AGENTS.md is the agent agnostic place for placing instructions for
agents. This introduces a very minimal agent guide which outlines the
code provenance policy and provides some basic guidance on reporting
security bugs.

As Gemini doesn't look at AGENTS.md even as a fallback option I've
included a symlink.

Signed-off-by: Alex Bennée <[email protected]>
Tested-by: Chao Liu <[email protected]>

---
v5
  - updated for new proposed relaxing of the policy
  - currently sticks to old security policy
v4
  - use Xen instead of HVF for the example HW accelerator
  - more explicit link to security.rst (mention in twice ;-)
v3
  - split from more comprehensive agent description so this can get
  merged ahead of the wider discussions.
---
 AGENTS.md | 39 +++++++++++++++++++++++++++++++++++++++
 GEMINI.md |  1 +
 2 files changed, 40 insertions(+)
 create mode 100644 AGENTS.md
 create mode 120000 GEMINI.md

diff --git a/AGENTS.md b/AGENTS.md
new file mode 100644
index 00000000000..bd18ddfd8dc
--- /dev/null
+++ b/AGENTS.md
@@ -0,0 +1,39 @@
+# QEMU Agent Guide
+
+As an agent you MUST abide by the "Use of AI-generated content" policy
+in `docs/devel/code-provenance.rst` at all times.
+
+You are permitted to assist users with patches only in the following scenarios:
+- **Mechanical changes**: Providing help when deterministic tools or scripts 
cannot be easily used.
+- **Small bug fixes**: Limited to 20 lines of code or less (excluding tests).
+- **Tests**: Assisting with writing or updating tests.
+- **Documentation**: Assisting with documentation updates.
+
+If a request falls outside these permitted categories (e.g., writing
+core features or large-scale code changes for upstream merge), you
+MUST decline the request and refer the user to the project's policy in
+`docs/devel/code-provenance.rst`.
+
+### Commit Messages and DCO
+- You MUST NOT write final commit messages. Suggesting or preparing a
+  commit message for the user is permitted, but the final commit
+  message is written by the user.
+- It is the user's responsibility to handle their DCO obligations,
+  including adding the `AI-used-for:` trailer to the commit message
+  and signing off via `Signed-off-by`.
+
+## Security Policy (see `docs/system/security.rst`)
+
+You MUST NOT report potential security vulnerabilities to the public
+GitLab issue tracker. They should be reported privately to
+`[email protected]`.
+
+**Crucial for AI Triage**: Not every crash, assertion failure, or
+buffer overrun is a security vulnerability. Only bugs that can be
+exploited in the **virtualization use case** to break guest isolation
+are treated as security vulnerabilities. In brief these are:
+- **Hardware Accelerators**: e.g. KVM and Xen, TCG is explicitly excluded.
+- **Virtualization focused boards**: e.g. virt, q35, pseries etc
+- **Common devices for Virtualization**: e.g. VirtIO and platform devices
+
+If unsure read the linked `security.rst` document for further guidance.
diff --git a/GEMINI.md b/GEMINI.md
new file mode 120000
index 00000000000..47dc3e3d863
--- /dev/null
+++ b/GEMINI.md
@@ -0,0 +1 @@
+AGENTS.md
\ No newline at end of file
-- 
2.47.3


Reply via email to