litellm/tests/integration/compatibility
ryan-crabbe-berri 9a473fbbb0
feat(proxy): give Codex accurate model entries for every model in /v1/models (#49825)
* feat(proxy): give Codex accurate model entries for every model in /v1/models

* fix(router): read a deployment's upstream model without a not-required key access

* fix(proxy): keep Codex tiers for unpriced deployments and match stock entries by declared provider

A deployment with no token price no longer votes a Codex service tier off,
an undescribed model keeps Codex's default reasoning summary parameter,
a Bedrock deployment naming its provider in custom_llm_provider gets Codex's
stock entry, and Bedrock provider namespaces follow the AWS model id format.

* fix(proxy): import cost tracking and provider helpers lazily in the Codex catalog

lite codex imports the catalog before the SDK is initialized, so importing
cost tracking, the Bedrock helpers or provider resolution at module level hit
a circular import and broke every lite command.

* fix(proxy): drop Codex's fast speed tier wherever its priority tier is dropped

Codex shows /fast for a leftover fast speed tier even when service_tiers
no longer offers priority, so an alias, an empty configured tier list or
a configured list without priority showed a /fast toggle that sends nothing.
One helper now sets service tiers, speed tiers and the default together.

* fix(proxy): give an older Codex a translated entry for models past its version

Codex's own entries name the oldest release that can read them in minimal_client_version. A release older than that can fail to decode the entry, such as a reasoning effort it has no name for, which fails the whole catalog, so it now gets the translated entry, whose levels are trimmed to that release
2026-11-05 19:31:32 -08:00
..
_a2a_peers.py fix(a2a): add per-agent a2a_protocol_version override for langgraph-api 0.15 cards (#44463) 2026-10-13 09:04:36 -04:00
_status_code_audit.py test(integration): stop GET /__observations from draining the upstream log (#47256) 2026-10-18 09:58:05 +00:00
test_a2a_protocol_version_bridge.py fix(a2a): add per-agent a2a_protocol_version override for langgraph-api 0.15 cards (#44463) 2026-10-13 09:04:36 -04:00
test_a2a_protocol_version_errors.py fix(a2a): add per-agent a2a_protocol_version override for langgraph-api 0.15 cards (#44463) 2026-10-13 09:04:36 -04:00
test_a2a_protocol_version_override.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_a2a_wire_versions.py test(integration): repair stale contract fixtures (#49700) 2026-11-02 11:23:11 -08:00
test_audio_speech_wire.py test(integration): cover audio endpoint contracts (#44699) 2026-10-14 03:41:20 +00:00
test_audio_transcriptions_wire.py feat(realtime)!: support latest OpenAI audio models (#35600) 2026-11-03 07:27:52 +00:00
test_audio_translations_wire.py test(integration): cover audio endpoint contracts (#44699) 2026-10-14 03:41:20 +00:00
test_codex_model_catalog.py feat(proxy): give Codex accurate model entries for every model in /v1/models (#49825) 2026-11-05 19:31:32 -08:00
test_compressed_request_bodies.py test(proxy): audit #47418 (#48766) 2026-10-28 03:23:34 -07:00
test_embedding_path_aliases.py test(integration): cover embeddings endpoint contracts (#44660) 2026-10-14 03:38:12 +00:00
test_fine_tuning_jobs.py fix(managed_files): send provider file ids when creating a fine-tuning job from managed files (#46552) 2026-10-19 14:40:15 -07:00
test_fine_tuning_managed_files_chaos.py fix(managed_files): send provider file ids when creating a fine-tuning job from managed files (#46552) 2026-10-19 14:40:15 -07:00
test_granian_admission_saturation.py test(integration): hand every harness server a port from one per-worker block (#46761) 2026-10-15 16:56:40 -07:00
test_integration_worker_cleanup.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_missing_body_param_status.py test: fix integration tests that fail on test order, races and intended changes (#49310) 2026-10-30 13:25:47 -07:00
test_openai_consumer.py fix(streaming)!: send the include_usage chunk with an empty choices array (#47109) 2026-10-21 02:26:05 +00:00
test_openai_sdk_client_paths.py fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493) 2026-11-02 14:13:17 -08:00
test_openai_sdk_client_paths_chaos.py test(integration): stop GET /__observations from draining the upstream log (#47256) 2026-10-18 09:58:05 +00:00
test_persisted_toolsets.py test(integration): give each owned proxy a private database and Redis by default (#47213) 2026-10-18 03:37:41 +00:00
test_prompt_management_routes.py test(integration): cover prompts_tags_caching endpoint contracts (#44686) 2026-10-14 04:10:31 +00:00
test_proxy_utils.py test(integration): cover config_utils endpoint contracts (#44737) 2026-10-14 07:00:23 +00:00
test_responses_openapi_schema.py fix(proxy): document request body and response schemas for the Responses API in OpenAPI (#42802) 2026-09-24 01:28:34 +00:00
test_status_code_followups.py test(integration): stop GET /__observations from draining the upstream log (#47256) 2026-10-18 09:58:05 +00:00
test_status_code_followups_chaos.py test(integration): stop GET /__observations from draining the upstream log (#47256) 2026-10-18 09:58:05 +00:00
test_status_code_followups_defaults.py test(integration): stop GET /__observations from draining the upstream log (#47256) 2026-10-18 09:58:05 +00:00
test_status_code_followups_requests.py test(integration): stop GET /__observations from draining the upstream log (#47256) 2026-10-18 09:58:05 +00:00