0
- package/dist/runtime/query/__tests__/tool-timeout.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/tool-timeout.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/tool-timeout.test.js +184 -0
- package/dist/runtime/query/__tests__/tool-timeout.test.js.map +1 -0
- package/dist/runtime/query/__tests__/trace-parenting.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/trace-parenting.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/trace-parenting.test.js +111 -0
- package/dist/runtime/query/__tests__/trace-parenting.test.js.map +1 -0
- package/dist/runtime/query/__tests__/wiring-seams.test.d.ts +2 -0
- package/dist/runtime/query/__tests__/wiring-seams.test.d.ts.map +1 -0
- package/dist/runtime/query/__tests__/wiring-seams.test.js +237 -0
- package/dist/runtime/query/__tests__/wiring-seams.test.js.map +1 -0
- package/dist/runtime/query/checkpoint.d.ts +124 -6
- package/dist/runtime/query/checkpoint.d.ts.map +1 -1
- package/dist/runtime/query/checkpoint.js +207 -6
- package/dist/runtime/query/checkpoint.js.map +1 -1
- package/dist/runtime/query/events.js +2 -2
- package/dist/runtime/query/events.js.map +1 -1
- package/dist/runtime/query/executor.d.ts +224 -7
- package/dist/runtime/query/executor.d.ts.map +1 -1
- package/dist/runtime/query/executor.js +662 -35
- package/dist/runtime/query/executor.js.map +1 -1
- package/dist/runtime/query/guard.d.ts +18 -0
- package/dist/runtime/query/guard.d.ts.map +1 -1
- package/dist/runtime/query/guard.js +16 -1
- package/dist/runtime/query/guard.js.map +1 -1
- package/dist/runtime/query/guardrail-presets.d.ts +36 -0
- package/dist/runtime/query/guardrail-presets.d.ts.map +1 -0
- package/dist/runtime/query/guardrail-presets.js +96 -0
- package/dist/runtime/query/guardrail-presets.js.map +1 -0
- package/dist/runtime/query/guardrails.d.ts +35 -0
- package/dist/runtime/query/guardrails.d.ts.map +1 -0
- package/dist/runtime/query/guardrails.js +102 -0
- package/dist/runtime/query/guardrails.js.map +1 -0
- package/dist/runtime/query/index.d.ts +213 -2
- package/dist/runtime/query/index.d.ts.map +1 -1
- package/dist/runtime/query/index.js +458 -10
- package/dist/runtime/query/index.js.map +1 -1
- package/dist/runtime/query/iteration/__tests__/cancel-settles-turn.test.d.ts +2 -0
- package/dist/runtime/query/iteration/__tests__/cancel-settles-turn.test.d.ts.map +1 -0
- package/dist/runtime/query/iteration/__tests__/cancel-settles-turn.test.js +131 -0
- package/dist/runtime/query/iteration/__tests__/cancel-settles-turn.test.js.map +1 -0
- package/dist/runtime/query/iteration/index.d.ts +76 -1
- package/dist/runtime/query/iteration/index.d.ts.map +1 -1
- package/dist/runtime/query/iteration/index.js +577 -34
- package/dist/runtime/query/iteration/index.js.map +1 -1
- package/dist/runtime/query/iteration/phases/advisory.d.ts.map +1 -1
- package/dist/runtime/query/iteration/phases/advisory.js +14 -2
- package/dist/runtime/query/iteration/phases/advisory.js.map +1 -1
- package/dist/runtime/query/iteration/phases/advisory.test.d.ts +1 -1
- package/dist/runtime/query/iteration/phases/advisory.test.js +4 -1
- package/dist/runtime/query/iteration/phases/advisory.test.js.map +1 -1
- package/dist/runtime/query/iteration/phases/checkpoint.js +2 -2
- package/dist/runtime/query/iteration/phases/checkpoint.js.map +1 -1
- package/dist/runtime/query/iteration/phases/compaction-safe-cut.test.js +1 -1
- package/dist/runtime/query/iteration/phases/compaction-safe-cut.test.js.map +1 -1
- package/dist/runtime/query/iteration/phases/compaction.d.ts +22 -1
- package/dist/runtime/query/iteration/phases/compaction.d.ts.map +1 -1
- package/dist/runtime/query/iteration/phases/compaction.js +297 -64
- package/dist/runtime/query/iteration/phases/compaction.js.map +1 -1
- package/dist/runtime/query/iteration/phases/context-measurement.test.d.ts +21 -0
- package/dist/runtime/query/iteration/phases/context-measurement.test.d.ts.map +1 -0
- package/dist/runtime/query/iteration/phases/context-measurement.test.js +161 -0
- package/dist/runtime/query/iteration/phases/context-measurement.test.js.map +1 -0
- package/dist/runtime/query/iteration/phases/context.d.ts +62 -2
- package/dist/runtime/query/iteration/phases/context.d.ts.map +1 -1
- package/dist/runtime/query/iteration/phases/context.js +87 -0
- package/dist/runtime/query/iteration/phases/context.js.map +1 -1
- package/dist/runtime/query/iteration/phases/hitl-answer-question.test.js +3 -1
- package/dist/runtime/query/iteration/phases/hitl-answer-question.test.js.map +1 -1
- package/dist/runtime/query/iteration/phases/overflow-escalation.test.d.ts +15 -0
- package/dist/runtime/query/iteration/phases/overflow-escalation.test.d.ts.map +1 -0
- package/dist/runtime/query/iteration/phases/overflow-escalation.test.js +130 -0
- package/dist/runtime/query/iteration/phases/overflow-escalation.test.js.map +1 -0
- package/dist/runtime/query/iteration/phases/plan.d.ts.map +1 -1
- package/dist/runtime/query/iteration/phases/plan.js +8 -2
- package/dist/runtime/query/iteration/phases/plan.js.map +1 -1
- package/dist/runtime/query/iteration/phases/retained-messages.test.d.ts +2 -0
- package/dist/runtime/query/iteration/phases/retained-messages.test.d.ts.map +1 -0
- package/dist/runtime/query/iteration/phases/retained-messages.test.js +180 -0
- package/dist/runtime/query/iteration/phases/retained-messages.test.js.map +1 -0
- package/dist/runtime/query/iteration/phases/tool-review-denials.test.d.ts +2 -0
- package/dist/runtime/query/iteration/phases/tool-review-denials.test.d.ts.map +1 -0
- package/dist/runtime/query/iteration/phases/tool-review-denials.test.js +224 -0
- package/dist/runtime/query/iteration/phases/tool-review-denials.test.js.map +1 -0
- package/dist/runtime/query/iteration/phases/tool-review.d.ts +29 -1
- package/dist/runtime/query/iteration/phases/tool-review.d.ts.map +1 -1
- package/dist/runtime/query/iteration/phases/tool-review.js +114 -44
- package/dist/runtime/query/iteration/phases/tool-review.js.map +1 -1
- package/dist/runtime/query/iteration/phases/working-memory-compaction.test.js +20 -9
- package/dist/runtime/query/iteration/phases/working-memory-compaction.test.js.map +1 -1
- package/dist/runtime/query/iteration/stream-turn.d.ts +2 -26
- package/dist/runtime/query/iteration/stream-turn.d.ts.map +1 -1
- package/dist/runtime/query/iteration/stream-turn.js +254 -16
- package/dist/runtime/query/iteration/stream-turn.js.map +1 -1
- package/dist/runtime/query/plugin-hooks.d.ts.map +1 -1
- package/dist/runtime/query/plugin-hooks.js +6 -2
- package/dist/runtime/query/plugin-hooks.js.map +1 -1
- package/dist/runtime/query/prompt.d.ts.map +1 -1
- package/dist/runtime/query/prompt.js +25 -1
- package/dist/runtime/query/prompt.js.map +1 -1
- package/dist/runtime/query/question-park.d.ts +85 -0
- package/dist/runtime/query/question-park.d.ts.map +1 -0
- package/dist/runtime/query/question-park.js +71 -0
- package/dist/runtime/query/question-park.js.map +1 -0
- package/dist/runtime/query/result.d.ts +9 -0
- package/dist/runtime/query/result.d.ts.map +1 -1
- package/dist/runtime/query/result.js +49 -0
- package/dist/runtime/query/result.js.map +1 -1
- package/dist/runtime/query/resume-pending.d.ts +106 -0
- package/dist/runtime/query/resume-pending.d.ts.map +1 -0
- package/dist/runtime/query/resume-pending.js +312 -0
- package/dist/runtime/query/resume-pending.js.map +1 -0
- package/dist/runtime/query/run-state.d.ts +52 -0
- package/dist/runtime/query/run-state.d.ts.map +1 -0
- package/dist/runtime/query/run-state.js +87 -0
- package/dist/runtime/query/run-state.js.map +1 -0
- package/dist/runtime/query/tool-grants.d.ts +44 -0
- package/dist/runtime/query/tool-grants.d.ts.map +1 -0
- package/dist/runtime/query/tool-grants.js +63 -0
- package/dist/runtime/query/tool-grants.js.map +1 -0
- package/dist/runtime/query/tool-output-budget.d.ts +83 -0
- package/dist/runtime/query/tool-output-budget.d.ts.map +1 -0
- package/dist/runtime/query/tool-output-budget.js +147 -0
- package/dist/runtime/query/tool-output-budget.js.map +1 -0
- package/dist/runtime/query/tool-pause.d.ts +41 -0
- package/dist/runtime/query/tool-pause.d.ts.map +1 -0
- package/dist/runtime/query/tool-pause.js +94 -0
- package/dist/runtime/query/tool-pause.js.map +1 -0
- package/dist/runtime/query/tooling.d.ts +10 -1
- package/dist/runtime/query/tooling.d.ts.map +1 -1
- package/dist/runtime/query/tooling.js +13 -0
- package/dist/runtime/query/tooling.js.map +1 -1
- package/dist/sandbox/__tests__/isolation.test.d.ts +2 -0
- package/dist/sandbox/__tests__/isolation.test.d.ts.map +1 -0
- package/dist/sandbox/__tests__/isolation.test.js +139 -0
- package/dist/sandbox/__tests__/isolation.test.js.map +1 -0
- package/dist/sandbox/__tests__/output-truncation.test.d.ts +2 -0
- package/dist/sandbox/__tests__/output-truncation.test.d.ts.map +1 -0
- package/dist/sandbox/__tests__/output-truncation.test.js +88 -0
- package/dist/sandbox/__tests__/output-truncation.test.js.map +1 -0
- package/dist/sandbox/__tests__/resource-limits.test.d.ts +2 -0
- package/dist/sandbox/__tests__/resource-limits.test.d.ts.map +1 -0
- package/dist/sandbox/__tests__/resource-limits.test.js +86 -0
- package/dist/sandbox/__tests__/resource-limits.test.js.map +1 -0
- package/dist/sandbox/factory.js +1 -1
- package/dist/sandbox/factory.js.map +1 -1
- package/dist/sandbox/index.d.ts +2 -0
- package/dist/sandbox/index.d.ts.map +1 -1
- package/dist/sandbox/index.js +1 -0
- package/dist/sandbox/index.js.map +1 -1
- package/dist/sandbox/isolation.d.ts +15 -0
- package/dist/sandbox/isolation.d.ts.map +1 -0
- package/dist/sandbox/isolation.js +53 -0
- package/dist/sandbox/isolation.js.map +1 -0
- package/dist/sandbox/provider/local.d.ts +51 -2
- package/dist/sandbox/provider/local.d.ts.map +1 -1
- package/dist/sandbox/provider/local.js +139 -69
- package/dist/sandbox/provider/local.js.map +1 -1
- package/dist/session/__tests__/integration/spawn-rollback.test.d.ts +1 -1
- package/dist/session/__tests__/integration/spawn-rollback.test.js +1 -1
- package/dist/session/handoff/broadcast.js +3 -3
- package/dist/session/handoff/broadcast.js.map +1 -1
- package/dist/session/migration/__tests__/filesystem.test.js +5 -1
- package/dist/session/migration/__tests__/filesystem.test.js.map +1 -1
- package/dist/session/migration/filesystem.d.ts.map +1 -1
- package/dist/session/migration/filesystem.js +7 -13
- package/dist/session/migration/filesystem.js.map +1 -1
- package/dist/session/migration/marker.d.ts.map +1 -1
- package/dist/session/migration/marker.js +5 -10
- package/dist/session/migration/marker.js.map +1 -1
- package/dist/session/retention/disk-backend.d.ts.map +1 -1
- package/dist/session/retention/disk-backend.js +5 -12
- package/dist/session/retention/disk-backend.js.map +1 -1
- package/dist/session/workspace/__tests__/git-worktree.test.js +6 -2
- package/dist/session/workspace/__tests__/git-worktree.test.js.map +1 -1
- package/dist/session/workspace/__tests__/shared-run.test.js +15 -0
- package/dist/session/workspace/__tests__/shared-run.test.js.map +1 -1
- package/dist/session/workspace/shared-run.js +8 -1
- package/dist/session/workspace/shared-run.js.map +1 -1
- package/dist/skills/__tests__/frontmatter.test.d.ts +2 -0
- package/dist/skills/__tests__/frontmatter.test.d.ts.map +1 -0
- package/dist/skills/__tests__/frontmatter.test.js +106 -0
- package/dist/skills/__tests__/frontmatter.test.js.map +1 -0
- package/dist/skills/loader.d.ts.map +1 -1
- package/dist/skills/loader.js +42 -3
- package/dist/skills/loader.js.map +1 -1
- package/dist/store/__tests__/checkpoint-integrity.test.d.ts +2 -0
- package/dist/store/__tests__/checkpoint-integrity.test.d.ts.map +1 -0
- package/dist/store/__tests__/checkpoint-integrity.test.js +112 -0
- package/dist/store/__tests__/checkpoint-integrity.test.js.map +1 -0
- package/dist/store/__tests__/checkpoint-versioning.test.d.ts +2 -0
- package/dist/store/__tests__/checkpoint-versioning.test.d.ts.map +1 -0
- package/dist/store/__tests__/checkpoint-versioning.test.js +151 -0
- package/dist/store/__tests__/checkpoint-versioning.test.js.map +1 -0
- package/dist/store/__tests__/schema-adoption.test.d.ts +2 -0
- package/dist/store/__tests__/schema-adoption.test.d.ts.map +1 -0
- package/dist/store/__tests__/schema-adoption.test.js +90 -0
- package/dist/store/__tests__/schema-adoption.test.js.map +1 -0
- package/dist/store/__tests__/schema.test.d.ts +2 -0
- package/dist/store/__tests__/schema.test.d.ts.map +1 -0
- package/dist/store/__tests__/schema.test.js +93 -0
- package/dist/store/__tests__/schema.test.js.map +1 -0
- package/dist/store/memory/disk.d.ts.map +1 -1
- package/dist/store/memory/disk.js +16 -16
- package/dist/store/memory/disk.js.map +1 -1
- package/dist/store/run/disk.d.ts +23 -0
- package/dist/store/run/disk.d.ts.map +1 -1
- package/dist/store/run/disk.js +148 -23
- package/dist/store/run/disk.js.map +1 -1
- package/dist/store/schema.d.ts +73 -0
- package/dist/store/schema.d.ts.map +1 -0
- package/dist/store/schema.js +103 -0
- package/dist/store/schema.js.map +1 -0
- package/dist/store/session/disk.d.ts.map +1 -1
- package/dist/store/session/disk.js +25 -13
- package/dist/store/session/disk.js.map +1 -1
- package/dist/store/task/__tests__/lookup-across-runs.test.d.ts +2 -0
- package/dist/store/task/__tests__/lookup-across-runs.test.d.ts.map +1 -0
- package/dist/store/task/__tests__/lookup-across-runs.test.js +60 -0
- package/dist/store/task/__tests__/lookup-across-runs.test.js.map +1 -0
- package/dist/store/task/disk.d.ts +18 -0
- package/dist/store/task/disk.d.ts.map +1 -1
- package/dist/store/task/disk.js +61 -16
- package/dist/store/task/disk.js.map +1 -1
- package/dist/store/thread/disk.d.ts.map +1 -1
- package/dist/store/thread/disk.js +20 -11
- package/dist/store/thread/disk.js.map +1 -1
- package/dist/streaming/coalesce.d.ts +1 -1
- package/dist/streaming/coalesce.js +1 -1
- package/dist/telemetry/__tests__/latency-instruments.test.d.ts +2 -0
- package/dist/telemetry/__tests__/latency-instruments.test.d.ts.map +1 -0
- package/dist/telemetry/__tests__/latency-instruments.test.js +82 -0
- package/dist/telemetry/__tests__/latency-instruments.test.js.map +1 -0
- package/dist/telemetry/__tests__/metrics.test.d.ts +2 -0
- package/dist/telemetry/__tests__/metrics.test.d.ts.map +1 -0
- package/dist/telemetry/__tests__/metrics.test.js +112 -0
- package/dist/telemetry/__tests__/metrics.test.js.map +1 -0
- package/dist/telemetry/__tests__/span-hierarchy.test.d.ts +2 -0
- package/dist/telemetry/__tests__/span-hierarchy.test.d.ts.map +1 -0
- package/dist/telemetry/__tests__/span-hierarchy.test.js +84 -0
- package/dist/telemetry/__tests__/span-hierarchy.test.js.map +1 -0
- package/dist/telemetry/attributes.d.ts +44 -0
- package/dist/telemetry/attributes.d.ts.map +1 -1
- package/dist/telemetry/attributes.js +80 -0
- package/dist/telemetry/attributes.js.map +1 -1
- package/dist/telemetry/metrics.d.ts +41 -0
- package/dist/telemetry/metrics.d.ts.map +1 -0
- package/dist/telemetry/metrics.js +160 -0
- package/dist/telemetry/metrics.js.map +1 -0
- package/dist/test-setup.d.ts +3 -3
- package/dist/test-setup.js +3 -3
- package/dist/test-support/paths.d.ts +14 -0
- package/dist/test-support/paths.d.ts.map +1 -0
- package/dist/test-support/paths.js +16 -0
- package/dist/test-support/paths.js.map +1 -0
- package/dist/tools/__tests__/path-containment.test.d.ts +2 -0
- package/dist/tools/__tests__/path-containment.test.d.ts.map +1 -0
- package/dist/tools/__tests__/path-containment.test.js +133 -0
- package/dist/tools/__tests__/path-containment.test.js.map +1 -0
- package/dist/tools/__tests__/posix-path.test.d.ts +2 -0
- package/dist/tools/__tests__/posix-path.test.d.ts.map +1 -0
- package/dist/tools/__tests__/posix-path.test.js +67 -0
- package/dist/tools/__tests__/posix-path.test.js.map +1 -0
- package/dist/tools/__tests__/sandboxed-search.test.d.ts +2 -0
- package/dist/tools/__tests__/sandboxed-search.test.d.ts.map +1 -0
- package/dist/tools/__tests__/sandboxed-search.test.js +114 -0
- package/dist/tools/__tests__/sandboxed-search.test.js.map +1 -0
- package/dist/tools/builtins/__tests__/computer-use.test.js +12 -2
- package/dist/tools/builtins/__tests__/computer-use.test.js.map +1 -1
- package/dist/tools/builtins/__tests__/edit.test.js +10 -216
- package/dist/tools/builtins/__tests__/edit.test.js.map +1 -1
- package/dist/tools/builtins/__tests__/payload-budget.test.js +16 -30
- package/dist/tools/builtins/__tests__/payload-budget.test.js.map +1 -1
- package/dist/tools/builtins/__tests__/read-file.test.js +23 -1
- package/dist/tools/builtins/__tests__/read-file.test.js.map +1 -1
- package/dist/tools/builtins/__tests__/write-file.test.js +13 -37
- package/dist/tools/builtins/__tests__/write-file.test.js.map +1 -1
- package/dist/tools/builtins/bash.d.ts.map +1 -1
- package/dist/tools/builtins/bash.js +33 -4
- package/dist/tools/builtins/bash.js.map +1 -1
- package/dist/tools/builtins/computer-use.d.ts +22 -22
- package/dist/tools/builtins/computer-use.d.ts.map +1 -1
- package/dist/tools/builtins/computer-use.js +7 -1
- package/dist/tools/builtins/computer-use.js.map +1 -1
- package/dist/tools/builtins/edit.d.ts +5 -2
- package/dist/tools/builtins/edit.d.ts.map +1 -1
- package/dist/tools/builtins/edit.js +125 -105
- package/dist/tools/builtins/edit.js.map +1 -1
- package/dist/tools/builtins/glob.d.ts +1 -1
- package/dist/tools/builtins/glob.d.ts.map +1 -1
- package/dist/tools/builtins/glob.js +63 -6
- package/dist/tools/builtins/glob.js.map +1 -1
- package/dist/tools/builtins/grep.d.ts.map +1 -1
- package/dist/tools/builtins/grep.js +61 -8
- package/dist/tools/builtins/grep.js.map +1 -1
- package/dist/tools/builtins/index.js +6 -6
- package/dist/tools/builtins/index.js.map +1 -1
- package/dist/tools/builtins/ls.d.ts.map +1 -1
- package/dist/tools/builtins/ls.js +4 -2
- package/dist/tools/builtins/ls.js.map +1 -1
- package/dist/tools/builtins/read-file.d.ts +1 -1
- package/dist/tools/builtins/read-file.d.ts.map +1 -1
- package/dist/tools/builtins/read-file.js +38 -4
- package/dist/tools/builtins/read-file.js.map +1 -1
- package/dist/tools/builtins/write-file.d.ts +2 -1
- package/dist/tools/builtins/write-file.d.ts.map +1 -1
- package/dist/tools/builtins/write-file.js +40 -66
- package/dist/tools/builtins/write-file.js.map +1 -1
- package/dist/tools/coordinator/__tests__/agent.test.d.ts +1 -1
- package/dist/tools/coordinator/__tests__/agent.test.js +2 -2
- package/dist/tools/coordinator/__tests__/agent.test.js.map +1 -1
- package/dist/tools/coordinator/agent.d.ts +20 -9
- package/dist/tools/coordinator/agent.d.ts.map +1 -1
- package/dist/tools/coordinator/agent.js +2 -1
- package/dist/tools/coordinator/agent.js.map +1 -1
- package/dist/tools/coordinator/index.d.ts +20 -0
- package/dist/tools/coordinator/index.d.ts.map +1 -1
- package/dist/tools/coordinator/index.js +80 -32
- package/dist/tools/coordinator/index.js.map +1 -1
- package/dist/tools/defineTool.d.ts +16 -0
- package/dist/tools/defineTool.d.ts.map +1 -1
- package/dist/tools/defineTool.js +4 -0
- package/dist/tools/defineTool.js.map +1 -1
- package/dist/tools/glob-match.d.ts +18 -0
- package/dist/tools/glob-match.d.ts.map +1 -0
- package/dist/tools/glob-match.js +50 -0
- package/dist/tools/glob-match.js.map +1 -0
- package/dist/tools/paths.d.ts +20 -0
- package/dist/tools/paths.d.ts.map +1 -0
- package/dist/tools/paths.js +41 -0
- package/dist/tools/paths.js.map +1 -0
- package/dist/tools/posix-path.d.ts +24 -0
- package/dist/tools/posix-path.d.ts.map +1 -0
- package/dist/tools/posix-path.js +67 -0
- package/dist/tools/posix-path.js.map +1 -0
- package/dist/types/advisory/config.d.ts +21 -3
- package/dist/types/advisory/config.d.ts.map +1 -1
- package/dist/types/advisory/result.d.ts +12 -10
- package/dist/types/advisory/result.d.ts.map +1 -1
- package/dist/types/agent/base.d.ts +20 -2
- package/dist/types/agent/base.d.ts.map +1 -1
- package/dist/types/agent/factory.d.ts +15 -9
- package/dist/types/agent/factory.d.ts.map +1 -1
- package/dist/types/agent/gateway.d.ts +18 -0
- package/dist/types/agent/gateway.d.ts.map +1 -1
- package/dist/types/agent/manager.d.ts +19 -0
- package/dist/types/agent/manager.d.ts.map +1 -1
- package/dist/types/agent/reactive.d.ts +48 -0
- package/dist/types/agent/reactive.d.ts.map +1 -1
- package/dist/types/agent/router.d.ts +11 -0
- package/dist/types/agent/router.d.ts.map +1 -1
- package/dist/types/agent/supervisor.d.ts +2 -2
- package/dist/types/agent/task.d.ts +24 -0
- package/dist/types/agent/task.d.ts.map +1 -1
- package/dist/types/bidi/index.d.ts +140 -0
- package/dist/types/bidi/index.d.ts.map +1 -0
- package/dist/types/bidi/index.js +2 -0
- package/dist/types/bidi/index.js.map +1 -0
- package/dist/types/common/__tests__/numeric-correctness.test.d.ts +2 -0
- package/dist/types/common/__tests__/numeric-correctness.test.d.ts.map +1 -0
- package/dist/types/common/__tests__/numeric-correctness.test.js +108 -0
- package/dist/types/common/__tests__/numeric-correctness.test.js.map +1 -0
- package/dist/types/common/index.d.ts +1 -1
- package/dist/types/common/index.d.ts.map +1 -1
- package/dist/types/common/index.js +15 -4
- package/dist/types/common/index.js.map +1 -1
- package/dist/types/connector/mcp.d.ts +29 -0
- package/dist/types/connector/mcp.d.ts.map +1 -1
- package/dist/types/errors/__tests__/catalog.test.d.ts +2 -0
- package/dist/types/errors/__tests__/catalog.test.d.ts.map +1 -0
- package/dist/types/errors/__tests__/catalog.test.js +106 -0
- package/dist/types/errors/__tests__/catalog.test.js.map +1 -0
- package/dist/types/errors/__tests__/errors.test.d.ts +2 -0
- package/dist/types/errors/__tests__/errors.test.d.ts.map +1 -0
- package/dist/types/errors/__tests__/errors.test.js +104 -0
- package/dist/types/errors/__tests__/errors.test.js.map +1 -0
- package/dist/types/errors/catalog.d.ts +83 -0
- package/dist/types/errors/catalog.d.ts.map +1 -0
- package/dist/types/errors/catalog.js +148 -0
- package/dist/types/errors/catalog.js.map +1 -0
- package/dist/types/errors/index.d.ts +73 -0
- package/dist/types/errors/index.d.ts.map +1 -0
- package/dist/types/errors/index.js +70 -0
- package/dist/types/errors/index.js.map +1 -0
- package/dist/types/guardrail/index.d.ts +57 -0
- package/dist/types/guardrail/index.d.ts.map +1 -0
- package/dist/types/guardrail/index.js +2 -0
- package/dist/types/guardrail/index.js.map +1 -0
- package/dist/types/hitl/index.d.ts +97 -14
- package/dist/types/hitl/index.d.ts.map +1 -1
- package/dist/types/hitl/index.js.map +1 -1
- package/dist/types/ids/index.d.ts +2 -2
- package/dist/types/message/content.d.ts +22 -0
- package/dist/types/message/content.d.ts.map +1 -0
- package/dist/types/message/content.js +49 -0
- package/dist/types/message/content.js.map +1 -0
- package/dist/types/message/index.d.ts +193 -8
- package/dist/types/message/index.d.ts.map +1 -1
- package/dist/types/message/index.js +19 -4
- package/dist/types/message/index.js.map +1 -1
- package/dist/types/plugin/index.d.ts +78 -3
- package/dist/types/plugin/index.d.ts.map +1 -1
- package/dist/types/plugin/index.js +0 -1
- package/dist/types/plugin/index.js.map +1 -1
- package/dist/types/provider/__tests__/cause-chain.test.d.ts +2 -0
- package/dist/types/provider/__tests__/cause-chain.test.d.ts.map +1 -0
- package/dist/types/provider/__tests__/cause-chain.test.js +108 -0
- package/dist/types/provider/__tests__/cause-chain.test.js.map +1 -0
- package/dist/types/provider/__tests__/declared-retryable.test.d.ts +2 -0
- package/dist/types/provider/__tests__/declared-retryable.test.d.ts.map +1 -0
- package/dist/types/provider/__tests__/declared-retryable.test.js +70 -0
- package/dist/types/provider/__tests__/declared-retryable.test.js.map +1 -0
- package/dist/types/provider/__tests__/overflow-classification.test.d.ts +2 -0
- package/dist/types/provider/__tests__/overflow-classification.test.d.ts.map +1 -0
- package/dist/types/provider/__tests__/overflow-classification.test.js +80 -0
- package/dist/types/provider/__tests__/overflow-classification.test.js.map +1 -0
- package/dist/types/provider/chat.d.ts +27 -1
- package/dist/types/provider/chat.d.ts.map +1 -1
- package/dist/types/provider/config.d.ts +83 -2
- package/dist/types/provider/config.d.ts.map +1 -1
- package/dist/types/provider/errors.d.ts +102 -0
- package/dist/types/provider/errors.d.ts.map +1 -0
- package/dist/types/provider/errors.js +393 -0
- package/dist/types/provider/errors.js.map +1 -0
- package/dist/types/provider/index.d.ts +3 -2
- package/dist/types/provider/index.d.ts.map +1 -1
- package/dist/types/provider/stream.d.ts +59 -3
- package/dist/types/provider/stream.d.ts.map +1 -1
- package/dist/types/rag/embedding.d.ts +11 -2
- package/dist/types/rag/embedding.d.ts.map +1 -1
- package/dist/types/run/__tests__/step.test.d.ts +2 -0
- package/dist/types/run/__tests__/step.test.d.ts.map +1 -0
- package/dist/types/run/__tests__/step.test.js +107 -0
- package/dist/types/run/__tests__/step.test.js.map +1 -0
- package/dist/types/run/answer-review.d.ts +46 -0
- package/dist/types/run/answer-review.d.ts.map +1 -0
- package/dist/types/run/answer-review.js +2 -0
- package/dist/types/run/answer-review.js.map +1 -0
- package/dist/types/run/config.d.ts +33 -0
- package/dist/types/run/config.d.ts.map +1 -1
- package/dist/types/run/derive-status.d.ts +29 -0
- package/dist/types/run/derive-status.d.ts.map +1 -0
- package/dist/types/run/derive-status.js +49 -0
- package/dist/types/run/derive-status.js.map +1 -0
- package/dist/types/run/entity.d.ts +16 -0
- package/dist/types/run/entity.d.ts.map +1 -1
- package/dist/types/run/events.d.ts +228 -4
- package/dist/types/run/events.d.ts.map +1 -1
- package/dist/types/run/events.js +7 -0
- package/dist/types/run/events.js.map +1 -1
- package/dist/types/run/index.d.ts +5 -0
- package/dist/types/run/index.d.ts.map +1 -1
- package/dist/types/run/index.js +3 -0
- package/dist/types/run/index.js.map +1 -1
- package/dist/types/run/memory-promotion.d.ts +90 -0
- package/dist/types/run/memory-promotion.d.ts.map +1 -0
- package/dist/types/run/memory-promotion.js +38 -0
- package/dist/types/run/memory-promotion.js.map +1 -0
- package/dist/types/run/prepare-step.d.ts +100 -0
- package/dist/types/run/prepare-step.d.ts.map +1 -0
- package/dist/types/run/prepare-step.js +2 -0
- package/dist/types/run/prepare-step.js.map +1 -0
- package/dist/types/run/state.d.ts +85 -0
- package/dist/types/run/state.d.ts.map +1 -0
- package/dist/types/run/state.js +33 -0
- package/dist/types/run/state.js.map +1 -0
- package/dist/types/run/step.d.ts +77 -0
- package/dist/types/run/step.d.ts.map +1 -0
- package/dist/types/run/step.js +26 -0
- package/dist/types/run/step.js.map +1 -0
- package/dist/types/run/stop-reason.d.ts +31 -3
- package/dist/types/run/stop-reason.d.ts.map +1 -1
- package/dist/types/sandbox/index.d.ts +82 -10
- package/dist/types/sandbox/index.d.ts.map +1 -1
- package/dist/types/sandbox/index.js +13 -1
- package/dist/types/sandbox/index.js.map +1 -1
- package/dist/types/structured-output/index.d.ts +6 -5
- package/dist/types/structured-output/index.d.ts.map +1 -1
- package/dist/types/thread/entity.d.ts +2 -3
- package/dist/types/thread/entity.d.ts.map +1 -1
- package/dist/types/tool/index.d.ts +193 -1
- package/dist/types/tool/index.d.ts.map +1 -1
- package/dist/types/tool/index.js +1 -1
- package/dist/types/tool/index.js.map +1 -1
- package/dist/types/tool/repair.d.ts +49 -0
- package/dist/types/tool/repair.d.ts.map +1 -0
- package/dist/types/tool/repair.js +2 -0
- package/dist/types/tool/repair.js.map +1 -0
- package/dist/types/toolset/index.d.ts +2 -5
- package/dist/types/toolset/index.d.ts.map +1 -1
- package/dist/utils/__tests__/atomic-write.test.d.ts +2 -0
- package/dist/utils/__tests__/atomic-write.test.d.ts.map +1 -0
- package/dist/utils/__tests__/atomic-write.test.js +91 -0
- package/dist/utils/__tests__/atomic-write.test.js.map +1 -0
- package/dist/utils/__tests__/shell-compress.test.d.ts +2 -0
- package/dist/utils/__tests__/shell-compress.test.d.ts.map +1 -0
- package/dist/utils/__tests__/shell-compress.test.js +41 -0
- package/dist/utils/__tests__/shell-compress.test.js.map +1 -0
- package/dist/utils/atomic-write.d.ts +10 -0
- package/dist/utils/atomic-write.d.ts.map +1 -0
- package/dist/utils/atomic-write.js +83 -0
- package/dist/utils/atomic-write.js.map +1 -0
- package/dist/utils/shell-compress.d.ts.map +1 -1
- package/dist/utils/shell-compress.js +12 -1
- package/dist/utils/shell-compress.js.map +1 -1
- package/dist/verification/presets.d.ts +6 -3
- package/dist/verification/presets.d.ts.map +1 -1
- package/dist/verification/presets.js +6 -3
- package/dist/verification/presets.js.map +1 -1
- package/package.json +3 -3
- package/src/__tests__/default-path-conformance.test.ts +306 -0
- package/src/__tests__/shipped-defaults.test.ts +111 -0
- package/src/advisory/__tests__/budget-enforcement.test.ts +208 -0
- package/src/advisory/__tests__/structured-response.test.ts +128 -0
- package/src/advisory/budget.ts +27 -0
- package/src/advisory/context.ts +19 -0
- package/src/advisory/executor.test.ts +12 -8
- package/src/advisory/executor.ts +37 -25
- package/src/advisory/index.ts +2 -0
- package/src/advisory/parse.ts +63 -0
- package/src/agents/AbstractAgent.ts +82 -0
- package/src/agents/PipelineAgent.ts +19 -0
- package/src/agents/ReactiveAgent.ts +47 -0
- package/src/agents/RouterAgent.ts +32 -2
- package/src/agents/SupervisorAgent.ts +31 -1
- package/src/agents/__tests__/idempotency-key.test.ts +177 -0
- package/src/agents/__tests__/invocation-lock.test.ts +154 -0
- package/src/agents/__tests__/reachability.test.ts +224 -0
- package/src/agents/__tests__/supervisor-ledger.test.ts +1 -1
- package/src/agents/index.ts +1 -1
- package/src/agents/lock.ts +0 -2
- package/src/bridge/a2a/late-events.test.ts +84 -0
- package/src/bridge/a2a/mapper.test.ts +1 -1
- package/src/bridge/a2a/mapper.ts +70 -5
- package/src/bridge/a2a/message.ts +5 -1
- package/src/bridge/sse/late-events.test.ts +182 -0
- package/src/bridge/sse/mapper.ts +109 -0
- package/src/compaction/__tests__/cleared-result-recovery.test.ts +118 -0
- package/src/compaction/__tests__/context-window.test.ts +77 -0
- package/src/compaction/__tests__/dangling.test.ts +16 -6
- package/src/compaction/__tests__/lossiness.test.ts +187 -0
- package/src/compaction/__tests__/state-across-resume.test.ts +99 -0
- package/src/compaction/__tests__/tool-result-editing.test.ts +213 -0
- package/src/compaction/__tests__/trim-opens-on-user.test.ts +118 -0
- package/src/compaction/__tests__/verifier-model.test.ts +83 -0
- package/src/compaction/context-window.ts +107 -0
- package/src/compaction/dangling.ts +48 -1
- package/src/compaction/extractor.ts +56 -1
- package/src/compaction/index.ts +16 -0
- package/src/compaction/manager.ts +53 -8
- package/src/compaction/managers/structured.ts +7 -6
- package/src/compaction/retention.ts +89 -0
- package/src/compaction/serializer.ts +42 -11
- package/src/compaction/tool-result-editing.ts +229 -0
- package/src/compaction/types.ts +10 -0
- package/src/compaction/verifier.ts +24 -1
- package/src/compaction/wire.ts +91 -0
- package/src/config/runtime.ts +63 -19
- package/src/connector/builtins/http.test.ts +13 -0
- package/src/connector/builtins/http.ts +15 -1
- package/src/connector/mcp/__tests__/discovery-policy.test.ts +133 -0
- package/src/connector/mcp/__tests__/list-pagination.test.ts +98 -0
- package/src/connector/mcp/__tests__/policy.test.ts +100 -0
- package/src/connector/mcp/__tests__/protocol-negotiation.test.ts +105 -0
- package/src/connector/mcp/__tests__/schema-fidelity.test.ts +250 -0
- package/src/connector/mcp/__tests__/structured-result.test.ts +143 -0
- package/src/connector/mcp/adapter.ts +306 -19
- package/src/connector/mcp/client.test.ts +159 -0
- package/src/connector/mcp/client.ts +160 -13
- package/src/connector/mcp/discovery.ts +74 -5
- package/src/connector/mcp/http-sse.ts +16 -1
- package/src/connector/mcp/index.ts +4 -0
- package/src/connector/mcp/policy.ts +134 -0
- package/src/connector/mcp/schema-refs.ts +126 -0
- package/src/constants/agent/index.ts +3 -0
- package/src/constants/compaction/index.ts +1 -1
- package/src/constants/continuation.ts +4 -4
- package/src/constants/mcp/index.ts +34 -0
- package/src/constants/plugin/index.ts +24 -2
- package/src/constants/sandbox/index.ts +6 -5
- package/src/constants/telemetry/index.ts +8 -0
- package/src/constants/tools/index.ts +20 -0
- package/src/contracts/api.ts +40 -0
- package/src/contracts/run-status.ts +43 -0
- package/src/eval/__tests__/case-deadline.test.ts +147 -0
- package/src/eval/__tests__/end-to-end.test.ts +259 -0
- package/src/eval/__tests__/harness-honesty.test.ts +99 -0
- package/src/eval/__tests__/harness.test.ts +249 -0
- package/src/eval/__tests__/judge.test.ts +306 -0
- package/src/eval/__tests__/scorer-gates.test.ts +156 -0
- package/src/eval/experiment.ts +335 -0
- package/src/eval/from-run.ts +48 -0
- package/src/eval/index.ts +21 -0
- package/src/eval/judge.ts +240 -0
- package/src/eval/scorers.ts +169 -0
- package/src/eval/types.ts +157 -0
- package/src/execution/local.test.ts +46 -0
- package/src/execution/local.ts +6 -1
- package/src/gateway/__tests__/list-survives-eviction.test.ts +124 -0
- package/src/gateway/local.ts +117 -3
- package/src/manager/agent/__tests__/dispose-cancels.test.ts +104 -0
- package/src/manager/agent/__tests__/lifecycle.test.ts +297 -0
- package/src/manager/agent/lifecycle.ts +127 -7
- package/src/manager/run/persistence.ts +132 -1
- package/src/plugin/__tests__/enable-contributions.test.ts +3 -3
- package/src/plugin/__tests__/hook-ordering.test.ts +252 -0
- package/src/plugin/__tests__/install-time-refusal.test.ts +68 -0
- package/src/plugin/__tests__/lifecycle.test.ts +95 -73
- package/src/plugin/lifecycle.ts +76 -22
- package/src/plugin/loader.ts +37 -1
- package/src/probe/registry.test.ts +49 -6
- package/src/probe/registry.ts +21 -1
- package/src/provider/__tests__/mock-script.test.ts +179 -0
- package/src/provider/__tests__/registry.test.ts +1 -1
- package/src/provider/__tests__/retry-visibility.test.ts +160 -0
- package/src/provider/__tests__/retry.test.ts +296 -0
- package/src/provider/capabilities.ts +4 -0
- package/src/provider/collect.test.ts +1 -1
- package/src/provider/collect.ts +1 -1
- package/src/provider/index.ts +8 -0
- package/src/provider/mock-register.ts +5 -2
- package/src/provider/mock.ts +117 -34
- package/src/provider/retry.ts +199 -0
- package/src/public-runtime.ts +111 -7
- package/src/public-types.ts +5 -1
- package/src/rag/__tests__/retrieval-math.test.ts +54 -0
- package/src/rag/chunking.ts +32 -1
- package/src/rag/embedding.test.ts +65 -10
- package/src/rag/embedding.ts +26 -5
- package/src/rag/index.ts +1 -1
- package/src/rag/retriever.ts +92 -21
- package/src/rag/vector-store.test.ts +2 -2
- package/src/registry/ManagedRegistry.test.ts +1 -1
- package/src/registry/Registry.test.ts +1 -1
- package/src/registry/connector/definitions.test.ts +1 -1
- package/src/registry/tool/__tests__/schema.test.ts +208 -0
- package/src/registry/tool/__tests__/tool-name-validation.test.ts +88 -0
- package/src/registry/tool/execute.ts +104 -22
- package/src/registry/tool/schema.ts +80 -0
- package/src/registry/toolset/catalog.test.ts +0 -1
- package/src/registry/toolset/catalog.ts +0 -1
- package/src/run/reporter.ts +84 -0
- package/src/runtime/bidi/__tests__/session.test.ts +232 -0
- package/src/runtime/bidi/index.ts +4 -0
- package/src/runtime/bidi/mock.ts +90 -0
- package/src/runtime/bidi/session.ts +205 -0
- package/src/runtime/decision/parser.test.ts +46 -0
- package/src/runtime/decision/parser.ts +8 -1
- package/src/runtime/query/__tests__/answer-review.test.ts +172 -0
- package/src/runtime/query/__tests__/capability-negotiation.test.ts +25 -129
- package/src/runtime/query/__tests__/checkpoint-store.test.ts +13 -50
- package/src/runtime/query/__tests__/checkpoint.test.ts +2 -10
- package/src/runtime/query/__tests__/citations.test.ts +111 -0
- package/src/runtime/query/__tests__/content-budget.test.ts +83 -0
- package/src/runtime/query/__tests__/context.test.ts +3 -2
- package/src/runtime/query/__tests__/deferred-tools.test.ts +23 -148
- package/src/runtime/query/__tests__/delegation-resume.test.ts +159 -0
- package/src/runtime/query/__tests__/document-attachments.test.ts +125 -0
- package/src/runtime/query/__tests__/durable-park-and-trace.test.ts +245 -0
- package/src/runtime/query/__tests__/durable-question-park.test.ts +305 -0
- package/src/runtime/query/__tests__/durable-run-state.test.ts +194 -0
- package/src/runtime/query/__tests__/executor-plugin-hooks.test.ts +24 -20
- package/src/runtime/query/__tests__/finish-reason-vs-tool-calls.test.ts +206 -0
- package/src/runtime/query/__tests__/grant-cannot-overrule-the-gate.test.ts +115 -0
- package/src/runtime/query/__tests__/guardrails-e2e.test.ts +164 -0
- package/src/runtime/query/__tests__/guardrails.test.ts +236 -0
- package/src/runtime/query/__tests__/hook-model-visibility.test.ts +143 -0
- package/src/runtime/query/__tests__/long-document-flow.test.ts +9 -2
- package/src/runtime/query/__tests__/memory-promotion.test.ts +148 -0
- package/src/runtime/query/__tests__/orphan-task-turn-end.test.ts +5 -31
- package/src/runtime/query/__tests__/overflow-relief.test.ts +139 -0
- package/src/runtime/query/__tests__/partial-batch-resume.test.ts +264 -0
- package/src/runtime/query/__tests__/plugin-hooks.test.ts +0 -1
- package/src/runtime/query/__tests__/prepare-step-chain.test.ts +127 -0
- package/src/runtime/query/__tests__/prepare-step.test.ts +233 -0
- package/src/runtime/query/__tests__/probe-veto-is-error.test.ts +145 -0
- package/src/runtime/query/__tests__/prompt.test.ts +1 -1
- package/src/runtime/query/__tests__/provider-fault-pauses.test.ts +104 -0
- package/src/runtime/query/__tests__/reasoning-stream.test.ts +177 -0
- package/src/runtime/query/__tests__/recoverable-settle.test.ts +145 -0
- package/src/runtime/query/__tests__/resume-budget.test.ts +158 -0
- package/src/runtime/query/__tests__/resume-pending.test.ts +273 -0
- package/src/runtime/query/__tests__/rich-content-budget-wiring.test.ts +109 -0
- package/src/runtime/query/__tests__/stop-condition.test.ts +265 -0
- package/src/runtime/query/__tests__/structured-output.test.ts +268 -0
- package/src/runtime/query/__tests__/structured-run-failure.test.ts +144 -0
- package/src/runtime/query/__tests__/terminal-tool.test.ts +148 -0
- package/src/runtime/query/__tests__/tool-grants.test.ts +102 -0
- package/src/runtime/query/__tests__/tool-output-budget.test.ts +0 -0
- package/src/runtime/query/__tests__/tool-pause.test.ts +209 -0
- package/src/runtime/query/__tests__/tool-progress.test.ts +154 -0
- package/src/runtime/query/__tests__/tool-repair-retry.test.ts +255 -0
- package/src/runtime/query/__tests__/tool-result-wire.test.ts +135 -0
- package/src/runtime/query/__tests__/tool-timeout.test.ts +230 -0
- package/src/runtime/query/__tests__/trace-parenting.test.ts +128 -0
- package/src/runtime/query/__tests__/wiring-seams.test.ts +288 -0
- package/src/runtime/query/checkpoint.ts +242 -10
- package/src/runtime/query/events.ts +2 -2
- package/src/runtime/query/executor.ts +847 -39
- package/src/runtime/query/guard.ts +26 -1
- package/src/runtime/query/guardrail-presets.ts +124 -0
- package/src/runtime/query/guardrails.ts +144 -0
- package/src/runtime/query/index.ts +759 -12
- package/src/runtime/query/iteration/__tests__/cancel-settles-turn.test.ts +177 -0
- package/src/runtime/query/iteration/index.ts +656 -40
- package/src/runtime/query/iteration/phases/advisory.test.ts +4 -1
- package/src/runtime/query/iteration/phases/advisory.ts +14 -2
- package/src/runtime/query/iteration/phases/checkpoint.ts +2 -2
- package/src/runtime/query/iteration/phases/compaction-safe-cut.test.ts +3 -1
- package/src/runtime/query/iteration/phases/compaction.ts +329 -64
- package/src/runtime/query/iteration/phases/context-measurement.test.ts +196 -0
- package/src/runtime/query/iteration/phases/context.ts +155 -2
- package/src/runtime/query/iteration/phases/hitl-answer-question.test.ts +3 -1
- package/src/runtime/query/iteration/phases/overflow-escalation.test.ts +167 -0
- package/src/runtime/query/iteration/phases/plan.ts +10 -2
- package/src/runtime/query/iteration/phases/retained-messages.test.ts +226 -0
- package/src/runtime/query/iteration/phases/tool-review-denials.test.ts +270 -0
- package/src/runtime/query/iteration/phases/tool-review.ts +140 -51
- package/src/runtime/query/iteration/phases/working-memory-compaction.test.ts +21 -9
- package/src/runtime/query/iteration/stream-turn.ts +285 -15
- package/src/runtime/query/plugin-hooks.ts +6 -2
- package/src/runtime/query/prompt.ts +26 -1
- package/src/runtime/query/question-park.ts +120 -0
- package/src/runtime/query/result.ts +64 -0
- package/src/runtime/query/resume-pending.ts +394 -0
- package/src/runtime/query/run-state.ts +124 -0
- package/src/runtime/query/tool-grants.ts +83 -0
- package/src/runtime/query/tool-output-budget.ts +183 -0
- package/src/runtime/query/tool-pause.ts +119 -0
- package/src/runtime/query/tooling.ts +23 -1
- package/src/sandbox/__tests__/isolation.test.ts +164 -0
- package/src/sandbox/__tests__/output-truncation.test.ts +106 -0
- package/src/sandbox/__tests__/resource-limits.test.ts +106 -0
- package/src/sandbox/factory.ts +1 -1
- package/src/sandbox/index.ts +2 -0
- package/src/sandbox/isolation.ts +72 -0
- package/src/sandbox/provider/local.ts +173 -74
- package/src/session/__tests__/integration/spawn-rollback.test.ts +1 -1
- package/src/session/handoff/broadcast.ts +3 -3
- package/src/session/migration/__tests__/filesystem.test.ts +26 -19
- package/src/session/migration/filesystem.ts +7 -12
- package/src/session/migration/marker.ts +5 -9
- package/src/session/retention/disk-backend.ts +5 -11
- package/src/session/workspace/__tests__/git-worktree.test.ts +6 -2
- package/src/session/workspace/__tests__/shared-run.test.ts +18 -0
- package/src/session/workspace/shared-run.ts +7 -1
- package/src/skills/__tests__/frontmatter.test.ts +135 -0
- package/src/skills/loader.ts +47 -3
- package/src/store/__tests__/checkpoint-integrity.test.ts +134 -0
- package/src/store/__tests__/checkpoint-versioning.test.ts +194 -0
- package/src/store/__tests__/schema-adoption.test.ts +118 -0
- package/src/store/__tests__/schema.test.ts +119 -0
- package/src/store/memory/disk.ts +17 -16
- package/src/store/run/disk.ts +169 -22
- package/src/store/schema.ts +135 -0
- package/src/store/session/disk.ts +30 -21
- package/src/store/task/__tests__/lookup-across-runs.test.ts +77 -0
- package/src/store/task/disk.ts +59 -15
- package/src/store/thread/disk.ts +21 -10
- package/src/streaming/coalesce.ts +1 -1
- package/src/telemetry/__tests__/latency-instruments.test.ts +120 -0
- package/src/telemetry/__tests__/metrics.test.ts +160 -0
- package/src/telemetry/__tests__/span-hierarchy.test.ts +94 -0
- package/src/telemetry/attributes.ts +109 -0
- package/src/telemetry/metrics.ts +190 -0
- package/src/test-setup.ts +3 -3
- package/src/test-support/paths.ts +17 -0
- package/src/tools/__tests__/path-containment.test.ts +167 -0
- package/src/tools/__tests__/posix-path.test.ts +83 -0
- package/src/tools/__tests__/sandboxed-search.test.ts +140 -0
- package/src/tools/builtins/__tests__/computer-use.test.ts +15 -2
- package/src/tools/builtins/__tests__/edit.test.ts +10 -270
- package/src/tools/builtins/__tests__/payload-budget.test.ts +20 -40
- package/src/tools/builtins/__tests__/read-file.test.ts +29 -1
- package/src/tools/builtins/__tests__/write-file.test.ts +13 -52
- package/src/tools/builtins/bash.ts +34 -4
- package/src/tools/builtins/computer-use.ts +7 -1
- package/src/tools/builtins/edit.ts +162 -116
- package/src/tools/builtins/glob.ts +71 -6
- package/src/tools/builtins/grep.ts +82 -8
- package/src/tools/builtins/index.ts +6 -6
- package/src/tools/builtins/ls.ts +4 -2
- package/src/tools/builtins/read-file.ts +40 -4
- package/src/tools/builtins/write-file.ts +44 -68
- package/src/tools/coordinator/__tests__/agent.test.ts +2 -2
- package/src/tools/coordinator/agent.ts +23 -10
- package/src/tools/coordinator/index.ts +111 -31
- package/src/tools/defineTool.ts +20 -0
- package/src/tools/glob-match.ts +50 -0
- package/src/tools/paths.ts +44 -0
- package/src/tools/posix-path.ts +73 -0
- package/src/types/advisory/config.ts +21 -3
- package/src/types/advisory/result.ts +12 -7
- package/src/types/agent/base.ts +22 -2
- package/src/types/agent/factory.ts +15 -9
- package/src/types/agent/gateway.ts +20 -0
- package/src/types/agent/manager.ts +19 -0
- package/src/types/agent/reactive.ts +50 -0
- package/src/types/agent/router.ts +11 -0
- package/src/types/agent/supervisor.ts +2 -2
- package/src/types/agent/task.ts +26 -0
- package/src/types/bidi/index.ts +119 -0
- package/src/types/common/__tests__/numeric-correctness.test.ts +123 -0
- package/src/types/common/index.ts +16 -4
- package/src/types/computer-use/index.ts +1 -1
- package/src/types/connector/mcp.ts +29 -0
- package/src/types/errors/__tests__/catalog.test.ts +130 -0
- package/src/types/errors/__tests__/errors.test.ts +118 -0
- package/src/types/errors/catalog.ts +211 -0
- package/src/types/errors/index.ts +121 -0
- package/src/types/guardrail/index.ts +62 -0
- package/src/types/hitl/index.ts +102 -20
- package/src/types/ids/index.ts +2 -2
- package/src/types/message/content.ts +50 -0
- package/src/types/message/index.ts +210 -9
- package/src/types/plugin/index.ts +82 -2
- package/src/types/provider/__tests__/cause-chain.test.ts +132 -0
- package/src/types/provider/__tests__/declared-retryable.test.ts +85 -0
- package/src/types/provider/__tests__/overflow-classification.test.ts +113 -0
- package/src/types/provider/chat.ts +29 -1
- package/src/types/provider/config.ts +83 -2
- package/src/types/provider/errors.ts +472 -0
- package/src/types/provider/index.ts +5 -0
- package/src/types/provider/stream.ts +63 -3
- package/src/types/rag/embedding.ts +11 -2
- package/src/types/run/__tests__/step.test.ts +123 -0
- package/src/types/run/answer-review.ts +51 -0
- package/src/types/run/config.ts +35 -0
- package/src/types/run/derive-status.ts +62 -0
- package/src/types/run/entity.ts +18 -0
- package/src/types/run/events.ts +230 -3
- package/src/types/run/index.ts +5 -0
- package/src/types/run/memory-promotion.ts +112 -0
- package/src/types/run/prepare-step.ts +109 -0
- package/src/types/run/state.ts +111 -0
- package/src/types/run/step.ts +95 -0
- package/src/types/run/stop-reason.ts +29 -1
- package/src/types/sandbox/index.ts +93 -12
- package/src/types/structured-output/index.ts +6 -5
- package/src/types/thread/entity.ts +2 -3
- package/src/types/tool/index.ts +204 -1
- package/src/types/tool/repair.ts +54 -0
- package/src/types/toolset/index.ts +2 -6
- package/src/utils/__tests__/atomic-write.test.ts +108 -0
- package/src/utils/__tests__/shell-compress.test.ts +49 -0
- package/src/utils/atomic-write.ts +85 -0
- package/src/utils/shell-compress.ts +12 -1
- package/src/verification/presets.ts +6 -3
package/dist/contracts/api.d.ts
CHANGED
|
@@ -44,7 +44,15 @@ export interface CreateMessageRequest {
|
|
|
44
44
|
* `completed`; domain `awaiting_hitl*` → wire `running`; domain
|
|
45
45
|
* `awaiting_subsession` → wire `running`).
|
|
46
46
|
*/
|
|
47
|
-
export type WireRunStatus = 'queued' | 'running' | 'completed' | 'failed' | 'cancelled' | 'cancelling'
|
|
47
|
+
export type WireRunStatus = 'queued' | 'running' | 'completed' | 'failed' | 'cancelled' | 'cancelling'
|
|
48
|
+
/**
|
|
49
|
+
* The run's approval window closed with nobody answering.
|
|
50
|
+
*
|
|
51
|
+
* Set by a host sweeping expired parks — there is no domain status that
|
|
52
|
+
* collapses onto it, because the kernel is suspended mid-iteration while
|
|
53
|
+
* parked and never gets to observe its own deadline passing.
|
|
54
|
+
*/
|
|
55
|
+
| 'expired';
|
|
48
56
|
export type RunStopReason = StopReason;
|
|
49
57
|
export interface WireRun {
|
|
50
58
|
id: RunId;
|
|
@@ -103,7 +111,37 @@ export interface CreateStatelessRunRequest {
|
|
|
103
111
|
config: RunConfig;
|
|
104
112
|
env?: Record<string, string>;
|
|
105
113
|
}
|
|
106
|
-
export type StreamEventType = 'run.started' | 'run.completed' | 'run.failed' | 'run.cancelled' | 'run.paused' | 'run.resuming' | 'iteration.started' | 'iteration.completed'
|
|
114
|
+
export type StreamEventType = 'run.started' | 'run.completed' | 'run.failed' | 'run.cancelled' | 'run.paused' | 'run.resuming' | 'iteration.started' | 'iteration.completed'
|
|
115
|
+
/**
|
|
116
|
+
* A compaction pass replaced a span of history with a summary. Wire-
|
|
117
|
+
* visible because the operation is destructive: a client rendering the
|
|
118
|
+
* transcript needs to know its middle was dropped, not infer it.
|
|
119
|
+
*/
|
|
120
|
+
| 'compaction.completed'
|
|
121
|
+
/** A guardrail refused or corrected the run. */
|
|
122
|
+
| 'guardrail.triggered'
|
|
123
|
+
/**
|
|
124
|
+
* Extended-thinking lifecycle. Wire-visible because without it a
|
|
125
|
+
* client renders a multi-second stall with no events while the model
|
|
126
|
+
* is demonstrably working.
|
|
127
|
+
*/
|
|
128
|
+
| 'reasoning.started' | 'reasoning.delta' | 'reasoning.completed'
|
|
129
|
+
/**
|
|
130
|
+
* A model call failed transiently and is being retried after a backoff.
|
|
131
|
+
* Wire-visible on the same grounds as `tool.progress` and the reasoning
|
|
132
|
+
* events: without it a client sees no event and no keepalive for the
|
|
133
|
+
* whole backoff, so a run that is about to succeed is indistinguishable
|
|
134
|
+
* from one that has hung.
|
|
135
|
+
*/
|
|
136
|
+
| 'provider.retry' | 'tool.executing'
|
|
137
|
+
/** Ephemeral progress from a long-running tool. Not in the transcript. */
|
|
138
|
+
| 'tool.progress' | 'tool.completed' | 'tool.error' | 'tool.input_started' | 'tool.input_delta' | 'tool.input_completed' | 'token.usage' | 'message.created' | 'message.delta' | 'message.completed'
|
|
139
|
+
/**
|
|
140
|
+
* A tool asked the user a question and the run is parked on it. Wire-
|
|
141
|
+
* visible for the same reason `review.requested` is: a client cannot
|
|
142
|
+
* render an approval card for something it never hears about.
|
|
143
|
+
*/
|
|
144
|
+
| 'question.asked' | 'question.answered' | 'review.requested' | 'review.completed' | 'checkpoint.created' | 'activity.created' | 'activity.updated' | 'plan.ready' | 'plan.approved' | 'plan.rejected' | 'plan.step_updated' | 'agent.pending' | 'agent.completed' | 'agent.failed' | 'agent.canceled' | 'task.created' | 'task.updated' | 'plugin.hook_executing' | 'plugin.hook_completed' | 'sandbox.created' | 'sandbox.exec' | 'sandbox.destroyed';
|
|
107
145
|
export interface StreamEvent {
|
|
108
146
|
event: StreamEventType;
|
|
109
147
|
data: Record<string, unknown>;
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"api.d.ts","sourceRoot":"","sources":["../../src/contracts/api.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,iBAAiB,EAAE,SAAS,EAAE,MAAM,wBAAwB,CAAA;AAC1E,OAAO,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,SAAS,EAAE,MAAM,uBAAuB,CAAA;AACxE,OAAO,KAAK,EAAE,WAAW,EAAE,MAAM,2BAA2B,CAAA;AAC5D,OAAO,KAAK,EAAE,UAAU,EAAE,MAAM,wBAAwB,CAAA;AAExD,YAAY,EAAE,WAAW,EAAE,UAAU,EAAE,SAAS,EAAE,iBAAiB,EAAE,CAAA;AAErE,MAAM,MAAM,YAAY,GAAG,MAAM,CAAA;AAEjC,MAAM,WAAW,aAAa;IAC7B,KAAK,EAAE,MAAM,CAAA;IACb,WAAW,CAAC,EAAE,MAAM,CAAA;IACpB,WAAW,EAAE,MAAM,CAAA;IACnB,iBAAiB,CAAC,EAAE,MAAM,CAAA;IAC1B,SAAS,CAAC,EAAE,MAAM,CAAA;CAClB;AAED,MAAM,WAAW,SAAS;IACzB,EAAE,EAAE,MAAM,CAAA;IACV,IAAI,EAAE,MAAM,CAAA;IACZ,OAAO,EAAE,MAAM,CAAA;IACf,QAAQ,EAAE,MAAM,CAAA;IAChB,WAAW,EAAE,MAAM,CAAA;IACnB,KAAK,EAAE,MAAM,EAAE,CAAA;IACf,QAAQ,EAAE,aAAa,CAAA;IACvB,IAAI,CAAC,EAAE,SAAS,CAAA;IAChB,YAAY,CAAC,EAAE,iBAAiB,CAAA;CAChC;AAED,MAAM,WAAW,YAAY;IAC5B,EAAE,EAAE,MAAM,CAAA;IACV,IAAI,EAAE,UAAU,CAAA;IAChB,QAAQ,EAAE;QACT,IAAI,EAAE,MAAM,CAAA;QACZ,SAAS,EAAE,MAAM,CAAA;KACjB,CAAA;CACD;AAED,MAAM,WAAW,oBAAoB;IACpC,IAAI,EAAE,MAAM,CAAA;IACZ,OAAO,EAAE,MAAM,CAAA;IACf,QAAQ,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAA;CAClC;AAED;;;;;;;;GAQG;AACH,MAAM,MAAM,aAAa,GACtB,QAAQ,GACR,SAAS,GACT,WAAW,GACX,QAAQ,GACR,WAAW,GACX,YAAY,
|
|
1
|
+
{"version":3,"file":"api.d.ts","sourceRoot":"","sources":["../../src/contracts/api.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,iBAAiB,EAAE,SAAS,EAAE,MAAM,wBAAwB,CAAA;AAC1E,OAAO,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,SAAS,EAAE,MAAM,uBAAuB,CAAA;AACxE,OAAO,KAAK,EAAE,WAAW,EAAE,MAAM,2BAA2B,CAAA;AAC5D,OAAO,KAAK,EAAE,UAAU,EAAE,MAAM,wBAAwB,CAAA;AAExD,YAAY,EAAE,WAAW,EAAE,UAAU,EAAE,SAAS,EAAE,iBAAiB,EAAE,CAAA;AAErE,MAAM,MAAM,YAAY,GAAG,MAAM,CAAA;AAEjC,MAAM,WAAW,aAAa;IAC7B,KAAK,EAAE,MAAM,CAAA;IACb,WAAW,CAAC,EAAE,MAAM,CAAA;IACpB,WAAW,EAAE,MAAM,CAAA;IACnB,iBAAiB,CAAC,EAAE,MAAM,CAAA;IAC1B,SAAS,CAAC,EAAE,MAAM,CAAA;CAClB;AAED,MAAM,WAAW,SAAS;IACzB,EAAE,EAAE,MAAM,CAAA;IACV,IAAI,EAAE,MAAM,CAAA;IACZ,OAAO,EAAE,MAAM,CAAA;IACf,QAAQ,EAAE,MAAM,CAAA;IAChB,WAAW,EAAE,MAAM,CAAA;IACnB,KAAK,EAAE,MAAM,EAAE,CAAA;IACf,QAAQ,EAAE,aAAa,CAAA;IACvB,IAAI,CAAC,EAAE,SAAS,CAAA;IAChB,YAAY,CAAC,EAAE,iBAAiB,CAAA;CAChC;AAED,MAAM,WAAW,YAAY;IAC5B,EAAE,EAAE,MAAM,CAAA;IACV,IAAI,EAAE,UAAU,CAAA;IAChB,QAAQ,EAAE;QACT,IAAI,EAAE,MAAM,CAAA;QACZ,SAAS,EAAE,MAAM,CAAA;KACjB,CAAA;CACD;AAED,MAAM,WAAW,oBAAoB;IACpC,IAAI,EAAE,MAAM,CAAA;IACZ,OAAO,EAAE,MAAM,CAAA;IACf,QAAQ,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAA;CAClC;AAED;;;;;;;;GAQG;AACH,MAAM,MAAM,aAAa,GACtB,QAAQ,GACR,SAAS,GACT,WAAW,GACX,QAAQ,GACR,WAAW,GACX,YAAY;AACd;;;;;;GAMG;GACD,SAAS,CAAA;AAKZ,MAAM,MAAM,aAAa,GAAG,UAAU,CAAA;AAEtC,MAAM,WAAW,OAAO;IACvB,EAAE,EAAE,KAAK,CAAA;IACT,UAAU,EAAE,SAAS,GAAG,IAAI,CAAA;IAC5B,UAAU,CAAC,EAAE,SAAS,CAAA;IACtB,QAAQ,EAAE,MAAM,CAAA;IAChB,UAAU,CAAC,EAAE,MAAM,CAAA;IACnB,MAAM,EAAE,aAAa,CAAA;IACrB,WAAW,CAAC,EAAE,aAAa,CAAA;IAC3B,UAAU,EAAE,YAAY,CAAA;IACxB,UAAU,CAAC,EAAE,YAAY,CAAA;IACzB,YAAY,CAAC,EAAE,YAAY,CAAA;IAC3B,WAAW,CAAC,EAAE,MAAM,CAAA;IACpB,KAAK,CAAC,EAAE,MAAM,CAAA;IACd,MAAM,EAAE,SAAS,CAAA;IACjB,KAAK,CAAC,EAAE,QAAQ,CAAA;IAChB,UAAU,CAAC,EAAE,MAAM,CAAA;IACnB,MAAM,CAAC,EAAE,MAAM,CAAA;IACf,UAAU,CAAC,EAAE,MAAM,CAAA;IAEnB,aAAa,CAAC,EAAE,KAAK,CAAA;IAErB,KAAK,CAAC,EAAE,MAAM,CAAA;IAEd,aAAa,CAAC,EAAE,KAAK,EAAE,CAAA;CACvB;AAED,MAAM,WAAW,gBAAgB;IAChC,MAAM,EAAE,KAAK,CAAA;IACb,QAAQ,EAAE,MAAM,CAAA;IAChB,KAAK,EAAE,MAAM,CAAA;IACb,MAAM,EAAE,aAAa,CAAA;IACrB,QAAQ,EAAE,gBAAgB,EAAE,CAAA;CAC5B;AAED,MAAM,MAAM,iBAAiB,GAAG,MAAM,GAAG,MAAM,CAAA;AAE/C,MAAM,WAAW,SAAS;IACzB,KAAK,CAAC,EAAE,MAAM,CAAA;IACd,WAAW,CAAC,EAAE,MAAM,CAAA;IACpB,WAAW,CAAC,EAAE,MAAM,CAAA;IACpB,iBAAiB,CAAC,EAAE,MAAM,CAAA;IAC1B,SAAS,CAAC,EAAE,MAAM,CAAA;IAClB,cAAc,CAAC,EAAE,iBAAiB,CAAA;IAElC,YAAY,CAAC,EAAE,MAAM,CAAA;CACrB;AAED,MAAM,WAAW,QAAQ;IACxB,YAAY,EAAE,MAAM,CAAA;IACpB,aAAa,EAAE,MAAM,CAAA;IACrB,YAAY,EAAE,MAAM,CAAA;IACpB,cAAc,CAAC,EAAE,MAAM,CAAA;CACvB;AAED,MAAM,WAAW,gBAAgB;IAChC,QAAQ,EAAE,MAAM,CAAA;IAChB,MAAM,EAAE,SAAS,CAAA;IACjB,GAAG,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IAC5B,MAAM,CAAC,EAAE,OAAO,CAAA;CAChB;AAED,MAAM,WAAW,yBAAyB;IACzC,QAAQ,EAAE,MAAM,CAAA;IAChB,OAAO,EAAE,MAAM,CAAA;IACf,MAAM,EAAE,SAAS,CAAA;IACjB,GAAG,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;CAC5B;AAED,MAAM,MAAM,eAAe,GACxB,aAAa,GACb,eAAe,GACf,YAAY,GACZ,eAAe,GACf,YAAY,GACZ,cAAc,GACd,mBAAmB,GACnB,qBAAqB;AACvB;;;;GAIG;GACD,sBAAsB;AACxB,gDAAgD;GAC9C,qBAAqB;AACvB;;;;GAIG;GACD,mBAAmB,GACnB,iBAAiB,GACjB,qBAAqB;AACvB;;;;;;GAMG;GACD,gBAAgB,GAChB,gBAAgB;AAClB,0EAA0E;GACxE,eAAe,GACf,gBAAgB,GAChB,YAAY,GAKZ,oBAAoB,GACpB,kBAAkB,GAClB,sBAAsB,GACtB,aAAa,GACb,iBAAiB,GACjB,eAAe,GACf,mBAAmB;AACrB;;;;GAIG;GACD,gBAAgB,GAChB,mBAAmB,GACnB,kBAAkB,GAClB,kBAAkB,GAClB,oBAAoB,GACpB,kBAAkB,GAClB,kBAAkB,GAClB,YAAY,GACZ,eAAe,GACf,eAAe,GACf,mBAAmB,GACnB,eAAe,GACf,iBAAiB,GACjB,cAAc,GACd,gBAAgB,GAChB,cAAc,GACd,cAAc,GACd,uBAAuB,GACvB,uBAAuB,GACvB,iBAAiB,GACjB,cAAc,GACd,mBAAmB,CAAA;AAEtB,MAAM,WAAW,WAAW;IAC3B,KAAK,EAAE,eAAe,CAAA;IACtB,IAAI,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAA;CAC7B;AAED,MAAM,WAAW,gBAAgB;IAChC,KAAK,CAAC,EAAE,MAAM,CAAA;IACd,KAAK,CAAC,EAAE,MAAM,CAAA;IACd,MAAM,CAAC,EAAE,MAAM,CAAA;IACf,KAAK,CAAC,EAAE,KAAK,GAAG,MAAM,CAAA;CACtB;AAED,MAAM,WAAW,iBAAiB,CAAC,CAAC;IACnC,IAAI,EAAE,CAAC,EAAE,CAAA;IACT,QAAQ,EAAE,OAAO,CAAA;IACjB,QAAQ,EAAE,MAAM,GAAG,IAAI,CAAA;IACvB,OAAO,EAAE,MAAM,GAAG,IAAI,CAAA;CACtB;AAED,MAAM,MAAM,YAAY,GACrB,kBAAkB,GAClB,sBAAsB,GACtB,WAAW,GACX,UAAU,GACV,qBAAqB,GACrB,gBAAgB,CAAA;AAEnB,MAAM,WAAW,QAAQ;IACxB,KAAK,EAAE;QACN,IAAI,EAAE,MAAM,CAAA;QACZ,OAAO,EAAE,MAAM,CAAA;QACf,IAAI,EAAE,YAAY,CAAA;QAClB,KAAK,CAAC,EAAE,MAAM,CAAA;KACd,CAAA;CACD"}
|
|
@@ -0,0 +1,17 @@
|
|
|
1
|
+
import type { RunStatus } from '../types/run/status.js';
|
|
2
|
+
import type { WireRunStatus } from './api.js';
|
|
3
|
+
/**
|
|
4
|
+
* Collapse a domain run status onto the wire enum.
|
|
5
|
+
*
|
|
6
|
+
* The mapping was documented on `WireRunStatus` and implemented nowhere, so
|
|
7
|
+
* every surface that needed it open-coded the collapse or, more often,
|
|
8
|
+
* passed a domain status where a wire one was expected and relied on the
|
|
9
|
+
* two enums happening to share spellings. They do not share all of them:
|
|
10
|
+
* `succeeded` and `awaiting_*` have no wire counterpart at all.
|
|
11
|
+
*
|
|
12
|
+
* Total over the domain enum, and exhaustive by construction so a new
|
|
13
|
+
* domain status is a type error here rather than an `undefined` on the
|
|
14
|
+
* wire.
|
|
15
|
+
*/
|
|
16
|
+
export declare function toWireRunStatus(status: RunStatus): WireRunStatus;
|
|
17
|
+
//# sourceMappingURL=run-status.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"run-status.d.ts","sourceRoot":"","sources":["../../src/contracts/run-status.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,SAAS,EAAE,MAAM,wBAAwB,CAAA;AACvD,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,UAAU,CAAA;AAE7C;;;;;;;;;;;;GAYG;AACH,wBAAgB,eAAe,CAAC,MAAM,EAAE,SAAS,GAAG,aAAa,CA0BhE"}
|
|
@@ -0,0 +1,41 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* Collapse a domain run status onto the wire enum.
|
|
3
|
+
*
|
|
4
|
+
* The mapping was documented on `WireRunStatus` and implemented nowhere, so
|
|
5
|
+
* every surface that needed it open-coded the collapse or, more often,
|
|
6
|
+
* passed a domain status where a wire one was expected and relied on the
|
|
7
|
+
* two enums happening to share spellings. They do not share all of them:
|
|
8
|
+
* `succeeded` and `awaiting_*` have no wire counterpart at all.
|
|
9
|
+
*
|
|
10
|
+
* Total over the domain enum, and exhaustive by construction so a new
|
|
11
|
+
* domain status is a type error here rather than an `undefined` on the
|
|
12
|
+
* wire.
|
|
13
|
+
*/
|
|
14
|
+
export function toWireRunStatus(status) {
|
|
15
|
+
switch (status) {
|
|
16
|
+
case 'queued':
|
|
17
|
+
return 'queued';
|
|
18
|
+
case 'running':
|
|
19
|
+
return 'running';
|
|
20
|
+
// A run waiting on a human is still a live run to a wire consumer:
|
|
21
|
+
// it has not settled, and nothing it can do will make it settle.
|
|
22
|
+
// `awaiting_hitl_resolution` is the persisted variant — the user is
|
|
23
|
+
// absent and the run survives until answered or cancelled — which is
|
|
24
|
+
// waiting, not finished.
|
|
25
|
+
case 'awaiting_hitl':
|
|
26
|
+
case 'awaiting_hitl_resolution':
|
|
27
|
+
case 'awaiting_subsession':
|
|
28
|
+
return 'running';
|
|
29
|
+
case 'succeeded':
|
|
30
|
+
return 'completed';
|
|
31
|
+
case 'failed':
|
|
32
|
+
return 'failed';
|
|
33
|
+
case 'cancelled':
|
|
34
|
+
return 'cancelled';
|
|
35
|
+
default: {
|
|
36
|
+
const _exhaustive = status;
|
|
37
|
+
throw new Error(`Unmapped run status: ${_exhaustive}`);
|
|
38
|
+
}
|
|
39
|
+
}
|
|
40
|
+
}
|
|
41
|
+
//# sourceMappingURL=run-status.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"run-status.js","sourceRoot":"","sources":["../../src/contracts/run-status.ts"],"names":[],"mappings":"AAGA;;;;;;;;;;;;GAYG;AACH,MAAM,UAAU,eAAe,CAAC,MAAiB;IAChD,QAAQ,MAAM,EAAE,CAAC;QAChB,KAAK,QAAQ;YACZ,OAAO,QAAQ,CAAA;QAChB,KAAK,SAAS;YACb,OAAO,SAAS,CAAA;QACjB,mEAAmE;QACnE,iEAAiE;QACjE,oEAAoE;QACpE,qEAAqE;QACrE,yBAAyB;QACzB,KAAK,eAAe,CAAC;QACrB,KAAK,0BAA0B,CAAC;QAChC,KAAK,qBAAqB;YACzB,OAAO,SAAS,CAAA;QACjB,KAAK,WAAW;YACf,OAAO,WAAW,CAAA;QACnB,KAAK,QAAQ;YACZ,OAAO,QAAQ,CAAA;QAChB,KAAK,WAAW;YACf,OAAO,WAAW,CAAA;QACnB,OAAO,CAAC,CAAC,CAAC;YACT,MAAM,WAAW,GAAU,MAAM,CAAA;YACjC,MAAM,IAAI,KAAK,CAAC,wBAAwB,WAAqB,EAAE,CAAC,CAAA;QACjE,CAAC;IACF,CAAC;AACF,CAAC"}
|
|
@@ -32,12 +32,12 @@ export declare const CreateMessageSchema: z.ZodObject<{
|
|
|
32
32
|
content: z.ZodString;
|
|
33
33
|
metadata: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodUnknown>>;
|
|
34
34
|
}, "strict", z.ZodTypeAny, {
|
|
35
|
-
role: "user";
|
|
36
35
|
content: string;
|
|
36
|
+
role: "user";
|
|
37
37
|
metadata?: Record<string, unknown> | undefined;
|
|
38
38
|
}, {
|
|
39
|
-
role: "user";
|
|
40
39
|
content: string;
|
|
40
|
+
role: "user";
|
|
41
41
|
metadata?: Record<string, unknown> | undefined;
|
|
42
42
|
}>;
|
|
43
43
|
export declare const CreateRunSchema: z.ZodObject<{
|
|
@@ -70,7 +70,6 @@ export declare const CreateRunSchema: z.ZodObject<{
|
|
|
70
70
|
env: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodString>>;
|
|
71
71
|
stream: z.ZodOptional<z.ZodBoolean>;
|
|
72
72
|
}, "strict", z.ZodTypeAny, {
|
|
73
|
-
agent_id: string;
|
|
74
73
|
config: {
|
|
75
74
|
timeoutMs?: number | undefined;
|
|
76
75
|
model?: string | undefined;
|
|
@@ -80,10 +79,10 @@ export declare const CreateRunSchema: z.ZodObject<{
|
|
|
80
79
|
permissionMode?: "plan" | "auto" | undefined;
|
|
81
80
|
systemPrompt?: string | undefined;
|
|
82
81
|
};
|
|
82
|
+
agent_id: string;
|
|
83
83
|
env?: Record<string, string> | undefined;
|
|
84
84
|
stream?: boolean | undefined;
|
|
85
85
|
}, {
|
|
86
|
-
agent_id: string;
|
|
87
86
|
config: {
|
|
88
87
|
timeoutMs?: number | undefined;
|
|
89
88
|
model?: string | undefined;
|
|
@@ -93,6 +92,7 @@ export declare const CreateRunSchema: z.ZodObject<{
|
|
|
93
92
|
permissionMode?: "plan" | "auto" | undefined;
|
|
94
93
|
systemPrompt?: string | undefined;
|
|
95
94
|
};
|
|
95
|
+
agent_id: string;
|
|
96
96
|
env?: Record<string, string> | undefined;
|
|
97
97
|
stream?: boolean | undefined;
|
|
98
98
|
}>;
|
|
@@ -127,7 +127,6 @@ export declare const CreateStatelessRunSchema: z.ZodObject<{
|
|
|
127
127
|
env: z.ZodOptional<z.ZodRecord<z.ZodString, z.ZodString>>;
|
|
128
128
|
}, "strict", z.ZodTypeAny, {
|
|
129
129
|
message: string;
|
|
130
|
-
agent_id: string;
|
|
131
130
|
config: {
|
|
132
131
|
timeoutMs?: number | undefined;
|
|
133
132
|
model?: string | undefined;
|
|
@@ -137,10 +136,10 @@ export declare const CreateStatelessRunSchema: z.ZodObject<{
|
|
|
137
136
|
permissionMode?: "plan" | "auto" | undefined;
|
|
138
137
|
systemPrompt?: string | undefined;
|
|
139
138
|
};
|
|
139
|
+
agent_id: string;
|
|
140
140
|
env?: Record<string, string> | undefined;
|
|
141
141
|
}, {
|
|
142
142
|
message: string;
|
|
143
|
-
agent_id: string;
|
|
144
143
|
config: {
|
|
145
144
|
timeoutMs?: number | undefined;
|
|
146
145
|
model?: string | undefined;
|
|
@@ -150,6 +149,7 @@ export declare const CreateStatelessRunSchema: z.ZodObject<{
|
|
|
150
149
|
permissionMode?: "plan" | "auto" | undefined;
|
|
151
150
|
systemPrompt?: string | undefined;
|
|
152
151
|
};
|
|
152
|
+
agent_id: string;
|
|
153
153
|
env?: Record<string, string> | undefined;
|
|
154
154
|
}>;
|
|
155
155
|
export declare const PaginationSchema: z.ZodObject<{
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"case-deadline.test.d.ts","sourceRoot":"","sources":["../../../src/eval/__tests__/case-deadline.test.ts"],"names":[],"mappings":""}
|
|
@@ -0,0 +1,128 @@
|
|
|
1
|
+
import { describe, expect, it } from 'vitest';
|
|
2
|
+
import { runExperiment } from '../experiment.js';
|
|
3
|
+
/**
|
|
4
|
+
* `executeCase` was a bare await, so a `run` closure that never settled
|
|
5
|
+
* blocked its worker and `runExperiment` never returned — no report, no
|
|
6
|
+
* partial results, nothing to read.
|
|
7
|
+
*
|
|
8
|
+
* Narrower than it sounds: the documented path inherits three deadlines
|
|
9
|
+
* from the runtime it drives. The residual is a closure that does not go
|
|
10
|
+
* through `query()`, and a mid-iteration provider stall the
|
|
11
|
+
* between-iterations guard cannot see. Both are reachable, and neither is
|
|
12
|
+
* the suite's to absorb silently.
|
|
13
|
+
*/
|
|
14
|
+
const emptyRun = () => ({
|
|
15
|
+
output: 'ok',
|
|
16
|
+
steps: [],
|
|
17
|
+
toolCalls: [],
|
|
18
|
+
totalTokens: 0,
|
|
19
|
+
totalCostUsd: 0,
|
|
20
|
+
durationMs: 0,
|
|
21
|
+
});
|
|
22
|
+
const never = () => new Promise(() => { });
|
|
23
|
+
const scorer = {
|
|
24
|
+
name: 'always-one',
|
|
25
|
+
score: async () => ({ score: 1, reason: 'fine' }),
|
|
26
|
+
};
|
|
27
|
+
describe('a case that never settles', () => {
|
|
28
|
+
it('is reported instead of hanging the suite', async () => {
|
|
29
|
+
const report = await runExperiment({
|
|
30
|
+
name: 'deadline',
|
|
31
|
+
cases: [{ name: 'hangs', input: null }],
|
|
32
|
+
scorers: [scorer],
|
|
33
|
+
timeoutMs: 20,
|
|
34
|
+
run: never,
|
|
35
|
+
});
|
|
36
|
+
expect(report.cases).toHaveLength(1);
|
|
37
|
+
expect(report.cases[0]?.run.error).toMatch(/timed out after 20ms/);
|
|
38
|
+
});
|
|
39
|
+
it('does not take the rest of the suite with it', async () => {
|
|
40
|
+
// Forty cases should not be lost to one that hung — the same rule
|
|
41
|
+
// the harness already applied to a case that threw.
|
|
42
|
+
const report = await runExperiment({
|
|
43
|
+
name: 'deadline',
|
|
44
|
+
cases: [
|
|
45
|
+
{ name: 'hangs', input: null },
|
|
46
|
+
{ name: 'fine', input: null },
|
|
47
|
+
],
|
|
48
|
+
scorers: [scorer],
|
|
49
|
+
timeoutMs: 20,
|
|
50
|
+
run: async (_input, evalCase) => (evalCase.name === 'hangs' ? await never() : emptyRun()),
|
|
51
|
+
});
|
|
52
|
+
expect(report.cases.map((c) => c.case).sort()).toEqual(['fine', 'hangs']);
|
|
53
|
+
expect(report.passed).toBe(1);
|
|
54
|
+
expect(report.failed).toBe(1);
|
|
55
|
+
});
|
|
56
|
+
it('reports the time it actually burned, not zero', async () => {
|
|
57
|
+
// A case that spent its whole deadline is the most interesting
|
|
58
|
+
// number in the report; zero would hide it.
|
|
59
|
+
const report = await runExperiment({
|
|
60
|
+
name: 'deadline',
|
|
61
|
+
cases: [{ name: 'hangs', input: null }],
|
|
62
|
+
scorers: [scorer],
|
|
63
|
+
timeoutMs: 30,
|
|
64
|
+
run: never,
|
|
65
|
+
});
|
|
66
|
+
expect(report.cases[0]?.run.durationMs).toBeGreaterThanOrEqual(20);
|
|
67
|
+
});
|
|
68
|
+
});
|
|
69
|
+
describe('the signal handed to run', () => {
|
|
70
|
+
it('fires when the deadline passes, so a cooperating closure can stop', async () => {
|
|
71
|
+
let aborted = false;
|
|
72
|
+
await runExperiment({
|
|
73
|
+
name: 'deadline',
|
|
74
|
+
cases: [{ name: 'watches', input: null }],
|
|
75
|
+
scorers: [scorer],
|
|
76
|
+
timeoutMs: 20,
|
|
77
|
+
run: async (_input, _case, signal) => {
|
|
78
|
+
signal.addEventListener('abort', () => {
|
|
79
|
+
aborted = true;
|
|
80
|
+
});
|
|
81
|
+
return await never();
|
|
82
|
+
},
|
|
83
|
+
});
|
|
84
|
+
expect(aborted).toBe(true);
|
|
85
|
+
});
|
|
86
|
+
it('stays quiet for a case that finished in time', async () => {
|
|
87
|
+
// A spurious abort after the work is done would train a closure to
|
|
88
|
+
// ignore the signal entirely.
|
|
89
|
+
let aborted = false;
|
|
90
|
+
await runExperiment({
|
|
91
|
+
name: 'deadline',
|
|
92
|
+
cases: [{ name: 'fast', input: null }],
|
|
93
|
+
scorers: [scorer],
|
|
94
|
+
timeoutMs: 5_000,
|
|
95
|
+
run: async (_input, _case, signal) => {
|
|
96
|
+
signal.addEventListener('abort', () => {
|
|
97
|
+
aborted = true;
|
|
98
|
+
});
|
|
99
|
+
return emptyRun();
|
|
100
|
+
},
|
|
101
|
+
});
|
|
102
|
+
expect(aborted).toBe(false);
|
|
103
|
+
});
|
|
104
|
+
});
|
|
105
|
+
describe('a suite with no deadline set', () => {
|
|
106
|
+
it('behaves exactly as before', async () => {
|
|
107
|
+
const report = await runExperiment({
|
|
108
|
+
name: 'no-deadline',
|
|
109
|
+
cases: [{ name: 'fine', input: null }],
|
|
110
|
+
scorers: [scorer],
|
|
111
|
+
run: async () => emptyRun(),
|
|
112
|
+
});
|
|
113
|
+
expect(report.passed).toBe(1);
|
|
114
|
+
expect(report.cases[0]?.run.error).toBeUndefined();
|
|
115
|
+
});
|
|
116
|
+
it('still turns a throw into a result rather than a crash', async () => {
|
|
117
|
+
const report = await runExperiment({
|
|
118
|
+
name: 'no-deadline',
|
|
119
|
+
cases: [{ name: 'throws', input: null }],
|
|
120
|
+
scorers: [scorer],
|
|
121
|
+
run: async () => {
|
|
122
|
+
throw new Error('broken case');
|
|
123
|
+
},
|
|
124
|
+
});
|
|
125
|
+
expect(report.cases[0]?.run.error).toBe('broken case');
|
|
126
|
+
});
|
|
127
|
+
});
|
|
128
|
+
//# sourceMappingURL=case-deadline.test.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"case-deadline.test.js","sourceRoot":"","sources":["../../../src/eval/__tests__/case-deadline.test.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,MAAM,EAAE,EAAE,EAAE,MAAM,QAAQ,CAAA;AAE7C,OAAO,EAAE,aAAa,EAAE,MAAM,kBAAkB,CAAA;AAGhD;;;;;;;;;;GAUG;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,MAAM,KAAK,GAAG,GAAG,EAAE,CAAC,IAAI,OAAO,CAAU,GAAG,EAAE,GAAE,CAAC,CAAC,CAAA;AAElD,MAAM,MAAM,GAAG;IACd,IAAI,EAAE,YAAY;IAClB,KAAK,EAAE,KAAK,IAAI,EAAE,CAAC,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE,MAAM,EAAE,MAAM,EAAE,CAAC;CACjD,CAAA;AAED,QAAQ,CAAC,2BAA2B,EAAE,GAAG,EAAE;IAC1C,EAAE,CAAC,0CAA0C,EAAE,KAAK,IAAI,EAAE;QACzD,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,IAAI,EAAE,UAAU;YAChB,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,OAAO,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC;YACvC,OAAO,EAAE,CAAC,MAAM,CAAC;YACjB,SAAS,EAAE,EAAE;YACb,GAAG,EAAE,KAAK;SACV,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,OAAO,CAAC,sBAAsB,CAAC,CAAA;IACnE,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,6CAA6C,EAAE,KAAK,IAAI,EAAE;QAC5D,kEAAkE;QAClE,oDAAoD;QACpD,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,IAAI,EAAE,UAAU;YAChB,KAAK,EAAE;gBACN,EAAE,IAAI,EAAE,OAAO,EAAE,KAAK,EAAE,IAAI,EAAE;gBAC9B,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,IAAI,EAAE;aAC7B;YACD,OAAO,EAAE,CAAC,MAAM,CAAC;YACjB,SAAS,EAAE,EAAE;YACb,GAAG,EAAE,KAAK,EAAE,MAAM,EAAE,QAAQ,EAAE,EAAE,CAAC,CAAC,QAAQ,CAAC,IAAI,KAAK,OAAO,CAAC,CAAC,CAAC,MAAM,KAAK,EAAE,CAAC,CAAC,CAAC,QAAQ,EAAE,CAAC;SACzF,CAAC,CAAA;QAEF,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,OAAO,CAAC,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC,CAAA;QACzE,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;IAC9B,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,+CAA+C,EAAE,KAAK,IAAI,EAAE;QAC9D,+DAA+D;QAC/D,4CAA4C;QAC5C,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,IAAI,EAAE,UAAU;YAChB,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,OAAO,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC;YACvC,OAAO,EAAE,CAAC,MAAM,CAAC;YACjB,SAAS,EAAE,EAAE;YACb,GAAG,EAAE,KAAK;SACV,CAAC,CAAA;QAEF,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,GAAG,CAAC,UAAU,CAAC,CAAC,sBAAsB,CAAC,EAAE,CAAC,CAAA;IACnE,CAAC,CAAC,CAAA;AACH,CAAC,CAAC,CAAA;AAEF,QAAQ,CAAC,0BAA0B,EAAE,GAAG,EAAE;IACzC,EAAE,CAAC,mEAAmE,EAAE,KAAK,IAAI,EAAE;QAClF,IAAI,OAAO,GAAG,KAAK,CAAA;QACnB,MAAM,aAAa,CAAC;YACnB,IAAI,EAAE,UAAU;YAChB,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,SAAS,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC;YACzC,OAAO,EAAE,CAAC,MAAM,CAAC;YACjB,SAAS,EAAE,EAAE;YACb,GAAG,EAAE,KAAK,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE;gBACpC,MAAM,CAAC,gBAAgB,CAAC,OAAO,EAAE,GAAG,EAAE;oBACrC,OAAO,GAAG,IAAI,CAAA;gBACf,CAAC,CAAC,CAAA;gBACF,OAAO,MAAM,KAAK,EAAE,CAAA;YACrB,CAAC;SACD,CAAC,CAAA;QAEF,MAAM,CAAC,OAAO,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;IAC3B,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,8CAA8C,EAAE,KAAK,IAAI,EAAE;QAC7D,mEAAmE;QACnE,8BAA8B;QAC9B,IAAI,OAAO,GAAG,KAAK,CAAA;QACnB,MAAM,aAAa,CAAC;YACnB,IAAI,EAAE,UAAU;YAChB,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC;YACtC,OAAO,EAAE,CAAC,MAAM,CAAC;YACjB,SAAS,EAAE,KAAK;YAChB,GAAG,EAAE,KAAK,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE;gBACpC,MAAM,CAAC,gBAAgB,CAAC,OAAO,EAAE,GAAG,EAAE;oBACrC,OAAO,GAAG,IAAI,CAAA;gBACf,CAAC,CAAC,CAAA;gBACF,OAAO,QAAQ,EAAE,CAAA;YAClB,CAAC;SACD,CAAC,CAAA;QAEF,MAAM,CAAC,OAAO,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;IAC5B,CAAC,CAAC,CAAA;AACH,CAAC,CAAC,CAAA;AAEF,QAAQ,CAAC,8BAA8B,EAAE,GAAG,EAAE;IAC7C,EAAE,CAAC,2BAA2B,EAAE,KAAK,IAAI,EAAE;QAC1C,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,IAAI,EAAE,aAAa;YACnB,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC;YACtC,OAAO,EAAE,CAAC,MAAM,CAAC;YACjB,GAAG,EAAE,KAAK,IAAI,EAAE,CAAC,QAAQ,EAAE;SAC3B,CAAC,CAAA;QAEF,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QAC7B,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,GAAG,CAAC,KAAK,CAAC,CAAC,aAAa,EAAE,CAAA;IACnD,CAAC,CAAC,CAAA;IAEF,EAAE,CAAC,uDAAuD,EAAE,KAAK,IAAI,EAAE;QACtE,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC;YAClC,IAAI,EAAE,aAAa;YACnB,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,QAAQ,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC;YACxC,OAAO,EAAE,CAAC,MAAM,CAAC;YACjB,GAAG,EAAE,KAAK,IAAI,EAAE;gBACf,MAAM,IAAI,KAAK,CAAC,aAAa,CAAC,CAAA;YAC/B,CAAC;SACD,CAAC,CAAA;QAEF,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,GAAG,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,aAAa,CAAC,CAAA;IACvD,CAAC,CAAC,CAAA;AACH,CAAC,CAAC,CAAA"}
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"end-to-end.test.d.ts","sourceRoot":"","sources":["../../../src/eval/__tests__/end-to-end.test.ts"],"names":[],"mappings":""}
|
|
@@ -0,0 +1,223 @@
|
|
|
1
|
+
import { describe, expect, it, vi } from 'vitest';
|
|
2
|
+
import { MockLLMProvider } from '../../provider/mock.js';
|
|
3
|
+
import { ToolExecutor } from '../../runtime/query/executor.js';
|
|
4
|
+
import { IterationOrchestrator } from '../../runtime/query/iteration/index.js';
|
|
5
|
+
import { ActivityStore } from '../../store/activity/memory.js';
|
|
6
|
+
import { hasToolCall } from '../../types/run/step.js';
|
|
7
|
+
import { runExperiment } from '../experiment.js';
|
|
8
|
+
import { evalRunFromRun } from '../from-run.js';
|
|
9
|
+
import { completionScorer, trajectoryScorer } from '../scorers.js';
|
|
10
|
+
/**
|
|
11
|
+
* The harness against the REAL loop, driven by the scriptable mock.
|
|
12
|
+
*
|
|
13
|
+
* The unit tests above check the scorers in isolation; this checks the
|
|
14
|
+
* thing that actually matters — that a behavior change in the agent shows
|
|
15
|
+
* up as a score drop. Every piece this depends on had to land first:
|
|
16
|
+
* `Run.steps` (otherwise a trajectory scorer would correlate raw events by
|
|
17
|
+
* iteration number) and a mock that can emit tool calls (otherwise the
|
|
18
|
+
* loop cannot be driven at all).
|
|
19
|
+
*/
|
|
20
|
+
const RUN_ID = 'run_eval';
|
|
21
|
+
function makeLogger() {
|
|
22
|
+
const stub = { info: vi.fn(), warn: vi.fn(), error: vi.fn(), debug: vi.fn() };
|
|
23
|
+
return { ...stub, child: vi.fn(() => ({ ...stub, child: vi.fn() })) };
|
|
24
|
+
}
|
|
25
|
+
/** Drive the loop with a scripted model and return the finished `Run`. */
|
|
26
|
+
async function driveAgent(turns) {
|
|
27
|
+
const messages = [];
|
|
28
|
+
let iteration = 0;
|
|
29
|
+
let stopReason;
|
|
30
|
+
const log = makeLogger();
|
|
31
|
+
const tools = {
|
|
32
|
+
get: vi.fn((name) => ({
|
|
33
|
+
name,
|
|
34
|
+
isConcurrencySafe: () => true,
|
|
35
|
+
isReadOnly: () => true,
|
|
36
|
+
isDestructive: () => false,
|
|
37
|
+
})),
|
|
38
|
+
execute: vi.fn(async (name) => ({ success: true, output: `${name} ok` })),
|
|
39
|
+
has: vi.fn(() => true),
|
|
40
|
+
listNames: vi.fn(() => []),
|
|
41
|
+
getAvailability: vi.fn(() => 'active'),
|
|
42
|
+
toLLMTools: vi.fn(() => []),
|
|
43
|
+
register: vi.fn(),
|
|
44
|
+
unregister: vi.fn(),
|
|
45
|
+
};
|
|
46
|
+
const activityStore = new ActivityStore(RUN_ID, {
|
|
47
|
+
enabled: false,
|
|
48
|
+
trackToolCalls: false,
|
|
49
|
+
trackLlmTurns: false,
|
|
50
|
+
});
|
|
51
|
+
const runMgr = {
|
|
52
|
+
id: RUN_ID,
|
|
53
|
+
messages,
|
|
54
|
+
tokenUsage: {
|
|
55
|
+
promptTokens: 0,
|
|
56
|
+
completionTokens: 0,
|
|
57
|
+
totalTokens: 0,
|
|
58
|
+
cachedTokens: 0,
|
|
59
|
+
cacheWriteTokens: 0,
|
|
60
|
+
},
|
|
61
|
+
costInfo: { inputCostPer1M: 0, outputCostPer1M: 0, totalCost: 0, cacheDiscount: 0 },
|
|
62
|
+
get currentIteration() {
|
|
63
|
+
return iteration;
|
|
64
|
+
},
|
|
65
|
+
incrementIteration: () => ++iteration,
|
|
66
|
+
pushMessage: (m) => {
|
|
67
|
+
messages.push(m);
|
|
68
|
+
},
|
|
69
|
+
recordTurnUsage: vi.fn(),
|
|
70
|
+
accumulateUsage: vi.fn(),
|
|
71
|
+
clearLastPromptTokens: vi.fn(),
|
|
72
|
+
lastPromptTokens: undefined,
|
|
73
|
+
setStopReason: (r) => {
|
|
74
|
+
stopReason = r;
|
|
75
|
+
},
|
|
76
|
+
setStructuredOutput: vi.fn(),
|
|
77
|
+
markCancelled: vi.fn(),
|
|
78
|
+
};
|
|
79
|
+
const orchestrator = new IterationOrchestrator({
|
|
80
|
+
provider: new MockLLMProvider({ turns: turns }),
|
|
81
|
+
runConfig: { model: 'mock', maxIterations: 10 },
|
|
82
|
+
tools,
|
|
83
|
+
runMgr,
|
|
84
|
+
toolExecutor: new ToolExecutor({
|
|
85
|
+
tools,
|
|
86
|
+
runId: RUN_ID,
|
|
87
|
+
workingDirectory: '/tmp',
|
|
88
|
+
permissionMode: 'auto',
|
|
89
|
+
env: {},
|
|
90
|
+
abortSignal: new AbortController().signal,
|
|
91
|
+
}, activityStore, async () => { }, log),
|
|
92
|
+
activityStore,
|
|
93
|
+
abortController: new AbortController(),
|
|
94
|
+
log,
|
|
95
|
+
emitEvent: async () => { },
|
|
96
|
+
drainPending: function* () { },
|
|
97
|
+
checkpointMgr: { create: async () => ({ id: 'cp_1' }) },
|
|
98
|
+
planManager: { active: undefined },
|
|
99
|
+
resumeHandler: async () => ({ action: 'approve_tools' }),
|
|
100
|
+
stopWhen: hasToolCall('finish'),
|
|
101
|
+
guard: {
|
|
102
|
+
beforeIteration: () => ({
|
|
103
|
+
shouldStop: iteration >= 10,
|
|
104
|
+
forceFinalize: false,
|
|
105
|
+
isCancelled: false,
|
|
106
|
+
stopReason: 'max_iterations',
|
|
107
|
+
}),
|
|
108
|
+
},
|
|
109
|
+
});
|
|
110
|
+
const gen = orchestrator.runLoop();
|
|
111
|
+
let next = await gen.next();
|
|
112
|
+
while (!next.done)
|
|
113
|
+
next = await gen.next();
|
|
114
|
+
return {
|
|
115
|
+
id: RUN_ID,
|
|
116
|
+
status: 'completed',
|
|
117
|
+
messages,
|
|
118
|
+
tokenUsage: runMgr.tokenUsage,
|
|
119
|
+
costInfo: runMgr.costInfo,
|
|
120
|
+
currentIteration: iteration,
|
|
121
|
+
startedAt: Date.now() - 10,
|
|
122
|
+
endedAt: Date.now(),
|
|
123
|
+
steps: orchestrator.getSteps(),
|
|
124
|
+
...(stopReason ? { stopReason } : {}),
|
|
125
|
+
result: 'done',
|
|
126
|
+
};
|
|
127
|
+
}
|
|
128
|
+
/** The trajectory a healthy agent takes for this task. */
|
|
129
|
+
const GOLDEN = [
|
|
130
|
+
{
|
|
131
|
+
name: 'reads before editing, then finishes',
|
|
132
|
+
input: 'edit the file',
|
|
133
|
+
expectedTools: ['read', 'edit', 'finish'],
|
|
134
|
+
},
|
|
135
|
+
];
|
|
136
|
+
const HEALTHY = [
|
|
137
|
+
{ toolCalls: [{ name: 'read' }] },
|
|
138
|
+
{ toolCalls: [{ name: 'edit' }] },
|
|
139
|
+
{ toolCalls: [{ name: 'finish' }] },
|
|
140
|
+
];
|
|
141
|
+
describe('the harness scores a real run', () => {
|
|
142
|
+
it('projects a finished Run into the shape scorers consume', async () => {
|
|
143
|
+
const run = await driveAgent(HEALTHY);
|
|
144
|
+
const projected = evalRunFromRun(run);
|
|
145
|
+
expect(projected.toolCalls).toEqual(['read', 'edit', 'finish']);
|
|
146
|
+
expect(projected.steps).toHaveLength(3);
|
|
147
|
+
expect(projected.stopReason).toBe('stop_condition');
|
|
148
|
+
});
|
|
149
|
+
it('scores the golden trajectory 1', async () => {
|
|
150
|
+
const report = await runExperiment({
|
|
151
|
+
name: 'file-editing',
|
|
152
|
+
cases: GOLDEN,
|
|
153
|
+
scorers: [trajectoryScorer(), completionScorer(['stop_condition'])],
|
|
154
|
+
run: async () => evalRunFromRun(await driveAgent(HEALTHY)),
|
|
155
|
+
});
|
|
156
|
+
expect(report.mean).toBe(1);
|
|
157
|
+
expect(report.failed).toBe(0);
|
|
158
|
+
});
|
|
159
|
+
});
|
|
160
|
+
describe('the harness catches a behavior regression', () => {
|
|
161
|
+
it('drops the score when the agent skips a step', async () => {
|
|
162
|
+
// The regression this is for: a tool-description change that makes the
|
|
163
|
+
// agent edit without reading first. Final-answer scoring cannot see
|
|
164
|
+
// it — the file still gets edited.
|
|
165
|
+
const regressed = [{ toolCalls: [{ name: 'edit' }] }, { toolCalls: [{ name: 'finish' }] }];
|
|
166
|
+
const report = await runExperiment({
|
|
167
|
+
name: 'file-editing',
|
|
168
|
+
cases: GOLDEN,
|
|
169
|
+
scorers: [trajectoryScorer()],
|
|
170
|
+
run: async () => evalRunFromRun(await driveAgent(regressed)),
|
|
171
|
+
});
|
|
172
|
+
expect(report.mean).toBeLessThan(1);
|
|
173
|
+
expect(report.failed).toBe(1);
|
|
174
|
+
expect(report.cases[0]?.scores.trajectory?.reason).toContain('read');
|
|
175
|
+
});
|
|
176
|
+
it('drops the score when the agent becomes wasteful', async () => {
|
|
177
|
+
// The regression this is for: a `search_tools` top-k change that makes
|
|
178
|
+
// the agent probe before acting. The answer is identical; the bill is
|
|
179
|
+
// not.
|
|
180
|
+
const wasteful = [
|
|
181
|
+
{ toolCalls: [{ name: 'ls' }] },
|
|
182
|
+
{ toolCalls: [{ name: 'glob' }] },
|
|
183
|
+
{ toolCalls: [{ name: 'read' }] },
|
|
184
|
+
{ toolCalls: [{ name: 'edit' }] },
|
|
185
|
+
{ toolCalls: [{ name: 'finish' }] },
|
|
186
|
+
];
|
|
187
|
+
const report = await runExperiment({
|
|
188
|
+
name: 'file-editing',
|
|
189
|
+
cases: GOLDEN,
|
|
190
|
+
scorers: [trajectoryScorer()],
|
|
191
|
+
run: async () => evalRunFromRun(await driveAgent(wasteful)),
|
|
192
|
+
});
|
|
193
|
+
expect(report.mean).toBeLessThan(1);
|
|
194
|
+
// Recall is intact — it did everything asked. Precision is what fell.
|
|
195
|
+
expect(report.cases[0]?.scores.trajectory?.details?.recall).toBe(1);
|
|
196
|
+
expect(report.cases[0]?.scores.trajectory?.details?.precision).toBeLessThan(1);
|
|
197
|
+
});
|
|
198
|
+
it('separates the two failures, which a pass/fail assertion would not', async () => {
|
|
199
|
+
const score = async (turns) => {
|
|
200
|
+
const report = await runExperiment({
|
|
201
|
+
name: 'x',
|
|
202
|
+
cases: GOLDEN,
|
|
203
|
+
scorers: [trajectoryScorer()],
|
|
204
|
+
run: async () => evalRunFromRun(await driveAgent(turns)),
|
|
205
|
+
});
|
|
206
|
+
return report.mean;
|
|
207
|
+
};
|
|
208
|
+
const skipped = await score([
|
|
209
|
+
{ toolCalls: [{ name: 'edit' }] },
|
|
210
|
+
{ toolCalls: [{ name: 'finish' }] },
|
|
211
|
+
]);
|
|
212
|
+
const wasteful = await score([
|
|
213
|
+
{ toolCalls: [{ name: 'ls' }] },
|
|
214
|
+
{ toolCalls: [{ name: 'read' }] },
|
|
215
|
+
{ toolCalls: [{ name: 'edit' }] },
|
|
216
|
+
{ toolCalls: [{ name: 'finish' }] },
|
|
217
|
+
]);
|
|
218
|
+
expect(skipped).not.toBe(wasteful);
|
|
219
|
+
// Skipping required work is worse than doing it inefficiently.
|
|
220
|
+
expect(skipped).toBeLessThan(wasteful);
|
|
221
|
+
});
|
|
222
|
+
});
|
|
223
|
+
//# sourceMappingURL=end-to-end.test.js.map
|
|
@@ -0,0 +1 @@
|
|
|
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"}
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"harness-honesty.test.d.ts","sourceRoot":"","sources":["../../../src/eval/__tests__/harness-honesty.test.ts"],"names":[],"mappings":""}
|