From 6923132655ef0e9fd5acbc797cd465f57534787c Mon Sep 17 00:00:00 2001
From: James Ketrenos <james_git@ketrenos.com>
Date: Mon, 12 May 2025 11:36:36 -0700
Subject: [PATCH] Restructured how BackstoryTextField works to not propogate
 changes until Enter

---
 frontend/src/BackstoryTextField.tsx |  30 ++--
 frontend/src/Conversation.tsx       |   9 +-
 frontend/src/Message.tsx            |   2 +-
 frontend/src/StyledMarkdown.tsx     |   9 +-
 src/utils/agents/job_description.py | 218 +++++++++++++++-------------
 5 files changed, 140 insertions(+), 128 deletions(-)

diff --git a/frontend/src/BackstoryTextField.tsx b/frontend/src/BackstoryTextField.tsx
index bb7bc44..39e0243 100644
--- a/frontend/src/BackstoryTextField.tsx
+++ b/frontend/src/BackstoryTextField.tsx
@@ -1,4 +1,4 @@
-import React, { useRef, useEffect, ChangeEvent, KeyboardEvent } from 'react';
+import React, { useRef, useEffect, ChangeEvent, KeyboardEvent, useState } from 'react';
 import { useTheme } from '@mui/material/styles';
 import './BackstoryTextField.css';
 
@@ -7,8 +7,7 @@ interface BackstoryTextFieldProps {
   disabled?: boolean;
   multiline?: boolean;
   placeholder?: string;
-  onChange?: (e: ChangeEvent<HTMLTextAreaElement | HTMLInputElement>) => void;
-  onKeyDown?: (e: KeyboardEvent<HTMLTextAreaElement | HTMLInputElement>) => void;
+  onEnter: (value: string) => void;
 }
 
 const BackstoryTextField: React.FC<BackstoryTextFieldProps> = ({
@@ -16,12 +15,12 @@ const BackstoryTextField: React.FC<BackstoryTextFieldProps> = ({
   disabled = false,
   multiline = false,
   placeholder,
-  onChange,
-  onKeyDown,
+  onEnter
 }) => {
   const theme = useTheme();
   const textareaRef = useRef<HTMLTextAreaElement>(null);
   const shadowRef = useRef<HTMLTextAreaElement>(null);
+  const [editValue, setEditValue] = useState<string>(value);
 
   useEffect(() => {
     if (multiline && textareaRef.current && shadowRef.current) {
@@ -43,15 +42,10 @@ const BackstoryTextField: React.FC<BackstoryTextFieldProps> = ({
     }
   }, [value, multiline, textareaRef, shadowRef, placeholder]);
 
-  const handleChange = (e: ChangeEvent<HTMLTextAreaElement | HTMLInputElement>) => {
-    if (onChange) {
-      onChange(e);
-    }
-  };
-
-  const handleKeyDown = (e: KeyboardEvent<HTMLTextAreaElement | HTMLInputElement>) => {
-    if (onKeyDown) {
-      onKeyDown(e);
+  const handleKeyDown = (event: KeyboardEvent<HTMLTextAreaElement | HTMLInputElement>) => {
+    if (event.key === 'Enter' && (!multiline || !event.shiftKey)) {
+      setEditValue('');
+      onEnter(event.currentTarget.value);
     }
   };
 
@@ -74,10 +68,10 @@ const BackstoryTextField: React.FC<BackstoryTextFieldProps> = ({
       <input
         className="BackstoryTextField"
         type="text"
-        value={value}
+        value={editValue}
         disabled={disabled}
         placeholder={placeholder}
-        onChange={handleChange}
+        onChange={(e) => { setEditValue(e.target.value); }}
         onKeyDown={handleKeyDown}
         style={sharedStyle}
       />
@@ -89,10 +83,10 @@ const BackstoryTextField: React.FC<BackstoryTextFieldProps> = ({
       <textarea
         className="BackstoryTextField"
         ref={textareaRef}
-        value={value}
+        value={editValue}
         disabled={disabled}
         placeholder={placeholder}
-        onChange={handleChange}
+        onChange={(e) => { setEditValue(e.target.value); }}
         onKeyDown={handleKeyDown}
         style={{
           ...sharedStyle,
diff --git a/frontend/src/Conversation.tsx b/frontend/src/Conversation.tsx
index 2b7672e..a16c4a6 100644
--- a/frontend/src/Conversation.tsx
+++ b/frontend/src/Conversation.tsx
@@ -246,10 +246,8 @@ const Conversation = forwardRef<ConversationHandle, ConversationProps>(({
     }
   };
 
-  const handleKeyPress = (event: any) => {
-    if (event.key === 'Enter' && !event.shiftKey) {
-      sendQuery(query);
-    }
+  const handleEnter = (value: string) => {
+    sendQuery(value);
   };
 
   useImperativeHandle(ref, () => ({
@@ -553,8 +551,7 @@ const Conversation = forwardRef<ConversationHandle, ConversationProps>(({
               disabled={processing}
               multiline={multiline ? true : false}
               value={query}
-              onChange={(e: any) => setQuery(e.target.value)}
-              onKeyDown={handleKeyPress}
+              onEnter={handleEnter}
               placeholder={prompt}
             />
           </div>
diff --git a/frontend/src/Message.tsx b/frontend/src/Message.tsx
index 830f24e..74b01cf 100644
--- a/frontend/src/Message.tsx
+++ b/frontend/src/Message.tsx
@@ -287,7 +287,7 @@ const Message = (props: MessageProps) => {
               overflow: "auto", /* Handles scrolling for the div */
             }}
           >
-            <StyledMarkdown {...{ content: formattedContent, submitQuery, sessionId, setSnack }} />
+            <StyledMarkdown streaming={message.role === "streaming"} {...{ content: formattedContent, submitQuery, sessionId, setSnack }} />
           </Scrollable>
            :
           <Typography
diff --git a/frontend/src/StyledMarkdown.tsx b/frontend/src/StyledMarkdown.tsx
index da8bf8f..afb636d 100644
--- a/frontend/src/StyledMarkdown.tsx
+++ b/frontend/src/StyledMarkdown.tsx
@@ -17,10 +17,11 @@ interface StyledMarkdownProps extends BackstoryElementProps {
   className?: string,
   content: string,
   sx?: SxProps,
+  streaming?: boolean,
 };
 
 const StyledMarkdown: React.FC<StyledMarkdownProps> = (props: StyledMarkdownProps) => {
-  const { className, content, submitQuery, sx } = props;
+  const { className, content, submitQuery, sx, streaming } = props;
   const theme = useTheme();
 
   const overrides: any = {
@@ -28,16 +29,16 @@ const StyledMarkdown: React.FC<StyledMarkdownProps> = (props: StyledMarkdownProp
       component: (element: any) => {
         const { className } = element.children.props;
         const content = element.children?.props?.children || "";
-        if (className === "lang-mermaid") {
+        if (className === "lang-mermaid" && !streaming) {
           return <Mermaid className="Mermaid" chart={content} />;
         }
         if (className === "lang-markdown") {
           return <MuiMarkdown children={content} />;
         }
-        if (className === "lang-json") {
+        if (className === "lang-json" && !streaming) {
           try {
             const fixed = jsonrepair(content);
-            return <Scrollable autoscroll className="JsonViewScrollable">
+            return <Scrollable className="JsonViewScrollable">
               <JsonView
                 className="JsonView"
                 style={{
diff --git a/src/utils/agents/job_description.py b/src/utils/agents/job_description.py
index a1ca0ac..5e6eb87 100644
--- a/src/utils/agents/job_description.py
+++ b/src/utils/agents/job_description.py
@@ -8,6 +8,7 @@ import json
 import traceback
 import asyncio
 import time
+from collections import defaultdict
 
 from . base import Agent, agent_registry, LLMMessage
 from .. conversation import Conversation
@@ -419,32 +420,60 @@ class JobDescription(Agent):
           metadata["error"] = message.response
           raise
 
+  def format_rag_context(self, rag_results: List[Dict[str, Any]]) -> str:
+      """
+      Format RAG results from process_job_requirements into a structured string.
+      
+      Args:
+          rag_results: List of dictionaries from process_job_requirements.
+      
+      Returns:
+          A formatted string for inclusion in the prompt.
+      """
+      if not rag_results:
+          return "No additional context available."
+      
+      # Group results by category and subcategory
+      grouped_context = defaultdict(list)
+      for result in rag_results:
+          key = f"{result['category']}/{result['subcategory']}".strip("/")
+          grouped_context[key].append({
+              "query": result["context"],
+              "content": result["content"][:100] + "..." if len(result["content"]) > 100 else result["content"]
+          })
+      
+      # Format as a structured string
+      context_lines = ["Additional Context from Document Retrieval:"]
+      for category, items in grouped_context.items():
+          context_lines.append(f"\nCategory: {category}")
+          for item in items:
+              context_lines.append(f"- Query: {item['query']}")
+              context_lines.append(f"  Relevant Document: {item['content']}")
+      
+      return "\n".join(context_lines)
+  
   # Stage 1B: Candidate Analysis Implementation
-  def create_candidate_analysis_prompt(self, resume: str, context: str) -> tuple[str, str]:
+  def create_candidate_analysis_prompt(self, resume: str, rag_results: List[Dict[str, Any]]) -> tuple[str, str]:
       """Create the prompt for candidate qualifications analysis."""
+  
       # system_prompt = """
-      # You are an objective resume analyzer. Your task is to catalog ALL skills, experiences, and qualifications
-      # present in a candidate's materials WITHOUT any reference to any job description.
-      
-      # ## INSTRUCTIONS:
-      
-      # 1. Analyze ONLY the candidate's resume and context provided.
-      # 2. Create a comprehensive inventory of the candidate's actual qualifications.
-      # 3. DO NOT consider any job requirements - this is a pure candidate analysis task.
-      # 4. For each qualification, cite exactly where in the materials it appears.
-      # 5. DO NOT duplicate or repeat time periods or skills once listed.
-      
-      # ## OUTPUT FORMAT:
-      
+      # You are an objective resume analyzer. Create a comprehensive inventory of all skills, experiences, and qualifications present in the candidate's materials.
+
+      # CORE PRINCIPLES:
+      # - Analyze ONLY the candidate's resume and provided context
+      # - Focus ONLY on the candidate's actual qualifications
+      # - Do not reference any job requirements
+      # - Include only explicitly mentioned information
+
+      # OUTPUT FORMAT:
       # ```json
       # {
       #   "candidate_qualifications": {
       #     "technical_skills": [
       #       {
       #         "skill": "skill name",
-      #         "evidence": "exact quote from materials",
-      #         "source": "resume or context",
-      #         "expertise_level": "explicit level mentioned or 'unspecified'"
+      #         "evidence_location": "where in resume this appears",
+      #         "expertise_level": "stated level or 'unspecified'"
       #       }
       #     ],
       #     "work_experience": [
@@ -462,88 +491,81 @@ class JobDescription(Agent):
       #         "degree": "degree name",
       #         "institution": "institution name",
       #         "completed": true/false,
-      #         "evidence": "exact quote from materials"
+      #         "graduation_date": "date or 'ongoing'"
       #       }
       #     ],
       #     "projects": [
       #       {
       #         "name": "project name",
       #         "description": "brief description",
-      #         "technologies_used": ["tech1", "tech2"],
-      #         "evidence": "exact quote from materials"
+      #         "technologies_used": ["tech1", "tech2"]
       #       }
       #     ],
       #     "soft_skills": [
       #       {
       #         "skill": "skill name",
-      #         "evidence": "exact quote or inference basis",
-      #         "source": "resume or context"
+      #         "context": "brief mention of where this appears"
       #       }
       #     ]
       #   }
       # }
-      # ```
-      
-      # Be thorough and precise. Include ONLY skills and experiences explicitly mentioned in the materials.
-      # For each entry, provide the exact text evidence from the materials that supports its inclusion.
-      # Do not make assumptions about skills based on job titles or project names - only include skills explicitly mentioned.
       # """
+      system_prompt = """\
+You are an objective resume analyzer. Create a comprehensive inventory of all skills, experiences, and qualifications present in the candidate's materials.
 
-      system_prompt = """
-      You are an objective resume analyzer. Create a comprehensive inventory of all skills, experiences, and qualifications present in the candidate's materials.
+CORE PRINCIPLES:
+- Analyze ONLY the candidate's resume and provided context.
+- Focus ONLY on the candidate's actual qualifications explicitly mentioned in the resume.
+- Use the additional context to clarify or provide background for terms, skills, or experiences mentioned in the resume (e.g., to understand the scope of a skill like 'Python' or a role's responsibilities).
+- Do NOT treat the context as job requirements or infer qualifications not explicitly stated in the resume.
+- Include only explicitly mentioned information from the resume, supplemented by context where relevant.
 
-      CORE PRINCIPLES:
-      - Analyze ONLY the candidate's resume and provided context
-      - Focus ONLY on the candidate's actual qualifications
-      - Do not reference any job requirements
-      - Include only explicitly mentioned information
-
-      OUTPUT FORMAT:
-      ```json
+OUTPUT FORMAT:
+```json
+{
+  "candidate_qualifications": {
+    "technical_skills": [
       {
-        "candidate_qualifications": {
-          "technical_skills": [
-            {
-              "skill": "skill name",
-              "evidence_location": "where in resume this appears",
-              "expertise_level": "stated level or 'unspecified'"
-            }
-          ],
-          "work_experience": [
-            {
-              "role": "job title",
-              "company": "company name",
-              "duration": "time period",
-              "responsibilities": ["resp1", "resp2"],
-              "technologies_used": ["tech1", "tech2"],
-              "achievements": ["achievement1", "achievement2"]
-            }
-          ],
-          "education": [
-            {
-              "degree": "degree name",
-              "institution": "institution name",
-              "completed": true/false,
-              "graduation_date": "date or 'ongoing'"
-            }
-          ],
-          "projects": [
-            {
-              "name": "project name",
-              "description": "brief description",
-              "technologies_used": ["tech1", "tech2"]
-            }
-          ],
-          "soft_skills": [
-            {
-              "skill": "skill name",
-              "context": "brief mention of where this appears"
-            }
-          ]
-        }
+        "skill": "skill name",
+        "evidence_location": "where in resume this appears",
+        "expertise_level": "stated level or 'unspecified'"
       }
-      """
-
+    ],
+    "work_experience": [
+      {
+        "role": "job title",
+        "company": "company name",
+        "duration": "time period",
+        "responsibilities": ["resp1", "resp2"],
+        "technologies_used": ["tech1", "tech2"],
+        "achievements": ["achievement1", "achievement2"]
+      }
+    ],
+    "education": [
+      {
+        "degree": "degree name",
+        "institution": "institution name",
+        "completed": true/false,
+        "graduation_date": "date or 'ongoing'"
+      }
+    ],
+    "projects": [
+      {
+        "name": "project name",
+        "description": "brief description",
+        "technologies_used": ["tech1", "tech2"]
+      }
+    ],
+    "soft_skills": [
+      {
+        "skill": "skill name",
+        "context": "brief mention of where this appears"
+      }
+    ]
+  }
+}
+"""
+      context = self.format_rag_context(rag_results)
       prompt = f"Resume:\n{resume}\n\nAdditional Context:\n{context}"
       return system_prompt, prompt
 
@@ -602,10 +624,10 @@ class JobDescription(Agent):
           message.status = "done"
           yield message
 
-  async def analyze_candidate_qualifications(self, message: Message, resume: str, additional_context: str, metadata: Dict[str, Any]) -> AsyncGenerator[Message, None]:
+  async def analyze_candidate_qualifications(self, message: Message, resume: str, rag_context: List[Dict[str, Any]], metadata: Dict[str, Any]) -> AsyncGenerator[Message, None]:
       """Analyze candidate qualifications from resume and context."""
       try:
-          system_prompt, prompt = self.create_candidate_analysis_prompt(resume, additional_context)
+          system_prompt, prompt = self.create_candidate_analysis_prompt(resume, rag_context)
           metadata["system_prompt"] = system_prompt
           metadata["prompt"] = prompt
           async for message in self.call_llm(message, system_prompt, prompt):
@@ -1048,7 +1070,7 @@ Based on the reference data above, please create a corrected version of the resu
                 
                 # Call find_similar for the item
                 try:
-                    rag_results = retriever.find_similar(item, top_k=10, threshold=0.7)
+                    rag_results = retriever.find_similar(item, top_k=20, threshold=0.4) # Strict matching
                     # Process each result
                     for doc_id, content, distance, metadata in zip(
                         rag_results["ids"], 
@@ -1089,21 +1111,22 @@ Based on the reference data above, please create a corrected version of the resu
         reverse=True
     )
     
-    # Return top 20 results
-    return sorted_results[:20]
+    # Return top 10 results
+    return sorted_results[:10]
 
 
   async def generate_rag_content(self, message: Message, job_requirements: Dict[str, Any]) -> AsyncGenerator[Message, None]:
     results = self.process_job_requirements(job_requirements = job_requirements)
-    message.response = f"Retrieved {len(results)} documents:\n"
-    for result in results:
-        message.response += f"""
-ID: {result['id']}, Context: {result['context']}, \
-Category: {result['category']}/{result['subcategory']}, \
-Similarity Score: {result['score']:.3f}, \
-Combined Score: {result['weight'] * result['score']:.3f}, \
-Content: {result['content']}
-"""
+    message.response = f"Retrieved {len(results)} documents."
+    message.metadata["rag_context"] = results
+#     for result in results:
+#         message.response += f"""
+# ID: {result['id']}, Context: {result['context']}, \
+# Category: {result['category']}/{result['subcategory']}, \
+# Similarity Score: {result['score']:.3f}, \
+# Combined Score: {result['weight'] * result['score']:.3f}, \
+# Content: {result['content']}
+# """
     message.status = "done"
     yield message
     return
@@ -1153,17 +1176,14 @@ Content: {result['content']}
     if message.status == "error":
       return
 
-    yield message    
-    return
-
-    additional_context = message.preamble["context"]
+    rag_context = message.metadata["rag_context"]
     metadata["analyze_candidate_qualifications"] = {
-        "additional_context": additional_context
+        "rag_context": rag_context
     }
     async for message in self.analyze_candidate_qualifications(
       message=message,
       resume=resume,
-      additional_context=additional_context, 
+      rag_context=rag_context, 
       metadata=metadata["analyze_candidate_qualifications"]):
       if message.status != "done":
         yield message