New-contributor onboarding currently requires stitching knowledge
together from `AGENTS.md`, per-package `Makefile`s, and external docs,
and neither the cross-layer request flow nor the `libs/code` process
model is mapped anywhere in the repo.
This adds:
- Root `ARCHITECTURE.md` (the three-layer `deepagents` → `create_agent`
→ LangGraph stack and request flow) and `DEVELOPMENT.md` (a single
bootstrap + command reference), cross-linked from `README.md` and
`libs/README.md`.
- `libs/code/ARCHITECTURE.md` (process model, interactive/headless
request lifecycles, module map, and a "where do I change X" cheat
sheet), linked from `DEV.md` and `AGENTS.md`.
Made by [Open SWE](https://openswe.vercel.app)
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Failed MCP servers now keep noisy or raw errors out of the inline server
list while still making full details accessible on demand. Shared
Unicode and control-character sanitization is reused across MCP local
context and UI rendering so terminal escapes and deceptive characters
are handled consistently.
Mason Daugherty