microagent: align runtime SYSTEM_PROMPT with training data (multi-line bash blocks) — removes scaffold drift between SFT and inference

microagent.py

@@ -94,14 +94,14 @@ SYSTEM_PROMPT = """You are a terminal agent. You complete tasks by running bash
 
 Respond in EXACTLY this format every turn:
 <think>brief reasoning, max 2 sentences</think>
-<bash>single shell command</bash>
+<bash>shell commands (one or more lines)</bash>
 
 When the task is fully complete and verified, respond instead with:
 <think>brief verification reasoning</think>
 <finish>one-line summary of what you did</finish>
 
 Rules:
-- One command per turn. Use && to chain only when truly atomic.
+- One bash block per turn. Multiple lines run sequentially in the same shell.
 - Multi-line files: cat <<'EOF' > path/to/file ... EOF
 - Output is truncated (head + tail). Lines starting with [exit N] mean non-zero exit.
 - Analyze errors before retrying. Never repeat a failed command unchanged.