Michelangelo Setaro c288dc7da0 fix(router): let an exact base_model widen a deployment's context window (#46197) ... * fix(router): honor explicit bedrock base model capacity * fix(router): honor an exact base_model's capacity for every non-Azure provider Extends the Bedrock-only check to every non-Azure provider and only uses the base_model when it has its own exact cost-map entry, so an unmapped or wildcard base_model falls back to the route id instead of raising in the router. * test(router): call _maps_to_exact_model_info directly in its cost-map tests * fix(router): let an exact base_model only widen a deployment's context window A base_model used as a pricing stand-in with a smaller window no longer narrows the route's limit, and a route with no window never takes one from base_model * test(router): count the base_model window helpers as covered through get_router_model_info * fix(router): widen only from a model_info base_model naming the same model A stand-in base_model for a different, larger model widened a smaller deployment's window, so pre-call checks sent it prompts the provider rejects with 400. The window now widens only when model_info.base_model names the same provider model id as the route, which is also the field /model/info reads. * fix(router): match a base_model's model id across Bedrock region prefixes and @ qualifiers * fix(router): read litellm_params.base_model too and look the base row up as written * test(router): cover a same-model base_model window on chat, messages, responses, and complexity escalation --------- Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>		2026-10-16 06:37:40 +00:00
..
_prompt_cache_pin_support.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
either_role.json	test(integration): add read-replica routing harness to the CircleCI integration suite (#42692)	2026-09-24 00:25:03 -07:00
test_advisor_failure_cooldown.py	test(integration): regression tests for July provider translation, routing and streaming bugs (#42693)	2026-09-23 09:51:06 -07:00
test_audit_any_sweep_chaos.py	test(integration): give chaos and timing tests a harness API and gate raw signals (#46031)	2026-10-12 05:27:33 -07:00
test_auto_router_management.py	test(integration): wait on the right signal in five flaky integration contracts (#46737)	2026-10-15 13:48:51 -07:00
test_azure_passthrough_spend_row.py	fix(vllm): write spend log rows for /vllm passthrough calls to router models (#45733)	2026-10-14 12:40:48 -07:00
test_base_model_context_window_owned_proxy.py	fix(router): let an exact base_model widen a deployment's context window (#46197)	2026-10-16 06:37:40 +00:00
test_complexity_router_databricks_classifier.py	test(integration): give chaos and timing tests a harness API and gate raw signals (#46031)	2026-10-12 05:27:33 -07:00
test_complexity_router_llm_classifier.py	refactor(types): replace Any with proven types in 7 files (#43844)	2026-10-02 02:47:47 -07:00
test_declared_provider_bare_model_routes.py	test(integration): hand every harness server a port from one per-worker block (#46761)	2026-10-15 16:56:40 -07:00
test_deployment_num_retries_generic_routes_wire.py	fix(router): retry a /v1/messages stream the provider drops before the first content chunk (#44276)	2026-10-05 22:53:39 +00:00
test_encrypted_content_affinity_no_peer.py	fix(router): serve Responses turns from a sibling when the encrypted content origin has no boundary peer (#43015)	2026-09-24 17:31:43 -07:00
test_end_user_region_routing.py	test(integration): move legacy proxy, router and Redis tests into tests/integration (#44128)	2026-10-01 23:00:54 -07:00
test_fallback_hop_foreign_encrypted_reasoning.py	test(integration): hand every harness server a port from one per-worker block (#46761)	2026-10-15 16:56:40 -07:00
test_fallback_retry_header_contracts.py	test: move 76 live top-level tests to offline unit and integration coverage (#45352)	2026-10-08 10:33:35 -07:00
test_include_fallback_errors_wire.py	fix(router): keep include_fallback_errors off the provider call on the sync Router path (#45218)	2026-10-07 22:25:12 -07:00
test_key_max_parallel_requests.py	test(integration): move legacy proxy, router and Redis tests into tests/integration (#44128)	2026-10-01 23:00:54 -07:00
test_key_tpm_reservation.py	test(integration): regression tests for July provider translation, routing and streaming bugs (#42693)	2026-09-23 09:51:06 -07:00
test_messages_stream_retry_budget_sources_owned_proxy.py	fix(router): retry a /v1/messages stream the provider drops before the first content chunk (#44276)	2026-10-05 22:53:39 +00:00
test_model_capability_flags.py	fix: keep model capability flags out of provider requests (#46647)	2026-10-15 14:30:10 +00:00
test_observed_routing.py	test(integration): cover health_routing endpoint contracts (#44744)	2026-10-14 06:34:22 +00:00
test_payment_required_cooldown.py	test(integration): give chaos and timing tests a harness API and gate raw signals (#46031)	2026-10-12 05:27:33 -07:00
test_payment_required_mapping.py	fix(exceptions): map upstream 402 to PaymentRequiredError and cool down 402 deployments (#44879)	2026-10-06 20:35:13 -07:00
test_pdf_document_pre_call_checks_owned_proxy.py	test(integration): remove six setup causes of CircleCI integration reds (#46490)	2026-10-14 12:00:35 -07:00
test_per_model_rate_limit_fallbacks.py	test(integration): give chaos and timing tests a harness API and gate raw signals (#46031)	2026-10-12 05:27:33 -07:00
test_per_model_rate_limit_fallbacks_lifecycle.py	test(integration): give chaos and timing tests a harness API and gate raw signals (#46031)	2026-10-12 05:27:33 -07:00
test_priority_model_tpm_enforcement.py	test(integration): regression tests for July provider translation, routing and streaming bugs (#42693)	2026-09-23 09:51:06 -07:00
test_priority_rate_limit_headers.py	chore(lint): remove the LIT002 mutable-construction rule (#43971)	2026-10-01 12:24:02 -07:00
test_priority_scheduler_queue_cleanup.py	test(integration): remove six setup causes of CircleCI integration reds (#46490)	2026-10-14 12:00:35 -07:00
test_prompt_cache_pin_memory_routes.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_prompt_cache_pin_ttl.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_prompt_cache_pin_ttl_chaos.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_prompt_caching_affinity_tool_call_marks.py	fix(caching): count tool_call cache_control marks in the injection census (#43556)	2026-10-03 17:33:48 -07:00
test_ptu_shares.py	feat(proxy): split Azure PTU deployments across teams with per-team PTU ceilings and PTU-hour reporting (#43043)	2026-10-15 18:44:30 +00:00
test_ptu_shares_regex_timing.py	feat(proxy): split Azure PTU deployments across teams with per-team PTU ceilings and PTU-hour reporting (#43043)	2026-10-15 18:44:30 +00:00
test_redis_increment_with_floor.py	ci(circleci): test Redis behavior against local Redis and print short tracebacks (#44062)	2026-10-01 13:00:54 -07:00
test_redis_recovery.py	test(integration): add read-replica routing harness to the CircleCI integration suite (#42692)	2026-09-24 00:25:03 -07:00
test_stale_cost_map_boot.py	fix(caching): key response cache by router model group in litellm_metadata (#44542)	2026-10-05 17:06:21 +00:00
test_team_tag_routing.py	test(integration): move legacy proxy, router and Redis tests into tests/integration (#44128)	2026-10-01 23:00:54 -07:00
test_usage_based_routing_redis_reads.py	test: fix stale and flaky tests across CircleCI, GHA and Buildkite (#45530)	2026-10-09 11:40:14 -07:00
test_user_config_routing.py	test: take keys out of the legacy proxy, enterprise and mcp unit tests before moving them (#42901)	2026-09-24 14:56:52 -07:00
test_video_poll_routing_wire.py	feat(dashscope): add Wan 3.0, Wan 2.7 and HappyHorse video generation via /v1/videos (#43706)	2026-10-14 10:10:07 -07:00
test_vllm_passthrough_spend_row.py	fix(vllm): write spend log rows for /vllm passthrough calls to router models (#45733)	2026-10-14 12:40:48 -07:00
test_vllm_passthrough_stream_relay.py	fix(vllm): write spend log rows for /vllm passthrough calls to router models (#45733)	2026-10-14 12:40:48 -07:00
test_vllm_passthrough_stream_usage_settings.py	fix(vllm): write spend log rows for /vllm passthrough calls to router models (#45733)	2026-10-14 12:40:48 -07:00