@avallon-labs/mcp 51.3.0-staging.1139 → 51.4.0

package/dist/index.js

@@ -46,5 +46,5 @@ function setupFetch() {
 
 // src/index.ts
 setupFetch();
-await import("./server-DACHXX2C.js");
+await import("./server-EZUDCD4M.js");
 //# sourceMappingURL=index.js.map

package/dist/{server-DACHXX2C.js → server-EZUDCD4M.js}

@@ -1476,6 +1476,28 @@ var createEvalBenchmark = async (evalId, createEvalBenchmarkBody, options) => {
   const data = body ? JSON.parse(body) : {};
   return { data, status: res.status, headers: res.headers };
 };
+var getListEvalBenchmarksUrl = (evalId, params) => {
+  const normalizedParams = new URLSearchParams();
+  Object.entries(params || {}).forEach(([key, value]) => {
+    if (value !== void 0) {
+      normalizedParams.append(key, value === null ? "null" : String(value));
+    }
+  });
+  const stringifiedParams = normalizedParams.toString();
+  return stringifiedParams.length > 0 ? `/v1/evals/${evalId}/benchmarks?${stringifiedParams}` : `/v1/evals/${evalId}/benchmarks`;
+};
+var listEvalBenchmarks = async (evalId, params, options) => {
+  const res = await fetch(
+    getListEvalBenchmarksUrl(evalId, params),
+    {
+      ...options,
+      method: "GET"
+    }
+  );
+  const body = [204, 205, 304].includes(res.status) ? null : await res.text();
+  const data = body ? JSON.parse(body) : {};
+  return { data, status: res.status, headers: res.headers };
+};
 var getGetBenchmarkUrl = (benchmarkId) => {
   return `/v1/benchmarks/${benchmarkId}`;
 };
@@ -1491,6 +1513,51 @@ var getBenchmark = async (benchmarkId, options) => {
   const data = body ? JSON.parse(body) : {};
   return { data, status: res.status, headers: res.headers };
 };
+var getListWorkerEvalsUrl = (workerId, params) => {
+  const normalizedParams = new URLSearchParams();
+  Object.entries(params || {}).forEach(([key, value]) => {
+    if (value !== void 0) {
+      normalizedParams.append(key, value === null ? "null" : String(value));
+    }
+  });
+  const stringifiedParams = normalizedParams.toString();
+  return stringifiedParams.length > 0 ? `/v1/workers/${workerId}/evals?${stringifiedParams}` : `/v1/workers/${workerId}/evals`;
+};
+var listWorkerEvals = async (workerId, params, options) => {
+  const res = await fetch(
+    getListWorkerEvalsUrl(workerId, params),
+    {
+      ...options,
+      method: "GET"
+    }
+  );
+  const body = [204, 205, 304].includes(res.status) ? null : await res.text();
+  const data = body ? JSON.parse(body) : {};
+  return { data, status: res.status, headers: res.headers };
+};
+var getCreateWorkerBenchmarksUrl = (workerId) => {
+  return `/v1/workers/${workerId}/benchmarks`;
+};
+var createWorkerBenchmarks = async (workerId, createWorkerBenchmarksBody, options) => {
+  const getHeaders = (h) => {
+    if (!h) return {};
+    if (h instanceof Headers) return Object.fromEntries(h.entries());
+    if (Array.isArray(h)) return Object.fromEntries(h);
+    return h;
+  };
+  const res = await fetch(
+    getCreateWorkerBenchmarksUrl(workerId),
+    {
+      ...options,
+      method: "POST",
+      headers: { "Content-Type": "application/json", ...getHeaders(options?.headers) },
+      body: JSON.stringify(createWorkerBenchmarksBody)
+    }
+  );
+  const body = [204, 205, 304].includes(res.status) ? null : await res.text();
+  const data = body ? JSON.parse(body) : {};
+  return { data, status: res.status, headers: res.headers };
+};
 var getCreateExtractorUrl = () => {
   return `/v1/extractors`;
 };
@@ -5074,6 +5141,29 @@ var createEvalBenchmarkHandler = async (args, options) => {
     structuredContent: res.data
   };
 };
+var listEvalBenchmarksHandler = async (args, options) => {
+  const res = await listEvalBenchmarks(args.pathParams.evalId, args.queryParams, options);
+  if (res.status >= 400) {
+    return {
+      content: [
+        {
+          type: "text",
+          text: JSON.stringify(res.data ?? null)
+        }
+      ],
+      isError: true
+    };
+  }
+  return {
+    content: [
+      {
+        type: "text",
+        text: JSON.stringify(res.data ?? null)
+      }
+    ],
+    structuredContent: res.data
+  };
+};
 var getBenchmarkHandler = async (args, options) => {
   const res = await getBenchmark(args.pathParams.benchmarkId, options);
   if (res.status >= 400) {
@@ -5097,6 +5187,52 @@ var getBenchmarkHandler = async (args, options) => {
     structuredContent: res.data
   };
 };
+var listWorkerEvalsHandler = async (args, options) => {
+  const res = await listWorkerEvals(args.pathParams.workerId, args.queryParams, options);
+  if (res.status >= 400) {
+    return {
+      content: [
+        {
+          type: "text",
+          text: JSON.stringify(res.data ?? null)
+        }
+      ],
+      isError: true
+    };
+  }
+  return {
+    content: [
+      {
+        type: "text",
+        text: JSON.stringify(res.data ?? null)
+      }
+    ],
+    structuredContent: res.data
+  };
+};
+var createWorkerBenchmarksHandler = async (args, options) => {
+  const res = await createWorkerBenchmarks(args.pathParams.workerId, args.bodyParams, options);
+  if (res.status >= 400) {
+    return {
+      content: [
+        {
+          type: "text",
+          text: JSON.stringify(res.data ?? null)
+        }
+      ],
+      isError: true
+    };
+  }
+  return {
+    content: [
+      {
+        type: "text",
+        text: JSON.stringify(res.data ?? null)
+      }
+    ],
+    structuredContent: res.data
+  };
+};
 var createExtractorHandler = async (args, options) => {
   const res = await createExtractor(args.bodyParams, options);
   if (res.status >= 400) {
@@ -9289,6 +9425,8 @@ var CreateEvalBenchmarkResponse = zod.object({
       })
     }), zod.null()]),
     "notes": zod.union([zod.array(zod.string()), zod.null()]),
+    "created_at": zod.string().datetime({ "offset": true }),
+    "completed_at": zod.union([zod.string().datetime({ "offset": true }), zod.null()]),
     "runs": zod.array(zod.object({
       "id": zod.string().uuid(),
       "eval_id": zod.string().uuid(),
@@ -9330,12 +9468,109 @@ var CreateEvalBenchmarkResponse = zod.object({
       "created_at": zod.string().datetime({ "offset": true }),
       "started_at": zod.union([zod.string().datetime({ "offset": true }), zod.null()]),
       "completed_at": zod.union([zod.string().datetime({ "offset": true }), zod.null()])
-    })),
-    "created_at": zod.string().datetime({ "offset": true }),
-    "completed_at": zod.union([zod.string().datetime({ "offset": true }), zod.null()])
+    }))
   }),
   "message": zod.string()
 });
+var ListEvalBenchmarksParams = zod.object({
+  "evalId": zod.string().uuid()
+});
+var listEvalBenchmarksQueryCountDefault = 50;
+var listEvalBenchmarksQueryCountMax = 100;
+var listEvalBenchmarksQueryOffsetDefault = 0;
+var listEvalBenchmarksQueryOffsetMin = 0;
+var listEvalBenchmarksQuerySortByDefault = `created_at`;
+var listEvalBenchmarksQuerySortOrderDefault = `desc`;
+var ListEvalBenchmarksQueryParams = zod.object({
+  "count": zod.number().min(1).max(listEvalBenchmarksQueryCountMax).default(listEvalBenchmarksQueryCountDefault),
+  "offset": zod.number().min(listEvalBenchmarksQueryOffsetMin).default(listEvalBenchmarksQueryOffsetDefault),
+  "sort_by": zod.enum(["created_at"]).default(listEvalBenchmarksQuerySortByDefault),
+  "sort_order": zod.enum(["asc", "desc"]).default(listEvalBenchmarksQuerySortOrderDefault)
+});
+var listEvalBenchmarksResponseDataItemCandidateVersionMin = -9007199254740991;
+var listEvalBenchmarksResponseDataItemCandidateVersionMax = 9007199254740991;
+var listEvalBenchmarksResponseDataItemBaselineVersionMin = -9007199254740991;
+var listEvalBenchmarksResponseDataItemBaselineVersionMax = 9007199254740991;
+var listEvalBenchmarksResponseDataItemRunsPerConfigurationMin = -9007199254740991;
+var listEvalBenchmarksResponseDataItemRunsPerConfigurationMax = 9007199254740991;
+var listEvalBenchmarksResponseDataItemRunSummaryOneCandidateRunsMin = -9007199254740991;
+var listEvalBenchmarksResponseDataItemRunSummaryOneCandidateRunsMax = 9007199254740991;
+var listEvalBenchmarksResponseDataItemRunSummaryOneCandidateGradedRunsMin = -9007199254740991;
+var listEvalBenchmarksResponseDataItemRunSummaryOneCandidateGradedRunsMax = 9007199254740991;
+var listEvalBenchmarksResponseDataItemRunSummaryOneBaselineRunsMin = -9007199254740991;
+var listEvalBenchmarksResponseDataItemRunSummaryOneBaselineRunsMax = 9007199254740991;
+var listEvalBenchmarksResponseDataItemRunSummaryOneBaselineGradedRunsMin = -9007199254740991;
+var listEvalBenchmarksResponseDataItemRunSummaryOneBaselineGradedRunsMax = 9007199254740991;
+var listEvalBenchmarksResponseMetaTotalMin = -9007199254740991;
+var listEvalBenchmarksResponseMetaTotalMax = 9007199254740991;
+var ListEvalBenchmarksResponse = zod.object({
+  "data": zod.array(zod.object({
+    "id": zod.string().uuid(),
+    "eval_id": zod.string().uuid(),
+    "candidate_version": zod.number().int().min(listEvalBenchmarksResponseDataItemCandidateVersionMin).max(listEvalBenchmarksResponseDataItemCandidateVersionMax),
+    "baseline_version": zod.number().int().min(listEvalBenchmarksResponseDataItemBaselineVersionMin).max(listEvalBenchmarksResponseDataItemBaselineVersionMax),
+    "runs_per_configuration": zod.number().int().min(listEvalBenchmarksResponseDataItemRunsPerConfigurationMin).max(listEvalBenchmarksResponseDataItemRunsPerConfigurationMax),
+    "status": zod.enum(["running", "completed", "error"]),
+    "run_summary": zod.union([zod.object({
+      "candidate": zod.object({
+        "runs": zod.number().int().min(listEvalBenchmarksResponseDataItemRunSummaryOneCandidateRunsMin).max(listEvalBenchmarksResponseDataItemRunSummaryOneCandidateRunsMax),
+        "graded_runs": zod.number().int().min(listEvalBenchmarksResponseDataItemRunSummaryOneCandidateGradedRunsMin).max(listEvalBenchmarksResponseDataItemRunSummaryOneCandidateGradedRunsMax),
+        "pass_rate": zod.union([zod.object({
+          "mean": zod.number(),
+          "stddev": zod.number(),
+          "min": zod.number(),
+          "max": zod.number()
+        }), zod.null()]),
+        "duration_seconds": zod.union([zod.object({
+          "mean": zod.number(),
+          "stddev": zod.number(),
+          "min": zod.number(),
+          "max": zod.number()
+        }), zod.null()]),
+        "fixture_matched_rate": zod.union([zod.object({
+          "mean": zod.number(),
+          "stddev": zod.number(),
+          "min": zod.number(),
+          "max": zod.number()
+        }), zod.null()])
+      }),
+      "baseline": zod.object({
+        "runs": zod.number().int().min(listEvalBenchmarksResponseDataItemRunSummaryOneBaselineRunsMin).max(listEvalBenchmarksResponseDataItemRunSummaryOneBaselineRunsMax),
+        "graded_runs": zod.number().int().min(listEvalBenchmarksResponseDataItemRunSummaryOneBaselineGradedRunsMin).max(listEvalBenchmarksResponseDataItemRunSummaryOneBaselineGradedRunsMax),
+        "pass_rate": zod.union([zod.object({
+          "mean": zod.number(),
+          "stddev": zod.number(),
+          "min": zod.number(),
+          "max": zod.number()
+        }), zod.null()]),
+        "duration_seconds": zod.union([zod.object({
+          "mean": zod.number(),
+          "stddev": zod.number(),
+          "min": zod.number(),
+          "max": zod.number()
+        }), zod.null()]),
+        "fixture_matched_rate": zod.union([zod.object({
+          "mean": zod.number(),
+          "stddev": zod.number(),
+          "min": zod.number(),
+          "max": zod.number()
+        }), zod.null()])
+      }),
+      "delta": zod.object({
+        "pass_rate": zod.union([zod.number(), zod.null()]),
+        "duration_seconds": zod.union([zod.number(), zod.null()]),
+        "fixture_matched_rate": zod.union([zod.number(), zod.null()])
+      })
+    }), zod.null()]),
+    "notes": zod.union([zod.array(zod.string()), zod.null()]),
+    "created_at": zod.string().datetime({ "offset": true }),
+    "completed_at": zod.union([zod.string().datetime({ "offset": true }), zod.null()])
+  })),
+  "message": zod.string(),
+  "meta": zod.object({
+    "total": zod.number().int().min(listEvalBenchmarksResponseMetaTotalMin).max(listEvalBenchmarksResponseMetaTotalMax).describe("Total number of benchmarks for the eval")
+  })
+});
 var GetBenchmarkParams = zod.object({
   "benchmarkId": zod.string().uuid()
 });
@@ -9435,6 +9670,8 @@ var GetBenchmarkResponse = zod.object({
       })
     }), zod.null()]),
     "notes": zod.union([zod.array(zod.string()), zod.null()]),
+    "created_at": zod.string().datetime({ "offset": true }),
+    "completed_at": zod.union([zod.string().datetime({ "offset": true }), zod.null()]),
     "runs": zod.array(zod.object({
       "id": zod.string().uuid(),
       "eval_id": zod.string().uuid(),
@@ -9476,10 +9713,158 @@ var GetBenchmarkResponse = zod.object({
       "created_at": zod.string().datetime({ "offset": true }),
       "started_at": zod.union([zod.string().datetime({ "offset": true }), zod.null()]),
       "completed_at": zod.union([zod.string().datetime({ "offset": true }), zod.null()])
+    }))
+  }),
+  "message": zod.string()
+});
+var ListWorkerEvalsParams = zod.object({
+  "workerId": zod.string().uuid()
+});
+var listWorkerEvalsQueryCountDefault = 50;
+var listWorkerEvalsQueryCountMax = 100;
+var listWorkerEvalsQueryOffsetDefault = 0;
+var listWorkerEvalsQueryOffsetMin = 0;
+var listWorkerEvalsQuerySortByDefault = `created_at`;
+var listWorkerEvalsQuerySortOrderDefault = `desc`;
+var ListWorkerEvalsQueryParams = zod.object({
+  "count": zod.number().min(1).max(listWorkerEvalsQueryCountMax).default(listWorkerEvalsQueryCountDefault),
+  "offset": zod.number().min(listWorkerEvalsQueryOffsetMin).default(listWorkerEvalsQueryOffsetDefault),
+  "sort_by": zod.enum(["created_at"]).default(listWorkerEvalsQuerySortByDefault),
+  "sort_order": zod.enum(["asc", "desc"]).default(listWorkerEvalsQuerySortOrderDefault)
+});
+var listWorkerEvalsResponseMetaTotalMin = -9007199254740991;
+var listWorkerEvalsResponseMetaTotalMax = 9007199254740991;
+var ListWorkerEvalsResponse = zod.object({
+  "data": zod.array(zod.object({
+    "id": zod.string().uuid(),
+    "name": zod.string(),
+    "target": zod.object({
+      "type": zod.enum(["worker", "chat_agent", "voice_agent"]),
+      "id": zod.string().uuid()
+    }),
+    "source": zod.object({
+      "type": zod.enum(["worker_run", "chat", "call"]),
+      "id": zod.string().uuid()
+    }),
+    "fixture": zod.object({
+      "version": zod.literal(1),
+      "type": zod.literal("worker_run_replay"),
+      "scope": zod.union([zod.record(zod.string(), zod.unknown()), zod.null()]),
+      "resolved_artifact_ids": zod.array(zod.string().uuid()),
+      "trigger_context": zod.union([zod.string(), zod.null()])
+    }),
+    "tool_mocks": zod.array(zod.object({
+      "mcp_type": zod.string(),
+      "tool_name": zod.string(),
+      "description": zod.string(),
+      "input_schema": zod.record(zod.string(), zod.unknown()),
+      "match": zod.record(zod.string(), zod.unknown()).optional(),
+      "logical_tool_name": zod.union([zod.string(), zod.null()]),
+      "responses": zod.array(zod.unknown()),
+      "inputs": zod.array(zod.unknown()).optional(),
+      "default": zod.unknown().optional()
     })),
+    "grader": zod.object({
+      "type": zod.literal("prompt"),
+      "assertions": zod.array(zod.string()),
+      "criterion": zod.string().describe("Deprecated: assertions joined by newlines. Use assertions.")
+    }),
+    "created_at": zod.string().datetime({ "offset": true })
+  })),
+  "message": zod.string(),
+  "meta": zod.object({
+    "total": zod.number().int().min(listWorkerEvalsResponseMetaTotalMin).max(listWorkerEvalsResponseMetaTotalMax).describe("Total number of evals for the worker")
+  })
+});
+var CreateWorkerBenchmarksParams = zod.object({
+  "workerId": zod.string().uuid()
+});
+var createWorkerBenchmarksBodyCandidateVersionMax = 9007199254740991;
+var createWorkerBenchmarksBodyBaselineVersionMax = 9007199254740991;
+var createWorkerBenchmarksBodyRunsPerConfigurationDefault = 3;
+var createWorkerBenchmarksBodyRunsPerConfigurationMax = 5;
+var CreateWorkerBenchmarksBody = zod.object({
+  "candidate_version": zod.number().int().min(1).max(createWorkerBenchmarksBodyCandidateVersionMax),
+  "baseline_version": zod.number().int().min(1).max(createWorkerBenchmarksBodyBaselineVersionMax),
+  "runs_per_configuration": zod.number().int().min(1).max(createWorkerBenchmarksBodyRunsPerConfigurationMax).default(createWorkerBenchmarksBodyRunsPerConfigurationDefault)
+});
+var createWorkerBenchmarksResponseDataItemCandidateVersionMin = -9007199254740991;
+var createWorkerBenchmarksResponseDataItemCandidateVersionMax = 9007199254740991;
+var createWorkerBenchmarksResponseDataItemBaselineVersionMin = -9007199254740991;
+var createWorkerBenchmarksResponseDataItemBaselineVersionMax = 9007199254740991;
+var createWorkerBenchmarksResponseDataItemRunsPerConfigurationMin = -9007199254740991;
+var createWorkerBenchmarksResponseDataItemRunsPerConfigurationMax = 9007199254740991;
+var createWorkerBenchmarksResponseDataItemRunSummaryOneCandidateRunsMin = -9007199254740991;
+var createWorkerBenchmarksResponseDataItemRunSummaryOneCandidateRunsMax = 9007199254740991;
+var createWorkerBenchmarksResponseDataItemRunSummaryOneCandidateGradedRunsMin = -9007199254740991;
+var createWorkerBenchmarksResponseDataItemRunSummaryOneCandidateGradedRunsMax = 9007199254740991;
+var createWorkerBenchmarksResponseDataItemRunSummaryOneBaselineRunsMin = -9007199254740991;
+var createWorkerBenchmarksResponseDataItemRunSummaryOneBaselineRunsMax = 9007199254740991;
+var createWorkerBenchmarksResponseDataItemRunSummaryOneBaselineGradedRunsMin = -9007199254740991;
+var createWorkerBenchmarksResponseDataItemRunSummaryOneBaselineGradedRunsMax = 9007199254740991;
+var CreateWorkerBenchmarksResponse = zod.object({
+  "data": zod.array(zod.object({
+    "id": zod.string().uuid(),
+    "eval_id": zod.string().uuid(),
+    "candidate_version": zod.number().int().min(createWorkerBenchmarksResponseDataItemCandidateVersionMin).max(createWorkerBenchmarksResponseDataItemCandidateVersionMax),
+    "baseline_version": zod.number().int().min(createWorkerBenchmarksResponseDataItemBaselineVersionMin).max(createWorkerBenchmarksResponseDataItemBaselineVersionMax),
+    "runs_per_configuration": zod.number().int().min(createWorkerBenchmarksResponseDataItemRunsPerConfigurationMin).max(createWorkerBenchmarksResponseDataItemRunsPerConfigurationMax),
+    "status": zod.enum(["running", "completed", "error"]),
+    "run_summary": zod.union([zod.object({
+      "candidate": zod.object({
+        "runs": zod.number().int().min(createWorkerBenchmarksResponseDataItemRunSummaryOneCandidateRunsMin).max(createWorkerBenchmarksResponseDataItemRunSummaryOneCandidateRunsMax),
+        "graded_runs": zod.number().int().min(createWorkerBenchmarksResponseDataItemRunSummaryOneCandidateGradedRunsMin).max(createWorkerBenchmarksResponseDataItemRunSummaryOneCandidateGradedRunsMax),
+        "pass_rate": zod.union([zod.object({
+          "mean": zod.number(),
+          "stddev": zod.number(),
+          "min": zod.number(),
+          "max": zod.number()
+        }), zod.null()]),
+        "duration_seconds": zod.union([zod.object({
+          "mean": zod.number(),
+          "stddev": zod.number(),
+          "min": zod.number(),
+          "max": zod.number()
+        }), zod.null()]),
+        "fixture_matched_rate": zod.union([zod.object({
+          "mean": zod.number(),
+          "stddev": zod.number(),
+          "min": zod.number(),
+          "max": zod.number()
+        }), zod.null()])
+      }),
+      "baseline": zod.object({
+        "runs": zod.number().int().min(createWorkerBenchmarksResponseDataItemRunSummaryOneBaselineRunsMin).max(createWorkerBenchmarksResponseDataItemRunSummaryOneBaselineRunsMax),
+        "graded_runs": zod.number().int().min(createWorkerBenchmarksResponseDataItemRunSummaryOneBaselineGradedRunsMin).max(createWorkerBenchmarksResponseDataItemRunSummaryOneBaselineGradedRunsMax),
+        "pass_rate": zod.union([zod.object({
+          "mean": zod.number(),
+          "stddev": zod.number(),
+          "min": zod.number(),
+          "max": zod.number()
+        }), zod.null()]),
+        "duration_seconds": zod.union([zod.object({
+          "mean": zod.number(),
+          "stddev": zod.number(),
+          "min": zod.number(),
+          "max": zod.number()
+        }), zod.null()]),
+        "fixture_matched_rate": zod.union([zod.object({
+          "mean": zod.number(),
+          "stddev": zod.number(),
+          "min": zod.number(),
+          "max": zod.number()
+        }), zod.null()])
+      }),
+      "delta": zod.object({
+        "pass_rate": zod.union([zod.number(), zod.null()]),
+        "duration_seconds": zod.union([zod.number(), zod.null()]),
+        "fixture_matched_rate": zod.union([zod.number(), zod.null()])
+      })
+    }), zod.null()]),
+    "notes": zod.union([zod.array(zod.string()), zod.null()]),
     "created_at": zod.string().datetime({ "offset": true }),
     "completed_at": zod.union([zod.string().datetime({ "offset": true }), zod.null()])
-  }),
+  })),
   "message": zod.string()
 });
 var CreateExtractorBody = zod.object({
@@ -12957,6 +13342,23 @@ var createMcpServer = (options) => {
       signal: options?.signal ? AbortSignal.any([options.signal, ctx.signal]) : ctx.signal
     })
   );
+  tools.listEvalBenchmarks = server2.registerTool(
+    "listEvalBenchmarks",
+    {
+      title: "List an eval's benchmarks",
+      description: "Benchmark history of an eval (newest first by default) without per-run details. Use GET /v1/benchmarks/{benchmarkId} for the runs.",
+      inputSchema: {
+        pathParams: ListEvalBenchmarksParams,
+        queryParams: ListEvalBenchmarksQueryParams
+      },
+      outputSchema: ListEvalBenchmarksResponse,
+      annotations: { readOnlyHint: true }
+    },
+    (args, ctx) => listEvalBenchmarksHandler(args, {
+      ...options,
+      signal: options?.signal ? AbortSignal.any([options.signal, ctx.signal]) : ctx.signal
+    })
+  );
   tools.getBenchmark = server2.registerTool(
     "getBenchmark",
     {
@@ -12973,6 +13375,40 @@ var createMcpServer = (options) => {
       signal: options?.signal ? AbortSignal.any([options.signal, ctx.signal]) : ctx.signal
     })
   );
+  tools.listWorkerEvals = server2.registerTool(
+    "listWorkerEvals",
+    {
+      title: "List a worker's evals",
+      description: "List the evals recorded for a worker, newest first by default.",
+      inputSchema: {
+        pathParams: ListWorkerEvalsParams,
+        queryParams: ListWorkerEvalsQueryParams
+      },
+      outputSchema: ListWorkerEvalsResponse,
+      annotations: { readOnlyHint: true }
+    },
+    (args, ctx) => listWorkerEvalsHandler(args, {
+      ...options,
+      signal: options?.signal ? AbortSignal.any([options.signal, ctx.signal]) : ctx.signal
+    })
+  );
+  tools.createWorkerBenchmarks = server2.registerTool(
+    "createWorkerBenchmarks",
+    {
+      title: "Benchmark two worker versions on all of the worker's evals",
+      description: "Create one benchmark per eval of the worker, each queueing runs_per_configuration trials against the candidate and the baseline version. Poll each benchmark with GET /v1/benchmarks/{benchmarkId}.",
+      inputSchema: {
+        pathParams: CreateWorkerBenchmarksParams,
+        bodyParams: CreateWorkerBenchmarksBody.optional()
+      },
+      outputSchema: CreateWorkerBenchmarksResponse,
+      annotations: { destructiveHint: true }
+    },
+    (args, ctx) => createWorkerBenchmarksHandler(args, {
+      ...options,
+      signal: options?.signal ? AbortSignal.any([options.signal, ctx.signal]) : ctx.signal
+    })
+  );
   tools.createExtractor = server2.registerTool(
     "createExtractor",
     {
@@ -14586,4 +15022,4 @@ var transport = new StdioServerTransport();
 server.connect(transport).then(() => {
   console.error("MCP server running on stdio");
 }).catch(console.error);
-//# sourceMappingURL=server-DACHXX2C.js.map
+//# sourceMappingURL=server-EZUDCD4M.js.map