M1 — Headless core loop + Anthropic
Goal
A working headless engine loop against a real provider (Anthropic), with the tool trait,
config loading, and permission service it depends on.
Scope
Tooltrait + config loading/schema- Engine loop: text → tool call → final text, with a doom-loop guard and retry scaffolding
- Permission service (auto-approve stub frontend for headless use)
- read, write, bash, glob, grep tools
- edit tool: opencode's replacer chain ported verbatim, including its test table
- Anthropic SSE codec + provider, registry wiring
harness-appcomposition rootharness run -p "<prompt>"debug command
Acceptance criteria
- Integration test: a scripted
MockProviderdoes text → tool call (read) → final text with
correct parts persisted. harness run -p "<prompt>"works against real Anthropic.
No due date
0% Completed