continuedev / continue

⏩ Continue is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains
https://docs.continue.dev/
Apache License 2.0
19.25k stars 1.66k forks source link

Chat: disappearing chats #2786

Open RomneyDa opened 2 weeks ago

RomneyDa commented 2 weeks ago

Before submitting your bug report

Relevant environment info

OS: Mac
VScode version: 1.95.1 
Continue version: v0.8.55
config.json:

{
  "models": [
    // {
    //   "title": "llama3.1:70b",
    //   "provider": "ollama",
    //   "model": "llama3.1:70b"
    // },
    {
      "title": "codestral",
      "provider": "ollama",
      "model": "codestral"
    }
    // {
    //   "title": "GPT-4o",
    //   "provider": "openai",
    //   "model": "GPT-4o",
    //   "apiKey": "..."
    // }
  ],
  "tabAutocompleteModel": {
    "title": "Starcoder",
    "provider": "ollama",
    "model": "starcoder2:3b"
  },
  "embeddingsProvider": {
    "provider": "ollama",
    "model": "nomic-embed-text"
  },
  "contextProviders": [
    {
      "name": "code",
      "params": {}
    },
    {
      "name": "docs",
      "params": {}
    },
    {
      "name": "diff",
      "params": {}
    },
    {
      "name": "terminal",
      "params": {}
    },
    {
      "name": "problems",
      "params": {}
    },
    {
      "name": "folder",
      "params": {}
    },
    {
      "name": "file",
      "params": {}
    },
    {
      "name": "codebase",
      "params": {
        "nRetrieve": 25,
        "nFinal": 5,
        "useReranking": true
      }
    },
    {
      "name": "open",
      "params": {
        "onlyPinned": true
      }
    }
  ],
  "slashCommands": [
    {
      "name": "edit",
      "description": "Edit selected code"
    },
    {
      "name": "comment",
      "description": "Write comments for the selected code"
    },
    {
      "name": "share",
      "description": "Export the current chat session to markdown"
    },
    {
      "name": "cmd",
      "description": "Generate a shell command"
    },
    {
      "name": "commit",
      "description": "Generate a git commit message"
    },
  ],
  "allowAnonymousTelemetry": false
}


### Description

Circa on discord:
https://discord.com/channels/1108621136150929458/1301764894869159956

>Using cmd+i, if I use @ and select a file, or use any context inputs such as @Codebase when I observe the logs under output > Continue - LLM Prompt Completion I can see the prompt is never sent. I can also tell nothing happens as system memory doesn't change. I've tried a few different models with no change. I've also checked the console logs under developer tools but there are no related errors, the prompt appears to be swallowed

(romneyda)
This seems to happen arbitrarily, especially when there are errors calling model. Redux state needs to be inspected, and chat error handling to make sure no silent fails

### To reproduce

_No response_

### Log output

_No response_