đŸ§Ș Stress-Testing repo-rag Against Real GitHub Repositories — From 99 Files to a 12k-File Monster A stress test of the repo-rag MCP server against four real GitHub repositories — gin, fiber, beego, and microsoft/vscode — found one bug, three architectural limits, and a keyless AI mode. The test measured cold start times ranging from 37.6 seconds for gin (99 files) to over 85 minutes for vscode (12,614 files, aborted), with peak RSS exceeding 1 GB for vscode. The bug, a nondeterministic argument binding order caused by Go map iteration, was fixed by making the schema's required list use []interface{}. ← All posts← Alle BeitrĂ€ge ../blog.html đŸ§Ș Stress-Testing repo-rag Against Real GitHub Repositories — From 99 Files to a 12k-File Monster We pointed repo rag server at four real repositories — gin, fiber, beego and microsoft/vscode — drove it with raw JSON-RPC over stdio, measured every phase with byte-level I/O accounting, and found one real bug, three architectural limits and a surprisingly capable keyless AI mode. This is the full lab report. Related reading: repo-rag MCP repo-rag-mcp.html — the server under test · pipe-docs MCP pipe-docs-mcp.html — the architecture it generalizes Everything you read below was measured against the actual MCP server process — not unit fixtures, not mocks. The question was simple: at what repository size does this design stop working, and why? 🔬 The setup: a measuring harness, not a vibe check We wrote a small Python harness harness.py that: - spawns the real pipe examples/repo rag server.pipe as a subprocess, - speaks newline-delimited JSON-RPC over stdio exactly like an MCP host, - polls /proc/