fix(agent-zero): route util and embed through llm bridge

apps/agent-zero/agent-zero.yaml

@@ -92,14 +92,16 @@ subjects:
 # =============================================================================
 # Agent Zero — AI Agent Web UI (NUC Edition, Blue Jay Profile)
 # =============================================================================
-# Connects to a local nginx proxy that routes to edge1 Pi 5 + AI HAT+ Ollama only
+# Chat / utility / embedding lanes route through fc-llm-bridge. Browser keeps
+# a local nginx proxy to edge1 Pi 5 + AI HAT+ until the bridge grows a live
+# Vision route and the in-pod tools stop calling Ollama directly.
 # Blue Jay profile with 21 tools, 3 prompts, 4 extensions
 
 ---
-# FC LLM Bridge API key for Agent Zero (ADR-088 chat_model routing).
+# FC LLM Bridge API key for Agent Zero (ADR-088 chat / util / embed routing).
 # Syncs from 1Password item "FC LLM Bridge API Keys" (field: agent-zero-k8s).
-# Consumed by the chat_model only; util / embedding / browser stay on local
+# Consumed by the OpenAI-compatible chat / util / embedding lanes. Browser
-# Ollama via the 127.0.0.1 sidecar proxy.
+# stays on the local Ollama sidecar until fc:vision is configured on the bridge.
 apiVersion: onepassword.com/v1
 kind: OnePasswordItem
 metadata:
@@ -295,13 +297,14 @@ spec:
               # The _model_config plugin reads config.json (NOT config.yaml).
               # 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
+              # api_key comes from OPENAI_API_KEY / A0_SET_chat_model_api_key.
-              # config.json). util + embedding go to local 127.0.0.1 nginx
+              # Utility + embedding now share the same bridge surface so Agent
-              # proxy which routes to edge1 Pi 5 + AI HAT+ ONLY (workstation
+              # Zero stops talking to Ollama directly for those model lanes.
-              # is private dev hardware, intentionally not in the cluster path).
+              # Browser stays on the local 127.0.0.1 proxy until the bridge has
+              # a live Vision route and the in-pod tools stop calling Ollama.
               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":"ollama","name":"qwen2.5:1.5b","api_base":"http://127.0.0.1:11434","ctx_length":8192,"ctx_input":0.7,"kwargs":{"num_ctx":8192}},"embedding_model":{"provider":"ollama","name":"nomic-embed-text","api_base":"http://127.0.0.1:11434","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":"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":"fc:embedding","api_base":"http://fc-llm-bridge.fc-llm-bridge.svc:8080/v1","kwargs":{}}}
               MODELCFG
               # Strip heredoc indentation
               sed -i 's/^              //' /a0/usr/plugins/_model_config/config.json
@@ -325,8 +328,9 @@ 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.
-            # Util / embedding / browser stay on local Ollama via 127.0.0.1 proxy
+            # Utility + embedding now share the bridge/auth surface too.
-            # for zero-latency, zero-cost small-model traffic.
+            # Browser stays on local Ollama until the bridge has a live
+            # Vision route and the in-pod tools stop calling Ollama directly.
             - name: A0_SET_chat_model_provider
               value: "openai"
             - name: A0_SET_chat_model_name
@@ -354,21 +358,22 @@ spec:
               value: '{"temperature": 0, "num_ctx": 8192}'
             # Utility model — fast small helper tier through the same proxy
             - name: A0_SET_util_model_provider
-              value: "ollama"
+              value: "openai"
             - name: A0_SET_util_model_name
-              value: "qwen2.5:1.5b"
+              value: "fc:cheap"
             - name: A0_SET_util_model_api_base
-              value: "http://127.0.0.1:11434"
+              value: "http://fc-llm-bridge.fc-llm-bridge.svc:8080/v1"
             - name: A0_SET_util_model_kwargs
               value: '{"num_ctx": 2048}'
-            # Embedding model — nomic through the same proxy
+            # Embedding model — bridge alias to nomic-embed-text on edge1
             - name: A0_SET_embed_model_provider
-              value: "ollama"
+              value: "openai"
             - name: A0_SET_embed_model_name
-              value: "nomic-embed-text"
+              value: "fc:embedding"
             - name: A0_SET_embed_model_api_base
-              value: "http://127.0.0.1:11434"
+              value: "http://fc-llm-bridge.fc-llm-bridge.svc:8080/v1"
-            # Browser model — small Gemma candidate through the same proxy
+            # Browser model — small Gemma candidate stays on the local proxy
+            # until fc:vision is configured on the bridge.
             - name: A0_SET_browser_model_provider
               value: "ollama"
             - name: A0_SET_browser_model_name