Image editing broken in v0.8.2-rc3 with GPT-Image-1.5 model #12062
Replies: 4 comments 2 replies
-
|
I think I see the issue, will be patched soon |
Beta Was this translation helpful? Give feedback.
0 replies
-
|
Fixed by #12066 |
Beta Was this translation helpful? Give feedback.
0 replies
-
|
This was quick. Thanks for the fixing. |
Beta Was this translation helpful? Give feedback.
0 replies
-
|
@danny-avila I tested with dev branch and still see 404 error for the GPT-Image-1.5. Also it shouldn't show image edited.
|
Beta Was this translation helpful? Give feedback.
2 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment


Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
What happened?
In the latest version of LibreChat, attempting to edit a previously generated image using the GPT-Image-1.5 model fails. Instead of editing the image, the assistant responds with:
"I don't have access to the previously generated image for direct editing. Please upload the cat image you want to modify, and I'll add a small ball to it for you!"
Additionally, the backend returns a 404 Resource Not Found error when attempting the edit operation.
The assistant should be able to reference and edit a previously generated image within the same conversation, as it did in v0.8.2-rc3
Actual Behavior
Image editing fails silently from the user's perspective with the above message.
Backend logs show a 404 Resource Not Found error.
Image generation works correctly; only editing is broken.
Version Information
v0.8.3-rc1
Steps to Reproduce
Configure IMAGE_GEN_OAI_* environment variables (see configuration below).
Generate an image using the GPT-Image-1.5 model.
In the same conversation, ask the assistant to modify the generated image (e.g., "Add a ball to this image").
Observe the error response and backend 404 error.
`- name: IMAGE_GEN_OAI_API_KEY
value:
value: "https://.cognitiveservices.azure.com/openai/deployments/gpt-image-1.5/"
value: "gpt-image-1.5"
value: "2024-02-01"`
What browsers are you seeing the problem on?
Microsoft Edge
Relevant log output
{"data":{"error":{"code":"404","message":"Resource not found"}},"headers":{"apim-request-id":"7b434ac3-dcb6-4da3-9492-a84f3176090f","content-length":"56","content-type":"application/json","date":"Wed, 04 Mar 2026 05:13:28 GMT","strict-transport-security":"max-age=31536000; includeSubDomains; preload","x-content-type-options":"nosniff"},"level":"error","message":"[image_edit_oai] Problem editing the image: The server responded with status 404: Request failed with status code 404","stack":"AxiosError: Request failed with status code 404\n at settle (/app/node_modules/axios/dist/node/axios.cjs:2099:12)\n at IncomingMessage.handleStreamEnd (/app/node_modules/axios/dist/node/axios.cjs:3307:11)\n at IncomingMessage.emit (node:events:536:35)\n at endReadableNT (node:internal/streams/readable:1698:12)\n at process.processTicksAndRejections (node:internal/process/task_queues:82:21)\n at Axios.request (/app/node_modules/axios/dist/node/axios.cjs:4483:41)\n at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n at async /app/api/app/clients/tools/structured/OpenAIImageTools.js:362:26\n at async DynamicStructuredTool.call (/app/node_modules/@langchain/core/dist/tools/index.cjs:156:22)\n at async ToolNode.runTool (/app/node_modules/@librechat/agents/dist/cjs/tools/ToolNode.cjs:132:28)\n at async Promise.all (index 0)\n at async ToolNode.run (/app/node_modules/@librechat/agents/dist/cjs/tools/ToolNode.cjs:232:23)\n at async ToolNode.invoke (/app/node_modules/@librechat/agents/dist/cjs/utils/run.cjs:58:27)\n at async RunnableSequence.invoke (/app/node_modules/@langchain/core/dist/runnables/base.cjs:1321:33)\n at async _runWithRetry (/app/node_modules/@langchain/langgraph/dist/pregel/retry.cjs:76:22)","status":404,"timestamp":"2026-03-04T05:13:29.005Z"}Screenshots
No response
Code of Conduct
Beta Was this translation helpful? Give feedback.
All reactions