fix: detect truncated tool_calls when finish_reason is not length

When API routers rewrite finish_reason from "length" to "tool_calls",
truncated JSON arguments bypassed the length handler and wasted 3
retry attempts in the generic JSON validation loop. Now detects
truncation patterns in tool call arguments regardless of finish_reason.

Fixes #7680

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

run_agent.py

@@ -9506,12 +9506,41 @@ class AIAgent:
                             invalid_json_args.append((tc.function.name, str(e)))
                     
                     if invalid_json_args:
+                        # Check if the invalid JSON is due to truncation rather
+                        # than a model formatting mistake.  Routers sometimes
+                        # rewrite finish_reason from "length" to "tool_calls",
+                        # hiding the truncation from the length handler above.
+                        # Detect truncation: args that don't end with } or ]
+                        # (after stripping whitespace) are cut off mid-stream.
+                        _truncated = any(
+                            not (tc.function.arguments or "").rstrip().endswith(("}", "]"))
+                            for tc in assistant_message.tool_calls
+                            if tc.function.name in {n for n, _ in invalid_json_args}
+                        )
+                        if _truncated:
+                            self._vprint(
+                                f"{self.log_prefix}⚠️  Truncated tool call arguments detected "
+                                f"(finish_reason={finish_reason!r}) — refusing to execute.",
+                                force=True,
+                            )
+                            self._invalid_json_retries = 0
+                            self._cleanup_task_resources(effective_task_id)
+                            self._persist_session(messages, conversation_history)
+                            return {
+                                "final_response": None,
+                                "messages": messages,
+                                "api_calls": api_call_count,
+                                "completed": False,
+                                "partial": True,
+                                "error": "Response truncated due to output length limit",
+                            }
+
                         # Track retries for invalid JSON arguments
                         self._invalid_json_retries += 1
-                        
+
                         tool_name, error_msg = invalid_json_args[0]
                         self._vprint(f"{self.log_prefix}⚠️  Invalid JSON in tool call arguments for '{tool_name}': {error_msg}")
-                        
+
                         if self._invalid_json_retries < 3:
                             self._vprint(f"{self.log_prefix}🔄 Retrying API call ({self._invalid_json_retries}/3)...")
                             # Don't add anything to messages, just retry the API call

tests/run_agent/test_run_agent.py

@@ -2169,6 +2169,35 @@ class TestRunConversation:
         mock_hfc.assert_called_once()
         assert result["final_response"] == "Done!"
 
+    def test_truncated_tool_args_detected_when_finish_reason_not_length(self, agent):
+        """When a router rewrites finish_reason from 'length' to 'tool_calls',
+        truncated JSON arguments should still be detected and refused rather
+        than wasting 3 retry attempts."""
+        self._setup_agent(agent)
+        agent.valid_tool_names.add("write_file")
+        bad_tc = _mock_tool_call(
+            name="write_file",
+            arguments='{"path":"report.md","content":"partial',
+            call_id="c1",
+        )
+        resp = _mock_response(
+            content="", finish_reason="tool_calls", tool_calls=[bad_tc],
+        )
+        agent.client.chat.completions.create.return_value = resp
+
+        with (
+            patch("run_agent.handle_function_call") as mock_handle_function_call,
+            patch.object(agent, "_persist_session"),
+            patch.object(agent, "_save_trajectory"),
+            patch.object(agent, "_cleanup_task_resources"),
+        ):
+            result = agent.run_conversation("write the report")
+
+        assert result["completed"] is False
+        assert result["partial"] is True
+        assert "truncated due to output length limit" in result["error"]
+        mock_handle_function_call.assert_not_called()
+
 
 class TestRetryExhaustion:
     """Regression: retry_count > max_retries was dead code (off-by-one).