Connic · Schema
AgentRunWithTraces
One run with its content, execution trace, token usage and cost.
CompanyArtificial IntelligencePlatformMunichAutomation
Properties
| Name | Type | Description |
|---|---|---|
| id | string | |
| agent_name | string | Base agent name; runs handled by an A/B variant are stored under the base name. |
| test_name | object | A/B test variant that handled the run, or the test case name for `deploy_gate` runs; null for runs of the base agent. |
| ab_test_ids | array | IDs of the A/B tests this run was counted in. |
| status | object | `scheduled` and `queued` runs have not started, `started` runs are executing, `awaiting_approval` runs wait for a tool approval, and `completed`, `failed` and `cancelled` are final. |
| input | object | Run input as text, with the environment's redacted keys masked; null after the run is deleted. |
| output | object | Final agent output, with the environment's redacted keys masked; null until the run finishes and after it is deleted. |
| error | object | Failure or cancellation message, if any; null after the run is deleted. |
| queued_at | string | When the run was created. |
| started_at | object | When execution began; null until the run starts. |
| ended_at | object | When the run reached a final status; null while it is active. |
| duration_ms | object | Execution time in milliseconds, excluding time spent waiting for approvals or child runs; null until the run ends. |
| data_deleted_at | object | When the run's content and trace were deleted; null if they were not. Status, usage and cost remain. |
| can_delete_data | boolean | True when the run and its background processing (usage accounting, judge evaluations, outbound deliveries) have finished, so it can be deleted. |
| scheduled_at | object | When a scheduled run is due to start; null for runs queued immediately. |
| queued_reason | object | Why a queued run has not started yet, for example `concurrency_wait`, `credit_exhausted` or `budget_limit_exceeded: |
| token_usage | object | Token counts for the agent's own model calls, excluding judge evaluations, with one `model_usages` entry per call. |
| traces | array | Execution trace: spans and log entries ordered by `start_time`, then `span_order`. Empty after the run is deleted. |
| connector | object | Connector whose event started the run; null for runs not started by a connector. |
| triggered_by | object | ID of the run whose agent started this run; older runs may hold a free-text value instead. |
| triggered_by_run | object | Parent run details when another agent in the same deployment started this run; null otherwise. |
| trigger_source | object | What started the run: a user or API call, a connector event, another agent, or a deployment test. |
| deployment_id | object | ID of the deployment that ran this run; null until the run is picked up. |
| token_cost | object | Cost of the agent's own model calls, excluding judge evaluations; null when no model calls were recorded. |
| run_context | object | Context values stored by the run's middleware and tools, with the environment's redacted keys masked; null after the run is deleted. |
| session | object | Persistent session the run belongs to; null for runs without one. |
| guardrail_interventions | array | Guardrail checks that warned about, blocked or redacted content during the run. |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/connic-co/json-schema/connic-co-agent-run-with-traces-schema.json",
"title": "AgentRunWithTraces",
"description": "One run with its content, execution trace, token usage and cost.",
"x-generated": "2026-11-04",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/_original/connic-co-public-openapi.json#/components/schemas/AgentRunWithTraces",
"properties": {
"id": {
"type": "string",
"format": "uuid",
"title": "Id"
},
"agent_name": {
"type": "string",
"title": "Agent Name",
"description": "Base agent name; runs handled by an A/B variant are stored under the base name."
},
"test_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Test Name",
"description": "A/B test variant that handled the run, or the test case name for `deploy_gate` runs; null for runs of the base agent."
},
"ab_test_ids": {
"items": {
"type": "string",
"format": "uuid"
},
"type": "array",
"title": "Ab Test Ids",
"description": "IDs of the A/B tests this run was counted in."
},
"status": {
"$ref": "#/$defs/RunStatus",
"description": "`scheduled` and `queued` runs have not started, `started` runs are executing, `awaiting_approval` runs wait for a tool approval, and `completed`, `failed` and `cancelled` are final."
},
"input": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Input",
"description": "Run input as text, with the environment's redacted keys masked; null after the run is deleted."
},
"output": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Output",
"description": "Final agent output, with the environment's redacted keys masked; null until the run finishes and after it is deleted."
},
"error": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Error",
"description": "Failure or cancellation message, if any; null after the run is deleted."
},
"queued_at": {
"type": "string",
"format": "date-time",
"title": "Queued At",
"description": "When the run was created."
},
"started_at": {
"anyOf": [
{
"type": "string",
"format": "date-time"
},
{
"type": "null"
}
],
"title": "Started At",
"description": "When execution began; null until the run starts."
},
"ended_at": {
"anyOf": [
{
"type": "string",
"format": "date-time"
},
{
"type": "null"
}
],
"title": "Ended At",
"description": "When the run reached a final status; null while it is active."
},
"duration_ms": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Duration Ms",
"description": "Execution time in milliseconds, excluding time spent waiting for approvals or child runs; null until the run ends."
},
"data_deleted_at": {
"anyOf": [
{
"type": "string",
"format": "date-time"
},
{
"type": "null"
}
],
"title": "Data Deleted At",
"description": "When the run's content and trace were deleted; null if they were not. Status, usage and cost remain."
},
"can_delete_data": {
"type": "boolean",
"title": "Can Delete Data",
"description": "True when the run and its background processing (usage accounting, judge evaluations, outbound deliveries) have finished, so it can be deleted.",
"default": false
},
"scheduled_at": {
"anyOf": [
{
"type": "string",
"format": "date-time"
},
{
"type": "null"
}
],
"title": "Scheduled At",
"description": "When a scheduled run is due to start; null for runs queued immediately."
},
"queued_reason": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Queued Reason",
"description": "Why a queued run has not started yet, for example `concurrency_wait`, `credit_exhausted` or `budget_limit_exceeded:<spend alert ID>`. Null once the run starts."
},
"token_usage": {
"$ref": "#/$defs/PublicRunTokenUsageResponse",
"description": "Token counts for the agent's own model calls, excluding judge evaluations, with one `model_usages` entry per call."
},
"traces": {
"items": {
"$ref": "#/$defs/AgentTraceResponse"
},
"type": "array",
"title": "Traces",
"description": "Execution trace: spans and log entries ordered by `start_time`, then `span_order`. Empty after the run is deleted.",
"default": []
},
"connector": {
"anyOf": [
{
"$ref": "#/$defs/ConnectorInfo"
},
{
"type": "null"
}
],
"description": "Connector whose event started the run; null for runs not started by a connector."
},
"triggered_by": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Triggered By",
"description": "ID of the run whose agent started this run; older runs may hold a free-text value instead."
},
"triggered_by_run": {
"anyOf": [
{
"$ref": "#/$defs/TriggeredByRunInfo"
},
{
"type": "null"
}
],
"description": "Parent run details when another agent in the same deployment started this run; null otherwise."
},
"trigger_source": {
"$ref": "#/$defs/TriggerSource",
"description": "What started the run: a user or API call, a connector event, another agent, or a deployment test.",
"default": "manual"
},
"deployment_id": {
"anyOf": [
{
"type": "string",
"format": "uuid"
},
{
"type": "null"
}
],
"title": "Deployment Id",
"description": "ID of the deployment that ran this run; null until the run is picked up."
},
"token_cost": {
"anyOf": [
{
"$ref": "#/$defs/PublicTokenCostResponse"
},
{
"type": "null"
}
],
"description": "Cost of the agent's own model calls, excluding judge evaluations; null when no model calls were recorded."
},
"run_context": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"title": "Run Context",
"description": "Context values stored by the run's middleware and tools, with the environment's redacted keys masked; null after the run is deleted."
},
"session": {
"anyOf": [
{
"$ref": "#/$defs/RunSessionInfo"
},
{
"type": "null"
}
],
"description": "Persistent session the run belongs to; null for runs without one."
},
"guardrail_interventions": {
"items": {
"$ref": "#/$defs/PublicGuardrailInterventionResponse"
},
"type": "array",
"title": "Guardrail Interventions",
"description": "Guardrail checks that warned about, blocked or redacted content during the run."
}
},
"type": "object",
"required": [
"id",
"agent_name",
"status",
"queued_at",
"token_usage"
],
"$defs": {
"AgentTraceResponse": {
"properties": {
"id": {
"type": "string",
"format": "uuid",
"title": "Id"
},
"run_id": {
"type": "string",
"format": "uuid",
"title": "Run Id",
"description": "ID of the run this entry belongs to."
},
"name": {
"type": "string",
"title": "Name",
"description": "Span name, or the log source for `log` entries, such as `log:system` or `log:tool:<tool name>`."
},
"type": {
"type": "string",
"enum": [
"span",
"log"
],
"title": "Type",
"description": "`span` for a timed step such as a model or tool call; `log` for a log line written during the run."
},
"status": {
"type": "string",
"title": "Status",
"description": "Span outcome; a value containing `ERROR` (any case) marks a failed span. For `log` entries, the log level: `debug`, `info`, `warning` or `error`."
},
"inputs": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Inputs",
"description": "Step input as text, with the environment's redacted keys masked."
},
"outputs": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Outputs",
"description": "Step output as text, with the environment's redacted keys masked. For `log` entries, the log message."
},
"thoughts": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Thoughts",
"description": "Model reasoning text for the step, when the model returns it."
},
"start_time": {
"type": "string",
"format": "date-time",
"title": "Start Time",
"description": "When the step started or the log line was written."
},
"end_time": {
"anyOf": [
{
"type": "string",
"format": "date-time"
},
{
"type": "null"
}
],
"title": "End Time",
"description": "When the span ended; null for `log` entries and unfinished spans."
},
"duration_ms": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Duration Ms",
"description": "Span duration in milliseconds; null for `log` entries."
},
"metadata": {
"additionalProperties": true,
"type": "object",
"title": "Metadata",
"description": "Additional span attributes as key-value pairs; empty for `log` entries."
},
"span_order": {
"type": "integer",
"title": "Span Order",
"description": "Recording order within the run; breaks ties between equal `start_time` values."
},
"span_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Span Id",
"description": "Span identifier, unique within the run."
},
"parent_span_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Parent Span Id",
"description": "`span_id` of the enclosing span; null for top-level spans and `log` entries."
}
},
"type": "object",
"required": [
"id",
"run_id",
"name",
"type",
"status",
"inputs",
"outputs",
"thoughts",
"start_time",
"end_time",
"duration_ms",
"metadata",
"span_order",
"span_id",
"parent_span_id"
],
"title": "AgentTraceResponse",
"description": "One span or log entry from a run's execution trace."
},
"ConnectorInfo": {
"properties": {
"id": {
"type": "string",
"format": "uuid",
"title": "Id"
},
"name": {
"type": "string",
"title": "Name"
},
"type": {
"type": "string",
"title": "Type",
"description": "Connector type, such as `http` or `cron`."
}
},
"type": "object",
"required": [
"id",
"name",
"type"
],
"title": "ConnectorInfo",
"description": "Connector whose event started a run."
},
"PublicGuardrailInterventionResponse": {
"properties": {
"id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Id"
},
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Name",
"description": "Name of the custom guardrail. Null for built-in types."
},
"type": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Type",
"description": "Guardrail type, such as `prompt_injection`, `pii`, `moderation`, `topic_restriction`, `regex` or `custom`."
},
"direction": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Direction",
"description": "`input` when the rule checked the run input, `output` when it checked the agent output."
},
"mode": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Mode",
"description": "Action configured for the rule: `block`, `warn` or `redact`."
},
"status": {
"type": "string",
"enum": [
"warned",
"blocked",
"redacted"
],
"title": "Status",
"description": "Outcome: `warned` let the content through with a warning, `blocked` stopped it, `redacted` removed the matched content."
},
"message": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Message",
"description": "Explanation from the guardrail. Empty after the run is deleted."
}
},
"type": "object",
"required": [
"status"
],
"title": "PublicGuardrailInterventionResponse",
"description": "A guardrail rule that did not pass during a run."
},
"PublicModelTokenUsageResponse": {
"properties": {
"input_tokens": {
"type": "integer",
"title": "Input Tokens",
"description": "Prompt tokens sent to the model, including cached tokens."
},
"output_tokens": {
"type": "integer",
"title": "Output Tokens",
"description": "Tokens the model generated, excluding thinking tokens."
},
"cached_input_tokens": {
"type": "integer",
"title": "Cached Input Tokens",
"description": "Part of `input_tokens` read from the provider's prompt cache."
},
"cache_write_input_tokens": {
"type": "integer",
"title": "Cache Write Input Tokens",
"description": "Part of `input_tokens` written to the provider's prompt cache.",
"default": 0
},
"thinking_tokens": {
"type": "integer",
"title": "Thinking Tokens",
"description": "Reasoning tokens the model generated."
},
"total_tokens": {
"type": "integer",
"title": "Total Tokens",
"description": "Input, output and thinking tokens combined."
},
"audio_input_tokens": {
"type": "integer",
"title": "Audio Input Tokens",
"description": "Part of `input_tokens` that was audio.",
"default": 0
},
"audio_output_tokens": {
"type": "integer",
"title": "Audio Output Tokens",
"description": "Part of `output_tokens` that was audio.",
"default": 0
},
"audio_cached_input_tokens": {
"type": "integer",
"title": "Audio Cached Input Tokens",
"description": "Part of `cached_input_tokens` that was audio.",
"default": 0
},
"audio_thinking_tokens": {
"type": "integer",
"title": "Audio Thinking Tokens",
"description": "Part of `thinking_tokens` that was audio.",
"default": 0
},
"audio_usage_missing": {
"type": "boolean",
"title": "Audio Usage Missing",
"description": "True when at least one model call did not report its audio breakdown, so audio counts may be too low.",
"default": false
},
"model": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Model",
"description": "Model that served the request. Null when not recorded."
}
},
"type": "object",
"required": [
"input_tokens",
"output_tokens",
"cached_input_tokens",
"thinking_tokens",
"total_tokens",
"model"
],
"title": "PublicModelTokenUsageResponse"
},
"PublicRunTokenUsageResponse": {
"properties": {
"input_tokens": {
"type": "integer",
"title": "Input Tokens",
"description": "Prompt tokens sent to the model, including cached tokens."
},
"output_tokens": {
"type": "integer",
"title": "Output Tokens",
"description": "Tokens the model generated, excluding thinking tokens."
},
"cached_input_tokens": {
"type": "integer",
"title": "Cached Input Tokens",
"description": "Part of `input_tokens` read from the provider's prompt cache."
},
"cache_write_input_tokens": {
"type": "integer",
"title": "Cache Write Input Tokens",
"description": "Part of `input_tokens` written to the provider's prompt cache.",
"default": 0
},
"thinking_tokens": {
"type": "integer",
"title": "Thinking Tokens",
"description": "Reasoning tokens the model generated."
},
"total_tokens": {
"type": "integer",
"title": "Total Tokens",
"description": "Input, output and thinking tokens combined."
},
"audio_input_tokens": {
"type": "integer",
"title": "Audio Input Tokens",
"description": "Part of `input_tokens` that was audio.",
"default": 0
},
"audio_output_tokens": {
"type": "integer",
"title": "Audio Output Tokens",
"description": "Part of `output_tokens` that was audio.",
"default": 0
},
"audio_cached_input_tokens": {
"type": "integer",
"title": "Audio Cached Input Tokens",
"description": "Part of `cached_input_tokens` that was audio.",
"default": 0
},
"audio_thinking_tokens": {
"type": "integer",
"title": "Audio Thinking Tokens",
"description": "Part of `thinking_tokens` that was audio.",
"default": 0
},
"audio_usage_missing": {
"type": "boolean",
"title": "Audio Usage Missing",
"description": "True when at least one model call did not report its audio breakdown, so audio counts may be too low.",
"default": false
},
"model_usages": {
"items": {
"$ref": "#/$defs/PublicModelTokenUsageResponse"
},
"type": "array",
"title": "Model Usages",
"description": "Usage of each model request, in call order."
}
},
"type": "object",
"required": [
"input_tokens",
"output_tokens",
"cached_input_tokens",
"thinking_tokens",
"total_tokens",
"model_usages"
],
"title": "PublicRunTokenUsageResponse"
},
"PublicTokenCostBreakdownResponse": {
"properties": {
"input_cost": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Input Cost",
"description": "Cost of input tokens neither read from nor written to the cache, including audio. Null when the split by token type is unknown."
},
"output_cost": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Output Cost",
"description": "Cost of output tokens, including audio. Null when the split by token type is unknown."
},
"cached_input_cost": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Cached Input Cost",
"description": "Cost of cached input tokens. Null when the split by token type is unknown."
},
"cache_write_input_cost": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Cache Write Input Cost",
"description": "Cost of input tokens written to the cache. Null when the split by token type is unknown.",
"default": "0.000000000000"
},
"thinking_cost": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Thinking Cost",
"description": "Cost of thinking tokens. Null when the split by token type is unknown."
},
"agent_cost": {
"type": "string",
"title": "Agent Cost",
"description": "Cost of the agent's own model calls."
},
"judge_cost": {
"type": "string",
"title": "Judge Cost",
"description": "Cost of judge evaluations."
},
"total_cost": {
"type": "string",
"title": "Total Cost",
"description": "`agent_cost` plus `judge_cost`. Always exact, even when the token type split is null."
},
"audio_input_cost": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Audio Input Cost",
"description": "Audio share of `input_cost`. Null when the split by token type is unknown.",
"default": "0.000000000000"
},
"audio_output_cost": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Audio Output Cost",
"description": "Audio share of `output_cost`. Null when the split by token type is unknown.",
"default": "0.000000000000"
},
"audio_cached_input_cost": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Audio Cached Input Cost",
"description": "Audio share of `cached_input_cost`. Null when the split by token type is unknown.",
"default": "0.000000000000"
},
"audio_thinking_cost": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Audio Thinking Cost",
"description": "Audio share of `thinking_cost`. Null when the split by token type is unknown.",
"default": "0.000000000000"
}
},
"type": "object",
"required": [
"input_cost",
"output_cost",
"cached_input_cost",
"thinking_cost",
"agent_cost",
"judge_cost",
"total_cost"
],
"title": "PublicTokenCostBreakdownResponse",
"description": "Cost in one currency, split by token type and by agent versus judge. Amounts are decimal strings."
},
"PublicTokenCostCoverageResponse": {
"properties": {
"complete": {
"type": "boolean",
"title": "Complete",
"description": "True when every model call could be priced."
},
"call_count": {
"type": "integer",
"title": "Call Count",
"description": "Model calls covered by the report."
},
"priced_call_count": {
"type": "integer",
"title": "Priced Call Count",
"description": "Calls included in the cost amounts."
},
"unpriced_call_count": {
"type": "integer",
"title": "Unpriced Call Count",
"description": "Calls without a known price or without reported token usage. They are left out of the amounts."
},
"unpriced_models": {
"items": {
"type": "string"
},
"type": "array",
"title": "Unpriced Models",
"description": "Models of the unpriced calls."
}
},
"type": "object",
"required": [
"complete",
"call_count",
"priced_call_count",
"unpriced_call_count",
"unpriced_models"
],
"title": "PublicTokenCostCoverageResponse",
"description": "How many model calls could be priced."
},
"PublicTokenCostResponse": {
"properties": {
"amounts": {
"additionalProperties": {
"type": "string"
},
"type": "object",
"title": "Amounts",
"description": "Total cost keyed by currency code (`EUR` or `USD`), as a decimal string with 12 decimal places. Only currencies with a nonzero amount are included."
},
"breakdown": {
"additionalProperties": {
"$ref": "#/$defs/PublicTokenCostBreakdownResponse"
},
"type": "object",
"title": "Breakdown",
"description": "Cost split by token type and by agent versus judge, keyed by currency code."
},
"coverage": {
"$ref": "#/$defs/PublicTokenCostCoverageResponse",
"description": "Whether every model call could be priced. Amounts exclude unpriced calls."
},
"converted_to": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Converted To",
"description": "Currency the amounts were converted to at the daily ECB reference rate of each call. Present only when `convert_costs_to` is set."
},
"native_amounts": {
"anyOf": [
{
"additionalProperties": {
"type": "string"
},
"type": "object"
},
{
"type": "null"
}
],
"title": "Native Amounts",
"description": "Totals in each model's pricing currency before conversion, as decimal strings keyed by currency code. Present only when `convert_costs_to` is set."
}
},
"type": "object",
"required": [
"amounts",
"breakdown",
"coverage"
],
"title": "PublicTokenCostResponse",
"description": "Token cost in each model's pricing currency, or in one currency when `convert_costs_to` is set."
},
"RunSessionInfo": {
"properties": {
"session_id": {
"type": "string",
"title": "Session Id",
"description": "Session ID, unique within the app name and user."
},
"app_name": {
"type": "string",
"title": "App Name",
"description": "Agent application name that owns the session."
},
"user_id": {
"type": "string",
"title": "User Id",
"description": "Agent user identity the session belongs to."
}
},
"type": "object",
"required": [
"session_id",
"app_name",
"user_id"
],
"title": "RunSessionInfo",
"description": "Persistent session a run belongs to."
},
"RunStatus": {
"type": "string",
"enum": [
"scheduled",
"queued",
"started",
"awaiting_approval",
"completed",
"failed",
"cancelled",
"blocked"
],
"title": "RunStatus",
"description": "Run state: `scheduled` until its start time, `queued`, `started` while executing, `awaiting_approval` while paused for a human decision, then `completed`, `failed` or `cancelled`."
},
"TriggerSource": {
"type": "string",
"enum": [
"manual",
"connector",
"agent",
"deploy_gate"
],
"title": "TriggerSource",
"description": "How a run was started: `manual` by a user, `connector` by an inbound connector event, `agent` by another agent, or `deploy_gate` as a deployment test run."
},
"TriggeredByRunInfo": {
"properties": {
"id": {
"type": "string",
"format": "uuid",
"title": "Id"
},
"agent_name": {
"type": "string",
"title": "Agent Name",
"description": "Agent of the parent run."
}
},
"type": "object",
"required": [
"id",
"agent_name"
],
"title": "TriggeredByRunInfo",
"description": "The run whose agent started this run."
}
}
}Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/connic-co-agent-run-with-traces"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.