mirror of
https://gitlab.com/openconnect/ocserv.git
synced 2026-08-08 09:21:48 +08:00
Nikos Mavrogiannopoulos
855966cd95
Introduce a structured AI assistance framework for the project: - AGENTS.md: single, comprehensive AI guidance file for all tools (Claude Code, Codex, Copilot, Cursor). Covers the privilege-separation architecture invariant, build/test instructions, code style (including a rule against deep preprocessor conditionals), memory allocator policy, IPC modification procedure, module-specific doc pointers, and a contribution checklist split into agent-runnable and human-judgment items. Includes a security disclosure gate that redirects potential vulnerability reports to the confidential issue tracker before any public MR is opened. - contrib/ai/personas/ocserv-core-dev.md: maintainer-facing persona with project-specific protocols for anti-hallucination (GnuTLS/protobuf/seccomp APIs), memory safety (talloc-first, gnutls_malloc exception), a taxonomy of ocserv-specific vulnerability classes, and a self-verification protocol that distinguishes what an agent can check automatically from what requires human judgment. - contrib/ai/personas/ocserv-contributor.md: external-contributor-facing persona with mandatory architecture orientation, a prominent security disclosure gate, five hard guardrails (privilege boundary, syscall portability, GnuTLS-only, protobuf regeneration, talloc), and a step-by-step workflow for features, bug fixes, and security fixes. Signed-off-by: Nikos Mavrogiannopoulos <n.mavrogiannopoulos@gmail.com>
474 B
474 B
AGENTS.md — contrib/ai
This directory contains AI agent persona files and related documentation. These are Markdown prompt-prefix files, not source code.
- Do not apply
clang-formator any other source formatter to files in this directory. - Do not run build or test checks against these files.
- Do not modify these files as part of a patch unless the task explicitly targets them.
For the project-wide agent guidance, see the root AGENTS.md.