Beschreibungen auf Englisch
Preview Lookup
Preflight: is a split for this text already cached — without sending the text
itself. Send text_hash (sha256 of the raw input_text, lowercase hex) +
template_id (+ generation_mode and config_override, if used) — the server rebuilds the same
preview_id and checks the cache.
Korrekturen an der Spezifikation · 1
Chunk preview is available with an API key
The machine-readable
llm.md§12 claims chunk preview is a web-cabinet endpoint that returns401for API keys. That is wrong: all three preview operations are part of the public surface and require theorders.readscope — as described by both the OpenAPI document and §7.1 of the very samellm.md. If an AI assistant cites §12, it is mistaken.
- 200
status=ready— already computed, no need to send the text. - 202
status=processing— the calculation for this text is still running. - 404 — nothing cached → send the full text via
POST /orders/chunks/preview.
Required key permission: orders.read.
Auf dieser Seite(4)
Parameter
Die Eingabefelder liegen direkt in der Anfragezeile: Wert eintragen und die URL ist fertig. Darunter stehen Typ, Pflichtangabe und erlaubte Werte jedes Parameters.
- stringin der Queryerforderlichuuid
Template UUID — the same one that was sent to
POST /orders/chunks/previewfor the calculation. Part of thepreview_ididentity. - stringin der QueryerforderlichMuster: ^[a-f0-9]{64}$
sha256 of the RAW
input_text(lowercase hex, 64 characters) — compute it yourself; the server normalizes the text on its own side and does not fold that into the hash. Together withtemplate_idandgeneration_modeit determinespreview_id: the same triple yields the same response, without sending the text itself. - stringin der Queryoptional
Generation mode, if one was used for the calculation (
paragraph— paragraph-based split). Must match what was sent toPOST— the mode is part of thepreview_ididentity.Zulässige Werte - array<string>in der Queryoptional
The
config_overridethe preview was computed with inPOST(if any). Settings that affect the split are part of thepreview_ididentity, the rest are not. Send it as a JSON string (config_override={"tts_settings":{"mode":"mode_v1"}}, URL-encoded) or as nested keys (config_override[tts_settings][mode]=mode_v1).
Mögliche Antworten
200Success. The payload is in data.
Success. The payload is in data.
{
"success": true,
"message": "string",
"data": {
"status": "string",
"preview_id": "string",
"summary": "string",
"chunks": [
"string"
],
"page": "string"
}
}Success flag. Branch on the HTTP status code instead: any 2xx response carries true here, while an error comes back in a different shape that need not contain this field at all.
A human-readable note in the account language. Fine to show to a user; do not parse it — the wording changes without notice and is not an error code.
dataerforderlichThe response payload.
object
The response payload.
Always ready for a 200 response — the calculation is done.
A content-based preview id (sha256 of text+template+mode+algorithm version). Use it for incremental re-preview (previous_preview_id) and for pagination (GET .../{previewId}).
Totals for the whole text — not just the current page of chunks.
Only the CURRENT page (see data.page), not the full list — use pagination (GET .../{previewId}?page=) for the rest.
Pagination meta for the CURRENT page of data.chunks.
202Accepted for processing. The result arrives asynchronously.
Accepted for processing. The result arrives asynchronously.
{
"success": true,
"message": "string",
"data": {
"status": "string",
"preview_id": "string",
"summary": "string",
"chunks": [
"string"
],
"page": "string"
}
}Success flag. Branch on the HTTP status code instead: any 2xx response carries true here, while an error comes back in a different shape that need not contain this field at all.
A human-readable note in the account language. Fine to show to a user; do not parse it — the wording changes without notice and is not an error code.
dataerforderlichThe response payload.
object
The response payload.
Always processing for a 202 response — the calculation is running in the background.
The preview id. Use it to subscribe to the private-chunks.preview.{userId} WS channel (the .ready event), or to poll GET /orders/chunks/preview/{previewId} manually.
Totals for the whole text — not just the current page of chunks.
Only the CURRENT page (see data.page), not the full list — use pagination (GET .../{previewId}?page=) for the rest.
Pagination meta for the CURRENT page of data.chunks.
401The key is missing, unknown, disabled or expired.
The key is missing, unknown, disabled or expired.
{
"success": false,
"message": "API key is missing. Provide it in the X-API-KEY header.",
"data": null
}Always false in error responses.
Error text in the key's language (set through the X-Locale header).
Always null when the request is rejected before processing.
403The key lacks the required permission, or the object belongs to another user.
The key lacks the required permission, or the object belongs to another user.
{
"success": false,
"message": "This API key does not have permission to perform this action."
}Always false in error responses.
Error text in the key's language (set through the X-Locale header).
404Not found, or not reachable with this key.
Not found, or not reachable with this key.
{
"success": false,
"message": "Resource not found."
}Always false in error responses.
The reason for the rejection in words, in the account language. Meant for display; do not branch on it, the wording changes.
A per-field breakdown — present only on validation errors (422): the key names a request field, the value lists the complaints about it. Other codes send null, since there is nothing to break down and the whole reason is in message.
422Validation error. Offending fields are listed in errors.
Validation error. Offending fields are listed in errors.
{
"message": "string",
"errors": {
"key": [
"string"
]
}
}Errors overview.
errorserforderlichA detailed description of each field that failed validation.
object
A detailed description of each field that failed validation.
429Limit exceeded: either the key's request rate or its token quota. Retry no earlier than Retry-After.
Limit exceeded: either the key's request rate or its token quota. Retry no earlier than Retry-After.
{
"success": false,
"message": "Too many attempts. Please wait a moment and try again.",
"reason": "rate_limit_exceeded",
"error_code": "rate_limit_exceeded",
"retry_after": 30
}Always false in error responses.
Error text in the key's language (set through the X-Locale header).
Machine-readable failure reason — branch on this, not on the message text.
The same machine-readable code as in reason — a second name for the field. The values always match; branch on either.
How many seconds to wait before retrying (the same value is in the Retry-After header).
Ereignisse, die dabei entstehen
Der Fortschritt kommt über WebSocket: Der Auftrag muss nicht in einer Schleife abgefragt werden. Das Abonnement braucht dasselbe Recht wie das Lesen von Aufträgen.
In der Nähe
Diese Seite einer KI geben
Spezifikation 0.0.1