Squashed commit of the following: (#9709)

commit b12a9892b7
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Wed Apr 2 08:09:56 2025 -0700

    fix(utils.py): don't modify openai_token_counter

commit 294de31803
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 21:22:40 2025 -0700

    fix: fix linting error

commit cb6e9fbe40
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 19:52:45 2025 -0700

    refactor: complete migration

commit bfc159172d
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 19:09:59 2025 -0700

    refactor: refactor more constants

commit 43ffb6a558
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:45:24 2025 -0700

    fix: test

commit 04dbe4310c
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:28:58 2025 -0700

    refactor: refactor: move more constants into constants.py

commit 3c26284aff
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:14:46 2025 -0700

    refactor: migrate hardcoded constants out of __init__.py

commit c11e0de69d
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:11:21 2025 -0700

    build: migrate all constants into constants.py

commit 7882bdc787
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:07:37 2025 -0700

    build: initial test banning hardcoded numbers in repo

litellm/litellm_core_utils/get_llm_provider_logic.py

@@ -3,6 +3,7 @@ from typing import Optional, Tuple
 import httpx
 
 import litellm
+from litellm.constants import REPLICATE_MODEL_NAME_WITH_ID_LENGTH
 from litellm.secret_managers.main import get_secret, get_secret_str
 
 from ..types.router import LiteLLM_Params
@@ -256,10 +257,13 @@ def get_llm_provider(  # noqa: PLR0915
         elif model in litellm.cohere_chat_models:
             custom_llm_provider = "cohere_chat"
         ## replicate
-        elif model in litellm.replicate_models or (":" in model and len(model) > 64):
+        elif model in litellm.replicate_models or (
+            ":" in model and len(model) > REPLICATE_MODEL_NAME_WITH_ID_LENGTH
+        ):
             model_parts = model.split(":")
             if (
-                len(model_parts) > 1 and len(model_parts[1]) == 64
+                len(model_parts) > 1
+                and len(model_parts[1]) == REPLICATE_MODEL_NAME_WITH_ID_LENGTH
             ):  ## checks if model name has a 64 digit code - e.g. "meta/llama-2-70b-chat:02e509c789964a7ea8736978a43525956ef40397be9033abf9fd2badfe68c9e3"
                 custom_llm_provider = "replicate"
             elif model in litellm.replicate_models:

litellm/litellm_core_utils/litellm_logging.py

@@ -28,6 +28,10 @@ from litellm._logging import _is_debugging_on, verbose_logger
 from litellm.batches.batch_utils import _handle_completed_batch
 from litellm.caching.caching import DualCache, InMemoryCache
 from litellm.caching.caching_handler import LLMCachingHandler
+from litellm.constants import (
+    DEFAULT_MOCK_RESPONSE_COMPLETION_TOKEN_COUNT,
+    DEFAULT_MOCK_RESPONSE_PROMPT_TOKEN_COUNT,
+)
 from litellm.cost_calculator import _select_model_name_for_cost_calc
 from litellm.integrations.arize.arize import ArizeLogger
 from litellm.integrations.custom_guardrail import CustomGuardrail
@@ -3745,9 +3749,12 @@ def create_dummy_standard_logging_payload() -> StandardLoggingPayload:
         response_cost=response_cost,
         response_cost_failure_debug_info=None,
         status=str("success"),
-        total_tokens=int(30),
-        prompt_tokens=int(20),
-        completion_tokens=int(10),
+        total_tokens=int(
+            DEFAULT_MOCK_RESPONSE_PROMPT_TOKEN_COUNT
+            + DEFAULT_MOCK_RESPONSE_COMPLETION_TOKEN_COUNT
+        ),
+        prompt_tokens=int(DEFAULT_MOCK_RESPONSE_PROMPT_TOKEN_COUNT),
+        completion_tokens=int(DEFAULT_MOCK_RESPONSE_COMPLETION_TOKEN_COUNT),
         startTime=start_time,
         endTime=end_time,
         completionStartTime=completion_start_time,

litellm/litellm_core_utils/llm_cost_calc/tool_call_cost_tracking.py

@@ -5,6 +5,7 @@ Helper utilities for tracking the cost of built-in tools.
 from typing import Any, Dict, List, Optional
 
 import litellm
+from litellm.constants import OPENAI_FILE_SEARCH_COST_PER_1K_CALLS
 from litellm.types.llms.openai import FileSearchTool, WebSearchOptions
 from litellm.types.utils import (
     ModelInfo,
@@ -132,7 +133,7 @@ class StandardBuiltInToolCostTracking:
         """
         if file_search is None:
             return 0.0
-        return 2.5 / 1000
+        return OPENAI_FILE_SEARCH_COST_PER_1K_CALLS
 
     @staticmethod
     def chat_completion_response_includes_annotations(

litellm/litellm_core_utils/token_counter.py

@@ -11,6 +11,10 @@ from litellm.constants import (
     DEFAULT_IMAGE_HEIGHT,
     DEFAULT_IMAGE_TOKEN_COUNT,
     DEFAULT_IMAGE_WIDTH,
+    MAX_LONG_SIDE_FOR_IMAGE_HIGH_RES,
+    MAX_SHORT_SIDE_FOR_IMAGE_HIGH_RES,
+    MAX_TILE_HEIGHT,
+    MAX_TILE_WIDTH,
 )
 from litellm.llms.custom_httpx.http_handler import _get_httpx_client
 
@@ -97,11 +101,14 @@ def resize_image_high_res(
     height: int,
 ) -> Tuple[int, int]:
     # Maximum dimensions for high res mode
-    max_short_side = 768
-    max_long_side = 2000
+    max_short_side = MAX_SHORT_SIDE_FOR_IMAGE_HIGH_RES
+    max_long_side = MAX_LONG_SIDE_FOR_IMAGE_HIGH_RES
 
     # Return early if no resizing is needed
-    if width <= 768 and height <= 768:
+    if (
+        width <= MAX_SHORT_SIDE_FOR_IMAGE_HIGH_RES
+        and height <= MAX_SHORT_SIDE_FOR_IMAGE_HIGH_RES
+    ):
         return width, height
 
     # Determine the longer and shorter sides
@@ -132,7 +139,10 @@ def resize_image_high_res(
 
 # Test the function with the given example
 def calculate_tiles_needed(
-    resized_width, resized_height, tile_width=512, tile_height=512
+    resized_width,
+    resized_height,
+    tile_width=MAX_TILE_WIDTH,
+    tile_height=MAX_TILE_HEIGHT,
 ):
     tiles_across = (resized_width + tile_width - 1) // tile_width
     tiles_down = (resized_height + tile_height - 1) // tile_height