2026-04-16 13:35:24 INFO    [utils.repo_logging] repo_logging.py:79 configure_text2sql_api_logging() | 日志文件: C:\Users\24019\Desktop\backman-camel\logs\text2sql_api.log
2026-04-16 13:35:29 INFO    [__main__] api_server.py:85 <module>() | [OK] 已加载配置文件: C:\Users\24019\Desktop\backman-camel\.env
2026-04-16 13:35:29 INFO    [__main__] api_server.py:1120 <module>() | 启动服务: http://0.0.0.0:8041
2026-04-16 13:35:29 INFO    [__main__] api_server.py:1121 <module>() | API文档: http://0.0.0.0:8041/docs
2026-04-16 13:35:29 INFO    [uvicorn.error] server.py:92 _serve() | Started server process [37328]
2026-04-16 13:35:29 INFO    [uvicorn.error] on.py:48 startup() | Waiting for application startup.
2026-04-16 13:35:29 INFO    [__main__] api_server.py:811 lifespan() | ============================================================
2026-04-16 13:35:29 INFO    [__main__] api_server.py:812 lifespan() | Text2SQL API Server 启动中...
2026-04-16 13:35:29 INFO    [__main__] api_server.py:813 lifespan() | ============================================================
2026-04-16 13:35:29 INFO    [main] main.py:126 setup_environment() | [OK] 环境检查通过
2026-04-16 13:35:29 INFO    [main] main.py:127 setup_environment() |   - Schema: data\schemas\G3SB_MCDataDictionary_table_structure.json
2026-04-16 13:35:29 INFO    [main] main.py:128 setup_environment() |   - LLM: openai
2026-04-16 13:35:29 INFO    [main] main.py:154 load_schema() | 加载Schema: ./data/schemas/G3SB_MCDataDictionary_table_structure.json
2026-04-16 13:35:29 INFO    [main] main.py:156 load_schema() |   表注释(meta): ./data/schemas/G3SB_MCDataDictionary_table_meta.json
2026-04-16 13:35:30 INFO    [schema.loader] loader.py:107 load_from_json() | [OK] 加载Schema完成(G3SB schemas): G3SB_MCDataDictionary_table_structure, 共2516张表
2026-04-16 13:35:30 INFO    [main] main.py:163 load_schema() | [OK] Schema加载完成: G3SB_MCDataDictionary_table_structure, 共2516张表, 59196个字段
2026-04-16 13:35:33 INFO    [llm.openai_client] openai_client.py:55 __init__() | [OK] OpenAIClient初始化: model=gpt-5.4, base_url=http://113.192.49.54:9080/v1
2026-04-16 13:35:35 INFO    [utils.embedding] embedding.py:144 __init__() | 使用 OpenAI Embedding API：model=text-embedding-ada-002，base_url=http://113.192.49.54:9080/v1，max_batch=100
2026-04-16 13:35:37 INFO    [utils.fewshot_chroma_store] fewshot_chroma_store.py:86 __init__() | [OK] FewShotChromaStore: 磁盘 data\embeddings\chroma_fewshot collection=fewshot_samples count=50
2026-04-16 13:35:37 INFO    [utils.fewshot_selector] fewshot_selector.py:128 _init_chroma_mode() | [Few-shot] 已从向量库加载（Chroma 50 条，data\embeddings\chroma_fewshot）
2026-04-16 13:35:37 INFO    [utils.fewshot_selector] fewshot_selector.py:159 _init_chroma_mode() | [OK] Few-shot 使用 Chroma（50 条）
2026-04-16 13:35:37 INFO    [agents.orchestrator] orchestrator.py:116 __init__() | Few-shot已启用: top_k=3, min_rating=7
2026-04-16 13:35:37 INFO    [agents.orchestrator] orchestrator.py:127 __init__() | [OK] Text2SQLOrchestrator初始化完成: max_retry=2, use_vector_search=True, fewshot=on, nl→zh_norm=on
2026-04-16 13:35:37 INFO    [__main__] api_server.py:132 get_orchestrator() | [OK] Orchestrator 初始化完成
2026-04-16 13:35:37 INFO    [__main__] api_server.py:817 lifespan() | [OK] 服务已就绪
2026-04-16 13:35:37 INFO    [uvicorn.error] on.py:62 startup() | Application startup complete.
2026-04-16 13:35:37 INFO    [uvicorn.error] server.py:224 _log_started_message() | Uvicorn running on http://0.0.0.0:8041 (Press CTRL+C to quit)
2026-04-16 13:35:52 INFO    [uvicorn.access] httptools_impl.py:483 send() | 127.0.0.1:23615 - "POST /g3sb/api/nl/chat/stream HTTP/1.1" 200
2026-04-16 13:35:52 INFO    [__main__] api_server.py:668 _chat_stream_events() | [API/stream] 开始: user_id='anonymous' visitor_biz_id=None session_id=None service_code=None model='gpt-4o-mini' lang_code='auto' msg_chars=15 preview='所有客户账户之间的股票转移记录' dialog_context_chars=0 last_turn_was_data_query=False
2026-04-16 13:35:55 INFO    [llm.openai_client] openai_client.py:55 __init__() | [OK] OpenAIClient初始化: model=gpt-4o-mini, base_url=http://113.192.49.54:9080/v1
2026-04-16 13:35:55 INFO    [utils.dialog_classifier] dialog_classifier.py:261 classify_dialog() | [dialog] intent=text2sql (hybrid fast: query hint) preview='所有客户账户之间的股票转移记录'
2026-04-16 13:35:55 INFO    [__main__] api_server.py:715 _chat_stream_events() | [GEN/API/stream] dialect=tsql top_k=20 dialog_context_chars=0 question_len=15 preview='所有客户账户之间的股票转移记录'
2026-04-16 13:35:57 INFO    [llm.openai_client] openai_client.py:55 __init__() | [OK] OpenAIClient初始化: model=gpt-4o-mini, base_url=http://113.192.49.54:9080/v1
2026-04-16 13:36:00 INFO    [agents.orchestrator] orchestrator.py:803 generate() | [GEN] 问句已归一中文：所有客户账户的股票转移记录
2026-04-16 13:36:00 INFO    [agents.orchestrator] orchestrator.py:816 generate() | [GEN] 开始生成SQL: question_chars=13 preview='所有客户账户的股票转移记录' dialog_context_chars=0
2026-04-16 13:36:00 INFO    [agents.orchestrator] orchestrator.py:831 generate() |   尝试 #1
2026-04-16 13:36:00 INFO    [schema.indexer] indexer.py:82 __init__() | [OK] 初始化SchemaIndexer(Chroma磁盘 path=data\embeddings\chroma): collection=schema_tables, count=2516
2026-04-16 13:36:00 INFO    [schema.indexer] indexer.py:106 ensure_index_for_schema() | Schema 向量索引已就绪（2516 张表），跳过向量化
2026-04-16 13:36:00 INFO    [agents.orchestrator] orchestrator.py:188 _coarse_filter() | [Orchestrator] 开始向量检索: query_chars=13 query_preview='所有客户账户的股票转移记录'
2026-04-16 13:36:02 INFO    [utils.embedding] embedding.py:163 _set_dim_from_vector() | [OK] Embedding 向量维度：1536
2026-04-16 13:36:03 INFO    [schema.indexer] indexer.py:244 search() | Schema 向量检索: query_chars=13 命中=20（阈值=0.1）top=[('VSBHKRpt0430', 0.8264), ('VSBHKRpt0431', 0.8188), ('TSBTransferInstruction', 0.8147), ('VSBTransferInstruction', 0.8134), ('VSBHKRpt0397', 0.8126), ('VSBHKRpt0672', 0.8117), ('VSBHKRpt0090C', 0.81), ('VSBHKRpt0570', 0.8084), ('VSBHKRpt1030A', 0.8077), ('VSBRpt0999E', 0.8065), ('VSBRpt0999C', 0.8064), ('TSBAccountEntitlementRelease', 0.8063), ('VSBRpt0999A', 0.8059), ('TSBAccountInstrumentMovement', 0.8038), ('VSBTransferInstructionGenerationByAccountContract', 0.8033)]
2026-04-16 13:36:03 INFO    [agents.orchestrator] orchestrator.py:204 _coarse_filter() | [Orchestrator] 向量粗筛: 命中=20 张（阈值内），表名+分: [('VSBHKRpt0430', 0.8264), ('VSBHKRpt0431', 0.8188), ('TSBTransferInstruction', 0.8147), ('VSBTransferInstruction', 0.8134), ('VSBHKRpt0397', 0.8126), ('VSBHKRpt0672', 0.8117), ('VSBHKRpt0090C', 0.81), ('VSBHKRpt0570', 0.8084), ('VSBHKRpt1030A', 0.8077), ('VSBRpt0999E', 0.8065), ('VSBRpt0999C', 0.8064), ('TSBAccountEntitlementRelease', 0.8063), ('VSBRpt0999A', 0.8059), ('TSBAccountInstrumentMovement', 0.8038), ('VSBTransferInstructionGenerationByAccountContract', 0.8033), ('VSBRpt0060', 0.8021), ('XCGatewayStockReconciliationReport', 0.802), ('TSBAccountEntitlementHold', 0.8013), ('WSBBatchLocationTransferDetail', 0.8012), ('VCAccountCashMovement', 0.8012)]
2026-04-16 13:36:07 INFO    [agents.orchestrator] orchestrator.py:258 _llm_select_tables() | LLM精筛选中表：['VSBHKRpt0430', 'VSBHKRpt0431', 'TSBTransferInstruction', 'VSBTransferInstruction', 'TSBAccountInstrumentMovement'] | reasoning_chars=181 reasoning_preview='问题涉及客户账户的股票转移记录，VSBHKRpt0430和VSBHKRpt0431提供了客户股票的日常转移报告和账户工具移动报告，TSBTransferInstruction和VSBTransferInstruction则记录了账户转移指令，TSBAccountInstrumentMovement包含账户工具的移动交易信息，这些表共同覆盖了股票转移的各个方面。'
2026-04-16 13:36:07 INFO    [agents.orchestrator] orchestrator.py:859 generate() |   选中表：['VSBHKRpt0430', 'VSBHKRpt0431', 'TSBTransferInstruction', 'VSBTransferInstruction', 'TSBAccountInstrumentMovement']，扩展后：['TSBTransferInstruction', 'VSBTransferInstruction', 'VSBHKRpt0431', 'VSBHKRpt0430', 'TSBAccountInstrumentMovement']
2026-04-16 13:36:08 INFO    [utils.fewshot_selector] fewshot_selector.py:209 select_best_with_score() | [Few-shot] best_with_score: qid=Q2 score=0.9575 preview='列出今日所有客户账户之间的股票转移记录。'
2026-04-16 13:36:08 INFO    [agents.orchestrator] orchestrator.py:432 _generate_sql_golden_adapt() | [GEN] 黄金 few-shot 条件适配: qid=Q2 score=0.9575
2026-04-16 13:36:12 INFO    [agents.orchestrator] orchestrator.py:450 _generate_sql_golden_adapt() | 生成的SQL（黄金适配，chars=494）:
-- 查询所有客户账户间股票转移记录
-- 使用 TSBAccountInstrumentMovement，MovementType='T' 表示账户间转移
SELECT 
    m.MovementID,
    m.AccountID AS FromAccountID,
    m.TransferToAccountID,
    m.InstrumentID,
    i.Name AS InstrumentSymbol,
    m.MovementType,
    m.Quantity AS TransferQuantity,
    m.ValueDate AS TransferDate
FROM TSBAccountInstrumentMovement m
LEFT JOIN MCInstrument i ON m.InstrumentID = i.InstrumentID
WHERE m.MovementType = 'T'
  AND m.ValueDate = CAST(GETDATE() AS DATE)
ORDER BY m.ValueDate;
2026-04-16 13:36:12 INFO    [db.engine] engine.py:45 get_engine() | SQLAlchemy engine initialized from database_url
2026-04-16 13:36:12 INFO    [db.dbhub_tools] dbhub_tools.py:627 _execute_sql() | _execute_sql 执行语句数=1 readonly=True max_rows=1
2026-04-16 13:36:15 INFO    [agents.orchestrator] orchestrator.py:754 _validate_sql() | [validate] 程序+探针+LLM 汇总: valid=True err_count=0 warn_count=0 db_execution_status=0 sql_chars=494
2026-04-16 13:36:15 INFO    [agents.orchestrator] orchestrator.py:921 generate() | [OK] SQL生成与验证通过（1次尝试）
2026-04-16 13:36:15 INFO    [__main__] api_server.py:776 _chat_stream_events() | [API/stream] Text2SQL 完成: valid=True attempts=1 tables_used=['TSBTransferInstruction', 'VSBTransferInstruction', 'VSBHKRpt0431', 'VSBHKRpt0430', 'TSBAccountInstrumentMovement'] sql_chars=494 sql_head="-- 查询所有客户账户间股票转移记录\n-- 使用 TSBAccountInstrumentMovement，MovementType='T' 表示账户间转移\nSELECT \n    m.MovementID,\n    m.AccountID AS FromAccountID,\n    m.TransferToAccountID,\n    m.InstrumentID,\n    i.Name AS InstrumentSymbol,\n    m.MovementType,\n    m.Quantity AS TransferQuantity,\n    m.ValueDate AS TransferDate\nFROM TSBAccountInstrumentMovement m\nLEFT JOIN MCInstrument i ON m.InstrumentID = i.InstrumentID\nWHERE m.MovementType = 'T'\n  AND m.ValueDate = CAST(GETDATE() AS DATE)\nORDER BY m.ValueDate;"
2026-04-16 13:47:46 INFO    [uvicorn.access] httptools_impl.py:483 send() | 127.0.0.1:27791 - "POST /g3sb/api/nl/chat/stream HTTP/1.1" 200
2026-04-16 13:47:46 INFO    [__main__] api_server.py:668 _chat_stream_events() | [API/stream] 开始: user_id='anonymous' visitor_biz_id=None session_id=None service_code=None model='gpt-4o-mini' lang_code='auto' msg_chars=15 preview='所有客户账户之间的股票转移记录' dialog_context_chars=0 last_turn_was_data_query=False
2026-04-16 13:47:49 INFO    [llm.openai_client] openai_client.py:55 __init__() | [OK] OpenAIClient初始化: model=gpt-4o-mini, base_url=http://113.192.49.54:9080/v1
2026-04-16 13:47:49 INFO    [utils.dialog_classifier] dialog_classifier.py:261 classify_dialog() | [dialog] intent=text2sql (hybrid fast: query hint) preview='所有客户账户之间的股票转移记录'
2026-04-16 13:47:49 INFO    [__main__] api_server.py:715 _chat_stream_events() | [GEN/API/stream] dialect=tsql top_k=20 dialog_context_chars=0 question_len=15 preview='所有客户账户之间的股票转移记录'
2026-04-16 13:47:52 INFO    [llm.openai_client] openai_client.py:55 __init__() | [OK] OpenAIClient初始化: model=gpt-4o-mini, base_url=http://113.192.49.54:9080/v1
2026-04-16 13:47:54 INFO    [agents.orchestrator] orchestrator.py:803 generate() | [GEN] 问句已归一中文：所有客户账户的股票转移记录
2026-04-16 13:47:54 INFO    [agents.orchestrator] orchestrator.py:816 generate() | [GEN] 开始生成SQL: question_chars=13 preview='所有客户账户的股票转移记录' dialog_context_chars=0
2026-04-16 13:47:54 INFO    [agents.orchestrator] orchestrator.py:831 generate() |   尝试 #1
2026-04-16 13:47:54 INFO    [schema.indexer] indexer.py:106 ensure_index_for_schema() | Schema 向量索引已就绪（2516 张表），跳过向量化
2026-04-16 13:47:54 INFO    [agents.orchestrator] orchestrator.py:188 _coarse_filter() | [Orchestrator] 开始向量检索: query_chars=13 query_preview='所有客户账户的股票转移记录'
2026-04-16 13:47:56 INFO    [schema.indexer] indexer.py:244 search() | Schema 向量检索: query_chars=13 命中=20（阈值=0.1）top=[('VSBHKRpt0430', 0.8264), ('VSBHKRpt0431', 0.8188), ('TSBTransferInstruction', 0.8147), ('VSBTransferInstruction', 0.8134), ('VSBHKRpt0397', 0.8126), ('VSBHKRpt0672', 0.8117), ('VSBHKRpt0090C', 0.81), ('VSBHKRpt0570', 0.8084), ('VSBHKRpt1030A', 0.8077), ('VSBRpt0999E', 0.8065), ('VSBRpt0999C', 0.8064), ('TSBAccountEntitlementRelease', 0.8063), ('VSBRpt0999A', 0.8059), ('TSBAccountInstrumentMovement', 0.8038), ('VSBTransferInstructionGenerationByAccountContract', 0.8033)]
2026-04-16 13:47:56 INFO    [agents.orchestrator] orchestrator.py:204 _coarse_filter() | [Orchestrator] 向量粗筛: 命中=20 张（阈值内），表名+分: [('VSBHKRpt0430', 0.8264), ('VSBHKRpt0431', 0.8188), ('TSBTransferInstruction', 0.8147), ('VSBTransferInstruction', 0.8134), ('VSBHKRpt0397', 0.8126), ('VSBHKRpt0672', 0.8117), ('VSBHKRpt0090C', 0.81), ('VSBHKRpt0570', 0.8084), ('VSBHKRpt1030A', 0.8077), ('VSBRpt0999E', 0.8065), ('VSBRpt0999C', 0.8064), ('TSBAccountEntitlementRelease', 0.8063), ('VSBRpt0999A', 0.8059), ('TSBAccountInstrumentMovement', 0.8038), ('VSBTransferInstructionGenerationByAccountContract', 0.8033), ('VSBRpt0060', 0.8021), ('XCGatewayStockReconciliationReport', 0.802), ('TSBAccountEntitlementHold', 0.8013), ('WSBBatchLocationTransferDetail', 0.8012), ('VCAccountCashMovement', 0.8012)]
2026-04-16 13:48:00 INFO    [agents.orchestrator] orchestrator.py:258 _llm_select_tables() | LLM精筛选中表：['VSBHKRpt0430', 'VSBHKRpt0431', 'TSBTransferInstruction', 'VSBTransferInstruction', 'TSBAccountInstrumentMovement'] | reasoning_chars=182 reasoning_preview='问题涉及客户账户的股票转移记录，VSBHKRpt0430和VSBHKRpt0431提供了客户股票的日常转移报告和账户工具移动报告，TSBTransferInstruction和VSBTransferInstruction包含账户转移指令的详细信息，TSBAccountInstrumentMovement记录账户工具的移动交易。这些表共同涵盖了股票转移的相关信息。'
2026-04-16 13:48:00 INFO    [agents.orchestrator] orchestrator.py:859 generate() |   选中表：['VSBHKRpt0430', 'VSBHKRpt0431', 'TSBTransferInstruction', 'VSBTransferInstruction', 'TSBAccountInstrumentMovement']，扩展后：['TSBTransferInstruction', 'VSBTransferInstruction', 'VSBHKRpt0431', 'VSBHKRpt0430', 'TSBAccountInstrumentMovement']
2026-04-16 13:48:01 INFO    [utils.fewshot_selector] fewshot_selector.py:209 select_best_with_score() | [Few-shot] best_with_score: qid=Q2 score=0.9575 preview='列出今日所有客户账户之间的股票转移记录。'
2026-04-16 13:48:01 INFO    [agents.orchestrator] orchestrator.py:432 _generate_sql_golden_adapt() | [GEN] 黄金 few-shot 条件适配: qid=Q2 score=0.9575
2026-04-16 13:48:06 INFO    [agents.orchestrator] orchestrator.py:450 _generate_sql_golden_adapt() | 生成的SQL（黄金适配，chars=494）:
-- 查询所有客户账户间股票转移记录
-- 使用 TSBAccountInstrumentMovement，MovementType='T' 表示账户间转移
SELECT 
    m.MovementID,
    m.AccountID AS FromAccountID,
    m.TransferToAccountID,
    m.InstrumentID,
    i.Name AS InstrumentSymbol,
    m.MovementType,
    m.Quantity AS TransferQuantity,
    m.ValueDate AS TransferDate
FROM TSBAccountInstrumentMovement m
LEFT JOIN MCInstrument i ON m.InstrumentID = i.InstrumentID
WHERE m.MovementType = 'T'
  AND m.ValueDate = CAST(GETDATE() AS DATE)
ORDER BY m.ValueDate;
2026-04-16 13:48:06 INFO    [db.dbhub_tools] dbhub_tools.py:627 _execute_sql() | _execute_sql 执行语句数=1 readonly=True max_rows=1
2026-04-16 13:48:08 INFO    [openai._base_client] _base_client.py:1111 _sleep_for_retry() | Retrying request to /chat/completions in 0.481978 seconds
2026-04-16 13:48:13 INFO    [agents.orchestrator] orchestrator.py:754 _validate_sql() | [validate] 程序+探针+LLM 汇总: valid=True err_count=0 warn_count=0 db_execution_status=0 sql_chars=494
2026-04-16 13:48:13 INFO    [agents.orchestrator] orchestrator.py:921 generate() | [OK] SQL生成与验证通过（1次尝试）
2026-04-16 13:48:13 INFO    [__main__] api_server.py:776 _chat_stream_events() | [API/stream] Text2SQL 完成: valid=True attempts=1 tables_used=['TSBTransferInstruction', 'VSBTransferInstruction', 'VSBHKRpt0431', 'VSBHKRpt0430', 'TSBAccountInstrumentMovement'] sql_chars=494 sql_head="-- 查询所有客户账户间股票转移记录\n-- 使用 TSBAccountInstrumentMovement，MovementType='T' 表示账户间转移\nSELECT \n    m.MovementID,\n    m.AccountID AS FromAccountID,\n    m.TransferToAccountID,\n    m.InstrumentID,\n    i.Name AS InstrumentSymbol,\n    m.MovementType,\n    m.Quantity AS TransferQuantity,\n    m.ValueDate AS TransferDate\nFROM TSBAccountInstrumentMovement m\nLEFT JOIN MCInstrument i ON m.InstrumentID = i.InstrumentID\nWHERE m.MovementType = 'T'\n  AND m.ValueDate = CAST(GETDATE() AS DATE)\nORDER BY m.ValueDate;"