mateo-berri 187cab5049 test(e2e): guard Azure reasoning_effort=none via base_model and xfail the dual token-param bug ... Adds two customer-regression rows to the Azure chat e2e suite. The first sends reasoning_effort=none to a custom-named deployment (gpt-5.6-sol-e2e, swappable via E2E_AZURE_CUSTOM_MODEL) whose capabilities resolve through base_model, asserting the request completes with zero reasoning tokens on a prompt that reasons at default effort, so both a gate 400 (GH #31243, SDK fix in PR #28490) and a silently dropped param fail the row. The second, a strict xfail until GH #31614 is fixed, sends a client max_completion_tokens to a gpt-4o deployment carrying a config-level max_tokens default; the proxy forwards both and Azure rejects the pair		2026-07-16 15:41:00 -07:00
..
access_control	test(e2e): migrate access-control and inference-endpoint regression tests (#32016)	2026-07-05 01:39:10 +00:00
batches	fix(e2e): bound spend-log snapshots to a /spend/logs/v2 window (#33265)	2026-07-14 13:32:10 -07:00
claude_code	test(claude_code): move the Claude Code compatibility matrix under tests/e2e (#32548)	2026-07-14 19:19:03 -07:00
coverage_registry	test(e2e): guard Azure reasoning_effort=none via base_model and xfail the dual token-param bug	2026-07-16 15:41:00 -07:00
llm_translation	test(e2e): guard Azure reasoning_effort=none via base_model and xfail the dual token-param bug	2026-07-16 15:41:00 -07:00
logging	test(e2e): failed request error span carries the full untruncated message and status (LIT-4179) (#33304)	2026-07-14 22:13:13 -07:00
management	test(e2e): cover key rpm/tpm rate limiting, window reset, and pacing headers	2026-07-11 16:15:16 -07:00
quota_management	refactor: make the code easier to read	2026-07-14 13:58:23 -07:00
bob_the_builder.py	test: litellm fix failing tests (#32577)	2026-07-09 13:54:45 -07:00
CLAUDE.md	test(claude_code): move the Claude Code compatibility matrix under tests/e2e (#32548)	2026-07-14 19:19:03 -07:00
conftest.py	refactor(e2e): move budgets and spend_tracking suites under quota_management	2026-07-11 16:14:21 -07:00
CONTRIBUTING.md	ci: gate tests/e2e on zero basedpyright errors in pre-commit and lint CI	2026-07-11 10:25:22 -07:00
docker-compose.yml	test(e2e): guard Azure reasoning_effort=none via base_model and xfail the dual token-param bug	2026-07-16 15:41:00 -07:00
e2e_config.py	test(e2e): guard Azure reasoning_effort=none via base_model and xfail the dual token-param bug	2026-07-16 15:41:00 -07:00
e2e_gateway.py	fix(e2e): bound spend-log snapshots to a /spend/logs/v2 window (#33265)	2026-07-14 13:32:10 -07:00
e2e_http.py	test(e2e): cover /chat/completions on Azure OpenAI, streaming and non-streaming	2026-07-15 16:11:45 -07:00
lifecycle.py	test(e2e): add live batches suite across providers and routing scenarios (#30958)	2026-07-02 08:05:23 -07:00
models.py	test(e2e): guard Azure reasoning_effort=none via base_model and xfail the dual token-param bug	2026-07-16 15:41:00 -07:00
pytest.ini	refactor(e2e): move budgets and spend_tracking suites under quota_management	2026-07-11 16:14:21 -07:00
test_e2e_gateway.py	fix(e2e): bound spend-log snapshots to a /spend/logs/v2 window (#33265)	2026-07-14 13:32:10 -07:00
test_lifecycle.py	test: add e2e tests for spend, budgets and llms (#30869)	2026-06-24 15:01:57 -07:00
test_transport.py	test(e2e): probe the full spend read surface including schema-hidden routes (#32267)	2026-07-06 14:02:05 -07:00
transport.py	test(e2e): probe the full spend read surface including schema-hidden routes (#32267)	2026-07-06 14:02:05 -07:00