The earlier VRAM-exhaustion failure was llama-server defaulting to full
GPU offload for Shieldstral while Ollama's gemma was also resident.
Restarting llama-server with -ngl 0 frees the GPU for gemma and the
full writer->judge ai-agents pipeline runs end to end with no VRAM
contention. Not an ai-agents limitation -- it never touches GPU
placement, only HTTP.
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>
