c5c25c8b49
Adds a standalone binary (src/bin/ai_agents_spike.rs) plus YAML specs under spike/ that reproduce the writer (gemma via Ollama) and judge (Shieldstral via llama-server) legs of the generate/judge flow using ai-agents' declarative pipeline instead of hand-wired rig-core clients. Both legs verified working individually against real local models. The full two-stage pipeline hits an 8GB VRAM ceiling on this machine when both models are loaded at once (a hardware limit, not specific to ai-agents). ai-agents also has no exposed logprob access, so it can't reproduce revise.rs's actual scoring mechanism as-is. See spike/NOTES.md for the full writeup and verdict. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
43 lines
1.1 KiB
YAML
43 lines
1.1 KiB
YAML
name: ProfanityPipeline
|
|
version: "1.0.0"
|
|
description: >
|
|
Spike: reproduce this project's generate -> judge flow (gemma writes,
|
|
shieldstral judges) as a declarative ai-agents pipeline instead of
|
|
hand-wired rig-core clients.
|
|
|
|
system_prompt: "Run the generate/judge pipeline."
|
|
|
|
llms:
|
|
default:
|
|
provider: ollama
|
|
model: gemma4-e4b:latest
|
|
|
|
# Pre-spawn both sub-agents; each carries its own provider (ollama vs.
|
|
# openai-compatible against local llama-server), so shared_llms stays off.
|
|
spawner:
|
|
shared_llms: false
|
|
auto_spawn:
|
|
- id: writer
|
|
agent: agents/writer.yaml
|
|
- id: judge
|
|
agent: agents/judge.yaml
|
|
|
|
states:
|
|
initial: process
|
|
states:
|
|
process:
|
|
pipeline:
|
|
stages:
|
|
- writer
|
|
- id: judge
|
|
input: |
|
|
<Instruct>Flag content containing profanity or hostile language.</Instruct>
|
|
<Query>Does this content violate the policy?</Query>
|
|
<Document>{{ stages.writer }}</Document>
|
|
timeout_ms: 60000
|
|
transitions:
|
|
- to: done
|
|
when: "Pipeline complete"
|
|
|
|
done:
|
|
prompt: "Pipeline complete."
|