No description

Austin Schaefer c5c25c8b49 spike: try ai-agents crate for declarative YAML agent config ... 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>		2026-08-06 09:38:49 +02:00
spike	spike: try ai-agents crate for declarative YAML agent config	2026-08-06 09:38:49 +02:00
src	spike: try ai-agents crate for declarative YAML agent config	2026-08-06 09:38:49 +02:00
.gitignore	feat: Introduce two agent flow with profanity verification.	2026-08-05 14:21:38 +02:00
Cargo.lock	spike: try ai-agents crate for declarative YAML agent config	2026-08-06 09:38:49 +02:00
Cargo.toml	spike: try ai-agents crate for declarative YAML agent config	2026-08-06 09:38:49 +02:00
FINDINGS.md	feat: iterative generate/score/revise loop, findings log	2026-08-05 15:07:42 +02:00