Running Paperclip Agents Through Manifest
Wire Manifest in front of opencode_local so every agent shares one auto-routing config — fallbacks across providers, cheap models on simple work, premium on complex. With the working opencode.json, the per-agent adapter_config, the discovery-skip patch, and a production checklist.
Running Paperclip Agents Through Manifest
Manifest is a request-time model router. Instead of pinning each agent to a specific model and tier, you point every agent at a single manifest/... model name and let Manifest classify the request, pick the cheapest capable model from your provider pool, and fall back across providers when one hits a cap. For a Paperclip operator running tens of agents — each previously hand-assigned to a model tier — this collapses three configs (tier-1, tier-2, tier-3 switcher scripts) into one.
This guide walks through wiring Manifest in front of the opencodelocal adapter: the config that goes into opencode.json, the per-agent adapterconfig, the discovery-validation patch you need until upstream PR #4718 lands, and the verification steps before flipping production agents.
> Battle-tested context: the working config below was rolled out across a 45-agent Paperclip instance after three Manifest bugs got fixed in late April 2026 (/v1/responses 404, todowrite case sensitivity, and >12KB system-prompt 400s). If you tried Manifest earlier and gave up, the live API should now handle all three.
---
What you actually gain
| Before | After | |---|---| | Manual tier switchers (switch-provider.sh, switch-model.sh) | One model name across every agent | | Per-agent model assignment by hand | Manifest's classifier picks per request | | Single-provider lock-in — one weekly cap stalls everything | Fallback chain across OpenAI, Anthropic, Z.AI, etc. | | Flat-rate tier costs | Cheap models on simple work, premium only when needed |
The trade-off is that cost becomes harder to reason about: you're now paying per-token for whatever Manifest picks rather than flat-rate for a Z.AI Coding Plan or similar. Watch your first 24 hours of spend before flipping mission-critical agents. And if a specific worker needs a specific model (high-quality copy from Claude, for instance), Manifest's classifier may not consistently pick it — you'll need to configure your provider pool deliberately.
---
The four pieces you need to wire