markdown-flow 0.2.14__tar.gz → 0.2.15__tar.gz

{markdown_flow-0.2.14 → markdown_flow-0.2.15}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: markdown-flow
-Version: 0.2.14
+Version: 0.2.15
 Summary: An agent library designed to parse and process MarkdownFlow documents
 Project-URL: Homepage, https://github.com/ai-shifu/markdown-flow-agent-py
 Project-URL: Bug Tracker, https://github.com/ai-shifu/markdown-flow-agent-py/issues

{markdown_flow-0.2.14 → markdown_flow-0.2.15}/markdown_flow/__init__.py

@@ -83,4 +83,4 @@ __all__ = [
     "replace_variables_in_text",
 ]
 
-__version__ = "0.2.14"
+__version__ = "0.2.15"

{markdown_flow-0.2.14 → markdown_flow-0.2.15}/markdown_flow/core.py

@@ -925,61 +925,67 @@ Original Error: {error_message}
         # System prompt for detection
         system_prompt = """You are an intelligent document processing assistant specializing in creating interactive forms.
 
-Task: Analyze the given content block and determine if it needs to be converted to an interaction block.
-
-**CORE PRINCIPLE**: Focus on INTENT and PATTERNS, not specific keywords.
-
-**CONVERSION REQUIRED when the text shows:**
-
-1. **Collection Pattern**:
-   - PATTERN: [Action verb] + [choices/options] + [storage indicator]
-   - PATTERN: Request for user input/selection/choice + destination variable
-   - PATTERN: Interactive UI request with specific options
-
-2. **Storage Indicators** (language-agnostic):
-   - Presence of target variable for NEW data: {{new_variable}}
-   - Assignment operators or arrows: →, =>, "to", "into", "as"
-   - Save/store/record semantics in ANY language
-
-3. **Interactive Intent Signals**:
-   - Imperative mood requesting user action
-   - Multiple specific options provided (not just descriptions)
-   - Form-like structure with fields to fill
-
-**DO NOT CONVERT when the text shows:**
-
-1. **Display/Reference Pattern**:
-   - PATTERN: Using {{existing_var}} + display/list/show action
-   - PATTERN: Information presentation without collection
-   - Keywords suggesting reference/viewing (regardless of language):
-     * "for reference", "供参考", "zur Referenz", "pour référence"
-     * "display", "show", "list", "罗列", "afficher", "anzeigen"
-
-2. **Information Flow**:
-   - Data flows FROM variable TO display (not from user to variable)
-   - Descriptive or explanatory content
-   - Recommendations or suggestions without explicit selection request
-
-**Language-Agnostic Examples**:
-
-❌ Don't convert (any language):
-- "Based on {{history}}, list/display/show [items] for reference"
-- "根据{{history}}的选择，罗列该朝代的皇帝或者年号，供用户参考"
-- "Selon {{history}}, afficher les empereurs pour référence"
-
-✅ Convert (any language):
-- "Ask user to select [option] and save to {{variable}}"
-- "让用户选择风格并记录到{{style}}"
-- "Create buttons: Yes/No" (implies interaction needed)
-- "Demander à l'utilisateur de choisir et enregistrer dans {{choix}}"
-
-**Decision Rule**:
-Look for the SEMANTIC INTENT, not specific words:
-- Is NEW information being COLLECTED from user? → Convert
-- Is EXISTING information being DISPLAYED to user? → Don't convert
-- When uncertain, check: Does this create a new {{variable}} or just use existing ones?
-
-If conversion is needed, generate a STANDARD interaction block format."""
+Task: Analyze the given content block and determine if it needs to be converted to an interaction block to collect user information.
+
+**ABSOLUTE RULE**: Convert ONLY when ALL THREE mandatory elements are explicitly present:
+1. Storage action word + target connector + variable
+2. No exceptions, no implications, no assumptions
+
+**MANDATORY TRIPLE PATTERN (ALL REQUIRED):**
+
+**Element 1: Storage Action Words**
+- Chinese: "记录", "保存", "存储", "收集", "采集"
+- English: "save", "store", "record", "collect", "gather"
+
+**Element 2: Target Connection Words**
+- Chinese: "到", "为", "在", "至"
+- English: "to", "as", "in", "into"
+
+**Element 3: Target Variable**
+- Must contain {{variable_name}} syntax for NEW data storage
+- Variable must be for collecting NEW information, not using existing data
+
+**VALID CONVERSION FORMULA:**
+[Storage Word] + [Connector] + {{new_variable}}
+
+Examples of VALID patterns:
+- "...记录到{{姓名}}"
+- "...保存为{{偏好}}"
+- "...存储在{{选择}}"
+- "...save to {{preference}}"
+- "...collect as {{user_input}}"
+
+**STRICT EXCLUSION RULES:**
+
+❌ NEVER convert if missing ANY element:
+- No storage action word = NO conversion
+- No target connector = NO conversion
+- No {{variable}} = NO conversion
+- Using existing {{variable}} instead of collecting new = NO conversion
+
+❌ NEVER convert casual conversation:
+- Simple questions without storage intent
+- Introduction requests without persistence
+- General inquiries without data collection
+- Educational or exploratory content
+
+❌ NEVER infer or assume storage intent:
+- Don't assume "询问姓名" means "保存姓名"
+- Don't assume "了解偏好" means "记录偏好"
+- Don't assume data collection without explicit storage words
+
+**PATTERN ANALYSIS METHOD:**
+1. **Exact Pattern Match**: Search for [Storage Word] + [Connector] + {{variable}}
+2. **No Pattern = No Conversion**: If exact pattern not found, return needs_interaction: false
+3. **Zero Tolerance**: No partial matches, no similar meanings, no interpretations
+
+**ULTRA-CONSERVATIVE APPROACH:**
+- If there's ANY doubt about storage intent = DON'T convert
+- If storage pattern is not 100% explicit = DON'T convert
+- If you need to "interpret" or "infer" storage intent = DON'T convert
+- Prefer false negatives over false positives
+
+When exact pattern is found, generate structured interaction data. Otherwise, always return needs_interaction: false."""
 
         # User message with content and context
         # Build user prompt with document context

{markdown_flow-0.2.14 → markdown_flow-0.2.15}/markdown_flow.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: markdown-flow
-Version: 0.2.14
+Version: 0.2.15
 Summary: An agent library designed to parse and process MarkdownFlow documents
 Project-URL: Homepage, https://github.com/ai-shifu/markdown-flow-agent-py
 Project-URL: Bug Tracker, https://github.com/ai-shifu/markdown-flow-agent-py/issues