chore: initial commit of Go API gateway
Baseline for the Kong replacement on api.riotpiao.com. Brings the working tree under version control for the first time: gateway source, the task board that drives the agent runs, test fixtures, and K8s manifests. Anchor the gateway ignore rule to the repo root. Unanchored, "gateway" also matched the cmd/gateway/ source directory, so the program entrypoint was excluded from every commit. Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
This commit is contained in:
@@ -0,0 +1,38 @@
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: api-gateway-config
|
||||
namespace: api
|
||||
labels:
|
||||
app: api-gateway
|
||||
data:
|
||||
config.yaml: |
|
||||
# Gateway configuration - loaded at startup, never compiled in
|
||||
# See REQUIREMENTS.md for full specification
|
||||
|
||||
# Routes: standard HTTP proxy routes (not LLM-specific)
|
||||
# These are for non-LLM services (agent-pod/console, etc.)
|
||||
routes: []
|
||||
|
||||
# Models: LLM model registry for body-based dispatch
|
||||
# POST /v1/chat/completions routes based on the "model" field in request JSON
|
||||
models:
|
||||
- name: "reasoning"
|
||||
address: "reasoning-predictor.llm-serving:80"
|
||||
path: "/v1/chat/completions"
|
||||
|
||||
- name: "ornith:35b"
|
||||
address: "ornith-predictor.llm-serving:80"
|
||||
path: "/v1/chat/completions"
|
||||
|
||||
- name: "qwen2.5:3b-instruct"
|
||||
address: "ornith-predictor.llm-serving:80"
|
||||
path: "/v1/chat/completions"
|
||||
|
||||
- name: "nomic-ai/nomic-embed-text-v2-moe"
|
||||
address: "embeddings-predictor.llm-serving:80"
|
||||
path: "/v1/embeddings"
|
||||
|
||||
- name: "BAAI/bge-reranker-base"
|
||||
address: "reranker-predictor.llm-serving:80"
|
||||
path: "/v1/rerank"
|
||||
Reference in New Issue
Block a user