Analyze and Recommend Third-Party Optimizations

Architecture

Scanner (deterministic)          →  AI Agent (generative)           →  Pipeline (deterministic)
1. Regex: detect hand-rolled code   1. Recommend library replacements    Score, plan, audit,
2. FS: detect code org issues       2. Identify capability gaps          filter, serialize
   (god-dirs, circular deps,        3. Recommend org patterns + tooling
    naming, barrel bloat)            using knowledge + Context7

Design constraints:

• No hardcoded library recommendations — evaluate project context dynamically
• Two analysis modes: replacement (hand-rolled code found) and gap (capability missing entirely)
• Human-in-the-loop: 4 gates at irreversible, preference-driven, or costly decision points
• Language: all output (gates, tables, recommendations, rationale) MUST match the user's input language. If user writes in Chinese, respond in Chinese. If English, respond in English. Never mix.

Gate Protocol