From 87050e72a9c022f957b209dec526121ff2dfe193 Mon Sep 17 00:00:00 2001
From: Andrew Stoltz <andrew@flowercore.io>
Date: Sat, 25 Apr 2026 16:56:39 -0500
Subject: [PATCH] fc-ttsreader: deploy Kokoro to the cluster (replaces
 BLUEJAY-WS host pointer)

The cluster ttsreader-web was reaching across to BLUEJAY-WS:10401 for
Kokoro synthesis, which meant a workstation-down event broke render-
pipeline TTS. Add a cluster-native ttsreader-kokoro Deployment and
Service inside fc-ttsreader so the cluster owns the engine.

- Image: ghcr.io/remsky/kokoro-fastapi-cpu:latest. Model + 67 voices
  ship inside the image, so no PVC is required.
- Port 8880 (the kokoro-fastapi default; the entrypoint hardcodes it).
- Resources: 250m/1Gi request, 2000m/3Gi limit. CPU-only inference
  matches what AiStation runs locally on BLUEJAY-WS.
- dnsPolicy: None to bypass CoreDNS's *.iamworkin.lan template hijack
  on huggingface.co lookups, same shape as ttsreader-align.
- Probes hit /v1/audio/voices since the kokoro server doesn't expose
  /health; that endpoint is cheap (lists configured voice files).

ttsreader-web env var TtsReader__Kokoro__BaseUrl flips from the
workstation pointer to the cluster service:
http://ttsreader-kokoro.fc-ttsreader.svc.cluster.local.:8880.

AiStation keeps its local http://localhost:8880 since the workstation
operator still wants the audio to render on the local sound device
without a network hop.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---
 apps/fc-ttsreader/fc-ttsreader.yaml | 89 ++++++++++++++++++++++++++++-
 1 file changed, 88 insertions(+), 1 deletion(-)

diff --git a/apps/fc-ttsreader/fc-ttsreader.yaml b/apps/fc-ttsreader/fc-ttsreader.yaml
index 8f546eb..ef71c29 100644
--- a/apps/fc-ttsreader/fc-ttsreader.yaml
+++ b/apps/fc-ttsreader/fc-ttsreader.yaml
@@ -229,6 +229,89 @@ spec:
       targetPort: 9200
       name: http
 ---
+# ttsreader-kokoro — Kokoro-82M TTS via the kokoro-fastapi container.
+# Provides high-quality English voices alongside Piper for the TtsReader
+# render pipeline AND for AiStation when it talks to the cluster TTS plane
+# (instead of pointing back at BLUEJAY-WS:10401). Model + voices ship
+# inside the container image, so no PVC is needed.
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: ttsreader-kokoro
+  namespace: fc-ttsreader
+  labels:
+    app.kubernetes.io/name: ttsreader-kokoro
+    app.kubernetes.io/part-of: flowercore
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: ttsreader-kokoro
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: ttsreader-kokoro
+        app.kubernetes.io/part-of: flowercore
+    spec:
+      # Same DNS bypass as ttsreader-align — without it, the *.iamworkin.lan
+      # CoreDNS template would hijack hexgrad/Kokoro-82M's HuggingFace-style
+      # repo lookups during model warmup.
+      dnsPolicy: None
+      dnsConfig:
+        nameservers:
+          - 10.43.0.10
+        searches:
+          - fc-ttsreader.svc.cluster.local
+          - svc.cluster.local
+          - cluster.local
+        options:
+          - name: ndots
+            value: "2"
+      containers:
+        - name: kokoro
+          image: ghcr.io/remsky/kokoro-fastapi-cpu:latest
+          ports:
+            - containerPort: 8880
+              name: http
+          resources:
+            requests:
+              cpu: 250m
+              memory: 1Gi
+            limits:
+              cpu: 2000m
+              memory: 3Gi
+          readinessProbe:
+            httpGet:
+              path: /v1/audio/voices
+              port: 8880
+            initialDelaySeconds: 30
+            periodSeconds: 10
+            timeoutSeconds: 5
+            failureThreshold: 18
+          livenessProbe:
+            httpGet:
+              path: /v1/audio/voices
+              port: 8880
+            initialDelaySeconds: 180
+            periodSeconds: 30
+            timeoutSeconds: 5
+            failureThreshold: 3
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: ttsreader-kokoro
+  namespace: fc-ttsreader
+spec:
+  selector:
+    app.kubernetes.io/name: ttsreader-kokoro
+  ports:
+    - port: 8880
+      targetPort: 8880
+      name: http
+---
 apiVersion: apps/v1
 kind: Deployment
 metadata:
@@ -286,7 +369,11 @@ spec:
             - name: TtsReader__Kokoro__Enabled
               value: "true"
             - name: TtsReader__Kokoro__BaseUrl
-              value: "http://10.0.56.20:10401"
+              # Cluster-native ttsreader-kokoro Service — replaces the prior
+              # BLUEJAY-WS host pointer so the render pipeline doesn't need
+              # the workstation up. AiStation can still hit its local
+              # http://localhost:8880 instance.
+              value: "http://ttsreader-kokoro.fc-ttsreader.svc.cluster.local.:8880"
             - name: TtsReader__Kokoro__TimeoutSeconds
               value: "120"
             - name: Speech__Alignment__Enabled