> ## Documentation Index > Fetch the complete documentation index at: https://docs.parser-app.com/llms.txt > Use this file to discover all available pages before exploring further. # Every email of a thread, in the order they arrived > The thread id is a job's `intake.email.thread_id` or an email's `thread_id`. Each email carries its outcome and job: the full story of a deal, from the submission through every reply and forward. ## OpenAPI ````yaml /openapi.json get /v1/emails/threads/{thread_id} openapi: 3.1.0 info: title: parser_backend summary: >- MCA packet parsing with GPT-6 Luna (OpenRouter), verified ledgers and underwriting metrics description: > MCA document parsing: merchant packets in (upload or email), verified bank-statement ledgers, ISO applications and underwriting metrics out. **How a packet is read** 1. *Intake* - files validated by content (PDF, PNG, JPEG), PDF safety-parsed, images converted to PDF; email attachments extracted from every MIME part. 2. *Split* - each PDF is split into documents (bank statement, merchant application, tax return, ...) by per-page classification and statement boundaries. 3. *Read* - a statement with a text layer is read by the **layout engine**: tables rebuilt from the text layer's geometry become the ledger JSON, with no model call. Pages without a text layer, and any statement whose layout read does not pass the gate, are rendered at 300 DPI and read by **GPT-6 Luna** through OpenRouter with a strict JSON schema at full image resolution (Luna's answer is the OCR): one owned page per call, neighbours as context, fanned out in parallel; the same answer categorizes every row. An image-read ledger is accepted only when a second, independent image read agrees on every amount, date and balance. 4. *Gate* - a ledger is **verified** only when it reconciles to the cent (`opening + credits - debits = closing`), reproduces the bank's printed totals and keeps every running balance chain. If it still fails after the image read it is returned as `review_required`, never as data. 5. *Categorize* - a category and counterparty per row: revenue, MCA funding / payment, loan, NSF, overdraft, returned item, transfers, payroll, taxes, ... or unknown. Image reads return them with the OCR; a layout-engine ledger goes to GPT-6 Luna once as JSON (rows grouped by description, with counts, amounts and dates). Deterministic rules cross-check every row. 6. *Aggregate* - accounts and statement months (missing months flagged); MCA and loan positions decided by GPT-6 Luna over the packet's possible financing streams and checked against the rows (cadence cross-checks); monthly summaries, and the withhold, EBITDA and revenue math. 7. *Packet* - the files are one submission (`result.submission_packet`): its typed documents in order, which ones the decision rests on and why the others are excluded (duplicates, failed or unreconciled reads, unclassified documents, another business's statement), the merchant's details with their sources, month-by-month coverage, whether the statements are one unbroken history, the balance chain across statements, undisclosed accounts and cross-document fraud signals. Every Luna call is metered (prompt, cached, completion and reasoning tokens; provider-reported cost) and every answer is replay-cached: a re-sent document or window costs nothing. **Integrating** * *Authentication*: `Authorization: Bearer ` (or `X-API-Key`) on every `/v1` route. The credential is an API key (`pk_live_...`, created with `POST /v1/api-keys`, scoped to permissions) or a WorkOS AuthKit access token (a person, with the permissions of their role). Each belongs to one tenant; jobs, caches, webhooks and settings are tenant-scoped. Errors are `{"error": {"code", "message", "request_id"}}`. * *Submit*: `POST /v1/parse` (multipart) or `POST /v1/intake/email` (raw MIME). The answer is `202` with a `job_id` and `status_url`, or the finished job when `wait` seconds suffice. Send an `Idempotency-Key` to make a retry return the same job. * *Get the result*: register a webhook once (`POST /v1/webhooks`) and receive `job.completed`, `job.review_required` or `job.failed` when each job ends, signed with the endpoint's secret; then fetch `GET /v1/jobs/{job_id}`. Or poll that route (`?wait=` long-polls). Every job ends in one of those three states, and its event is stored with it: a job that runs past `JOB_TIMEOUT_SECONDS`, or that the service stopped during too many runs, fails with its `job.failed` event. * *Status*: `completed` - every check passed; `review_required` - the result is usable but `review_reasons` name what a person should look at; `failed` - nothing could be processed (`error`). version: 0.1.0 servers: - url: https://api.parser-app.com security: [] tags: - name: parse description: Submit documents for parsing - name: email description: Submit a raw email; its attachments are parsed as one packet - name: jobs description: Poll jobs and read results - name: underwriting description: Withhold, EBITDA and capacity calculator - name: webhooks description: Signed job events pushed to your endpoint, retried until delivered - name: usage description: Token usage, cost and service metrics - name: identity description: 'Who is calling: tenant, permissions, modules' - name: tenant description: This tenant's settings - name: api-keys description: 'Scoped API keys: create, rotate, revoke' - name: mailboxes description: Forwarding addresses and Gmail mailboxes, and each message's outcome - name: emails description: 'Every inbound email tracked: its thread, raw .eml, tags and erasure' - name: integrations description: Connections to the tenant's CRM and other systems, fed by job events - name: audit description: Every change made in the tenant - name: platform description: Tenants across the platform (platform:admin) - name: health description: Liveness and readiness paths: /v1/emails/threads/{thread_id}: get: tags: - emails summary: Every email of a thread, in the order they arrived description: >- The thread id is a job's `intake.email.thread_id` or an email's `thread_id`. Each email carries its outcome and job: the full story of a deal, from the submission through every reply and forward. operationId: get_thread_v1_emails_threads__thread_id__get parameters: - name: thread_id in: path required: true schema: type: string title: Thread Id responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/EmailThreadOut' '401': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Unauthorized '403': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Forbidden '404': description: No such email (or thread) for this tenant content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - APIKeyHeader: [] - HTTPBearer: [] components: schemas: EmailThreadOut: properties: thread_id: type: string title: Thread Id emails: items: $ref: '#/components/schemas/EmailOut' type: array title: Emails description: In the order they arrived additionalProperties: false type: object required: - thread_id - emails title: EmailThreadOut ErrorResponse: properties: error: $ref: '#/components/schemas/ErrorBody' additionalProperties: false type: object required: - error title: ErrorResponse HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError EmailOut: properties: email_id: type: string title: Email Id description: 'Stable: a redelivery of the same message is the same email' thread_id: anyOf: - type: string - type: 'null' title: Thread Id description: 'Its thread: the mailbox and the thread''s root Message-ID' mailbox_id: anyOf: - type: string - type: 'null' title: Mailbox Id description: Null when posted to `/v1/intake/email` with an API key provider_message_id: type: string title: Provider Message Id description: Its Message-ID, or the provider's id for it message_id: anyOf: - type: string - type: 'null' title: Message Id description: The Message-ID header, without its angle brackets in_reply_to: anyOf: - type: string - type: 'null' title: In Reply To references: items: type: string type: array title: References description: The References header's message ids, oldest first from: anyOf: - type: string - type: 'null' title: From to: items: type: string type: array title: To cc: items: type: string type: array title: Cc subject: anyOf: - type: string - type: 'null' title: Subject received_at: type: string format: date-time title: Received At size_bytes: anyOf: - type: integer - type: 'null' title: Size Bytes description: The raw message's size attachments: items: $ref: '#/components/schemas/EmailAttachmentOut' type: array title: Attachments description: Every attachment, processable or not outcome: type: string title: Outcome description: job, merged, ignored: or refused job_id: anyOf: - type: string - type: 'null' title: Job Id description: >- The job it started or belongs to: its thread's job when it was handled routing: anyOf: - $ref: '#/components/schemas/EmailRoutingOut' - type: 'null' description: The router's verdict; null when not routed tags: items: type: string type: array title: Tags raw_stored: type: boolean title: Raw Stored description: 'Its raw .eml is kept: `GET /v1/emails/{email_id}/raw`' additionalProperties: false type: object required: - email_id - thread_id - mailbox_id - provider_message_id - message_id - in_reply_to - references - from - to - cc - subject - received_at - size_bytes - attachments - outcome - job_id - routing - tags - raw_stored title: EmailOut description: >- A tracked inbound email: its envelope and what became of it, never its body. ErrorBody: properties: code: type: string title: Code description: unauthenticated, forbidden, not_found, conflict, limit_reached, ... message: type: string title: Message request_id: type: string title: Request Id description: Also in the X-Request-ID response header additionalProperties: false type: object required: - code - message - request_id title: ErrorBody ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError EmailAttachmentOut: properties: filename: type: string title: Filename content_type: type: string title: Content Type description: As the email declared it size_bytes: type: integer title: Size Bytes sha256: type: string title: Sha256 additionalProperties: false type: object required: - filename - content_type - size_bytes - sha256 title: EmailAttachmentOut EmailRoutingOut: properties: intent: type: string enum: - new_submission - more_documents - question_or_update - internal_note - contract_or_funding - not_deal_related title: Intent confidence: type: number title: Confidence description: >- The model's own confidence in that intent, 0-1 (not a measured probability) model: type: string title: Model description: The router asked (typesafe/jev-router) served_model: anyOf: - type: string - type: 'null' title: Served Model description: The model the router chose additionalProperties: false type: object required: - intent - confidence - model title: EmailRoutingOut description: >- What TypeSafe's Jev Router decided an email is for (``EMAIL_ROUTING_API_KEY``). securitySchemes: APIKeyHeader: type: apiKey description: API key in: header name: X-API-Key HTTPBearer: type: http description: API key or AuthKit access token scheme: bearer ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.