remove max token limit, increase timeout, update config

app/config.py

@@ -25,7 +25,7 @@ class Settings(BaseSettings):
 
     api_host: str = "0.0.0.0"
     api_port: int = 8000
-    debug: bool = False
+    debug: bool = True
 
     log_level: str = "DEBUG"
     log_filename: str = "app.log"

app/core/job_parser.py

@@ -41,7 +41,6 @@ Include the full original text under "description".
                 {"role": "user", "content": raw_text},
             ],
             temperature=0.2,
-            max_tokens=500,
         )
         # Parse the JSON output
         parsed = json.loads(response.choices[0].message.content)

app/core/query_gen.py

@@ -68,7 +68,6 @@ Offer Extended
                 {"role": "user", "content": job_description.strip()},
             ],
             temperature=0.2,
-            max_tokens=300,
         )
 
         return json.loads(response.choices[0].message.content)

app/core/scoring.py

@@ -284,7 +284,6 @@ class CandidateScorer:
                     {"role": "user", "content": user_prompt.strip()},
                 ],
                 temperature=0.1,
-                max_tokens=300,
             )
 
             result = asyncio.run(

app/services/api_clients.py

@@ -204,7 +204,7 @@ class LinkedInProfileClient:
                 "x-rapidapi-host": "fresh-linkedin-profile-data.p.rapidapi.com",
                 "x-rapidapi-key": settings.rapidapi_api_key,
             },
-            timeout=30.0,
+            timeout=60.0,
         )
         self.semaphore = asyncio.Semaphore(settings.max_concurrent_requests)
 
@@ -321,7 +321,7 @@ class GitHubClient:
     """Client for fetching GitHub profile HTML"""
 
     def __init__(self):
-        self._client = httpx.AsyncClient(timeout=20.0)
+        self._client = httpx.AsyncClient(timeout=60.0)
         self.semaphore = asyncio.Semaphore(settings.max_concurrent_requests)
 
     async def __aenter__(self):