# -*- coding: utf-8 -*- import os def load_config(): base_config = { # --- 基础运行参数 --- "lit_target_papers": int(os.environ.get("LIT_TARGET_PAPERS", "80")), "lit_per_page": int(os.environ.get("LIT_PER_PAGE", "100")), "lit_max_workers": int(os.environ.get("LIT_MAX_WORKERS", "5")), "chunk_words_default": int(os.environ.get("CHUNK_WORDS_DEFAULT", "1500")), "target_words_min": 5000, "target_words_default": 5000, "target_words_max": 20000, "search_max_retries": max(1, int(os.environ.get("SEARCH_MAX_RETRIES", "4"))), "translation_batch_tokens": max(800, int(os.environ.get("TRANSLATION_BATCH_TOKENS", "2500"))), "translation_glossary_term_limit": max(10, int(os.environ.get("TRANSLATION_GLOSSARY_TERM_LIMIT", "40"))), "translation_min_coverage_ratio": float(os.environ.get("TRANSLATION_MIN_COVERAGE_RATIO", "0.25")), "translation_min_block_ratio_zh": float(os.environ.get("TRANSLATION_MIN_BLOCK_RATIO_ZH", "0.28")), "translation_min_block_ratio_cyrillic": float(os.environ.get("TRANSLATION_MIN_BLOCK_RATIO_CYRILLIC", "0.65")), "translation_max_block_ratio": float(os.environ.get("TRANSLATION_MAX_BLOCK_RATIO", "2.20")), "openalex_email": os.environ.get("OPENALEX_EMAIL", "").strip(), # --- RAG 与解析配置 --- "rag_chunk_size": int(os.environ.get("RAG_CHUNK_SIZE", "3000")), "rag_top_k": int(os.environ.get("RAG_TOP_K", "3")), "max_extract_chars": int(os.environ.get("MAX_EXTRACT_CHARS", "150000")), # A DeepSeek request must fail before the 90-second Worker generation # lease can expire without real execution progress. Retries renew the # lease through the execution heartbeat hook. "api_timeouts": { "standard": (15, 70), "stream": (15, 70), "search": 15 }, "deepseek_stream_idle_seconds": max( 20, min(65, int(os.environ.get("DEEPSEEK_STREAM_IDLE_SECONDS", "60"))), ), # --- API 节点配置 --- "deepseek_api_url": os.environ.get( "DEEPSEEK_API_URL", "https://api.deepseek.com/chat/completions", ), # Model names are centralized here and can be upgraded in HF Variables. # Application and engine code select a task role, never a concrete model. "deepseek_models": { "reasoning": os.environ.get( "DEEPSEEK_MODEL_REASONING", "deepseek-v4-pro", ), "writing": os.environ.get( "DEEPSEEK_MODEL_WRITING", "deepseek-v4-pro", ), "translation": os.environ.get( "DEEPSEEK_MODEL_TRANSLATION", "deepseek-v4-pro", ), "fast": os.environ.get( "DEEPSEEK_MODEL_FAST", "deepseek-v4-flash", ), "fallback": os.environ.get( "DEEPSEEK_MODEL_FALLBACK", "deepseek-v4-flash", ), }, "deepseek_task_settings": { "reasoning": { "thinking": True, "reasoning_effort": os.environ.get( "DEEPSEEK_REASONING_EFFORT", "high", ), "allow_fallback": False, }, "writing": { "thinking": False, "reasoning_effort": "high", "allow_fallback": False, }, "translation": { "thinking": False, "reasoning_effort": "high", "allow_fallback": False, }, "fast": { "thinking": False, "reasoning_effort": "low", "allow_fallback": True, }, }, "deepseek_max_retries": int( os.environ.get("DEEPSEEK_MAX_RETRIES", "3") ), "deepseek_show_reasoning": os.environ.get( "DEEPSEEK_SHOW_REASONING", "false", ).strip().lower() in {"1", "true", "yes", "on"}, # Citation-semantic audit repairs only affected sentences. Technical # failures fall back to deterministic single-source recovery and are # recorded in the audit log instead of terminating the whole paper. "citation_semantic_audit": { "enabled": os.environ.get( "CITATION_SEMANTIC_AUDIT_ENABLED", "true", ).strip().lower() in {"1", "true", "yes", "on"}, "batch_size": max( 1, int(os.environ.get("CITATION_SEMANTIC_BATCH_SIZE", "5")), ), "candidate_limit": max( 3, int(os.environ.get("CITATION_SEMANTIC_CANDIDATE_LIMIT", "10")), ), "fail_closed": os.environ.get( "CITATION_SEMANTIC_FAIL_CLOSED", "false", ).strip().lower() in {"1", "true", "yes", "on"}, "technical_retries": max( 1, int(os.environ.get("CITATION_SEMANTIC_TECHNICAL_RETRIES", "2")), ), "json_repair_retries": max( 0, int(os.environ.get("CITATION_SEMANTIC_JSON_REPAIR_RETRIES", "1")), ), }, # R3-Free task execution runs outside Streamlit. The executor renews # the Worker lease only while real Python/model progress is recent. "executor_heartbeat_interval_seconds": max( 10, int(os.environ.get("SMARTPAPER_EXECUTOR_HEARTBEAT_SECONDS", "15")), ), "executor_activity_grace_seconds": max( 30, int(os.environ.get("SMARTPAPER_EXECUTOR_ACTIVITY_GRACE_SECONDS", "45")), ), "executor_bootstrap_timeout_seconds": max( 5, int(os.environ.get("SMARTPAPER_EXECUTOR_BOOTSTRAP_TIMEOUT_SECONDS", "20")), ), "executor_bootstrap_poll_ms": max( 50, int(os.environ.get("SMARTPAPER_EXECUTOR_BOOTSTRAP_POLL_MS", "100")), ), "manuscript_quality": { "abstract_max_words": int(os.environ.get("ABSTRACT_MAX_WORDS", "200")), "abstract_max_numeric_mentions": int(os.environ.get("ABSTRACT_MAX_NUMERIC_MENTIONS", "6")), "forbidden_phrases": [ "delve into", "intricate", "paramount", "overarching", "pivotal", "foster", "seamlessly", "multifaceted", "beacon", "landscape", "underscore", "robust", "firstly", "secondly", "moreover", "furthermore", "in conclusion", "to summarize", "as an ai", "ai-generated", "this response", ], }, "openalex_api_url": os.environ.get("OPENALEX_API_URL", "https://api.openalex.org/works"), "s2_api_url": os.environ.get("S2_API_URL", "https://api.semanticscholar.org/graph/v1"), # --- UI 多语言标签 --- "ui_labels": { "中文": {"title": "📊 工商管理论文智能体", "btn_generate": "🚀 生成初稿", "btn_download": "📥 下载文件", "topic_label": "📝 论文名称", "keywords_label": "🔍 关键字", "words_label": "📏 目标总单词数 (5000-20000单词)", "success": "🎉 流水线推演完毕!双语文档已就绪。"}, "English": {"title": "📊 Business Administration Article Agent", "btn_generate": "🚀 Generate Draft", "btn_download": "📥 Download", "topic_label": "📝 Article Title", "keywords_label": "🔍 Keywords", "words_label": "📏 Target Word Count", "success": "🎉 Task complete!"}, "Русский": {"title": "📊 Агент статей по бизнес-администрированию", "btn_generate": "🚀 Черновик", "btn_download": "📥 Скачать", "topic_label": "📝 Тема", "keywords_label": "🔍 Ключевые слова", "words_label": "📏 Количество слов", "success": "🎉 Задача выполнена!"}, "Қазақша": {"title": "📊 Бизнес-басқару жөніндегі ғылыми мақала агенті", "btn_generate": "🚀 Жоба дайындау", "btn_download": "📥 Жүктеу", "topic_label": "📝 Мақала атауы", "keywords_label": "🔍 Түйін сөздер", "words_label": "📏 Мақсатты сөз саны", "success": "🎉 Тапсырма аяқталды!"} }, "target_lang_map": { "中文": "Simplified Chinese (简体中文)", "English": "Simplified Chinese (简体中文)", "Русский": "Russian (Русский)", "Қазақша": "Kazakh (Қазақша)" }, "workspace_dir": ".workspace", "docx_styles": { "font_name": "Times New Roman", "font_size_pt": 12, "code_font": "Courier New", "code_size_pt": 11 }, "blacklists": { "meta_sections": [ "abstract", "keyword", "keywords", "摘要", "关键词", "关键字", "reference", "references", "reference list", "参考文献", "acknowledgment", "acknowledgements", "致谢", "аннотация", "ключевые слова", "түйіндеме", "кілт сөздер" ] }, # ===================================================================== # Canonical manuscript structures. Top-level titles are deterministic: # the model may write content, but it may not rename, remove, or reorder # required sections. # ===================================================================== "amj_schema": [ { "section_id": "introduction", "section": "Introduction", "weight": 0.10, "subsections": [], }, { "section_id": "theory", "section": "Theoretical Background and Hypotheses", "weight": 0.27, "subsections": [ {"subsection_id": "conceptual_background", "title": "Conceptual Background and Research Gap", "share": 0.23}, {"subsection_id": "theoretical_mechanisms", "title": "Theoretical Mechanisms", "share": 0.27}, {"subsection_id": "hypothesis_development", "title": "Hypothesis Development", "share": 0.35}, {"subsection_id": "integrated_model", "title": "Integrated Research Model", "share": 0.15}, ], }, { "section_id": "methodology", "section": "Methodology", "weight": 0.20, "subsections": [ {"subsection_id": "research_design", "title": "Research Design and Context", "share": 0.18}, {"subsection_id": "sample_data", "title": "Sample and Data Collection", "share": 0.20}, {"subsection_id": "measures", "title": "Measures and Construct Operationalization", "share": 0.25}, {"subsection_id": "analysis_strategy", "title": "Analytical Strategy", "share": 0.22}, {"subsection_id": "validity_bias", "title": "Validity, Bias, and Robustness Procedures", "share": 0.15}, ], }, { "section_id": "results", "section": "Results", "weight": 0.23, "subsections": [ {"subsection_id": "measurement_results", "title": "Descriptive Statistics and Measurement Assessment", "share": 0.34}, {"subsection_id": "hypothesis_results", "title": "Hypothesis and Association Tests", "share": 0.46}, {"subsection_id": "additional_results", "title": "Additional Analyses and Robustness Checks", "share": 0.20}, ], }, { "section_id": "discussion", "section": "Discussion", "weight": 0.15, "subsections": [ {"subsection_id": "interpretation", "title": "Interpretation of the Findings", "share": 0.30}, {"subsection_id": "theoretical_contributions", "title": "Theoretical Contributions", "share": 0.30}, {"subsection_id": "practical_implications", "title": "Practical Implications", "share": 0.20}, {"subsection_id": "limitations", "title": "Limitations and Future Research", "share": 0.20}, ], }, { "section_id": "conclusion", "section": "Conclusion", "weight": 0.05, "subsections": [], }, ], "asq_schema": [ { "section_id": "introduction", "section": "Introduction", "weight": 0.10, "subsections": [], }, { "section_id": "theoretical_framing", "section": "Theoretical Framing", "weight": 0.18, "subsections": [ {"subsection_id": "phenomenon_puzzle", "title": "Phenomenon and Theoretical Puzzle", "share": 0.35}, {"subsection_id": "conceptual_tension", "title": "Relevant Literature and Conceptual Tension", "share": 0.40}, {"subsection_id": "research_question", "title": "Research Question and Analytical Focus", "share": 0.25}, ], }, { "section_id": "methods", "section": "Research Setting and Methods", "weight": 0.17, "subsections": [ {"subsection_id": "research_setting", "title": "Research Setting", "share": 0.24}, {"subsection_id": "data_collection", "title": "Data Sources and Collection", "share": 0.28}, {"subsection_id": "analytic_procedure", "title": "Analytical Procedure", "share": 0.30}, {"subsection_id": "trustworthiness", "title": "Trustworthiness, Ethics, and Reflexivity", "share": 0.18}, ], }, { "section_id": "findings", "section": "Findings", "weight": 0.30, "dynamic_subsections": "qualitative_themes", "subsections": [ {"subsection_id": "emergent_model", "title": "Emergent Process Model", "share": 0.18}, ], }, { "section_id": "discussion", "section": "Discussion", "weight": 0.15, "subsections": [ {"subsection_id": "interpretation", "title": "Interpretation of the Emergent Findings", "share": 0.30}, {"subsection_id": "theoretical_contributions", "title": "Theoretical Contributions", "share": 0.30}, {"subsection_id": "boundaries", "title": "Boundary Conditions and Transferability", "share": 0.20}, {"subsection_id": "practical_implications", "title": "Practical Implications", "share": 0.20}, ], }, { "section_id": "conclusion", "section": "Conclusion", "weight": 0.05, "subsections": [], }, { "section_id": "appendix", "section": "Appendix: Data Structure and Evidence", "weight": 0.05, "subsections": [], }, ], "manuscript_validation": { "minimum_total_ratio": 0.85, "maximum_total_ratio": 1.15, "minimum_section_words": 120, "minimum_conclusion_words": 120, "minimum_qualitative_themes": 3, "minimum_qualitative_quotes": 8, }, "prompt_templates": { "meta_extract": """You are an expert academic data extractor. Read the provided text and extract the core metadata. CRITICAL: You MUST output ONLY a valid JSON object. Do not include markdown formatting or explanations. { "paper_title": "", "core_theory": "", "variables": { "IV": "", "DV": "", "Mediators": "", "Moderators": "" }, "methodology": { "sample_size": "", "context": "", "analysis_tool": "" }, "key_findings": "", "future_gaps": "" }""", "synthesis_system": "You are a top-tier academic researcher in Business Administration.", "synthesis_user": """Topic: {topic}{user_injection} Literature Metadata: {refs_text} [SYNTHESIS MANDATE: THEMATIC INTEGRATION] 1. You MUST NOT summarize papers sequentially (e.g., "A found X. B found Y."). 2. Synthesize by THEME or THEORETICAL TENSION rather than paper-by-paper summaries. 3. Apply claim-specific citation: each sentence may contain at most one [CITE-XX] tag. Never group multiple sources in one parenthesis or sentence. If sources support different claims, use separate sentences; if they support the same claim, select the single most direct source. 4. Explicitly highlight theoretical conflicts or consensus. 5. Conclude by revealing a specific blind spot that necessitates our current research. {directive}""" } } # ===================================================================== # 定量引擎 (AMJ 风格) - 保持原样,极致严谨与假设推演 # ===================================================================== amj_prompts = { "sys_academic_writer": """You are a distinguished, highly cited scholar writing a manuscript for the Academy of Management Journal (AMJ). Your writing must exhibit unparalleled theoretical rigor, causal depth, and academic authority. [CRITICAL LANGUAGE MANDATE]: You MUST generate all responses strictly in ACADEMIC ENGLISH. Even if the user provides topic, data, or context in Chinese or another language, your final output MUST be in English. [ABSOLUTE ANTI-AI-TONE MANDATES]: 1. CRITICAL: NEVER use these cliché AI words: delve into, intricate, paramount, overarching, pivotal, foster, seamlessly, multifaceted, beacon, landscape, underscore, robust. 2. CRITICAL: NEVER use robotic transition phrases (e.g., Firstly, Moreover, Furthermore, In conclusion, To summarize). Use conceptual bridges instead. 3. NATURAL SYNTAX: Vary sentence structure only where the argument requires it. Avoid artificial short-long sentence alternation and repetitive templates. 4. ACADEMIC HEDGING: Use strategic hedging (e.g., 'This suggests a tendency toward X, bounded by Y'). 5. NO SWEEPING GENERALIZATIONS: Every sentence must carry specific theoretical weight or empirical fact. 6. FOCUS ON CAUSALITY: You MUST articulate the exact theoretical mechanism driving the relationship. 7. ACADEMIC REGISTER: Use concise, accurate, and rigorous language. Concepts must be explicit, hierarchy clear, and reasoning logically traceable. 8. PROHIBITED RHETORIC: Never use metaphors, analogies, rhetorical questions, literary embellishment, or promotional claims. 9. ABSTRACT DISCIPLINE: In abstracts, report only the minimum numerical evidence needed to convey the main finding; do not crowd the abstract with coefficients or test statistics. 10. STRUCTURAL DISCIPLINE: Cover only the assigned section and subsection. Do not recreate earlier sections, invent alternative headings, or omit required analytical elements. 11. CLAIM-SPECIFIC CITATION: Each sentence may contain at most one [CITE-XX] tag. Never group multiple references in one parenthesis or sentence. Separate distinct source-supported claims into separate sentences; when sources support the same claim, retain only the single most direct source. Every cited sentence must express a claim directly supported by the cited source evidence. """, "deep_refinement_directive": "Produce a final, polished section ready for top-tier submission. Ensure flawless logical flow without meta-commentary. Apply claim-specific citation: use at most one [CITE-XX] tag per sentence, never combine sources in one parenthesis, and cite only the single most direct source when multiple sources support the same claim.\n[SELF-REFLECTION]: Before drafting, critically analyze common AI clichés related to this topic and actively suppress them in your output.", "deep_synthesis_directive": "Structure this synthesis to expose a critical theoretical tension: Consensus vs Paradox, Competing Perspectives, Theoretical Blind Spot.", "hypothesis_development_directive": "Construct a rigorous causal chain: 1. Base Theory. 2. Mechanism (Mediator logic). 3. Boundary Condition (Moderator logic). 4. Hypothesis Phrasing (italicized).", "methodological_defense_directive": "Write with extreme defensive precision: Justify Contextual Relevance, Detail Endogeneity & Bias Mitigation, Measurement Validity, and Analytical Strategy.", "discussion_depth_directive": "Elevate findings back to grand theory. Explicitly state how the study extends, refines, or challenges named theories. Provide counter-intuitive implications.", "conclusion_anchor_directive": "1. Conceptual Pivot. 2. Mechanism Summary. 3. Call to Action for the next decade.", "anchor_generation_directive": "Generate a STRUCTURED ABSTRACT (max 200 words) mimicking an AMJ abstract, and a CONCLUSION ANCHOR (approx. 150 words). Output format:\n---ABSTRACT---\n...\n---CONCLUSION---\n...", "empirical_data_logic": "Maintain strict adherence to APA 7th edition reporting standards. Include plausible degrees of freedom, exact p-values, confidence intervals, and effect sizes.", } # ===================================================================== # 定性引擎 (ASQ 风格) - 聚焦现象描述、意义建构与语录引用 # ===================================================================== asq_prompts = { "sys_academic_writer": """You are a senior editor and distinguished qualitative researcher writing for Administrative Science Quarterly (ASQ). Your writing style is phenomenon-driven, deeply narrative, and theoretically rich. [CRITICAL LANGUAGE MANDATE]: You MUST generate all responses strictly in ACADEMIC ENGLISH. [ABSOLUTE ASQ MANDATES]: 1. FOCUS ON THE PUZZLE: Embrace counter-intuitive empirical phenomena and paradoxes. 2. THICK DESCRIPTION: Use descriptive, evocative language to ground your qualitative findings in reality. 3. SENSEMAKING: Focus on how organizational actors interpret, negotiate, and construct their reality. 4. NO FORMAL HYPOTHESES: DO NOT use 'Hypothesis 1' phrasing. Use 'Propositions' or conceptual emergent models instead. 5. NO AI CLICHES: Strictly avoid 'delve', 'tapestry', 'multifaceted', 'beacon', 'landscape'. 6. ACADEMIC REGISTER: Use concise, accurate, and rigorous language with explicit concepts and logically ordered claims. 7. PROHIBITED RHETORIC: Never use metaphors, analogies, rhetorical questions, literary embellishment, or promotional claims. Use concrete evidence-based description rather than decorative prose. 8. ABSTRACT DISCIPLINE: Keep numerical details to the minimum needed to communicate the empirical puzzle, main finding, and contribution. 9. CLAIM-SPECIFIC CITATION: Each sentence may contain at most one [CITE-XX] tag. Never group multiple references in one parenthesis or sentence. Separate distinct source-supported claims into separate sentences; when sources support the same claim, retain only the single most direct source. Every cited sentence must express a claim directly supported by the cited source evidence.""", "deep_refinement_directive": "Ensure logical flow and focus on the emergent theoretical model. Write in continuous, engaging paragraphs. Apply claim-specific citation: use at most one [CITE-XX] tag per sentence, never combine sources in one parenthesis, and cite only the single most direct source when several sources support the same claim.", "deep_synthesis_directive": "Structure this synthesis to highlight a critical empirical puzzle or theoretical paradox that qualitative investigation can unravel.", "hypothesis_development_directive": "Develop the theoretical framing. DO NOT use formal hypotheses. Detail the conceptual gaps and frame the overarching research questions or theoretical propositions.", "methodological_defense_directive": "Detail the research setting vividly. Justify data sources (interviews, ethnographic observations, archives), and rigorously explain the step-by-step coding process (e.g., Gioia methodology).", "discussion_depth_directive": "Elevate the emergent qualitative findings back to grand theory. Contrast your inductive process model with existing linear or variance-based theories.", "conclusion_anchor_directive": "Summarize the theoretical contribution, the resolution of the empirical puzzle, and the sensemaking implications.", "anchor_generation_directive": "Generate a NARRATIVE ABSTRACT (max 200 words) mimicking an ASQ abstract (focusing on the puzzle, setting, and emergent model), and a CONCLUSION ANCHOR (approx. 150 words). Output format:\n---ABSTRACT---\n...\n---CONCLUSION---\n...", "empirical_data_logic": "Present findings as a compelling narrative. You MUST integrate representative quotes seamlessly into the text to provide raw evidence for each 1st-order concept and 2nd-order theme. Ensure the voice of the informants is central.", } generic_prompts = amj_prompts.copy() return base_config, amj_prompts, asq_prompts, generic_prompts DEFAULT_CONFIG, AMJ_PROMPTS, ASQ_PROMPTS, GENERIC_PROMPTS = load_config() APP_CONFIG = DEFAULT_CONFIG.copy()