{"version":3,"sources":["../src/legacy.ts","../src/harness.ts","../src/legacy/evaluate/index.ts","../src/legacy/format.ts","../src/internal/matchers.ts","../src/internal/toolCallScorer.ts","../src/legacy/scorers/toolCallScorer.ts","../src/internal/structuredOutputScorer.ts","../src/legacy/scorers/structuredOutputScorer.ts"],"sourcesContent":["/**\n * Temporary scorer-first compatibility entrypoint.\n *\n * Keep this module isolated from the harness-first API surface. Do not route\n * new features through here; this file should stay easy to delete.\n */\nimport {\n assert,\n afterEach as vitestAfterEach,\n beforeEach as vitestBeforeEach,\n describe,\n expect,\n test,\n} from \"vitest\";\nimport \"vitest\";\nimport {\n normalizeMetadata,\n toJsonValue,\n type JsonValue,\n type ToolCall as NormalizedToolCall,\n} from \"./harness\";\nexport { configure, evaluate } from \"./legacy/evaluate\";\nimport { formatScores, wrapText } from \"./legacy/format\";\nimport type {\n BaseScorerOptions,\n Score,\n ScoreFn,\n TaskFn,\n ToolCall as LegacyToolCall,\n} from \"./legacy/shared\";\nexport type {\n BaseScorerOptions,\n Score,\n ScoreFn,\n TaskFn,\n TaskResult,\n ToolCall,\n} from \"./legacy/shared\";\nexport {\n StructuredOutputScorer,\n type StructuredOutputScorerConfig,\n type StructuredOutputScorerOptions,\n ToolCallScorer,\n type ToolCallScorerConfig,\n type ToolCallScorerOptions,\n} from \"./legacy/scorers\";\n\n/** Options for the temporary scorer-first `describeEval(...)` compatibility API. */\nexport interface LegacyDescribeEvalOptions {\n data: () => Promise<\n Array<{ input: string; name?: string } & Record>\n >;\n task: TaskFn;\n skipIf?: () => boolean;\n scorers: ScoreFn[];\n threshold?: number | null;\n timeout?: number;\n beforeEach?: () => void | Promise;\n afterEach?: () => void | Promise;\n}\n\n/** Legacy Vitest matcher function used by `expect(input).toEval(...)`. */\nexport type ToEval = (\n expected: any,\n taskFn: TaskFn,\n scoreFn: ScoreFn,\n threshold?: number,\n) => Promise;\n\ndeclare module \"vitest\" {\n interface Assertion {\n toEval: ToEval;\n }\n\n interface AsymmetricMatchersContaining {\n toEval: ToEval;\n }\n}\n\nexpect.extend({\n toEval: async function toEval(\n input: string,\n expected: any,\n taskFn: TaskFn,\n scoreFn: ScoreFn,\n threshold = 1.0,\n ) {\n const taskOutput = await taskFn(input);\n const output =\n typeof taskOutput === \"string\" ? taskOutput : taskOutput.result;\n const toolCalls =\n typeof taskOutput === \"object\" ? taskOutput.toolCalls : undefined;\n\n let result = scoreFn({ input, expected, output, toolCalls });\n if (result instanceof Promise) {\n result = await result;\n }\n\n return {\n pass: (result.score ?? 0) >= threshold,\n message: () => formatScores([{ ...result, name: scoreFn.name }]),\n };\n },\n});\n\n/** Defines a scorer-first legacy eval suite. Prefer root `describeEval(...)`. */\nexport function describeEval(\n name: string,\n options: LegacyDescribeEvalOptions,\n): void;\nexport function describeEval(name: string, options: LegacyDescribeEvalOptions) {\n return describe(name, async () => {\n if (options.beforeEach) {\n vitestBeforeEach(options.beforeEach);\n }\n if (options.afterEach) {\n vitestAfterEach(options.afterEach);\n }\n\n const testFn = options.skipIf ? test.skipIf(options.skipIf()) : test;\n for (const { input, name: testName, ...params } of await options.data()) {\n testFn(\n testName ?? input,\n {\n timeout: options.timeout ?? 60000,\n },\n async ({ task: testTask }) => {\n const taskOutput = await options.task(input);\n const output =\n typeof taskOutput === \"string\" ? taskOutput : taskOutput.result;\n const toolCalls =\n typeof taskOutput === \"object\" ? taskOutput.toolCalls : undefined;\n const threshold =\n options.threshold === undefined ? 1.0 : options.threshold;\n\n const scores = await Promise.all(\n options.scorers.map((scorer) => {\n const result = scorer({ input, ...params, output, toolCalls });\n if (result instanceof Promise) {\n return result;\n }\n return new Promise((resolve) => resolve(result));\n }),\n );\n const scoresWithName = scores.map((score, index) => ({\n ...score,\n name: options.scorers[index].name,\n }));\n const normalizedScoresWithName = scoresWithName.map(\n ({ metadata, ...score }) => ({\n ...score,\n ...(metadata ? { metadata: normalizeMetadata(metadata) } : {}),\n }),\n );\n\n const avgScore =\n scores.reduce((acc, score) => acc + (score.score ?? 0), 0) /\n scores.length;\n const thresholdFailed = threshold !== null && avgScore < threshold;\n\n const normalizedToolCalls = normalizeLegacyToolCalls(toolCalls);\n\n testTask.meta.eval = {\n scores: normalizedScoresWithName,\n avgScore,\n output,\n ...(normalizedToolCalls ? { toolCalls: normalizedToolCalls } : {}),\n thresholdFailed,\n };\n\n if (thresholdFailed) {\n assert(\n avgScore >= threshold,\n [\n `Score: ${avgScore.toFixed(2)} below threshold: ${threshold.toFixed(2)}`,\n `Output: ${wrapText(output)}`,\n formatScores(scoresWithName),\n ].join(\"\\n\\n\"),\n );\n }\n },\n );\n }\n });\n}\n\nfunction normalizeLegacyToolCalls(\n toolCalls: LegacyToolCall[] | undefined,\n): NormalizedToolCall[] | undefined {\n return toolCalls?.map((call) => {\n const args = toJsonValue(call.arguments);\n return {\n name: call.name,\n ...(isJsonObject(args) ? { arguments: args } : {}),\n status: \"ok\",\n };\n });\n}\n\nfunction isJsonObject(\n value: JsonValue | undefined,\n): value is Record {\n return (\n value !== undefined &&\n value !== null &&\n typeof value === \"object\" &&\n !Array.isArray(value)\n );\n}\n\nexport { formatScores, wrapText } from \"./legacy/format\";\n","import {\n assistantMessages,\n failedSpans,\n latestAssistantMessageContent,\n messagesByRole,\n messagesToTranscriptEvents,\n NormalizedSessionSchema,\n spans,\n spansByKind,\n systemMessages,\n TranscriptEventSchema,\n toolCalls,\n toolMessages,\n userMessages,\n} from \"@vitest-evals/core\";\nimport type {\n GenAiOperationName,\n HarnessRun,\n HarnessRunError,\n NormalizedError,\n JsonPrimitive,\n JsonValue,\n TranscriptMessageEvent,\n NormalizedSession,\n NormalizedSpan,\n NormalizedSpanAttributes,\n NormalizedSpanEvent,\n TranscriptEvent,\n NormalizedTrace,\n TimingSummary,\n ToolCall,\n TranscriptMessageInput,\n TranscriptMessageContentPart,\n TranscriptMessageTextPart,\n TranscriptMessageToolCallPart,\n TranscriptMessageToolCall,\n TranscriptMessageToolResultPart,\n UsageSummary,\n} from \"@vitest-evals/core\";\n\nexport {\n assistantMessages,\n failedSpans,\n latestAssistantMessageContent,\n messagesByRole,\n messagesToTranscriptEvents,\n spans,\n spansByKind,\n systemMessages,\n toolCalls,\n toolMessages,\n userMessages,\n} from \"@vitest-evals/core\";\nexport type {\n GenAiOperationName,\n GenAiOutputType,\n GenAiProviderName,\n GenAiSemanticAttributeKey,\n GenAiSemanticAttributes,\n GenAiTokenType,\n GenAiToolType,\n HarnessRun,\n HarnessRunError,\n NormalizedError,\n JsonPrimitive,\n JsonValue,\n TranscriptMessageEvent,\n NormalizedSession,\n NormalizedSpan,\n NormalizedSpanAttributeKey,\n NormalizedSpanAttributes,\n NormalizedSpanEvent,\n TranscriptToolCallEvent,\n TranscriptToolResultEvent,\n TranscriptEvent,\n NormalizedTrace,\n OpenTelemetrySemanticAttributeKey,\n OpenTelemetrySemanticAttributes,\n TimingSummary,\n ToolCall,\n TranscriptMessageInput,\n TranscriptMessageContentPart,\n TranscriptMessageTextPart,\n TranscriptMessageToolCallPart,\n TranscriptMessageToolCall,\n TranscriptMessageToolResultPart,\n UsageSummary,\n} from \"@vitest-evals/core\";\n\n/** Options for attaching a fallback run trace to a harness result. */\nexport type EnsureRunTraceOptions = {\n /** Human-readable run or harness name. */\n name: string;\n /** Wall-clock start time for the harness run. */\n startedAt: Date;\n /** Wall-clock finish time for the harness run. */\n finishedAt: Date;\n /** Optional trace id. A generated id is used when omitted. */\n id?: string;\n /** GenAI operation name to place on the root run span. */\n operationName?: GenAiOperationName;\n /** Optional JSON-safe source marker for the trace metadata. */\n source?: string;\n};\n\ntype OutputField =\n undefined extends TOutput ? { output?: TOutput } : { output: TOutput };\n\n/** Generic JSON-like metadata record used by normalized artifacts and reports. */\nexport type HarnessMetadata = Record;\n\n/**\n * Runtime context passed from the eval fixture into a harness run.\n *\n * @example\n * ```ts\n * const harness: Harness = {\n * name: \"refund-agent\",\n * async run(input, context) {\n * context.setArtifact(\"inputLength\", input.length);\n *\n * return {\n * output: undefined,\n * session: { events: [{ type: \"message\", role: \"user\", content: input }] },\n * usage: {},\n * errors: [],\n * };\n * },\n * };\n * ```\n */\nexport type HarnessContext = {\n /** Abort signal from Vitest when available. */\n signal?: AbortSignal;\n /** Mutable JSON-safe artifact bag shared with the harness. */\n artifacts: Record;\n /** Stores one JSON-safe artifact on the current run. */\n setArtifact: (name: string, value: JsonValue) => void;\n};\n\n/**\n * Adapter that executes the system under test and returns a normalized run.\n *\n * @example\n * ```ts\n * const harness: Harness = {\n * name: \"refund-agent\",\n * async run(input, context) {\n * return normalizeHarnessRun(input, await runRefundFlow(input), context);\n * },\n * };\n * ```\n */\nexport type Harness<\n TInput = unknown,\n TOutput extends JsonValue | undefined = JsonValue | undefined,\n> = {\n /** Stable harness name used in reports. */\n name: string;\n /** Executes the system under test and returns a normalized run. */\n run: (input: TInput, context: HarnessContext) => Promise>;\n};\n\n/** Value or promise accepted by lightweight harness callbacks. */\nexport type MaybePromise = T | Promise;\n\n/** Lightweight span event accepted by `createHarness(...)` results. */\nexport type SimpleSpanEvent = Omit & {\n /** Raw event attributes accepted by `createHarness(...)` before normalization. */\n attributes?: Record;\n};\n\n/** Lightweight span record accepted by `createHarness(...)` results. */\nexport type SimpleSpanRecord = Omit<\n NormalizedSpan,\n \"attributes\" | \"error\" | \"events\"\n> & {\n /** Raw span attributes accepted by `createHarness(...)` before normalization. */\n attributes?: Record;\n /** Raw span error accepted by `createHarness(...)` before normalization. */\n error?: unknown;\n /** Raw span events accepted by `createHarness(...)` before normalization. */\n events?: SimpleSpanEvent[];\n};\n\n/** Lightweight trace record accepted by `createHarness(...)` results. */\nexport type SimpleTraceRecord = Omit & {\n /** Raw trace metadata accepted by `createHarness(...)` before normalization. */\n metadata?: Record;\n /** Lightweight spans to normalize into the trace. */\n spans: SimpleSpanRecord[];\n};\n\n/** Lightweight transcript input accepted by `createHarness(...)` results. */\nexport type SimpleTranscriptInput =\n | {\n /** Ordered normalized transcript events for the application run. */\n events: TranscriptEvent[];\n messages?: never;\n }\n | {\n /** Strict camelCase message transport normalized into transcript events. */\n messages: TranscriptMessageInput[];\n events?: never;\n };\n\n/**\n * Lightweight result shape normalized by `createHarness(...)`.\n *\n * @example\n * ```ts\n * const result: SimpleHarnessResult<{ status: \"approved\" }> = {\n * output: { status: \"approved\" },\n * events: [\n * { type: \"message\", role: \"user\", content: \"Refund invoice inv_123\" },\n * { type: \"message\", role: \"assistant\", content: { status: \"approved\" } },\n * ],\n * usage: { totalTokens: 260 },\n * };\n * ```\n */\nexport type SimpleHarnessResult<\n TOutput extends JsonValue | undefined = JsonValue | undefined,\n> = OutputField &\n SimpleTranscriptInput & {\n /** Usage summary to attach to the run. */\n usage?: UsageSummary;\n /** Timing summary to attach to the run. */\n timings?: TimingSummary;\n /** Raw artifact values to normalize and merge into the run. */\n artifacts?: Record;\n /** Lightweight traces and spans to normalize into the run. */\n traces?: SimpleTraceRecord[];\n /** Raw session metadata to normalize into the session. */\n metadata?: Record;\n /** Raw errors to normalize into the run. */\n errors?: unknown[];\n };\n\n/** Either a complete normalized run or a lightweight result to normalize. */\nexport type HarnessResultLike<\n TOutput extends JsonValue | undefined = JsonValue | undefined,\n> = HarnessRun | SimpleHarnessResult;\n\n/** Arguments passed to the `createHarness(...)` convenience callback. */\nexport type CreateHarnessRunArgs = {\n /** Original input passed to `run(input)`. */\n input: TInput;\n /** Abort signal from Vitest when available. */\n signal?: AbortSignal;\n /** Mutable run artifact bag. */\n artifacts: HarnessContext[\"artifacts\"];\n /** Stores one JSON-safe artifact on the current run. */\n setArtifact: HarnessContext[\"setArtifact\"];\n};\n\n/**\n * Options for creating a lightweight custom application harness.\n *\n * Prefer this helper for custom harnesses. Implement `Harness` directly only\n * when the callback already returns a full `HarnessRun` with canonical\n * `session.events`.\n *\n * @example\n * ```ts\n * const options: CreateHarnessOptions = {\n * name: \"refund-agent\",\n * run: async ({ input }) => ({\n * output: await classifyRefund(input),\n * events: [{ type: \"message\", role: \"user\", content: input }],\n * }),\n * };\n * ```\n */\nexport type CreateHarnessOptions<\n TInput = unknown,\n TOutput extends JsonValue | undefined = JsonValue | undefined,\n> = {\n /** Stable harness name used in reports. */\n name: string;\n /** Executes application code and returns either a lightweight result or full `HarnessRun`. */\n run: (\n args: CreateHarnessRunArgs,\n ) => MaybePromise>;\n};\n\nfunction isJsonPrimitive(value: unknown): value is JsonPrimitive {\n return (\n value === null ||\n typeof value === \"string\" ||\n typeof value === \"boolean\" ||\n (typeof value === \"number\" && Number.isFinite(value))\n );\n}\n\nfunction isJsonRecord(value: unknown): value is Record {\n return typeof value === \"object\" && value !== null && !Array.isArray(value);\n}\n\nfunction normalizeJsonArray(value: unknown[], seen: WeakSet) {\n if (seen.has(value)) {\n return undefined;\n }\n\n seen.add(value);\n const normalized = value.map((item) => {\n const normalized = toJsonValueInternal(item, seen);\n return normalized === undefined ? null : normalized;\n });\n seen.delete(value);\n\n return normalized;\n}\n\nfunction normalizeJsonObject(\n value: Record,\n seen: WeakSet,\n): Record {\n const normalized: Record = {};\n\n if (seen.has(value)) {\n return normalized;\n }\n\n seen.add(value);\n try {\n for (const [key, entryValue] of Object.entries(value)) {\n const entry = toJsonValueInternal(entryValue, seen);\n if (entry !== undefined) {\n normalized[key] = entry;\n }\n }\n } finally {\n seen.delete(value);\n }\n\n return normalized;\n}\n\n/** Returns true when a value exposes a callable method with the given name. */\nexport function hasCallableMethod(value: unknown, methodName: string) {\n return (\n value !== null &&\n (typeof value === \"object\" || typeof value === \"function\") &&\n methodName in value &&\n typeof (value as Record)[methodName] === \"function\"\n );\n}\n\n/** Normalizes an unknown value into the JSON-safe shape used by harness runs. */\nexport function toJsonValue(value: unknown): JsonValue | undefined {\n return toJsonValueInternal(value, new WeakSet());\n}\n\nfunction toJsonValueInternal(\n value: unknown,\n seen: WeakSet,\n): JsonValue | undefined {\n if (isJsonPrimitive(value)) {\n return value;\n }\n\n if (\n value !== null &&\n typeof value === \"object\" &&\n seen.has(value as object)\n ) {\n return undefined;\n }\n\n if (Array.isArray(value)) {\n return normalizeJsonArray(value, seen);\n }\n\n if (isJsonRecord(value)) {\n return normalizeJsonObject(value, seen);\n }\n\n return undefined;\n}\n\n/** Drops non-JSON properties from a record while preserving valid values. */\nexport function normalizeRecord(\n value: Record,\n): Record {\n return normalizeJsonObject(value, new WeakSet());\n}\n\n/** Normalizes metadata and omits the field entirely when nothing survives. */\nexport function normalizeMetadata(\n value: Record,\n): Record | undefined {\n const normalized = normalizeRecord(value);\n return Object.keys(normalized).length > 0 ? normalized : undefined;\n}\n\n/** Converts arbitrary content into the JSON-safe message content shape. */\nexport function normalizeContent(value: unknown): JsonValue {\n const normalized = toJsonValue(value);\n return normalized !== undefined ? normalized : String(value);\n}\n\n/**\n * Creates a harness from the common \"run app code and return output\" shape.\n *\n * @param options - Harness name plus the callback that executes app code.\n *\n * @example\n * ```ts\n * import { createHarness } from \"vitest-evals\";\n *\n * export const refundHarness = createHarness<\n * string,\n * { status: \"approved\" | \"denied\" }\n * >({\n * name: \"refund-agent\",\n * run: async ({ input, setArtifact }) => {\n * const result = await runRefundFlow(input);\n * const output = { status: result.status };\n *\n * setArtifact(\"case\", { invoiceId: result.invoiceId });\n *\n * return {\n * output,\n * events: [\n * { type: \"message\", role: \"user\", content: input },\n * {\n * type: \"tool_call\",\n * id: \"call_lookup\",\n * name: \"lookupInvoice\",\n * arguments: { invoiceId: result.invoiceId },\n * },\n * {\n * type: \"tool_result\",\n * toolCallId: \"call_lookup\",\n * name: \"lookupInvoice\",\n * content: { refundable: result.refundable },\n * },\n * { type: \"message\", role: \"assistant\", content: output },\n * ],\n * usage: { provider: \"openai\", model: \"gpt-4o-mini\" },\n * };\n * },\n * });\n * ```\n */\nexport function createHarness<\n TInput = unknown,\n TOutput extends JsonValue | undefined = JsonValue | undefined,\n>(options: CreateHarnessOptions): Harness;\nexport function createHarness<\n TInput = unknown,\n TOutput extends JsonValue | undefined = JsonValue | undefined,\n>(options: CreateHarnessOptions): Harness {\n const harness: Harness = {\n name: options.name,\n run: async (input, context) => {\n const startedAt = new Date();\n\n try {\n const result = await options.run({\n input,\n signal: context.signal,\n artifacts: context.artifacts,\n setArtifact: context.setArtifact,\n });\n const run = normalizeHarnessRun(input, result, context);\n ensureRunTrace(run, {\n name: options.name,\n startedAt,\n finishedAt: new Date(),\n });\n\n return run;\n } catch (error) {\n const partialRun = getHarnessRunFromError(error);\n if (partialRun) {\n if (\n Object.keys(context.artifacts).length > 0 &&\n !partialRun.artifacts\n ) {\n partialRun.artifacts = context.artifacts;\n }\n ensureRunTrace(partialRun, {\n name: options.name,\n startedAt,\n finishedAt: new Date(),\n });\n throw attachHarnessRunToError(error, partialRun);\n }\n\n const failedRun = createFailedHarnessRun(input, error, {\n artifacts: context.artifacts,\n });\n ensureRunTrace(failedRun, {\n name: options.name,\n startedAt,\n finishedAt: new Date(),\n });\n\n throw attachHarnessRunToError(error, failedRun);\n }\n },\n };\n\n return harness;\n}\n\n/**\n * Normalizes a lightweight harness result into the reporter-facing run shape.\n *\n * @param input - Original input passed to the harness.\n * @param result - Lightweight result or pre-normalized harness run.\n * @param context - Optional per-run context used to merge artifacts.\n *\n * @example\n * ```ts\n * const run = normalizeHarnessRun(\"Refund invoice inv_123\", {\n * output: { status: \"approved\" },\n * events: [\n * { type: \"message\", role: \"user\", content: \"Refund invoice inv_123\" },\n * {\n * type: \"tool_call\",\n * id: \"call_lookup\",\n * name: \"lookupInvoice\",\n * arguments: { invoiceId: \"inv_123\" },\n * },\n * {\n * type: \"tool_result\",\n * toolCallId: \"call_lookup\",\n * name: \"lookupInvoice\",\n * content: { refundable: true },\n * },\n * ],\n * usage: { provider: \"openai\", model: \"gpt-4o-mini\" },\n * });\n *\n * expect(toolCalls(run)).toHaveLength(1);\n * ```\n */\nexport function normalizeHarnessRun<\n TInput = unknown,\n TOutput extends JsonValue | undefined = JsonValue | undefined,\n>(\n input: TInput,\n result: HarnessResultLike,\n context?: HarnessContext,\n): HarnessRun {\n if (isHarnessRun(result)) {\n if (\n context &&\n Object.keys(context.artifacts).length > 0 &&\n !result.artifacts\n ) {\n return {\n ...result,\n artifacts: context.artifacts,\n };\n }\n\n return result;\n }\n\n if (\"toolCalls\" in result) {\n throw new TypeError(\n 'createHarness results do not accept top-level toolCalls. Return ordered session events with type: \"tool_call\" and type: \"tool_result\" entries instead.',\n );\n }\n\n const output = result.output;\n const usage = result.usage ?? {};\n const events = normalizeTranscriptInput(result);\n if (!events) {\n throw new TypeError(\n \"createHarness results must include ordered events or messages. Return a full HarnessRun or a lightweight result with events/messages.\",\n );\n }\n if (events.length === 0) {\n throw new TypeError(\n \"createHarness results must include at least one transcript event. Return ordered events or message transport inputs that normalize into events.\",\n );\n }\n const metadata = result.metadata\n ? normalizeMetadata(result.metadata)\n : undefined;\n const artifacts = normalizeMergedArtifacts(\n context?.artifacts,\n result.artifacts,\n );\n const traces = normalizeSimpleTraces(result.traces);\n\n return {\n session: {\n events,\n ...(usage.provider ? { provider: usage.provider } : {}),\n ...(usage.model ? { model: usage.model } : {}),\n ...(metadata ? { metadata } : {}),\n },\n ...(output !== undefined ? { output } : {}),\n usage,\n ...(result.timings ? { timings: result.timings } : {}),\n ...(artifacts ? { artifacts } : {}),\n ...(traces ? { traces } : {}),\n errors: normalizeSimpleErrors(result.errors),\n } as HarnessRun;\n}\n\nfunction normalizeTranscriptInput(\n result: HarnessResultLike,\n): TranscriptEvent[] | undefined {\n if (\"events\" in result && Array.isArray(result.events)) {\n return result.events.map((event) => TranscriptEventSchema.parse(event));\n }\n\n if (\"messages\" in result && Array.isArray(result.messages)) {\n return messagesToTranscriptEvents(result.messages).map((event) =>\n TranscriptEventSchema.parse(event),\n );\n }\n\n return undefined;\n}\n\n/**\n * Builds a JSON-safe failed run for errors that happen before a harness can return.\n *\n * @param input - Original input passed to the harness.\n * @param error - Error thrown by setup or execution.\n * @param options - Optional artifacts to preserve on the failed run.\n */\nexport function createFailedHarnessRun(\n input: unknown,\n error: unknown,\n options: { artifacts?: Record } = {},\n): HarnessRun {\n const artifacts = options.artifacts;\n\n return {\n session: {\n events: [\n {\n type: \"message\",\n role: \"user\",\n content: normalizeContent(input),\n },\n ],\n },\n usage: {},\n ...(artifacts && Object.keys(artifacts).length > 0 ? { artifacts } : {}),\n errors: [serializeError(error)],\n };\n}\n\nfunction normalizeMergedArtifacts(\n contextArtifacts: Record | undefined,\n resultArtifacts: Record | undefined,\n) {\n const artifacts = {\n ...(contextArtifacts ?? {}),\n ...(resultArtifacts ? normalizeRecord(resultArtifacts) : {}),\n };\n\n return Object.keys(artifacts).length > 0 ? artifacts : undefined;\n}\n\nfunction normalizeSimpleErrors(\n errors: unknown[] | undefined,\n): Array> {\n return (errors ?? []).map((error) => {\n const normalized = toJsonValue(error);\n\n if (\n normalized &&\n typeof normalized === \"object\" &&\n !Array.isArray(normalized) &&\n Object.keys(normalized).length > 0\n ) {\n return normalized;\n }\n\n return serializeError(error);\n });\n}\n\nfunction normalizeSimpleTraces(\n traces: SimpleTraceRecord[] | undefined,\n): NormalizedTrace[] | undefined {\n if (!Array.isArray(traces)) {\n return undefined;\n }\n\n const normalized = traces\n .map(normalizeSimpleTrace)\n .filter((trace): trace is NormalizedTrace => Boolean(trace));\n\n return normalized.length > 0 ? normalized : undefined;\n}\n\nfunction normalizeSimpleTrace(trace: unknown): NormalizedTrace | undefined {\n if (!isJsonRecord(trace)) {\n return undefined;\n }\n\n const {\n metadata: rawMetadata,\n spans: rawSpans,\n ...traceFields\n } = trace as Partial;\n const spans = (Array.isArray(rawSpans) ? rawSpans : [])\n .map((span) => normalizeSimpleSpan(span))\n .filter((span): span is NormalizedSpan => Boolean(span));\n const metadata = isJsonRecord(rawMetadata)\n ? normalizeMetadata(rawMetadata)\n : undefined;\n\n if (spans.length === 0 && !traceFields.id && !traceFields.name) {\n return undefined;\n }\n\n return {\n ...traceFields,\n ...(metadata ? { metadata } : {}),\n spans,\n };\n}\n\nfunction normalizeSimpleSpan(span: unknown): NormalizedSpan | undefined {\n if (!isJsonRecord(span) || typeof span.name !== \"string\" || !span.name) {\n return undefined;\n }\n\n const {\n attributes: rawAttributes,\n error: rawError,\n events: rawEvents,\n ...spanFields\n } = span as Partial & { name: string };\n const attributes = rawAttributes\n ? isJsonRecord(rawAttributes)\n ? normalizeMetadata(rawAttributes)\n : undefined\n : undefined;\n const error = normalizeSpanError(rawError);\n const events = normalizeSimpleSpanEvents(rawEvents);\n\n return {\n ...spanFields,\n ...(attributes\n ? { attributes: attributes as NormalizedSpanAttributes }\n : {}),\n ...(error ? { error } : {}),\n ...(events ? { events } : {}),\n };\n}\n\nfunction normalizeSimpleSpanEvents(\n events: unknown,\n): NormalizedSpanEvent[] | undefined {\n if (!Array.isArray(events)) {\n return undefined;\n }\n\n const normalized = events\n .map(normalizeSimpleSpanEvent)\n .filter((event): event is NormalizedSpanEvent => Boolean(event));\n\n return normalized.length > 0 ? normalized : undefined;\n}\n\nfunction normalizeSimpleSpanEvent(\n event: unknown,\n): NormalizedSpanEvent | undefined {\n if (!isJsonRecord(event) || typeof event.name !== \"string\" || !event.name) {\n return undefined;\n }\n\n const { attributes: rawAttributes, ...eventFields } =\n event as Partial & { name: string };\n const attributes = rawAttributes\n ? isJsonRecord(rawAttributes)\n ? normalizeMetadata(rawAttributes)\n : undefined\n : undefined;\n\n return {\n ...eventFields,\n ...(attributes\n ? { attributes: attributes as NormalizedSpanAttributes }\n : {}),\n };\n}\n\n/** Normalizes arbitrary span errors while preserving object-shaped messages. */\nexport function normalizeSpanError(\n error: unknown,\n): NormalizedSpan[\"error\"] | undefined {\n if (error === undefined) {\n return undefined;\n }\n\n if (error instanceof Error) {\n const details = normalizeMetadata(\n error as unknown as Record,\n );\n\n return {\n ...(details ?? {}),\n type: error.name,\n message: error.message,\n };\n }\n\n if (\n error &&\n typeof error === \"object\" &&\n !Array.isArray(error) &&\n typeof (error as { message?: unknown }).message === \"string\"\n ) {\n const normalized = normalizeMetadata(error as Record);\n const { message, type, ...details } = normalized ?? {};\n\n return {\n ...details,\n message: message as string,\n ...(typeof type === \"string\" ? { type } : {}),\n };\n }\n\n const serialized = serializeError(error);\n const { message, type, ...details } = serialized;\n\n return {\n ...details,\n message: typeof message === \"string\" ? message : String(message),\n ...(typeof type === \"string\" ? { type } : {}),\n };\n}\n\n/** Normalizes raw span attributes into the JSON-safe span attribute shape. */\nexport function normalizeSpanAttributes(\n attributes: Record,\n): NormalizedSpanAttributes | undefined {\n return normalizeMetadata(attributes) as NormalizedSpanAttributes | undefined;\n}\n\n/** Builds common OpenTelemetry GenAI usage attributes from a usage summary. */\nexport function createGenAiUsageAttributes(\n usage: UsageSummary | undefined,\n options: { provider?: string } = {},\n) {\n return {\n \"gen_ai.provider.name\": usage?.provider ?? options.provider,\n \"gen_ai.request.model\": usage?.model,\n \"gen_ai.response.model\": usage?.model,\n \"gen_ai.usage.input_tokens\": usage?.inputTokens,\n \"gen_ai.usage.output_tokens\": usage?.outputTokens,\n \"gen_ai.usage.reasoning.output_tokens\": usage?.reasoningTokens,\n } satisfies Record;\n}\n\n/**\n * Attaches a fallback run trace when a harness result does not already contain spans.\n *\n * This keeps custom harnesses inspectable while first-party harness packages\n * remain free to attach richer native traces.\n */\nexport function ensureRunTrace(\n run: HarnessRun,\n options: EnsureRunTraceOptions,\n): NormalizedTrace | undefined {\n if (spans(run).length > 0) {\n return undefined;\n }\n\n const traceId = options.id ?? createGeneratedTraceId();\n const rootSpanId = `${traceId}:run`;\n const durationMs = options.finishedAt.getTime() - options.startedAt.getTime();\n const rootError =\n run.errors.length > 0 ? normalizeSpanError(run.errors[0]) : undefined;\n const runSpan: NormalizedSpan = {\n id: rootSpanId,\n traceId,\n name: options.name,\n kind: \"run\",\n startedAt: options.startedAt.toISOString(),\n finishedAt: options.finishedAt.toISOString(),\n durationMs,\n status: rootError ? \"error\" : \"ok\",\n ...(rootError ? { error: rootError } : {}),\n attributes: normalizeSpanAttributes({\n \"gen_ai.operation.name\": options.operationName ?? \"invoke_workflow\",\n \"gen_ai.workflow.name\": options.name,\n ...createGenAiUsageAttributes(run.usage),\n }),\n };\n const trace: NormalizedTrace = {\n id: traceId,\n name: options.name,\n startedAt: options.startedAt.toISOString(),\n finishedAt: options.finishedAt.toISOString(),\n durationMs,\n ...(options.source ? { metadata: { source: options.source } } : {}),\n spans: [runSpan],\n };\n\n run.traces = [trace];\n return trace;\n}\n\nlet nextGeneratedTraceId = 0;\n\nfunction createGeneratedTraceId() {\n nextGeneratedTraceId += 1;\n return `trace_${nextGeneratedTraceId}`;\n}\n\n/**\n * Attaches a partial or complete harness run to an arbitrary thrown error.\n *\n * @param error - Thrown value to wrap.\n * @param run - Partial or complete normalized harness run to preserve.\n *\n * @example\n * ```ts\n * try {\n * return await runAgent(input);\n * } catch (error) {\n * throw attachHarnessRunToError(error, partialRun);\n * }\n * ```\n */\nexport function attachHarnessRunToError(\n error: unknown,\n run: HarnessRun,\n): HarnessRunError {\n const baseError =\n error instanceof Error\n ? error\n : new Error(String(error ?? \"Unknown error\"));\n return Object.assign(baseError, {\n vitestEvalsRun: run,\n });\n}\n\n/**\n * Reads an attached harness run back off a previously wrapped error value.\n *\n * @param error - Unknown thrown value that may contain a harness run.\n *\n * @example\n * ```ts\n * const partialRun = getHarnessRunFromError(error);\n *\n * if (partialRun) {\n * console.log(toolCalls(partialRun.session));\n * }\n * ```\n */\nexport function getHarnessRunFromError(error: unknown): HarnessRun | undefined {\n if (\n error &&\n typeof error === \"object\" &&\n \"vitestEvalsRun\" in error &&\n isHarnessRun((error as { vitestEvalsRun?: unknown }).vitestEvalsRun)\n ) {\n return (error as { vitestEvalsRun: HarnessRun }).vitestEvalsRun;\n }\n\n return undefined;\n}\n\n/** Returns true when a value matches the normalized `HarnessRun` contract. */\nexport function isHarnessRun(value: unknown): value is HarnessRun {\n if (!value || typeof value !== \"object\") {\n return false;\n }\n\n const candidate = value as {\n session?: unknown;\n usage?: unknown;\n errors?: unknown;\n };\n\n return (\n isNormalizedSession(candidate.session) &&\n Boolean(candidate.usage) &&\n typeof candidate.usage === \"object\" &&\n !Array.isArray(candidate.usage) &&\n Array.isArray(candidate.errors)\n );\n}\n\n/** Returns true when a value matches the normalized session contract. */\nexport function isNormalizedSession(\n value: unknown,\n): value is NormalizedSession {\n return NormalizedSessionSchema.safeParse(value).success;\n}\n\n/** Reuses pre-normalized harness errors when a runtime already returns them. */\nexport function resolveHarnessRunErrors(\n result: unknown,\n): Array> {\n if (\n result &&\n typeof result === \"object\" &&\n Array.isArray((result as Record).errors)\n ) {\n return (result as { errors: Array> }).errors;\n }\n\n return [];\n}\n\n/** Serializes an arbitrary thrown value into the normalized error shape. */\nexport function serializeError(error: unknown): Record {\n if (error instanceof Error) {\n return {\n type: error.name,\n message: error.message,\n };\n }\n\n return {\n type: \"Error\",\n message: String(error),\n };\n}\n","/**\n * Temporary compatibility wrapper for the old `evaluate(...)` helper.\n *\n * Keep this module isolated from the harness-first API so legacy suites can be\n * removed cleanly in a later deletion pass.\n */\nimport { generateObject } from \"ai\";\nimport { z } from \"zod\";\nimport { assert, test } from \"vitest\";\nimport { wrapText } from \"../format\";\n\ntype LanguageModel = Parameters[0][\"model\"];\n\nlet defaultModel: LanguageModel | undefined;\n\n/** Configures the default language model used by legacy `evaluate(...)`. */\nexport function configure(opts: { model: LanguageModel }) {\n defaultModel = opts.model;\n}\n\nconst EVAL_SYSTEM = `You are assessing a submitted output based on a given criterion. Ignore differences in style, grammar, punctuation, or length. Focus only on whether the criterion is met.`;\n\nconst EVAL_PROMPT = (output: string, criteria: string) => `\n${output}\n\n\n\n${criteria}\n\n\nDoes the submission meet the criteria? Select one option:\n(A) The criteria is fully met with no issues\n(B) The criteria is mostly met with minor gaps\n(C) The criteria is partially met with notable gaps\n(D) The criteria is barely met or only tangentially addressed\n(E) The criteria is not met at all`;\n\nconst CHOICE_SCORES: Record = {\n A: 1.0,\n B: 0.75,\n C: 0.5,\n D: 0.25,\n E: 0.0,\n};\n\ninterface EvaluateOptions {\n task: () => Promise;\n criteria: string;\n threshold?: number;\n}\n\ninterface TestTaskContext {\n task: { meta: Record };\n}\n\n/** @internal Core evaluation logic, exported for testing. */\nexport async function _evaluate(\n ctx: TestTaskContext,\n opts: EvaluateOptions,\n): Promise {\n if (!defaultModel) {\n throw new Error(\n \"No model configured. Call configure({ model }) before using evaluate.\",\n );\n }\n\n let output: string;\n try {\n output = await opts.task();\n } catch (error) {\n const errorMessage = error instanceof Error ? error.message : String(error);\n ctx.task.meta.eval = {\n scores: [\n {\n score: 0,\n name: \"evaluate\",\n metadata: { rationale: `Task failed: ${errorMessage}` },\n },\n ],\n avgScore: 0,\n };\n throw error;\n }\n\n let object: { answer: string; rationale: string };\n try {\n ({ object } = await generateObject({\n model: defaultModel,\n schema: z.object({\n answer: z.enum([\"A\", \"B\", \"C\", \"D\", \"E\"]),\n rationale: z.string(),\n }),\n system: EVAL_SYSTEM,\n prompt: EVAL_PROMPT(output, opts.criteria),\n }));\n } catch (error) {\n const errorMessage = error instanceof Error ? error.message : String(error);\n ctx.task.meta.eval = {\n scores: [\n {\n score: 0,\n name: \"evaluate\",\n metadata: { rationale: `Judge failed: ${errorMessage}` },\n },\n ],\n avgScore: 0,\n };\n throw error;\n }\n\n const score = CHOICE_SCORES[object.answer];\n const threshold = opts.threshold ?? 1.0;\n\n ctx.task.meta.eval = {\n scores: [\n {\n score,\n name: \"evaluate\",\n metadata: { rationale: object.rationale, answer: object.answer },\n },\n ],\n avgScore: score,\n };\n\n if (score < threshold) {\n assert(\n false,\n `Score: ${score} (${object.answer}) below threshold: ${threshold}\\n\\n## Output:\\n${wrapText(output)}\\n\\n## Rationale:\\n${wrapText(object.rationale)}`,\n );\n }\n}\n\n/** Defines a legacy model-graded eval test. Prefer harness-backed suites. */\nexport function evaluate(\n name: string,\n opts: EvaluateOptions & { timeout?: number },\n) {\n test(name, { timeout: opts.timeout ?? 60000 }, async ({ task: testTask }) => {\n await _evaluate({ task: testTask }, opts);\n });\n}\n","import type { Score } from \"./shared\";\n\n/**\n * Temporary legacy formatter helpers.\n *\n * Keep these local to the scorer-first compatibility layer so legacy can be\n * deleted without touching the harness-first entrypoint.\n */\n\n/** Wraps scorer output into fixed-width lines for legacy failure messages. */\nexport function wrapText(text: string, width = 80): string {\n if (!text || text.length <= width) {\n return text;\n }\n\n const words = text.split(/\\s+/);\n const lines: string[] = [];\n let currentLine = \"\";\n\n for (const word of words) {\n if (currentLine.length + word.length + 1 > width) {\n lines.push(currentLine.trim());\n currentLine = word;\n } else {\n currentLine += (currentLine ? \" \" : \"\") + word;\n }\n }\n\n if (currentLine) {\n lines.push(currentLine);\n }\n\n return lines.join(\"\\n\");\n}\n\n/** Formats legacy scorer results for matcher and assertion output. */\nexport function formatScores(scores: (Score & { name: string })[]) {\n return scores\n .map((score) => {\n const scoreLine = `${score.name || \"Unknown\"} [${(score.score ?? 0).toFixed(1)}]`;\n if (\n ((score.score ?? 0) < 1.0 && score.metadata?.rationale) ||\n score.metadata?.output\n ) {\n let formattedOutput = \"\";\n if (score.metadata?.output !== undefined) {\n const output = score.metadata.output;\n formattedOutput =\n typeof output === \"string\"\n ? `\\noutput ${wrapText(output)}`\n : `\\noutput ${wrapText(JSON.stringify(output, null, 2))}`;\n }\n\n return `${scoreLine}${\n score.metadata?.rationale\n ? `\\nreason ${wrapText(score.metadata.rationale)}`\n : \"\"\n }${formattedOutput}`;\n }\n return scoreLine;\n })\n .join(\"\\n\\n\");\n}\n","/**\n * Shared configuration for built-in value matchers.\n *\n * @example\n * ```ts\n * const config: BaseMatcherConfig = {\n * requireAll: true,\n * allowExtras: false,\n * };\n * ```\n */\nexport interface BaseMatcherConfig {\n /** Require every expected field or tool to match. */\n requireAll?: boolean;\n /** Allow actual output/tool calls to contain extra fields or calls. */\n allowExtras?: boolean;\n /** Emit matcher debug details to the console. */\n debug?: boolean;\n}\n\n/**\n * Matching strategy used by structured-output and tool-call judges.\n *\n * @example\n * ```ts\n * const exact: MatchStrategy = \"strict\";\n * const custom: MatchStrategy = (expected, actual) =>\n * String(actual).includes(String(expected));\n * ```\n */\nexport type MatchStrategy =\n | \"strict\"\n | \"fuzzy\"\n | ((expected: T, actual: T, context?: string) => boolean);\n\n/**\n * Options controlling fuzzy matcher behavior.\n *\n * @example\n * ```ts\n * const fuzzyOptions: FuzzyMatchOptions = {\n * caseInsensitive: true,\n * substring: true,\n * numericTolerance: 0.01,\n * };\n * ```\n */\nexport interface FuzzyMatchOptions {\n /** Compare strings without case sensitivity. */\n caseInsensitive?: boolean;\n /** Treat either string containing the other as a match. */\n substring?: boolean;\n /** Relative and absolute tolerance used for numeric comparisons. */\n numericTolerance?: number;\n /** Match arrays without requiring the same order. */\n ignoreArrayOrder?: boolean;\n /** Allow simple string/number/boolean coercions before failing. */\n coerceTypes?: boolean;\n}\n\ntype Mismatch = {\n key: string;\n expected: unknown;\n actual: unknown;\n};\n\n/** Debug logger interface accepted by matcher helpers. */\nexport interface Logger {\n log: (message: string, ...args: unknown[]) => void;\n}\n\nfunction isRecord(value: unknown): value is Record {\n return typeof value === \"object\" && value !== null && !Array.isArray(value);\n}\n\n/** Compares two values with strict deep equality semantics. */\nexport function strictEquals(\n expected: unknown,\n actual: unknown,\n context?: string,\n): boolean {\n void context;\n\n if (expected === actual) {\n return true;\n }\n\n if (\n expected === null ||\n expected === undefined ||\n actual === null ||\n actual === undefined\n ) {\n return false;\n }\n\n if (typeof expected !== typeof actual) {\n return false;\n }\n\n if (Array.isArray(expected)) {\n return (\n Array.isArray(actual) &&\n expected.length === actual.length &&\n expected.every((item, index) =>\n strictEquals(item, actual[index], context),\n )\n );\n }\n\n if (isRecord(expected) && isRecord(actual)) {\n const expectedKeys = Object.keys(expected);\n const actualKeys = Object.keys(actual);\n\n return (\n expectedKeys.length === actualKeys.length &&\n expectedKeys.every(\n (key) =>\n key in actual && strictEquals(expected[key], actual[key], context),\n )\n );\n }\n\n return false;\n}\n\nfunction fuzzyMatchString(\n expected: string,\n actual: string,\n options: FuzzyMatchOptions,\n): boolean {\n const { caseInsensitive = true, substring = false } = options;\n const expectedText = caseInsensitive ? expected.toLowerCase() : expected;\n const actualText = caseInsensitive ? actual.toLowerCase() : actual;\n\n return substring\n ? actualText.includes(expectedText) || expectedText.includes(actualText)\n : expectedText === actualText;\n}\n\nfunction fuzzyMatchNumber(\n expected: number,\n actual: number,\n options: FuzzyMatchOptions,\n): boolean {\n const { numericTolerance = 0.001 } = options;\n const tolerance = Math.max(\n Math.abs(expected) * numericTolerance,\n numericTolerance,\n );\n\n return Math.abs(expected - actual) <= tolerance;\n}\n\nfunction fuzzyMatchArray(\n expected: unknown[],\n actual: unknown[],\n options: FuzzyMatchOptions,\n context?: string,\n): boolean {\n const { ignoreArrayOrder = true } = options;\n\n if (!ignoreArrayOrder) {\n return (\n expected.length === actual.length &&\n expected.every((item, index) =>\n fuzzyMatch(item, actual[index], options, context),\n )\n );\n }\n\n const actualUsed = actual.map(() => false);\n return expected.every((expectedItem) => {\n for (const [index, actualItem] of actual.entries()) {\n if (actualUsed[index]) {\n continue;\n }\n\n if (fuzzyMatch(expectedItem, actualItem, options, context)) {\n actualUsed[index] = true;\n return true;\n }\n }\n\n return false;\n });\n}\n\nfunction fuzzyMatchObject(\n expected: Record,\n actual: Record,\n options: FuzzyMatchOptions,\n context?: string,\n): boolean {\n return Object.entries(expected).every(\n ([key, value]) =>\n key in actual && fuzzyMatch(value, actual[key], options, context),\n );\n}\n\nfunction fuzzyMatchWithCoercion(expected: unknown, actual: unknown): boolean {\n if (typeof expected === \"boolean\" && typeof actual === \"string\") {\n return expected === (actual.toLowerCase() === \"true\" || actual === \"1\");\n }\n\n if (typeof expected === \"string\" && typeof actual === \"number\") {\n return Number.parseFloat(expected) === actual;\n }\n\n if (typeof expected === \"number\" && typeof actual === \"string\") {\n return expected === Number.parseFloat(actual);\n }\n\n return false;\n}\n\n/** Compares two values with the configured fuzzy matching rules. */\nexport function fuzzyMatch(\n expected: unknown,\n actual: unknown,\n options: FuzzyMatchOptions = {},\n context?: string,\n): boolean {\n const { coerceTypes = false } = options;\n\n if (expected instanceof RegExp) {\n return typeof actual === \"string\" && expected.test(actual);\n }\n\n if (typeof expected === \"function\") {\n return Boolean((expected as (value: unknown) => unknown)(actual));\n }\n\n if (\n expected === null ||\n expected === undefined ||\n actual === null ||\n actual === undefined\n ) {\n return expected === actual;\n }\n\n if (typeof expected === \"string\" && typeof actual === \"string\") {\n return fuzzyMatchString(expected, actual, options);\n }\n\n if (typeof expected === \"number\" && typeof actual === \"number\") {\n return fuzzyMatchNumber(expected, actual, options);\n }\n\n if (Array.isArray(expected) && Array.isArray(actual)) {\n return fuzzyMatchArray(expected, actual, options, context);\n }\n\n if (isRecord(expected) && isRecord(actual)) {\n return fuzzyMatchObject(expected, actual, options, context);\n }\n\n if (coerceTypes && fuzzyMatchWithCoercion(expected, actual)) {\n return true;\n }\n\n return expected === actual;\n}\n\n/** Builds a reusable matcher function from a strict, fuzzy, or custom strategy. */\nexport function createMatcher(\n strategy: MatchStrategy,\n options?: FuzzyMatchOptions,\n): (expected: T, actual: T, context?: string) => boolean {\n if (typeof strategy === \"function\") {\n return (expected, actual, context) => strategy(expected, actual, context);\n }\n\n if (strategy === \"strict\") {\n return (expected, actual, context) =>\n strictEquals(expected, actual, context);\n }\n\n return (expected, actual, context) =>\n fuzzyMatch(expected, actual, options ?? {}, context);\n}\n\n/** Formats a value for scorer rationale and debug output. */\nexport function formatValue(value: unknown): string {\n if (value === undefined) {\n return \"undefined\";\n }\n\n if (value === null) {\n return \"null\";\n }\n\n if (value instanceof RegExp) {\n return value.toString();\n }\n\n if (typeof value === \"string\") {\n return `\"${value}\"`;\n }\n\n if (typeof value === \"object\") {\n try {\n return JSON.stringify(value);\n } catch {\n return String(value);\n }\n }\n\n return String(value);\n}\n\n/** Returns a normalized partial-credit score for match-based scorers. */\nexport function calculatePartialScore(\n matched: number,\n total: number,\n requireAll: boolean,\n): number {\n if (requireAll && matched < total) {\n return 0;\n }\n\n return total > 0 ? matched / total : 1;\n}\n\nconst defaultLogger: Logger = {\n log: (message: string, ...args: unknown[]) => {\n if (\n process.env.NODE_ENV === \"development\" ||\n process.env.NODE_ENV === \"test\" ||\n process.env.VITEST_EVALS_DEBUG === \"true\"\n ) {\n console.log(message, ...args);\n }\n },\n};\n\n/** Emits scorer debug details through the provided logger. */\nexport function debugLog(\n context: string,\n data: {\n expected: unknown;\n actual: unknown;\n matches?: string[];\n mismatches?: Mismatch[];\n extras?: string[];\n },\n logger: Logger = defaultLogger,\n): void {\n logger.log(`${context} debug:`);\n logger.log(\"Expected:\", data.expected);\n logger.log(\"Actual:\", data.actual);\n if (data.matches) {\n logger.log(\"Matches:\", data.matches);\n }\n if (data.mismatches) {\n logger.log(\"Mismatches:\", data.mismatches);\n }\n if (data.extras) {\n logger.log(\"Extras:\", data.extras);\n }\n}\n","import type { BaseScorerOptions, ScoredResult, ToolCallLike } from \"./scoring\";\nimport { normalizeContent } from \"../harness\";\nimport {\n createMatcher,\n type BaseMatcherConfig,\n type FuzzyMatchOptions,\n type MatchStrategy,\n} from \"./matchers\";\n\nexport type ExpectedTool = {\n /** Expected tool name. */\n name: string;\n /** Expected tool arguments matched according to the configured strategy. */\n arguments?: unknown;\n};\n\nexport interface ToolCallScorerOptions extends BaseScorerOptions {\n /** Expected tool calls for the run. */\n expectedTools?: ExpectedTool[];\n}\n\nexport interface ToolCallScorerConfig extends BaseMatcherConfig {\n /** Require expected tools to appear in the configured order. */\n ordered?: boolean;\n /** Matching strategy for expected tool arguments. */\n params?: MatchStrategy;\n /** Options used when argument matching is fuzzy. */\n fuzzyOptions?: FuzzyMatchOptions;\n}\n\n/** Creates a tool-call scorer used by both harness judges and legacy wrappers. */\nexport function ToolCallScorer(config: ToolCallScorerConfig = {}) {\n const {\n ordered = false,\n requireAll = true,\n allowExtras = true,\n params = \"strict\",\n fuzzyOptions: userFuzzyOptions,\n } = config;\n\n const fuzzyOptions: FuzzyMatchOptions = {\n substring: true,\n caseInsensitive: true,\n ignoreArrayOrder: true,\n numericTolerance: 0.001,\n coerceTypes: false,\n ...userFuzzyOptions,\n };\n const argMatcher = createMatcher(params, fuzzyOptions);\n\n const scorer = async (opts: ToolCallScorerOptions): Promise => {\n const expectedTools = opts.expectedTools ?? [];\n const actualCalls = opts.toolCalls ?? [];\n\n if (expectedTools.length === 0) {\n return {\n score: 1,\n metadata: {\n rationale: \"No tool calls expected\",\n },\n };\n }\n\n if (actualCalls.length === 0) {\n return {\n score: 0,\n metadata: {\n rationale: `Expected ${expectedTools.length} tool(s) but none were called`,\n },\n };\n }\n\n return ordered\n ? evaluateOrderedTools(expectedTools, actualCalls, {\n argMatcher,\n allowExtras,\n requireAllTools: requireAll,\n })\n : evaluateUnorderedTools(expectedTools, actualCalls, {\n argMatcher,\n requireAllTools: requireAll,\n allowExtras,\n });\n };\n\n Object.defineProperty(scorer, \"name\", {\n value: \"ToolCallScorer\",\n });\n\n return scorer;\n}\n\nfunction evaluateOrderedTools(\n expected: ExpectedTool[],\n actual: ToolCallLike[],\n options: {\n argMatcher: (expected: unknown, actual: unknown) => boolean;\n allowExtras: boolean;\n requireAllTools: boolean;\n },\n): ScoredResult {\n let expectedIndex = 0;\n let actualIndex = 0;\n\n while (expectedIndex < expected.length && actualIndex < actual.length) {\n const expectedTool = expected[expectedIndex];\n const actualTool = actual[actualIndex];\n\n if (expectedTool.name === actualTool.name) {\n if (\n expectedTool.arguments !== undefined &&\n !options.argMatcher(expectedTool.arguments, actualTool.arguments ?? {})\n ) {\n return {\n score: expectedIndex / expected.length,\n metadata: {\n rationale: `Tool '${expectedTool.name}' called with incorrect arguments at position ${expectedIndex + 1} (${expectedIndex}/${expected.length} tools matched correctly)`,\n expected: normalizeContent(expectedTool.arguments),\n actual:\n actualTool.arguments === undefined\n ? undefined\n : normalizeContent(actualTool.arguments),\n matched: expectedIndex,\n total: expected.length,\n },\n };\n }\n\n expectedIndex++;\n actualIndex++;\n continue;\n }\n\n if (options.allowExtras) {\n actualIndex++;\n continue;\n }\n\n return {\n score: 0,\n metadata: {\n rationale: `Expected '${expectedTool.name}' at position ${expectedIndex + 1} but found '${actualTool.name}'`,\n },\n };\n }\n\n if (expectedIndex < expected.length) {\n const missing = expected.slice(expectedIndex).map((tool) => tool.name);\n if (options.requireAllTools) {\n return {\n score: 0,\n metadata: {\n rationale: `Missing required tools in sequence: ${missing.join(\", \")}`,\n },\n };\n }\n\n const matchedCount = expectedIndex;\n const totalCount = expected.length;\n return {\n score: totalCount > 0 ? matchedCount / totalCount : 1,\n metadata: {\n rationale: `Partial match: ${matchedCount}/${totalCount} tools called in order (missing: ${missing.join(\", \")})`,\n matched: matchedCount,\n total: totalCount,\n },\n };\n }\n\n if (!options.allowExtras && actualIndex < actual.length) {\n const extra = actual.slice(actualIndex).map((tool) => tool.name);\n return {\n score: 0,\n metadata: {\n rationale: `Unexpected extra tools: ${extra.join(\", \")}`,\n },\n };\n }\n\n return {\n score: 1,\n metadata: {\n rationale: \"All tools called in expected order with correct arguments\",\n },\n };\n}\n\nfunction evaluateUnorderedTools(\n expected: ExpectedTool[],\n actual: ToolCallLike[],\n options: {\n argMatcher: (expected: unknown, actual: unknown) => boolean;\n requireAllTools: boolean;\n allowExtras: boolean;\n },\n): ScoredResult {\n const remainingExpected = [...expected];\n const remainingActual = [...actual];\n const issues: string[] = [];\n\n for (let index = remainingExpected.length - 1; index >= 0; index--) {\n const expectedTool = remainingExpected[index];\n const matchIndex = remainingActual.findIndex((actualTool) => {\n if (expectedTool.name !== actualTool.name) {\n return false;\n }\n\n return expectedTool.arguments === undefined\n ? true\n : options.argMatcher(\n expectedTool.arguments,\n actualTool.arguments ?? {},\n );\n });\n\n if (matchIndex !== -1) {\n remainingExpected.splice(index, 1);\n remainingActual.splice(matchIndex, 1);\n }\n }\n\n for (const missingTool of remainingExpected) {\n if (missingTool.arguments !== undefined) {\n const wrongArgsCalls = actual.filter(\n (call) => call.name === missingTool.name,\n );\n issues.push(\n wrongArgsCalls.length > 0\n ? `Tool '${missingTool.name}' called but with incorrect arguments`\n : `Missing required tool: ${missingTool.name}`,\n );\n } else {\n issues.push(`Missing required tool: ${missingTool.name}`);\n }\n }\n\n const extraTools = remainingActual.map((tool) => tool.name);\n if (!options.allowExtras && extraTools.length > 0) {\n issues.push(`Unexpected extra tools: ${extraTools.join(\", \")}`);\n }\n\n const expectedMatched = expected.length - remainingExpected.length;\n const score = expected.length > 0 ? expectedMatched / expected.length : 1;\n if (issues.length > 0 && (options.requireAllTools || !options.allowExtras)) {\n return {\n score: 0,\n metadata: {\n rationale: issues.join(\"; \"),\n },\n };\n }\n\n if (score === 1) {\n const extraInfo =\n extraTools.length > 0 ? ` (plus extra: ${extraTools.join(\", \")})` : \"\";\n\n return {\n score: 1,\n metadata: {\n rationale: `All expected tools were called${extraInfo}`,\n },\n };\n }\n\n return {\n score,\n metadata: {\n rationale: issues.join(\"; \"),\n matched: expectedMatched,\n total: expected.length,\n },\n };\n}\n","import type { BaseScorerOptions, ScoreFn } from \"../shared\";\nimport { ToolCallScorer as createToolCallScorer } from \"../../internal/toolCallScorer\";\nimport type {\n BaseMatcherConfig,\n FuzzyMatchOptions,\n MatchStrategy,\n} from \"./utils\";\n\n/** Options passed to the legacy tool-call scorer. */\nexport interface ToolCallScorerOptions extends BaseScorerOptions {\n expectedTools?: Array<{\n name: string;\n arguments?: unknown;\n }>;\n}\n\n/** Configuration for the legacy tool-call scorer factory. */\nexport interface ToolCallScorerConfig extends BaseMatcherConfig {\n ordered?: boolean;\n params?: MatchStrategy;\n fuzzyOptions?: FuzzyMatchOptions;\n}\n\n/**\n * Temporary scorer-first compatibility wrapper.\n *\n * Keep new harness-first code on the non-legacy scorer implementation so this\n * wrapper can be deleted without preserving legacy-specific seams.\n */\nexport function ToolCallScorer(\n config: ToolCallScorerConfig = {},\n): ScoreFn {\n return createToolCallScorer(config) as ScoreFn;\n}\n","import type { BaseScorerOptions, ScoredResult } from \"./scoring\";\nimport {\n createMatcher,\n debugLog,\n formatValue,\n type BaseMatcherConfig,\n type FuzzyMatchOptions,\n type MatchStrategy,\n} from \"./matchers\";\n\nexport interface StructuredOutputScorerOptions extends BaseScorerOptions {\n /** Expected structured output fields. */\n expected?: Record;\n}\n\nexport interface StructuredOutputScorerConfig extends BaseMatcherConfig {\n /** Field matching strategy used for expected structured output values. */\n match?: MatchStrategy;\n /** Output field that indicates an error. Set to `null` to disable. */\n errorField?: string | null;\n /** Options used when `match` is `\"fuzzy\"`. */\n fuzzyOptions?: FuzzyMatchOptions;\n}\n\nfunction formatMismatchDetails(\n mismatches: Array<{ key: string; expected: unknown; actual: unknown }>,\n): string {\n return mismatches\n .map(\n ({ key, expected, actual }) =>\n `${key}: expected ${formatValue(expected)}, got ${formatValue(actual)}`,\n )\n .join(\"; \");\n}\n\n/** Creates a structured-output scorer used by both harness judges and legacy wrappers. */\nexport function StructuredOutputScorer(\n config: StructuredOutputScorerConfig = {},\n) {\n const {\n match = \"strict\",\n requireAll = true,\n allowExtras = true,\n debug = false,\n errorField = \"error\",\n fuzzyOptions = {},\n } = config;\n\n const fieldMatcher =\n typeof match === \"function\" ? match : createMatcher(match, fuzzyOptions);\n\n const scorer = async (\n opts: StructuredOutputScorerOptions,\n ): Promise => {\n const expected = opts.expected ?? {};\n let parsed: Record;\n\n try {\n parsed = JSON.parse(opts.output) as Record;\n } catch (error) {\n return {\n score: 0,\n metadata: {\n rationale: `Failed to parse output as JSON: ${error}`,\n output: opts.output,\n },\n };\n }\n\n if (Object.keys(expected).length === 0) {\n return {\n score: 1,\n metadata: {\n rationale: \"Valid JSON output (no expected fields specified)\",\n },\n };\n }\n\n const errorValue = errorField !== null ? parsed[errorField] : undefined;\n if (\n errorField !== null &&\n errorValue &&\n errorValue !== \"\" &&\n errorValue !== null\n ) {\n return {\n score: 0,\n metadata: {\n rationale: `Output contains error: ${String(errorValue)}`,\n output: opts.output,\n },\n };\n }\n\n const matches: string[] = [];\n const mismatches: Array<{\n key: string;\n expected: unknown;\n actual: unknown;\n }> = [];\n const extras: string[] = [];\n\n for (const [key, expectedValue] of Object.entries(expected)) {\n const actualValue = parsed[key];\n if (fieldMatcher(expectedValue, actualValue, key)) {\n matches.push(key);\n } else {\n mismatches.push({\n key,\n expected: expectedValue,\n actual: actualValue,\n });\n }\n }\n\n const expectedKeys = new Set(Object.keys(expected));\n for (const key of Object.keys(parsed)) {\n if (!expectedKeys.has(key)) {\n extras.push(key);\n }\n }\n\n if (debug) {\n debugLog(\"StructuredOutputScorer\", {\n expected,\n actual: parsed,\n matches,\n mismatches,\n extras,\n });\n }\n\n const totalExpected = Object.keys(expected).length;\n const totalMatched = matches.length;\n\n if (requireAll && mismatches.length > 0) {\n return {\n score: 0,\n metadata: {\n rationale: `Missing required fields: ${mismatches.map((mismatch) => mismatch.key).join(\", \")} - ${formatMismatchDetails(mismatches)}`,\n },\n };\n }\n\n if (!allowExtras && extras.length > 0) {\n return {\n score: 0,\n metadata: {\n rationale: `Unexpected extra fields: ${extras.join(\", \")}`,\n },\n };\n }\n\n const score = totalExpected > 0 ? totalMatched / totalExpected : 1;\n if (score === 1) {\n const extraInfo =\n extras.length > 0 ? ` (plus extra fields: ${extras.join(\", \")})` : \"\";\n\n return {\n score: 1,\n metadata: {\n rationale: `All expected fields match${extraInfo}`,\n },\n };\n }\n\n return {\n score,\n metadata: {\n rationale: `Matched ${totalMatched}/${totalExpected} fields - ${formatMismatchDetails(mismatches)}`,\n matched: totalMatched,\n total: totalExpected,\n },\n };\n };\n\n Object.defineProperty(scorer, \"name\", {\n value: \"StructuredOutputScorer\",\n });\n\n return scorer;\n}\n","import type { BaseScorerOptions, ScoreFn } from \"../shared\";\nimport { StructuredOutputScorer as createStructuredOutputScorer } from \"../../internal/structuredOutputScorer\";\nimport type {\n BaseMatcherConfig,\n FuzzyMatchOptions,\n MatchStrategy,\n} from \"./utils\";\n\n/** Options passed to the legacy structured-output scorer. */\nexport interface StructuredOutputScorerOptions extends BaseScorerOptions {\n expected?: Record;\n}\n\n/** Configuration for the legacy structured-output scorer factory. */\nexport interface StructuredOutputScorerConfig extends BaseMatcherConfig {\n match?: MatchStrategy;\n errorField?: string | null;\n fuzzyOptions?: FuzzyMatchOptions;\n}\n\n/**\n * Temporary scorer-first compatibility wrapper.\n *\n * Keep new harness-first code on the non-legacy scorer implementation so this\n * wrapper can be deleted without preserving legacy-specific seams.\n */\nexport function StructuredOutputScorer(\n config: StructuredOutputScorerConfig = {},\n): ScoreFn {\n return createStructuredOutputScorer(\n config,\n ) as ScoreFn;\n}\n"],"mappings":";AAMA;AAAA,EACE,UAAAA;AAAA,EACA,aAAa;AAAA,EACb,cAAc;AAAA,EACd;AAAA,EACA;AAAA,EACA,QAAAC;AAAA,OACK;AACP,OAAO;;;ACdP;AAAA,EAKE;AAAA,EACA;AAAA,EACA;AAAA,EAGA;AAAA,OAIK;AA0BP;AAAA,EACE,qBAAAC;AAAA,EACA,eAAAC;AAAA,EACA,iCAAAC;AAAA,EACA,kBAAAC;AAAA,EACA,8BAAAC;AAAA,EACA,SAAAC;AAAA,EACA,eAAAC;AAAA,EACA,kBAAAC;AAAA,EACA,aAAAC;AAAA,EACA,gBAAAC;AAAA,EACA,gBAAAC;AAAA,OACK;AA0OP,SAAS,gBAAgB,OAAwC;AAC/D,SACE,UAAU,QACV,OAAO,UAAU,YACjB,OAAO,UAAU,aAChB,OAAO,UAAU,YAAY,OAAO,SAAS,KAAK;AAEvD;AAEA,SAAS,aAAa,OAAkD;AACtE,SAAO,OAAO,UAAU,YAAY,UAAU,QAAQ,CAAC,MAAM,QAAQ,KAAK;AAC5E;AAEA,SAAS,mBAAmB,OAAkB,MAAuB;AACnE,MAAI,KAAK,IAAI,KAAK,GAAG;AACnB,WAAO;AAAA,EACT;AAEA,OAAK,IAAI,KAAK;AACd,QAAM,aAAa,MAAM,IAAI,CAAC,SAAS;AACrC,UAAMC,cAAa,oBAAoB,MAAM,IAAI;AACjD,WAAOA,gBAAe,SAAY,OAAOA;AAAA,EAC3C,CAAC;AACD,OAAK,OAAO,KAAK;AAEjB,SAAO;AACT;AAEA,SAAS,oBACP,OACA,MAC2B;AAC3B,QAAM,aAAwC,CAAC;AAE/C,MAAI,KAAK,IAAI,KAAK,GAAG;AACnB,WAAO;AAAA,EACT;AAEA,OAAK,IAAI,KAAK;AACd,MAAI;AACF,eAAW,CAAC,KAAK,UAAU,KAAK,OAAO,QAAQ,KAAK,GAAG;AACrD,YAAM,QAAQ,oBAAoB,YAAY,IAAI;AAClD,UAAI,UAAU,QAAW;AACvB,mBAAW,GAAG,IAAI;AAAA,MACpB;AAAA,IACF;AAAA,EACF,UAAE;AACA,SAAK,OAAO,KAAK;AAAA,EACnB;AAEA,SAAO;AACT;AAaO,SAAS,YAAY,OAAuC;AACjE,SAAO,oBAAoB,OAAO,oBAAI,QAAQ,CAAC;AACjD;AAEA,SAAS,oBACP,OACA,MACuB;AACvB,MAAI,gBAAgB,KAAK,GAAG;AAC1B,WAAO;AAAA,EACT;AAEA,MACE,UAAU,QACV,OAAO,UAAU,YACjB,KAAK,IAAI,KAAe,GACxB;AACA,WAAO;AAAA,EACT;AAEA,MAAI,MAAM,QAAQ,KAAK,GAAG;AACxB,WAAO,mBAAmB,OAAO,IAAI;AAAA,EACvC;AAEA,MAAI,aAAa,KAAK,GAAG;AACvB,WAAO,oBAAoB,OAAO,IAAI;AAAA,EACxC;AAEA,SAAO;AACT;AAGO,SAAS,gBACd,OAC2B;AAC3B,SAAO,oBAAoB,OAAO,oBAAI,QAAQ,CAAC;AACjD;AAGO,SAAS,kBACd,OACuC;AACvC,QAAM,aAAa,gBAAgB,KAAK;AACxC,SAAO,OAAO,KAAK,UAAU,EAAE,SAAS,IAAI,aAAa;AAC3D;AAGO,SAAS,iBAAiB,OAA2B;AAC1D,QAAM,aAAa,YAAY,KAAK;AACpC,SAAO,eAAe,SAAY,aAAa,OAAO,KAAK;AAC7D;;;AC1YA,SAAS,sBAAsB;AAC/B,SAAS,SAAS;AAClB,SAAS,QAAQ,YAAY;;;ACEtB,SAAS,SAAS,MAAc,QAAQ,IAAY;AACzD,MAAI,CAAC,QAAQ,KAAK,UAAU,OAAO;AACjC,WAAO;AAAA,EACT;AAEA,QAAM,QAAQ,KAAK,MAAM,KAAK;AAC9B,QAAM,QAAkB,CAAC;AACzB,MAAI,cAAc;AAElB,aAAW,QAAQ,OAAO;AACxB,QAAI,YAAY,SAAS,KAAK,SAAS,IAAI,OAAO;AAChD,YAAM,KAAK,YAAY,KAAK,CAAC;AAC7B,oBAAc;AAAA,IAChB,OAAO;AACL,sBAAgB,cAAc,MAAM,MAAM;AAAA,IAC5C;AAAA,EACF;AAEA,MAAI,aAAa;AACf,UAAM,KAAK,WAAW;AAAA,EACxB;AAEA,SAAO,MAAM,KAAK,IAAI;AACxB;AAGO,SAAS,aAAa,QAAsC;AACjE,SAAO,OACJ,IAAI,CAAC,UAAU;AACd,UAAM,YAAY,GAAG,MAAM,QAAQ,SAAS,MAAM,MAAM,SAAS,GAAG,QAAQ,CAAC,CAAC;AAC9E,SACI,MAAM,SAAS,KAAK,KAAO,MAAM,UAAU,aAC7C,MAAM,UAAU,QAChB;AACA,UAAI,kBAAkB;AACtB,UAAI,MAAM,UAAU,WAAW,QAAW;AACxC,cAAM,SAAS,MAAM,SAAS;AAC9B,0BACE,OAAO,WAAW,WACd;AAAA,UAAa,SAAS,MAAM,CAAC,KAC7B;AAAA,UAAa,SAAS,KAAK,UAAU,QAAQ,MAAM,CAAC,CAAC,CAAC;AAAA,MAC9D;AAEA,aAAO,GAAG,SAAS,GACjB,MAAM,UAAU,YACZ;AAAA,UAAa,SAAS,MAAM,SAAS,SAAS,CAAC,KAC/C,EACN,GAAG,eAAe;AAAA,IACpB;AACA,WAAO;AAAA,EACT,CAAC,EACA,KAAK,MAAM;AAChB;;;ADjDA,IAAI;AAGG,SAAS,UAAU,MAAgC;AACxD,iBAAe,KAAK;AACtB;AAEA,IAAM,cAAc;AAEpB,IAAM,cAAc,CAAC,QAAgB,aAAqB;AAAA,EACxD,MAAM;AAAA;AAAA;AAAA;AAAA,EAIN,QAAQ;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAUV,IAAM,gBAAwC;AAAA,EAC5C,GAAG;AAAA,EACH,GAAG;AAAA,EACH,GAAG;AAAA,EACH,GAAG;AAAA,EACH,GAAG;AACL;AAaA,eAAsB,UACpB,KACA,MACe;AACf,MAAI,CAAC,cAAc;AACjB,UAAM,IAAI;AAAA,MACR;AAAA,IACF;AAAA,EACF;AAEA,MAAI;AACJ,MAAI;AACF,aAAS,MAAM,KAAK,KAAK;AAAA,EAC3B,SAAS,OAAO;AACd,UAAM,eAAe,iBAAiB,QAAQ,MAAM,UAAU,OAAO,KAAK;AAC1E,QAAI,KAAK,KAAK,OAAO;AAAA,MACnB,QAAQ;AAAA,QACN;AAAA,UACE,OAAO;AAAA,UACP,MAAM;AAAA,UACN,UAAU,EAAE,WAAW,gBAAgB,YAAY,GAAG;AAAA,QACxD;AAAA,MACF;AAAA,MACA,UAAU;AAAA,IACZ;AACA,UAAM;AAAA,EACR;AAEA,MAAI;AACJ,MAAI;AACF,KAAC,EAAE,OAAO,IAAI,MAAM,eAAe;AAAA,MACjC,OAAO;AAAA,MACP,QAAQ,EAAE,OAAO;AAAA,QACf,QAAQ,EAAE,KAAK,CAAC,KAAK,KAAK,KAAK,KAAK,GAAG,CAAC;AAAA,QACxC,WAAW,EAAE,OAAO;AAAA,MACtB,CAAC;AAAA,MACD,QAAQ;AAAA,MACR,QAAQ,YAAY,QAAQ,KAAK,QAAQ;AAAA,IAC3C,CAAC;AAAA,EACH,SAAS,OAAO;AACd,UAAM,eAAe,iBAAiB,QAAQ,MAAM,UAAU,OAAO,KAAK;AAC1E,QAAI,KAAK,KAAK,OAAO;AAAA,MACnB,QAAQ;AAAA,QACN;AAAA,UACE,OAAO;AAAA,UACP,MAAM;AAAA,UACN,UAAU,EAAE,WAAW,iBAAiB,YAAY,GAAG;AAAA,QACzD;AAAA,MACF;AAAA,MACA,UAAU;AAAA,IACZ;AACA,UAAM;AAAA,EACR;AAEA,QAAM,QAAQ,cAAc,OAAO,MAAM;AACzC,QAAM,YAAY,KAAK,aAAa;AAEpC,MAAI,KAAK,KAAK,OAAO;AAAA,IACnB,QAAQ;AAAA,MACN;AAAA,QACE;AAAA,QACA,MAAM;AAAA,QACN,UAAU,EAAE,WAAW,OAAO,WAAW,QAAQ,OAAO,OAAO;AAAA,MACjE;AAAA,IACF;AAAA,IACA,UAAU;AAAA,EACZ;AAEA,MAAI,QAAQ,WAAW;AACrB;AAAA,MACE;AAAA,MACA,UAAU,KAAK,KAAK,OAAO,MAAM,sBAAsB,SAAS;AAAA;AAAA;AAAA,EAAmB,SAAS,MAAM,CAAC;AAAA;AAAA;AAAA,EAAsB,SAAS,OAAO,SAAS,CAAC;AAAA,IACrJ;AAAA,EACF;AACF;AAGO,SAAS,SACd,MACA,MACA;AACA,OAAK,MAAM,EAAE,SAAS,KAAK,WAAW,IAAM,GAAG,OAAO,EAAE,MAAM,SAAS,MAAM;AAC3E,UAAM,UAAU,EAAE,MAAM,SAAS,GAAG,IAAI;AAAA,EAC1C,CAAC;AACH;;;AErEA,SAAS,SAAS,OAAkD;AAClE,SAAO,OAAO,UAAU,YAAY,UAAU,QAAQ,CAAC,MAAM,QAAQ,KAAK;AAC5E;AAGO,SAAS,aACd,UACA,QACA,SACS;AACT,OAAK;AAEL,MAAI,aAAa,QAAQ;AACvB,WAAO;AAAA,EACT;AAEA,MACE,aAAa,QACb,aAAa,UACb,WAAW,QACX,WAAW,QACX;AACA,WAAO;AAAA,EACT;AAEA,MAAI,OAAO,aAAa,OAAO,QAAQ;AACrC,WAAO;AAAA,EACT;AAEA,MAAI,MAAM,QAAQ,QAAQ,GAAG;AAC3B,WACE,MAAM,QAAQ,MAAM,KACpB,SAAS,WAAW,OAAO,UAC3B,SAAS;AAAA,MAAM,CAAC,MAAM,UACpB,aAAa,MAAM,OAAO,KAAK,GAAG,OAAO;AAAA,IAC3C;AAAA,EAEJ;AAEA,MAAI,SAAS,QAAQ,KAAK,SAAS,MAAM,GAAG;AAC1C,UAAM,eAAe,OAAO,KAAK,QAAQ;AACzC,UAAM,aAAa,OAAO,KAAK,MAAM;AAErC,WACE,aAAa,WAAW,WAAW,UACnC,aAAa;AAAA,MACX,CAAC,QACC,OAAO,UAAU,aAAa,SAAS,GAAG,GAAG,OAAO,GAAG,GAAG,OAAO;AAAA,IACrE;AAAA,EAEJ;AAEA,SAAO;AACT;AAEA,SAAS,iBACP,UACA,QACA,SACS;AACT,QAAM,EAAE,kBAAkB,MAAM,YAAY,MAAM,IAAI;AACtD,QAAM,eAAe,kBAAkB,SAAS,YAAY,IAAI;AAChE,QAAM,aAAa,kBAAkB,OAAO,YAAY,IAAI;AAE5D,SAAO,YACH,WAAW,SAAS,YAAY,KAAK,aAAa,SAAS,UAAU,IACrE,iBAAiB;AACvB;AAEA,SAAS,iBACP,UACA,QACA,SACS;AACT,QAAM,EAAE,mBAAmB,KAAM,IAAI;AACrC,QAAM,YAAY,KAAK;AAAA,IACrB,KAAK,IAAI,QAAQ,IAAI;AAAA,IACrB;AAAA,EACF;AAEA,SAAO,KAAK,IAAI,WAAW,MAAM,KAAK;AACxC;AAEA,SAAS,gBACP,UACA,QACA,SACA,SACS;AACT,QAAM,EAAE,mBAAmB,KAAK,IAAI;AAEpC,MAAI,CAAC,kBAAkB;AACrB,WACE,SAAS,WAAW,OAAO,UAC3B,SAAS;AAAA,MAAM,CAAC,MAAM,UACpB,WAAW,MAAM,OAAO,KAAK,GAAG,SAAS,OAAO;AAAA,IAClD;AAAA,EAEJ;AAEA,QAAM,aAAa,OAAO,IAAI,MAAM,KAAK;AACzC,SAAO,SAAS,MAAM,CAAC,iBAAiB;AACtC,eAAW,CAAC,OAAO,UAAU,KAAK,OAAO,QAAQ,GAAG;AAClD,UAAI,WAAW,KAAK,GAAG;AACrB;AAAA,MACF;AAEA,UAAI,WAAW,cAAc,YAAY,SAAS,OAAO,GAAG;AAC1D,mBAAW,KAAK,IAAI;AACpB,eAAO;AAAA,MACT;AAAA,IACF;AAEA,WAAO;AAAA,EACT,CAAC;AACH;AAEA,SAAS,iBACP,UACA,QACA,SACA,SACS;AACT,SAAO,OAAO,QAAQ,QAAQ,EAAE;AAAA,IAC9B,CAAC,CAAC,KAAK,KAAK,MACV,OAAO,UAAU,WAAW,OAAO,OAAO,GAAG,GAAG,SAAS,OAAO;AAAA,EACpE;AACF;AAEA,SAAS,uBAAuB,UAAmB,QAA0B;AAC3E,MAAI,OAAO,aAAa,aAAa,OAAO,WAAW,UAAU;AAC/D,WAAO,cAAc,OAAO,YAAY,MAAM,UAAU,WAAW;AAAA,EACrE;AAEA,MAAI,OAAO,aAAa,YAAY,OAAO,WAAW,UAAU;AAC9D,WAAO,OAAO,WAAW,QAAQ,MAAM;AAAA,EACzC;AAEA,MAAI,OAAO,aAAa,YAAY,OAAO,WAAW,UAAU;AAC9D,WAAO,aAAa,OAAO,WAAW,MAAM;AAAA,EAC9C;AAEA,SAAO;AACT;AAGO,SAAS,WACd,UACA,QACA,UAA6B,CAAC,GAC9B,SACS;AACT,QAAM,EAAE,cAAc,MAAM,IAAI;AAEhC,MAAI,oBAAoB,QAAQ;AAC9B,WAAO,OAAO,WAAW,YAAY,SAAS,KAAK,MAAM;AAAA,EAC3D;AAEA,MAAI,OAAO,aAAa,YAAY;AAClC,WAAO,QAAS,SAAyC,MAAM,CAAC;AAAA,EAClE;AAEA,MACE,aAAa,QACb,aAAa,UACb,WAAW,QACX,WAAW,QACX;AACA,WAAO,aAAa;AAAA,EACtB;AAEA,MAAI,OAAO,aAAa,YAAY,OAAO,WAAW,UAAU;AAC9D,WAAO,iBAAiB,UAAU,QAAQ,OAAO;AAAA,EACnD;AAEA,MAAI,OAAO,aAAa,YAAY,OAAO,WAAW,UAAU;AAC9D,WAAO,iBAAiB,UAAU,QAAQ,OAAO;AAAA,EACnD;AAEA,MAAI,MAAM,QAAQ,QAAQ,KAAK,MAAM,QAAQ,MAAM,GAAG;AACpD,WAAO,gBAAgB,UAAU,QAAQ,SAAS,OAAO;AAAA,EAC3D;AAEA,MAAI,SAAS,QAAQ,KAAK,SAAS,MAAM,GAAG;AAC1C,WAAO,iBAAiB,UAAU,QAAQ,SAAS,OAAO;AAAA,EAC5D;AAEA,MAAI,eAAe,uBAAuB,UAAU,MAAM,GAAG;AAC3D,WAAO;AAAA,EACT;AAEA,SAAO,aAAa;AACtB;AAGO,SAAS,cACd,UACA,SACuD;AACvD,MAAI,OAAO,aAAa,YAAY;AAClC,WAAO,CAAC,UAAU,QAAQ,YAAY,SAAS,UAAU,QAAQ,OAAO;AAAA,EAC1E;AAEA,MAAI,aAAa,UAAU;AACzB,WAAO,CAAC,UAAU,QAAQ,YACxB,aAAa,UAAU,QAAQ,OAAO;AAAA,EAC1C;AAEA,SAAO,CAAC,UAAU,QAAQ,YACxB,WAAW,UAAU,QAAQ,WAAW,CAAC,GAAG,OAAO;AACvD;AAGO,SAAS,YAAY,OAAwB;AAClD,MAAI,UAAU,QAAW;AACvB,WAAO;AAAA,EACT;AAEA,MAAI,UAAU,MAAM;AAClB,WAAO;AAAA,EACT;AAEA,MAAI,iBAAiB,QAAQ;AAC3B,WAAO,MAAM,SAAS;AAAA,EACxB;AAEA,MAAI,OAAO,UAAU,UAAU;AAC7B,WAAO,IAAI,KAAK;AAAA,EAClB;AAEA,MAAI,OAAO,UAAU,UAAU;AAC7B,QAAI;AACF,aAAO,KAAK,UAAU,KAAK;AAAA,IAC7B,QAAQ;AACN,aAAO,OAAO,KAAK;AAAA,IACrB;AAAA,EACF;AAEA,SAAO,OAAO,KAAK;AACrB;AAeA,IAAM,gBAAwB;AAAA,EAC5B,KAAK,CAAC,YAAoB,SAAoB;AAC5C,QACE,QAAQ,IAAI,aAAa,iBACzB,QAAQ,IAAI,aAAa,UACzB,QAAQ,IAAI,uBAAuB,QACnC;AACA,cAAQ,IAAI,SAAS,GAAG,IAAI;AAAA,IAC9B;AAAA,EACF;AACF;AAGO,SAAS,SACd,SACA,MAOA,SAAiB,eACX;AACN,SAAO,IAAI,GAAG,OAAO,SAAS;AAC9B,SAAO,IAAI,aAAa,KAAK,QAAQ;AACrC,SAAO,IAAI,WAAW,KAAK,MAAM;AACjC,MAAI,KAAK,SAAS;AAChB,WAAO,IAAI,YAAY,KAAK,OAAO;AAAA,EACrC;AACA,MAAI,KAAK,YAAY;AACnB,WAAO,IAAI,eAAe,KAAK,UAAU;AAAA,EAC3C;AACA,MAAI,KAAK,QAAQ;AACf,WAAO,IAAI,WAAW,KAAK,MAAM;AAAA,EACnC;AACF;;;AC1UO,SAAS,eAAe,SAA+B,CAAC,GAAG;AAChE,QAAM;AAAA,IACJ,UAAU;AAAA,IACV,aAAa;AAAA,IACb,cAAc;AAAA,IACd,SAAS;AAAA,IACT,cAAc;AAAA,EAChB,IAAI;AAEJ,QAAM,eAAkC;AAAA,IACtC,WAAW;AAAA,IACX,iBAAiB;AAAA,IACjB,kBAAkB;AAAA,IAClB,kBAAkB;AAAA,IAClB,aAAa;AAAA,IACb,GAAG;AAAA,EACL;AACA,QAAM,aAAa,cAAc,QAAQ,YAAY;AAErD,QAAM,SAAS,OAAO,SAAuD;AAC3E,UAAM,gBAAgB,KAAK,iBAAiB,CAAC;AAC7C,UAAM,cAAc,KAAK,aAAa,CAAC;AAEvC,QAAI,cAAc,WAAW,GAAG;AAC9B,aAAO;AAAA,QACL,OAAO;AAAA,QACP,UAAU;AAAA,UACR,WAAW;AAAA,QACb;AAAA,MACF;AAAA,IACF;AAEA,QAAI,YAAY,WAAW,GAAG;AAC5B,aAAO;AAAA,QACL,OAAO;AAAA,QACP,UAAU;AAAA,UACR,WAAW,YAAY,cAAc,MAAM;AAAA,QAC7C;AAAA,MACF;AAAA,IACF;AAEA,WAAO,UACH,qBAAqB,eAAe,aAAa;AAAA,MAC/C;AAAA,MACA;AAAA,MACA,iBAAiB;AAAA,IACnB,CAAC,IACD,uBAAuB,eAAe,aAAa;AAAA,MACjD;AAAA,MACA,iBAAiB;AAAA,MACjB;AAAA,IACF,CAAC;AAAA,EACP;AAEA,SAAO,eAAe,QAAQ,QAAQ;AAAA,IACpC,OAAO;AAAA,EACT,CAAC;AAED,SAAO;AACT;AAEA,SAAS,qBACP,UACA,QACA,SAKc;AACd,MAAI,gBAAgB;AACpB,MAAI,cAAc;AAElB,SAAO,gBAAgB,SAAS,UAAU,cAAc,OAAO,QAAQ;AACrE,UAAM,eAAe,SAAS,aAAa;AAC3C,UAAM,aAAa,OAAO,WAAW;AAErC,QAAI,aAAa,SAAS,WAAW,MAAM;AACzC,UACE,aAAa,cAAc,UAC3B,CAAC,QAAQ,WAAW,aAAa,WAAW,WAAW,aAAa,CAAC,CAAC,GACtE;AACA,eAAO;AAAA,UACL,OAAO,gBAAgB,SAAS;AAAA,UAChC,UAAU;AAAA,YACR,WAAW,SAAS,aAAa,IAAI,iDAAiD,gBAAgB,CAAC,KAAK,aAAa,IAAI,SAAS,MAAM;AAAA,YAC5I,UAAU,iBAAiB,aAAa,SAAS;AAAA,YACjD,QACE,WAAW,cAAc,SACrB,SACA,iBAAiB,WAAW,SAAS;AAAA,YAC3C,SAAS;AAAA,YACT,OAAO,SAAS;AAAA,UAClB;AAAA,QACF;AAAA,MACF;AAEA;AACA;AACA;AAAA,IACF;AAEA,QAAI,QAAQ,aAAa;AACvB;AACA;AAAA,IACF;AAEA,WAAO;AAAA,MACL,OAAO;AAAA,MACP,UAAU;AAAA,QACR,WAAW,aAAa,aAAa,IAAI,iBAAiB,gBAAgB,CAAC,eAAe,WAAW,IAAI;AAAA,MAC3G;AAAA,IACF;AAAA,EACF;AAEA,MAAI,gBAAgB,SAAS,QAAQ;AACnC,UAAM,UAAU,SAAS,MAAM,aAAa,EAAE,IAAI,CAAC,SAAS,KAAK,IAAI;AACrE,QAAI,QAAQ,iBAAiB;AAC3B,aAAO;AAAA,QACL,OAAO;AAAA,QACP,UAAU;AAAA,UACR,WAAW,uCAAuC,QAAQ,KAAK,IAAI,CAAC;AAAA,QACtE;AAAA,MACF;AAAA,IACF;AAEA,UAAM,eAAe;AACrB,UAAM,aAAa,SAAS;AAC5B,WAAO;AAAA,MACL,OAAO,aAAa,IAAI,eAAe,aAAa;AAAA,MACpD,UAAU;AAAA,QACR,WAAW,kBAAkB,YAAY,IAAI,UAAU,oCAAoC,QAAQ,KAAK,IAAI,CAAC;AAAA,QAC7G,SAAS;AAAA,QACT,OAAO;AAAA,MACT;AAAA,IACF;AAAA,EACF;AAEA,MAAI,CAAC,QAAQ,eAAe,cAAc,OAAO,QAAQ;AACvD,UAAM,QAAQ,OAAO,MAAM,WAAW,EAAE,IAAI,CAAC,SAAS,KAAK,IAAI;AAC/D,WAAO;AAAA,MACL,OAAO;AAAA,MACP,UAAU;AAAA,QACR,WAAW,2BAA2B,MAAM,KAAK,IAAI,CAAC;AAAA,MACxD;AAAA,IACF;AAAA,EACF;AAEA,SAAO;AAAA,IACL,OAAO;AAAA,IACP,UAAU;AAAA,MACR,WAAW;AAAA,IACb;AAAA,EACF;AACF;AAEA,SAAS,uBACP,UACA,QACA,SAKc;AACd,QAAM,oBAAoB,CAAC,GAAG,QAAQ;AACtC,QAAM,kBAAkB,CAAC,GAAG,MAAM;AAClC,QAAM,SAAmB,CAAC;AAE1B,WAAS,QAAQ,kBAAkB,SAAS,GAAG,SAAS,GAAG,SAAS;AAClE,UAAM,eAAe,kBAAkB,KAAK;AAC5C,UAAM,aAAa,gBAAgB,UAAU,CAAC,eAAe;AAC3D,UAAI,aAAa,SAAS,WAAW,MAAM;AACzC,eAAO;AAAA,MACT;AAEA,aAAO,aAAa,cAAc,SAC9B,OACA,QAAQ;AAAA,QACN,aAAa;AAAA,QACb,WAAW,aAAa,CAAC;AAAA,MAC3B;AAAA,IACN,CAAC;AAED,QAAI,eAAe,IAAI;AACrB,wBAAkB,OAAO,OAAO,CAAC;AACjC,sBAAgB,OAAO,YAAY,CAAC;AAAA,IACtC;AAAA,EACF;AAEA,aAAW,eAAe,mBAAmB;AAC3C,QAAI,YAAY,cAAc,QAAW;AACvC,YAAM,iBAAiB,OAAO;AAAA,QAC5B,CAAC,SAAS,KAAK,SAAS,YAAY;AAAA,MACtC;AACA,aAAO;AAAA,QACL,eAAe,SAAS,IACpB,SAAS,YAAY,IAAI,0CACzB,0BAA0B,YAAY,IAAI;AAAA,MAChD;AAAA,IACF,OAAO;AACL,aAAO,KAAK,0BAA0B,YAAY,IAAI,EAAE;AAAA,IAC1D;AAAA,EACF;AAEA,QAAM,aAAa,gBAAgB,IAAI,CAAC,SAAS,KAAK,IAAI;AAC1D,MAAI,CAAC,QAAQ,eAAe,WAAW,SAAS,GAAG;AACjD,WAAO,KAAK,2BAA2B,WAAW,KAAK,IAAI,CAAC,EAAE;AAAA,EAChE;AAEA,QAAM,kBAAkB,SAAS,SAAS,kBAAkB;AAC5D,QAAM,QAAQ,SAAS,SAAS,IAAI,kBAAkB,SAAS,SAAS;AACxE,MAAI,OAAO,SAAS,MAAM,QAAQ,mBAAmB,CAAC,QAAQ,cAAc;AAC1E,WAAO;AAAA,MACL,OAAO;AAAA,MACP,UAAU;AAAA,QACR,WAAW,OAAO,KAAK,IAAI;AAAA,MAC7B;AAAA,IACF;AAAA,EACF;AAEA,MAAI,UAAU,GAAG;AACf,UAAM,YACJ,WAAW,SAAS,IAAI,iBAAiB,WAAW,KAAK,IAAI,CAAC,MAAM;AAEtE,WAAO;AAAA,MACL,OAAO;AAAA,MACP,UAAU;AAAA,QACR,WAAW,iCAAiC,SAAS;AAAA,MACvD;AAAA,IACF;AAAA,EACF;AAEA,SAAO;AAAA,IACL;AAAA,IACA,UAAU;AAAA,MACR,WAAW,OAAO,KAAK,IAAI;AAAA,MAC3B,SAAS;AAAA,MACT,OAAO,SAAS;AAAA,IAClB;AAAA,EACF;AACF;;;ACnPO,SAASC,gBACd,SAA+B,CAAC,GACA;AAChC,SAAO,eAAqB,MAAM;AACpC;;;ACTA,SAAS,sBACP,YACQ;AACR,SAAO,WACJ;AAAA,IACC,CAAC,EAAE,KAAK,UAAU,OAAO,MACvB,GAAG,GAAG,cAAc,YAAY,QAAQ,CAAC,SAAS,YAAY,MAAM,CAAC;AAAA,EACzE,EACC,KAAK,IAAI;AACd;AAGO,SAAS,uBACd,SAAuC,CAAC,GACxC;AACA,QAAM;AAAA,IACJ,QAAQ;AAAA,IACR,aAAa;AAAA,IACb,cAAc;AAAA,IACd,QAAQ;AAAA,IACR,aAAa;AAAA,IACb,eAAe,CAAC;AAAA,EAClB,IAAI;AAEJ,QAAM,eACJ,OAAO,UAAU,aAAa,QAAQ,cAAc,OAAO,YAAY;AAEzE,QAAM,SAAS,OACb,SAC0B;AAC1B,UAAM,WAAW,KAAK,YAAY,CAAC;AACnC,QAAI;AAEJ,QAAI;AACF,eAAS,KAAK,MAAM,KAAK,MAAM;AAAA,IACjC,SAAS,OAAO;AACd,aAAO;AAAA,QACL,OAAO;AAAA,QACP,UAAU;AAAA,UACR,WAAW,mCAAmC,KAAK;AAAA,UACnD,QAAQ,KAAK;AAAA,QACf;AAAA,MACF;AAAA,IACF;AAEA,QAAI,OAAO,KAAK,QAAQ,EAAE,WAAW,GAAG;AACtC,aAAO;AAAA,QACL,OAAO;AAAA,QACP,UAAU;AAAA,UACR,WAAW;AAAA,QACb;AAAA,MACF;AAAA,IACF;AAEA,UAAM,aAAa,eAAe,OAAO,OAAO,UAAU,IAAI;AAC9D,QACE,eAAe,QACf,cACA,eAAe,MACf,eAAe,MACf;AACA,aAAO;AAAA,QACL,OAAO;AAAA,QACP,UAAU;AAAA,UACR,WAAW,0BAA0B,OAAO,UAAU,CAAC;AAAA,UACvD,QAAQ,KAAK;AAAA,QACf;AAAA,MACF;AAAA,IACF;AAEA,UAAM,UAAoB,CAAC;AAC3B,UAAM,aAID,CAAC;AACN,UAAM,SAAmB,CAAC;AAE1B,eAAW,CAAC,KAAK,aAAa,KAAK,OAAO,QAAQ,QAAQ,GAAG;AAC3D,YAAM,cAAc,OAAO,GAAG;AAC9B,UAAI,aAAa,eAAe,aAAa,GAAG,GAAG;AACjD,gBAAQ,KAAK,GAAG;AAAA,MAClB,OAAO;AACL,mBAAW,KAAK;AAAA,UACd;AAAA,UACA,UAAU;AAAA,UACV,QAAQ;AAAA,QACV,CAAC;AAAA,MACH;AAAA,IACF;AAEA,UAAM,eAAe,IAAI,IAAI,OAAO,KAAK,QAAQ,CAAC;AAClD,eAAW,OAAO,OAAO,KAAK,MAAM,GAAG;AACrC,UAAI,CAAC,aAAa,IAAI,GAAG,GAAG;AAC1B,eAAO,KAAK,GAAG;AAAA,MACjB;AAAA,IACF;AAEA,QAAI,OAAO;AACT,eAAS,0BAA0B;AAAA,QACjC;AAAA,QACA,QAAQ;AAAA,QACR;AAAA,QACA;AAAA,QACA;AAAA,MACF,CAAC;AAAA,IACH;AAEA,UAAM,gBAAgB,OAAO,KAAK,QAAQ,EAAE;AAC5C,UAAM,eAAe,QAAQ;AAE7B,QAAI,cAAc,WAAW,SAAS,GAAG;AACvC,aAAO;AAAA,QACL,OAAO;AAAA,QACP,UAAU;AAAA,UACR,WAAW,4BAA4B,WAAW,IAAI,CAAC,aAAa,SAAS,GAAG,EAAE,KAAK,IAAI,CAAC,MAAM,sBAAsB,UAAU,CAAC;AAAA,QACrI;AAAA,MACF;AAAA,IACF;AAEA,QAAI,CAAC,eAAe,OAAO,SAAS,GAAG;AACrC,aAAO;AAAA,QACL,OAAO;AAAA,QACP,UAAU;AAAA,UACR,WAAW,4BAA4B,OAAO,KAAK,IAAI,CAAC;AAAA,QAC1D;AAAA,MACF;AAAA,IACF;AAEA,UAAM,QAAQ,gBAAgB,IAAI,eAAe,gBAAgB;AACjE,QAAI,UAAU,GAAG;AACf,YAAM,YACJ,OAAO,SAAS,IAAI,wBAAwB,OAAO,KAAK,IAAI,CAAC,MAAM;AAErE,aAAO;AAAA,QACL,OAAO;AAAA,QACP,UAAU;AAAA,UACR,WAAW,4BAA4B,SAAS;AAAA,QAClD;AAAA,MACF;AAAA,IACF;AAEA,WAAO;AAAA,MACL;AAAA,MACA,UAAU;AAAA,QACR,WAAW,WAAW,YAAY,IAAI,aAAa,aAAa,sBAAsB,UAAU,CAAC;AAAA,QACjG,SAAS;AAAA,QACT,OAAO;AAAA,MACT;AAAA,IACF;AAAA,EACF;AAEA,SAAO,eAAe,QAAQ,QAAQ;AAAA,IACpC,OAAO;AAAA,EACT,CAAC;AAED,SAAO;AACT;;;AC3JO,SAASC,wBACd,SAAuC,CAAC,GACA;AACxC,SAAO;AAAA,IACL;AAAA,EACF;AACF;;;AR+CA,OAAO,OAAO;AAAA,EACZ,QAAQ,eAAe,OACrB,OACA,UACA,QACA,SACA,YAAY,GACZ;AACA,UAAM,aAAa,MAAM,OAAO,KAAK;AACrC,UAAM,SACJ,OAAO,eAAe,WAAW,aAAa,WAAW;AAC3D,UAAMC,aACJ,OAAO,eAAe,WAAW,WAAW,YAAY;AAE1D,QAAI,SAAS,QAAQ,EAAE,OAAO,UAAU,QAAQ,WAAAA,WAAU,CAAC;AAC3D,QAAI,kBAAkB,SAAS;AAC7B,eAAS,MAAM;AAAA,IACjB;AAEA,WAAO;AAAA,MACL,OAAO,OAAO,SAAS,MAAM;AAAA,MAC7B,SAAS,MAAM,aAAa,CAAC,EAAE,GAAG,QAAQ,MAAM,QAAQ,KAAK,CAAC,CAAC;AAAA,IACjE;AAAA,EACF;AACF,CAAC;AAOM,SAAS,aAAa,MAAc,SAAoC;AAC7E,SAAO,SAAS,MAAM,YAAY;AAChC,QAAI,QAAQ,YAAY;AACtB,uBAAiB,QAAQ,UAAU;AAAA,IACrC;AACA,QAAI,QAAQ,WAAW;AACrB,sBAAgB,QAAQ,SAAS;AAAA,IACnC;AAEA,UAAM,SAAS,QAAQ,SAASC,MAAK,OAAO,QAAQ,OAAO,CAAC,IAAIA;AAChE,eAAW,EAAE,OAAO,MAAM,UAAU,GAAG,OAAO,KAAK,MAAM,QAAQ,KAAK,GAAG;AACvE;AAAA,QACE,YAAY;AAAA,QACZ;AAAA,UACE,SAAS,QAAQ,WAAW;AAAA,QAC9B;AAAA,QACA,OAAO,EAAE,MAAM,SAAS,MAAM;AAC5B,gBAAM,aAAa,MAAM,QAAQ,KAAK,KAAK;AAC3C,gBAAM,SACJ,OAAO,eAAe,WAAW,aAAa,WAAW;AAC3D,gBAAMD,aACJ,OAAO,eAAe,WAAW,WAAW,YAAY;AAC1D,gBAAM,YACJ,QAAQ,cAAc,SAAY,IAAM,QAAQ;AAElD,gBAAM,SAAS,MAAM,QAAQ;AAAA,YAC3B,QAAQ,QAAQ,IAAI,CAAC,WAAW;AAC9B,oBAAM,SAAS,OAAO,EAAE,OAAO,GAAG,QAAQ,QAAQ,WAAAA,WAAU,CAAC;AAC7D,kBAAI,kBAAkB,SAAS;AAC7B,uBAAO;AAAA,cACT;AACA,qBAAO,IAAI,QAAe,CAAC,YAAY,QAAQ,MAAM,CAAC;AAAA,YACxD,CAAC;AAAA,UACH;AACA,gBAAM,iBAAiB,OAAO,IAAI,CAAC,OAAO,WAAW;AAAA,YACnD,GAAG;AAAA,YACH,MAAM,QAAQ,QAAQ,KAAK,EAAE;AAAA,UAC/B,EAAE;AACF,gBAAM,2BAA2B,eAAe;AAAA,YAC9C,CAAC,EAAE,UAAU,GAAG,MAAM,OAAO;AAAA,cAC3B,GAAG;AAAA,cACH,GAAI,WAAW,EAAE,UAAU,kBAAkB,QAAQ,EAAE,IAAI,CAAC;AAAA,YAC9D;AAAA,UACF;AAEA,gBAAM,WACJ,OAAO,OAAO,CAAC,KAAK,UAAU,OAAO,MAAM,SAAS,IAAI,CAAC,IACzD,OAAO;AACT,gBAAM,kBAAkB,cAAc,QAAQ,WAAW;AAEzD,gBAAM,sBAAsB,yBAAyBA,UAAS;AAE9D,mBAAS,KAAK,OAAO;AAAA,YACnB,QAAQ;AAAA,YACR;AAAA,YACA;AAAA,YACA,GAAI,sBAAsB,EAAE,WAAW,oBAAoB,IAAI,CAAC;AAAA,YAChE;AAAA,UACF;AAEA,cAAI,iBAAiB;AACnB,YAAAE;AAAA,cACE,YAAY;AAAA,cACZ;AAAA,gBACE,UAAU,SAAS,QAAQ,CAAC,CAAC,qBAAqB,UAAU,QAAQ,CAAC,CAAC;AAAA,gBACtE,WAAW,SAAS,MAAM,CAAC;AAAA,gBAC3B,aAAa,cAAc;AAAA,cAC7B,EAAE,KAAK,MAAM;AAAA,YACf;AAAA,UACF;AAAA,QACF;AAAA,MACF;AAAA,IACF;AAAA,EACF,CAAC;AACH;AAEA,SAAS,yBACPF,YACkC;AAClC,SAAOA,YAAW,IAAI,CAAC,SAAS;AAC9B,UAAM,OAAO,YAAY,KAAK,SAAS;AACvC,WAAO;AAAA,MACL,MAAM,KAAK;AAAA,MACX,GAAI,aAAa,IAAI,IAAI,EAAE,WAAW,KAAK,IAAI,CAAC;AAAA,MAChD,QAAQ;AAAA,IACV;AAAA,EACF,CAAC;AACH;AAEA,SAAS,aACP,OACoC;AACpC,SACE,UAAU,UACV,UAAU,QACV,OAAO,UAAU,YACjB,CAAC,MAAM,QAAQ,KAAK;AAExB;","names":["assert","test","assistantMessages","failedSpans","latestAssistantMessageContent","messagesByRole","messagesToTranscriptEvents","spans","spansByKind","systemMessages","toolCalls","toolMessages","userMessages","normalized","ToolCallScorer","StructuredOutputScorer","toolCalls","test","assert"]}