chore(bridge): bump fc-llm-bridge image tag v202604292028

apps/agent-zero/agent-zero.yaml

@@ -92,16 +92,13 @@ subjects:
 # =============================================================================
 # Agent Zero — AI Agent Web UI (NUC Edition, Blue Jay Profile)
 # =============================================================================
-# Connects directly to fc-llm-bridge for chat + internal util/embed + browser.
+# Connects directly to fc-llm-bridge for chat + util + embeddings + browser.
-# Agent Zero's internal util/embed slots stay on the bridge's OpenAI-compatible
-# /v1 surface, while browser + corpus-search use the Ollama-compatible /api/*
-# surface through OLLAMA_HOST.
 # Blue Jay profile with 21 tools, 3 prompts, 4 extensions.
 
 ---
 # FC LLM Bridge API key for Agent Zero (ADR-088 chat/util/embed/browser routing).
 # Syncs from 1Password item "FC LLM Bridge API Keys" (field: agent-zero-k8s).
-# Consumed by chat, internal util/embed, browser, and corpus-search requests
+# Consumed by chat, util, embeddings, browser, and corpus-search requests
 # that traverse fc-llm-bridge.
 apiVersion: onepassword.com/v1
 kind: OnePasswordItem
@@ -138,7 +135,7 @@ metadata:
   annotations:
     agent-zero/deployment: "nuc"
     agent-zero/profile: "bluejay"
-    agent-zero/ollama: "fc-llm-bridge fronts edge1 Pi 5 + AI HAT+ Ollama for cluster browser/corpus-search traffic; internal chat/util/embed route through the bridge's authenticated OpenAI surface"
+    agent-zero/ollama: "edge1 Pi 5 + AI HAT+ only (10.0.57.17:11434) — workstation Ollama is private dev hardware, not a cluster dependency"
 spec:
   replicas: 1
   selector:
@@ -231,12 +228,11 @@ spec:
               # chat_model: FlowerCore LLM Bridge (ADR-088) — OpenAI-compat,
               # spend-tracked, tier-aliased (fc:balanced → Claude Sonnet).
               # api_key comes from A0_SET_chat_model_api_key env var (overrides
-              # config.json). Utility + embedding stay on the authenticated
+              # config.json). Utility / embedding / browser all point at the
-              # OpenAI-compatible /v1 surface; browser and direct tool traffic
+              # same bridge root and use Ollama-compatible endpoints there.
-              # use the bridge's Ollama-compatible root via OLLAMA_HOST.
               mkdir -p /a0/usr/plugins/_model_config
               cat > /a0/usr/plugins/_model_config/config.json << 'MODELCFG'
-              {"allow_chat_override":true,"chat_model":{"provider":"openai","name":"fc:balanced","api_base":"http://fc-llm-bridge.fc-llm-bridge.svc:8080/v1","ctx_length":8192,"ctx_history":0.7,"vision":false,"kwargs":{"temperature":0,"num_ctx":8192}},"utility_model":{"provider":"openai","name":"fc:cheap","api_base":"http://fc-llm-bridge.fc-llm-bridge.svc:8080/v1","ctx_length":8192,"ctx_input":0.7,"kwargs":{"num_ctx":8192}},"embedding_model":{"provider":"openai","name":"openai/fc:embedding","api_base":"http://fc-llm-bridge.fc-llm-bridge.svc:8080/v1","kwargs":{}}}
+              {"allow_chat_override":true,"chat_model":{"provider":"openai","name":"fc:balanced","api_base":"http://fc-llm-bridge.fc-llm-bridge.svc:8080/v1","ctx_length":8192,"ctx_history":0.7,"vision":false,"kwargs":{"temperature":0,"num_ctx":8192}},"utility_model":{"provider":"ollama","name":"qwen2.5:1.5b","api_base":"http://fc-llm-bridge.fc-llm-bridge.svc:8080","ctx_length":8192,"ctx_input":0.7,"kwargs":{"num_ctx":8192}},"embedding_model":{"provider":"ollama","name":"nomic-embed-text","api_base":"http://fc-llm-bridge.fc-llm-bridge.svc:8080","kwargs":{}}}
               MODELCFG
               # Strip heredoc indentation
               sed -i 's/^              //' /a0/usr/plugins/_model_config/config.json
@@ -260,9 +256,8 @@ spec:
             # Chat model — routed through FlowerCore LLM Bridge (ADR-088)
             # so spend is tracked and tier aliases (fc:cheap/fc:balanced/fc:deep)
             # dispatch to Ollama or Anthropic via a single OpenAI-compat endpoint.
-            # Internal utility + embedding use the authenticated OpenAI surface,
+            # Utility / embedding / browser now traverse fc-llm-bridge too so
-            # while browser/corpus-search use the bridge's Ollama-compatible
+            # Agent Zero no longer needs a local Ollama proxy sidecar.
-            # endpoints so Agent Zero no longer needs a local proxy sidecar.
             - name: A0_SET_chat_model_provider
               value: "openai"
             - name: A0_SET_chat_model_name
@@ -293,24 +288,32 @@ spec:
               value: "8192"
             - name: A0_SET_chat_model_kwargs
               value: '{"temperature": 0, "num_ctx": 8192}'
-            # Utility model — fast small helper tier through the OpenAI surface
+            # Utility model — fast small helper tier through the same proxy
             - name: A0_SET_util_model_provider
-              value: "openai"
+              value: "ollama"
             - name: A0_SET_util_model_name
-              value: "fc:cheap"
+              value: "qwen2.5:1.5b"
             - name: A0_SET_util_model_api_base
-              value: "http://fc-llm-bridge.fc-llm-bridge.svc:8080/v1"
+              value: "http://fc-llm-bridge.fc-llm-bridge.svc:8080"
+            - name: A0_SET_util_model_api_key
+              valueFrom:
+                secretKeyRef:
+                  name: fc-llm-bridge-api-keys
+                  key: agent-zero-k8s
             - name: A0_SET_util_model_kwargs
               value: '{"num_ctx": 2048}'
-            # Embedding model — authenticated bridge alias to nomic-embed-text.
+            # Embedding model — nomic through the same proxy
-            # LiteLLM's embedding() path needs an explicit provider prefix here
-            # even though the chat slot can use bare fc:* aliases.
             - name: A0_SET_embed_model_provider
-              value: "openai"
+              value: "ollama"
             - name: A0_SET_embed_model_name
-              value: "openai/fc:embedding"
+              value: "nomic-embed-text"
             - name: A0_SET_embed_model_api_base
-              value: "http://fc-llm-bridge.fc-llm-bridge.svc:8080/v1"
+              value: "http://fc-llm-bridge.fc-llm-bridge.svc:8080"
+            - name: A0_SET_embed_model_api_key
+              valueFrom:
+                secretKeyRef:
+                  name: fc-llm-bridge-api-keys
+                  key: agent-zero-k8s
             # Browser model — small Gemma candidate through the same proxy
             - name: A0_SET_browser_model_provider
               value: "ollama"