fix(agent-loop): update AGENTS.md and fix test invocation for InProgress workflow (#131)

State/Ready → State/InProgress is already set by agent_loop.py before
the agent starts. Update AGENTS.md to reflect that agents invoked via
the loop must not set InProgress themselves (only manual workflows need
to). Also fix TestMain tests that called main() directly, which caused
argparse to consume sys.argv; they now call _run_loop() instead.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

AGENTS.md

@@ -23,7 +23,9 @@ fgj issue list --json --state open | jq '[.[] | select(.labels[].name == "State/
 Rules:
 
 - Never start work on an issue without `State/Ready`
-- Switch `State/Ready` → `State/InProgress` as your **first action** when picking up an issue — before reading any code:
+- When working via the agent loop: `State/Ready` → `State/InProgress` is set automatically
+  by `agent_loop.py` before the agent starts — do **not** set it yourself.
+- When working manually: switch to `State/InProgress` as your **first action**:
   ```bash
   fgj issue edit <NUMBER> --remove-label "State/Ready" --add-label "State/InProgress"
   ```