Skip to content

Pop up error "content.parts is not iterable" #5912

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
3 tasks
skim2257 opened this issue May 30, 2025 · 0 comments
Open
3 tasks

Pop up error "content.parts is not iterable" #5912

skim2257 opened this issue May 30, 2025 · 0 comments
Assignees
Labels
area:chat Relates to chat interface kind:bug Indicates an unexpected problem or unintended behavior os:windows Happening specifically on Windows

Comments

@skim2257
Copy link

Before submitting your bug report

Relevant environment info

- OS: Windows
- Continue version: 1.0.10
- IDE version: 1.100.2
- Model: Gemini 2.5 Pro
- config:
  
name: Local Assistant
version: 1.0.0
schema: v1
models:
  - name: Gemini 2.5 Pro Experimental
    provider: gemini
    model: gemini-2.5-pro-preview-05-06
    apiKey: REDACTED
  - name: Gemini 2.0 Flash
    provider: gemini
    model: gemini-2.0-flash
    apiKey: REDACTED
context:
  - provider: code
  - provider: docs
  - provider: diff
  - provider: terminal
  - provider: problems
  - provider: folder
  - provider: codebase

Description

threw pop up error "content.parts is not iterable"

To reproduce

No response

Log output

Error handling webview message: {
  "msg": {
    "messageId": "a01665d1-969f-400d-9cb7-25df605f8af8",
    "messageType": "llm/streamChat",
    "data": {
      "completionOptions": {},
      "title": "Gemini 2.5 Pro Experimental",
      "messages": [
        {
          "role": "system",
          "content": "<important_rules>\n  You are in chat mode.\n\n  If the user asks to make changes to files offer that they can use the Apply Button on the code block, or switch to Agent Mode to make the suggested updates automatically.\n  If needed consisely explain to the user they can switch to agent mode using the Mode Selector dropdown and provide no other details.\n\n  Always include the language and file name in the info string when you write code blocks.\n  If you are editing \"src/main.py\" for example, your code block should start with ' src/main.py'\n\n  When addressing code modification requests, present a concise code snippet that\n  emphasizes only the necessary changes and uses abbreviated placeholders for\n  unmodified sections. For example:\n\n   /path/to/file\n  // ... existing code ...\n\n  {{ modified code here }}\n\n  // ... existing code ...\n\n  {{ another modification }}\n\n  // ... rest of code ...\n  \n\n  In existing files, you should always restate the function or class that the snippet belongs to:\n\n   /path/to/file\n  // ... existing code ...\n\n  function exampleFunction() {\n    // ... existing code ...\n\n    {{ modified code here }}\n\n    // ... rest of function ...\n  }\n\n  // ... rest of code ...\n  \n\n  Since users have access to their complete file, they prefer reading only the\n  relevant modifications. It's perfectly acceptable to omit unmodified portions\n  at the beginning, middle, or end of files using these \"lazy\" comments. Only\n  provide the complete file when explicitly requested. Include a concise explanation\n  of changes unless the user specifically asks for code only.\n\n</important_rules>"
        },
        {
          "role": "user",
          "content": [
            {
              "type": "text",
              "text": "help me write a Dockerfile that runs my repository in pytorch 1.8.0 and cuda 11.1 and runs all of the pixi files. "
            }
          ]
        },
        {
          "role": "assistant",
          "content": "\nlock during the build.\nOkay, I can help you with that! Here's a Dockerfile designed to use PyTorch 1.8.0 with CUDA 11.1, install `pixi`, and set up your project.\n\nThis Dockerfile assumes:\n1.  Your repository has a `pixi.toml` file in its root directory.\n2.  \"Runs all of the pixi files\" means:\n    *   Installing the environment and dependencies defined in `pixi.toml` (using `pixi install`).\n    *   Running a specific task (e.g., `start`, `train`, `serve`) defined in your `pixi.toml` using `pixi run <task_name>`. You'll need to specify this task.\n\nHere's"
        },
        {
          "role": "user",
          "content": [
            {
              "type": "text",
              "text": "Continue your response exactly where you left off:"
            }
          ]
        },
        {
          "role": "assistant",
          "content": ""
        }
      ]
    }
  }
}

TypeError: content.parts is not iterable
@dosubot dosubot bot added area:chat Relates to chat interface kind:bug Indicates an unexpected problem or unintended behavior os:windows Happening specifically on Windows labels May 30, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
area:chat Relates to chat interface kind:bug Indicates an unexpected problem or unintended behavior os:windows Happening specifically on Windows
Projects
Status: Todo
Development

No branches or pull requests

2 participants