> ## Documentation Index > Fetch the complete documentation index at: https://docs.veri.studio/llms.txt > Use this file to discover all available pages before exploring further. # Agent observability overview > Totals, a zero-filled series, live counts and top tools, agents and models over the workspace's agent conversations: managed agent sessions and external agent threads (requests sent with `X-Veri-Thread-Id`). ## OpenAPI ````yaml /api-reference/openapi.json get /v1/observability/overview openapi: 3.1.0 info: title: Veri API description: >- REST API for the Veri RL post-training platform. All requests require a Bearer API key (`vk_` prefix). license: name: '' version: 0.1.0 servers: - url: https://api.veri.studio description: Production security: [] tags: - name: Training jobs description: Create, monitor, and manage training jobs. - name: Datasets description: Upload and connect training datasets. - name: Deployments description: Serve trained models and run inference. - name: Volumes description: Persistent file storage mounted into jobs. - name: Models description: Custom model registry deployments serve from. - name: Regions description: Discover available launch regions. - name: GPU description: Live GPU availability by provider and region. - name: Code artifacts description: Upload custom training script bundles. - name: Billing description: Credit balance and transaction history. - name: API keys description: Create and revoke API keys. - name: Account description: The authenticated caller's identity. - name: Settings description: Account-level integrations (Weights & Biases). - name: Metrics description: Prometheus metrics export for your own observability stack. - name: Evaluators description: 'Evaluators: versioned scoring rules (LLM judge, code, human).' - name: Experiments description: >- Experiments: offline runs of a pinned dataset snapshot through a target, scored by pinned evaluators. - name: Annotation queues description: >- Human review: queue traces, threads and experiment items, reserve one at a time, score them and feed corrections back into datasets. - name: Monitors description: >- Monitors: evaluators scoring a sampled share of a deployment's live traffic. - name: Observability description: Agent conversations, agents and their traffic. - name: Public runs description: Unauthenticated reads of runs their owners published to Explore. paths: /v1/observability/overview: get: tags: - Observability summary: Agent observability overview description: >- Totals, a zero-filled series, live counts and top tools, agents and models over the workspace's agent conversations: managed agent sessions and external agent threads (requests sent with `X-Veri-Thread-Id`). operationId: overview parameters: - name: from in: query description: 'Window start (RFC 3339). Default: `to` minus 24 hours.' required: false schema: type: string format: date-time - name: to in: query description: 'Window end (RFC 3339). Default: now. At most 30 days after `from`.' required: false schema: type: string format: date-time - name: agent in: query description: Only this agent (its `key`). required: false schema: type: string - name: deployment_id in: query description: |- Only this deployment's threads and the sessions whose environment version serves from it. required: false schema: type: string responses: '200': description: '' content: application/json: schema: $ref: '#/components/schemas/OverviewResponse' '400': description: Bad window, or observability disabled security: - bearerAuth: [] components: schemas: OverviewResponse: type: object required: - object - from - to - interval - active - totals - series - top_tools - top_agents - top_models properties: object: type: string description: Always "observability.overview". from: type: string format: date-time to: type: string format: date-time interval: $ref: '#/components/schemas/MetricsInterval' description: |- Series bucket width, chosen from the window: five_minutes up to 6 hours, hour up to 7 days, day beyond. active: $ref: '#/components/schemas/ActiveCounts' totals: $ref: '#/components/schemas/OverviewTotals' series: type: array items: $ref: '#/components/schemas/SeriesPoint' top_tools: type: array items: $ref: '#/components/schemas/TopTool' description: Top 6 each. top_agents: type: array items: $ref: '#/components/schemas/TopAgent' top_models: type: array items: $ref: '#/components/schemas/TopModel' MetricsInterval: type: string enum: - auto - minute - five_minutes - hour - day ActiveCounts: type: object description: Conversations live now, independent of the window. required: - agents - conversations - window_minutes properties: agents: type: integer format: int64 conversations: type: integer format: int64 window_minutes: type: integer format: int64 description: |- A thread counts as active with a request in this many minutes; a session while provisioning, ready or running. OverviewTotals: type: object required: - conversations - turns - llm_calls - tool_calls - tool_errors - prompt_tokens - cached_prompt_tokens - completion_tokens - errors - error_rate - agents - flagged properties: conversations: type: integer format: int64 turns: type: integer format: int64 llm_calls: type: integer format: int64 tool_calls: type: integer format: int64 tool_errors: type: integer format: int64 prompt_tokens: type: integer format: int64 cached_prompt_tokens: type: integer format: int64 completion_tokens: type: integer format: int64 errors: type: integer format: int64 error_rate: type: number format: double description: errors / llm_calls (0 without calls). agents: type: integer format: int64 description: Agents with conversations in the window. flagged: type: integer format: int64 description: >- Scores with passed = false on trace and thread targets in the window. SeriesPoint: type: object description: One series bucket (zero-filled). required: - t - conversations - llm_calls - tool_calls - errors - prompt_tokens - completion_tokens - flagged properties: t: type: string format: date-time description: Bucket start. conversations: type: integer format: int64 description: Conversations that started in this bucket (each counted once). llm_calls: type: integer format: int64 tool_calls: type: integer format: int64 errors: type: integer format: int64 prompt_tokens: type: integer format: int64 completion_tokens: type: integer format: int64 flagged: type: integer format: int64 TopTool: type: object required: - name - calls - errors properties: name: type: string calls: type: integer format: int64 errors: type: integer format: int64 TopAgent: type: object required: - key - name - kind - conversations properties: key: type: string name: type: string kind: type: string description: managed | external conversations: type: integer format: int64 TopModel: type: object required: - name - llm_calls properties: name: type: string llm_calls: type: integer format: int64 securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API key description: API key with the `vk_` prefix. Create one from the dashboard. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.