> ## 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. # List conversations > Threads and sessions with activity in the window, newest activity first, keyset paged with `after` = the previous page's `next_cursor`. ## OpenAPI ````yaml /api-reference/openapi.json get /v1/observability/conversations 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/conversations: get: tags: - Observability summary: List conversations description: >- Threads and sessions with activity in the window, newest activity first, keyset paged with `after` = the previous page's `next_cursor`. operationId: conversations 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.' 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 required: false schema: type: string - name: kind in: query description: session | thread required: false schema: type: string - name: active in: query description: Only conversations live now. required: false schema: type: boolean - name: errors_only in: query description: Only conversations with errors. required: false schema: type: boolean - name: q in: query description: Case-insensitive substring of the title, preview or thread id. required: false schema: type: string - name: limit in: query description: Page size, 1..=100 (default 50). required: false schema: type: integer format: int64 - name: after in: query description: '`next_cursor` of the previous page.' required: false schema: type: string - name: evaluator in: query description: |- Score filter: only threads with an ok score of this evaluator (id or name; any evaluator when omitted) matching every given bound. Sessions never match a score filter. required: false schema: type: string - name: label in: query description: |- Score filter: a categorical label, or `true` / `false` for a boolean score. required: false schema: type: string - name: min_score in: query description: |- Score filter: inclusive lower bound on the numeric value (a Jev noul score's P(yes)). required: false schema: type: number format: double - name: max_score in: query description: |- Score filter: inclusive upper bound on the numeric value (a Jev noul score's P(yes)). required: false schema: type: number format: double - name: min_confidence in: query description: 'Score filter: inclusive lower bound on the judge''s confidence, 0..1.' required: false schema: type: number format: double - name: max_confidence in: query description: |- Score filter: inclusive upper bound on the judge's confidence, 0..1 (the dashboard's "needs review" view uses 0.5). required: false schema: type: number format: double responses: '200': description: '' content: application/json: schema: $ref: '#/components/schemas/ConversationList' '400': description: Bad window, filter or cursor, or observability disabled security: - bearerAuth: [] components: schemas: ConversationList: type: object required: - object - has_more - data properties: object: type: string description: Always "list". has_more: type: boolean next_cursor: type: - string - 'null' description: Pass as `after` for the next page; null on the last page. data: type: array items: $ref: '#/components/schemas/Conversation' Conversation: type: object required: - id - kind - agent - status - turns - llm_calls - tool_calls - tool_errors - errors - prompt_tokens - cached_prompt_tokens - completion_tokens - started_at - last_activity_at - span_strip - scores properties: id: type: string description: The session id, or `{deployment_id}:{thread_id}`. kind: type: string description: session | thread title: type: - string - 'null' preview: type: - string - 'null' description: The first user message (200 chars). agent: $ref: '#/components/schemas/AgentRef' deployment_id: type: - string - 'null' thread_id: type: - string - 'null' session_id: type: - string - 'null' environment_id: type: - string - 'null' status: type: string description: 'thread: active | idle. session: active | paused | ended | failed.' turns: type: integer format: int64 llm_calls: type: integer format: int64 tool_calls: type: integer format: int64 tool_errors: type: integer format: int64 errors: type: integer format: int64 prompt_tokens: type: integer format: int64 cached_prompt_tokens: type: integer format: int64 completion_tokens: type: integer format: int64 cost_usd: type: - number - 'null' format: double description: 'Sessions: charged so far. Threads: null.' started_at: type: string format: date-time last_activity_at: type: string format: date-time span_strip: type: array items: $ref: '#/components/schemas/Span' description: Ordered, the most recent 60. scores: $ref: '#/components/schemas/ScoreSummary' AgentRef: type: object description: Who a conversation belongs to. required: - key - name - kind properties: key: type: string description: |- `env:` (managed), `agent:`, or `deployment:` for threads sent without an agent name. name: type: string kind: type: string description: managed | external Span: type: object description: 'One timeline segment: a model call or the tool work between two calls.' required: - kind - ms properties: kind: type: string description: llm | tool ms: type: integer format: int64 ScoreSummary: type: object required: - total - failed - evaluators properties: total: type: integer format: int64 failed: type: integer format: int64 description: Scores with passed = false. evaluators: type: array items: type: string description: Distinct evaluator names (at most 5). 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.