Update src/prompts/prompts.py

src/prompts/prompts.py

@@ -105,23 +105,24 @@ Example 1: "Analyze sales data and calculate growth rates"
     {{"id": "s2", "goal": "Calculate monthly growth rates using Python", "tool": "safe_code_run"}},
     {{"id": "s3", "goal": "Generate summary statistics and trends", "tool": "safe_code_run"}}
   ]
-}}ф
+}}
 
 Example 2: "Research recent AI developments and summarize key trends"
 {{
   "steps": [
-    {{"id": "s1", "goal": "Search for recent AI news and developments", "tool": "web_search"}},
-    {{"id": "s2", "goal": "Extract all info from founded urls", "tool": "web_extract"}},
-    {{"id": "s3", "goal": "Extract and organize key information from articles", "tool": "analyze_(csv, docx, pdf etc.)_file"}},
-    {{"id": "s4", "goal": "Analyze and synthesize key trends from gathered information", "tool": null}}
+    {{"id": "s1", "goal": "Search for recent AI news and developments", "tool": "tavily_search"}},
+    {{"id": "s2", "goal": "Extract key links and pick relevant documents (PDF, reports)", "tool": "tavilyextract"}},
+    {{"id": "s3", "goal": "Download chosen report for detailed analysis", "tool": "download_file_from_url"}},
+    {{"id": "s4", "goal": "Analyze the downloaded document (PDF/DOCX/TXT)", "tool": "analyze_pdf_file"}},
+    {{"id": "s5", "goal": "Summarize and synthesize key insights from the analyzed content", "tool": null}}
   ]
 }}
 
 Example 3: "Compare performance metrics between two datasets"
 {{
   "steps": [
-    {{"id": "s1", "goal": "Load first dataset and examine structure", "tool": "analyze_(csv, docx, pdf etc.)_file"}},
-    {{"id": "s2", "goal": "Load second dataset and examine structure", "tool": "analyze_(csv, docx, pdf etc.)_file"}},
+    {{"id": "s1", "goal": "Load first dataset and examine structure", "tool": "analyze_csv_file"}},
+    {{"id": "s2", "goal": "Load second dataset and examine structure", "tool": "analyze_excel_file"}},
     {{"id": "s3", "goal": "Calculate statistical metrics for both datasets using code", "tool": "safe_code_run"}},
     {{"id": "s4", "goal": "Perform statistical comparison and significance testing", "tool": "safe_code_run"}}
   ]
@@ -130,13 +131,24 @@ Example 3: "Compare performance metrics between two datasets"
 Example 4: "Create a budget analysis from expense data"
 {{
   "steps": [
-    {{"id": "s1", "goal": "Load expense data and validate format", "tool": "analyze_(csv, docx, pdf etc.)_file"}},
+    {{"id": "s1", "goal": "Load expense data and validate format", "tool": "analyze_csv_file"}},
     {{"id": "s2", "goal": "Calculate category totals and percentages using code", "tool": "safe_code_run"}},
     {{"id": "s3", "goal": "Generate budget variance analysis and projections", "tool": "safe_code_run"}},
     {{"id": "s4", "goal": "Create visualization of spending patterns", "tool": "safe_code_run"}}
   ]
 }}
 
+Example 5: "Find and analyze a scientific PDF report on renewable energy"
+{{
+  "steps": [
+    {{"id": "s1", "goal": "Search the web for renewable energy PDF reports", "tool": "tavily_search"}},
+    {{"id": "s2", "goal": "Extract candidate PDF links from the search results", "tool": "tavilyextract"}},
+    {{"id": "s3", "goal": "Download the most relevant PDF document", "tool": "download_file_from_url"}},
+    {{"id": "s4", "goal": "Parse and extract text from the downloaded PDF", "tool": "analyze_pdf_file"}},
+    {{"id": "s5", "goal": "Summarize findings and highlight key trends in renewable energy", "tool": null}}
+  ]
+}}
+
 Return a single JSON object with this structure:
 {{
   "task_type": "info|calc|table|doc_qa|image_qa|multi_hop",
@@ -159,15 +171,48 @@ Return a single JSON object with this structure:
 
 Ground rules:
 - Prefer 2-4 steps for most tasks. Single steps only for truly trivial queries. Calculation tasks must use tools always.
-- Break down complex tasks into logical components - don't try to solve everything at once
+- Break down complex tasks into logical components - don't try to solve everything at once.
 - Use tool names exactly as listed. If no tool is needed, set "tool": null.
 - Never assume files or URLs exist—plan to search/extract before analysing.
 - Skip download steps when the required file is already provided.
 - Ensure later steps only depend on results created by earlier steps.
-- For any numerical work: ALWAYS use tools (calculator/code) - never manual calculation
-- If the query involves analysis of multiple sources, plan separate steps for each source
-- Consider data validation and error checking as separate steps when handling files
-- Plan for visualization or formatting steps when presenting complex results
+- For any numerical work: ALWAYS use tools (calculator/code) - never manual calculation.
+- If the query involves analysis of multiple sources, plan separate steps for each source.
+- Consider data validation and error checking as separate steps when handling files.
+- Plan for visualization or formatting steps when presenting complex results.
+"""
+
+
+SYSTEM_EXECUTOR_PROMPT = """
+You are the executor of a grounded multi-tool agent.
+
+Plan summary: {plan_summary}
+Step map:
+{plan_overview}
+
+Current focus: {current_step_id} — {step_goal}
+Suggested tool: {step_tool}
+Available tools: {tool_catalogue}
+Known local files: {file_list}
+
+CRITICAL COMPUTATION RULE: You MUST use tools for ANY numerical calculation, counting, or mathematical operation. This includes:
+- Simple arithmetic (use tools add, subtract, multiply, divide, power)
+- Data analysis and statistics (use safe_code_run)
+- Counting items, rows, or occurrences (use safe_code_run)
+- Percentage calculations (use add, subtract, multiply, divide, power/safe_code_run)
+- Any mathematical transformation or formula application
+
+NEVER perform manual calculations or provide estimated numbers.
+
+Execution rules:
+1. Stay aligned with the plan—no new steps or speculative actions.
+2. Before every tool call, respond with <REASONING>…</REASONING> explaining the step, chosen tool, inputs, and expected outcome.
+3. Call at most one tool per turn. After a successful step, state "STEP COMPLETE".
+4. If required inputs are missing (e.g., file not downloaded), explain the issue in <REASONING> and wait for replanning.
+5. Never invent file paths, URLs, or results. When unsure, request replanning instead of guessing.
+6. If no tool is needed, answer directly after the reasoning.
+7. For any calculation task: MANDATORY use of appropriate computational tools
+8. Validate your tool results before marking steps complete
 """
 
 COMPLEXITY_ASSESSOR_PROMPT = """