> ## Documentation Index > Fetch the complete documentation index at: https://docs.stefanbrain.com/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > Follow the content contract in AGENTS.md. > Treat text as the canonical explanation; video and screenshots enhance it. > Do not publish unverified product behavior or duplicate an existing canonical article. # Tell StefanBrain where the API got in your way > For agents first: when an endpoint or MCP tool fails, returns the wrong thing, answers with an error that does not say how to fix it, or lacks something you need, send one report per problem while you still have the request, the error code and the id. The StefanBrain team reads every report and replies; read the reply with GET /v1/feedback/{feedbackId}. Replies to recent reports also arrive in the MCP server instructions when the account next connects. Free (never billed), 60 reports an hour per account, any key scope. Intake coerces instead of refusing: long text is trimmed, an unknown category is filed as other, a credential-looking value is redacted, unrecognized fields are kept, and `adjustments` says what changed. Only a report with no text is refused. ## OpenAPI ````yaml /developers/openapi/stefanbrain-v1.json post /api/developers/v1/feedback openapi: 3.1.0 info: title: StefanBrain Developer API version: 1.0.0 description: >- REST access to StefanBrain agent runs, tools, and jobs. Authenticate with an API key from Settings → Developers. REST usage bills your prepaid API wallet at the published per-token rates (see https://docs.stefanbrain.com/developers/pricing); the MCP endpoint (/api/developers/v1/mcp, not described here) is member pricing from your plan pool. Human documentation: https://docs.stefanbrain.com/developers servers: - url: https://stefanbrain.com security: - bearerAuth: [] - apiKeyHeader: [] tags: - name: tools description: Directly invocable StefanBrain tools. - name: jobs description: Long-running tool jobs (poll for results). - name: runs description: Agentic chat runs with event streams. - name: files description: Workspace files agent runs produced in a chat. - name: media description: 'Stored Meta ad media facts: video transcripts on demand.' - name: feedback description: >- Tell StefanBrain where the API got in your way, and read the team's replies. paths: /api/developers/v1/feedback: post: tags: - feedback summary: Tell StefanBrain where the API got in your way description: >- For agents first: when an endpoint or MCP tool fails, returns the wrong thing, answers with an error that does not say how to fix it, or lacks something you need, send one report per problem while you still have the request, the error code and the id. The StefanBrain team reads every report and replies; read the reply with GET /v1/feedback/{feedbackId}. Replies to recent reports also arrive in the MCP server instructions when the account next connects. Free (never billed), 60 reports an hour per account, any key scope. Intake coerces instead of refusing: long text is trimmed, an unknown category is filed as other, a credential-looking value is redacted, unrecognized fields are kept, and `adjustments` says what changed. Only a report with no text is refused. operationId: sendFeedback requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/FeedbackRequest' responses: '201': description: The stored report, with what happens next in `guidance`. content: application/json: schema: $ref: '#/components/schemas/FeedbackReceipt' '400': description: >- No report text (code invalid_feedback; the message shows a valid body), or a body that is not a JSON object (code invalid_json). content: application/json: schema: $ref: '#/components/schemas/Error' '401': description: Missing, invalid, or revoked API key. content: application/json: schema: $ref: '#/components/schemas/Error' '403': description: >- Suspended key (code api_key_suspended) or no active StefanBrain plan or trial (code developer_access_forbidden). Every key scope may use feedback. content: application/json: schema: $ref: '#/components/schemas/Error' '413': description: A body over 256 KB (code request_too_large). content: application/json: schema: $ref: '#/components/schemas/Error' '429': description: >- More than 60 reports in the last hour (code feedback_rate_limited, Retry-After header), or the request rate limits every authenticated call shares. content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: FeedbackRequest: type: object required: - summary properties: summary: type: string description: >- One line: what went wrong, or what you needed. If omitted, the first line of details is used. Up to 300 characters; longer text is trimmed. category: type: string enum: - bug - docs - confusing - missing_feature - performance - other default: other description: >- bug (something broke or returned the wrong result); docs (the docs were missing, wrong, or unclear); confusing (it worked, but a name, parameter, or error message misled you); missing_feature (you needed something the API does not do); performance (too slow, timed out, or rate-limited sooner than expected); other (anything else). An unknown value is filed as other. impact: type: string enum: - blocked - worked_around - minor description: >- blocked (you could not finish the task); worked_around (you finished, but had to work around it); minor (small friction). An unknown value is left empty. details: type: string description: >- What you tried, what you expected and what happened: the call and the error text. Up to 8,000 characters; longer text is trimmed. suggestion: type: string description: >- What would have helped: a parameter, a clearer error, a doc line. Up to 2,000 characters; longer text is trimmed. endpoint: type: string description: >- The REST endpoint, e.g. "POST /api/developers/v1/runs". Up to 300 characters; longer text is trimmed. tool: type: string description: >- The MCP tool, e.g. "ask_stefanbrain". Up to 120 characters; longer text is trimmed. error_code: type: string description: >- The error code you got, e.g. "invalid_output_config". Up to 120 characters; longer text is trimmed. request_id: type: string description: >- The req_, run_, job_ or chat_ id of the call that failed. Up to 120 characters; longer text is trimmed. agent: type: string description: >- Your agent or client and its version, e.g. "Claude Code 2.1". Up to 200 characters; longer text is trimmed. additionalProperties: true FeedbackReceipt: allOf: - $ref: '#/components/schemas/Feedback' - type: object required: - guidance properties: guidance: type: string description: What happens next and where the reply will be. Error: type: object required: - error properties: error: type: object required: - message - type properties: message: type: string type: type: string enum: - invalid_request_error - authentication_error - permission_error - rate_limit_error - api_error - service_unavailable_error code: type: string additionalProperties: true additionalProperties: true Feedback: type: object description: One report and, once there is one, the StefanBrain team's reply. required: - object - id - status - category - summary - adjustments - created_at - updated_at properties: object: type: string const: feedback id: type: string description: fb_ id. status: type: string enum: - open - acknowledged - resolved - wont_fix category: type: string enum: - bug - docs - confusing - missing_feature - performance - other impact: type: - string - 'null' enum: - blocked - worked_around - minor - null summary: type: string details: type: - string - 'null' suggestion: type: - string - 'null' endpoint: type: - string - 'null' tool: type: - string - 'null' error_code: type: - string - 'null' request_id: type: - string - 'null' agent: type: - string - 'null' adjustments: type: array items: type: string description: >- What intake changed: a trimmed field, an unknown category filed as other, a redacted value. reply: type: - string - 'null' description: The team's reply; null until there is one. replied_at: type: - string - 'null' format: date-time created_at: type: string format: date-time updated_at: type: string format: date-time additionalProperties: true securitySchemes: bearerAuth: type: http scheme: bearer description: >- Authorization: Bearer stefan_sk_... (API key — bills the API wallet) or stefan_oat_... (OAuth member token — bills your plan pool). apiKeyHeader: type: apiKey in: header name: x-api-key ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.