@dalmia/calibrate-mcp 0.0.48 → 0.0.50

package/bin/mcp-server.js

@@ -53020,9 +53020,9 @@ var init_config = __esm(() => {
   SDK_METADATA = {
     language: "typescript",
     openapiDocVersion: "0.1.0",
-    sdkVersion: "0.0.48",
+    sdkVersion: "0.0.50",
     genVersion: "2.915.1",
-    userAgent: "speakeasy-sdk/mcp-typescript 0.0.48 2.915.1 0.1.0 @dalmia/calibrate-mcp"
+    userAgent: "speakeasy-sdk/mcp-typescript 0.0.50 2.915.1 0.1.0 @dalmia/calibrate-mcp"
   };
 });
 
@@ -56214,6 +56214,7 @@ var init_testcaseresult = __esm(() => {
     judge_results: array(JudgeResult$zodSchema).nullable().optional().describe("One verdict for each evaluator"),
     latency_ms: number2().nullable().optional().describe("How long the agent took to respond, in milliseconds"),
     name: string2().nullable().optional().describe("Name of the test"),
+    not_run: boolean2().default(false).describe("Whether this case never started, because a user stopped the run first. It is counted neither as passed nor as failed"),
     output: TestOutput$zodSchema.nullable().optional().describe("The agent's output for this case"),
     passed: boolean2().nullable().optional().describe("Whether the case passed"),
     reasoning: string2().nullable().optional().describe("The judge's reasoning, or the tool-call diff for a tool-call test"),
@@ -56284,6 +56285,7 @@ var init_benchmarkstatusresponse = __esm(() => {
   init_taskstatus();
   init_testrunevaluator();
   BenchmarkStatusResponse$zodSchema = object({
+    aborted: boolean2().default(false).describe("Whether a user stopped this run before it finished. The results collected up to that point are kept, and test cases that never ran are counted neither as passed nor as failed"),
     error: boolean2().default(false).describe("True if the run failed"),
     evaluators: array(TestRunEvaluator$zodSchema).nullable().optional().describe("The evaluators used in this run. Each verdict in `judge_results` links to one of these by `evaluator_uuid`"),
     is_public: boolean2().default(false).describe("Whether the run is shared publicly"),
@@ -56444,6 +56446,7 @@ var init_testrunstatusresponse = __esm(() => {
   init_testcaseresult();
   init_testrunevaluator();
   TestRunStatusResponse$zodSchema = object({
+    aborted: boolean2().default(false).describe("Whether a user stopped this run before it finished. The results collected up to that point are kept, and test cases that never ran are counted neither as passed nor as failed"),
     cost: record(string2(), any()).nullable().optional().describe("Aggregated cost as `{mean, min, max, count}` (USD)"),
     error: boolean2().default(false).describe("True if the run failed"),
     evaluators: array(TestRunEvaluator$zodSchema).nullable().optional().describe("The evaluators used in this run. Each verdict in `judge_results` links to one of these by `evaluator_uuid`"),
@@ -57002,6 +57005,7 @@ var init_agenttestrunlistitem = __esm(() => {
     "llm-benchmark"
   ]).describe("What kind of run this is:\n- `llm-unit-test`: a single run of the agent's tests\n- `llm-benchmark`: a multi-model comparison");
   AgentTestRunListItem$zodSchema = object({
+    aborted: boolean2().default(false).describe("Whether a user stopped this run before it finished. The results collected up to that point are kept, and test cases that never ran are counted neither as passed nor as failed"),
     cost: record(string2(), any()).nullable().optional().describe("Aggregated cost as `{mean, min, max, count}` (USD)"),
     created_at: string2().describe("When the run was created (ISO 8601 UTC)"),
     error: boolean2().default(false).describe("True if the run failed"),
@@ -57370,12 +57374,13 @@ var init_batchtestskip = __esm(() => {
   init_zod();
   Reason$zodSchema = _enum([
     "no_linked_tests",
-    "connection_not_verified"
-  ]).describe("Why this agent was not run:\n- `no_linked_tests`: the agent has no tests linked\n- `connection_not_verified`: the agent's connection is not verified");
+    "connection_not_verified",
+    "over_row_limit"
+  ]).describe("Why this agent was not run:\n- `no_linked_tests`: the agent has no tests linked\n- `connection_not_verified`: the agent's connection is not verified\n- `over_row_limit`: the agent has more linked tests than this workspace allows in one run");
   BatchTestSkip$zodSchema = object({
     agent_name: string2().describe("Name of the skipped agent"),
     agent_uuid: string2().describe("ID of the skipped agent"),
-    reason: Reason$zodSchema.describe("Why this agent was not run:\n- `no_linked_tests`: the agent has no tests linked\n- `connection_not_verified`: the agent's connection is not verified")
+    reason: Reason$zodSchema.describe("Why this agent was not run:\n- `no_linked_tests`: the agent has no tests linked\n- `connection_not_verified`: the agent's connection is not verified\n- `over_row_limit`: the agent has more linked tests than this workspace allows in one run")
   });
 });
 
@@ -61642,7 +61647,7 @@ hits its trace limit.
 function createMCPServer(deps) {
   const server = new McpServer({
     name: "CalibrateMcp",
-    version: "0.0.48"
+    version: "0.0.50"
   });
   const getClient = deps.getSDK || (() => new CalibrateMcpCore({
     security: deps.security,
@@ -62920,7 +62925,7 @@ http_headers = { "api-key-auth" = "YOUR_API_KEY_AUTH" }`;
         <h1>Instructions</h1>
         <p>One-click installation for Claude Desktop users</p>
         <div class="instruction-item">
-          <a href="https://github.com/dalmia/calibrate-mcp/releases/download/v0.0.48/mcp-server.mcpb" download="mcp-server.mcpb" class="action-button header-action" style="display: inline-flex; margin-bottom: 16px;">
+          <a href="https://github.com/dalmia/calibrate-mcp/releases/download/v0.0.50/mcp-server.mcpb" download="mcp-server.mcpb" class="action-button header-action" style="display: inline-flex; margin-bottom: 16px;">
             \uD83D\uDCE5 Download MCP Bundle
           </a>
         </div>
@@ -65807,7 +65812,7 @@ var routes = buildRouteMap({
 var app = buildApplication(routes, {
   name: "mcp",
   versionInfo: {
-    currentVersion: "0.0.48"
+    currentVersion: "0.0.50"
   }
 });
 run(app, process4.argv.slice(2), buildContext(process4));
@@ -65815,5 +65820,5 @@ export {
   app
 };
 
-//# debugId=070CB4FCEC8F307264756E2164756E21
+//# debugId=C9B13E4BDAC1050764756E2164756E21
 //# sourceMappingURL=mcp-server.js.map