Verisyntax — User Manual (prototype 0.1)
Optional local AI
The default code-suggestion model is glm-4.7-flash:latest. The model field offers locally tested alternatives and also accepts another installed Ollama model name. Context is 64K by default; 128K is an explicit choice.
Every code suggestion:
- contacts only the displayed loopback Ollama endpoint;
- checks the installed model's reported context capacity;
- receives the versioned, C++-tested Verisyntax syntax reference;
- returns structured JSON;
- is parsed and semantically checked by the authoritative C++ compiler;
- remains unapplied until Replace editor with reviewed draft is explicitly approved.
There is no automatic cloud fallback. Model output never becomes a fact or active rule automatically. extraction_confidence describes extraction/structuring confidence, not the probability that a claim is true.
Imported data to reviewed fact in the standalone IDE
After metadata initialization and an import, select the database and use this exact sequence:
- Configure reviewer stores a project-local identity; it is not read from macOS or sent to a service.
- Load imported cells runs a bounded read-only metadata query.
- Choose one cell and Capture selected mention. The C++ backend binds it through
source_cell -> source_record -> import_run -> source_versionand stores an immutable evidence mention. - Select one or more visible mentions and click Suggest claim locally. The model receives only the selected evidence bundle, must use its mention IDs, and returns schema-validated JSON.
- Edit the JSON, then click Store reviewed proposal. C++ revalidates it and stores an inactive claim version.
- Approve as fact or Reject claim is a separate action with a reason, timestamp, reviewer, version ID, and exact content hash. Approval creates the fact; rejection never does.
The Artifact and Results tabs show the raw receipts and hashes. Editing the .vsx file invalidates the workflow until it is saved again, preventing a decision from being applied to another document snapshot.
