Alex 9a69e89096 fix: assistant input content must be output_text, not input_text ...

Live /v1/responses rejects input_text for the assistant role
(input[N].content[0] -> "Supported values are: 'output_text' and
'refusal'"). Revert the previous review-driven change: encode assistant
turns as output_text and user/system turns as input_text. The SDK type
union suggested input_* only, but the API enforces output_text per-role —
confirmed against the live endpoint.

2026-06-03 15:00:14 +01:00

..

handlers

fix: backup model response parsing

2026-06-01 11:30:37 +02:00

__init__.py

chore: more tests

2026-03-30 16:13:08 +01:00

test_anthropic_llm.py

feat: model registry and capabilities for multi-provider support (#2158)

2025-11-14 13:13:19 +02:00

test_anthropic.py

chore: more tests

2026-03-30 16:13:08 +01:00

test_base_llm.py

chore: handlers tests

2026-03-30 12:53:50 +01:00

test_base.py

feat: log gen end

2026-05-31 18:00:51 +02:00

test_fallback.py

fix: backup model response parsing

2026-06-01 11:30:37 +02:00

test_google_ai.py

Deepseek (#2499)

2026-05-25 23:49:25 +01:00

test_google_llm.py

Deepseek (#2499)

2026-05-25 23:49:25 +01:00

test_llama_cpp.py

chore: more tests

2026-03-30 16:13:08 +01:00

test_novita_llm.py

fix: test errors

2026-03-28 13:04:21 +00:00

test_openai_llm.py

feat: stream thinking tokens (#2275)

2026-02-09 13:46:27 +00:00

test_openai_responses.py

fix: assistant input content must be output_text, not input_text

2026-06-03 15:00:14 +01:00

test_openai.py

feat: add OpenAI Responses API support via per-model api_flavor

2026-06-03 13:43:04 +01:00

test_premai.py

chore: more tests

2026-03-30 16:13:08 +01:00

test_sagemaker.py

fix: tests

2024-12-20 18:13:37 +00:00