> ## Documentation Index > Fetch the complete documentation index at: https://docs.tela.com/llms.txt > Use this file to discover all available pages before exploring further. # List completion runs > Returns a paginated list of completion runs in the authenticated workspace, most recently updated first (`updatedAt` desc, then `id` desc). Rows are returned with camelCase keys (unlike the snake_case webhook payload). ## OpenAPI ````yaml GET /v1/completion-run openapi: 3.0.1 info: title: Tela API license: name: MIT version: 1.0.0 servers: - url: https://api.tela.com security: [] paths: /v1/completion-run: get: tags: - Completion Run summary: List completion runs description: > Returns a paginated list of completion runs in the authenticated workspace, most recently updated first (`updatedAt` desc, then `id` desc). Rows are returned with camelCase keys (unlike the snake_case webhook payload). When `promptApplicationId`, `promptVersionId` or `promptId` is given, the referenced resource must be accessible to the caller (404 otherwise), except when federated runs already exist for that filter. Requires the `member` role or higher; workspace-level API keys satisfy this. parameters: - name: limit in: query required: false description: Page size. Defaults to 10 and is clamped to 1–100. schema: type: integer minimum: 1 maximum: 100 default: 10 - name: offset in: query required: false description: Number of runs to skip. Defaults to 0. schema: type: integer minimum: 0 default: 0 - name: objectLinks in: query required: false description: >- When `true`, `meta.links.*` are returned as objects instead of query strings. schema: type: string enum: - 'true' - 'false' - name: promptApplicationId in: query required: false description: Restrict to runs of this Workstation/App. schema: type: string format: uuid - name: promptVersionId in: query required: false description: Restrict to runs of this Canvas version. schema: type: string format: uuid - name: promptId in: query required: false description: Restrict to runs of this Canvas (prompt). schema: type: string format: uuid - name: tags in: query required: false description: >- Tags the run must contain (all of them). JSON-encoded array (`["a","b"]`) or comma-separated list (`a,b`). schema: type: string responses: '200': description: Paginated list of completion runs content: application/json: schema: $ref: '#/components/schemas/CompletionRunListResponse' example: data: - id: b83b1558-de5b-4e45-b517-7bececbdd154 status: succeeded inputContent: variables: document: files: - file_url: https://example.com/document.pdf messages: [] files: - name: document url: https://example.com/document.pdf usedAt: variables outputContent: role: assistant content: fileSummary: >- Quarterly financial report with a 15% revenue increase. rawInput: canvas_id: 95cec438-6080-44fe-8275-28b16bd40178 version_id: 76065caa-c519-441a-8fe2-cc43e29664ab variables: document: file_url: https://example.com/document.pdf rawOutput: fileSummary: Quarterly financial report with a 15% revenue increase. compatibilityDate: '2024-10-14' metadata: promptVersion: modelConfigurations: model: gpt-4o type: chat variablesDefinitions: - name: document type: file required: true tags: - batch-1 creditsUsed: 3 promptId: 95cec438-6080-44fe-8275-28b16bd40178 promptVersionId: 76065caa-c519-441a-8fe2-cc43e29664ab promptApplicationId: null workspaceId: 3f55cfd9-4427-4887-a181-d9ad39967802 createdAt: '2024-10-14T19:00:53.664Z' updatedAt: '2024-10-14T19:01:15.892Z' deletedAt: null meta: totalCount: 1 limit: 10 offset: 0 currentPage: 1 totalPages: 1 links: first: >- ?promptVersionId=76065caa-c519-441a-8fe2-cc43e29664ab&limit=10&offset=0 last: >- ?promptVersionId=76065caa-c519-441a-8fe2-cc43e29664ab&limit=10&offset=0 next: null previous: null '400': description: Invalid query content: application/json: schema: $ref: '#/components/schemas/Error' '401': description: Missing or invalid API key content: application/json: schema: $ref: '#/components/schemas/Error' '403': description: The caller's role is below `member` content: application/json: schema: $ref: '#/components/schemas/Error' '404': description: >- The referenced app, Canvas version or Canvas was not found or is not accessible content: application/json: schema: $ref: '#/components/schemas/Error' security: - bearerAuth: [] components: schemas: CompletionRunListResponse: type: object properties: data: type: array items: $ref: '#/components/schemas/CompletionRun' meta: $ref: '#/components/schemas/TaskPaginationMeta' required: - data - meta Error: {} CompletionRun: type: object title: Completion run description: A single execution of a Canvas version. Keys are camelCase. properties: id: type: string format: uuid status: type: string enum: - created - failed - running - succeeded inputContent: $ref: '#/components/schemas/TaskInputContent' outputContent: type: object nullable: true additionalProperties: true description: >- The assistant message produced by the run (`role`, `content`, …), or the workflow response. rawInput: $ref: '#/components/schemas/TaskRawInput' rawOutput: type: object nullable: true additionalProperties: true compatibilityDate: type: string format: date nullable: true metadata: $ref: '#/components/schemas/CompletionRunMetadata' tags: type: array items: type: string creditsUsed: type: integer nullable: true promptId: type: string format: uuid nullable: true promptVersionId: type: string format: uuid nullable: true promptApplicationId: type: string format: uuid nullable: true workspaceId: type: string format: uuid createdAt: type: string format: date-time updatedAt: type: string format: date-time deletedAt: type: string format: date-time nullable: true required: - id - status - tags - workspaceId - createdAt - updatedAt TaskPaginationMeta: type: object title: Pagination metadata properties: totalCount: type: integer limit: type: integer offset: type: integer currentPage: type: integer totalPages: type: integer lastReference: type: integer description: >- Highest `reference` among the app's/agent's non-deleted tasks (`0` when neither `promptApplicationId` nor `agentId` was given). Only present on `GET /task`. links: type: object description: >- Links to other pages. Query strings (e.g. `?promptApplicationId=…&limit=10&offset=10`) by default, or objects (`{ ...filters, limit, offset }`) when `objectLinks=true`. properties: first: oneOf: - type: string - type: object additionalProperties: true last: oneOf: - type: string - type: object additionalProperties: true next: nullable: true oneOf: - type: string - type: object additionalProperties: true previous: nullable: true oneOf: - type: string - type: object additionalProperties: true required: - first - last - next - previous required: - totalCount - limit - offset - currentPage - totalPages - links TaskInputContent: type: object nullable: true title: Input content description: >- Normalized input of the execution. `null` until the run has been prepared. properties: variables: type: object additionalProperties: $ref: '#/components/schemas/TaskInternalVariableContent' messages: type: array items: $ref: '#/components/schemas/TaskMessage' files: type: array items: $ref: '#/components/schemas/TaskInputFile' TaskRawInput: type: object nullable: true title: Raw input description: >- The completion request the task is executed with. Same shape as the `/v2/chat/completions` body; `application_id` is set by the server from `promptApplicationId`. properties: application_id: type: string format: uuid description: >- Set by the server; any value you send is overwritten with `promptApplicationId`. canvas_id: type: string format: uuid version_id: type: string format: uuid environment_name: type: string variables: type: object description: >- Variables keyed by the app's variable names. Files are passed here (see `TaskVariableValue`). additionalProperties: $ref: '#/components/schemas/TaskVariableValue' messages: type: array items: $ref: '#/components/schemas/TaskMessage' input: type: string webhook_url: type: string description: URL that receives a POST when the execution finishes. override: $ref: '#/components/schemas/Override' stream: type: boolean async: type: boolean long_response: type: boolean label: type: string tags: type: array items: type: string CompletionRunMetadata: type: object nullable: true properties: requestedEnvironmentName: type: string promptVersion: type: object description: Snapshot of the Canvas version used for the run. properties: modelConfigurations: type: object additionalProperties: true variablesDefinitions: type: array items: type: object properties: id: type: string name: type: string type: type: string enum: - file - text - mixed required: type: boolean description: type: string processingOptions: type: object properties: allowMultimodal: type: boolean content: type: string required: - name - type - required resourceContext: $ref: '#/components/schemas/TaskResourceContext' TaskInternalVariableContent: description: >- Normalized variable value as stored on the task. A string, `{ files: [...] }`, or `{ text, files }` (a single file object is normalized into `files`). oneOf: - type: string - type: object properties: files: type: array items: $ref: '#/components/schemas/TaskVariableFile' required: - files - type: object properties: text: oneOf: - type: string - type: object additionalProperties: type: string files: type: array items: $ref: '#/components/schemas/TaskVariableFile' required: - text - files TaskMessage: type: object properties: role: type: string content: description: A string, a single content part, or an array of content parts. oneOf: - type: string - $ref: '#/components/schemas/TaskMessageContentPart' - type: array items: $ref: '#/components/schemas/TaskMessageContentPart' function_call: type: object properties: name: type: string arguments: type: string required: - name - arguments required: - role - content TaskInputFile: type: object description: >- A file that took part in the execution, either from a variable (`usedAt: variables`) or from a message (`usedAt: messages`). properties: name: type: string description: Variable name, or `message-{index}` for files found in messages. type: type: string usedAt: type: string enum: - variables - messages url: type: string mimeType: type: string jobId: type: string description: Parser job identifier, when the file was parsed. filename: type: string pages: type: number parserData: type: object additionalProperties: true description: Parser result payload (structure not documented here). filePagesAsImage: type: array items: type: string TaskVariableValue: description: >- Value of a variable when creating a task. A string for text variables; a file object for a single file; `{ files: [...] }` for several files; `{ text, files }` for mixed content. oneOf: - type: string title: Text - $ref: '#/components/schemas/TaskVariableFile' - type: object title: Files properties: files: type: array items: $ref: '#/components/schemas/TaskVariableFile' required: - files - type: object title: Mixed properties: text: oneOf: - type: string - type: object additionalProperties: type: string files: type: array items: $ref: '#/components/schemas/TaskVariableFile' required: - text - files Override: type: object description: >- Override default settings specified in the canvas. This allows for fine-tuning the completion behavior for this specific request. properties: model: type: string description: >- The specific model to use for this completion. If not specified, the default model set in the canvas will be used. temperature: type: number description: >- Controls randomness in the output. Values between 0 and 1. Lower values make the output more focused and deterministic. type: type: string enum: - chat - completion description: Specifies whether to use a chat or completion model. functions: type: array items: type: object properties: id: type: string name: type: string description: type: string parameters: type: object properties: type: type: string enum: - object properties: type: object additionalProperties: true required: type: array items: type: string description: >- An array of functions that the model can call. This allows for more structured and interactive completions. structured_output: type: object properties: enabled: type: boolean description: Whether to enable structured output for this completion. schema: type: object properties: properties: type: object additionalProperties: true description: Defines the properties of the structured output type: type: string enum: - object description: >- The type of the schema, always "object" for structured output title: type: string description: The title of the schema description: type: string description: A description of the schema required: type: array items: type: string description: An array of required property names description: >- The schema defining the structure of the output. This is used when structured output is enabled. description: Configuration for generating structured output. required: - type TaskResourceContext: type: object description: >- Set by the server on tasks that run against a resource shared from another workspace (federated). Client-supplied values are discarded. properties: isFederated: type: boolean entitlementId: type: string nullable: true executionWorkspaceId: type: string billingWorkspaceId: type: string resourceWorkspaceId: type: string credentialWorkspaceId: type: string projectId: type: string nullable: true TaskVariableFile: type: object title: File properties: file_url: type: string description: Publicly reachable URL or a `vault://` reference of the file. file_name: type: string mime_type: type: string vault_reference: type: string options: type: object properties: range: type: array description: Page range to process (e.g. for PDFs). items: type: number required: - file_url TaskMessageContentPart: oneOf: - type: object title: Text part properties: type: type: string enum: - text text: type: string required: - type - text - type: object title: Image part properties: type: type: string enum: - image_url image_url: type: object properties: url: type: string detail: type: string enum: - auto - high - low required: - url required: - type - image_url securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT or UUID ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.