{"record":{"id":"5eefa2d9b218fdcd","repo":"binary-husky/gpt_academic","slug":"error-5eefa2","errorCode":null,"errorMessage":"程序终止。","messagePattern":"程序终止。","errorType":"exception","errorClass":"RuntimeError","httpStatus":null,"severity":"error","filePath":"request_llms/bridge_moss.py","lineNumber":200,"sourceCode":"        moss_handle = GetGLMHandle()\n        if len(observe_window) >= 1: observe_window[0] = load_message + \"\\n\\n\" + moss_handle.info\n        if not moss_handle.success:\n            error = moss_handle.info\n            moss_handle = None\n            raise RuntimeError(error)\n\n    # chatglm 没有 sys_prompt 接口，因此把prompt加入 history\n    history_feedin = []\n    for i in range(len(history)//2):\n        history_feedin.append([history[2*i], history[2*i+1]] )\n\n    watch_dog_patience = 5 # 看门狗 (watchdog) 的耐心, 设置5秒即可\n    response = \"\"\n    for response in moss_handle.stream_chat(query=inputs, history=history_feedin, sys_prompt=sys_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):\n        if len(observe_window) >= 1:  observe_window[0] = response\n        if len(observe_window) >= 2:\n            if (time.time()-observe_window[1]) > watch_dog_patience:\n                raise RuntimeError(\"程序终止。\")\n    return response\n\n\n\ndef predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):\n    \"\"\"\n        单线程方法\n        函数的说明请见 request_llms/bridge_all.py\n    \"\"\"\n    chatbot.append((inputs, \"\"))\n\n    global moss_handle\n    if moss_handle is None:\n        moss_handle = GetGLMHandle()\n        chatbot[-1] = (inputs, load_message + \"\\n\\n\" + moss_handle.info)\n        yield from update_ui(chatbot=chatbot, history=[])\n        if not moss_handle.success:\n            moss_handle = None","sourceCodeStart":182,"sourceCodeEnd":218,"githubUrl":"https://github.com/binary-husky/gpt_academic/blob/d6bde0fa54373309bd05823a49bda8da019d2c77/request_llms/bridge_moss.py#L182-L218","documentation":"Watchdog abort for the MOSS stream: inside the loop over moss_handle.stream_chat, if time.time() - observe_window[1] exceeds watch_dog_patience (5s) without a yield, RuntimeError('程序终止。') is raised. Local MOSS inference between tokens can easily exceed 5s, especially on CPU or with long contexts.","triggerScenarios":"MOSS local generation stalls >5s between yields: slow CPU inference, long prefill, warm-up after load, or the loader thread hung/crashed mid-stream (e.g. CUDA OOM).","commonSituations":"CPU-only device, GPU OOM killing generation, first token after cold load, loaded machine, patience left at default 5s.","solutions":["Check the MOSS thread/process is alive and stderr for OOM/crash.","Increase watch_dog_patience (>=60s) or refresh observe_window[1] per yield in the caller.","Use GPU/quantization to cut inter-token latency.","Restart to rebuild a dead handle before retrying."],"exampleFix":null,"handlingStrategy":"retry","validationCode":"import time\nwindow = ['', time.time()]\n# refresh window[1] per poll; set patience to hardware worst case","typeGuard":null,"tryCatchPattern":"try:\n    resp = moss_predict_no_ui_long_connection(..., observe_window=window)\nexcept RuntimeError as e:\n    if '程序终止' in str(e):\n        window[1] = time.time()\n        resp = moss_predict_no_ui_long_connection(..., observe_window=window)","preventionTips":["watch_dog_patience >= 60s for local MOSS","Monitor thread for OOM/crash","Warm up after cold load before timing streams"],"tags":["moss","watchdog","timeout","local-model"],"backgroundTag":null,"analyzedSha":"d6bde0fa54373309bd05823a49bda8da019d2c77","analyzedAt":"2026-08-14T22:48:35.038Z","schemaVersion":2},"datasetVersion":"2026-08-15T17:31:12.345Z"}