Open Responses API doesn't accept "output_text" as an input Item
I maintainer di solito rispondono entro 1 giorno
Nessuno ha ancora preso questa issue.
Valutazione
- Difficoltà
- 2/5
- Tempo stimato
- 1-3 ore
- Idoneità per principianti
- 78/100
Direzione di ricerca
Inizia in core/http/endpoints/openresponses/responses.go intorno alle righe 727 e 750-754, quindi riproduci la richiesta /v1/responses usando come input l’output di una risposta precedente. Verifica come gli elementi output_text vengono convertiti nell’input del backend. Il lavoro è completato quando un output copiato contenente output_text viene accettato e il contenuto della risposta precedente raggiunge il contesto del modello.
Scritto dal modello di indicizzazione a partire dal testo della issue.
Descrizione
LocalAI version:
v4.10.0 (7ad0cbf259f0c7bf9920fe2438fc3630ecd6c672)
Environment, CPU architecture, OS, and Version:
Docker, x86, Linux
Describe the bug
Open Response API doesn't accept output_text as an Item per the spec.
https://www.openresponses.org/reference#request-body
https://github.com/mudler/LocalAI/blob/b77937f61c522feb64f362a1ce322b5ef979cb7d/core/http/endpoints/openresponses/responses.go#L727
You should be able to exactly copy the "output" JSON from one call into the "input" JSON of the next call.
To Reproduce
Start a new OR API request (/v1/responses) with output messages from a previous response.
Expected behavior
The model sees the previous responses in the context for the new response
Logs
Example input:
Input JSON
{
"model": "gemma-4-26b-a4b-it",
"instructions": "These are scanned hand-written notes. Combine the notes, but do not reorder or change the wording of the notes except for the footnotes and endnotes. ",
"input": [
{
"id": "msg_8c030eaa-8eca-402d-9a37-3b81097dedf8",
"role": "assistant",
"type": "message",
"status": "completed",
"content": [
{
"text": "text 1",
"type": "output_text",
"logprobs": [],
"annotations": []
}
],
"summary": [],
"arguments": ""
},
{
"id": "msg_936e093d-e8b7-46b1-a3ed-c5058f5092af",
"role": "assistant",
"type": "message",
"status": "completed",
"content": [
{
"text": "text 2",
"type": "output_text",
"logprobs": [],
"annotations": []
}
],
"summary": [],
"arguments": ""
},
{
"id": "msg_259556ea-700d-42e6-905a-9897fb6674d9",
"role": "assistant",
"type": "message",
"status": "completed",
"content": [
{
"text": "text 3",
"type": "output_text",
"logprobs": [],
"annotations": []
}
],
"summary": [],
"arguments": ""
},
{
"id": "msg_427a8eff-6185-402e-99a6-1a93c3b3f705",
"role": "assistant",
"type": "message",
"status": "completed",
"content": [
{
"text": "text 4",
"type": "output_text",
"logprobs": [],
"annotations": []
}
],
"summary": [],
"arguments": ""
}
],
"temperature": 0.8
}
Example Backend Input:
Backend Input
[
{
"role": "system",
"content": "These are scanned hand-written notes. Combine the notes, but do not reorder or change the wording of the notes except for the footnotes and endnotes. "
}
]
Backend Output
{
"id": "resp_ac7c7791-7680-4685-a4cc-c206264b073f",
"object": "response",
"created_at": 1790610865,
"completed_at": 1790610910,
"status": "completed",
"model": "gemma-4-26b-a4b-it",
"output": [
{
"type": "message",
"id": "msg_8f7ba482-ca80-4cc9-8633-9d71dd0e8fa3",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "Please provide the scanned hand-written notes (by uploading the images or providing the text). \n\nOnce you provide them, I will combine them according to your exact constraints:\n1. **No reordering:** I will keep the notes in their original sequence.\n2. **No wording changes:** I will not change a single word in the body of the notes.\n3. **Footnotes/Endnotes exception:** I will only adjust the footnotes and endnotes to ensure they are correctly placed or formatted according to your requirements.",
"annotations": [],
"logprobs": []
}
],
"arguments": "",
"summary": []
}
],
"error": null,
"incomplete_details": null,
"previous_response_id": null,
"instructions": "These are scanned hand-written notes. Combine the notes, but do not reorder or change the wording of the notes except for the footnotes and endnotes. ",
"tools": [],
"tool_choice": "none",
"parallel_tool_calls": true,
"max_tool_calls": null,
"temperature": 0.8,
"top_p": 1,
"presence_penalty": 0,
"frequency_penalty": 0,
"top_logprobs": 0,
"max_output_tokens": null,
"text": {
"format": {
"type": "text"
}
},
"truncation": "auto",
"reasoning": null,
"usage": {
"input_tokens": 43,
"output_tokens": 1546,
"total_tokens": 1589,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens_details": {
"reasoning_tokens": 0
}
},
"metadata": {},
"store": true,
"background": false,
"service_tier": "default",
"safety_identifier": null,
"prompt_cache_key": null
}
Additional context
I believe | "output_text" (Pseudo code since I am unfamiliar with go) needs to be added here as a quick solution, but I'm unsure if it will cause downstream problems.
https://github.com/mudler/LocalAI/blob/b77937f61c522feb64f362a1ce322b5ef979cb7d/core/http/endpoints/openresponses/responses.go#L750-L754
- Lingua principale
- Go
- Stelle
- 49.3k
- Fork
- 4.5k
- Merge medio
- 1g 7h
- PR unite (30g)
- 362
Preparare l'ambiente
Avvia il container di sviluppo del progetto nel browser, con il tuo account GitHub.
- Include un Dockerfile o un file Docker Compose
- Ha un modello di pull request
- Leggi la guida per i contributori
Come iniziare
- Leggi tutta la issue e poi la guida ai contributi del progetto.
- Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
- Fai un fork del repository e lavora su un branch.
- Apri una pull request che faccia riferimento al numero della issue.
Altre issue di mudler/LocalAI
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 76/100
mudler/LocalAI#11995 · 1 commento ·
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 75/100
mudler/LocalAI#11991 · 1 commento ·
I maintainer di solito rispondono entro 1 giorno
-
fish-speech: make compile:true usable on Blackwell sm_121 by honouring the CUDA toolkit's ptxasApertaenhancement
Difficoltà 2/5 1-3 ore Idoneità per principianti 76/100
mudler/LocalAI#11348 · 1 commento ·
I maintainer di solito rispondono entro 1 giorno
-
barholeurApertabug unconfirmed
Difficoltà 5/5 Più di una settimana Idoneità per principianti 10/100
I maintainer di solito rispondono entro 1 giorno
-
bug unconfirmed
Difficoltà 3/5 1-2 giorni Idoneità per principianti 72/100
I maintainer di solito rispondono entro 1 giorno
Tutte le issue di mudler/LocalAI
Issue simili
-
bug docs
Difficoltà 2/5 1-3 ore Idoneità per principianti 88/100
I maintainer di solito rispondono entro 1 giorno
-
bug needs-acceptance wg/evaluation-quality
Difficoltà 2/5 1-3 ore Idoneità per principianti 76/100
vllm-project/semantic-router#4424 ·
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 90/100
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 76/100
NVIDIA/k8s-device-plugin#2076 ·
I maintainer di solito rispondono entro 1 giorno
-
Documentation help wanted
Difficoltà 2/5 1-3 ore Idoneità per principianti 68/100
golang/go#81933 · 2 commenti ·
I maintainer di solito rispondono entro 1 giorno