fix: resolve opencode.ai context window to 1M and clean up display formatting

Two issues resolved:

1. Add opencode.ai to _URL_TO_PROVIDER mapping so base_url routes through
   models.dev lookup (which has mimo-v2-pro at 1M context) instead of
   falling back to probing /models (404) and defaulting to 128K.

2. Fix _format_context_length to round cleanly: 1048576 → '1M' instead
   of '1.048576M'. Applies same rounding logic to K values.

agent/model_metadata.py

@@ -197,6 +197,7 @@ _URL_TO_PROVIDER: Dict[str, str] = {
     "api.githubcopilot.com": "copilot",
     "models.github.ai": "copilot",
     "api.fireworks.ai": "fireworks",
+    "opencode.ai": "opencode-go",
 }