github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-05-07 11:28:35 -05:00
Code Issues 1.3k Packages Projects Releases 126 Wiki Activity

[GH-ISSUE #24193] issue: System Prompt missing after reload #58893

New Issue
Closed
opened 2026-05-06 00:22:16 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-06 00:22:16 -05:00
Owner
Copy Link

Originally created by @Scarjit on GitHub (Apr 28, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/24193

Check Existing Issues

  • I have searched for any existing and/or related issues.
  • I have searched for any existing and/or related discussions.
  • I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
  • I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

v0.9.2

Ollama Version (if applicable)

No response

Operating System

Arch Linux x86_64 (Linux 7.0.1-1-cachyos-eevdf)

Browser (if applicable)

Firefox 150.0 (64-bit)

Confirmation

  • I have read and followed all instructions in README.md.
  • I am using the latest version of both Open WebUI and Ollama.
  • I have included the browser console logs.
  • I have included the Docker container logs.
  • I have provided every relevant configuration, setting, and environment variable used in my setup.
  • I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
  • I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
  • Start with the initial platform/version/OS and dependencies used,
  • Specify exact install/launch/configure commands,
  • List URLs visited, user input (incl. example values/emails/passwords if needed),
  • Describe all options and toggles enabled or changed,
  • Include any files or environmental changes,
  • Identify the expected and actual result at each stage,
  • Ensure any reasonably skilled user can follow and hit the same issue.

Expected Behavior

System prompt should be shown (and applied for completions) after page reload

Actual Behavior

System prompt is empty after reload

Steps to Reproduce

  1. Create a new chat
  2. Enter a system prompt
  3. Send a chat message
  4. Reload your page

The same behavior is consistent across multiple devices (PC, Android) and Browsers (Firefox, Chromium).

Logs & Screenshots

https://github.com/user-attachments/assets/3cf2c682-7e8b-4674-bc87-62a531488b16

Docker logs

API response

As seen here the system prompt is not returned.

{
  "id": "196ef940-921e-4266-a174-d0024dd347c3",
  "user_id": "8a921023-0315-4419-9671-004a485da7a9",
  "title": "✅ Functionality Test Done",
  "chat": {
    "id": "196ef940-921e-4266-a174-d0024dd347c3",
    "title": "✅ Functionality Test Done",
    "models": [
      "openrouter/free"
    ],
    "history": {
      "currentId": "8b0e5ead-0024-45d9-93b7-3d5bb3994ef5",
      "messages": {
        "52589bb8-412c-4b8d-ac94-9e997b9763f1": {
          "id": "52589bb8-412c-4b8d-ac94-9e997b9763f1",
          "parentId": null,
          "childrenIds": [
            "8b0e5ead-0024-45d9-93b7-3d5bb3994ef5"
          ],
          "role": "user",
          "content": "test",
          "timestamp": 1777388868,
          "models": [
            "openrouter/free"
          ]
        },
        "8b0e5ead-0024-45d9-93b7-3d5bb3994ef5": {
          "id": "8b0e5ead-0024-45d9-93b7-3d5bb3994ef5",
          "parentId": "52589bb8-412c-4b8d-ac94-9e997b9763f1",
          "childrenIds": [],
          "role": "assistant",
          "content": "Test received! I am functioning correctly. How can I help you today?",
          "done": true,
          "model": "openrouter/free",
          "timestamp": 1777388868,
          "output": [
            {
              "type": "message",
              "id": "msg_59a70eb2ca1d4930bb2d7b28",
              "status": "completed",
              "role": "assistant",
              "content": [
                {
                  "type": "output_text",
                  "text": "Test received! I am functioning correctly. How can I help you today?"
                }
              ]
            }
          ],
          "usage": {
            "prompt_tokens": 4,
            "completion_tokens": 15,
            "total_tokens": 19,
            "cost": 0,
            "is_byok": false,
            "prompt_tokens_details": {
              "cached_tokens": 0,
              "cache_write_tokens": 0,
              "audio_tokens": 0,
              "video_tokens": 0
            },
            "cost_details": {
              "upstream_inference_cost": 0,
              "upstream_inference_prompt_cost": 0,
              "upstream_inference_completions_cost": 0
            },
            "completion_tokens_details": {
              "reasoning_tokens": 0,
              "image_tokens": 0,
              "audio_tokens": 0
            },
            "input_tokens": 4,
            "output_tokens": 15
          }
        }
      }
    },
    "messages": [
      {
        "role": "user",
        "content": "test"
      }
    ],
    "tags": [],
    "timestamp": 1777388868316
  },
  "updated_at": 1777388875,
  "created_at": 1777388868,
  "share_id": null,
  "archived": false,
  "pinned": false,
  "meta": {},
  "folder_id": null,
  "tasks": null,
  "summary": null
}

Completion API

As seen here, the frontend sends the system prompt

{
  "stream": true,
  "model": "openrouter/free",
  "messages": [
    {
      "role": "system",
      "content": "TEST SYSTEM PROMPT"
    }
  ],
  "params": {
    "system": "TEST SYSTEM PROMPT"
  },
  "tool_servers": [],
  "features": {
    "voice": false,
    "image_generation": false,
    "code_interpreter": false,
    "web_search": false
  },
  "variables": {
    "{{USER_NAME}}": "<redacted>",
    "{{USER_EMAIL}}": "<redacted>",
    "{{USER_LOCATION}}": "Unknown",
    "{{CURRENT_DATETIME}}": "2026-04-28 17:15:11",
    "{{CURRENT_DATE}}": "2026-04-28",
    "{{CURRENT_TIME}}": "17:15:11",
    "{{CURRENT_WEEKDAY}}": "Tuesday",
    "{{CURRENT_TIMEZONE}}": "Europe/Berlin",
    "{{USER_LANGUAGE}}": "en-US"
  },
  "model_item": {
    "id": "openrouter/free",
    "canonical_slug": "openrouter/free",
    "hugging_face_id": "",
    "name": "Free Models Router",
    "created": 1769917427,
    "description": "The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...",
    "context_length": 200000,
    "architecture": {
      "modality": "text+image->text",
      "input_modalities": [
        "text",
        "image"
      ],
      "output_modalities": [
        "text"
      ],
      "tokenizer": "Router",
      "instruct_type": null
    },
    "pricing": {
      "prompt": "0",
      "completion": "0"
    },
    "top_provider": {
      "context_length": null,
      "max_completion_tokens": null,
      "is_moderated": false
    },
    "per_request_limits": null,
    "supported_parameters": [
      "frequency_penalty",
      "include_reasoning",
      "max_tokens",
      "min_p",
      "presence_penalty",
      "reasoning",
      "repetition_penalty",
      "response_format",
      "seed",
      "stop",
      "structured_outputs",
      "temperature",
      "tool_choice",
      "tools",
      "top_k",
      "top_p"
    ],
    "default_parameters": {
      "temperature": null,
      "top_p": null,
      "frequency_penalty": null
    },
    "knowledge_cutoff": null,
    "expiration_date": null,
    "links": {
      "details": "/api/v1/models/openrouter/free/endpoints"
    },
    "connection_type": "external",
    "owned_by": "openai",
    "openai": {
      "id": "openrouter/free",
      "canonical_slug": "openrouter/free",
      "hugging_face_id": "",
      "name": "Free Models Router",
      "created": 1769917427,
      "description": "The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...",
      "context_length": 200000,
      "architecture": {
        "modality": "text+image->text",
        "input_modalities": [
          "text",
          "image"
        ],
        "output_modalities": [
          "text"
        ],
        "tokenizer": "Router",
        "instruct_type": null
      },
      "pricing": {
        "prompt": "0",
        "completion": "0"
      },
      "top_provider": {
        "context_length": null,
        "max_completion_tokens": null,
        "is_moderated": false
      },
      "per_request_limits": null,
      "supported_parameters": [
        "frequency_penalty",
        "include_reasoning",
        "max_tokens",
        "min_p",
        "presence_penalty",
        "reasoning",
        "repetition_penalty",
        "response_format",
        "seed",
        "stop",
        "structured_outputs",
        "temperature",
        "tool_choice",
        "tools",
        "top_k",
        "top_p"
      ],
      "default_parameters": {
        "temperature": null,
        "top_p": null,
        "frequency_penalty": null
      },
      "knowledge_cutoff": null,
      "expiration_date": null,
      "links": {
        "details": "/api/v1/models/openrouter/free/endpoints"
      },
      "connection_type": "external"
    },
    "urlIdx": 0,
    "actions": [],
    "filters": [],
    "tags": []
  },
  "session_id": "wnHYuA5JCC6ooNTHAAJZ",
  "id": "c4c1512e-4d50-4b1f-84c5-f20c1bad36a4",
  "parent_id": null,
  "user_message": {
    "id": "eab6a889-b324-49f9-bf1e-a0c9b1da34e2",
    "parentId": null,
    "childrenIds": [
      "c4c1512e-4d50-4b1f-84c5-f20c1bad36a4"
    ],
    "role": "user",
    "content": "Test",
    "timestamp": 1777389311,
    "models": [
      "openrouter/free"
    ]
  },
  "background_tasks": {
    "title_generation": true,
    "tags_generation": false,
    "follow_up_generation": false
  }
}

Firefox console logs

Pre-reload:

Invalid URI: a3c882c5-8450-4603-96aa-c24cbf5f60dd
GET  /static/favicon.png  [200]
GET  /api/v1/models/model/profile/image?id=pf1-.inflection/inflection-3-productivity  [302]
GET  /api/v1/models/model/profile/image?id=pf1-.inflection/inflection-3-pi  [302]
GET  /api/v1/models/model/profile/image?id=pf1-.alfredpros/codellama-7b-instruct-solidity  [302]
GET  /api/v1/models/model/profile/image?id=pf1-.microsoft/phi-4  [302]
GET  /api/v1/models/model/profile/image?id=pf1-.liquid/lfm-2-24b-a2b  [302]
GET  /api/v1/models/model/profile/image?id=pf1-.stepfun/step-3.5-flash  [302]
GET  /api/v1/models/model/profile/image?id=pf1-.rekaai/reka-flash-3  [302]
GET  /api/v1/models/model/profile/image?id=pf1-.liquid/lfm-2.5-1.2b-thinking:free  [302]
GET  /api/v1/models/model/profile/image?id=pf1-.liquid/lfm-2.5-1.2b-instruct:free  [302]
GET  /api/v1/models/model/profile/image?id=pf1-.baidu/qianfan-ocr-fast:free  [302]
GET  /api/v1/models/model/profile/image?id=pf1-.xiaomi/mimo-v2-flash  [302]
GET  /api/v1/models/model/profile/image?id=pf1-.qwen/qwen3.5-flash-02-23  [302]
GET  /api/v1/models/model/profile/image?id=pf1-.openai/gpt-oss-safeguard-20b  [302]
GET  /api/v1/models/model/profile/image?id=pf1-.openai/gpt-oss-20b:free  [302]
GET  /api/v1/models/model/profile/image?id=pf1-.openai/gpt-oss-120b:free  [302]
GET  /api/v1/models/model/profile/image?id=pf1-.z-ai/glm-4.5-air:free  [302]
GET  /api/v1/models/model/profile/image?id=inflection/inflection-3-productivity  [302]
GET  /api/v1/models/model/profile/image?id=inflection/inflection-3-pi  [302]
GET  /api/v1/models/model/profile/image?id=alfredpros/codellama-7b-instruct-solidity  [302]
GET  /api/v1/models/model/profile/image?id=minimax/minimax-m2.5:free  [200]
GET  /api/v1/models/model/profile/image?id=openai/gpt-oss-20b:free  [302]
GET  /api/v1/models/model/profile/image?id=z-ai/glm-4.5-air:free  [302]
GET  /api/v1/models/model/profile/image?id=qwen/qwen3-coder:free  [302]
GET  /api/v1/models/model/profile/image?id=google/gemma-3-4b-it:free  [302]
GET  /api/v1/models/model/profile/image?id=tencent/hy3-preview:free  [302]
GET  /api/v1/models/model/profile/image?id=openai/gpt-oss-120b:free  [302]
GET  /api/v1/models/model/profile/image?id=baidu/qianfan-ocr-fast:free  [302]
GET  /api/v1/models/model/profile/image?id=google/gemma-4-31b-it:free  [302]
GET  /api/v1/models/model/profile/image?id=google/gemma-3-12b-it:free  [302]
GET  /api/v1/models/model/profile/image?id=google/gemma-3-27b-it:free  [302]
GET  /api/v1/models/model/profile/image?id=inclusionai/ling-2.6-1t:free  [302]
GET  /api/v1/models/model/profile/image?id=openrouter/free  [302]
XHR GET   /api/v1/tools/  [200]
XHR POST  /api/chat/completions  [200]
XHR GET   /api/v1/chats/?page=1  [200]

Post-reload:

Invalid URI: a3c882c5-8450-4603-96aa-c24cbf5f60dd
GET  /static/favicon.png  [200]
GET  /static/favicon.svg  [200]
GET  /static/apple-touch-icon.png  [200]
GET  /assets/fonts/Inter-Variable.ttf  [200]
GET  /assets/fonts/Archivo-Variable.ttf  [200]
GET  /_app/immutable/chunks/*.js  [200]  (many)
GET  /_app/immutable/assets/*.css  [200]  (many)
GET  /_app/immutable/nodes/23.BAV26l4u.js  [200]
GET  data:image/png;base64,...  (1x1 placeholder)
GET  /api/v1/models/model/profile/image?id=openrouter/free  [200/302]
GET  /api/v1/users/8a921023-.../profile/image  [200]
WSS  /ws/socket.io/?EIO=4&transport=websocket  [101]
XHR GET   /api/config  [200]
XHR GET   /api/v1/auths/  [200]
XHR GET   /api/v1/users/user/settings  [200]
XHR POST  /api/v1/auths/update/timezone  [200]
XHR GET   /api/v1/configs/banners  [200]
XHR GET   /api/v1/tools/  [200]
XHR GET   /api/v1/functions/  [200]
XHR GET   /api/v1/terminals/  [200]
XHR GET   /api/models?  [200]
XHR GET   /api/version  [200]
XHR GET   /api/version/updates  [200]
XHR GET   /api/v1/chats/196ef940-...  [200]
XHR GET   /api/v1/chats/196ef940-.../tags  [200]
XHR GET   /api/tasks/chat/196ef940-...  [200]
CSS Error: invalid 'text-decoration'  [Chat.BfPPNywX.css:32]
CSS Error: unknown property 'undefined'  [196ef940-...:1]
Invalid URI: 196ef940-921e-4266-a174-d0024dd347c3

URLS for pre-reload and post-reload have been de duplicated for readability.

Docker Compose config

services:
  qdrant:
    image: qdrant/qdrant:latest
    container_name: qdrant
    volumes:
      - /mnt/nvme1n1/open-webui-jennifer/qdrant_db:/qdrant/storage
    ports:
      - 127.0.0.1:6333:6333
    restart: unless-stopped

  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: open-webui
    volumes:
      - /mnt/nvme1n1/open-webui-jennifer/owi:/app/backend/data
      - /mnt/nvme1n1/open-webui-jennifer/qdrant_multitenancy_patched.py:/app/backend/open_webui/retrieval/vector/dbs/qdrant_multitenancy.py:ro
    ports:
      - 127.0.0.1:51241:8080
    environment:
      - 'WEBUI_SECRET_KEY=<redacted>'
      - 'VECTOR_DB=qdrant'
      - 'QDRANT_URI=http://qdrant:6333'
      - 'RAG_EMBEDDING_MODEL=BAAI/bge-large-en-v1.5'
    extra_hosts:
      - host.docker.internal:host-gateway
    depends_on:
      - qdrant
    restart: unless-stopped

Additional Information

If i reload old chats, the system prompt stays there.

Originally created by @Scarjit on GitHub (Apr 28, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/24193 ### Check Existing Issues - [x] I have searched for any existing and/or related issues. - [x] I have searched for any existing and/or related discussions. - [x] I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!). - [x] I am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version v0.9.2 ### Ollama Version (if applicable) _No response_ ### Operating System Arch Linux x86_64 (Linux 7.0.1-1-cachyos-eevdf) ### Browser (if applicable) Firefox 150.0 (64-bit) ### Confirmation - [x] I have read and followed all instructions in `README.md`. - [x] I am using the latest version of **both** Open WebUI and Ollama. - [x] I have included the browser console logs. - [x] I have included the Docker container logs. - [x] I have **provided every relevant configuration, setting, and environment variable used in my setup.** - [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc). - [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps: - Start with the initial platform/version/OS and dependencies used, - Specify exact install/launch/configure commands, - List URLs visited, user input (incl. example values/emails/passwords if needed), - Describe all options and toggles enabled or changed, - Include any files or environmental changes, - Identify the expected and actual result at each stage, - Ensure any reasonably skilled user can follow and hit the same issue. ### Expected Behavior System prompt should be shown (and applied for completions) after page reload ### Actual Behavior System prompt is empty after reload ### Steps to Reproduce 1. Create a new chat 2. Enter a system prompt 3. Send a chat message 4. Reload your page The same behavior is consistent across multiple devices (PC, Android) and Browsers (Firefox, Chromium). ### Logs & Screenshots https://github.com/user-attachments/assets/3cf2c682-7e8b-4674-bc87-62a531488b16 [Docker logs](https://github.com/user-attachments/files/27171702/open-webui_logs.txt) ## API response As seen here the system prompt is not returned. ```json { "id": "196ef940-921e-4266-a174-d0024dd347c3", "user_id": "8a921023-0315-4419-9671-004a485da7a9", "title": "✅ Functionality Test Done", "chat": { "id": "196ef940-921e-4266-a174-d0024dd347c3", "title": "✅ Functionality Test Done", "models": [ "openrouter/free" ], "history": { "currentId": "8b0e5ead-0024-45d9-93b7-3d5bb3994ef5", "messages": { "52589bb8-412c-4b8d-ac94-9e997b9763f1": { "id": "52589bb8-412c-4b8d-ac94-9e997b9763f1", "parentId": null, "childrenIds": [ "8b0e5ead-0024-45d9-93b7-3d5bb3994ef5" ], "role": "user", "content": "test", "timestamp": 1777388868, "models": [ "openrouter/free" ] }, "8b0e5ead-0024-45d9-93b7-3d5bb3994ef5": { "id": "8b0e5ead-0024-45d9-93b7-3d5bb3994ef5", "parentId": "52589bb8-412c-4b8d-ac94-9e997b9763f1", "childrenIds": [], "role": "assistant", "content": "Test received! I am functioning correctly. How can I help you today?", "done": true, "model": "openrouter/free", "timestamp": 1777388868, "output": [ { "type": "message", "id": "msg_59a70eb2ca1d4930bb2d7b28", "status": "completed", "role": "assistant", "content": [ { "type": "output_text", "text": "Test received! I am functioning correctly. How can I help you today?" } ] } ], "usage": { "prompt_tokens": 4, "completion_tokens": 15, "total_tokens": 19, "cost": 0, "is_byok": false, "prompt_tokens_details": { "cached_tokens": 0, "cache_write_tokens": 0, "audio_tokens": 0, "video_tokens": 0 }, "cost_details": { "upstream_inference_cost": 0, "upstream_inference_prompt_cost": 0, "upstream_inference_completions_cost": 0 }, "completion_tokens_details": { "reasoning_tokens": 0, "image_tokens": 0, "audio_tokens": 0 }, "input_tokens": 4, "output_tokens": 15 } } } }, "messages": [ { "role": "user", "content": "test" } ], "tags": [], "timestamp": 1777388868316 }, "updated_at": 1777388875, "created_at": 1777388868, "share_id": null, "archived": false, "pinned": false, "meta": {}, "folder_id": null, "tasks": null, "summary": null } ``` ## Completion API As seen here, the frontend sends the system prompt ```json { "stream": true, "model": "openrouter/free", "messages": [ { "role": "system", "content": "TEST SYSTEM PROMPT" } ], "params": { "system": "TEST SYSTEM PROMPT" }, "tool_servers": [], "features": { "voice": false, "image_generation": false, "code_interpreter": false, "web_search": false }, "variables": { "{{USER_NAME}}": "<redacted>", "{{USER_EMAIL}}": "<redacted>", "{{USER_LOCATION}}": "Unknown", "{{CURRENT_DATETIME}}": "2026-04-28 17:15:11", "{{CURRENT_DATE}}": "2026-04-28", "{{CURRENT_TIME}}": "17:15:11", "{{CURRENT_WEEKDAY}}": "Tuesday", "{{CURRENT_TIMEZONE}}": "Europe/Berlin", "{{USER_LANGUAGE}}": "en-US" }, "model_item": { "id": "openrouter/free", "canonical_slug": "openrouter/free", "hugging_face_id": "", "name": "Free Models Router", "created": 1769917427, "description": "The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...", "context_length": 200000, "architecture": { "modality": "text+image->text", "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "tokenizer": "Router", "instruct_type": null }, "pricing": { "prompt": "0", "completion": "0" }, "top_provider": { "context_length": null, "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "knowledge_cutoff": null, "expiration_date": null, "links": { "details": "/api/v1/models/openrouter/free/endpoints" }, "connection_type": "external", "owned_by": "openai", "openai": { "id": "openrouter/free", "canonical_slug": "openrouter/free", "hugging_face_id": "", "name": "Free Models Router", "created": 1769917427, "description": "The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...", "context_length": 200000, "architecture": { "modality": "text+image->text", "input_modalities": [ "text", "image" ], "output_modalities": [ "text" ], "tokenizer": "Router", "instruct_type": null }, "pricing": { "prompt": "0", "completion": "0" }, "top_provider": { "context_length": null, "max_completion_tokens": null, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "frequency_penalty", "include_reasoning", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "default_parameters": { "temperature": null, "top_p": null, "frequency_penalty": null }, "knowledge_cutoff": null, "expiration_date": null, "links": { "details": "/api/v1/models/openrouter/free/endpoints" }, "connection_type": "external" }, "urlIdx": 0, "actions": [], "filters": [], "tags": [] }, "session_id": "wnHYuA5JCC6ooNTHAAJZ", "id": "c4c1512e-4d50-4b1f-84c5-f20c1bad36a4", "parent_id": null, "user_message": { "id": "eab6a889-b324-49f9-bf1e-a0c9b1da34e2", "parentId": null, "childrenIds": [ "c4c1512e-4d50-4b1f-84c5-f20c1bad36a4" ], "role": "user", "content": "Test", "timestamp": 1777389311, "models": [ "openrouter/free" ] }, "background_tasks": { "title_generation": true, "tags_generation": false, "follow_up_generation": false } } ``` ## Firefox console logs Pre-reload: ``` Invalid URI: a3c882c5-8450-4603-96aa-c24cbf5f60dd GET /static/favicon.png [200] GET /api/v1/models/model/profile/image?id=pf1-.inflection/inflection-3-productivity [302] GET /api/v1/models/model/profile/image?id=pf1-.inflection/inflection-3-pi [302] GET /api/v1/models/model/profile/image?id=pf1-.alfredpros/codellama-7b-instruct-solidity [302] GET /api/v1/models/model/profile/image?id=pf1-.microsoft/phi-4 [302] GET /api/v1/models/model/profile/image?id=pf1-.liquid/lfm-2-24b-a2b [302] GET /api/v1/models/model/profile/image?id=pf1-.stepfun/step-3.5-flash [302] GET /api/v1/models/model/profile/image?id=pf1-.rekaai/reka-flash-3 [302] GET /api/v1/models/model/profile/image?id=pf1-.liquid/lfm-2.5-1.2b-thinking:free [302] GET /api/v1/models/model/profile/image?id=pf1-.liquid/lfm-2.5-1.2b-instruct:free [302] GET /api/v1/models/model/profile/image?id=pf1-.baidu/qianfan-ocr-fast:free [302] GET /api/v1/models/model/profile/image?id=pf1-.xiaomi/mimo-v2-flash [302] GET /api/v1/models/model/profile/image?id=pf1-.qwen/qwen3.5-flash-02-23 [302] GET /api/v1/models/model/profile/image?id=pf1-.openai/gpt-oss-safeguard-20b [302] GET /api/v1/models/model/profile/image?id=pf1-.openai/gpt-oss-20b:free [302] GET /api/v1/models/model/profile/image?id=pf1-.openai/gpt-oss-120b:free [302] GET /api/v1/models/model/profile/image?id=pf1-.z-ai/glm-4.5-air:free [302] GET /api/v1/models/model/profile/image?id=inflection/inflection-3-productivity [302] GET /api/v1/models/model/profile/image?id=inflection/inflection-3-pi [302] GET /api/v1/models/model/profile/image?id=alfredpros/codellama-7b-instruct-solidity [302] GET /api/v1/models/model/profile/image?id=minimax/minimax-m2.5:free [200] GET /api/v1/models/model/profile/image?id=openai/gpt-oss-20b:free [302] GET /api/v1/models/model/profile/image?id=z-ai/glm-4.5-air:free [302] GET /api/v1/models/model/profile/image?id=qwen/qwen3-coder:free [302] GET /api/v1/models/model/profile/image?id=google/gemma-3-4b-it:free [302] GET /api/v1/models/model/profile/image?id=tencent/hy3-preview:free [302] GET /api/v1/models/model/profile/image?id=openai/gpt-oss-120b:free [302] GET /api/v1/models/model/profile/image?id=baidu/qianfan-ocr-fast:free [302] GET /api/v1/models/model/profile/image?id=google/gemma-4-31b-it:free [302] GET /api/v1/models/model/profile/image?id=google/gemma-3-12b-it:free [302] GET /api/v1/models/model/profile/image?id=google/gemma-3-27b-it:free [302] GET /api/v1/models/model/profile/image?id=inclusionai/ling-2.6-1t:free [302] GET /api/v1/models/model/profile/image?id=openrouter/free [302] XHR GET /api/v1/tools/ [200] XHR POST /api/chat/completions [200] XHR GET /api/v1/chats/?page=1 [200] ``` Post-reload: ``` Invalid URI: a3c882c5-8450-4603-96aa-c24cbf5f60dd GET /static/favicon.png [200] GET /static/favicon.svg [200] GET /static/apple-touch-icon.png [200] GET /assets/fonts/Inter-Variable.ttf [200] GET /assets/fonts/Archivo-Variable.ttf [200] GET /_app/immutable/chunks/*.js [200] (many) GET /_app/immutable/assets/*.css [200] (many) GET /_app/immutable/nodes/23.BAV26l4u.js [200] GET data:image/png;base64,... (1x1 placeholder) GET /api/v1/models/model/profile/image?id=openrouter/free [200/302] GET /api/v1/users/8a921023-.../profile/image [200] WSS /ws/socket.io/?EIO=4&transport=websocket [101] XHR GET /api/config [200] XHR GET /api/v1/auths/ [200] XHR GET /api/v1/users/user/settings [200] XHR POST /api/v1/auths/update/timezone [200] XHR GET /api/v1/configs/banners [200] XHR GET /api/v1/tools/ [200] XHR GET /api/v1/functions/ [200] XHR GET /api/v1/terminals/ [200] XHR GET /api/models? [200] XHR GET /api/version [200] XHR GET /api/version/updates [200] XHR GET /api/v1/chats/196ef940-... [200] XHR GET /api/v1/chats/196ef940-.../tags [200] XHR GET /api/tasks/chat/196ef940-... [200] CSS Error: invalid 'text-decoration' [Chat.BfPPNywX.css:32] CSS Error: unknown property 'undefined' [196ef940-...:1] Invalid URI: 196ef940-921e-4266-a174-d0024dd347c3 ``` URLS for pre-reload and post-reload have been de duplicated for readability. ## Docker Compose config ```yaml services: qdrant: image: qdrant/qdrant:latest container_name: qdrant volumes: - /mnt/nvme1n1/open-webui-jennifer/qdrant_db:/qdrant/storage ports: - 127.0.0.1:6333:6333 restart: unless-stopped open-webui: image: ghcr.io/open-webui/open-webui:main container_name: open-webui volumes: - /mnt/nvme1n1/open-webui-jennifer/owi:/app/backend/data - /mnt/nvme1n1/open-webui-jennifer/qdrant_multitenancy_patched.py:/app/backend/open_webui/retrieval/vector/dbs/qdrant_multitenancy.py:ro ports: - 127.0.0.1:51241:8080 environment: - 'WEBUI_SECRET_KEY=<redacted>' - 'VECTOR_DB=qdrant' - 'QDRANT_URI=http://qdrant:6333' - 'RAG_EMBEDDING_MODEL=BAAI/bge-large-en-v1.5' extra_hosts: - host.docker.internal:host-gateway depends_on: - qdrant restart: unless-stopped ``` ### Additional Information If i reload old chats, the system prompt stays there.
GiteaMirror added the bug label 2026-05-06 00:22:16 -05:00
GiteaMirror commented 2026-05-06 00:22:19 -05:00
Author
Owner
Copy Link

@Intcc commented on GitHub (May 1, 2026):

i have the same issue, fresh install - no global system prompt there.

<!-- gh-comment-id:4359285971 --> @Intcc commented on GitHub (May 1, 2026): i have the same issue, fresh install - no global system prompt there.
GiteaMirror commented 2026-05-06 00:22:21 -05:00
Author
Owner
Copy Link

@Classic298 commented on GitHub (May 4, 2026):

likely fixed by

86df8bf27e

testing wanted

<!-- gh-comment-id:4373656236 --> @Classic298 commented on GitHub (May 4, 2026): likely fixed by https://github.com/open-webui/open-webui/commit/86df8bf27e1b84abbe2eeedcc8650df59c7d23d6 testing wanted
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#58893
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?