apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization
# Explicit allowlist, matching k8s/apps/api. Anything added to this directory
# and not listed here is silently dropped — no error, no drift shown.
#
# These five were adopted from live state on 2026-08-15; they had been applied
# by hand and carried no ArgoCD ownership. Each was exported and verified with
# `kubectl diff -f <file>` returning empty before the Application below was
# created, so the first sync was a no-op rather than a redeploy. Re-verify that
# way after any edit here: a GPU predictor restart is a weights reload measured
# in tens of seconds, not a rolling update.
resources:
  # clef-flash runs through clef-serve.yaml, not through an SGLang runtime. SGLang needs
  # v0.5.22+, published only on CUDA 13, and CUDA 13 dropped Volta kernels. The model
  # instead runs the implementation it ships (joint_schema_model.py) in fp16 on one V100.
  # coder-14b-fp16.yaml owns the `candle-vllm` Deployment name and the
  # `app: candle-vllm` label that coder-service.yaml selects. It must be the only
  # workload with that label, or the Service splits traffic across two models.
  #
  # fp16 on two V100s, not GPTQ on one: measured 39.7 ms ITL and 287 tok/s at 16
  # streams against 71.5 ms and 215 tok/s for the 4-bit MoE. The V100 has FP16
  # tensor cores and no INT4 ones, so 4-bit pays dequantisation on the SM while
  # the memory controller idles at 19%.
  - coder-14b-fp16.yaml
  - clef-serve.yaml
  # Stable client-facing name for the chat model. poimen-memory points at this Service,
  # so the vLLM -> candle-vllm handoff is a selector edit here and no client change.
  - coder-service.yaml
  - reasoning-long-service.yaml
  # ornith is retired: its InferenceService still reports Ready=True while running zero
  # replicas, because desired equals available at 0. Its manifest was never committed,
  # so it is left unmanaged and is not listed here. Delete the CR when convenient.
  - embeddings.yaml
  - reranker.yaml
  - qwen-cpu.yaml
  - networkpolicy.yaml
# No namespace transformer: every file sets its own, and the transformer would
# rewrite metadata.namespace on anything cross-namespace added later.

# app.py lives in git next to this file. The generator hashes the ConfigMap name, so an
# edit to app.py rolls the pod instead of leaving a stale copy mounted.
configMapGenerator:
  - name: clef-serve-app
    namespace: llm-serving
    files:
      - clef-serve/app.py
    options:
      disableNameSuffixHash: false