You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@opendal.apache.org by xu...@apache.org on 2026/08/26 07:50:58 UTC
(opendal) branch main updated: docs: forbid speculative service changes in agent guidance (#8152)
This is an automated email from the ASF dual-hosted git repository.
Xuanwo pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/opendal.git
The following commit(s) were added to refs/heads/main by this push:
new 2c2fd48d6 docs: forbid speculative service changes in agent guidance (#8152)
2c2fd48d6 is described below
commit 2c2fd48d63f919b2a3abc2a12fc36bf00421a40e
Author: Xuanwo <gi...@xuanwo.io>
AuthorDate: Wed Aug 26 15:50:52 2026 +0800
docs: forbid speculative service changes in agent guidance (#8152)
---
AGENTS.md | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/AGENTS.md b/AGENTS.md
index 0f6b370e7..4f2701aa7 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -17,8 +17,15 @@ policy.
- Do not publish an Issue, Pull Request, Discussion, or review comment unless a
human has meaningfully reviewed the content and explicitly asked you to submit
it.
-- Treat source-code findings as hypotheses until they are reproduced. Reproduce
- service-specific bugs against the actual service.
+- Do not implement or submit a service-specific change based only on source-code
+ analysis, a mock or emulator, a synthetic malformed response, or another
+ service's implementation. Reproduce the problem against the actual service
+ first.
+- If actual-service reproduction is unavailable, stop before changing code or
+ opening a Pull Request. Raise the hypothesis in a Discussion unless a
+ maintainer has explicitly accepted it as a hardening or maintenance goal.
+- A test against a fabricated response can verify implementation behavior, but
+ it does not establish that the change solves a real-world problem.
- In a Pull Request, briefly disclose AI's material role and any assumptions or
unknowns that affect review. Do not repeat routine validation output.