What problem does it solve? Setting up Actual Computer (actual.inc) as an inference provider involves two distinct modes (hosted relay and local daemon), device authorization that requires a human in a browser, and several cryptic failure modes like HTTP 400s from reasoning_effort values and empty streams from context-window overflow. This Skill walks through the correct configuration path and documents the known pitfalls. ## Core Features & Use Cases - Relay/API Mode Setup: Configure the hosted end-to-end-encrypted relay at api.actual.inc using an ACTUAL_API_KEY, with model discovery via the /v1/models endpoint. - Local Daemon Mode: Point Indagis at the on-device daemon at 127.0.0.1:8080 with no-auth loopback, including model search, download with explicit quantization, and load by installed name. - Pitfall Troubleshooting: Diagnose reasoning_effort clamping, context-window overflow on small GGUF models, download-id vs installed-name mismatches, and empty-content reasoning models. - Use Case: A user with an ac_ key wants Indagis routed through their Actual cluster; the Skill sets the env var, selects the provider and model, and verifies end-to-end with a hermes chat command. ## Quick Start Ask the agent to set up actual.inc as the Indagis inference provider using your ACTUAL_API_KEY and verify it with a test chat message.
