algomath-extract 1.0.13 → 1.0.14

package/bin/install.js

@@ -73,7 +73,7 @@ console.log(GREEN + `
    ██╔══██║██║     ██║   ██║██║   ██║██║╚██╔╝██║██╔══██║   ██║   ██╔══██║
    ██║  ██║███████╗╚██████╔╝╚██████╔╝██║ ╚═╝ ██║██║  ██║   ██║   ██║  ██║
    ╚═╝  ╚═╝╚══════╝ ╚═════╝  ╚═════╝ ╚═╝     ╚═╝╚═╝  ╚═╝   ╚═╝   ╚═╝  ╚═╝
-                    Framework Installer v1.0.11
+                    Framework Installer v1.0.14
               Mathematical Algorithm Extraction & Code
 ` + RESET + '\n');
 

package/commands/algo-extract.md

@@ -13,10 +13,23 @@ Supports automatic extraction or step-by-step with review points.
 </objective>
 
 <execution>
-Execute the extraction by running the Node.js wrapper:
+Execute the extraction by running:
+
+**Option 1 - Using npx (no install required):**
 ```bash
-npx algoextract "$@"
+npx -p algomath-extract algoextract "$@"
 ```
+
+**Option 2 - If installed globally:**
+```bash
+algoextract "$@"
+```
+
+**Option 3 - If installed locally in project:**
+```bash
+./node_modules/.bin/algoextract "$@"
+```
+
 This will:
 1. Parse the provided file or arguments
 2. Extract algorithm steps using LLM
@@ -27,49 +40,50 @@ This will:
 <process>
 Execute extraction workflow:
 
+
 1. **Parse Arguments**
-   - Check if file path provided
-   - Determine mode: auto, step-by-step, or interactive
+- Check if file path provided
+- Determine mode: auto, step-by-step, or interactive
 
 2. **Extract Text from File**
-   - Auto-detect file type (PDF, .txt, .md)
-   - Use pdfplumber for PDFs
-   - Handle encoding issues
-   - Validate extraction success
+- Auto-detect file type (PDF, .txt, .md)
+- Use pdfplumber for PDFs
+- Handle encoding issues
+- Validate extraction success
 
 3. **Parse Algorithm Structure**
-   - Use opencode LLM to parse text
-   - Identify algorithm name
-   - Extract inputs and outputs
-   - Parse step-by-step procedure
-   - Handle mathematical notation
+- Use opencode LLM to parse text
+- Identify algorithm name
+- Extract inputs and outputs
+- Parse step-by-step procedure
+- Handle mathematical notation
 
 4. **Review Point (if step-by-step)**
-   - Display extracted text
-   - Ask user to confirm or edit
-   - Apply user corrections
+- Display extracted text
+- Ask user to confirm or edit
+- Apply user corrections
 
 5. **Generate Structured Steps**
-   - Convert parsed text to Algorithm object
-   - Validate step structure
-   - Check for completeness
+- Convert parsed text to Algorithm object
+- Validate step structure
+- Check for completeness
 
 6. **Review Point (if step-by-step)**
-   - Display structured steps
-   - Show inputs, outputs, step list
-   - Allow editing
+- Display structured steps
+- Show inputs, outputs, step list
+- Allow editing
 
 7. **Save Algorithm**
-   - Create directory: .algomath/algorithms/{name}/
-   - Save source.txt (original text)
-   - Save steps.json (structured)
-   - Save metadata.json (info)
+- Create directory: .algomath/algorithms/{name}/
+- Save source.txt (original text)
+- Save steps.json (structured)
+- Save metadata.json (info)
 
 8. **Display Summary**
-   - Show algorithm name
-   - Show step count
-   - Display next steps
-   - Suggest: /algo-generate
+- Show algorithm name
+- Show step count
+- Display next steps
+- Suggest: /algo-generate
 </process>
 
 <examples>

package/commands/algo-generate.md

@@ -4,6 +4,7 @@ argument-hint: "[--review] [--template-only] [--llm-only]"
 tools:
   read: true
   write: true
+  Bash: true
 ---
 
 <objective>
@@ -11,83 +12,111 @@ Generate executable Python code from structured algorithm steps.
 Supports template-based generation (fast, reliable) or LLM-enhanced (for complex expressions).
 </objective>
 
+<execution>
+Execute the code generation by running:
+
+**Option 1 - Using npx (no install required):**
+```bash
+npx -p algomath-extract algogenerate "$@"
+```
+
+**Option 2 - If installed globally:**
+```bash
+algogenerate "$@"
+```
+
+**Option 3 - If installed locally in project:**
+```bash
+./node_modules/.bin/algogenerate "$@"
+```
+
+This will:
+1. Load the extracted algorithm from .algomath/algorithms/
+2. Generate Python code using template or LLM
+3. Save generated code to .algomath/generated/
+4. Display generation summary
+</execution>
 
 <process>
 Execute code generation workflow:
 
+
 1. **Load Algorithm**
-   - Read steps.json from current algorithm
-   - Validate step structure
-   - Check for completeness
+- Read steps.json from current algorithm
+- Validate step structure
+- Check for completeness
 
 2. **Select Generation Mode**
-   - Default: Hybrid (template + LLM for complex parts)
-   - --template-only: Rule-based only (faster)
-   - --llm-only: Full LLM generation (slower, more accurate)
+- Default: Hybrid (template + LLM for complex parts)
+- --template-only: Rule-based only (faster)
+- --llm-only: Full LLM generation (slower, more accurate)
 
 3. **Generate Function Signature**
-   - Extract inputs and outputs
-   - Add type hints
-   - Generate docstring
-
-4. **Generate Step Code**
-   - Convert each step to Python
-   - Handle loops, conditionals, assignments
-   - Preserve variable names
-   - Add comments explaining logic
-
-5. **Review Point (if --review)**
-   - Display generated code
-   - Syntax highlighting
-   - Ask for approval
-   - Allow editing
-
-6. **Validate Code**
-   - Syntax check with Python parser
-   - Check for common errors
-   - Ensure all variables defined
-
-7. **Save Code**
-   - Write to .algomath/algorithms/{name}/generated.py
-   - Update metadata.json
+- Extract inputs and outputs
+- Add type hints
+- Create docstring
+
+4. **Generate Step Implementation**
+- Convert each step to Python code
+- Handle mathematical operations
+- Manage variable scope
+- Add error handling
+
+5. **Add Helper Functions**
+- Generate necessary imports
+- Create utility functions
+- Add validation
+
+6. **Review Point (if --review)**
+- Display generated code
+- Ask for approval
+- Allow regeneration with feedback
+
+7. **Save Generated Code**
+- Save to .algomath/generated/{name}.py
+- Create __init__.py for imports
+- Add requirements.txt if needed
 
 8. **Display Summary**
-   - Show generated file path
-   - Line count
-   - Next steps: /algo-run
+- Show file path
+- Display code preview
+- Suggest: /algo-run
 </process>
 
 <examples>
 
-**Generate with default hybrid mode:**
+**Generate with review:**
 /algo-generate
 
-**Generate with review:**
-/algo-generate --review
+**Auto-generate:**
+/algo-generate --auto
 
-**Template-based only (faster):**
+**Template-only (faster):**
 /algo-generate --template-only
 
-**LLM-enhanced only (better for complex):**
+**LLM-enhanced (better for complex math):**
 /algo-generate --llm-only
 
 </examples>
 
 <options>
 
---review
-Show generated code for review before saving
+--auto
+Skip review, generate automatically
 
 --template-only
-Use rule-based generation only (no LLM)
+Use only template-based generation (faster, no LLM)
 
 --llm-only
-Use LLM for all generation (slower but more accurate)
+Use only LLM generation (slower, handles complex expressions)
+
+--review
+Force review mode even in auto mode
 
 </options>
 
 <next_steps>
 /algo-run - Execute the generated code
-/algo-verify - Verify execution results
-/algo-status - Check algorithm state
+/algo-verify - Verify the generated code
+/algo-status - Check current state
 </next_steps>

package/commands/algo-help.md

@@ -10,6 +10,22 @@ tools:
 Display help information, available commands, and usage examples.
 </objective>
 
+<execution>
+Show help by running:
+```bash
+npx algomath-extract algohelp "$@"
+```
+
+Or if algomath-extract is installed globally:
+```bash
+algohelp "$@"
+```
+
+This will display:
+1. Available commands and their descriptions
+2. Usage examples
+3. Workflow information
+</execution>
 
 <process>
 Display help:

package/commands/algo-list.md

@@ -10,6 +10,22 @@ tools:
 Display list of all saved algorithms with their status and basic info.
 </objective>
 
+<execution>
+List algorithms by running:
+```bash
+npx algomath-extract algolist "$@"
+```
+
+Or if algomath-extract is installed globally:
+```bash
+algolist "$@"
+```
+
+This will:
+1. Scan .algomath/algorithms/ directory
+2. List all saved algorithms
+3. Display status and basic info for each
+</execution>
 
 <process>
 List algorithms:

package/commands/algo-run.md

@@ -4,6 +4,7 @@ argument-hint: "[--skip] [--timeout <seconds>]"
 tools:
   read: true
   write: true
+  Bash: true
 ---
 
 <objective>
@@ -11,68 +12,89 @@ Execute generated Python code in a safe sandboxed environment.
 Captures stdout, stderr, and execution results.
 </objective>
 
+<execution>
+Execute the generated code by running:
+
+**Option 1 - Using npx (no install required):**
+```bash
+npx -p algomath-extract algorun "$@"
+```
+
+**Option 2 - If installed globally:**
+```bash
+algorun "$@"
+```
+
+**Option 3 - If installed locally in project:**
+```bash
+./node_modules/.bin/algorun "$@"
+```
+
+This will:
+1. Load the generated Python code
+2. Execute in a sandboxed environment
+3. Capture output and results
+4. Display execution summary
+</execution>
 
 <process>
 Execute code in sandbox:
 
+
 1. **Load Generated Code**
-   - Read generated.py from current algorithm
-   - Validate code exists
-   - Check syntax
+- Read generated.py from current algorithm
+- Validate code exists
+- Check for syntax errors
 
-2. **Create Sandbox**
-   - Create isolated temp directory
-   - Copy code to sandbox
-   - Set resource limits
+2. **Prepare Execution**
+- Create isolated sandbox
+- Set resource limits
+- Prepare input data
+- Set timeout (default: 30s)
 
 3. **Execute Code**
-   - Run in subprocess with timeout (default 30s)
-   - Capture stdout and stderr
-   - Monitor resource usage
-   - Handle exceptions
-
-4. **Process Results**
-   - Capture output
-   - Record execution time
-   - Check for errors
-   - Format results
-
-5. **Save Results**
-   - Write to execution.log
-   - Update metadata.json
-   - Update state to EXECUTION_COMPLETE
-
-6. **Display Results**
-   - Show output
-   - Show execution time
-   - Show status (success/error)
-   - Suggest next steps
+- Run in subprocess
+- Capture stdout/stderr
+- Monitor execution
+- Handle timeouts
+
+4. **Capture Results**
+- Save output to execution.log
+- Capture return code
+- Record execution time
+- Store any generated files
+
+5. **Display Results**
+- Show stdout
+- Show stderr (if any)
+- Display execution time
+- Show success/failure status
 </process>
 
 <examples>
 
-**Execute code:**
+**Execute current algorithm:**
 /algo-run
 
-**Skip execution:**
-/algo-run --skip
-
-**Custom timeout:**
+**Execute with custom timeout:**
 /algo-run --timeout 60
 
+**Skip execution (for testing):**
+/algo-run --skip
+
 </examples>
 
 <options>
 
 --skip
-Skip execution and proceed directly to verification
+Skip execution, just validate
 
 --timeout <seconds>
-Maximum execution time (default: 30)
+Set execution timeout (default: 30)
 
 </options>
 
 <next_steps>
 /algo-verify - Verify execution results
-/algo-status - Check algorithm state
+/algo-status - Check current state
 </next_steps>

package/commands/algo-status.md

@@ -11,6 +11,22 @@ Display current algorithm state, progress, and available next steps.
 Shows workflow state, completion status, and suggestions.
 </objective>
 
+<execution>
+Check status by running:
+```bash
+npx algomath-extract algostatus "$@"
+```
+
+Or if algomath-extract is installed globally:
+```bash
+algostatus "$@"
+```
+
+This will:
+1. Load current algorithm state
+2. Display progress and completion status
+3. Show available next steps
+</execution>
 
 <process>
 Display status:

package/commands/algo-verify.md

@@ -4,6 +4,7 @@ argument-hint: "[--step <N>] [--detailed] [--diagnostic] [--expected <value>]"
 tools:
   read: true
   write: true
+  Bash: true
 ---
 
 <objective>
@@ -11,89 +12,107 @@ Verify execution results, compare to expected values, explain algorithm behavior
 and identify potential edge cases.
 </objective>
 
+<execution>
+Execute verification by running:
+
+**Option 1 - Using npx (no install required):**
+```bash
+npx -p algomath-extract algoverify "$@"
+```
+
+**Option 2 - If installed globally:**
+```bash
+algoverify "$@"
+```
+
+**Option 3 - If installed locally in project:**
+```bash
+./node_modules/.bin/algoverify "$@"
+```
+
+This will:
+1. Load execution results and algorithm steps
+2. Verify correctness against expected values
+3. Generate explanation of algorithm behavior
+4. Identify edge cases and potential issues
+</execution>
 
 <process>
 Execute verification workflow:
 
+
 1. **Load Execution Results**
-   - Read execution.log
-   - Load algorithm steps
-   - Get generated code
-
-2. **Verify Execution**
-   - Check if execution succeeded
-   - Verify no errors
-   - Validate output present
-
-3. **Compare Results (if --expected)**
-   - Compare actual vs expected output
-   - Support numeric tolerance for floats
-   - Show differences
-
-4. **Generate Explanation**
-   - Brief mode: 1-2 sentence summary
-   - Detailed mode: Step-by-step walkthrough
-   - Step mode: Explain specific step N
-
-5. **Detect Edge Cases**
-   - Empty inputs
-   - Boundary values
-   - Division by zero
-   - Array bounds
-   - Infinite loops
-
-6. **Diagnostic Mode (if failed)**
-   - Analyze error
-   - Suggest fixes
-   - Explain failure point
-
-7. **Save Report**
-   - Write to verification.log
-   - Update state to VERIFIED
-
-8. **Display Summary**
-   - Execution status
-   - Explanation
-   - Edge cases found
-   - Next steps
+- Read execution.log
+- Load algorithm steps
+- Check execution status
+
+2. **Check Results**
+- Compare output to expected
+- Validate return codes
+- Check for errors
+- Verify output format
+
+3. **Generate Explanation**
+- Explain what the algorithm does
+- Describe each step
+- Show data flow
+- Explain mathematical concepts
+
+4. **Identify Edge Cases**
+- Empty inputs
+- Single element
+- Maximum values
+- Boundary conditions
+- Error conditions
+
+5. **Suggest Tests**
+- Propose test cases
+- Suggest inputs to try
+- Recommend validations
+
+6. **Display Summary**
+- Show verification status
+- Display explanation
+- List edge cases
+- Suggest improvements
 </process>
 
 <examples>
 
-**Verify results:**
+**Verify current algorithm:**
 /algo-verify
 
-**Explain specific step:**
-/algo-verify --step 3
+**Verify specific step:**
+/algo-verify --step 5
 
-**Detailed explanation:**
+**Detailed verification:**
 /algo-verify --detailed
 
-**Compare with expected:**
-/algo-verify --expected "42"
-
-**Diagnostic for failed runs:**
+**Diagnostic mode:**
 /algo-verify --diagnostic
 
+**Compare to expected:**
+/algo-verify --expected "[1, 2, 3]"
+
 </examples>
 
 <options>
 
 --step <N>
-Explain step number N in detail
+Explain specific step number
 
 --detailed
-Show detailed step-by-step explanation
+Show detailed verification
 
 --diagnostic
-Run diagnostic mode for failed executions
+Run diagnostic checks
 
 --expected <value>
-Expected output for comparison
+Compare to expected output
 
 </options>
 
 <next_steps>
-/algo-extract - Start with new algorithm
 /algo-status - Check current state
+/algo-list - View all algorithms
 </next_steps>

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "algomath-extract",
-  "version": "1.0.13",
+  "version": "1.0.14",
   "description": "AlgoMath Framework - Transform AI assistants into reliable mathematical problem-solving environments",
   "main": "index.js",
   "bin": {