dotfiles/home-manager/progs/opencode.nix

{
  config,
  lib,
  pkgs,
  inputs,
  ...
}:
let
  # what model should be used in place of haiku?
  # glm 4.7-flash is an example
  haiku-model = "openrouter/z-ai/glm-4.7-flash";

  opus-model = "openrouter/moonshotai/kimi-k2.5";

  ohMyOpencodeConfig = {
    "$schema" =
      "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json";
    agents = {
      sisyphus.model = opus-model;
      oracle = {
        model = "openrouter/openai/gpt-5.2";
        variant = "high";
      };
      librarian.model = haiku-model;
      explore.model = haiku-model;
      multimodal-looker.model = "openrouter/google/gemini-3-flash-preview";

      prometheus.model = opus-model;
      metis.model = opus-model;
      momus = {
        model = "openrouter/openai/gpt-5.2";
        variant = "medium";
      };
      atlas.model = opus-model;
    };
    categories = {
      visual-engineering.model = "openrouter/google/gemini-3-pro";
      ultrabrain = {
        model = "openrouter/openai/gpt-5.2-codex";
        variant = "xhigh";
      };
      artistry = {
        model = "openrouter/google/gemini-3-pro";
        variant = "max";
      };
      quick.model = haiku-model;
      "unspecified-low".model = opus-model;
      "unspecified-high".model = opus-model;
      writing.model = "openrouter/google/gemini-3-flash-preview";
    };
  };
in
{
  home.packages = [
    inputs.oh-my-opencode.packages.${pkgs.stdenv.hostPlatform.system}.oh-my-opencode
  ];

  xdg.configFile."opencode/oh-my-opencode.json".text = builtins.toJSON ohMyOpencodeConfig;

  programs.opencode = {
    package = inputs.llm-agents.packages.${pkgs.stdenv.targetPlatform.system}.opencode;
    enable = true;
    rules = ''
      You are an intelligent and observant agent.
      If instructed to commit, disable gpg signing.
      You are on nixOS, if you don't have access to a tool, you can access it via the `nix-shell` command.

      ## Think deeply about everything.
      When given a problem, break it down, abstract it out, understand the fundamentals, then solve it in the real world.

      ## Misc
      For long-running commands, make sure you set the timeout of the Bash tool provided to a larger value.
      Do NOT read secret files. Do not directly read files that are api keys or are contextually sensitive.

      ## Behavior
      Do not be sycophantic in your responses.
      Do not use emojis unless explicitly asked to. This includes in code.
      Use Test Driven Development methodology.

      ## Nix
      For using `nix build` append `-L` to get better visibility into the logs.
      If you get an error that a file can't be found, always try to `git add` the file before trying other troubleshooting steps.


      ## Android UI Interaction Workflow Summary
      1. Taking Screenshots
      adb exec-out screencap -p > /tmp/screen.png
      Captures the current screen state as a PNG image.

      2. Analyzing Screenshots
      I delegate screenshot analysis to an explore agent rather than analyzing images directly:
      mcp_task(subagent_type="explore", prompt="Analyze /tmp/screen.png. What screen is this? What elements are visible?")
      The agent describes the UI, identifies elements, and estimates Y coordinates.

      3. Getting Precise Element Coordinates
      UI Automator dump - extracts the full UI hierarchy as XML:
      adb shell uiautomator dump /sdcard/ui.xml && adb pull /sdcard/ui.xml /tmp/ui.xml
      Then grep for specific elements:
      # Find by text
      grep -oP 'text="Login".*?bounds="[^"]*"' /tmp/ui.xml
      # Find by class
      grep -oP 'class="android.widget.EditText".*?bounds="[^"]*"' /tmp/ui.xml
      Bounds format: [left,top][right,bottom] → tap center: ((left+right)/2, (top+bottom)/2)

      4. Tapping Elements
      adb shell input tap X Y
      Where X, Y are pixel coordinates from the bounds.

      5. Text Input
      adb shell input text "some_text"
      Note: Special characters need escaping (\!, \;, etc.)

      6. Other Gestures
      # Swipe/scroll
      adb shell input swipe startX startY endX endY duration_ms
      # Key events
      adb shell input keyevent KEYCODE_BACK
      adb shell input keyevent KEYCODE_ENTER

      7. WebView Limitation
      - UI Automator can see WebView content if accessibility is enabled
      - Touch events on iframe content (like Cloudflare Turnstile) often fail due to cross-origin isolation
      - Form fields in WebViews work if you get exact bounds from the UI dump

      Typical Flow
      1. Take screenshot → analyze with explore agent (get rough layout)
      2. Dump UI hierarchy → grep for exact element bounds
         - NEVER ASSUME COORDINATES. You must ALWAYS check first.
         - Do this before ANY tap action as elements on the screen may of changed.
      3. Calculate center coordinates from bounds
      4. Tap/interact
      5. Wait → screenshot → verify result
    '';
    settings = {
      theme = "opencode";

      model = opus-model;
      # small model used for titles
      small_model = "openrouter/openai/gpt-oss-20b:free";

      autoshare = false;
      autoupdate = true;
      agent = { };
      plugin = [ "oh-my-opencode" ];
      provider = {
        openrouter = {
          models = {
            "openai/gpt-oss-20b:free" = { };
            "minimax/minimax-m2.1" = { };
            "z-ai/glm-4.7-flash" = { };
          };
          options = {
            # TODO! use agenix here instead
            apiKey = "{file:${../secrets/openrouter_api_key}}";
          };
        };
      };
    };
  };
}