Run OpenCode on General Compute.

# Install OpenCode
curl -fsSL https://opencode.ai/install | bash

# Or install with npm
npm install -g opencode-ai

# Optional browser / desktop UI
opencode web

# Export your key so OpenCode can read it
export GENERALCOMPUTE_API_KEY=gc-...

# Sanity check
opencode --version && [ -n "$GENERALCOMPUTE_API_KEY" ] && echo OK

Sign me up for a General Compute API account and get an API key. Use https://docs.generalcompute.com/agent-signup for the signup flow. New accounts receive $100 in free credit. When you finish, return the API key and do not commit it to the repo.

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "generalcompute": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "General Compute",
      "options": {
        "baseURL": "https://api.generalcompute.com/v1",
        "apiKey": "{env:GENERALCOMPUTE_API_KEY}"
      },
      "models": {
        "minimax-m2.7": { "name": "MiniMax M2.7" },
        "deepseek-v3.1": { "name": "DeepSeek V3.1" }
      }
    }
  }
}

Configure OpenCode to use General Compute.

1. Update or create ~/.config/opencode/opencode.json.
2. Read the General Compute key from the GENERALCOMPUTE_API_KEY environment variable — do not paste it inline.
3. Keep the provider id "generalcompute" unless I ask for a different local alias.
4. General Compute is not a listed OpenCode provider yet, so use the OpenAI-compatible custom provider package.
5. Start OpenCode and run /models so I can verify the provider appears.

Use this exact file content:
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "generalcompute": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "General Compute",
      "options": {
        "baseURL": "https://api.generalcompute.com/v1",
        "apiKey": "{env:GENERALCOMPUTE_API_KEY}"
      },
      "models": {
        "minimax-m2.7": { "name": "MiniMax M2.7" },
        "deepseek-v3.1": { "name": "DeepSeek V3.1" }
      }
    }
  }
}

curl https://api.generalcompute.com/v1/chat/completions \
  -H "Authorization: Bearer $GENERALCOMPUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m2.7",
    "messages": [{"role": "user", "content": "Hello from OpenCode"}],
    "stream": true
  }'

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "generalcompute": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "General Compute",
      "options": {
        "baseURL": "https://api.generalcompute.com/v1",
        "apiKey": "{env:GENERALCOMPUTE_API_KEY}"
      },
      "models": {
        "minimax-m2.7": { "name": "MiniMax M2.7" }
      }
    }
  },
  "agent": {
    "build": { "model": "generalcompute/minimax-m2.7" }
  }
}

Create a minimalist, pet-friendly "hello world" landing page in this directory. One index.html, one style.css, no JS frameworks. Soft pastel palette, a friendly paw-print emoji, a short tagline ("Hello, friend"), and a single call-to-action button. Keep it under 80 lines of HTML+CSS combined. Open the file when done.

"agent": {
  "build": { "model": "generalcompute/minimax-m2.7" },
  "plan":  { "model": "anthropic/claude-sonnet-4-6" }
}

Read index.html and style.css in this directory. Elaborate a plan to extend this landing page into a "pet adoption finder" demo:
- A gallery of 6 placeholder pet cards (name, species, one-line bio) in a CSS grid.
- A search input that filters cards by name (vanilla JS, no frameworks).
- A dark-mode toggle that persists in localStorage.
Include the exact file layout, the JS event handlers needed, and a verification checklist. Don't modify any code yet.

Write the plan into PLAN.md and execute every step. After each step, list which acceptance criteria from the plan are now satisfied. Open index.html at the end so I can verify in the browser.

export CONTEXT7_API_KEY=ctx7sk-...

"mcp": {
  "context7": {
    "type": "remote",
    "url": "https://mcp.context7.com/mcp",
    "headers": { "CONTEXT7_API_KEY": "{env:CONTEXT7_API_KEY}" }
  }
}

Use the context7 MCP server to look up current docs for the date-fns library — specifically formatDistanceToNow with the addSuffix option, and how to load date-fns in a plain browser page via its UMD CDN build (the dateFns global) vs ESM named imports. Elaborate a plan for "Phase 2: relative date labels" describing how to give each pet card a fixed data-added ISO date and render an "Added X days ago" label from it on load. Use the up-to-date API from Context7 — not what you remember. Quote the exact <script> CDN tag, the global function call, and addSuffix usage verbatim from the docs, and include a verification step.

Update PLAN.md to include the "Phase 2" part and execute it. After loading, open index.html and confirm each card shows an "Added X days ago" label.