NCBM 0da6e8da8d lmproto: give every DeepSeek assistant round its reasoning field ...

Thinking mode checks the field per round, not per call: an answer whose message
carried no `reasoning_content` came back 400 with the wording a call gets ("the
`reasoning_content` … must be passed back to the API"), while an empty string
satisfies the check. The injection now touches every assistant message instead
of only the ones carrying `tool_calls`.

2026-10-06 23:23:24 +08:00

..

test_anthropic.py

test/lmproto: cover anthropic messages client HTTP round-trips

2026-08-01 00:41:59 +08:00

test_chat_compat.py

core/lmproto: coerce developer role for chat completions

2026-07-28 22:16:36 +08:00

test_deepseek_anthropic.py

config: rename the DeepSeek flash model to deepseek-flash

2026-10-06 21:22:35 +08:00

test_deepseek_chat.py

lmproto: give every DeepSeek assistant round its reasoning field

2026-10-06 23:23:24 +08:00

test_deepseek_responses.py

config: rename the DeepSeek flash model to deepseek-flash

2026-10-06 21:22:35 +08:00

test_models.py

ci/lint: apply ruff format and import sort fixes

2026-07-15 22:09:52 +08:00

test_responses.py

ci/lint: apply ruff format and import sort fixes

2026-07-15 22:09:52 +08:00

test_sse_parse.py

core/lmproto: allow null logprobs and usage on stream chunks

2026-07-15 14:23:23 +08:00