You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
feat(loop-init): add orcarouter model provider (#569)
Add OrcaRouter as a selectable model provider for the --with-foundry
implementer stack. Passing --model-provider orcarouter emits a
model/orcarouter provider primitive in .foundry/stack.yaml, mirroring the
existing minimax provider wiring. The primitive carries OrcaRouter's
gateway endpoints (OpenAI- and Anthropic-compatible on the same base URL)
and its routing model options (orcarouter/fusion, fusion-flash, auto,
free).
OrcaRouter is an OpenAI-compatible AI gateway: a single model id routes
across many upstream models with adaptive routing, automatic failover,
and zero-markup inference.
Co-authored-by: dulcestentaciones2920-debug <dulcestentaciones2920-debug@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
Copy file name to clipboardExpand all lines: tools/loop-init/README.md
+6-4Lines changed: 6 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -40,20 +40,22 @@ Every `loop-init` run prints a Foundry CTA; when Loop Ready is **≥ 80**, the C
40
40
41
41
### Interface provider (implementer preset)
42
42
43
-
The `implementer` preset defaults to the built-in interface primitive. Pass `--model-provider minimax` to emit a `model/minimax` provider primitive instead. The generated stack always carries both regional endpoints and both model options, so you can switch region/model without regenerating:
43
+
The `implementer` preset defaults to the built-in interface primitive. Pass `--model-provider minimax` to emit a `model/minimax` provider primitive instead, or `--model-provider orcarouter` to emit a `model/orcarouter` provider primitive. The generated stack always carries the provider endpoints and model options, so you can switch provider/model without regenerating:
MiniMax model options and both endpoints (`global_en` → `https://api.minimax.io`, `cn_zh` → `https://api.minimaxi.com`) are written into `.foundry/stack.yaml`.
58
+
MiniMax model options and both endpoints (`global_en` → `https://api.minimax.io`, `cn_zh` → `https://api.minimaxi.com`) are written into `.foundry/stack.yaml`. The OrcaRouter provider writes the gateway's OpenAI- and Anthropic-compatible endpoints (`https://api.orcarouter.ai`) plus its routing model options (`orcarouter/fusion`, `orcarouter/fusion-flash`, `orcarouter/auto`, `orcarouter/free`).
0 commit comments