bluejay/bluejay-infra
1
0
Fork 0
Code Issues Pull Requests 14 Actions Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Andrew Stoltz
2026-04-29 19:14:01 -05:00
parent 1b633f57b2
commit 0d5a1fd530
1 changed files with 24 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
apps/agent-zero/agent-zero.yaml
View File

@@ -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
# Ollama via the 127.0.0.1 sidecar proxy.
# Consumed by the OpenAI-compatible chat / util / embedding lanes. Browser
# 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
# config.json). util + embedding go to local 127.0.0.1 nginx
# proxy which routes to edge1 Pi 5 + AI HAT+ ONLY (workstation
# is private dev hardware, intentionally not in the cluster path).
# api_key comes from OPENAI_API_KEY / A0_SET_chat_model_api_key.
# Utility + embedding now share the same bridge surface so Agent
# Zero stops talking to Ollama directly for those model lanes.
# 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
# for zero-latency, zero-cost small-model traffic.
# Utility + embedding now share the bridge/auth surface too.
# 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"
# Browser model — small Gemma candidate through the same proxy
value: "http://fc-llm-bridge.fc-llm-bridge.svc:8080/v1"
# 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