> ## Documentation Index
> Fetch the complete documentation index at: https://ona.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Get Agent Trace Time Series

> Gets agent trace data as a time series.

`Unary` · [`Usage`](https://ona.com/docs/api-reference/generated/usage/overview)

Gets agent trace data as a time series.

Use this method to:

* Chart agent sessions and line changes over time
* Select hourly, daily, weekly, or monthly buckets
* Scope agent trace insights to a project, user, or team

### Example

```yaml theme={null}
dateRange:
  startTime: "2024-01-01T00:00:00Z"
  endTime: "2024-02-01T00:00:00Z"
resolution: RESOLUTION_WEEKLY
projectId: "d2c94c27-3b76-4a42-b88c-95a85e392c68"
```

## Endpoint

```text theme={null}
POST /api/gitpod.v1.UsageService/GetAgentTraceTimeSeries
```

Send a Bearer token as described in [Authentication](https://ona.com/docs/api-reference.md#authenticate-requests). If your organization uses a custom management-plane domain, replace `https://app.ona.com` with that domain.

## Request example

```bash cURL theme={null}
export ONA_HOST=https://app.ona.com
export ONA_API_KEY=<your-token>

curl --request POST \
  --url "$ONA_HOST/api/gitpod.v1.UsageService/GetAgentTraceTimeSeries" \
  --header "Authorization: Bearer $ONA_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "dateRange": {
    "endTime": "2026-01-01T00:00:00Z",
    "startTime": "2026-01-01T00:00:00Z"
  }
}'
```

```python Python theme={null}
import gitpod.v1.usage_pb2 as usage_pb2
import google.protobuf.timestamp_pb2 as timestamp_pb2
from ona_sdk import create_client_from_env

ona = create_client_from_env()
request = usage_pb2.GetAgentTraceTimeSeriesRequest(
    date_range=usage_pb2.DateRange(
        start_time=timestamp_pb2.Timestamp(seconds=1767225600),
        end_time=timestamp_pb2.Timestamp(seconds=1767225600),
    ),
)
response = ona.services.usage.get_agent_trace_time_series(request)
print(response)
```

```typescript TypeScript theme={null}
import { create } from "@bufbuild/protobuf";
import { createClientFromEnv } from "@gitpod/sdk";
import { GetAgentTraceTimeSeriesRequestSchema } from "@gitpod/sdk/gitpod/v1/usage_pb";
import { timestampFromDate } from "@bufbuild/protobuf/wkt";

async function main() {
  const ona = createClientFromEnv();
  const request = create(GetAgentTraceTimeSeriesRequestSchema, {
    dateRange: {
      startTime: timestampFromDate(new Date("2026-01-01T00:00:00Z")),
      endTime: timestampFromDate(new Date("2026-01-01T00:00:00Z")),
    },
  });
  const response = await ona.services.usage.getAgentTraceTimeSeries(request);
  console.log(response);
}

main().catch(console.error);
```

```go Go theme={null}
package main

import (
	"context"
	"fmt"
	"log"

	"connectrpc.com/connect"
	"github.com/gitpod-io/gitpod-sdk-go/sdk"
	gitpodpb "github.com/gitpod-io/gitpod-sdk-go/v1"
	timestamppb "google.golang.org/protobuf/types/known/timestamppb"
)

func main() {
	ona, err := sdk.NewFromEnv()
	if err != nil {
		log.Fatal(err)
	}

	request := connect.NewRequest(&gitpodpb.GetAgentTraceTimeSeriesRequest{
		DateRange: &gitpodpb.DateRange{
			StartTime: &timestamppb.Timestamp{Seconds: 1767225600},
			EndTime: &timestamppb.Timestamp{Seconds: 1767225600},
		},
	})
	response, err := ona.Services.Usage.GetAgentTraceTimeSeries(context.Background(), request)
	if err != nil {
		log.Fatal(err)
	}
	fmt.Println(response.Msg)
}
```

```json Request body theme={null}
{
  "dateRange": {
    "endTime": "2026-01-01T00:00:00Z",
    "startTime": "2026-01-01T00:00:00Z"
  }
}
```

## Request

`gitpod.v1.GetAgentTraceTimeSeriesRequest`

| Field | Type | Required | Description |
| - | - | - | - |
| `dateRange` | [DateRange](#type-gitpod-v1-date-range) | Yes | Date range to query within. Constraints: `required=true`. |
| `projectId` | string | No | Optional project ID to scope results. |
| `resolution` | [Resolution](#enum-gitpod-v1-resolution) | No | Time resolution for the series data. Constraints: `enum.defined_only=true`. |
| `userId` | string | No | Optional user ID to scope results to a specific user. Mutually exclusive with team\_id. |
| `teamId` | string | No | Optional team ID to scope results to a specific team. Mutually exclusive with user\_id. |

## Response

`gitpod.v1.GetAgentTraceTimeSeriesResponse`

| Field | Type | Required | Description |
| - | - | - | - |
| `timeSeries` | array of [AgentTraceTimeBucket](#type-gitpod-v1-agent-trace-time-bucket) | No | Time series of agent trace stats, bucketed by the requested resolution. |

## Related types

> [accordion] AgentTraceModelBreakdown
>
> AgentTraceModelBreakdown contains stats for a single LLM model.
>
> `gitpod.v1.AgentTraceModelBreakdown`
>
> | Field | Type | Required | Description |
> | - | - | - | - |
> | `model` | [SupportedModel](#enum-gitpod-v1-supported-model) | No | The model these stats are for. |
> | `sessions` | 64-bit integer string | No | Number of sessions that used this model. |
> | `linesAdded` | 64-bit integer string | No | Lines added by sessions using this model. |
> | `linesRemoved` | 64-bit integer string | No | Lines removed by sessions using this model. |

> [accordion] AgentTraceTimeBucket
>
> AgentTraceTimeBucket contains stats for a single time period.
>
> `gitpod.v1.AgentTraceTimeBucket`
>
> | Field | Type | Required | Description |
> | - | - | - | - |
> | `startTime` | RFC 3339 timestamp | No | Start of this time bucket. |
> | `totalSessions` | 64-bit integer string | No | Number of agent trace sessions in this bucket. |
> | `totalLinesAdded` | 64-bit integer string | No | Total lines added in this bucket. |
> | `totalLinesRemoved` | 64-bit integer string | No | Total lines removed in this bucket. |
> | `byModel` | array of [AgentTraceModelBreakdown](#type-gitpod-v1-agent-trace-model-breakdown) | No | Per-model breakdown for this bucket. |

> [accordion] DateRange
>
> DateRange specifies a time period for queries.
>
> `gitpod.v1.DateRange`
>
> | Field | Type | Required | Description |
> | - | - | - | - |
> | `startTime` | RFC 3339 timestamp | Yes | Start time of the date range (inclusive). Constraints: `required=true`. |
> | `endTime` | RFC 3339 timestamp | Yes | End time of the date range (exclusive). Constraints: `required=true`. |

> [accordion] Resolution
>
> Resolution specifies the time granularity for time series data.
>
> | Value | Number | Description |
> | - | -: | - |
> | `RESOLUTION_UNSPECIFIED` | 0 | |
> | `RESOLUTION_HOURLY` | 1 | |
> | `RESOLUTION_DAILY` | 2 | |
> | `RESOLUTION_WEEKLY` | 3 | |
> | `RESOLUTION_MONTHLY` | 4 | |

> [accordion] SupportedModel
>
> SupportedModel enumerates the LLM models available for agent executions
>
> | Value | Number | Description |
> | - | -: | - |
> | `SUPPORTED_MODEL_UNSPECIFIED` | 0 | |
> | `SUPPORTED_MODEL_SONNET_3_5` | 1 | |
> | `SUPPORTED_MODEL_SONNET_3_7` | 2 | |
> | `SUPPORTED_MODEL_SONNET_3_7_EXTENDED` | 3 | |
> | `SUPPORTED_MODEL_SONNET_4` | 4 | |
> | `SUPPORTED_MODEL_SONNET_4_EXTENDED` | 5 | |
> | `SUPPORTED_MODEL_SONNET_4_5` | 8 | |
> | `SUPPORTED_MODEL_SONNET_4_5_EXTENDED` | 9 | |
> | `SUPPORTED_MODEL_SONNET_4_6` | 18 | |
> | `SUPPORTED_MODEL_SONNET_4_6_EXTENDED` | 19 | |
> | `SUPPORTED_MODEL_SONNET_5` | 32 | |
> | `SUPPORTED_MODEL_OPUS_4` | 6 | |
> | `SUPPORTED_MODEL_OPUS_4_EXTENDED` | 7 | |
> | `SUPPORTED_MODEL_OPUS_4_5` | 14 | |
> | `SUPPORTED_MODEL_OPUS_4_5_EXTENDED` | 15 | |
> | `SUPPORTED_MODEL_OPUS_4_6` | 16 | |
> | `SUPPORTED_MODEL_OPUS_4_6_EXTENDED` | 17 | |
> | `SUPPORTED_MODEL_OPUS_4_7` | 22 | |
> | `SUPPORTED_MODEL_OPUS_4_8` | 31 | |
> | `SUPPORTED_MODEL_HAIKU_4_5` | 21 | |
> | `SUPPORTED_MODEL_OPENAI_4O` | 10 | |
> | `SUPPORTED_MODEL_OPENAI_4O_MINI` | 11 | |
> | `SUPPORTED_MODEL_OPENAI_O1` | 12 | |
> | `SUPPORTED_MODEL_OPENAI_O1_MINI` | 13 | |
> | `SUPPORTED_MODEL_OPENAI_AUTO` | 23 | SUPPORTED\_MODEL\_OPENAI\_AUTO flags a request as OpenAI-bound without encoding a specific model slug. The actual model is chosen by the client (today: native Codex via \~/.codex/config.toml) and captured from the upstream Responses-API response.model field for metering and rate-card lookup. This keeps the proto stable across OpenAI model-catalog churn. Reserved numbers 24-30 are intentionally left free for future OpenAI routing sentinels if we ever need to distinguish sub-families. |


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.