> ## Documentation Index > Fetch the complete documentation index at: https://docs.getoneprofile.ai/llms.txt > Use this file to discover all available pages before exploring further. # Resume the follow-ups a reply the AI could not read stopped > Resume follow-ups on a conversation's "Couldn't read this reply" card, for a person who read the reply and wants the sequence to go on. Every sequence that stopped the contact for it (`stop_reason` `unread_reply`) picks up at the step it kept. The card stays while the AI has not read the reply, so Try again is still there. A contact stopped for anything else is untouched. With `dry_run` it makes the same checks and answers the conversation as Resume would leave it, resuming nothing. ## OpenAPI ````yaml /openapi.json post /inbox/threads/{thread_id}/unread-reply/resume/ openapi: 3.1.0 info: contact: email: support@getoneprofile.ai name: Oneprofile Support description: >- REST API reference for Oneprofile, the GTM data layer for your CRM. Manage tables, enrichments, and integrations. Authenticate with an API key to get started. termsOfService: https://www.getoneprofile.ai/terms title: API Reference | Oneprofile version: '0.0' servers: - url: https://api.getoneprofile.ai security: [] tags: - description: >- The docked AI Assistant: its general chat about the workspace and the product, streamed as Server-Sent Events, and the one list of a person's threads across every assistant, with pin, rename, delete and the search-to-table link. name: assistant - description: >- The messages a person keeps to send the assistant again: the ones the workspace saved and the ones that ship with the product, with save, rename, edit and delete. name: assistant-prompt - description: >- Granted workspace actions: what the AI Assistant proposed or applied in a conversation, the approve and dismiss decisions on each card, the workspace's spend threshold and default grants, and the eight verbs. name: workspace-actions - description: >- The Getting started checklist: a workspace's progress through the six steps from its first people search to its first launched sequence. name: onboarding - description: Senders, connected mailboxes, tags, and the Google connect flow. name: senders - description: The workspace do-not-contact list, enforced before every send. name: suppression - description: >- The workspace's recontact rule: how long before anyone hears from us again. name: contact_cooldown - description: 'Sequence authoring: the graph, the table-backed audience, previews.' name: sequences - description: >- The outbound agent behind a sequence: the voice it writes in, its per-message prompts, what it wrote and what people told it. name: outbound-agents - description: >- The LinkedIn channel: connecting an account to a sender, its safety limits and history, and the protocol the browser extension speaks. name: linkedin - description: >- The approval queue: everything waiting on a person across every sender and channel, and the workspace's manual or automatic modes per channel. name: outreach - description: 'The unified outreach inbox: threads, replies, labels, events.' name: inbox - description: 'The AI reply layer: workspace settings, drafts, and approval.' name: inbox-ai - description: Notification rules, per-user preferences, and the Slack connection. name: notifications - description: Endpoints for seeing all available integration types. name: integration-types - description: Endpoints for creating and managing integrations. name: integrations - description: Endpoints for the generic OAuth install/claim app-listings engine. name: app-listings - description: Endpoints for creating and managing API keys. name: apikey - description: >- AI apps connected to the workspace: Claude, ChatGPT, Claude Code or any other MCP client a person signed in to Oneprofile's MCP server with. name: ai_apps - description: Endpoints for managing billing and subscription information. name: billing - description: Endpoints for creating and managing tables. name: tables - description: Endpoints for table columns, formula previews, and on-demand column runs. name: table-columns - description: Endpoints for table rows and manual cell edits. name: table-rows - description: Endpoints for observing and cancelling table recompute runs. name: table-runs - description: >- Endpoints for org-shared per-column display preferences: hidden, pinned, width, and colour tint. name: table-ui-prefs - description: >- Endpoints for the org-shared names given to the column tint palette: what this organisation calls each colour. Org-level, not per-table. name: table-column-color-labels - description: >- Endpoints for the enrichment action catalog, model list, presets, draft generation, and saved agents. name: table-enrichments - description: >- Endpoints for an agent's Preview: example rows run one at a time, and a Looks good on each. Needs work lives under agent-learnings. name: agent-training - description: >- An agent's learnings, the one-line rules it follows on every output, and the thumbs down that teaches them: give one with what was wrong, list the ones on a subject, Undo one, and price the redo it would run. name: agent-learnings - description: >- The durable audit trail of a table's enrichment actions: configured, edited, run, cancelled, and settled cost. name: table-enrichment-audit-logs - description: Endpoints for saving and applying column templates. name: table-templates - description: Server-sent change feed for a table's grid. name: table-events - description: 'Endpoints for org-shared saved table views: sort, filters, hidden columns.' name: table-views - description: >- Endpoints for PER-USER table preferences: favourites and recently opened. Unlike the rest of the table surface these are personal, so two members of one organisation legitimately see different answers. name: table-user-prefs - description: >- Endpoints for building a table from an uploaded CSV: upload and preview the inferred columns, commit the reviewed mapping, then poll the row load. name: table-imports - description: Endpoint for downloading a table's rows as CSV. name: table-export - description: >- Endpoints for the integration a table imports from: attach and preview it, promote imported fields into columns, and run the import on demand. name: table-sources - description: >- Endpoints for a table's recurring import cadence: set it, pause it, and read the next fire times. name: table-schedules - description: >- Endpoints for pushing a table's rows out to a connected integration: list writable destinations, derive their write capabilities, and map export columns. name: table-writeback - description: >- Endpoints backing a lookup column's setup: the connections whose records a column could read, and the identity fields one record type can be looked up by. name: table-integration-lookup - description: >- Endpoints for sourcing leads from the lead database: count and preview matches, land them in a table, and keep saved searches. Alongside people and company searches, leads can be sourced from buying signals (what a company or person just did), with a catalogue endpoint behind the picker that builds them. name: find-leads - description: >- Endpoints for discovering a domain's subdomains from public certificate logs and landing the results in a table. name: find-subdomains - description: Endpoints for the credit balance meter and usage reporting. name: credits - description: >- Endpoints for the workspace referral program: the shareable link, the friends who joined through it, and claiming a code after signup. name: referral - description: >- Endpoints for the affiliate program's own dashboard: enrolling and claiming a code, the summary, stats and activity feed, the commission ledger, and identity verification and payouts. name: affiliate - description: >- Endpoints for recording where a new workspace came from: the marketing page or campaign its signup link carried, sent once after signup. name: attribution - description: >- Endpoints for the design partner program's customer surface: whether this workspace is a design partner, the badges its feedback has earned, and sending and reading that feedback. name: design-partner - description: >- Endpoints for the org-level AI business context (company description, ideal customer profile, buyer personas, interest signals and social proof), plus domain-based generation and the reference documents whose summaries ride alongside those fields. name: ai-context - description: >- Endpoints for the signed-in user's Google Drive connection: starting and finishing the OAuth grant, checking or dropping it, and minting the short-lived token the Google Picker needs. name: google-drive paths: /inbox/threads/{thread_id}/unread-reply/resume/: post: tags: - inbox summary: Resume the follow-ups a reply the AI could not read stopped description: >- Resume follow-ups on a conversation's "Couldn't read this reply" card, for a person who read the reply and wants the sequence to go on. Every sequence that stopped the contact for it (`stop_reason` `unread_reply`) picks up at the step it kept. The card stays while the AI has not read the reply, so Try again is still there. A contact stopped for anything else is untouched. With `dry_run` it makes the same checks and answers the conversation as Resume would leave it, resuming nothing. operationId: resume_after_unread_reply parameters: - in: path name: thread_id required: true schema: format: uuid title: Thread Id type: string - description: >- Answer the conversation as Resume would leave it, and change nothing. in: query name: dry_run required: false schema: default: false description: >- Answer the conversation as Resume would leave it, and change nothing. title: Dry Run type: boolean responses: '200': content: application/json: schema: $ref: '#/components/schemas/ThreadReadSchema' description: Successful Response '401': content: application/json: schema: $ref: '#/components/schemas/UnauthorizedResponse' description: Unauthorized '403': content: application/json: schema: $ref: '#/components/schemas/ForbiddenResponse' description: Forbidden '404': content: application/json: schema: $ref: '#/components/schemas/NotFoundResponse' description: Not found. '409': description: Nothing this reply stopped is still stopped for it. '422': content: application/json: schema: $ref: '#/components/schemas/UnprocessableEntityResponse' description: Invalid request made to the API. '500': content: application/json: schema: $ref: '#/components/schemas/ServerErrorResponse' description: Internal server error. '502': content: application/json: schema: $ref: '#/components/schemas/ServerErrorResponse' description: Bad gateway error. '503': content: application/json: schema: $ref: '#/components/schemas/ServerErrorResponse' description: Service unavailable. security: - APIKeyHeader: [] - HTTPBearer: [] components: schemas: ThreadReadSchema: properties: blocked_reply: anyOf: - $ref: '#/components/schemas/ThreadBlockedReplySchema' - type: 'null' description: >- The conversation's newest reply, which its sequence's agent would answer and wrote no draft for, and why, while nothing of ours answered it and no `question_card` asks instead: the conversation says "No draft for this reply", and `POST /inbox/threads/{thread_id}/blocked-reply/retry/` has the agent write it now. Only the single-thread read sets it; the list leaves it null. came_back: description: >- Back in the Inbox because our answer went three business days unanswered: `returns_at` has passed. title: Came Back type: boolean can_reply_on_linkedin: default: false description: >- Whether an explicit channel='linkedin' reply can go out on this thread, because it carries a LinkedIn member identity and a paired account. The composer's channel toggle keys off this. title: Can Reply On Linkedin type: boolean channel: $ref: '#/components/schemas/InboxChannel' contact_email: anyOf: - type: string - type: 'null' title: Contact Email contact_key: title: Contact Key type: string contact_linkedin_url: anyOf: - type: string - type: 'null' description: >- The contact's LinkedIn profile URL, when our own evidence (invitation ledger, dispatched actions, or the sequence's mapped column) names one. Only the SINGLE-thread read resolves it; the list leaves it null. title: Contact Linkedin Url contact_name: title: Contact Name type: string contact_replied: anyOf: - type: boolean - type: 'null' description: >- Whether the contact has written back in this thread: a person's reply, never an auto-reply, a bounce or a robot's acknowledgement. False on a send nobody answered, which the working views never list. Only the thread LIST populates it; single-thread reads leave it null. title: Contact Replied contact_status_live: default: false description: >- Whether the contact is still moving through the sequence (their word is one of the Audience tab's In progress words), so its follow-ups may still go out. False when it is waiting on an approval, paused, done or blocked, and on the list, which never resolves it. title: Contact Status Live type: boolean contact_status_word: anyOf: - type: string - type: 'null' description: >- The contact's status in this thread's sequence, in the word the sequence's Audience tab shows for them (Finished, Failed, Paused, Replied, In progress, Needs approval...). Set with enrolment_id; only the SINGLE-thread read resolves it, the list leaves it null. title: Contact Status Word created_at: format: date-time title: Created At type: string done_at: anyOf: - format: date-time type: string - type: 'null' description: >- When a person marked the conversation done. `is_done` says whether the mark still holds. title: Done At enrolment_id: anyOf: - format: uuid type: string - type: 'null' description: >- The contact's enrolment in this thread's sequence, when it has one: the id the 'Resume cadence' action targets. title: Enrolment Id follow_up_expected: description: >- Whether an answer of ours they leave unanswered would come back to the Inbox: the contact has written, and the verdict on their latest reply, by the classifier or a label a person set, does not say the conversation is over. title: Follow Up Expected type: boolean has_open_questions: default: false description: >- The agent asks questions before it answers a reply here, so the conversation waits in Needs approval. Only the thread LIST populates it; single-thread reads leave it False and carry `question_card` instead. title: Has Open Questions type: boolean has_pending_draft: default: false description: >- An AI reply is waiting for approval on this thread: the list row's 'Action required' mark. Only the thread LIST populates it; single-thread reads leave it False and the open conversation fetches the draft itself. title: Has Pending Draft type: boolean id: format: uuid title: Id type: string is_bounce: title: Is Bounce type: boolean is_done: description: >- Marked done, and no new message has reached us since: out of the Inbox. Their reply, or an answer of ours, arriving after the mark ends it, whatever time the message gives itself; an auto-reply, a bounce, a forward or a reply still waiting on Tasks does not. title: Is Done type: boolean is_out_of_office: title: Is Out Of Office type: boolean is_unread: title: Is Unread type: boolean label_ids: items: format: uuid type: string title: Label Ids type: array last_message_at: format: date-time title: Last Message At type: string last_snippet: title: Last Snippet type: string linkedin_account_status: anyOf: - $ref: '#/components/schemas/LinkedInAccountStatus' - type: 'null' description: >- The pairing state of the LinkedIn account this thread replies from. Anything but 'active' blocks queueing a LinkedIn reply: 'revoked' was disconnected and 'pending' never bound a member. Only the SINGLE-thread read resolves it; the list leaves it null, as does a thread with no LinkedIn account or one whose account row is gone. linkedin_checkpoint_status: anyOf: - $ref: '#/components/schemas/LinkedInCheckpointStatus' - type: 'null' description: >- Whether LinkedIn is currently challenging that account. Single-thread read only; the list leaves it null. linkedin_last_seen_at: anyOf: - format: date-time type: string - type: 'null' description: >- When a browser on that account last checked in; null when none ever has. Single-thread read only; the list leaves it null. title: Linkedin Last Seen At linkedin_presence: anyOf: - $ref: '#/components/schemas/LinkedInPresence' - type: 'null' description: >- How recently a browser on that account checked in: active, idle or not seen. Carried beside the status rather than blanked for a non-active account (the senders list does that), because the composer shows the two as separate facts. Single-thread read only; the list leaves it null. linkedin_queue_expiry_days: anyOf: - type: integer - type: 'null' description: >- Always null. The wait window was retired: a queued LinkedIn reply now waits for a person, or for a browser, without expiring. The field stays so older clients still find it; a null hides the composer's sentence about it. title: Linkedin Queue Expiry Days linkedin_sender_profile_id: anyOf: - format: uuid type: string - type: 'null' description: >- The sender the LinkedIn account belongs to, so the composer can send a person to that sender's LinkedIn tab to reconnect. Single-thread read only; the list leaves it null. title: Linkedin Sender Profile Id listed_at: description: >- The moment the list sorts this conversation by: its last message, or later when a reminder went off or, on the Inbox's own views, when it came back from silence. The time to show beside the row. format: date-time title: Listed At type: string mailbox_id: anyOf: - format: uuid type: string - type: 'null' title: Mailbox Id match_excerpt: anyOf: - type: string - type: 'null' description: >- The matched message, headlined around the match. Only set when searching. title: Match Excerpt message_count: title: Message Count type: integer pending_draft_id: anyOf: - format: uuid type: string - type: 'null' description: >- Which AI reply waits for approval here, by its draft id: what a bulk Approve and send names, so the reply it sends is the one that was read. Only the thread LIST populates it, like `has_pending_draft`. title: Pending Draft Id question_card: anyOf: - $ref: '#/components/schemas/ThreadQuestionCardSchema' - type: 'null' description: >- What the agent needs before it answers the conversation's newest reply it could not answer alone, while nobody answered it, the contact did not write again and the agent still writes replies to it: "Before I answer, I need to know" with a box per question, or the reason a person must answer. Only the single-thread read sets it; the list leaves it null. returns_at: anyOf: - format: date-time type: string - type: 'null' description: >- When this conversation comes back to the Inbox if the contact stays quiet: three business days after our latest answer, at the same time of day, counted in the sender's timezone. In the past once it has come back (`came_back`). Null when it will not: they have the last word, the verdict on their latest reply, by the classifier or a label a person set, says the conversation is over (Negative, Meeting booked, Meeting completed, Closed or Wrong contact), or it is done. title: Returns At rewriting_draft: anyOf: - $ref: '#/components/schemas/ThreadRewritingDraftSchema' - type: 'null' description: >- The reply a sequence's agent wrote, retired to be written again (a Needs work, or Write again), while it is the conversation's newest draft: nothing was written in its place yet, or the rewrite wrote nothing usable. Its thumbs-down event says which. Only the single-thread read sets it; the list leaves it null. sequence_id: anyOf: - format: uuid type: string - type: 'null' description: >- The sequence the conversation is filed under: the one its newest reply answers, else the first that wrote to the contact. title: Sequence Id snoozed_until: anyOf: - format: date-time type: string - type: 'null' description: Hidden from the working views until this instant. title: Snoozed Until step_id: anyOf: - format: uuid type: string - type: 'null' title: Step Id stop_reason: anyOf: - $ref: '#/components/schemas/StopReason' - type: 'null' description: >- Set when the cadence is stopped (reply, unsubscribe, bounce, ...). None for a live or normally-completed enrolment. Only 'reply' is resumable through the sequence; 'unread_reply' is resumed from this conversation's unread-reply card. stop_request: anyOf: - $ref: '#/components/schemas/ThreadStopRequestSchema' - type: 'null' description: >- The newest reply the AI read as asking never to be contacted again, while nobody undid it and it still keeps the contact on do-not-contact or stopped somewhere for good: the conversation says "Asked not to be contacted again" with Undo. Only the single-thread read sets it; the list leaves it null. subject: title: Subject type: string unread_reply_id: anyOf: - format: uuid type: string - type: 'null' description: >- The reply the AI could not read, a second try included, while it is the conversation's newest reply and nothing answered it: the conversation shows "Couldn't read this reply" with Try again. Only the single-thread read sets it; the list leaves it null. title: Unread Reply Id updated_at: format: date-time title: Updated At type: string waiting_since: anyOf: - format: date-time type: string - type: 'null' description: >- When the reply waiting on a person here was sent: the message a waiting AI reply answers, or the oldest reply the agent's questions wait on, the older when both do. Needs approval shows it as how long the contact has waited. Only the thread LIST populates it; null when nothing waits on a person, and on single-thread reads. title: Waiting Since required: - id - contact_email - contact_key - channel - contact_name - mailbox_id - sequence_id - step_id - subject - last_message_at - last_snippet - is_unread - is_out_of_office - is_bounce - message_count - label_ids - created_at - updated_at - is_done - came_back - follow_up_expected - listed_at title: ThreadReadSchema type: object UnauthorizedResponse: properties: detail: description: The detail of why the request is unauthorized. title: Detail type: string required: - detail title: UnauthorizedResponse type: object ForbiddenResponse: properties: detail: description: The detail of why the request is forbidden. title: Detail type: string required: - detail title: ForbiddenResponse type: object NotFoundResponse: properties: detail: description: The detail of why the resource was not found. title: Detail type: string required: - detail title: NotFoundResponse type: object UnprocessableEntityResponse: properties: detail: description: >- The detail of the error. This is the error message to show to the user. You should also use the issues field to show more detailed error messages per field. Use this field for a single liner error message. title: Detail type: string issues: description: >- The issues that caused the error. There can be multiple issues. Each issue is a user-facing error message. items: $ref: '#/components/schemas/UnprocessableEntityIssue' title: Issues type: array required: - detail - issues title: UnprocessableEntityResponse type: object ServerErrorResponse: properties: detail: description: The detail of why the server returned an error. title: Detail type: string required: - detail title: ServerErrorResponse type: object ThreadBlockedReplySchema: description: >- The conversation's newest reply, which its sequence's agent wrote no draft for. properties: message_id: description: The reply the agent wrote no draft for. format: uuid title: Message Id type: string reason: $ref: '#/components/schemas/ReplyBlockedReason' description: >- Why: `credits`, the workspace could not pay for the write; `spending_limit`, the sequence reached its spending limit; `throttled`, the AI was too busy or writing was paused; `empty_draft`, the write came to nothing usable; `rejected_before`, a person discarded a reply to it, so the agent writes no other on its own; `dormant`, it came long after the contact's sequence ended, so it was left to a person; `no_enrolment`, the contact is no longer in the sequence, so there is nothing to write from. required: - message_id - reason title: ThreadBlockedReplySchema type: object InboxChannel: description: >- Which surface a conversation happens on. Threads are contact-scoped, not channel-scoped, so this says how a thread is REACHED rather than partitioning the inbox: a reply arrives, is classified and stops the cadence identically either way, and only the send path differs. enum: - email - linkedin title: InboxChannel type: string LinkedInAccountStatus: description: |- Pairing lifecycle. ``PENDING`` exists between "the user asked to connect" and "an extension actually bound a LinkedIn member to it", so the sender page can show a half-finished connection rather than nothing at all. enum: - pending - active - revoked title: LinkedInAccountStatus type: string LinkedInCheckpointStatus: description: Whether LinkedIn is currently challenging this account. enum: - ok - checkpoint title: LinkedInCheckpointStatus type: string LinkedInPresence: description: >- How recently ANY browser connected to this sender checked in. Three states, not two, because two different questions are asked of a connection. ``ACTIVE`` answers "can a step run right now": a browser is open and heartbeating. ``IDLE`` answers "is this still set up": the laptop was closed for the evening. ``NOT_SEEN`` is the one that needs a person: nothing has checked in for a day, and queued work is silently waiting. enum: - active - idle - not_seen title: LinkedInPresence type: string ThreadQuestionCardSchema: description: What the agent needs before it answers the conversation's reply. properties: message_id: description: The reply the card is on; the answers name it. format: uuid title: Message Id type: string others_waiting: default: 0 description: >- Other conversations of the same sequence waiting on these questions that these answers, with the Q&A, would answer too: what `also_answer_waiting` on the answers writes, each a reply charged as any the agent writes. At most 20. title: Others Waiting type: integer questions: description: What to answer, in order; empty for `needs_person`. items: $ref: '#/components/schemas/ReplyQuestionSchema' title: Questions type: array readiness: $ref: '#/components/schemas/ReplyReadiness' description: >- `needs_facts`: the agent asks `questions` before it writes, and answering them has it write the reply. `needs_person`: answering is a call only a person can make, so there are no questions, only `reason`. reason: anyOf: - type: string - type: 'null' description: The AI's one or two sentences on why it asks. title: Reason saved_answers: additionalProperties: type: string description: >- The workspace's Q&A answer to each question it answers already, by question id, matched on the question's words. The card offers it as the answer. title: Saved Answers type: object shared_question_ids: description: >- The questions here those conversations ask. Their answers must be saved to the Q&A for `also_answer_waiting` to answer them. items: type: string title: Shared Question Ids type: array waiting_since: description: 'When the reply came: the contact''s wait.' format: date-time title: Waiting Since type: string required: - message_id - readiness - questions - reason - waiting_since title: ThreadQuestionCardSchema type: object ThreadRewritingDraftSchema: description: >- The agent's reply retired to be written again, while nothing was written in its place. properties: draft_id: description: The retired reply, which the rewrite replaces. format: uuid title: Draft Id type: string learning_subject_key: description: >- What a Needs work on the reply is filed under: its newest event in `GET /agent-learnings/thumbs-downs/?subject_key=` says whether the rewrite is still being written, or how it ended. title: Learning Subject Key type: string required: - draft_id - learning_subject_key title: ThreadRewritingDraftSchema type: object StopReason: enum: - reply - unsubscribe - bounce - manual - company_reply - row_left_audience - row_left_paused - step_removed - removed - cooldown - rejected - mailbox_removed - unread_reply - declined - trashed - trashed_paused title: StopReason type: string ThreadStopRequestSchema: description: >- A reply the AI read as asking never to be contacted again, and what it did. properties: blocked: description: The contact's address is on do-not-contact because of this reply. title: Blocked type: boolean message_id: description: The reply read as a stop request; Undo names it. format: uuid title: Message Id type: string sequences_stopped: description: >- The sequences it stopped the contact in for good, still stopped for it. title: Sequences Stopped type: integer required: - message_id - blocked - sequences_stopped title: ThreadStopRequestSchema type: object UnprocessableEntityIssue: properties: input: anyOf: - type: string - type: integer - type: number - type: boolean - items: {} type: array - additionalProperties: true type: object description: The user's input that caused the error. title: Input loc: description: >- The location of the error. Always contains 1 or 2 elements. The first element is the type of location (e.g. 'body', 'query', 'path', 'header'). The second element is the name of the field that caused the error. If the error is not related to a specific field, the second element is not present. items: type: string title: Loc type: array msg: description: The message of the error. The error message to show to the user. title: Msg type: string type: description: >- The type of the error. Useful for frontend code to handle different types of errors. title: Type type: string required: - loc - msg - type - input title: UnprocessableEntityIssue type: object ReplyBlockedReason: description: >- Why a sequence's agent wrote no draft for a reply its write gate let in (G9, 2026-10-20). Stored on the reply's assessment by the claim that held it back, or the settle of a write that came to nothing; cleared once a draft exists or the next claim writes. ``CREDITS``: the workspace could not pay for the write. ``SPENDING_LIMIT``: the sequence reached its spending limit. ``REJECTED_BEFORE``: a person discarded a reply to that message, so nothing unattended writes another. ``NO_ENROLMENT``: the contact is no longer in the sequence (or their row is gone), so there is nothing to write from. ``THROTTLED``: the AI was too busy, or writing was paused; the chain waits it out, and the reason stays once its tries are spent. ``EMPTY_DRAFT``: the write came to nothing usable. ``DORMANT``: the reply came long after the contact's sequence ended (D10), so it is left to a person. enum: - credits - spending_limit - rejected_before - no_enrolment - throttled - empty_draft - dormant title: ReplyBlockedReason type: string ReplyQuestionSchema: description: >- One fact the agent needs from the sender's team before it answers a reply. properties: id: description: The question's id within its card; an answer names it. title: Id type: string text: description: >- The question, to the sender's team, written to stand without the conversation and naming nothing of the contact. title: Text type: string required: - id - text title: ReplyQuestionSchema type: object ReplyReadiness: description: >- Whether the agent could answer a reply with what it has (E2, 2026-10-19). READY: everything an answer needs is in hand, or no answer is needed. NEEDS_FACTS: an answer needs a fact about the sender's offer nobody wrote down, asked for in the verdict's questions. NEEDS_PERSON: an answer needs a judgement only a person of the sender's can make, said in the reason. enum: - ready - needs_facts - needs_person title: ReplyReadiness type: string securitySchemes: APIKeyHeader: in: header name: X-API-Key type: apiKey HTTPBearer: scheme: bearer type: http ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.