Reference

Changelog

Notable changes to the AYETO API.

View as Markdown

Changes that affect API clients are listed here, newest first. Additions that do not change existing behaviour (a new optional field, a new endpoint) are listed too, so you can see what became available.

2026-11-21

  • New endpoint POST /api/v3/embeddings: embedding vectors for a batch of texts (models small and large, optional dimensions), with the new scope ayeto.embeddings. Existing API keys with all scopes (*) can use it right away; a key with selected scopes needs the new scope added.
  • New endpoint POST /api/v3/data-loader/load-batch: converts several files to text in one request, in parallel, with a result or an error per file. A minimum price is applied once per batch.

2026-11-18

  • The progress text of a tool call can no longer close its own block: a line of the text that reads *** gets a zero width space (U+200B) in front, in content and in the tool_call_output events of the stream (Tool calls in the answer). Until now such a line ended the block early for clients that parse the markers.

2026-11-05

  • When a chat stream ends early, the results of tool calls that already finished stay in the conversation, so the next message does not run them again. Only calls that did not finish are reported to the model as interrupted.
  • A model call interrupted by a disconnect is charged with the part of the prompt that the previous call of the conversation already sent at the cached price.
  • Conversations with tool calls read more of their history from the prompt cache after a new message, which lowers the input cost of long conversations.
  • Conversations whose older messages were automatically compacted keep using the prompt cache for their whole history, which makes their model calls much cheaper.

2026-10-19

  • Workflow exports list the workspaces the steps name with their names (workflow.workspaces); import and copy take workspace_map to use other workspaces instead (Export and import).
  • Workflows work with workspaces: new node types workspace.read, workspace.list, workspace.search, workspace.write, workspace.save_file and workspace.manage, and the trigger trigger.workspace that starts the published workflow on changes in a workspace folder (Workspaces). Deployment triggers carry workspace_id and folder.
  • assistant.run takes workspaces: workspaces the assistant may use in that step only.
  • Workflows keep values between runs: node types state.get / state.set and new POST /api/v3/workflow/state/list, /workflow/state/set and /workflow/state/delete (Stored values).
  • New run field not_before: a queued run of a workspace trigger waits until then.
  • Shares carry shared_by (user id) and shared_at (timestamp): who added the share and when. The server sets them; values sent in sharing / group_sharing are ignored (workflow object).
  • A user with read-only access to a shared workflow sees only their own share and the groups they are in, not the other recipients.
  • Users can decline a share, block users and stop accepting shares in AYETO. A recipient who does not accept your share is left out when you create or update the sharing; the returned object shows what was stored.
  • New read-only field sharing_declined on workflows: users who declined the group sharing.

2026-10-14

  • Text to speech has new models and voices: gpt-4o-mini-tts (recommended) with 13 voices, among them the new marin and cedar, and a speaking style set by instructions. tts/mp3 takes the new optional fields model, style and instructions; voice accepts every voice of the chosen model (Text to speech).
  • New POST /api/v3/tts/audio: the speech as mp3, opus, aac, flac or wav.
  • New POST /api/v3/tts/voices: the models, their voices, the speaking style presets and the length limit.
  • The default voice is marin (was onyx) where the installation uses gpt-4o-mini-tts.
  • A request converts at most 60,000 characters (about an hour of audio); a longer text gets 422. An empty text gets 422 The text is empty (was 500 No audio generated), an unknown model or voice 422 with the reason.
  • The text is spoken in parts of whole paragraphs instead of sentence by sentence, and the balance is checked against the estimated price of the whole text before the speech is generated. gpt-4o-mini-tts is charged by tokens, the older models by characters.

2026-10-08

  • The chat stream with runner_version "2" repeats the tool_call_pending status while the model writes the arguments of a tool call, about once a second, with data.arguments_chars (characters written so far). Long tool calls show progress instead of a single event.
  • A model call interrupted because the client closed the connection is charged for the part generated until then.

2026-10-07

  • New workflow steps booster.lock and booster.unlock: the locks of booster database records and collections that panels use, with a bounded wait and an expiry.
  • Workflow steps that read files accept files of booster panels the user can use (the panel's file reference or id), also in triggered runs.
  • Booster panels with AYETO sign-in can call the API on behalf of the signed-in person: the session token works as uni-api-key with the scopes the person agreed to (Authentication).
  • Booster file storage: large files can be uploaded directly to the storage service (upload/init, upload/complete), where the installation offers it.
  • New workflow trigger trigger.booster_file: starts the published workflow when a file of a booster panel storage is stored, changed or deleted; the file is input.file. Workflow triggers list it with the panel and the watched folder in collection.
  • New: booster file storage. Panels can keep files in folders with access rules; /booster/storage/private/* uploads (multipart or base64), lists, links, moves and deletes them with the new scopes ayeto.booster.storage and ayeto.booster.storage.write.
  • Files served by AYETO links carry X-Content-Type-Options: nosniff; SVG, HTML and XML files are always downloaded, never shown in the browser (<img> keeps showing SVG images).

2026-10-06

  • The model catalogue (/ai_model/get_all) lists only models you can use: models switched off (is_enabled false) or retired (is_deprecated true) are no longer returned.
  • The model catalogue (/ai_model/get_all) has a new field is_recommended: models the administrators recommend.
  • The chat stream with runner_version "2" has a new status phase conversation_named (data.name): a new conversation is named from its first message while the first answer is generated, instead of after it. The name is stored when the event arrives.
  • find and count reject filters and sort_key on internal fields stored with a record (for example secrets) with 422; before, such conditions were accepted.

2026-10-05

  • Conversations have two new fields, booster_panel_id and panel_user_id: conversations of the signed-in users of your booster panels with your assistants. /conversation/find returns them with your other conversations (filter them out with ["panel_user_id", "==", null]); /chat answers 403 for them, only the panel user continues them.
  • Booster database records have a new field owner (UUID or null): the panel user who created the record, on panels with user accounts. find and count accept owner in filters and as sort_key. Records created through the API have owner: null. When a panel user account is deleted for good, the records it created are deleted too.
  • Collection rules have two new levels, user and owner. Like the other levels except none, they allow requests made through the API, on all records.
  • POST /ai_model/get_all can return models of the new type google_video_gen (video generation). Videos generated in chat are listed in attachments of the answer, like generated images.
  • In chat over the API, tool actions that the AYETO app lets the user confirm in the chat (for example creating a booster panel or a workflow from the chat) are refused: the tool call ends with an error and the model continues its answer.
  • POST /ai_tool/get_all lists two more tools, BoosterStudioStartFunctionTool (creates a booster panel from a template) and WorkflowStudioStartFunctionTool (creates a workflow). You can give them to your assistants; they need the user's confirmation in the chat of the AYETO app, so in chat over the API they are refused as described above.
  • Newly documented: POST /booster/panel/info, which returns a panel's name, its organization and the key's user, and checks access to the panel. The endpoint itself is unchanged.

2026-10-04

  • Tools returned by POST /ai_tool/get_all have a new field companion_of_groups (array of group names): like companion_of_group, for a helper tool that accompanies several groups.

2026-10-03

  • Tools returned by POST /ai_tool/get_all have two new fields: vision (the tool shows images to the model and is offered only with models that can see images) and outbound (the tool can send data outside AYETO, for example web requests or e-mail).
  • Malformed list queries are rejected with 422 and a clear detail instead of 500: a condition without 3 or 4 elements, a filters element that is neither an array nor an object, a group object with no key or several keys, an AND / OR group whose value is not a non-empty array, groups nested deeper than 32 levels, a negative limit_from, and a limit_to lower than limit_from.
  • 429 responses of the rate limiter have the body {"detail": "Too many requests"} like every other error (the reason key is gone); Retry-After is unchanged.
  • A missing API key scope is answered with 401 API key is invalid everywhere.
  • .../get and .../delete endpoints also accept the id in a JSON body {"id": "<uuid>"}; the entity_id query parameter still works. Neither, or two different ids, gives 422. A body sent to them must be JSON.
  • New POST /user_credit/get_self and POST /version (GET still works and shares the rate limit); /version is rate limited on the static tier (1,200 requests a minute).
  • POST /ai_tool/get_all no longer returns hidden or deprecated tools.
  • New POST /conversation/count (scope ayeto.conversation, same body as /conversation/find).
  • Conversation cost (POST /usage/cost/conversation) is the sum of the credits actually charged, not a repricing at current prices; it includes the text tokens of image models and no longer fails with 404 for models removed since.
  • Chat with a model that cannot stream stores the answer and returns it (before, the answer was lost and the response returned the user's message).
  • Chat attachments are checked and stored before anything else: an attachment refused with 422 (file is too large, a storage quota, invalid data) no longer leaves the user message behind. Malformed base64 returns 422 invalid base64 data in attachment '<filename>' (or invalid data URI in attachment '<filename>') instead of 500. The size field of attachments is no longer required and is ignored.
  • A chat follow-up to a conversation created in an organization runs in that organization when the request names none (charged there, membership required); naming a different organization returns 422 the conversation belongs to another organization. Another user's conversation is refused with 403 before any attachment is stored.
  • The structured chat stream (runner_version "2") no longer sends the unused iteration field.
  • Booster database: creating a record with a key that already exists returns 422 a record with key '<key>' already exists instead of 500; limit_from without limit_to returns up to 100 records from limit_from (limit_from must be lower than 1000); malformed AND / OR filters return 422 instead of 500.
  • Data loader: unsupported file types return 422 unsupported file type '<mime>' and are not charged.
  • Workflows: a file named by its id in the run input stays the user's and is no longer deleted with the run (files sent as base64 still belong to the run).

2026-10-02

  • Booster database collection rules apply only to panels in public database mode; in private mode they are ignored. Users a panel is shared with read-only can now write its records and take locks (in both modes).
  • POST /tts/mp3 requires the new ayeto.tts scope and POST /data-loader/load the new ayeto.data_loader scope. Existing API keys were given both scopes; keys created by pairing a desktop client (ayeto.connector only) can no longer call these endpoints.
  • POST /tts/mp3 and POST /data-loader/load accept an optional organization_id: the request runs in the organization and is charged to the user's credit there (admins and members only; guests and non-members get 403).
  • POST /tts/mp3 returns 422 with not enough user credit / not enough organization credit when the credit runs out, instead of 500 Failed to generate audio.
  • Chat refuses a model switched off by the administrators (requested directly or as the assistant's model) with 422 model is disabled, and an automatic model with no available model with 422 model is not available; model is deprecated is returned before the conversation is touched.
  • Reading another user's conversation with /conversation/get (refused with 404) no longer updates its accessed field.
  • The language header of an API request no longer changes the user's preferred language in the AYETO app (before, every request saved it, and a request without the header reset it to English).
  • POST /assistant/avatar/get accepts API keys with the new ayeto.assistant scope, which can now be selected when creating a key (it also covers /assistant/find).
  • New documentation of API v3, replacing the earlier beta notes.
  • Workflows are available on the API: reading, running, streaming runs, approvals, editing, publishing, export and import (ayeto.workflow, ayeto.workflow.write).
  • Private booster database API with its own scopes (ayeto.booster.database, ayeto.booster.database.write).