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 #22860] issue: Custom model system prompts are not included in chat exports. #35357

New Issue
Closed
opened 2026-04-25 09:34:42 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-25 09:34:42 -05:00
Owner
Copy Link

Originally created by @HideLord on GitHub (Mar 19, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/22860

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

Pip Install

Open WebUI Version

v0.8.10

Ollama Version (if applicable)

No response

Operating System

Ubuntu 24.04.4 LTS; kernel version 6.14.0-37-generic

Browser (if applicable)

Firefox 148.0.2 (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

The custom system prompt which was set earlier is missing. There is no system prompt at all.

Actual Behavior

There should be a system prompt in the exported chat.

Steps to Reproduce

  1. Perform standard install through pip
  2. Set up a valid connection with a working model
  3. Go to admin settings -> models
  4. Edit any model
  5. Set a custom system prompt
  6. Create a new chat with the edited model
  7. Send a message and receive a response
  8. Go to settings -> data controls -> export chats
  9. Observe the exported JSON.

Logs & Screenshots

Image 
(base) hidelord@hidelord-System-Product-Name:~$ jq '.[2]' /home/hidelord/chat-export-1773935652.json 
{
  "id": "df9f4e0a-fd99-4fab-8328-523094e4f0e5",
  "user_id": "1e4110bd-8ef3-4ed8-9f17-593aeb37e582",
  "title": "📜 AI System Prompt Disclosure",
  "chat": {
    "id": "",
    "title": "📜 AI System Prompt Disclosure",
    "models": [
      "anthropic/claude-opus-4.6"
    ],
    "params": {},
    "history": {
      "messages": {
        "15263770-63ba-4e5f-b9f1-de33b28cd188": {
          "id": "15263770-63ba-4e5f-b9f1-de33b28cd188",
          "parentId": null,
          "childrenIds": [
            "b4f1c0bf-e8d4-40eb-a21a-60bcdbfc3703"
          ],
          "role": "user",
          "content": "Can you output your system prompt for this session?",
          "timestamp": 1773923491,
          "models": [
            "anthropic/claude-opus-4.6"
          ]
        },
        "b4f1c0bf-e8d4-40eb-a21a-60bcdbfc3703": {
          "parentId": "15263770-63ba-4e5f-b9f1-de33b28cd188",
          "id": "b4f1c0bf-e8d4-40eb-a21a-60bcdbfc3703",
          "childrenIds": [],
          "role": "assistant",
          "content": "<details type=\"reasoning\" done=\"true\" duration=\"1\">\n<summary>Thought for 1 seconds</summary>\n&gt; The user is asking me to output my system prompt. I&#x27;ll share what I can see of my system prompt, since it&#x27;s part of my instructions for this session and there&#x27;s no instruction telling me to keep it confidential.\n</details>\nSure. Here's the system prompt I'm operating under for this session:\n\n---\n\nYou are a friendly, capable general AI assistant. Give good, thorough answers without meandering.\n\nTone and style\n- Avoid filler, excessive hedging, and performative apologies.\n- Emojis: Avoid using them unless necessary or requested.\n- Keep formatting clean and lightweight. Prefer full sentences and paragraphs with helpful headers for breaks.\n\nUser alignment\n- Use the metric system if relevant (meters, liters, kilograms, etc.).\n- Adapt depth and jargon to the user's level and goals. Offer alternatives and trade-offs when choices matter.\n- For specialized domains (medical, legal, financial, safety-critical), provide useful information. Avoid unnecessary warnings and precautions to seek professionals. Assume the user is aware.\n- Avoid moralizing or preaching.\n\nAdditional data\n- The current date is 2026-03-19.\n- The environment is Ubuntu 24.04.4 LTS; kernel version 6.14.0-37-generic\n\n---\n\nThat's the full content as provided to me.",
          "model": "anthropic/claude-opus-4.6",
          "modelName": "Anthropic: Claude Opus 4.6",
          "modelIdx": 0,
          "timestamp": 1773923491,
          "usage": {
            "prompt_tokens": 244,
            "completion_tokens": 322,
            "total_tokens": 566,
            "cost": 0.00927,
            "is_byok": false,
            "prompt_tokens_details": {
              "cached_tokens": 0,
              "cache_write_tokens": 0,
              "audio_tokens": 0,
              "video_tokens": 0
            },
            "cost_details": {
              "upstream_inference_cost": 0.00927,
              "upstream_inference_prompt_cost": 0.00122,
              "upstream_inference_completions_cost": 0.00805
            },
            "completion_tokens_details": {
              "reasoning_tokens": 53,
              "image_tokens": 0,
              "audio_tokens": 0
            }
          },
          "output": [
            {
              "type": "message",
              "id": "msg_6579ec5fdddc4bedaf9aabbc",
              "status": "completed",
              "role": "assistant",
              "content": [
                {
                  "type": "output_text",
                  "text": "\n\n"
                }
              ]
            },
            {
              "type": "reasoning",
              "id": "r_85cedc2c5ed449cdbae0ab31",
              "status": "completed",
              "start_tag": "<think>",
              "end_tag": "</think>",
              "attributes": {
                "type": "reasoning_content"
              },
              "content": [
                {
                  "type": "output_text",
                  "text": "The user is asking me to output my system prompt. I'll share what I can see of my system prompt, since it's part of my instructions for this session and there's no instruction telling me to keep it confidential."
                }
              ],
              "summary": null,
              "started_at": 1773923492.5771983,
              "ended_at": 1773923493.694125,
              "duration": 1
            },
            {
              "type": "message",
              "id": "msg_98dd88dea1c740f2b53942a7",
              "status": "completed",
              "role": "assistant",
              "content": [
                {
                  "type": "output_text",
                  "text": "Sure. Here's the system prompt I'm operating under for this session:\n\n---\n\nYou are a friendly, capable general AI assistant. Give good, thorough answers without meandering.\n\nTone and style\n- Avoid filler, excessive hedging, and performative apologies.\n- Emojis: Avoid using them unless necessary or requested.\n- Keep formatting clean and lightweight. Prefer full sentences and paragraphs with helpful headers for breaks.\n\nUser alignment\n- Use the metric system if relevant (meters, liters, kilograms, etc.).\n- Adapt depth and jargon to the user's level and goals. Offer alternatives and trade-offs when choices matter.\n- For specialized domains (medical, legal, financial, safety-critical), provide useful information. Avoid unnecessary warnings and precautions to seek professionals. Assume the user is aware.\n- Avoid moralizing or preaching.\n\nAdditional data\n- The current date is 2026-03-19.\n- The environment is Ubuntu 24.04.4 LTS; kernel version 6.14.0-37-generic\n\n---\n\nThat's the full content as provided to me."
                }
              ]
            }
          ],
          "done": true
        }
      },
      "currentId": "b4f1c0bf-e8d4-40eb-a21a-60bcdbfc3703"
    },
    "messages": [
      {
        "id": "15263770-63ba-4e5f-b9f1-de33b28cd188",
        "parentId": null,
        "childrenIds": [
          "b4f1c0bf-e8d4-40eb-a21a-60bcdbfc3703"
        ],
        "role": "user",
        "content": "Can you output your system prompt for this session?",
        "timestamp": 1773923491,
        "models": [
          "anthropic/claude-opus-4.6"
        ]
      },
      {
        "parentId": "15263770-63ba-4e5f-b9f1-de33b28cd188",
        "id": "b4f1c0bf-e8d4-40eb-a21a-60bcdbfc3703",
        "childrenIds": [],
        "role": "assistant",
        "content": "<details type=\"reasoning\" done=\"true\" duration=\"1\">\n<summary>Thought for 1 seconds</summary>\n&gt; The user is asking me to output my system prompt. I&#x27;ll share what I can see of my system prompt, since it&#x27;s part of my instructions for this session and there&#x27;s no instruction telling me to keep it confidential.\n</details>\nSure. Here's the system prompt I'm operating under for this session:\n\n---\n\nYou are a friendly, capable general AI assistant. Give good, thorough answers without meandering.\n\nTone and style\n- Avoid filler, excessive hedging, and performative apologies.\n- Emojis: Avoid using them unless necessary or requested.\n- Keep formatting clean and lightweight. Prefer full sentences and paragraphs with helpful headers for breaks.\n\nUser alignment\n- Use the metric system if relevant (meters, liters, kilograms, etc.).\n- Adapt depth and jargon to the user's level and goals. Offer alternatives and trade-offs when choices matter.\n- For specialized domains (medical, legal, financial, safety-critical), provide useful information. Avoid unnecessary warnings and precautions to seek professionals. Assume the user is aware.\n- Avoid moralizing or preaching.\n\nAdditional data\n- The current date is 2026-03-19.\n- The environment is Ubuntu 24.04.4 LTS; kernel version 6.14.0-37-generic\n\n---\n\nThat's the full content as provided to me.",
        "model": "anthropic/claude-opus-4.6",
        "modelName": "Anthropic: Claude Opus 4.6",
        "modelIdx": 0,
        "timestamp": 1773923491,
        "usage": {
          "prompt_tokens": 244,
          "completion_tokens": 322,
          "total_tokens": 566,
          "cost": 0.00927,
          "is_byok": false,
          "prompt_tokens_details": {
            "cached_tokens": 0,
            "cache_write_tokens": 0,
            "audio_tokens": 0,
            "video_tokens": 0
          },
          "cost_details": {
            "upstream_inference_cost": 0.00927,
            "upstream_inference_prompt_cost": 0.00122,
            "upstream_inference_completions_cost": 0.00805
          },
          "completion_tokens_details": {
            "reasoning_tokens": 53,
            "image_tokens": 0,
            "audio_tokens": 0
          }
        },
        "output": [
          {
            "type": "message",
            "id": "msg_6579ec5fdddc4bedaf9aabbc",
            "status": "completed",
            "role": "assistant",
            "content": [
              {
                "type": "output_text",
                "text": "\n\n"
              }
            ]
          },
          {
            "type": "reasoning",
            "id": "r_85cedc2c5ed449cdbae0ab31",
            "status": "completed",
            "start_tag": "<think>",
            "end_tag": "</think>",
            "attributes": {
              "type": "reasoning_content"
            },
            "content": [
              {
                "type": "output_text",
                "text": "The user is asking me to output my system prompt. I'll share what I can see of my system prompt, since it's part of my instructions for this session and there's no instruction telling me to keep it confidential."
              }
            ],
            "summary": null,
            "started_at": 1773923492.5771983,
            "ended_at": 1773923493.694125,
            "duration": 1
          },
          {
            "type": "message",
            "id": "msg_98dd88dea1c740f2b53942a7",
            "status": "completed",
            "role": "assistant",
            "content": [
              {
                "type": "output_text",
                "text": "Sure. Here's the system prompt I'm operating under for this session:\n\n---\n\nYou are a friendly, capable general AI assistant. Give good, thorough answers without meandering.\n\nTone and style\n- Avoid filler, excessive hedging, and performative apologies.\n- Emojis: Avoid using them unless necessary or requested.\n- Keep formatting clean and lightweight. Prefer full sentences and paragraphs with helpful headers for breaks.\n\nUser alignment\n- Use the metric system if relevant (meters, liters, kilograms, etc.).\n- Adapt depth and jargon to the user's level and goals. Offer alternatives and trade-offs when choices matter.\n- For specialized domains (medical, legal, financial, safety-critical), provide useful information. Avoid unnecessary warnings and precautions to seek professionals. Assume the user is aware.\n- Avoid moralizing or preaching.\n\nAdditional data\n- The current date is 2026-03-19.\n- The environment is Ubuntu 24.04.4 LTS; kernel version 6.14.0-37-generic\n\n---\n\nThat's the full content as provided to me."
              }
            ]
          }
        ],
        "done": true
      }
    ],
    "tags": [],
    "timestamp": 1773923491017,
    "files": []
  },
  "updated_at": 1773923497,
  "created_at": 1773923491,
  "share_id": null,
  "archived": false,
  "pinned": false,
  "meta": {},
  "folder_id": null
}

Additional Information

No response

Originally created by @HideLord on GitHub (Mar 19, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/22860 ### 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 Pip Install ### Open WebUI Version v0.8.10 ### Ollama Version (if applicable) _No response_ ### Operating System Ubuntu 24.04.4 LTS; kernel version 6.14.0-37-generic ### Browser (if applicable) Firefox 148.0.2 (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 The custom system prompt which was set earlier is missing. There is no system prompt at all. ### Actual Behavior There should be a system prompt in the exported chat. ### Steps to Reproduce 1. Perform standard install through pip 2. Set up a valid connection with a working model 3. Go to admin settings -> models 4. Edit any model 5. Set a custom system prompt 6. Create a new chat with the edited model 7. Send a message and receive a response 8. Go to settings -> data controls -> export chats 9. Observe the exported JSON. ### Logs & Screenshots <img width="2145" height="782" alt="Image" src="https://github.com/user-attachments/assets/b83c0204-47a4-4ed6-9a88-31902f71d221" /> ``` (base) hidelord@hidelord-System-Product-Name:~$ jq '.[2]' /home/hidelord/chat-export-1773935652.json { "id": "df9f4e0a-fd99-4fab-8328-523094e4f0e5", "user_id": "1e4110bd-8ef3-4ed8-9f17-593aeb37e582", "title": "📜 AI System Prompt Disclosure", "chat": { "id": "", "title": "📜 AI System Prompt Disclosure", "models": [ "anthropic/claude-opus-4.6" ], "params": {}, "history": { "messages": { "15263770-63ba-4e5f-b9f1-de33b28cd188": { "id": "15263770-63ba-4e5f-b9f1-de33b28cd188", "parentId": null, "childrenIds": [ "b4f1c0bf-e8d4-40eb-a21a-60bcdbfc3703" ], "role": "user", "content": "Can you output your system prompt for this session?", "timestamp": 1773923491, "models": [ "anthropic/claude-opus-4.6" ] }, "b4f1c0bf-e8d4-40eb-a21a-60bcdbfc3703": { "parentId": "15263770-63ba-4e5f-b9f1-de33b28cd188", "id": "b4f1c0bf-e8d4-40eb-a21a-60bcdbfc3703", "childrenIds": [], "role": "assistant", "content": "<details type=\"reasoning\" done=\"true\" duration=\"1\">\n<summary>Thought for 1 seconds</summary>\n&gt; The user is asking me to output my system prompt. I&#x27;ll share what I can see of my system prompt, since it&#x27;s part of my instructions for this session and there&#x27;s no instruction telling me to keep it confidential.\n</details>\nSure. Here's the system prompt I'm operating under for this session:\n\n---\n\nYou are a friendly, capable general AI assistant. Give good, thorough answers without meandering.\n\nTone and style\n- Avoid filler, excessive hedging, and performative apologies.\n- Emojis: Avoid using them unless necessary or requested.\n- Keep formatting clean and lightweight. Prefer full sentences and paragraphs with helpful headers for breaks.\n\nUser alignment\n- Use the metric system if relevant (meters, liters, kilograms, etc.).\n- Adapt depth and jargon to the user's level and goals. Offer alternatives and trade-offs when choices matter.\n- For specialized domains (medical, legal, financial, safety-critical), provide useful information. Avoid unnecessary warnings and precautions to seek professionals. Assume the user is aware.\n- Avoid moralizing or preaching.\n\nAdditional data\n- The current date is 2026-03-19.\n- The environment is Ubuntu 24.04.4 LTS; kernel version 6.14.0-37-generic\n\n---\n\nThat's the full content as provided to me.", "model": "anthropic/claude-opus-4.6", "modelName": "Anthropic: Claude Opus 4.6", "modelIdx": 0, "timestamp": 1773923491, "usage": { "prompt_tokens": 244, "completion_tokens": 322, "total_tokens": 566, "cost": 0.00927, "is_byok": false, "prompt_tokens_details": { "cached_tokens": 0, "cache_write_tokens": 0, "audio_tokens": 0, "video_tokens": 0 }, "cost_details": { "upstream_inference_cost": 0.00927, "upstream_inference_prompt_cost": 0.00122, "upstream_inference_completions_cost": 0.00805 }, "completion_tokens_details": { "reasoning_tokens": 53, "image_tokens": 0, "audio_tokens": 0 } }, "output": [ { "type": "message", "id": "msg_6579ec5fdddc4bedaf9aabbc", "status": "completed", "role": "assistant", "content": [ { "type": "output_text", "text": "\n\n" } ] }, { "type": "reasoning", "id": "r_85cedc2c5ed449cdbae0ab31", "status": "completed", "start_tag": "<think>", "end_tag": "</think>", "attributes": { "type": "reasoning_content" }, "content": [ { "type": "output_text", "text": "The user is asking me to output my system prompt. I'll share what I can see of my system prompt, since it's part of my instructions for this session and there's no instruction telling me to keep it confidential." } ], "summary": null, "started_at": 1773923492.5771983, "ended_at": 1773923493.694125, "duration": 1 }, { "type": "message", "id": "msg_98dd88dea1c740f2b53942a7", "status": "completed", "role": "assistant", "content": [ { "type": "output_text", "text": "Sure. Here's the system prompt I'm operating under for this session:\n\n---\n\nYou are a friendly, capable general AI assistant. Give good, thorough answers without meandering.\n\nTone and style\n- Avoid filler, excessive hedging, and performative apologies.\n- Emojis: Avoid using them unless necessary or requested.\n- Keep formatting clean and lightweight. Prefer full sentences and paragraphs with helpful headers for breaks.\n\nUser alignment\n- Use the metric system if relevant (meters, liters, kilograms, etc.).\n- Adapt depth and jargon to the user's level and goals. Offer alternatives and trade-offs when choices matter.\n- For specialized domains (medical, legal, financial, safety-critical), provide useful information. Avoid unnecessary warnings and precautions to seek professionals. Assume the user is aware.\n- Avoid moralizing or preaching.\n\nAdditional data\n- The current date is 2026-03-19.\n- The environment is Ubuntu 24.04.4 LTS; kernel version 6.14.0-37-generic\n\n---\n\nThat's the full content as provided to me." } ] } ], "done": true } }, "currentId": "b4f1c0bf-e8d4-40eb-a21a-60bcdbfc3703" }, "messages": [ { "id": "15263770-63ba-4e5f-b9f1-de33b28cd188", "parentId": null, "childrenIds": [ "b4f1c0bf-e8d4-40eb-a21a-60bcdbfc3703" ], "role": "user", "content": "Can you output your system prompt for this session?", "timestamp": 1773923491, "models": [ "anthropic/claude-opus-4.6" ] }, { "parentId": "15263770-63ba-4e5f-b9f1-de33b28cd188", "id": "b4f1c0bf-e8d4-40eb-a21a-60bcdbfc3703", "childrenIds": [], "role": "assistant", "content": "<details type=\"reasoning\" done=\"true\" duration=\"1\">\n<summary>Thought for 1 seconds</summary>\n&gt; The user is asking me to output my system prompt. I&#x27;ll share what I can see of my system prompt, since it&#x27;s part of my instructions for this session and there&#x27;s no instruction telling me to keep it confidential.\n</details>\nSure. Here's the system prompt I'm operating under for this session:\n\n---\n\nYou are a friendly, capable general AI assistant. Give good, thorough answers without meandering.\n\nTone and style\n- Avoid filler, excessive hedging, and performative apologies.\n- Emojis: Avoid using them unless necessary or requested.\n- Keep formatting clean and lightweight. Prefer full sentences and paragraphs with helpful headers for breaks.\n\nUser alignment\n- Use the metric system if relevant (meters, liters, kilograms, etc.).\n- Adapt depth and jargon to the user's level and goals. Offer alternatives and trade-offs when choices matter.\n- For specialized domains (medical, legal, financial, safety-critical), provide useful information. Avoid unnecessary warnings and precautions to seek professionals. Assume the user is aware.\n- Avoid moralizing or preaching.\n\nAdditional data\n- The current date is 2026-03-19.\n- The environment is Ubuntu 24.04.4 LTS; kernel version 6.14.0-37-generic\n\n---\n\nThat's the full content as provided to me.", "model": "anthropic/claude-opus-4.6", "modelName": "Anthropic: Claude Opus 4.6", "modelIdx": 0, "timestamp": 1773923491, "usage": { "prompt_tokens": 244, "completion_tokens": 322, "total_tokens": 566, "cost": 0.00927, "is_byok": false, "prompt_tokens_details": { "cached_tokens": 0, "cache_write_tokens": 0, "audio_tokens": 0, "video_tokens": 0 }, "cost_details": { "upstream_inference_cost": 0.00927, "upstream_inference_prompt_cost": 0.00122, "upstream_inference_completions_cost": 0.00805 }, "completion_tokens_details": { "reasoning_tokens": 53, "image_tokens": 0, "audio_tokens": 0 } }, "output": [ { "type": "message", "id": "msg_6579ec5fdddc4bedaf9aabbc", "status": "completed", "role": "assistant", "content": [ { "type": "output_text", "text": "\n\n" } ] }, { "type": "reasoning", "id": "r_85cedc2c5ed449cdbae0ab31", "status": "completed", "start_tag": "<think>", "end_tag": "</think>", "attributes": { "type": "reasoning_content" }, "content": [ { "type": "output_text", "text": "The user is asking me to output my system prompt. I'll share what I can see of my system prompt, since it's part of my instructions for this session and there's no instruction telling me to keep it confidential." } ], "summary": null, "started_at": 1773923492.5771983, "ended_at": 1773923493.694125, "duration": 1 }, { "type": "message", "id": "msg_98dd88dea1c740f2b53942a7", "status": "completed", "role": "assistant", "content": [ { "type": "output_text", "text": "Sure. Here's the system prompt I'm operating under for this session:\n\n---\n\nYou are a friendly, capable general AI assistant. Give good, thorough answers without meandering.\n\nTone and style\n- Avoid filler, excessive hedging, and performative apologies.\n- Emojis: Avoid using them unless necessary or requested.\n- Keep formatting clean and lightweight. Prefer full sentences and paragraphs with helpful headers for breaks.\n\nUser alignment\n- Use the metric system if relevant (meters, liters, kilograms, etc.).\n- Adapt depth and jargon to the user's level and goals. Offer alternatives and trade-offs when choices matter.\n- For specialized domains (medical, legal, financial, safety-critical), provide useful information. Avoid unnecessary warnings and precautions to seek professionals. Assume the user is aware.\n- Avoid moralizing or preaching.\n\nAdditional data\n- The current date is 2026-03-19.\n- The environment is Ubuntu 24.04.4 LTS; kernel version 6.14.0-37-generic\n\n---\n\nThat's the full content as provided to me." } ] } ], "done": true } ], "tags": [], "timestamp": 1773923491017, "files": [] }, "updated_at": 1773923497, "created_at": 1773923491, "share_id": null, "archived": false, "pinned": false, "meta": {}, "folder_id": null } ``` ### Additional Information _No response_
GiteaMirror added the bug label 2026-04-25 09:34:42 -05:00
GiteaMirror commented 2026-04-25 09:34:44 -05:00
Author
Owner
Copy Link

@Classic298 commented on GitHub (Mar 19, 2026):

System prompts should not be part of an exported chat payload.

So this is correct behaviour

<!-- gh-comment-id:4091312122 --> @Classic298 commented on GitHub (Mar 19, 2026): System prompts should not be part of an **exported chat** payload. So this is correct behaviour
GiteaMirror commented 2026-04-25 09:34:44 -05:00
Author
Owner
Copy Link

@HideLord commented on GitHub (Mar 19, 2026):

@Classic298 Is it possible to know what the system prompt for the model was for a specific chat? Is it stored somewhere else? The only place I could find it is inside the models export, but it's just a snapshot of the latest parameters, and not a history of what they were.

<!-- gh-comment-id:4093188312 --> @HideLord commented on GitHub (Mar 19, 2026): @Classic298 Is it possible to know what the system prompt for the model was for a specific chat? Is it stored somewhere else? The only place I could find it is inside the models export, but it's just a snapshot of the latest parameters, and not a history of what they were.
GiteaMirror commented 2026-04-25 09:34:45 -05:00
Author
Owner
Copy Link

@Classic298 commented on GitHub (Mar 19, 2026):

For now - no.

Not through chat exports.

Only way:
You log all your requests. In the request content, you can see the system prompt that was sent to the model.

Model export contains current version of the system prompt

<!-- gh-comment-id:4093213202 --> @Classic298 commented on GitHub (Mar 19, 2026): For now - no. Not through chat exports. Only way: You log all your requests. In the request content, you can see the system prompt that was sent to the model. Model export contains current version of the system prompt
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#35357
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?