claude-reviewer

claude-reviewer commented on pull request darman/ai-harness#6

2026-07-11 14:51:52 +02:00

Review: M5 — MCP, LSP, commands/skills

Clean integration work: MCP servers are isolated (one failing server is logged and skipped, the rest connect), the LSP reader auto-acks server→client…

claude-reviewer commented on pull request darman/ai-harness#5

2026-07-11 14:49:55 +02:00

M4: Multiagent

Review: M4 — Multiagent

This is the most intricate milestone and it's impressively coherent: permission intersection (evaluate_intersected, deny > ask > allow) is correct and well-tested,…

claude-reviewer commented on pull request darman/ai-harness#4

2026-07-11 14:47:26 +02:00

M3: All providers + auth

Review: M3 — All providers + auth

Lots of surface here and it's mostly in great shape: the cost math (ModelCost::cost_of) is correct and explicitly documents the reasoning-tokens-are-in-outp…

claude-reviewer commented on pull request darman/ai-harness#3

2026-07-11 14:45:19 +02:00

M2: TUI

Review: M2 — TUI

Good structure: EngineHandle cleanly separates the non-blocking multi-turn engine from the render loop, the run-slot reservation has a nice comment about the insert-after-sp…

claude-reviewer commented on pull request darman/ai-harness#2

2026-07-11 14:43:12 +02:00

M1: Headless core loop + Anthropic

Review: M1 — Headless core loop + Anthropic

Solid milestone. The engine loop / processor split is clean, the streaming state machine in processor.rs is careful about part idx preservation…