From 99a63d5180f7094250ed1d578d0a91c6dca92cdd Mon Sep 17 00:00:00 2001 From: Sameer Kankute Date: Wed, 20 May 2026 22:33:14 +0530 Subject: [PATCH 1/2] feat(gemini): add gemini-3.1-flash-lite model cost map (#28320) * feat(gemini): add gemini-3.1-flash-lite model cost map entries Co-authored-by: Cursor * Update model_prices_and_context_window.json * Update source URL for model pricing information * Sync source URL for gemini-3.1-flash-lite in backup JSON * fix(model_cost_map): add mistral/ministral-8b-2512 entry Mistral rotated the 'mistral/mistral-tiny' alias to return 'ministral-8b-2512' as the response model, which is not in the cost map. This caused test_completion_mistral_api and test_completion_mistral_api_modified_input to fail in completion_cost lookup. Add the entry mirroring the existing openrouter/mistralai/ministral-8b-2512 pricing. * test(cost_calculator): assert output_cost_per_reasoning_token for gemini-3.1-flash-lite * fix(tests): backfill local backup entries into runtime model_cost litellm.model_cost is loaded from LITELLM_MODEL_COST_MAP_URL (pinned to main) at import time, so any pricing entries added to the in-tree backup on this branch aren't visible at test runtime until they also land on main. The Mistral cassette currently returns model=ministral-8b-2512 and the cost-calculator lookup in test_completion_mistral_api / test_completion_mistral_api_modified_input fails despite the entry existing in the local backup. Backfill missing backup entries into litellm.model_cost in the local_testing conftest so these lookups succeed against the cassette state the branch is being tested with. * fix(tests): guard conftest backfill against empty local cost map --------- Co-authored-by: Cursor Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 227 +++++++++++++++++- model_prices_and_context_window.json | 191 +++++++++++++++ tests/local_testing/conftest.py | 14 ++ tests/test_litellm/test_cost_calculator.py | 19 ++ 4 files changed, 450 insertions(+), 1 deletion(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 6d7c3eeb0b8..9ba337da0a5 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -1448,6 +1448,35 @@ "supports_native_structured_output": true, "supports_minimal_reasoning_effort": true }, + "jp.anthropic.claude-sonnet-4-6": { + "cache_creation_input_token_cost": 4.125e-06, + "cache_read_input_token_cost": 3.3e-07, + "input_cost_per_token": 3.3e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_max_reasoning_effort": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346, + "supports_native_structured_output": true, + "supports_minimal_reasoning_effort": true + }, "anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, @@ -9602,6 +9631,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "supports_adaptive_thinking": true, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -9795,6 +9825,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -9828,6 +9859,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -9861,6 +9893,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -9895,6 +9928,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_function_calling": true, @@ -14883,7 +14917,65 @@ "mode": "chat", "output_cost_per_reasoning_token": 1.5e-06, "output_cost_per_token": 1.5e-06, - "source": "https://ai.google.dev/gemini-api/docs/models", + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "supports_service_tier": true + }, + "gemini-3.1-flash-lite": { + "cache_read_input_token_cost": 4.5e-08, + "cache_read_input_token_cost_per_audio_token": 9e-08, + "input_cost_per_audio_token": 9e-07, + "input_cost_per_token": 4.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 2.7e-06, + "output_cost_per_token": 2.7e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -16987,6 +17079,66 @@ "web_search_billing_unit": "per_query", "supports_service_tier": true }, + "gemini/gemini-3.1-flash-lite": { + "cache_read_input_token_cost": 4.5e-08, + "cache_read_input_token_cost_per_audio_token": 9e-08, + "input_cost_per_audio_token": 9e-07, + "input_cost_per_token": 4.5e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 2.7e-06, + "output_cost_per_token": 2.7e-06, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "tpm": 250000, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "supports_service_tier": true + }, "gemini/gemini-3-flash-preview": { "cache_read_input_token_cost": 5e-08, "input_cost_per_audio_token": 1e-06, @@ -24285,6 +24437,21 @@ "supports_tool_choice": true, "supports_vision": true }, + "mistral/ministral-8b-2512": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "mistral/mistral-tiny": { "input_cost_per_token": 2.5e-07, "litellm_provider": "mistral", @@ -33605,6 +33772,64 @@ }, "web_search_billing_unit": "per_query" }, + "vertex_ai/gemini-3.1-flash-lite": { + "cache_read_input_token_cost": 4.5e-08, + "cache_read_input_token_cost_per_audio_token": 9e-08, + "input_cost_per_audio_token": 9e-07, + "input_cost_per_token": 4.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 2.7e-06, + "output_cost_per_token": 2.7e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "supports_service_tier": true + }, "vertex_ai/deep-research-pro-preview-12-2025": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index e7a03bb0984..27d6a59740f 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -14957,6 +14957,64 @@ "web_search_billing_unit": "per_query", "supports_service_tier": true }, + "gemini-3.1-flash-lite": { + "cache_read_input_token_cost": 4.5e-08, + "cache_read_input_token_cost_per_audio_token": 9e-08, + "input_cost_per_audio_token": 9e-07, + "input_cost_per_token": 4.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 2.7e-06, + "output_cost_per_token": 2.7e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "supports_service_tier": true + }, "deep-research-pro-preview-12-2025": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, @@ -17021,6 +17079,66 @@ "web_search_billing_unit": "per_query", "supports_service_tier": true }, + "gemini/gemini-3.1-flash-lite": { + "cache_read_input_token_cost": 4.5e-08, + "cache_read_input_token_cost_per_audio_token": 9e-08, + "input_cost_per_audio_token": 9e-07, + "input_cost_per_token": 4.5e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 2.7e-06, + "output_cost_per_token": 2.7e-06, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "tpm": 250000, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "supports_service_tier": true + }, "gemini/gemini-3-flash-preview": { "cache_read_input_token_cost": 5e-08, "input_cost_per_audio_token": 1e-06, @@ -24319,6 +24437,21 @@ "supports_tool_choice": true, "supports_vision": true }, + "mistral/ministral-8b-2512": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "mistral/mistral-tiny": { "input_cost_per_token": 2.5e-07, "litellm_provider": "mistral", @@ -33639,6 +33772,64 @@ }, "web_search_billing_unit": "per_query" }, + "vertex_ai/gemini-3.1-flash-lite": { + "cache_read_input_token_cost": 4.5e-08, + "cache_read_input_token_cost_per_audio_token": 9e-08, + "input_cost_per_audio_token": 9e-07, + "input_cost_per_token": 4.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 2.7e-06, + "output_cost_per_token": 2.7e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "web_search_billing_unit": "per_query", + "supports_service_tier": true + }, "vertex_ai/deep-research-pro-preview-12-2025": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, diff --git a/tests/local_testing/conftest.py b/tests/local_testing/conftest.py index 6a746041f15..06637b844b1 100644 --- a/tests/local_testing/conftest.py +++ b/tests/local_testing/conftest.py @@ -22,6 +22,20 @@ sys.path.insert( ) # Adds the parent directory to the system path import litellm +# ``litellm.model_cost`` is loaded at import time from the URL pinned to +# ``main`` (``LITELLM_MODEL_COST_MAP_URL``). The in-tree backup ships with +# this branch and can include pricing entries that main has not yet picked +# up (e.g. an upstream provider rotates a model id and the test cassette +# records the new name). Backfill any entries that are missing from the +# remote-fetched map so cost-calculator lookups in tests succeed against +# the cassette state the branch is being tested with. +from litellm.litellm_core_utils.get_model_cost_map import GetModelCostMap + +_local_cost_map = GetModelCostMap.load_local_model_cost_map() +for _k, _v in _local_cost_map.items(): + litellm.model_cost.setdefault(_k, _v) +del _local_cost_map + from tests._vcr_conftest_common import ( # noqa: E402,F401 VerboseReporterState, _pin_multipart_boundary, diff --git a/tests/test_litellm/test_cost_calculator.py b/tests/test_litellm/test_cost_calculator.py index 1be4abbec6e..18ab8a2a07a 100644 --- a/tests/test_litellm/test_cost_calculator.py +++ b/tests/test_litellm/test_cost_calculator.py @@ -2059,6 +2059,25 @@ def test_openrouter_gemini_3_1_flash_lite_preview_pricing(): assert model_info["max_output_tokens"] == 65536 +def test_gemini_3_1_flash_lite_pricing(): + os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True" + litellm.model_cost = litellm.get_model_cost_map(url="") + + for model_name in ( + "gemini-3.1-flash-lite", + "gemini/gemini-3.1-flash-lite", + "vertex_ai/gemini-3.1-flash-lite", + ): + model_info = litellm.model_cost.get(model_name) + assert model_info is not None, f"Missing model pricing entry: {model_name}" + assert model_info["input_cost_per_token"] == 4.5e-07 + assert model_info["input_cost_per_audio_token"] == 9e-07 + assert model_info["output_cost_per_token"] == 2.7e-06 + assert model_info["output_cost_per_reasoning_token"] == 2.7e-06 + assert model_info["cache_read_input_token_cost"] == 4.5e-08 + assert model_info["max_input_tokens"] == 1048576 + + def test_custom_pricing_applies_cache_read_input_cost(): """ Bug 1 reproduction: custom_cost_per_token with cache_read_input_token_cost From 0fb710400f80088fdcc1e382d3efa90a7ec895ea Mon Sep 17 00:00:00 2001 From: milan-berri Date: Wed, 20 May 2026 20:57:08 +0300 Subject: [PATCH 2/2] fix(spend_counter): seed Redis counter via SET NX to prevent cross-pod double-seed (#27854) * fix(spend_counter): seed Redis counter via SET NX to prevent cross-pod double-seed Symptom ------- Customers on multi-pod deployments see team `spend` jump to ~2x (or N x the pod count) shortly after a Redis cache miss / TTL expiry, triggering spurious "Budget Crossed" alerts and blocked requests until the value is manually reset. Root cause ---------- `SpendCounterReseed.coalesced` warmed the primary spend counter by calling `redis.async_increment(key, value=db_spend, refresh_ttl=True)`, which lowers to Redis `INCRBYFLOAT`. That is additive, not idempotent. The per-counter `asyncio.Lock` only coalesces seeders inside one process. With N pods sharing one Redis, on a cold key (cold start, TTL expiry, manual delete) every pod independently passes its lock + Redis re-check, reads the same `db_spend`, and issues `INCRBYFLOAT db_spend`. Final value: N x db_spend. Fix --- Use `redis.async_set_cache(key, value=db_spend, nx=True)` for the seed. SET NX is atomic across pods: exactly one writer initializes the key; losers read the winner's value via `async_get_cache`. This is the same idiom already used by `coalesced_window` in the same file, so the two seed paths are now consistent. Per-request deltas continue to use `INCRBYFLOAT` (correct - additive behaviour is what we want for increments, not for initial seed). Verification ------------ Live two-process repro against the same Postgres + Redis (DB spend = 506): Unpatched: 4/4 runs -> Redis counter = ~1012 (~2 x db_spend) Patched: 12/12 runs -> Redis counter = ~506 Unit tests (`test_proxy_server.py`): - New `test_primary_spend_counter_redis_concurrent_seed_does_not_double_seed` patches `_get_lock` to return a fresh lock per caller (otherwise the per-process lock masks the race), races two `coalesced` calls, and asserts final = 506 with exactly one of two SET NX attempts winning. - 4 existing tests updated for the new seed contract (SET NX for the seed, INCRBYFLOAT only for the per-request delta). - Full `spend_counter or reseed or budget` slice: 22 passed. Co-authored-by: Cursor * test(spend_counter): make SET NX mock atomic so loser branch is exercised Greptile flagged that `redis_set_cache` in test_primary_spend_counter_redis_concurrent_seed_does_not_double_seed placed `await asyncio.sleep(0)` AFTER the NX membership check. Both concurrent tasks observed an empty `redis_store`, passed the guard, and both returned True - so the loser branch (else: read back winner's value) was never exercised. Fix the mock to model real atomic Redis SET NX: - Yield BEFORE the membership check so two concurrent callers interleave the way real SET NX does (first to resume runs check + write atomically and wins; second resumes after the key exists and loses). - Track set_cache return values; assert sorted([loser, winner]) so we know exactly one task wins and one loses. - Track async_get_cache calls that happen AFTER at least one SET NX has completed; assert at least one such read - that is the loser-path fallback (`current_value = float(cached)` when seeded is False). Verified by temporarily reverting the mock to the old order: the test now fails with `expected exactly one SET NX winner and one loser, got [True, True]`, exactly the failure mode Greptile described. No production code change. Co-authored-by: Cursor * test(spend_counter): mock async_set_cache to populate redis_store in concurrent read+write test `test_concurrent_read_and_write_paths_share_one_db_query` mocks `async_increment` to populate the in-memory `redis_store`, but did not mock `async_set_cache`. After the SET-NX seed change in `coalesced()`, the seed step writes via `async_set_cache(nx=True)` (default AsyncMock, no `redis_store` write), so the simulated Redis stays empty after the first reseed. The second `get_current_spend` then sees a clean Redis miss, re-enters the DB read path, and the test fails with `expected 1 DB query, got 2`. Fix: add a `redis_set_cache` side_effect that updates `redis_store` on `nx=True` (and rejects when the key already exists), matching the pattern used by the four sibling tests fixed in this branch's first commit. Pre-existing assertions are unchanged. Full `tests/test_litellm/proxy/test_proxy_server.py`: 158 passed. Co-authored-by: Cursor --------- Co-authored-by: Cursor --- litellm/proxy/db/spend_counter_reseed.py | 27 ++- tests/test_litellm/proxy/test_proxy_server.py | 167 ++++++++++++++++-- 2 files changed, 176 insertions(+), 18 deletions(-) diff --git a/litellm/proxy/db/spend_counter_reseed.py b/litellm/proxy/db/spend_counter_reseed.py index 19ec6699390..e7c5fa3f72c 100644 --- a/litellm/proxy/db/spend_counter_reseed.py +++ b/litellm/proxy/db/spend_counter_reseed.py @@ -178,15 +178,28 @@ class SpendCounterReseed: if db_spend is None: return None # Warm even when 0 so subsequent reads hit cache, not DB. + # + # Seed via SET NX (cross-pod safe): only one pod initializes the + # Redis key with db_spend; concurrent seeders read the winner's + # value. INCRBYFLOAT-of-db_spend from N pods would multiply the + # counter (N x db_spend) and trigger spurious budget alerts. + current_value: float = float(db_spend) try: if spend_counter_cache.redis_cache is not None: - current_value = ( - await spend_counter_cache.redis_cache.async_increment( - key=counter_key, - value=db_spend, - refresh_ttl=True, - ) + seeded = await spend_counter_cache.redis_cache.async_set_cache( + key=counter_key, + value=db_spend, + nx=True, ) + if seeded: + current_value = float(db_spend) + else: + cached = await spend_counter_cache.redis_cache.async_get_cache( + key=counter_key + ) + current_value = ( + float(cached) if cached is not None else float(db_spend) + ) spend_counter_cache.in_memory_cache.set_cache( key=counter_key, value=current_value, @@ -202,7 +215,7 @@ class SpendCounterReseed: ) if require_cache_warm: raise - return db_spend + return current_value @staticmethod async def window_from_spend_logs( diff --git a/tests/test_litellm/proxy/test_proxy_server.py b/tests/test_litellm/proxy/test_proxy_server.py index 6d10d2a6353..ae0996d16d5 100644 --- a/tests/test_litellm/proxy/test_proxy_server.py +++ b/tests/test_litellm/proxy/test_proxy_server.py @@ -5708,6 +5708,7 @@ async def test_init_and_increment_spend_counter_reseeds_from_db_on_counter_miss( fake_redis = AsyncMock() fake_redis.async_increment = AsyncMock(side_effect=record_increment) fake_redis.async_get_cache = AsyncMock(return_value=None) # counter missing + fake_redis.async_set_cache = AsyncMock(return_value=True) # SET NX wins counter_cache.redis_cache = fake_redis # Prisma returns spend=42.0 (authoritative) while the stale cached @@ -5744,16 +5745,131 @@ async def test_init_and_increment_spend_counter_reseeds_from_db_on_counter_miss( fake_prisma.db.litellm_teamtable.find_unique.assert_awaited_once_with( where={"team_id": "team-9"} ) - # Two increments keyed on the counter: seed ($42) then request ($1.50). + # Seed uses SET NX with db_spend (42) — cross-pod safe, no INCR of 42. + # Only the per-request delta (1.5) goes through INCRBYFLOAT. + fake_redis.async_set_cache.assert_awaited_once_with( + key="spend:team:team-9", value=42.0, nx=True + ) writes = [(c["key"], c["value"]) for c in recorded_increments] - assert ("spend:team:team-9", 42.0) in writes - assert ("spend:team:team-9", 1.5) in writes + assert writes == [("spend:team:team-9", 1.5)] finally: ps.user_api_key_cache = orig_user ps.spend_counter_cache = orig_counter ps.prisma_client = orig_prisma +@pytest.mark.asyncio +async def test_primary_spend_counter_redis_concurrent_seed_does_not_double_seed(): + """Two pods both observing a missing Redis counter must not both + INCRBYFLOAT the full DB spend. SpendCounterReseed.coalesced uses SET NX + so the loser reads the winner's value; final Redis = db_spend, not + 2 * db_spend. + + The per-counter asyncio.Lock is per-process, so it does NOT coordinate + across pods. We simulate two pods by patching _get_lock to return a + fresh lock per call (each "pod" has its own lock registry in real life). + """ + from litellm.caching.dual_cache import DualCache + from litellm.proxy.db.spend_counter_reseed import SpendCounterReseed + + counter_key = "spend:team:team-concurrent-seed" + redis_store: dict = {} + db_read_count = 0 + set_results: list = [] + get_after_set_count = 0 + set_completed_count = 0 + + async def redis_set_cache(key, value, nx=False, **_): + # Yield BEFORE the membership check so two concurrent callers + # interleave the way real atomic Redis SET NX does: the first + # to resume runs check + write atomically and wins; the second + # resumes after the key exists and loses. Yielding *after* the + # check would let both callers pass the empty-store check before + # either writes, so neither would ever lose. + await asyncio.sleep(0) + if nx and key in redis_store: + set_results.append(False) + return False + redis_store[key] = float(value) + set_results.append(True) + nonlocal set_completed_count + set_completed_count += 1 + return True + + async def redis_get_cache(key): + # Track reads that happen after at least one SET NX has completed + # — those are the loser-path fallback reads we want to verify. + if set_completed_count > 0: + nonlocal get_after_set_count + get_after_set_count += 1 + return redis_store.get(key) + + fake_redis = AsyncMock() + fake_redis.async_get_cache = AsyncMock(side_effect=redis_get_cache) + fake_redis.async_set_cache = AsyncMock(side_effect=redis_set_cache) + + async def slow_find_unique(**_): + nonlocal db_read_count + db_read_count += 1 + # Both pods read DB before either's SET NX lands. + await asyncio.sleep(0) + row = MagicMock() + row.spend = 506.0 + return row + + fake_prisma = MagicMock() + fake_prisma.db.litellm_teamtable.find_unique = AsyncMock( + side_effect=slow_find_unique + ) + + pod_a = DualCache() + pod_a.redis_cache = fake_redis + pod_b = DualCache() + pod_b.redis_cache = fake_redis + + # Each "pod" has its own per-process lock registry. Patch _get_lock to + # always return a fresh lock so the two coalesced calls do not serialize + # via one in-process lock (which is what would happen across pods). + async def fresh_lock(_counter_key): + return asyncio.Lock() + + with patch.object(SpendCounterReseed, "_get_lock", side_effect=fresh_lock): + results = await asyncio.gather( + SpendCounterReseed.coalesced( + prisma_client=fake_prisma, + spend_counter_cache=pod_a, + counter_key=counter_key, + ), + SpendCounterReseed.coalesced( + prisma_client=fake_prisma, + spend_counter_cache=pod_b, + counter_key=counter_key, + ), + ) + + assert all(r == 506.0 for r in results), results + assert redis_store[counter_key] == pytest.approx(506.0), redis_store + # Both pods read the DB and both attempted SET NX; exactly one wrote + # (winner) and one was rejected (loser). + assert db_read_count == 2 + assert fake_redis.async_set_cache.await_count == 2 + nx_writes = [ + call + for call in fake_redis.async_set_cache.await_args_list + if call.kwargs.get("nx") is True + ] + assert len(nx_writes) == 2 + assert sorted(set_results) == [False, True], ( + f"expected exactly one SET NX winner and one loser, got {set_results}" + ) + # Loser path executed: after the winner's SET NX returned True, the + # losing coalesced() call falls back to async_get_cache to read the + # winner's value rather than re-seeding. + assert get_after_set_count >= 1, ( + "loser branch (else: read back winner's value) was never exercised" + ) + + @pytest.mark.asyncio async def test_reseed_spend_from_db_user_and_org_prefixes(): """User and org counters reseed from their own DB tables. @@ -5877,9 +5993,16 @@ async def test_init_spend_counter_redis_clean_miss_skips_stale_in_memory(): redis_store[key] = (redis_store.get(key) or 0.0) + value return redis_store[key] + async def redis_set_cache(key, value, nx=False, **_): + if nx and key in redis_store: + return False + redis_store[key] = float(value) + return True + fake_redis = AsyncMock() fake_redis.async_get_cache = AsyncMock(return_value=None) fake_redis.async_increment = AsyncMock(side_effect=redis_increment) + fake_redis.async_set_cache = AsyncMock(side_effect=redis_set_cache) counter_cache.redis_cache = fake_redis db_row = MagicMock() @@ -5907,6 +6030,7 @@ async def test_init_spend_counter_redis_clean_miss_skips_stale_in_memory(): fake_prisma.db.litellm_teamtable.find_unique.assert_awaited_once_with( where={"team_id": "team-stale-local"} ) + # Seed via SET NX (42) + delta via INCRBYFLOAT (1.5) = 43.5. assert redis_store[counter_key] == pytest.approx(43.5) assert counter_cache.in_memory_cache.get_cache( key=counter_key @@ -6297,14 +6421,14 @@ async def test_get_current_spend_reseeds_from_db_when_counter_missing(): from litellm.proxy.proxy_server import get_current_spend counter_cache = DualCache() - recorded_warms: list = [] + recorded_seeds: list = [] - async def record_increment(key, value, ttl=None, **kwargs): - recorded_warms.append({"key": key, "value": value}) - return value + async def record_set_cache(key, value, nx=False, **kwargs): + recorded_seeds.append({"key": key, "value": value, "nx": nx}) + return True fake_redis = AsyncMock() - fake_redis.async_increment = AsyncMock(side_effect=record_increment) + fake_redis.async_set_cache = AsyncMock(side_effect=record_set_cache) fake_redis.async_get_cache = AsyncMock(return_value=None) counter_cache.redis_cache = fake_redis @@ -6329,9 +6453,9 @@ async def test_get_current_spend_reseeds_from_db_when_counter_missing(): f"expected DB reseed to return 362.0, got {spend} " f"(fallback would have returned 30.0 and caused bypass)" ) - # Counter warmed so subsequent reads are fast - assert ("spend:team_member:user-1:team-1", 362.0) in [ - (w["key"], w["value"]) for w in recorded_warms + # Counter warmed via SET NX so subsequent reads are fast. + assert ("spend:team_member:user-1:team-1", 362.0, True) in [ + (s["key"], s["value"], s["nx"]) for s in recorded_seeds ] assert counter_cache.in_memory_cache.get_cache( key="spend:team_member:user-1:team-1" @@ -6408,8 +6532,15 @@ async def test_get_current_spend_coalesces_concurrent_reseeds(): redis_store[key] = (redis_store.get(key) or 0.0) + value return redis_store[key] + async def redis_set_cache(key, value, nx=False, **_): + if nx and key in redis_store: + return False + redis_store[key] = float(value) + return True + fake_redis.async_get_cache = AsyncMock(side_effect=redis_get) fake_redis.async_increment = AsyncMock(side_effect=redis_increment) + fake_redis.async_set_cache = AsyncMock(side_effect=redis_set_cache) counter_cache.redis_cache = fake_redis fake_prisma = MagicMock() @@ -6516,9 +6647,16 @@ async def test_concurrent_read_and_write_paths_share_one_db_query(): redis_store[key] = (redis_store.get(key) or 0.0) + value return redis_store[key] + async def redis_set_cache(key, value, nx=False, **_): + if nx and key in redis_store: + return False + redis_store[key] = float(value) + return True + fake_redis = AsyncMock() fake_redis.async_get_cache = AsyncMock(side_effect=redis_get) fake_redis.async_increment = AsyncMock(side_effect=redis_increment) + fake_redis.async_set_cache = AsyncMock(side_effect=redis_set_cache) counter_cache.redis_cache = fake_redis fake_prisma = MagicMock() @@ -6621,9 +6759,16 @@ async def test_reseed_warms_cache_even_on_zero_db_spend(): redis_store[key] = (redis_store.get(key) or 0.0) + value return redis_store[key] + async def redis_set_cache(key, value, nx=False, **_): + if nx and key in redis_store: + return False + redis_store[key] = float(value) + return True + fake_redis = AsyncMock() fake_redis.async_get_cache = AsyncMock(side_effect=redis_get) fake_redis.async_increment = AsyncMock(side_effect=redis_increment) + fake_redis.async_set_cache = AsyncMock(side_effect=redis_set_cache) counter_cache.redis_cache = fake_redis db_call_count = 0