feat: add DeepSeek extreme reasoning tier

This commit is contained in:
wuyang
2026-07-26 17:40:51 +08:00
parent ade5ea1210
commit 2e8e81c790
25 changed files with 567 additions and 30 deletions
+7
View File
@@ -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
+5
View File
@@ -39,6 +39,11 @@ listed above. `https://api.k1412.top` remains the external API entrypoint, but
Runtime must not send long-running Agent inference through the public reverse
proxy.
Set `DEEPSEEK_API_BASE_URL=https://api.deepseek.com` and place
`DEEPSEEK_API_KEY` only in the protected deployment `.env`. The key is used
only by Runtime for the extreme tier and must never be added to a browser,
Compose file, image, repository, or log.
The SSH override removes `/var/run/docker.sock` from Gateway and mounts the
dedicated SSH directory read-only at `/root/.ssh`.