@soat/sdk 0.60.0 → 0.61.0

package/dist/index.cjs

@@ -2669,7 +2669,7 @@ var Guardrails = class {
 	/**
 	* Dry-run evaluate a guardrail
 	*
-	* Runs the full evaluation pipeline — the `class` expression, the guard, the context tool per `context_mode`, live `runtime.*` resolution — against caller-supplied `args` and `guardrail_context`, and returns the exact `guardrail_evaluation` record a real call would produce. Nothing executes, no approval item is filed, and no activity entry is written. This is the adoption path: preview a document's decisions against production-shaped calls before attaching it — or before editing a widely-attached one. Pass an optional `tool_id` to resolve `runtime.tool.*`.
+	* Runs the full evaluation pipeline — the `class` expression, the guard, the context tool per `context_mode`, live `runtime.*` resolution — against caller-supplied `args` and `guardrail_context`, and returns the exact `guardrail_evaluation` record a real call would produce. Nothing executes, no approval item is filed, and no activity entry is written. This is the adoption path: preview a document's decisions against production-shaped calls before attaching it — or before editing a widely-attached one. Pass an optional `tool_id` to resolve `runtime.tools.*`.
 	*
 	*/
 	static evaluateGuardrail(options) {
@@ -4354,7 +4354,7 @@ var Usage = class {
 	/**
 	* List usage events
 	*
-	* Returns the raw usage events the caller can access, most recent first, narrowed by any combination of the same filters the aggregate takes — agent, generation, trace, actor, session, AI provider, orchestration run, orchestration, trigger, action, meter type, model or `source` — so a rollup and the events behind it are addressed the same way. Each event is the per-generation token usage as reported by the provider, for audit and reconciliation.
+	* Returns the raw usage events the caller can access, most recent first, narrowed by any combination of the same filters the aggregate takes — agent, generation, trace, actor, session, AI provider, orchestration run, orchestration, tool, trigger, action, outcome, meter type, model or `source` — so a rollup and the events behind it are addressed the same way. Each event is the per-generation token usage as reported by the provider, for audit and reconciliation.
 	*
 	* An id naming nothing in scope yields an empty page rather than dropping the filter, so a mistyped narrowing can never widen the list past what was asked for.
 	*
@@ -4368,9 +4368,9 @@ var Usage = class {
 	/**
 	* Get aggregated usage for a project
 	*
-	* Returns a project's usage rolled up over an optional `[from, to]` time window, optionally bucketed by a single dimension and narrowed by any combination of thirteen filters — session, actor, agent, AI provider, orchestration run, orchestration, generation, trace, meter type, model, source, trigger and action. That is how "what did this conversation cost", "what has this end user cost" and "what did this agent cost" are answered. Each group and the grand total carry an `event_count`, summed token counts, a measured `quantity` per component (so infra meters report their real amount, not zeros), and `cost_usd` (null when no event in the bucket was priced). This is the per-project cost-by-range/by-category query — a monthly figure without scanning raw usage events client-side.
+	* Returns a project's usage rolled up over an optional `[from, to]` time window, optionally bucketed by a single dimension and narrowed by any combination of fifteen filters — session, actor, agent, AI provider, orchestration run, orchestration, generation, trace, tool, meter type, model, source, trigger, action and outcome. That is how "what did this conversation cost", "what has this end user cost" and "what did this agent cost" are answered. Each group and the grand total carry an `event_count`, summed token counts, a measured `quantity` per component (so infra meters report their real amount, not zeros), and `cost_usd` (null when no event in the bucket was priced). This is the per-project cost-by-range/by-category query — a monthly figure without scanning raw usage events client-side.
 	*
-	* Narrowings intersect and apply to the whole rollup — every bucket, `totals` and `totals.distinct` alike — so each composes with any `group_by`, and all thirteen are echoed back under `filters`. The eight naming a resource are resolved against the project, and one naming nothing there empties the rollup rather than being dropped: a mistyped id must never read back as the project's whole spend. The other five are matched against the value the event recorded.
+	* Narrowings intersect and apply to the whole rollup — every bucket, `totals` and `totals.distinct` alike — so each composes with any `group_by`, and all fifteen are echoed back under `filters`. The nine naming a resource are resolved against the project, and one naming nothing there empties the rollup rather than being dropped: a mistyped id must never read back as the project's whole spend. The other six are matched against the value the event recorded.
 	*
 	* `groups` is paginated. Its `total` is the number of distinct buckets in the window — bucket cardinality, including a null bucket for the events the dimension does not apply to, and never a count of entities. To count entities, send `include=distinct` and read `totals.distinct`. `totals` always describes the whole window — never the page above it, and never the bucketing: omit `group_by` and `totals` is unchanged while `groups` is empty.
 	*

package/dist/index.d.cts

@@ -3466,7 +3466,7 @@ type QuotaResourceProperties = {
   /**
    * Only for metric cost_usd. The meter this cap answers for; omit it and the cap sums every priced meter. See the quotas REST contract.
    */
-  meter_type?: 'llm_tokens' | 'compute_execution' | 'api_request' | 'storage';
+  meter_type?: 'llm_tokens' | 'compute_execution' | 'api_request' | 'storage' | 'tool_execution';
 };
 /**
  * Creates a guardrail — an action-class document (`class`/`guard`) that gates tool-call autonomy. Attach it to a tool or agent via that resource's `guardrail_ids` (a `{ "ref": … }` to this resource in the same template resolves to its physical id at deploy time). Mirrors the guardrails REST contract; `class`/`default_class`/`guard`/`escalate` are flattened here from the REST API's single `document` object.
@@ -5616,7 +5616,7 @@ type Quota = {
   /**
    * The meter a cost_usd cap answers for. Null is every priced meter, which is what a quota created without one carries.
    */
-  meter_type?: 'llm_tokens' | 'compute_execution' | 'api_request' | 'storage' | null;
+  meter_type?: 'llm_tokens' | 'compute_execution' | 'api_request' | 'storage' | 'tool_execution' | null;
   /**
    * Pricing posture of a cost_usd quota over an unpriced blackout — block refuses generations, allow lets them through (the quota_unpriced exception is filed either way, and for a partly priced window, which no posture refuses). Null for metrics with no pricing dependency.
    */
@@ -6764,12 +6764,22 @@ type UsageEvent = {
    */
   action_id?: string | null;
   /**
-   * What the event measures: `llm_tokens`, `compute_execution`, `api_request`, or `storage`.
+   * Public ID of the tool a `tool_execution` event metered. Null on every other meter, for an inline tool definition, and once the tool is deleted.
+   *
+   */
+  tool_id?: string | null;
+  /**
+   * How a `tool_execution` call that went out ended, whatever the target answered: `ok`, `error` (including a non-2xx answer), or `timeout`. Null on every other meter.
+   *
+   */
+  outcome?: string | null;
+  /**
+   * What the event measures: `llm_tokens`, `compute_execution`, `api_request`, `storage`, or `tool_execution` — one outbound tool call, a single `tool_call` component of quantity 1, unpriced.
    *
    */
   meter_type?: string;
   /**
-   * What the spend was incurred for. `eval` is an eval run's item generations and `eval_judge` an `llm_judge` scorer's own completion, so verification spend is `source` in (`eval`, `eval_judge`) and the two are distinct so running a suite can be priced apart from grading it. `embedding` is any embedding call — the endpoint, document ingestion, a memory store write, or a search's query vector. Null for ordinary agent traffic.
+   * What the spend was incurred for. `eval` is an eval run's item generations and `eval_judge` an `llm_judge` scorer's own completion, and `eval_scorer` a `tool` scorer's call, so verification spend is `source` in (`eval`, `eval_judge`, `eval_scorer`) and they are distinct so running a suite can be priced apart from grading it. `embedding` is any embedding call — the endpoint, document ingestion, a memory store write, or a search's query vector. Null for ordinary agent traffic.
    *
    */
   source?: string | null;
@@ -6791,10 +6801,10 @@ type UsageEvent = {
   created_at?: Date;
 };
 /**
- * The dimension an aggregate buckets on. `orchestration_run` buckets on the orchestration run; work that runs no orchestration collapses into the single `null` bucket.
+ * The dimension an aggregate buckets on. `orchestration_run` buckets on the orchestration run; work that runs no orchestration collapses into the single `null` bucket. `tool` buckets `tool_execution` events on the tool they metered; every other meter is the `null` bucket.
  *
  */
-type UsageGroupBy = 'model' | 'ai_provider' | 'agent' | 'orchestration_run' | 'day' | 'meter_type' | 'actor' | 'session' | 'source';
+type UsageGroupBy = 'model' | 'ai_provider' | 'agent' | 'orchestration_run' | 'day' | 'meter_type' | 'actor' | 'session' | 'source' | 'tool';
 /**
  * How many distinct entities of each kind the window touched — the counters a "how many generations / runs / actors this cycle" question reads. Present on `totals` exactly when `include=distinct` was sent, and never on a group — filling it per bucket would mean a `COUNT(DISTINCT)` per bucket on the page query.
  *
@@ -6811,6 +6821,7 @@ type UsageDistinct = {
   actors?: number;
   sessions?: number;
   ai_providers?: number;
+  tools?: number;
 };
 /**
  * One measured dimension of a bucket, summed across its events. This is what makes the rollup uniform over meter types: the token fields only describe `llm_tokens`, so an infra meter's amount is read here.
@@ -6854,7 +6865,7 @@ type UsageAggregateTotals = UsageAggregateBucket & {
   distinct?: UsageDistinct;
 };
 /**
- * Every narrowing the rollup applied, echoed back exactly as the caller sent it and null when unset. Echoed because a rollup of zeros is otherwise indistinguishable from a project that spent nothing, and always complete so a caller reading one key can tell "not filtered" from "this endpoint does not know that filter". The eight naming a resource are resolved against the project and empty the rollup when they name nothing in it; the other five are matched against the value the event recorded.
+ * Every narrowing the rollup applied, echoed back exactly as the caller sent it and null when unset. Echoed because a rollup of zeros is otherwise indistinguishable from a project that spent nothing, and always complete so a caller reading one key can tell "not filtered" from "this endpoint does not know that filter". The nine naming a resource are resolved against the project and empty the rollup when they name nothing in it; the other six are matched against the value the event recorded.
  *
  */
 type UsageAggregateFilters = {
@@ -6871,6 +6882,8 @@ type UsageAggregateFilters = {
   orchestration_id?: string | null;
   generation_id?: string | null;
   trace_id?: string | null;
+  tool_id?: string | null;
+  outcome?: string | null;
 };
 type UsageAggregate = {
   project_id?: string;
@@ -6906,7 +6919,7 @@ type UsageAggregate = {
 };
 type UsageAggregateGroup = {
   /**
-   * The bucket's value in the chosen dimension (a model id, meter type, AI provider / agent / orchestration run / actor / session public id, or `YYYY-MM-DD` UTC day). Null when the dimension does not apply to an event — under `actor`/`session` this is the bucket holding everything with no end user behind it, and under `orchestration_run` the one holding every generation that ran no orchestration.
+   * The bucket's value in the chosen dimension (a model id, meter type, AI provider / agent / orchestration run / actor / session / tool public id, or `YYYY-MM-DD` UTC day). Null when the dimension does not apply to an event — under `actor`/`session` this is the bucket holding everything with no end user behind it, and under `orchestration_run` the one holding every generation that ran no orchestration.
    *
    */
   key?: string | null;
@@ -13557,7 +13570,7 @@ type EvaluateGuardrailData = {
       [key: string]: unknown;
     };
     /**
-     * Optional tool to resolve `runtime.tool.*` against.
+     * Optional tool to resolve `runtime.tools.*` against.
      */
     tool_id?: string;
   };
@@ -16744,7 +16757,7 @@ type CreateQuotaData = {
     /**
      * Only for metric cost_usd (400 on any other metric). The meter this cap answers for. Omit it and the cap sums every priced meter, which is the existing behaviour; name one and only that meter's cost counts, so an AI spend cap is not consumed by platform meters the operator prices (and vice versa). Part of the quota's identity, so two meter scopes can share a scope/metric/window and neither conflicts with an unscoped cap. Immutable after creation — replace the quota to change it.
      */
-    meter_type?: 'llm_tokens' | 'compute_execution' | 'api_request' | 'storage';
+    meter_type?: 'llm_tokens' | 'compute_execution' | 'api_request' | 'storage' | 'tool_execution';
   };
   path?: never;
   query?: never;
@@ -18648,12 +18661,22 @@ type ListUsageEventsData = {
      */
     action_id?: string;
     /**
-     * Filter by meter type (e.g. `llm_tokens`, `compute_execution`, `api_request`, `storage`)
+     * Filter by the tool a `tool_execution` event metered. A tool that does not exist in scope yields an empty page.
+     *
+     */
+    tool_id?: string;
+    /**
+     * Filter by how a `tool_execution` call ended: `ok`, `error` or `timeout`. Every other meter carries no outcome and is matched by none of them.
+     *
+     */
+    outcome?: string;
+    /**
+     * Filter by meter type (e.g. `llm_tokens`, `compute_execution`, `api_request`, `storage`, `tool_execution`)
      *
      */
     meter_type?: string;
     /**
-     * Filter by what the spend was incurred for. `eval` is an eval run's item generations and `eval_judge` an `llm_judge` scorer's own completion, so verification spend is `source` in (`eval`, `eval_judge`); `embedding` is any embedding call. Ordinary agent traffic carries no source and is matched by none of them.
+     * Filter by what the spend was incurred for. `eval` is an eval run's item generations, `eval_judge` an `llm_judge` scorer's own completion and `eval_scorer` a `tool` scorer's call, so verification spend is `source` in (`eval`, `eval_judge`, `eval_scorer`); `embedding` is any embedding call. Ordinary agent traffic carries no source and is matched by none of them.
      *
      */
     source?: string;
@@ -18718,7 +18741,7 @@ type GetUsageAggregateData = {
      */
     to?: Date;
     /**
-     * Narrow the rollup to one meter type (e.g. `llm_tokens`, `compute_execution`, `api_request`, `storage`). Omit to include every meter. An unknown type yields an empty rollup, not an error.
+     * Narrow the rollup to one meter type (e.g. `llm_tokens`, `compute_execution`, `api_request`, `storage`, `tool_execution`). Omit to include every meter. An unknown type yields an empty rollup, not an error.
      *
      */
     meter_type?: string;
@@ -18780,6 +18803,16 @@ type GetUsageAggregateData = {
      *
      */
     action_id?: string;
+    /**
+     * Narrow to the executions of one tool. An id naming no tool in this project yields an empty rollup.
+     *
+     */
+    tool_id?: string;
+    /**
+     * Narrow `tool_execution` events by how the call ended — `ok`, `error` or `timeout` — matched as recorded. `outcome=error` is a tool's failures without a second meter.
+     *
+     */
+    outcome?: string;
     /**
      * Maximum number of `groups` entries to return. Clamped to 100. Does not affect `totals` or `groups.total`, which describe the whole window.
      *
@@ -20934,7 +20967,7 @@ export declare class Guardrails {
   /**
    * Dry-run evaluate a guardrail
    *
-   * Runs the full evaluation pipeline — the `class` expression, the guard, the context tool per `context_mode`, live `runtime.*` resolution — against caller-supplied `args` and `guardrail_context`, and returns the exact `guardrail_evaluation` record a real call would produce. Nothing executes, no approval item is filed, and no activity entry is written. This is the adoption path: preview a document's decisions against production-shaped calls before attaching it — or before editing a widely-attached one. Pass an optional `tool_id` to resolve `runtime.tool.*`.
+   * Runs the full evaluation pipeline — the `class` expression, the guard, the context tool per `context_mode`, live `runtime.*` resolution — against caller-supplied `args` and `guardrail_context`, and returns the exact `guardrail_evaluation` record a real call would produce. Nothing executes, no approval item is filed, and no activity entry is written. This is the adoption path: preview a document's decisions against production-shaped calls before attaching it — or before editing a widely-attached one. Pass an optional `tool_id` to resolve `runtime.tools.*`.
    *
    */
   static evaluateGuardrail<ThrowOnError extends boolean = false>(options: Options<EvaluateGuardrailData, ThrowOnError>): RequestResult<EvaluateGuardrailResponses, EvaluateGuardrailErrors, ThrowOnError>;
@@ -21775,7 +21808,7 @@ export declare class Usage {
   /**
    * List usage events
    *
-   * Returns the raw usage events the caller can access, most recent first, narrowed by any combination of the same filters the aggregate takes — agent, generation, trace, actor, session, AI provider, orchestration run, orchestration, trigger, action, meter type, model or `source` — so a rollup and the events behind it are addressed the same way. Each event is the per-generation token usage as reported by the provider, for audit and reconciliation.
+   * Returns the raw usage events the caller can access, most recent first, narrowed by any combination of the same filters the aggregate takes — agent, generation, trace, actor, session, AI provider, orchestration run, orchestration, tool, trigger, action, outcome, meter type, model or `source` — so a rollup and the events behind it are addressed the same way. Each event is the per-generation token usage as reported by the provider, for audit and reconciliation.
    *
    * An id naming nothing in scope yields an empty page rather than dropping the filter, so a mistyped narrowing can never widen the list past what was asked for.
    *
@@ -21784,9 +21817,9 @@ export declare class Usage {
   /**
    * Get aggregated usage for a project
    *
-   * Returns a project's usage rolled up over an optional `[from, to]` time window, optionally bucketed by a single dimension and narrowed by any combination of thirteen filters — session, actor, agent, AI provider, orchestration run, orchestration, generation, trace, meter type, model, source, trigger and action. That is how "what did this conversation cost", "what has this end user cost" and "what did this agent cost" are answered. Each group and the grand total carry an `event_count`, summed token counts, a measured `quantity` per component (so infra meters report their real amount, not zeros), and `cost_usd` (null when no event in the bucket was priced). This is the per-project cost-by-range/by-category query — a monthly figure without scanning raw usage events client-side.
+   * Returns a project's usage rolled up over an optional `[from, to]` time window, optionally bucketed by a single dimension and narrowed by any combination of fifteen filters — session, actor, agent, AI provider, orchestration run, orchestration, generation, trace, tool, meter type, model, source, trigger, action and outcome. That is how "what did this conversation cost", "what has this end user cost" and "what did this agent cost" are answered. Each group and the grand total carry an `event_count`, summed token counts, a measured `quantity` per component (so infra meters report their real amount, not zeros), and `cost_usd` (null when no event in the bucket was priced). This is the per-project cost-by-range/by-category query — a monthly figure without scanning raw usage events client-side.
    *
-   * Narrowings intersect and apply to the whole rollup — every bucket, `totals` and `totals.distinct` alike — so each composes with any `group_by`, and all thirteen are echoed back under `filters`. The eight naming a resource are resolved against the project, and one naming nothing there empties the rollup rather than being dropped: a mistyped id must never read back as the project's whole spend. The other five are matched against the value the event recorded.
+   * Narrowings intersect and apply to the whole rollup — every bucket, `totals` and `totals.distinct` alike — so each composes with any `group_by`, and all fifteen are echoed back under `filters`. The nine naming a resource are resolved against the project, and one naming nothing there empties the rollup rather than being dropped: a mistyped id must never read back as the project's whole spend. The other six are matched against the value the event recorded.
    *
    * `groups` is paginated. Its `total` is the number of distinct buckets in the window — bucket cardinality, including a null bucket for the events the dimension does not apply to, and never a count of entities. To count entities, send `include=distinct` and read `totals.distinct`. `totals` always describes the whole window — never the page above it, and never the bucketing: omit `group_by` and `totals` is unchanged while `groups` is empty.
    *

package/dist/index.d.mts

@@ -3466,7 +3466,7 @@ type QuotaResourceProperties = {
   /**
    * Only for metric cost_usd. The meter this cap answers for; omit it and the cap sums every priced meter. See the quotas REST contract.
    */
-  meter_type?: 'llm_tokens' | 'compute_execution' | 'api_request' | 'storage';
+  meter_type?: 'llm_tokens' | 'compute_execution' | 'api_request' | 'storage' | 'tool_execution';
 };
 /**
  * Creates a guardrail — an action-class document (`class`/`guard`) that gates tool-call autonomy. Attach it to a tool or agent via that resource's `guardrail_ids` (a `{ "ref": … }` to this resource in the same template resolves to its physical id at deploy time). Mirrors the guardrails REST contract; `class`/`default_class`/`guard`/`escalate` are flattened here from the REST API's single `document` object.
@@ -5616,7 +5616,7 @@ type Quota = {
   /**
    * The meter a cost_usd cap answers for. Null is every priced meter, which is what a quota created without one carries.
    */
-  meter_type?: 'llm_tokens' | 'compute_execution' | 'api_request' | 'storage' | null;
+  meter_type?: 'llm_tokens' | 'compute_execution' | 'api_request' | 'storage' | 'tool_execution' | null;
   /**
    * Pricing posture of a cost_usd quota over an unpriced blackout — block refuses generations, allow lets them through (the quota_unpriced exception is filed either way, and for a partly priced window, which no posture refuses). Null for metrics with no pricing dependency.
    */
@@ -6764,12 +6764,22 @@ type UsageEvent = {
    */
   action_id?: string | null;
   /**
-   * What the event measures: `llm_tokens`, `compute_execution`, `api_request`, or `storage`.
+   * Public ID of the tool a `tool_execution` event metered. Null on every other meter, for an inline tool definition, and once the tool is deleted.
+   *
+   */
+  tool_id?: string | null;
+  /**
+   * How a `tool_execution` call that went out ended, whatever the target answered: `ok`, `error` (including a non-2xx answer), or `timeout`. Null on every other meter.
+   *
+   */
+  outcome?: string | null;
+  /**
+   * What the event measures: `llm_tokens`, `compute_execution`, `api_request`, `storage`, or `tool_execution` — one outbound tool call, a single `tool_call` component of quantity 1, unpriced.
    *
    */
   meter_type?: string;
   /**
-   * What the spend was incurred for. `eval` is an eval run's item generations and `eval_judge` an `llm_judge` scorer's own completion, so verification spend is `source` in (`eval`, `eval_judge`) and the two are distinct so running a suite can be priced apart from grading it. `embedding` is any embedding call — the endpoint, document ingestion, a memory store write, or a search's query vector. Null for ordinary agent traffic.
+   * What the spend was incurred for. `eval` is an eval run's item generations and `eval_judge` an `llm_judge` scorer's own completion, and `eval_scorer` a `tool` scorer's call, so verification spend is `source` in (`eval`, `eval_judge`, `eval_scorer`) and they are distinct so running a suite can be priced apart from grading it. `embedding` is any embedding call — the endpoint, document ingestion, a memory store write, or a search's query vector. Null for ordinary agent traffic.
    *
    */
   source?: string | null;
@@ -6791,10 +6801,10 @@ type UsageEvent = {
   created_at?: Date;
 };
 /**
- * The dimension an aggregate buckets on. `orchestration_run` buckets on the orchestration run; work that runs no orchestration collapses into the single `null` bucket.
+ * The dimension an aggregate buckets on. `orchestration_run` buckets on the orchestration run; work that runs no orchestration collapses into the single `null` bucket. `tool` buckets `tool_execution` events on the tool they metered; every other meter is the `null` bucket.
  *
  */
-type UsageGroupBy = 'model' | 'ai_provider' | 'agent' | 'orchestration_run' | 'day' | 'meter_type' | 'actor' | 'session' | 'source';
+type UsageGroupBy = 'model' | 'ai_provider' | 'agent' | 'orchestration_run' | 'day' | 'meter_type' | 'actor' | 'session' | 'source' | 'tool';
 /**
  * How many distinct entities of each kind the window touched — the counters a "how many generations / runs / actors this cycle" question reads. Present on `totals` exactly when `include=distinct` was sent, and never on a group — filling it per bucket would mean a `COUNT(DISTINCT)` per bucket on the page query.
  *
@@ -6811,6 +6821,7 @@ type UsageDistinct = {
   actors?: number;
   sessions?: number;
   ai_providers?: number;
+  tools?: number;
 };
 /**
  * One measured dimension of a bucket, summed across its events. This is what makes the rollup uniform over meter types: the token fields only describe `llm_tokens`, so an infra meter's amount is read here.
@@ -6854,7 +6865,7 @@ type UsageAggregateTotals = UsageAggregateBucket & {
   distinct?: UsageDistinct;
 };
 /**
- * Every narrowing the rollup applied, echoed back exactly as the caller sent it and null when unset. Echoed because a rollup of zeros is otherwise indistinguishable from a project that spent nothing, and always complete so a caller reading one key can tell "not filtered" from "this endpoint does not know that filter". The eight naming a resource are resolved against the project and empty the rollup when they name nothing in it; the other five are matched against the value the event recorded.
+ * Every narrowing the rollup applied, echoed back exactly as the caller sent it and null when unset. Echoed because a rollup of zeros is otherwise indistinguishable from a project that spent nothing, and always complete so a caller reading one key can tell "not filtered" from "this endpoint does not know that filter". The nine naming a resource are resolved against the project and empty the rollup when they name nothing in it; the other six are matched against the value the event recorded.
  *
  */
 type UsageAggregateFilters = {
@@ -6871,6 +6882,8 @@ type UsageAggregateFilters = {
   orchestration_id?: string | null;
   generation_id?: string | null;
   trace_id?: string | null;
+  tool_id?: string | null;
+  outcome?: string | null;
 };
 type UsageAggregate = {
   project_id?: string;
@@ -6906,7 +6919,7 @@ type UsageAggregate = {
 };
 type UsageAggregateGroup = {
   /**
-   * The bucket's value in the chosen dimension (a model id, meter type, AI provider / agent / orchestration run / actor / session public id, or `YYYY-MM-DD` UTC day). Null when the dimension does not apply to an event — under `actor`/`session` this is the bucket holding everything with no end user behind it, and under `orchestration_run` the one holding every generation that ran no orchestration.
+   * The bucket's value in the chosen dimension (a model id, meter type, AI provider / agent / orchestration run / actor / session / tool public id, or `YYYY-MM-DD` UTC day). Null when the dimension does not apply to an event — under `actor`/`session` this is the bucket holding everything with no end user behind it, and under `orchestration_run` the one holding every generation that ran no orchestration.
    *
    */
   key?: string | null;
@@ -13557,7 +13570,7 @@ type EvaluateGuardrailData = {
       [key: string]: unknown;
     };
     /**
-     * Optional tool to resolve `runtime.tool.*` against.
+     * Optional tool to resolve `runtime.tools.*` against.
      */
     tool_id?: string;
   };
@@ -16744,7 +16757,7 @@ type CreateQuotaData = {
     /**
      * Only for metric cost_usd (400 on any other metric). The meter this cap answers for. Omit it and the cap sums every priced meter, which is the existing behaviour; name one and only that meter's cost counts, so an AI spend cap is not consumed by platform meters the operator prices (and vice versa). Part of the quota's identity, so two meter scopes can share a scope/metric/window and neither conflicts with an unscoped cap. Immutable after creation — replace the quota to change it.
      */
-    meter_type?: 'llm_tokens' | 'compute_execution' | 'api_request' | 'storage';
+    meter_type?: 'llm_tokens' | 'compute_execution' | 'api_request' | 'storage' | 'tool_execution';
   };
   path?: never;
   query?: never;
@@ -18648,12 +18661,22 @@ type ListUsageEventsData = {
      */
     action_id?: string;
     /**
-     * Filter by meter type (e.g. `llm_tokens`, `compute_execution`, `api_request`, `storage`)
+     * Filter by the tool a `tool_execution` event metered. A tool that does not exist in scope yields an empty page.
+     *
+     */
+    tool_id?: string;
+    /**
+     * Filter by how a `tool_execution` call ended: `ok`, `error` or `timeout`. Every other meter carries no outcome and is matched by none of them.
+     *
+     */
+    outcome?: string;
+    /**
+     * Filter by meter type (e.g. `llm_tokens`, `compute_execution`, `api_request`, `storage`, `tool_execution`)
      *
      */
     meter_type?: string;
     /**
-     * Filter by what the spend was incurred for. `eval` is an eval run's item generations and `eval_judge` an `llm_judge` scorer's own completion, so verification spend is `source` in (`eval`, `eval_judge`); `embedding` is any embedding call. Ordinary agent traffic carries no source and is matched by none of them.
+     * Filter by what the spend was incurred for. `eval` is an eval run's item generations, `eval_judge` an `llm_judge` scorer's own completion and `eval_scorer` a `tool` scorer's call, so verification spend is `source` in (`eval`, `eval_judge`, `eval_scorer`); `embedding` is any embedding call. Ordinary agent traffic carries no source and is matched by none of them.
      *
      */
     source?: string;
@@ -18718,7 +18741,7 @@ type GetUsageAggregateData = {
      */
     to?: Date;
     /**
-     * Narrow the rollup to one meter type (e.g. `llm_tokens`, `compute_execution`, `api_request`, `storage`). Omit to include every meter. An unknown type yields an empty rollup, not an error.
+     * Narrow the rollup to one meter type (e.g. `llm_tokens`, `compute_execution`, `api_request`, `storage`, `tool_execution`). Omit to include every meter. An unknown type yields an empty rollup, not an error.
      *
      */
     meter_type?: string;
@@ -18780,6 +18803,16 @@ type GetUsageAggregateData = {
      *
      */
     action_id?: string;
+    /**
+     * Narrow to the executions of one tool. An id naming no tool in this project yields an empty rollup.
+     *
+     */
+    tool_id?: string;
+    /**
+     * Narrow `tool_execution` events by how the call ended — `ok`, `error` or `timeout` — matched as recorded. `outcome=error` is a tool's failures without a second meter.
+     *
+     */
+    outcome?: string;
     /**
      * Maximum number of `groups` entries to return. Clamped to 100. Does not affect `totals` or `groups.total`, which describe the whole window.
      *
@@ -20934,7 +20967,7 @@ export declare class Guardrails {
   /**
    * Dry-run evaluate a guardrail
    *
-   * Runs the full evaluation pipeline — the `class` expression, the guard, the context tool per `context_mode`, live `runtime.*` resolution — against caller-supplied `args` and `guardrail_context`, and returns the exact `guardrail_evaluation` record a real call would produce. Nothing executes, no approval item is filed, and no activity entry is written. This is the adoption path: preview a document's decisions against production-shaped calls before attaching it — or before editing a widely-attached one. Pass an optional `tool_id` to resolve `runtime.tool.*`.
+   * Runs the full evaluation pipeline — the `class` expression, the guard, the context tool per `context_mode`, live `runtime.*` resolution — against caller-supplied `args` and `guardrail_context`, and returns the exact `guardrail_evaluation` record a real call would produce. Nothing executes, no approval item is filed, and no activity entry is written. This is the adoption path: preview a document's decisions against production-shaped calls before attaching it — or before editing a widely-attached one. Pass an optional `tool_id` to resolve `runtime.tools.*`.
    *
    */
   static evaluateGuardrail<ThrowOnError extends boolean = false>(options: Options<EvaluateGuardrailData, ThrowOnError>): RequestResult<EvaluateGuardrailResponses, EvaluateGuardrailErrors, ThrowOnError>;
@@ -21775,7 +21808,7 @@ export declare class Usage {
   /**
    * List usage events
    *
-   * Returns the raw usage events the caller can access, most recent first, narrowed by any combination of the same filters the aggregate takes — agent, generation, trace, actor, session, AI provider, orchestration run, orchestration, trigger, action, meter type, model or `source` — so a rollup and the events behind it are addressed the same way. Each event is the per-generation token usage as reported by the provider, for audit and reconciliation.
+   * Returns the raw usage events the caller can access, most recent first, narrowed by any combination of the same filters the aggregate takes — agent, generation, trace, actor, session, AI provider, orchestration run, orchestration, tool, trigger, action, outcome, meter type, model or `source` — so a rollup and the events behind it are addressed the same way. Each event is the per-generation token usage as reported by the provider, for audit and reconciliation.
    *
    * An id naming nothing in scope yields an empty page rather than dropping the filter, so a mistyped narrowing can never widen the list past what was asked for.
    *
@@ -21784,9 +21817,9 @@ export declare class Usage {
   /**
    * Get aggregated usage for a project
    *
-   * Returns a project's usage rolled up over an optional `[from, to]` time window, optionally bucketed by a single dimension and narrowed by any combination of thirteen filters — session, actor, agent, AI provider, orchestration run, orchestration, generation, trace, meter type, model, source, trigger and action. That is how "what did this conversation cost", "what has this end user cost" and "what did this agent cost" are answered. Each group and the grand total carry an `event_count`, summed token counts, a measured `quantity` per component (so infra meters report their real amount, not zeros), and `cost_usd` (null when no event in the bucket was priced). This is the per-project cost-by-range/by-category query — a monthly figure without scanning raw usage events client-side.
+   * Returns a project's usage rolled up over an optional `[from, to]` time window, optionally bucketed by a single dimension and narrowed by any combination of fifteen filters — session, actor, agent, AI provider, orchestration run, orchestration, generation, trace, tool, meter type, model, source, trigger, action and outcome. That is how "what did this conversation cost", "what has this end user cost" and "what did this agent cost" are answered. Each group and the grand total carry an `event_count`, summed token counts, a measured `quantity` per component (so infra meters report their real amount, not zeros), and `cost_usd` (null when no event in the bucket was priced). This is the per-project cost-by-range/by-category query — a monthly figure without scanning raw usage events client-side.
    *
-   * Narrowings intersect and apply to the whole rollup — every bucket, `totals` and `totals.distinct` alike — so each composes with any `group_by`, and all thirteen are echoed back under `filters`. The eight naming a resource are resolved against the project, and one naming nothing there empties the rollup rather than being dropped: a mistyped id must never read back as the project's whole spend. The other five are matched against the value the event recorded.
+   * Narrowings intersect and apply to the whole rollup — every bucket, `totals` and `totals.distinct` alike — so each composes with any `group_by`, and all fifteen are echoed back under `filters`. The nine naming a resource are resolved against the project, and one naming nothing there empties the rollup rather than being dropped: a mistyped id must never read back as the project's whole spend. The other six are matched against the value the event recorded.
    *
    * `groups` is paginated. Its `total` is the number of distinct buckets in the window — bucket cardinality, including a null bucket for the events the dimension does not apply to, and never a count of entities. To count entities, send `include=distinct` and read `totals.distinct`. `totals` always describes the whole window — never the page above it, and never the bucketing: omit `group_by` and `totals` is unchanged while `groups` is empty.
    *

package/dist/index.mjs

@@ -2668,7 +2668,7 @@ var Guardrails = class {
 	/**
 	* Dry-run evaluate a guardrail
 	*
-	* Runs the full evaluation pipeline — the `class` expression, the guard, the context tool per `context_mode`, live `runtime.*` resolution — against caller-supplied `args` and `guardrail_context`, and returns the exact `guardrail_evaluation` record a real call would produce. Nothing executes, no approval item is filed, and no activity entry is written. This is the adoption path: preview a document's decisions against production-shaped calls before attaching it — or before editing a widely-attached one. Pass an optional `tool_id` to resolve `runtime.tool.*`.
+	* Runs the full evaluation pipeline — the `class` expression, the guard, the context tool per `context_mode`, live `runtime.*` resolution — against caller-supplied `args` and `guardrail_context`, and returns the exact `guardrail_evaluation` record a real call would produce. Nothing executes, no approval item is filed, and no activity entry is written. This is the adoption path: preview a document's decisions against production-shaped calls before attaching it — or before editing a widely-attached one. Pass an optional `tool_id` to resolve `runtime.tools.*`.
 	*
 	*/
 	static evaluateGuardrail(options) {
@@ -4353,7 +4353,7 @@ var Usage = class {
 	/**
 	* List usage events
 	*
-	* Returns the raw usage events the caller can access, most recent first, narrowed by any combination of the same filters the aggregate takes — agent, generation, trace, actor, session, AI provider, orchestration run, orchestration, trigger, action, meter type, model or `source` — so a rollup and the events behind it are addressed the same way. Each event is the per-generation token usage as reported by the provider, for audit and reconciliation.
+	* Returns the raw usage events the caller can access, most recent first, narrowed by any combination of the same filters the aggregate takes — agent, generation, trace, actor, session, AI provider, orchestration run, orchestration, tool, trigger, action, outcome, meter type, model or `source` — so a rollup and the events behind it are addressed the same way. Each event is the per-generation token usage as reported by the provider, for audit and reconciliation.
 	*
 	* An id naming nothing in scope yields an empty page rather than dropping the filter, so a mistyped narrowing can never widen the list past what was asked for.
 	*
@@ -4367,9 +4367,9 @@ var Usage = class {
 	/**
 	* Get aggregated usage for a project
 	*
-	* Returns a project's usage rolled up over an optional `[from, to]` time window, optionally bucketed by a single dimension and narrowed by any combination of thirteen filters — session, actor, agent, AI provider, orchestration run, orchestration, generation, trace, meter type, model, source, trigger and action. That is how "what did this conversation cost", "what has this end user cost" and "what did this agent cost" are answered. Each group and the grand total carry an `event_count`, summed token counts, a measured `quantity` per component (so infra meters report their real amount, not zeros), and `cost_usd` (null when no event in the bucket was priced). This is the per-project cost-by-range/by-category query — a monthly figure without scanning raw usage events client-side.
+	* Returns a project's usage rolled up over an optional `[from, to]` time window, optionally bucketed by a single dimension and narrowed by any combination of fifteen filters — session, actor, agent, AI provider, orchestration run, orchestration, generation, trace, tool, meter type, model, source, trigger, action and outcome. That is how "what did this conversation cost", "what has this end user cost" and "what did this agent cost" are answered. Each group and the grand total carry an `event_count`, summed token counts, a measured `quantity` per component (so infra meters report their real amount, not zeros), and `cost_usd` (null when no event in the bucket was priced). This is the per-project cost-by-range/by-category query — a monthly figure without scanning raw usage events client-side.
 	*
-	* Narrowings intersect and apply to the whole rollup — every bucket, `totals` and `totals.distinct` alike — so each composes with any `group_by`, and all thirteen are echoed back under `filters`. The eight naming a resource are resolved against the project, and one naming nothing there empties the rollup rather than being dropped: a mistyped id must never read back as the project's whole spend. The other five are matched against the value the event recorded.
+	* Narrowings intersect and apply to the whole rollup — every bucket, `totals` and `totals.distinct` alike — so each composes with any `group_by`, and all fifteen are echoed back under `filters`. The nine naming a resource are resolved against the project, and one naming nothing there empties the rollup rather than being dropped: a mistyped id must never read back as the project's whole spend. The other six are matched against the value the event recorded.
 	*
 	* `groups` is paginated. Its `total` is the number of distinct buckets in the window — bucket cardinality, including a null bucket for the events the dimension does not apply to, and never a count of entities. To count entities, send `include=distinct` and read `totals.distinct`. `totals` always describes the whole window — never the page above it, and never the bucketing: omit `group_by` and `totals` is unchanged while `groups` is empty.
 	*

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@soat/sdk",
-  "version": "0.60.0",
+  "version": "0.61.0",
   "description": "TypeScript SDK for SOAT — open-source infrastructure for production-ready AI agents.",
   "keywords": [
     "ai-agents",