@amigo-ai/platform-sdk 0.83.0 → 0.85.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -713,6 +713,46 @@ export interface paths {
713
713
  patch?: never;
714
714
  trace?: never;
715
715
  };
716
+ "/v1/{workspace_id}/agent-runs": {
717
+ parameters: {
718
+ query?: never;
719
+ header?: never;
720
+ path?: never;
721
+ cookie?: never;
722
+ };
723
+ get?: never;
724
+ put?: never;
725
+ /**
726
+ * Dispatch a framework agent run
727
+ * @description Proxies to agent-runner, which executes the chosen framework UNMODIFIED (natural setup) against the platform MCP world-tools edge under the caller's own bearer. Non-blocking — poll GET /agent-runs/{run_id} for the result.
728
+ */
729
+ post: operations["create_agent_run_v1__workspace_id__agent_runs_post"];
730
+ delete?: never;
731
+ options?: never;
732
+ head?: never;
733
+ patch?: never;
734
+ trace?: never;
735
+ };
736
+ "/v1/{workspace_id}/agent-runs/{run_id}": {
737
+ parameters: {
738
+ query?: never;
739
+ header?: never;
740
+ path?: never;
741
+ cookie?: never;
742
+ };
743
+ /**
744
+ * Get a framework agent run
745
+ * @description Run status, final text, token usage, and the adapter-normalized trajectory of the framework's native output.
746
+ */
747
+ get: operations["get_agent_run_v1__workspace_id__agent_runs__run_id__get"];
748
+ put?: never;
749
+ post?: never;
750
+ delete?: never;
751
+ options?: never;
752
+ head?: never;
753
+ patch?: never;
754
+ trace?: never;
755
+ };
716
756
  "/v1/{workspace_id}/agents": {
717
757
  parameters: {
718
758
  query?: never;
@@ -6139,6 +6179,31 @@ export interface paths {
6139
6179
  patch?: never;
6140
6180
  trace?: never;
6141
6181
  };
6182
+ "/v1/{workspace_id}/simulations/performance": {
6183
+ parameters: {
6184
+ query?: never;
6185
+ header?: never;
6186
+ path?: never;
6187
+ cookie?: never;
6188
+ };
6189
+ /**
6190
+ * Get Simulation Performance
6191
+ * @description Aggregate recent graded (case/suite) runs into the Simulations overview:
6192
+ * overall pass rate, per-metric trend series, and per-case / per-suite rollups
6193
+ * (each with its per-conversation verdicts).
6194
+ *
6195
+ * ``limit`` bounds how many recent runs are read (capped at 50). One request
6196
+ * replaces the console's former one-fetch-per-run fan-out.
6197
+ */
6198
+ get: operations["get-simulation-performance"];
6199
+ put?: never;
6200
+ post?: never;
6201
+ delete?: never;
6202
+ options?: never;
6203
+ head?: never;
6204
+ patch?: never;
6205
+ trace?: never;
6206
+ };
6142
6207
  "/v1/{workspace_id}/simulations/runs": {
6143
6208
  parameters: {
6144
6209
  query?: never;
@@ -8119,6 +8184,50 @@ export interface components {
8119
8184
  */
8120
8185
  workspace_id: string;
8121
8186
  };
8187
+ /** AgentRunDetail */
8188
+ AgentRunDetail: {
8189
+ /**
8190
+ * Duration Ms
8191
+ * @default 0
8192
+ */
8193
+ duration_ms?: number;
8194
+ /**
8195
+ * Error
8196
+ * @description Failure detail for failed/timed_out runs. Empty otherwise.
8197
+ * @default
8198
+ */
8199
+ error?: string;
8200
+ /**
8201
+ * Framework
8202
+ * @enum {string}
8203
+ */
8204
+ framework: "claude-agent-sdk" | "openai-agents";
8205
+ /**
8206
+ * Run Id
8207
+ * Format: uuid
8208
+ */
8209
+ run_id: string;
8210
+ /**
8211
+ * Status
8212
+ * @enum {string}
8213
+ */
8214
+ status: "running" | "succeeded" | "failed" | "timed_out";
8215
+ /**
8216
+ * Text
8217
+ * @description Final agent text. Empty while the run is still running or on failure.
8218
+ * @default
8219
+ */
8220
+ text?: string;
8221
+ /**
8222
+ * Trajectory
8223
+ * @description AgentEffect-shaped step dicts (kind, seq, content, tool_name, ...) — the adapter's normalize() over the framework's NATIVE output. Untyped passthrough in v1: the AgentEffect projection is a server-private shape still converging across frameworks; typing it here now would freeze a premature wire contract. A typed discriminated union lands in a follow-up.
8224
+ * @default []
8225
+ */
8226
+ trajectory?: {
8227
+ [key: string]: unknown;
8228
+ }[];
8229
+ usage?: components["schemas"]["Usage"];
8230
+ };
8122
8231
  /** AgentTranscriptDeltaEvent */
8123
8232
  AgentTranscriptDeltaEvent: {
8124
8233
  /** Delta */
@@ -11064,6 +11173,49 @@ export interface components {
11064
11173
  description?: components["schemas"]["DescriptionString"];
11065
11174
  name: components["schemas"]["NameString"];
11066
11175
  };
11176
+ /** CreateAgentRunRequest */
11177
+ CreateAgentRunRequest: {
11178
+ /**
11179
+ * Framework
11180
+ * @description Agent framework the run executes on — runs unmodified in the framework's own design.
11181
+ * @enum {string}
11182
+ */
11183
+ framework: "claude-agent-sdk" | "openai-agents";
11184
+ /**
11185
+ * Message
11186
+ * @description User message the framework agent is invoked with.
11187
+ */
11188
+ message: string;
11189
+ /**
11190
+ * Service Id
11191
+ * Format: uuid
11192
+ */
11193
+ service_id: string;
11194
+ /**
11195
+ * Timeout S
11196
+ * @description Server-side wall-clock budget for the run, in seconds (max 300).
11197
+ * @default 120
11198
+ */
11199
+ timeout_s?: number;
11200
+ /**
11201
+ * @description Named version set on the service whose pinned config the run uses.
11202
+ * @default release
11203
+ */
11204
+ version_set?: components["schemas"]["NameString"];
11205
+ };
11206
+ /** CreateAgentRunResponse */
11207
+ CreateAgentRunResponse: {
11208
+ /**
11209
+ * Run Id
11210
+ * Format: uuid
11211
+ */
11212
+ run_id: string;
11213
+ /**
11214
+ * Status
11215
+ * @constant
11216
+ */
11217
+ status: "running";
11218
+ };
11067
11219
  /** CreateAgentVersionRequest */
11068
11220
  CreateAgentVersionRequest: {
11069
11221
  /** @default */
@@ -21497,6 +21649,136 @@ export interface components {
21497
21649
  */
21498
21650
  signal: string;
21499
21651
  };
21652
+ /** SimCaseAssertionResponse */
21653
+ SimCaseAssertionResponse: {
21654
+ /** Eval Key */
21655
+ eval_key: string;
21656
+ /**
21657
+ * Eval Type
21658
+ * @enum {string}
21659
+ */
21660
+ eval_type: "assertion" | "metric";
21661
+ /**
21662
+ * Failed
21663
+ * @default 0
21664
+ */
21665
+ failed?: number;
21666
+ /** Pass Rate */
21667
+ pass_rate?: number | null;
21668
+ /**
21669
+ * Passed
21670
+ * @default 0
21671
+ */
21672
+ passed?: number;
21673
+ /**
21674
+ * Pending
21675
+ * @default 0
21676
+ */
21677
+ pending?: number;
21678
+ /** Results */
21679
+ results?: components["schemas"]["SimulationEvalResultResponse"][];
21680
+ };
21681
+ /** SimCasePerfResponse */
21682
+ SimCasePerfResponse: {
21683
+ /** Assertions */
21684
+ assertions?: components["schemas"]["SimCaseAssertionResponse"][];
21685
+ /** Case Id */
21686
+ case_id?: string | null;
21687
+ /** Case Name */
21688
+ case_name: string;
21689
+ /** Latest Run At */
21690
+ latest_run_at?: string | null;
21691
+ /**
21692
+ * Latest Run Id
21693
+ * Format: uuid
21694
+ */
21695
+ latest_run_id: string;
21696
+ /**
21697
+ * Measured
21698
+ * @default 0
21699
+ */
21700
+ measured?: number;
21701
+ /** Pass Rate */
21702
+ pass_rate?: number | null;
21703
+ /**
21704
+ * Passed
21705
+ * @default 0
21706
+ */
21707
+ passed?: number;
21708
+ };
21709
+ /** SimMetricPerfResponse */
21710
+ SimMetricPerfResponse: {
21711
+ /** Label */
21712
+ label: string;
21713
+ /** Metric Key */
21714
+ metric_key: string;
21715
+ /** Per Run */
21716
+ per_run?: components["schemas"]["SimMetricRunPointResponse"][];
21717
+ };
21718
+ /**
21719
+ * SimMetricRunPointResponse
21720
+ * @description One run's contribution to a metric: the mean value that run (null for
21721
+ * non-numeric metrics) plus how many conversations passed / were measured.
21722
+ */
21723
+ SimMetricRunPointResponse: {
21724
+ /** At */
21725
+ at?: string | null;
21726
+ /**
21727
+ * Measured
21728
+ * @default 0
21729
+ */
21730
+ measured?: number;
21731
+ /**
21732
+ * Passed
21733
+ * @default 0
21734
+ */
21735
+ passed?: number;
21736
+ /** Value */
21737
+ value?: number | null;
21738
+ };
21739
+ /** SimPerformanceOverviewResponse */
21740
+ SimPerformanceOverviewResponse: {
21741
+ /**
21742
+ * Evals Run
21743
+ * @default 0
21744
+ */
21745
+ evals_run?: number;
21746
+ /**
21747
+ * Needs Attention Count
21748
+ * @default 0
21749
+ */
21750
+ needs_attention_count?: number;
21751
+ /** Overall Pass Rate */
21752
+ overall_pass_rate?: number | null;
21753
+ /**
21754
+ * Runs Analyzed
21755
+ * @default 0
21756
+ */
21757
+ runs_analyzed?: number;
21758
+ };
21759
+ /** SimSuitePerfResponse */
21760
+ SimSuitePerfResponse: {
21761
+ /** Cases */
21762
+ cases?: components["schemas"]["SimCasePerfResponse"][];
21763
+ /** Latest Run At */
21764
+ latest_run_at?: string | null;
21765
+ /**
21766
+ * Measured
21767
+ * @default 0
21768
+ */
21769
+ measured?: number;
21770
+ /** Pass Rate */
21771
+ pass_rate?: number | null;
21772
+ /**
21773
+ * Passed
21774
+ * @default 0
21775
+ */
21776
+ passed?: number;
21777
+ /** Suite Id */
21778
+ suite_id?: string | null;
21779
+ /** Suite Name */
21780
+ suite_name: string;
21781
+ };
21500
21782
  /** SimulationBenchmarkAggregateSummary */
21501
21783
  SimulationBenchmarkAggregateSummary: {
21502
21784
  /** Average Score */
@@ -21962,6 +22244,20 @@ export interface components {
21962
22244
  */
21963
22245
  tools_called?: string[];
21964
22246
  };
22247
+ /**
22248
+ * SimulationPerformanceResponse
22249
+ * @description Aggregated Simulations overview: one request in place of the console's
22250
+ * former one-detail-fetch-per-run fan-out.
22251
+ */
22252
+ SimulationPerformanceResponse: {
22253
+ /** By Case */
22254
+ by_case?: components["schemas"]["SimCasePerfResponse"][];
22255
+ /** By Suite */
22256
+ by_suite?: components["schemas"]["SimSuitePerfResponse"][];
22257
+ /** Metrics */
22258
+ metrics?: components["schemas"]["SimMetricPerfResponse"][];
22259
+ overview: components["schemas"]["SimPerformanceOverviewResponse"];
22260
+ };
21965
22261
  /**
21966
22262
  * SimulationRunResponse
21967
22263
  * @description Full run payload — used by GET /runs/{run_id} for replay flows.
@@ -25907,6 +26203,31 @@ export interface components {
25907
26203
  UpsertVersionSetRequest: {
25908
26204
  version_set: components["schemas"]["VersionSet-Input"];
25909
26205
  };
26206
+ /** Usage */
26207
+ Usage: {
26208
+ /**
26209
+ * Cache Creation Tokens
26210
+ * @description Cache-WRITE input tokens (Anthropic cache_creation_input_tokens; 0 on providers without it).
26211
+ * @default 0
26212
+ */
26213
+ cache_creation_tokens?: number;
26214
+ /**
26215
+ * Cached Tokens
26216
+ * @description Cache-READ input tokens (billed at the provider's cache-hit rate).
26217
+ * @default 0
26218
+ */
26219
+ cached_tokens?: number;
26220
+ /**
26221
+ * Input Tokens
26222
+ * @default 0
26223
+ */
26224
+ input_tokens?: number;
26225
+ /**
26226
+ * Output Tokens
26227
+ * @default 0
26228
+ */
26229
+ output_tokens?: number;
26230
+ };
25910
26231
  /** UsageBucket */
25911
26232
  UsageBucket: {
25912
26233
  /**
@@ -29437,6 +29758,73 @@ export interface operations {
29437
29758
  };
29438
29759
  };
29439
29760
  };
29761
+ create_agent_run_v1__workspace_id__agent_runs_post: {
29762
+ parameters: {
29763
+ query?: never;
29764
+ header?: never;
29765
+ path: {
29766
+ workspace_id: string;
29767
+ };
29768
+ cookie?: never;
29769
+ };
29770
+ requestBody: {
29771
+ content: {
29772
+ "application/json": components["schemas"]["CreateAgentRunRequest"];
29773
+ };
29774
+ };
29775
+ responses: {
29776
+ /** @description Successful Response */
29777
+ 202: {
29778
+ headers: {
29779
+ [name: string]: unknown;
29780
+ };
29781
+ content: {
29782
+ "application/json": components["schemas"]["CreateAgentRunResponse"];
29783
+ };
29784
+ };
29785
+ /** @description Validation Error */
29786
+ 422: {
29787
+ headers: {
29788
+ [name: string]: unknown;
29789
+ };
29790
+ content: {
29791
+ "application/json": components["schemas"]["HTTPValidationError"];
29792
+ };
29793
+ };
29794
+ };
29795
+ };
29796
+ get_agent_run_v1__workspace_id__agent_runs__run_id__get: {
29797
+ parameters: {
29798
+ query?: never;
29799
+ header?: never;
29800
+ path: {
29801
+ workspace_id: string;
29802
+ run_id: string;
29803
+ };
29804
+ cookie?: never;
29805
+ };
29806
+ requestBody?: never;
29807
+ responses: {
29808
+ /** @description Successful Response */
29809
+ 200: {
29810
+ headers: {
29811
+ [name: string]: unknown;
29812
+ };
29813
+ content: {
29814
+ "application/json": components["schemas"]["AgentRunDetail"];
29815
+ };
29816
+ };
29817
+ /** @description Validation Error */
29818
+ 422: {
29819
+ headers: {
29820
+ [name: string]: unknown;
29821
+ };
29822
+ content: {
29823
+ "application/json": components["schemas"]["HTTPValidationError"];
29824
+ };
29825
+ };
29826
+ };
29827
+ };
29440
29828
  "list-agents": {
29441
29829
  parameters: {
29442
29830
  query?: {
@@ -35782,6 +36170,7 @@ export interface operations {
35782
36170
  sort_by?: string;
35783
36171
  status?: components["schemas"]["_FileStatus"] | null;
35784
36172
  search?: string | null;
36173
+ include_withdrawn?: boolean;
35785
36174
  };
35786
36175
  header?: never;
35787
36176
  path: {
@@ -42520,6 +42909,40 @@ export interface operations {
42520
42909
  };
42521
42910
  };
42522
42911
  };
42912
+ "get-simulation-performance": {
42913
+ parameters: {
42914
+ query?: {
42915
+ service_id?: string | null;
42916
+ limit?: number;
42917
+ };
42918
+ header?: never;
42919
+ path: {
42920
+ workspace_id: string;
42921
+ };
42922
+ cookie?: never;
42923
+ };
42924
+ requestBody?: never;
42925
+ responses: {
42926
+ /** @description Successful Response */
42927
+ 200: {
42928
+ headers: {
42929
+ [name: string]: unknown;
42930
+ };
42931
+ content: {
42932
+ "application/json": components["schemas"]["SimulationPerformanceResponse"];
42933
+ };
42934
+ };
42935
+ /** @description Validation Error */
42936
+ 422: {
42937
+ headers: {
42938
+ [name: string]: unknown;
42939
+ };
42940
+ content: {
42941
+ "application/json": components["schemas"]["HTTPValidationError"];
42942
+ };
42943
+ };
42944
+ };
42945
+ };
42523
42946
  "list-simulation-runs": {
42524
42947
  parameters: {
42525
42948
  query?: {