Add large output handling and iteration budget to agent

- Tool outputs >2K chars saved to workspace/tool_outputs/ with preview
- Agent gets first 1500 chars + file path to read the rest
- Iteration budget bumped to 10 rounds (configurable per template)
- Warning injected when 2 rounds remaining to help model wrap up

agent/agent.py

@@ -32,7 +32,7 @@ OLLAMA_URL = CONFIG.get("ollama_url", "http://172.16.0.1:11434")
 CONTEXT_SIZE = CONFIG.get("context_size", 20)
 MAX_RESPONSE_LINES = CONFIG.get("max_response_lines", 50)
 TOOLS_ENABLED = CONFIG.get("tools", True)
-MAX_TOOL_ROUNDS = CONFIG.get("max_tool_rounds", 5)
+MAX_TOOL_ROUNDS = CONFIG.get("max_tool_rounds", 10)
 WORKSPACE = "/workspace"
 SKILL_DIRS = ["/opt/skills", f"{WORKSPACE}/skills"]
 
@@ -169,9 +169,15 @@ def discover_skills():
     return tools, scripts
 
 
+LARGE_OUTPUT_THRESHOLD = 2000
+LARGE_OUTPUT_DIR = f"{WORKSPACE}/tool_outputs"
+_output_counter = 0
+
+
 def execute_skill(script_path, args):
-    """Execute a skill script with args as JSON on stdin."""
-    # Pass config extras via env
+    """Execute a skill script with args as JSON on stdin.
+    Large outputs are saved to a file with a preview returned."""
+    global _output_counter
     env = os.environ.copy()
     env["WORKSPACE"] = WORKSPACE
     env["SEARX_URL"] = CONFIG.get("searx_url", "https://searx.mymx.me")
@@ -188,7 +194,19 @@ def execute_skill(script_path, args):
         output = result.stdout
         if result.stderr:
             output += f"\n[stderr] {result.stderr}"
-        return output.strip() or "[no output]"
+        output = output.strip() or "[no output]"
+
+        # Large output handling — save to file, return preview
+        if len(output) > LARGE_OUTPUT_THRESHOLD:
+            os.makedirs(LARGE_OUTPUT_DIR, exist_ok=True)
+            _output_counter += 1
+            filepath = f"{LARGE_OUTPUT_DIR}/output_{_output_counter}.txt"
+            with open(filepath, "w") as f:
+                f.write(output)
+            preview = output[:1500]
+            return f"{preview}\n\n[output truncated — full result ({len(output)} chars) saved to {filepath}. Use run_command to read it: cat {filepath}]"
+
+        return output
     except subprocess.TimeoutExpired:
         return "[skill timed out after 120s]"
     except Exception as e:
@@ -323,6 +341,7 @@ def query_ollama(messages):
         payload["tools"] = TOOLS
 
     for round_num in range(MAX_TOOL_ROUNDS):
+        remaining = MAX_TOOL_ROUNDS - round_num
         try:
             data = ollama_request(payload)
         except (urllib.error.URLError, TimeoutError) as e:
@@ -341,6 +360,9 @@ def query_ollama(messages):
                     fn.get("arguments", {}),
                     round_num + 1,
                 )
+                # Warn when budget is running low
+                if remaining <= 2:
+                    result += f"\n[warning: {remaining - 1} tool rounds remaining — wrap up]"
                 messages.append({"role": "tool", "content": result})
             payload["messages"] = messages
             continue
@@ -353,6 +375,8 @@ def query_ollama(messages):
             if fn_name in SKILL_SCRIPTS:
                 messages.append({"role": "assistant", "content": content})
                 result = dispatch_tool(fn_name, fn_args, round_num + 1)
+                if remaining <= 2:
+                    result += f"\n[warning: {remaining - 1} tool rounds remaining — wrap up]"
                 messages.append({
                     "role": "user",
                     "content": f"Tool result:\n{result}\n\nNow respond to the user based on this result.",