fix(evolution): track guide updates and refresh repository overview

[jhinpan]

Summary

• align the README, skill prompt, citation, and GitHub description with the active gfx942/gfx950 scope and actual maintainer-controlled workflow
• distinguish complete baseline harvests from rolling per-source discovery without duplicating volatile snapshot metadata
• allowlist the canonical AMDGPU guide path so future updates are discovered, with a regression test and refreshed manifest provenance
• document the enforced file/line budgets, Draft creation behavior, CI triggers, and administrator bypass accurately

Test plan

• python3 -m pytest tests (56 passed)
• python3 scripts/validate.py (0 errors)
• retrieval and answer evaluations
• artifact provenance and corpus manifest checks

[gemini-code-assist]

Caution

The consumer version of Gemini Code Assist on GitHub has been sunset. All code review activity has officially ceased.

[sourcery-ai]

Reviewer's guide (collapsed on small PRs)

Reviewer's Guide

Documentation-only README refresh aligning the project overview and citation with current CDNA scope, and surfacing details of the evidence/refresh pipeline and maintenance tooling.

Flow diagram for the evidence refresh and validation pipeline

flowchart LR
  A[data_sources_yaml] --> B[daily_worker]
  B --> C[disposable_clone]
  C --> D[rolling_Draft_PR]
  D --> E[approved_hardware_tasks]
  E --> F[trusted_MI355_node_validation]
  F --> G[merged_PR]

  B --- H[self_evolution_boundary]
  H --- I[human_review_and_merge]

Loading

File-Level Changes

Change	Details	Files
Clarified project overview, skill packaging, and governance model in README introduction.	Reworded the CDNA3/CDNA4 scope and Codex/Claude skill packaging description. Explained that the repo root is the skill directory so git pull updates tooling and corpus together. Documented coupling of architecture-scoped synthesis with provenance, real-silicon validation, and a review-gated evidence flywheel, including automation constraints.	README.md
Described the refresh pipeline and hardware validation workflow.	Added data/sources.yaml as canonical registry for the budgeted refresh pipeline. Explained daily worker behavior using disposable clones and rolling Draft PRs. Documented that approved hardware tasks run on a trusted MI355 node against an exact candidate SHA.	README.md
Updated BibTeX citation to match CDNA-only scope.	Changed citation title from CDNA/RDNA to CDNA-only GPU kernel optimization knowledge base.	README.md

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey - I've left some high level feedback:

• Consider briefly defining terms like “budgeted refresh pipeline” and “review-gated evidence flywheel” or linking to sections that explain them, so readers unfamiliar with your internal nomenclature can understand the workflow quickly.
• The sentence describing the daily worker and trusted MI355 node is dense; breaking it into two sentences or a short bullet list could make the maintenance pipeline and hardware validation steps clearer.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- Consider briefly defining terms like “budgeted refresh pipeline” and “review-gated evidence flywheel” or linking to sections that explain them, so readers unfamiliar with your internal nomenclature can understand the workflow quickly.
- The sentence describing the daily worker and trusted MI355 node is dense; breaking it into two sentences or a short bullet list could make the maintenance pipeline and hardware validation steps clearer.

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[jhinpan]

Superseded by #15, which preserves the same reviewed tree plus the final watermark fixes in one exact-author commit. The replacement avoids force-pushing this review history and allows a rebase merge that retains Jin Pan jin.pan@amd.com.