Add guidelines and tooling for AI-assisted code review of DPDK patches. AGENTS.md provides a two-tier review framework: correctness bugs (resource leaks, use-after-free, race conditions) are reported at >=50% confidence; style issues require >80% with false positive suppression. Mechanical checks handled by checkpatches.sh are excluded to avoid redundant findings.
The analyze-patch.py script supports multiple AI providers (Anthropic, OpenAI, xAI, Google) with mbox splitting, prompt caching, and direct SMTP sending. v9 - update AGENTS to reduce false positives - remove commit message/SPDX items from prompt (checkpatch's job). - update contributing guide text to match actual AGENTS.md coverage. Stephen Hemminger (6): doc: add AGENTS.md for AI code review tools devtools: add multi-provider AI patch review script devtools: add compare-reviews.sh for multi-provider analysis devtools: add multi-provider AI documentation review script doc: add AI-assisted patch review to contributing guide MAINTAINERS: add section for AI review tools AGENTS.md | 1917 ++++++++++++++++++++++++ MAINTAINERS | 8 + devtools/analyze-patch.py | 1348 +++++++++++++++++ devtools/compare-reviews.sh | 192 +++ devtools/review-doc.py | 1099 ++++++++++++++ doc/guides/contributing/new_driver.rst | 2 + doc/guides/contributing/patches.rst | 59 + 7 files changed, 4625 insertions(+) create mode 100644 AGENTS.md create mode 100755 devtools/analyze-patch.py create mode 100755 devtools/compare-reviews.sh create mode 100755 devtools/review-doc.py -- 2.51.0
