> ## Documentation Index > Fetch the complete documentation index at: https://docs.biomni.phylo.bio/llms.txt > Use this file to discover all available pages before exploring further. # List messages > See the full back-and-forth of a Task — everything you asked and everything the agent replied, in order. Your messages come back as `role: "user"` and the agent's as `role: "assistant"`. Each agent reply is a single message whose `content[]` holds the whole reply (text, tool calls, results); a reply still in progress shows `status: "streaming"` with the content so far. **Paging.** `limit` (default 200, max 500) caps how much underlying detail is pulled — one agent reply is assembled from many small rows, so you get back far fewer messages than `limit`. When `has_more` is `true`, older detail was omitted: request the same `limit` with `offset` set to the returned `next_offset` to walk back through the history. ## OpenAPI ````yaml api-reference/openapi.json GET /messages openapi: 3.1.0 info: title: Biomni Public API — V0 description: >- The public API for **Biomni** — the AI agent platform for clinical genomics (variant annotation, ClinVar lookups, PMID-cited literature, and project file drives). Create projects and Tasks, send messages to the agent, stream its replies, manage files, and check your usage — all from your own code. **Authentication**: send `Authorization: Bearer `. The adapter forwards your key straight to Biomni; it never stores it. **Safe retries**: send `Idempotency-Key: ` on POST endpoints (`/projects`, `/tasks`, `/messages`, `/files/uploads`) so a retried request won't create a duplicate. version: 0.1.0 servers: - url: https://api.phylo.bio/api/v1 security: [] paths: /messages: get: tags: - messages summary: List messages description: >- See the full back-and-forth of a Task — everything you asked and everything the agent replied, in order. operationId: list_messages_messages_get parameters: - name: task_id in: query required: true schema: type: string title: Task Id - name: limit in: query required: false schema: type: integer maximum: 500 minimum: 1 default: 200 title: Limit - name: offset in: query required: false schema: type: integer minimum: 0 default: 0 title: Offset responses: '200': description: Aggregated message list. Alternates user/assistant. content: application/json: schema: $ref: '#/components/schemas/MessageList' example: object: list data: - id: msg_a4f9b5cc30d8 object: message task_id: sess_d9711ec9b477 created: 1779132780 role: user content: - type: text text: >- I'm a clinical genomics analyst working up Patient001. There are 3 BRCA1 pathogenic-flagged variants in the attached VCF. For each variant: describe ClinVar significance, flag PARP inhibitor eligibility, note any conflicts in the literature. Cite ClinVar VCV/RCV IDs and PMIDs. metadata: {} platform: api - id: msg_1a0ef0fa8e26 object: message task_id: sess_d9711ec9b477 created: 1779132785 role: assistant status: completed completed_at: 1779133414 content: - type: text text: >- Loaded the genetic-variant-annotation skill. For these 3 BRCA1 variants I'll (1) query ClinVar's REST API directly for each rsID to get current assertions, review status, star ratings, and conditions, and (2) cross-reference NCBI's ClinVar records for conflicting submissions and literature PMIDs. - type: tool_use id: toolu_01RkjLRcNtbVHBBwWDDk7gmF name: Skill input: action: load name: genetic-variant-annotation - type: tool_result tool_use_id: toolu_01RkjLRcNtbVHBBwWDDk7gmF content: >- # Skill: genetic-variant-annotation **Category**: genomics_genetics **Description**: Annotate genomic variants in VCF files with functional effects, clinical significance, and pathogenicity predictions. … (truncated) - type: text text: >- Here is the full structured report. Two deliverables are saved: `report_Patient001_BRCA1_variants.md` and `Patient001_BRCA1_variant_report.json`. All three variants are confirmed pathogenic by ClinVar (3-star review); PARP inhibitor eligibility applies for HBOC and ovarian indications. … (truncated; real response has 61 content blocks) metadata: {} platform: api input: user_message_id: msg_a4f9b5cc30d8 file_ids: [] has_more: false total: 2 security: - bearerAuth: [] components: schemas: MessageList: properties: object: type: string const: list title: Object default: list data: items: $ref: '#/components/schemas/Message' type: array title: Data has_more: type: boolean title: Has More default: false total: type: integer title: Total type: object required: - data - total title: MessageList Message: properties: id: type: string title: Id object: type: string const: message title: Object default: message task_id: type: string title: Task Id created: type: integer title: Created role: type: string enum: - user - assistant - system title: Role content: items: additionalProperties: true type: object type: array title: Content finish_reason: anyOf: - type: string - type: 'null' title: Finish Reason status: anyOf: - type: string enum: - pending - streaming - completed - cancelling - cancelled - failed - type: 'null' title: Status stop_reason: anyOf: - type: string enum: - stop - length - cancelled - error - type: 'null' title: Stop Reason started_at: anyOf: - type: integer - type: 'null' title: Started At completed_at: anyOf: - type: integer - type: 'null' title: Completed At error: anyOf: - type: string - type: 'null' title: Error metadata: additionalProperties: true type: object title: Metadata platform: type: string enum: - api - mcp - web - desktop - mobile title: Platform default: api input: anyOf: - additionalProperties: true type: object - type: 'null' title: Input output: anyOf: - additionalProperties: true type: object - type: 'null' title: Output _links: anyOf: - additionalProperties: true type: object - type: 'null' title: Links type: object required: - id - task_id - created - role - content title: Message securitySchemes: bearerAuth: type: http scheme: bearer description: Requires an API key. See the Authentication guide. ````