File size: 7,670 Bytes
e0b6f12
 
1a943f1
f03a154
e0b6f12
 
 
 
 
 
27f4250
9a88164
 
1a943f1
2c15ffb
 
 
 
 
 
1a943f1
27f4250
1d3eed5
e0b6f12
 
 
 
 
 
 
27f4250
5b7f342
1a943f1
 
9f8e537
cd88d31
9f8e537
 
 
 
 
 
f03a154
 
9f8e537
1a943f1
f03a154
1a943f1
 
5b7f342
 
 
 
 
 
631e1ee
 
 
 
 
 
 
 
 
 
 
 
 
 
5b7f342
 
 
 
631e1ee
 
 
5b7f342
 
791be58
5b7f342
631e1ee
5b7f342
 
 
 
 
791be58
1c90111
 
 
 
 
 
 
 
 
 
f03a154
1c90111
 
 
f03a154
1c90111
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f03a154
1c90111
f03a154
1c90111
 
 
f03a154
1c90111
 
 
 
 
 
 
 
 
 
 
 
 
791be58
 
1c90111
e9db129
791be58
 
 
631e1ee
2c15ffb
1c90111
2c15ffb
 
1c90111
 
 
e9db129
 
 
 
 
 
 
791be58
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
import openai
import os
import json
import re

def analyze_code(code: str) -> str:
    """
    Uses OpenAI's GPT-4.1 mini model to analyze the given code.
    Returns the analysis as a string.
    """
    from openai import OpenAI
    client = OpenAI(api_key=os.getenv("modal_api"))
    client.base_url = os.getenv("base_url")
    system_prompt = (
        "You are a highly precise and strict JSON generator. Analyze the code given to you. "
        "Your ONLY output must be a valid JSON object with the following keys: 'strength', 'weaknesses', 'speciality', 'relevance rating'. "
        "Do NOT include any explanation, markdown, or text outside the JSON. Do NOT add any commentary, preamble, or postscript. "
        "If you cannot answer, still return a valid JSON with empty strings for each key. "
        "Example of the ONLY valid output:\n"
        "{\n  'strength': '...', \n  'weaknesses': '...', \n  'speciality': '...', \n  'relevance rating': '...'\n}"
    )
    response = client.chat.completions.create(
        model="Orion-zhen/Qwen2.5-Coder-7B-Instruct-AWQ",  # Updated model
        messages=[
            {"role": "system", "content": system_prompt},
            {"role": "user", "content": code}
        ],
        max_tokens=512,
        temperature=0.7
    )
    return response.choices[0].message.content

def parse_llm_json_response(response: str):
    try:
        # Extract only the substring between the first '{' and the last '}'
        print("DEBUGGGGG ::: ",response)
        start = response.find('{')
        end = response.rfind('}')
        if start != -1 and end != -1 and end > start:
            json_str = response[start:end+1]
        else:
            json_str = response
        # Replace single quotes with double quotes for JSON keys/values
        json_str = re.sub(r"(?<!\\)'", '"', json_str)
        return json.loads(json_str)
    except Exception as e:
        print("DEBUGGGGG error ::: ", e)
        return {"error": f"Failed to parse JSON: {e}", "raw": response}

def combine_repo_files_for_llm(repo_dir="repo_files", output_file="combined_repo.txt"):
    """
    Combines all .py and .md files in the given directory (recursively) into a single text file.
    Returns the path to the combined file.
    """
    combined_content = []
    seen_files = set()
    # Priority files
    priority_files = ["app.py", "README.md"]
    for pf in priority_files:
        pf_path = os.path.join(repo_dir, pf)
        if os.path.isfile(pf_path):
            try:
                with open(pf_path, "r", encoding="utf-8") as f:
                    combined_content.append(f"\n# ===== File: {pf} =====\n")
                    combined_content.append(f.read())
                seen_files.add(os.path.abspath(pf_path))
            except Exception as e:
                combined_content.append(f"\n# Could not read {pf_path}: {e}\n")
    # All other .py and .md files
    for root, _, files in os.walk(repo_dir):
        for file in files:
            if file.endswith(".py") or file.endswith(".md"):
                file_path = os.path.join(root, file)
                abs_path = os.path.abspath(file_path)
                if abs_path in seen_files:
                    continue
                try:
                    with open(file_path, "r", encoding="utf-8") as f:
                        combined_content.append(f"\n# ===== File: {file} =====\n")
                        combined_content.append(f.read())
                    seen_files.add(abs_path)
                except Exception as e:
                    combined_content.append(f"\n# Could not read {file_path}: {e}\n")
    with open(output_file, "w", encoding="utf-8") as out_f:
        out_f.write("\n".join(combined_content))
    return output_file

def analyze_code_chunk(code: str) -> str:
    """
    Analyzes a code chunk and returns a JSON summary for that chunk.
    """
    from openai import OpenAI
    client = OpenAI(api_key=os.getenv("modal_api"))
    client.base_url = os.getenv("base_url")
    chunk_prompt = (
        "You are a highly precise and strict JSON generator. Analyze the following code chunk. "
        "Your ONLY output must be a valid JSON object with the following keys: 'strength', 'weaknesses', 'speciality', 'relevance rating'. "
        "All property names and string values MUST use double quotes (\"). Do NOT use single quotes. "
        "Do NOT include any explanation, markdown, or text outside the JSON. Do NOT add any commentary, preamble, or postscript. "
        "If you cannot answer, still return a valid JSON with empty strings for each key. "
        "Example of the ONLY valid output:\n"
        '{\n  "strength": "...", \n  "weaknesses": "...", \n  "speciality": "...", \n  "relevance rating": "..."\n}'
    )
    response = client.chat.completions.create(
        model="Orion-zhen/Qwen2.5-Coder-7B-Instruct-AWQ",
        messages=[
            {"role": "system", "content": chunk_prompt},
            {"role": "user", "content": code}
        ],
        max_tokens=512,
        temperature=0.7
    )
    return response.choices[0].message.content

def aggregate_chunk_analyses(chunk_jsons: list) -> str:
    """
    Aggregates a list of chunk JSONs into a single JSON summary using the LLM.
    """
    from openai import OpenAI
    client = OpenAI(api_key=os.getenv("modal_api"))
    client.base_url = os.getenv("base_url")
    aggregation_prompt = (
        "You are a highly precise and strict, code analyzer and JSON generator. You are given a list of JSON analyses of code chunks. "
        "Aggregate these into a SINGLE overall JSON summary with the same keys: 'strength', 'weaknesses', 'speciality', 'relevance rating'. "
        "All property names and string values MUST use double quotes (\"). Do NOT use single quotes. "
        "Summarize and combine the information from all chunks. Do NOT include any explanation, markdown, or text outside the JSON. "
        "If a key is missing in all chunks, use an empty string. "
        "Example of the ONLY valid output:\n"
        '{\n  "strength": "...", \n  "weaknesses": "...", \n  "speciality": "...", \n  "relevance rating": "..."\n}'
    )
    user_content = "Here are the chunk analyses:\n" + "\n".join(chunk_jsons)
    response = client.chat.completions.create(
        model="Orion-zhen/Qwen2.5-Coder-7B-Instruct-AWQ",
        messages=[
            {"role": "system", "content": aggregation_prompt},
            {"role": "user", "content": user_content}
        ],
        max_tokens=512,
        temperature=0.3
    )
    return response.choices[0].message.content

def analyze_combined_file(output_file="combined_repo.txt"):
    """
    Reads the combined file, splits it into 500-line chunks, analyzes each chunk, and aggregates the LLM's output into a final summary.
    Returns the chunk JSONs (for debugging) and the aggregated analysis as a string.
    """
    try:
        with open(output_file, "r", encoding="utf-8") as f:
            lines = f.readlines()
        chunk_size = 500
        chunk_jsons = []
        for i in range(0, len(lines), chunk_size):
            chunk = "".join(lines[i:i+chunk_size])
            analysis = analyze_code_chunk(chunk)
            chunk_jsons.append(analysis)
        final_summary = aggregate_chunk_analyses(chunk_jsons)
        debug_output = (
            "==== Chunk JSON Outputs ===="
            + "\n\n".join([f"Chunk {i+1} JSON:\n{chunk_jsons[i]}" for i in range(len(chunk_jsons))])
            + "\n\n==== Final Aggregated Summary ===="
            + f"\n{final_summary}"
        )
        return debug_output
    except Exception as e:
        return f"Error analyzing combined file: {e}"