Improved token counting for OpenAI endpoints (llama.cpp token count -> cached prompt_tokens from last output -> naive string estimate). Logger refactoring with JSON format debugging to log file. Various bugfixes. Removed unused templates.py

logging_config.py

@@ -1,25 +1,56 @@
-import sys
+import json
 import logging
+import logging.handlers
+from datetime import datetime, timezone
 from rich.logging import RichHandler
-from rich.console import Console
 
-def setup_logging(level=logging.INFO, debug=False):
-    
-    # silence noisy libraries
-    for lib_name in ("urllib3","requests","http.client","markdown","Markdown"):
+
+class JSONFormatter(logging.Formatter):
+    def format(self, record):
+        log_entry = {
+            "timestamp": datetime.now(timezone.utc).isoformat(),
+            "level": record.levelname,
+            "logger": record.name,
+            "message": record.getMessage(),
+            "module": record.module,
+            "function": record.funcName,
+            "line": record.lineno,
+        }
+        standard_keys = set(logging.LogRecord("", 0, "", 0, "", (), None).__dict__.keys())
+        for key, value in record.__dict__.items():
+            if key not in standard_keys and key not in ("message", "msg", "args"):
+                log_entry[key] = value
+        if record.exc_info and record.exc_info[0]:
+            log_entry["exception"] = self.formatException(record.exc_info)
+        return json.dumps(log_entry, default=str, ensure_ascii=False)
+
+
+def setup_logging(level=logging.INFO, log_file=None):
+    for lib_name in ("urllib3", "requests", "http.client", "markdown", "Markdown"):
         logging.getLogger(lib_name).setLevel(logging.WARNING)
 
+    handlers = [
+        RichHandler(
+            rich_tracebacks=True,
+            show_path=False,
+            log_time_format="[%H:%M:%S]",
+            markup=True,
+        )
+    ]
+
+    if log_file:
+        file_handler = logging.handlers.RotatingFileHandler(
+            log_file, maxBytes=10_000_000, backupCount=3, encoding="utf-8"
+        )
+        file_handler.setFormatter(JSONFormatter())
+        handlers.append(file_handler)
+
     logging.basicConfig(
         level=level,
         format="%(message)s",
         datefmt="[%X]",
-        handlers=[RichHandler(
-            rich_tracebacks=True, 
-            show_path=False, 
-            log_time_format="[%H:%M:%S]",
-            markup=True
-        )],
+        handlers=handlers,
     )
 
-    if debug:
-        logging.getLogger(__name__).debug("[dim]Debug mode active.[/dim]")
+    if level == logging.DEBUG:
+        logging.getLogger(__name__).debug("[dim]Debug mode active.[/dim]")