feat(gateway): dispatch /v1/systemone by model

Browse Source

Clef-flash is a decision model, not a chat model. It serves Clef's own
System One / Jev API at /v1/systemone: a state plus a schema of typed
questions in, one probability per allowed option out, single prefill
pass, no decoding and no free-form text.

Router previously dispatched by body `model` only for
/v1/chat/completions, /v1/embeddings and /v1/rerank. A request to
/v1/systemone therefore fell through to the configured routes, found
none, and answered "no routes configured". Adding the path to the
dispatch predicate is the whole fix: routeByModel already sets
upstreamPath := path, so the upstream receives /v1/systemone unchanged.
There is deliberately no /rerank-style rewrite.

Config: `ornith:35b` is removed with the Ollama predictor, and its GPU
now serves clef-flash. `qwen2.5:3b-instruct` already pointed at qwen-cpu
and is unchanged. Callers of ornith:35b must move to `reasoning`, which
keeps its serving name while running Qwen3-30B-A3B.

Tests cover body dispatch, unknown_model parity with the other three
paths, and that the upstream path is not rewritten.

...

This commit is contained in:

Admin Bot

2026-10-27 23:32:24 -07:00

parent 67fe20d7a3

commit d521d7a48b

3 changed files with 177 additions and 5 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

k8s/gateway-config-secret.yaml

+1 -1

File diff suppressed because one or more lines are too long