feat: add DeepSeek extreme reasoning tier

2026-07-26 17:40:51 +08:00
parent ade5ea1210
commit 2e8e81c790
25 changed files with 567 additions and 30 deletions
@@ -34,6 +34,13 @@ Every run records its model tier, strategy version, scheduler version, context
 policy, model/tool events, failures, and completion. This event stream is the
 foundation for replay, evaluation, and future experiment assignment.

+The light, medium, and high tiers use the internal K1412 model endpoint. The
+extreme tier uses DeepSeek V4 Pro with thinking enabled and maximum reasoning
+effort. Provider selection and credentials remain server-side. Thinking state
+is preserved across tool turns because DeepSeek requires the assistant's
+`reasoning_content` to be returned with the following tool results; Work never
+publishes that hidden state as its own user-facing reasoning.
+
 Work completion is evidence-gated. Requests for scripts, reports, code, or
 other concrete artifacts are not accepted as complete until a file mutation
 has succeeded and a later read, diff, or command has verified the latest