litellm/tests/unit/proxy/common_utils
tavren27 a4de720144
fix(count_tokens): count grok-4-1, grok-4.3 and DeepSeek V4.1 tool requests the way their hosts bill them (#49074)
* fix(count_tokens): count grok-4-1, grok-4.3 and DeepSeek V4.1 tool requests like their chat templates

Render grok-4-1, grok-4.3 and DeepSeek V4.1 tool schemas the way each chat
template does, and add a per-deployment token_count_tool_framing next to
token_count_framing for the hidden tool preamble a host bills. The Azure AI
Foundry grok-4-1, xAI grok-4.3 and Fireworks DeepSeek V4.1 cost map rows carry
the measured framing, overridable in model_info

* fix(count_tokens): count Azure grok-4-1 Responses requests with their own framing and use the tool framing in place of the base framing

* fix(count_tokens): keep operator framing on tool and Responses counts, frame bridged Responses like chat, follow base_model for tool rendering, count grok tool_choice

* fix(token_counter): count Azure Responses strict default, skip false strict and built-in-only tools, per-kind operator framing

* fix(token_counter): count an explicit null strict like false on Azure Responses

* fix(count_tokens): follow the chat completions bridge flag and Azure's strict default on azure/ deployments

Keep Azure grok-4-1 chat tool counts at or over the bill by raising its tool framing to 302

* fix(token_counter): keep strict false for non-grok templates, coerce the bridge flag, frame DeepSeek API counts

* fix(proxy): frame Responses counts for the api_base router defaults send inference to

* fix(proxy): keep the api_base helper's name so main's /v1/messages count caller resolves

---------

Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
2026-11-02 12:37:35 -08:00
..
html_forms test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
__init__.py ci: move tests/proxy_unit_tests to tests/unit/proxy and run the proxy-db shards from litellm-tests (#42903) 2026-09-24 22:59:11 +00:00
test_admin_ui_utils.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_auth_cache_invalidation_pubsub.py fix(scim): write a group's roster in one locked transaction instead of one member at a time (#45197) 2026-10-15 10:57:00 -07:00
test_cache_aware_routing.py refactor(router): route the router family through RoutingContext and close the outside surface (#49118) 2026-10-30 19:18:54 -07:00
test_cache_codec.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_callback_config_validation.py feat(otel): let a team or key excluded_services override the global setting for its OTel v2 destination (#45880) 2026-10-12 19:25:52 -04:00
test_callback_utils.py feat(router): opt in to non-chat deployment filtering (#46257) 2026-10-29 08:33:36 -07:00
test_check_batch_cost.py fix(batches): cost an unmanaged gs:// batch through the deployment that created it (#49301) 2026-10-30 15:25:47 -07:00
test_check_responses_cost.py refactor(router): move router callers onto the entry points and invert the proxy imports (#48847) 2026-10-29 17:26:33 +00:00
test_codex_model_catalog.py feat(lite): offer each model group's reasoning efforts in pi, OpenCode and Codex (#48949) 2026-10-29 18:15:44 -07:00
test_config_sync_pubsub.py fix(proxy): apply new model rows on every worker as soon as they are written (#49034) 2026-10-30 03:19:25 -07:00
test_credential_hydration.py fix(secret_managers)!: resolve oidc/file and oidc/env refs in admin-configured api_key per request (#47341) 2026-10-20 01:43:59 +00:00
test_custom_openapi_spec.py docs(proxy): describe /v1/decisions and /v1/systemone in Swagger UI (#45838) 2026-10-10 21:04:59 +00:00
test_debug_utils.py fix(router): keep the prompt caching affinity pin alive as long as the prefix's cache_control ttl (#46084) 2026-10-14 21:10:09 -07:00
test_discoverable_model_filter.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_encrypt_decrypt_utils.py refactor(proxy): expose public names for private proxy helpers (#45170) 2026-10-07 18:59:27 -07:00
test_error_body_call_id.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_expired_ui_session_key_cleanup_manager.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_get_routes.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_http_parsing_utils.py fix(proxy): abort the request with a 499 when the client disconnects during the body upload (#48640) 2026-10-27 16:49:56 -07:00
test_json_merge_patch.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_key_rotation_e2e.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_key_rotation_integration.py fix(security): remove the publicly known master key from the repo (#44718) 2026-10-06 10:55:24 -07:00
test_key_rotation_lock.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_key_rotation_manager.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_load_config_utils.py fix(security): remove the publicly known master key from the repo (#44718) 2026-10-06 10:55:24 -07:00
test_model_deprecation.py refactor(router): move router callers onto the entry points and invert the proxy imports (#48847) 2026-10-29 17:26:33 +00:00
test_model_listing_utils.py fix(proxy): resolve model aliases to their target deployment for listing metadata (#41041) 2026-10-15 00:38:50 -07:00
test_openai_endpoint_utils.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_openai_error_payload.py fix(proxy)!: label shared-handler errors the way the route catch-alls do (#39555) 2026-10-30 06:58:05 -07:00
test_openapi_route.py fix(proxy): build the OpenAPI schema off the event loop so a cold /openapi.json no longer stalls the worker (#47352) 2026-10-20 04:31:37 +00:00
test_openapi_schema_compat.py fix(proxy): build the OpenAPI schema off the event loop so a cold /openapi.json no longer stalls the worker (#47352) 2026-10-20 04:31:37 +00:00
test_periodic_reload_schedule.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_proxy_encrypt_decrypt.py fix(security): remove the publicly known master key from the repo (#44718) 2026-10-06 10:55:24 -07:00
test_rbac_utils.py refactor(proxy): expose public names for private proxy helpers (#45170) 2026-10-07 18:59:27 -07:00
test_realtime_cache.py fix(proxy): check the model in every OpenAI websocket passthrough frame (#48979) 2026-11-02 09:48:59 -08:00
test_registry_read_through.py fix(proxy): apply new model rows on every worker as soon as they are written (#49034) 2026-10-30 03:19:25 -07:00
test_request_tag_mappings.py feat(proxy): map baggage values to budget tags (#47358) 2026-10-20 09:09:42 +00:00
test_reset_budget_job.py fix(proxy): reconcile team member total_spend with current cycle spend (#48260) 2026-10-24 17:57:09 -07:00
test_resource_ownership.py refactor(core_utils): move resource_ownership out of the proxy (#45805) 2026-10-10 21:02:53 +00:00
test_scheduled_job_stagger.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_semantic_text_index.py fix(mcp): leave out tool texts too long to embed instead of failing tool search (#43554) 2026-10-14 14:53:00 -07:00
test_slow_gc_logger.py test(e2e): event_loop_stalls perf case fails on a gateway event-loop hold over 100 ms that is not on its allowlist (#46974) 2026-10-17 06:55:53 +00:00
test_sse_keepalive.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_static_asset_utils.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_swagger_utils.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_timezone_utils.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_token_count_log.py feat(proxy): log one line per token count call (#47657) 2026-10-28 11:23:52 -07:00
test_token_count_settings.py fix(count_tokens): count grok-4-1, grok-4.3 and DeepSeek V4.1 tool requests the way their hosts bill them (#49074) 2026-11-02 12:37:35 -08:00
test_upsert_budget_membership.py fix(team): keep the team reset schedule when a temp budget increase is set on a member inheriting the team default (#48495) 2026-10-26 17:13:56 -07:00
test_user_api_key_cache.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
test_validation_error_body.py fix(proxy): keep the submitted body out of 422 validation errors (#43231) 2026-09-25 17:05:53 -07:00