github re-analysis due

Azure-Samples/agent-architecture-review-sample

The Architecture Review Agent is an open-source AI agent sample that reviews software architectures and generates interactive diagrams automatically.

Drift inferred · capture-to-capture

No drift recorded — single capability capture; advisories appear once its surface changes.

capabilities 2 tools

transport streamable-http · http counts 2 tools · 0 res · 0 prompts permission surface via code analysis

infer_architecture

LLM inference only - extract components, types, and connections from any unstructured text (README, code, design doc, prose) without running the full review pipeline
review_architecture

One-call pipeline - smart-parse (with automatic LLM fallback) → risk analysis → diagram + Excalidraw MCP render + PNG export → component map → structured report with executive summary and prioritised

skills & danger signals github-tarball

prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed commit a58a49d · analyzer v17 · 2d ago

code evidence vHEAD · github-tarball

evidence-backed findings quoted directly from the published source artifact — not inferred

fs Azure-Samples-agent-architecture-review-sample-a58a49d/api.py :16 from pathlib import Path
fs Azure-Samples-agent-architecture-review-sample-a58a49d/main.py :11 from pathlib import Path
fs Azure-Samples-agent-architecture-review-sample-a58a49d/run_local.py :145 with open(saved, "r", encoding="utf-8") as f:
fs Azure-Samples-agent-architecture-review-sample-a58a49d/tools.py :967 with open(filepath, "w", encoding="utf-8") as f:

net Azure-Samples-agent-architecture-review-sample-a58a49d/tools.py :1256 import httpx # type: ignore[import-untyped]

secrets Azure-Samples-agent-architecture-review-sample-a58a49d/tools.py :610 api_key = os.environ.get("AZURE_OPENAI_API_KEY", "")