bluejay/bluejay-infra
1
0
Fork 0
Code Issues Pull Requests 15 Actions Packages Projects Releases Wiki Activity

agent-zero(models): tool-capable qwen2.5 on GX10 via fc-llm-bridge (Wiring A)

Browse Source 
Agent Zero's agentic tool-loop ran on cloud Anthropic Sonnet (the bridge's
Anthropic key is currently 401) + gemma3:4b util (gemma3 returns 400 "does not
support tools" — fatal for the loop). Repoint the bridge ModelRouter tiers:
Balanced -> Ollama qwen2.5:14b (AZ chat) and Cheap -> qwen2.5:7b (AZ util), both
on the GX10 VIP 10.0.57.201 (already the bridge OllamaBaseUrl). Env-only, no
rebuild; Wiring A keeps the budget ledger + cache. Also: AZ chat ctx -> 32768,
browser -> qwen2.5:7b (text/tool-capable, vision off), AGENT_NAME -> "Blue Jay"
(the NUC role is retired). qwen2.5:7b + :14b pulled + warm-pinned on the GX10.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Andrew Stoltz
2026-06-14 02:38:17 -05:00
parent 9d5a1cce97
commit 0c8e6ee8ab
2 changed files with 19 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
apps/fc-llm-bridge/fc-llm-bridge.yaml
View File

@@ -169,6 +169,21 @@ spec:
value: "http://10.0.57.201:11434"
- name: FlowerCore__Chat__HttpTimeout
value: "00:05:00"
# Tier routing override (Wiring A, 2026-06-14): repoint Agent Zero's
# chat (Balanced) + util (Cheap) tiers to the GX10's tool-capable
# local qwen2.5. Balanced was Anthropic Sonnet (cloud/cost, and the
# Anthropic key is currently 401); Cheap was gemma3:4b which CANNOT
# call tools (400 does not support tools) — fatal for an agentic loop.
# qwen2.5 instruct supports the tool-calling loop; GX10 has the memory.
# OllamaBaseUrl above already points at the GX10 VIP (10.0.57.201).
- name: FlowerCore__Chat__ModelRouter__DefaultRoutes__Balanced__Provider
value: "Ollama"
- name: FlowerCore__Chat__ModelRouter__DefaultRoutes__Balanced__Model
value: "qwen2.5:14b"
- name: FlowerCore__Chat__ModelRouter__DefaultRoutes__Cheap__Provider
value: "Ollama"
- name: FlowerCore__Chat__ModelRouter__DefaultRoutes__Cheap__Model
value: "qwen2.5:7b"
# Shared.Chat — Anthropic
- name: FlowerCore__Chat__Anthropic__Enabled
value: "true"