Open (or resume) the current conversation with a role
const url = 'https://api.harperharbor.com/open/v1/conversation/start';const options = { method: 'POST', headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'}, body: '{"roleId":"2489E9AD-2EE2-8E00-8EC9-32D5F69181C0","language":"example","userName":"example","greetingIndex":1,"firstPageSize":0}'};
try { const response = await fetch(url, options); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}curl --request POST \ --url https://api.harperharbor.com/open/v1/conversation/start \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data '{ "roleId": "2489E9AD-2EE2-8E00-8EC9-32D5F69181C0", "language": "example", "userName": "example", "greetingIndex": 1, "firstPageSize": 0 }'Opens or resumes the current conversation for the caller and agent. Requires chat.play and agent access. Inserts the selected greeting when creating the conversation, or into an existing conversation that has no messages yet; this endpoint does not call a model. Returns conversationId, defaultRelay (greeting text), historyConversation, roleInfo and xmlV3Compatibility=false. With firstPageSize above 0 (limit 100), a resumed conversation also returns firstPage, the same object as conversation/messages with pageNum=1 and that pageSize; a new conversation returns none. Missing or invalid roleId returns 400. Shareable configurations can be used across application tenants without community review. The conversation, player settings and subsequent charges remain scoped to the calling application and player; the source configuration and its Lorebooks remain in their storage tenant. HarperHarbor advertises responseSettingsVersion=1 for conversation response preferences. Optional capability on services that support account model preferences: When this user first starts a conversation with an agent configuration in this application, the saved account model or lane preference takes priority over the application default, unless a model is already saved for that configuration. If the preferred model or exact lane is no longer selectable or is unavailable, this call saves the application default for that configuration and returns modelPreferenceFallback=true. The account preference is retained for future configurations. Previously opened configurations keep their own model settings.
Authorizations
Section titled “Authorizations”Request Bodyrequired
Section titled “Request Bodyrequired”object
Responses
Section titled “Responses”Successful response.
object
object
object
object
object
Optional capability on services that support account model preferences: true only when this call first starts an agent configuration for this user and saves the application default because the account’s preferred model or exact lane is unavailable or absent from the selectable catalog. The account preference is retained for future configurations. Resuming a previously opened configuration does not reapply the account preference.
Example
{ "responseSettingsVersion": 1, "firstPage": { "chats": [ { "chatRole": "USER" } ], "operations": [ { "kind": "send", "state": "accepted" } ], "responseSettingsVersion": 1 }}Invalid_request
object
Error code (snake_case) or, for legacy handlers, a free-text/localized message.
Human-readable sentence. Present only on middleware errors and /me, /me/wallet.
Whether retrying may succeed. Present only on middleware errors, /me, /me/wallet and service/share routes.
Only on a first-turn context_capacity_exceeded: the smallest context tier that fits the whole card with room to talk. Save it as context in player settings and resend. Absent when no tier fits.
The token budget of required_context_tier for the selected model, for display.
Only on a first-turn context_capacity_exceeded: whether saving trimConstantLore=true lets the card play at the current tier. Absent on mid-conversation capacity errors.
Only on insufficient_credits: the credits this turn needs before it can start. Absent when the refusal came without an estimate.
Only on insufficient_credits: the credits the wallet could set aside for it.
Examplegenerated
{ "error": "example", "message": "example", "retryable": true, "required_context_tier": 1, "required_context_tokens": 1, "constant_lore_trim_fits": true, "credits_needed": 1, "credits_available": 1}Unauthorized
object
Error code (snake_case) or, for legacy handlers, a free-text/localized message.
Human-readable sentence. Present only on middleware errors and /me, /me/wallet.
Whether retrying may succeed. Present only on middleware errors, /me, /me/wallet and service/share routes.
Only on a first-turn context_capacity_exceeded: the smallest context tier that fits the whole card with room to talk. Save it as context in player settings and resend. Absent when no tier fits.
The token budget of required_context_tier for the selected model, for display.
Only on a first-turn context_capacity_exceeded: whether saving trimConstantLore=true lets the card play at the current tier. Absent on mid-conversation capacity errors.
Only on insufficient_credits: the credits this turn needs before it can start. Absent when the refusal came without an estimate.
Only on insufficient_credits: the credits the wallet could set aside for it.
Examplegenerated
{ "error": "example", "message": "example", "retryable": true, "required_context_tier": 1, "required_context_tokens": 1, "constant_lore_trim_fits": true, "credits_needed": 1, "credits_available": 1}Insufficient_scope: requires chat.play
object
Error code (snake_case) or, for legacy handlers, a free-text/localized message.
Human-readable sentence. Present only on middleware errors and /me, /me/wallet.
Whether retrying may succeed. Present only on middleware errors, /me, /me/wallet and service/share routes.
Only on a first-turn context_capacity_exceeded: the smallest context tier that fits the whole card with room to talk. Save it as context in player settings and resend. Absent when no tier fits.
The token budget of required_context_tier for the selected model, for display.
Only on a first-turn context_capacity_exceeded: whether saving trimConstantLore=true lets the card play at the current tier. Absent on mid-conversation capacity errors.
Only on insufficient_credits: the credits this turn needs before it can start. Absent when the refusal came without an estimate.
Only on insufficient_credits: the credits the wallet could set aside for it.
Examplegenerated
{ "error": "example", "message": "example", "retryable": true, "required_context_tier": 1, "required_context_tokens": 1, "constant_lore_trim_fits": true, "credits_needed": 1, "credits_available": 1}Not_found: inaccessible resource
object
Error code (snake_case) or, for legacy handlers, a free-text/localized message.
Human-readable sentence. Present only on middleware errors and /me, /me/wallet.
Whether retrying may succeed. Present only on middleware errors, /me, /me/wallet and service/share routes.
Only on a first-turn context_capacity_exceeded: the smallest context tier that fits the whole card with room to talk. Save it as context in player settings and resend. Absent when no tier fits.
The token budget of required_context_tier for the selected model, for display.
Only on a first-turn context_capacity_exceeded: whether saving trimConstantLore=true lets the card play at the current tier. Absent on mid-conversation capacity errors.
Only on insufficient_credits: the credits this turn needs before it can start. Absent when the refusal came without an estimate.
Only on insufficient_credits: the credits the wallet could set aside for it.
Examplegenerated
{ "error": "example", "message": "example", "retryable": true, "required_context_tier": 1, "required_context_tokens": 1, "constant_lore_trim_fits": true, "credits_needed": 1, "credits_available": 1}Chat_operation_conflict
object
Error code (snake_case) or, for legacy handlers, a free-text/localized message.
Human-readable sentence. Present only on middleware errors and /me, /me/wallet.
Whether retrying may succeed. Present only on middleware errors, /me, /me/wallet and service/share routes.
Only on a first-turn context_capacity_exceeded: the smallest context tier that fits the whole card with room to talk. Save it as context in player settings and resend. Absent when no tier fits.
The token budget of required_context_tier for the selected model, for display.
Only on a first-turn context_capacity_exceeded: whether saving trimConstantLore=true lets the card play at the current tier. Absent on mid-conversation capacity errors.
Only on insufficient_credits: the credits this turn needs before it can start. Absent when the refusal came without an estimate.
Only on insufficient_credits: the credits the wallet could set aside for it.
Examplegenerated
{ "error": "example", "message": "example", "retryable": true, "required_context_tier": 1, "required_context_tokens": 1, "constant_lore_trim_fits": true, "credits_needed": 1, "credits_available": 1}Temporarily_unavailable
object
Error code (snake_case) or, for legacy handlers, a free-text/localized message.
Human-readable sentence. Present only on middleware errors and /me, /me/wallet.
Whether retrying may succeed. Present only on middleware errors, /me, /me/wallet and service/share routes.
Only on a first-turn context_capacity_exceeded: the smallest context tier that fits the whole card with room to talk. Save it as context in player settings and resend. Absent when no tier fits.
The token budget of required_context_tier for the selected model, for display.
Only on a first-turn context_capacity_exceeded: whether saving trimConstantLore=true lets the card play at the current tier. Absent on mid-conversation capacity errors.
Only on insufficient_credits: the credits this turn needs before it can start. Absent when the refusal came without an estimate.
Only on insufficient_credits: the credits the wallet could set aside for it.
Examplegenerated
{ "error": "example", "message": "example", "retryable": true, "required_context_tier": 1, "required_context_tokens": 1, "constant_lore_trim_fits": true, "credits_needed": 1, "credits_available": 1}