feat(filter): ✨ add full glob pattern support for model filtering

Mirrowel · Mirrowel · commit b7df2fec029a · 2025-12-14T18:34:58.000+01:00
This commit upgrades the model filtering system to support complete glob/fnmatch pattern syntax, replacing the previous limited wildcard implementation.

- Migrate from custom prefix-only wildcard matching to full fnmatch support
- Add support for suffix wildcards (*-preview), contains wildcards (*-preview*), single character matching (gpt-?), and character sets (gpt-[45]*)
- Implement cross-platform mouse wheel scrolling with normalized delta calculation for Windows, macOS, and Linux
- Update help documentation with comprehensive pattern examples
- Refactor duplicate model filtering logic in both GUI (FilterEngine) and client (RotatingClient) to use unified fnmatch approach
- Add traceback printing for better debugging of .env save errors
- Fix clipboard copy logic to properly include models without explicit status
- Improve code formatting with consistent line breaks and spacing
- Add pyinstaller to requirements and remove tkinter from build exclusions
- Bump rotator_library version to 1.05 and remove unused dependencies from pyproject.toml

The enhanced pattern matching provides users with significantly more flexibility when defining filter rules, supporting industry-standard glob syntax familiar from shell wildcards.
diff --git a/requirements.txt b/requirements.txt
@@ -22,3 +22,6 @@ rich
 
 # GUI for model filter configuration
 customtkinter
+
+# For building the executable
+pyinstaller
diff --git a/src/proxy_app/build.py b/src/proxy_app/build.py
@@ -3,6 +3,7 @@
 import platform
 import subprocess
 
+
 def get_providers():
     """
     Scans the 'src/rotator_library/providers' directory to find all provider modules.
@@ -24,6 +25,7 @@ def get_providers():
             hidden_imports.append(f"--hidden-import={module_name}")
     return hidden_imports
 
+
 def main():
     """
     Constructs and runs the PyInstaller command to build the executable.
@@ -47,22 +49,27 @@ def main():
         "--collect-data",
         "litellm",
         # Optimization: Exclude unused heavy modules
-        "--exclude-module=tkinter",
         "--exclude-module=matplotlib",
         "--exclude-module=IPython",
         "--exclude-module=jupyter",
         "--exclude-module=notebook",
         "--exclude-module=PIL.ImageTk",
         # Optimization: Enable UPX compression (if available)
-        "--upx-dir=upx" if platform.system() != "Darwin" else "--noupx",  # macOS has issues with UPX
+        "--upx-dir=upx"
+        if platform.system() != "Darwin"
+        else "--noupx",  # macOS has issues with UPX
         # Optimization: Strip debug symbols (smaller binary)
-        "--strip" if platform.system() != "Windows" else "--console",  # Windows gets clean console
+        "--strip"
+        if platform.system() != "Windows"
+        else "--console",  # Windows gets clean console
     ]
 
     # Add hidden imports for providers
     provider_imports = get_providers()
     if not provider_imports:
-        print("Warning: No providers found. The build might not include any LLM providers.")
+        print(
+            "Warning: No providers found. The build might not include any LLM providers."
+        )
     command.extend(provider_imports)
 
     # Add the main script
@@ -80,5 +87,6 @@ def main():
     except FileNotFoundError:
         print("Error: PyInstaller is not installed or not in the system's PATH.")
 
+
 if __name__ == "__main__":
     main()
diff --git a/src/proxy_app/model_filter_gui.py b/src/proxy_app/model_filter_gui.py
@@ -16,9 +16,12 @@
 import customtkinter as ctk
 from tkinter import Menu
 import asyncio
+import fnmatch
+import platform
 import threading
 import os
 import re
+import traceback
 from pathlib import Path
 from dataclasses import dataclass, field
 from typing import List, Dict, Tuple, Optional, Callable, Set
@@ -90,6 +93,34 @@
 FONT_SIZE_HEADER = 20
 
 
+# ════════════════════════════════════════════════════════════════════════════════
+# CROSS-PLATFORM UTILITIES
+# ════════════════════════════════════════════════════════════════════════════════
+
+
+def get_scroll_delta(event) -> int:
+    """
+    Calculate scroll delta in a cross-platform manner.
+
+    On Windows, event.delta is typically ±120 per notch.
+    On macOS, event.delta is typically ±1 per scroll event.
+    On Linux/X11, behavior varies but is usually similar to macOS.
+
+    Returns a normalized scroll direction value (typically ±1).
+    """
+    system = platform.system()
+    if system == "Darwin":  # macOS
+        return -event.delta
+    elif system == "Linux":
+        # Linux with X11 typically uses ±1 like macOS
+        # but some configurations may use larger values
+        if abs(event.delta) >= 120:
+            return -1 * (event.delta // 120)
+        return -event.delta
+    else:  # Windows
+        return -1 * (event.delta // 120)
+
+
 # ════════════════════════════════════════════════════════════════════════════════
 # DATA CLASSES
 # ════════════════════════════════════════════════════════════════════════════════
@@ -254,25 +285,26 @@ def _pattern_matches(self, model_id: str, pattern: str) -> bool:
         """
         Check if a pattern matches a model ID.
 
-        Supports:
+        Supports full glob/fnmatch syntax:
         - Exact match: "gpt-4" matches only "gpt-4"
         - Prefix wildcard: "gpt-4*" matches "gpt-4", "gpt-4-turbo", etc.
+        - Suffix wildcard: "*-preview" matches "gpt-4-preview", "o1-preview", etc.
+        - Contains wildcard: "*-preview*" matches anything containing "-preview"
         - Match all: "*" matches everything
+        - Single char wildcard: "gpt-?" matches "gpt-4", "gpt-5", etc.
+        - Character sets: "gpt-[45]*" matches "gpt-4*", "gpt-5*"
         """
         # Extract model name without provider prefix
         if "/" in model_id:
             provider_model_name = model_id.split("/", 1)[1]
         else:
             provider_model_name = model_id
 
-        if pattern == "*":
-            return True
-        elif pattern.endswith("*"):
-            prefix = pattern[:-1]
-            return provider_model_name.startswith(prefix) or model_id.startswith(prefix)
-        else:
-            # Exact match against full ID or provider model name
-            return model_id == pattern or provider_model_name == pattern
+        # Use fnmatch for full glob pattern support
+        # Match against both the provider model name and the full model ID
+        return fnmatch.fnmatch(provider_model_name, pattern) or fnmatch.fnmatch(
+            model_id, pattern
+        )
 
     def pattern_is_covered_by(self, new_pattern: str, existing_pattern: str) -> bool:
         """
@@ -491,6 +523,7 @@ def save_to_env(self, provider: str) -> bool:
             return True
         except Exception as e:
             print(f"Error saving to .env: {e}")
+            traceback.print_exc()
             return False
 
     def has_unsaved_changes(self) -> bool:
@@ -801,7 +834,9 @@ def _create_content(self):
     def _on_mousewheel(self, event):
         """Handle mouse wheel with faster scrolling."""
         # CTkTextbox uses _textbox internally
-        self.text_box._textbox.yview_scroll(-1 * (event.delta // 40), "units")
+        # Use larger scroll amount (3 units) for faster scrolling in help window
+        delta = get_scroll_delta(event) * 3
+        self.text_box._textbox.yview_scroll(delta, "units")
         return "break"
 
     def _insert_help_content(self):
@@ -838,7 +873,7 @@ def _insert_help_content(self):
             ),
             (
                 "✏️ Pattern Syntax",
-                """Three types of patterns are supported:
+                """Full glob/wildcard patterns are supported:
 
 EXACT MATCH
   Pattern: gpt-4
@@ -847,10 +882,26 @@ def _insert_help_content(self):
 PREFIX WILDCARD  
   Pattern: gpt-4*
   Matches: "gpt-4", "gpt-4-turbo", "gpt-4-preview", etc.
-   
+
+SUFFIX WILDCARD
+  Pattern: *-preview
+  Matches: "gpt-4-preview", "o1-preview", etc.
+
+CONTAINS WILDCARD
+  Pattern: *-preview*
+  Matches: anything containing "-preview"
+
 MATCH ALL
   Pattern: *
-  Matches: every model for this provider""",
+  Matches: every model for this provider
+
+SINGLE CHARACTER
+  Pattern: gpt-?
+  Matches: "gpt-4", "gpt-5", etc. (any single char)
+
+CHARACTER SET
+  Pattern: gpt-[45]*
+  Matches: "gpt-4", "gpt-4-turbo", "gpt-5", etc.""",
             ),
             (
                 "💡 Common Patterns",
@@ -1533,7 +1584,7 @@ def _on_configure(self, event=None):
 
     def _on_mousewheel(self, event):
         """Handle mouse wheel scrolling."""
-        delta = -1 * (event.delta // 120)
+        delta = get_scroll_delta(event)
         self.canvas.yview_scroll(delta, "units")
         self._render()
         return "break"
@@ -1998,16 +2049,12 @@ def _copy_filtered_models(self):
         """Copy filtered/available model names to clipboard (comma-separated)."""
         if not self.models:
             return
-        # Get only models that are not ignored
+        # Get only models that are not ignored (models without status default to available)
         available = [
             self._get_model_display_name(m)
             for m in self.models
-            if self.statuses.get(m) and self.statuses[m].status != "ignored"
+            if self.statuses.get(m) is None or self.statuses[m].status != "ignored"
         ]
-        # Also include models with no status (default to available)
-        for m in self.models:
-            if m not in self.statuses:
-                available.append(self._get_model_display_name(m))
         text = ", ".join(available)
         self.clipboard_clear()
         self.clipboard_append(text)
@@ -2182,7 +2229,7 @@ def _on_configure(self, event=None):
 
     def _on_mousewheel(self, event):
         """Handle mouse wheel scrolling."""
-        delta = -1 * (event.delta // 120)
+        delta = get_scroll_delta(event)
         self.canvas.yview_scroll(delta, "units")
         self._render()
         return "break"
diff --git a/src/rotator_library/client.py b/src/rotator_library/client.py
@@ -1,4 +1,5 @@
 import asyncio
+import fnmatch
 import json
 import re
 import codecs
@@ -274,7 +275,14 @@ def __init__(
     def _is_model_ignored(self, provider: str, model_id: str) -> bool:
         """
         Checks if a model should be ignored based on the ignore list.
-        Supports exact and partial matching for both full model IDs and model names.
+        Supports full glob/fnmatch patterns for both full model IDs and model names.
+
+        Pattern examples:
+        - "gpt-4" - exact match
+        - "gpt-4*" - prefix wildcard (matches gpt-4, gpt-4-turbo, etc.)
+        - "*-preview" - suffix wildcard (matches gpt-4-preview, o1-preview, etc.)
+        - "*-preview*" - contains wildcard (matches anything with -preview)
+        - "*" - match all
         """
         model_provider = model_id.split("/")[0]
         if model_provider not in self.ignore_models:
@@ -291,52 +299,43 @@ def _is_model_ignored(self, provider: str, model_id: str) -> bool:
             provider_model_name = model_id
 
         for ignored_pattern in ignore_list:
-            if ignored_pattern.endswith("*"):
-                match_pattern = ignored_pattern[:-1]
-                # Match wildcard against the provider's model name
-                if provider_model_name.startswith(match_pattern):
-                    return True
-            else:
-                # Exact match against the full proxy ID OR the provider's model name
-                if (
-                    model_id == ignored_pattern
-                    or provider_model_name == ignored_pattern
-                ):
-                    return True
+            # Use fnmatch for full glob pattern support
+            if fnmatch.fnmatch(provider_model_name, ignored_pattern) or fnmatch.fnmatch(
+                model_id, ignored_pattern
+            ):
+                return True
         return False
 
     def _is_model_whitelisted(self, provider: str, model_id: str) -> bool:
         """
         Checks if a model is explicitly whitelisted.
-        Supports exact and partial matching for both full model IDs and model names.
+        Supports full glob/fnmatch patterns for both full model IDs and model names.
+
+        Pattern examples:
+        - "gpt-4" - exact match
+        - "gpt-4*" - prefix wildcard (matches gpt-4, gpt-4-turbo, etc.)
+        - "*-preview" - suffix wildcard (matches gpt-4-preview, o1-preview, etc.)
+        - "*-preview*" - contains wildcard (matches anything with -preview)
+        - "*" - match all
         """
         model_provider = model_id.split("/")[0]
         if model_provider not in self.whitelist_models:
             return False
 
         whitelist = self.whitelist_models[model_provider]
+
+        try:
+            # This is the model name as the provider sees it (e.g., "gpt-4" or "google/gemma-7b")
+            provider_model_name = model_id.split("/", 1)[1]
+        except IndexError:
+            provider_model_name = model_id
+
         for whitelisted_pattern in whitelist:
-            if whitelisted_pattern == "*":
+            # Use fnmatch for full glob pattern support
+            if fnmatch.fnmatch(
+                provider_model_name, whitelisted_pattern
+            ) or fnmatch.fnmatch(model_id, whitelisted_pattern):
                 return True
-
-            try:
-                # This is the model name as the provider sees it (e.g., "gpt-4" or "google/gemma-7b")
-                provider_model_name = model_id.split("/", 1)[1]
-            except IndexError:
-                provider_model_name = model_id
-
-            if whitelisted_pattern.endswith("*"):
-                match_pattern = whitelisted_pattern[:-1]
-                # Match wildcard against the provider's model name
-                if provider_model_name.startswith(match_pattern):
-                    return True
-            else:
-                # Exact match against the full proxy ID OR the provider's model name
-                if (
-                    model_id == whitelisted_pattern
-                    or provider_model_name == whitelisted_pattern
-                ):
-                    return True
         return False
 
     def _sanitize_litellm_log(self, log_data: dict) -> dict:
diff --git a/src/rotator_library/pyproject.toml b/src/rotator_library/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "rotator_library"
-version = "1.0"
+version = "1.05"
 authors = [
     { name="Mirrowel", email="nuh@uh.com" },
 ]
@@ -16,11 +16,7 @@ classifiers = [
     "License :: OSI Approved :: MIT License",
     "Operating System :: OS Independent",
 ]
-dependencies = [
-    "litellm",
-    "filelock",
-    "httpx"
-]
+dependencies = []
 
 [project.urls]
 "Homepage" = "https://github.com/Mirrowel/LLM-API-Key-Proxy"
