{ "tasks": 30, "target_hit_rate": 0, "file_hit_rate": 0.1, "macro_line_precision": 0.0, "macro_line_recall": 0.0, "macro_line_f1": 0.0, "latency_median_seconds": 32.87817524649654, "latency_p95_seconds": 44.770849431097304, "statuses": { "budget_exhausted": 23, "completed": 7 }, "total_tool_errors": 22, "total_invalid_actions": 51, "mean_rounds": 5.3, "mean_tool_calls": 4.366666666666666, "total_input_tokens": 464686, "total_output_tokens": 4643, "mean_returned_chars": 419.6, "per_repository": { "requests": { "tasks": 10, "target_hit_rate": 0, "file_hit_rate": 0.2, "macro_line_precision": 0.0, "macro_line_recall": 0.0, "macro_line_f1": 0.0, "latency_median_seconds": 30.96327949500119, "latency_p95_seconds": 35.69990707220022, "statuses": { "budget_exhausted": 6, "completed": 4 }, "total_tool_errors": 6, "total_invalid_actions": 14, "mean_rounds": 4.8, "mean_tool_calls": 4, "total_input_tokens": 135648, "total_output_tokens": 1407, "mean_returned_chars": 774.7 }, "flask": { "tasks": 10, "target_hit_rate": 0, "file_hit_rate": 0.1, "macro_line_precision": 0.0, "macro_line_recall": 0.0, "macro_line_f1": 0.0, "latency_median_seconds": 31.488584604001517, "latency_p95_seconds": 34.95061498904797, "statuses": { "budget_exhausted": 8, "completed": 2 }, "total_tool_errors": 7, "total_invalid_actions": 18, "mean_rounds": 5.4, "mean_tool_calls": 4.4, "total_input_tokens": 161045, "total_output_tokens": 1584, "mean_returned_chars": 238.9 }, "click": { "tasks": 10, "target_hit_rate": 0, "file_hit_rate": 0, "macro_line_precision": 0.0, "macro_line_recall": 0.0, "macro_line_f1": 0.0, "latency_median_seconds": 43.22066144999917, "latency_p95_seconds": 46.640672169248504, "statuses": { "budget_exhausted": 9, "completed": 1 }, "total_tool_errors": 9, "total_invalid_actions": 19, "mean_rounds": 5.7, "mean_tool_calls": 4.7, "total_input_tokens": 167993, "total_output_tokens": 1652, "mean_returned_chars": 245.2 } }, "sampled_peak_gpu_memory_mib": null, "gpu_sampling_interval_seconds": 1, "execution_note": "The process was interrupted after 28 persisted tasks. Only the remaining two tasks were run after verifying the frozen suite, source, repository, and adapter hashes, with a fresh model warm-up. Original in-memory GPU samples were lost; no full-run GPU peak is reported." }