@dalmia/calibrate-mcp 0.0.48 → 0.0.49

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/bin/mcp-server.js CHANGED
@@ -53020,9 +53020,9 @@ var init_config = __esm(() => {
53020
53020
  SDK_METADATA = {
53021
53021
  language: "typescript",
53022
53022
  openapiDocVersion: "0.1.0",
53023
- sdkVersion: "0.0.48",
53023
+ sdkVersion: "0.0.49",
53024
53024
  genVersion: "2.915.1",
53025
- userAgent: "speakeasy-sdk/mcp-typescript 0.0.48 2.915.1 0.1.0 @dalmia/calibrate-mcp"
53025
+ userAgent: "speakeasy-sdk/mcp-typescript 0.0.49 2.915.1 0.1.0 @dalmia/calibrate-mcp"
53026
53026
  };
53027
53027
  });
53028
53028
 
@@ -56214,6 +56214,7 @@ var init_testcaseresult = __esm(() => {
56214
56214
  judge_results: array(JudgeResult$zodSchema).nullable().optional().describe("One verdict for each evaluator"),
56215
56215
  latency_ms: number2().nullable().optional().describe("How long the agent took to respond, in milliseconds"),
56216
56216
  name: string2().nullable().optional().describe("Name of the test"),
56217
+ not_run: boolean2().default(false).describe("Whether this case never started, because a user stopped the run first. It is counted neither as passed nor as failed"),
56217
56218
  output: TestOutput$zodSchema.nullable().optional().describe("The agent's output for this case"),
56218
56219
  passed: boolean2().nullable().optional().describe("Whether the case passed"),
56219
56220
  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(() => {
56284
56285
  init_taskstatus();
56285
56286
  init_testrunevaluator();
56286
56287
  BenchmarkStatusResponse$zodSchema = object({
56288
+ aborted: boolean2().default(false).describe("Whether a user stopped this run before it finished. The results collected up to that point are kept, and test cases that never ran are counted neither as passed nor as failed"),
56287
56289
  error: boolean2().default(false).describe("True if the run failed"),
56288
56290
  evaluators: array(TestRunEvaluator$zodSchema).nullable().optional().describe("The evaluators used in this run. Each verdict in `judge_results` links to one of these by `evaluator_uuid`"),
56289
56291
  is_public: boolean2().default(false).describe("Whether the run is shared publicly"),
@@ -56444,6 +56446,7 @@ var init_testrunstatusresponse = __esm(() => {
56444
56446
  init_testcaseresult();
56445
56447
  init_testrunevaluator();
56446
56448
  TestRunStatusResponse$zodSchema = object({
56449
+ aborted: boolean2().default(false).describe("Whether a user stopped this run before it finished. The results collected up to that point are kept, and test cases that never ran are counted neither as passed nor as failed"),
56447
56450
  cost: record(string2(), any()).nullable().optional().describe("Aggregated cost as `{mean, min, max, count}` (USD)"),
56448
56451
  error: boolean2().default(false).describe("True if the run failed"),
56449
56452
  evaluators: array(TestRunEvaluator$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(() => {
57002
57005
  "llm-benchmark"
57003
57006
  ]).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");
57004
57007
  AgentTestRunListItem$zodSchema = object({
57008
+ 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"),
57005
57009
  cost: record(string2(), any()).nullable().optional().describe("Aggregated cost as `{mean, min, max, count}` (USD)"),
57006
57010
  created_at: string2().describe("When the run was created (ISO 8601 UTC)"),
57007
57011
  error: boolean2().default(false).describe("True if the run failed"),
@@ -61642,7 +61646,7 @@ hits its trace limit.
61642
61646
  function createMCPServer(deps) {
61643
61647
  const server = new McpServer({
61644
61648
  name: "CalibrateMcp",
61645
- version: "0.0.48"
61649
+ version: "0.0.49"
61646
61650
  });
61647
61651
  const getClient = deps.getSDK || (() => new CalibrateMcpCore({
61648
61652
  security: deps.security,
@@ -62920,7 +62924,7 @@ http_headers = { "api-key-auth" = "YOUR_API_KEY_AUTH" }`;
62920
62924
  <h1>Instructions</h1>
62921
62925
  <p>One-click installation for Claude Desktop users</p>
62922
62926
  <div class="instruction-item">
62923
- <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;">
62927
+ <a href="https://github.com/dalmia/calibrate-mcp/releases/download/v0.0.49/mcp-server.mcpb" download="mcp-server.mcpb" class="action-button header-action" style="display: inline-flex; margin-bottom: 16px;">
62924
62928
  \uD83D\uDCE5 Download MCP Bundle
62925
62929
  </a>
62926
62930
  </div>
@@ -65807,7 +65811,7 @@ var routes = buildRouteMap({
65807
65811
  var app = buildApplication(routes, {
65808
65812
  name: "mcp",
65809
65813
  versionInfo: {
65810
- currentVersion: "0.0.48"
65814
+ currentVersion: "0.0.49"
65811
65815
  }
65812
65816
  });
65813
65817
  run(app, process4.argv.slice(2), buildContext(process4));
@@ -65815,5 +65819,5 @@ export {
65815
65819
  app
65816
65820
  };
65817
65821
 
65818
- //# debugId=070CB4FCEC8F307264756E2164756E21
65822
+ //# debugId=F5A9C365B934497264756E2164756E21
65819
65823
  //# sourceMappingURL=mcp-server.js.map