Conversation
Isolate product code from a future local runtime. Fake load/unload/ generate/cancel/status/health need no model. Failures map to AppError. No Tauri commands, no network, no inference crate.
McanKul
approved these changes
Sep 10, 2026
McanKul
left a comment
McanKul
left a comment
Owner
There was a problem hiding this comment.
Thanks — this keeps the runtime boundary isolated and testable without exposing an unfinished model integration.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds a small Rust
InferenceBackendseam (load/unload/generate/cancel/status/health) plus an in-process deterministic Fake so cancel, fail, and health can be tested without a real model. Product code does not import llama.cpp / candle / ort. No Tauri commands, no network, no model download.Fixes #81.
Why
Parent #76 and epic #80 need a place to plug a local runtime later. This fold is the isolation layer only: Fake is UTF-8 prompt → UTF-8 text;
FAIL/SLOWdriveAI_*andCANCELLED. Model store, Settings UI, and PDF ingest stay out.Validation
cargo test --manifest-path src-tauri/Cargo.toml --lib ai_(11 passed)npm test/npm run typecheck/cargo test --libonepic/local-ai-runtimePrivacy Checklist