Skip to content

fix: evaluation report link + ADR-006 Code Review Tooling#345

Merged
rdmueller merged 2 commits into
LLM-Coding:mainfrom
raifdmueller:fix/evaluation-report-link
Mar 24, 2026
Merged

fix: evaluation report link + ADR-006 Code Review Tooling#345
rdmueller merged 2 commits into
LLM-Coding:mainfrom
raifdmueller:fix/evaluation-report-link

Conversation

@raifdmueller
Copy link
Copy Markdown
Contributor

@raifdmueller raifdmueller commented Mar 24, 2026

Summary

  • Fix broken link to evaluation report on the evaluations page (../evaluation-report.htmlevaluation-report.html)
  • Add ADR-006: Code Review Tooling evaluation (Proposed). Compares CodeRabbit Free, GitHub Copilot Review, Claude Code CLI, Claude Code App. Pugh matrix to be filled after parallel evaluation.

References #164

Test plan

  • Verify evaluation report link works on the website
  • ADR-006 accessible in docs/specs/adrs/

🤖 Generated with Claude Code

Summary by CodeRabbit

Dokumentation

  • Dokumentation
    • Aktualisierte Dokumentationslinks für verbesserte Navigationserfahrung.
    • Neue Dokumentation zur Evaluierung des Code-Review-Prozesses hinzugefügt.

raifdmueller and others added 2 commits March 24, 2026 21:16
Evaluates CodeRabbit Free vs. GitHub Copilot Review vs. Claude Code CLI
vs. Claude Code App. Pugh matrix to be filled after parallel evaluation
on next PR.

Motivation: CodeRabbit Free Tier limit reached regularly.

References LLM-Coding#164

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Fix relative link to evaluation-report.html (SPA serves from root)
- Add ADR-006: evaluates CodeRabbit vs Copilot vs Claude Code for
  code reviews. Pugh matrix to be filled after parallel evaluation.

References LLM-Coding#164

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
@coderabbitai
Copy link
Copy Markdown

coderabbitai Bot commented Mar 24, 2026

Walkthrough

Der PR enthält zwei Dokumentationsänderungen: Korrektur eines relativen Link-Pfads in der Anchor-Evaluations-Datei durch Entfernen eines übergeordneten Verzeichnispräfix sowie Hinzufügen eines neuen Architecture Decision Record (ADR) zur Bewertung von Code-Review-Tools.

Changes

Cohort / File(s) Summary
Hyperlink-Korrektur
docs/anchor-evaluations.adoc
Entfernung des Parent-Directory-Präfix (../) aus dem Link zu evaluation-report.html zur Anpassung der Pfadrelativität im docs/-Verzeichnis.
Neues ADR-Dokument
docs/specs/adrs/adr-006-code-review-tooling.adoc
Neues Architecture Decision Record für die Evaluierung von Code-Review-Tools. Dokumentiert aktuellen Status (CodeRabbit Free Tier), drei Kandidaten (GitHub Copilot Code Review, Claude Code CLI, CodeRabbit) mit Bewertungskriterien, Pugh-Matrix-Entwurf und Risiko-/Folgenanalyse. Status: Evaluation läuft, keine finale Entscheidung getroffen.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~12 minutes

Possibly related PRs

🚥 Pre-merge checks | ✅ 3
✅ Passed checks (3 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed Der PR-Titel bezieht sich auf beide Hauptänderungen des Changesets: Die Behebung des Links zum Evaluierungsbericht und die Ergänzung der ADR-006 zum Code-Review-Tooling.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

Copy link
Copy Markdown

@coderabbitai coderabbitai Bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 3

🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.

Inline comments:
In `@docs/anchor-evaluations.adoc`:
- Line 15: Die Link-Ziel-Angabe in der AsciiDoc-Zeile
link:evaluation-report.html[**View the latest evaluation results →**] ist
relativ falsch und führt im gebauten Site-Pfad auf docs/evaluation-report.html
statt auf die Root-Datei; ändere das Ziel zurück auf ../evaluation-report.html
(also wieder "../" vor den Dateinamen) damit der Link korrekt auf
/evaluation-report.html zeigt.

In `@docs/specs/adrs/adr-006-code-review-tooling.adoc`:
- Line 7: Replace Markdown-style double-asterisk bold markers with AsciiDoc
single-asterisk bold markers: change instances like "**Proposed**" to
"*Proposed*", and similarly convert all "**...**" occurrences in the file
(including the ranges noted around lines 16-18, 54-59, 103-104) to "*...*"; also
ensure bullet lists use single asterisks (`* item`) rather than Markdown dashes
or double-asterisk formats so the document follows the AsciiDoc convention.
- Line 51: The decision text "Der nächste inhaltliche PR wird parallel von allen
drei Tools reviewed." contradicts the ADR's matrix which lists four alternatives
(including Claude App); update the sentence to reflect the correct number of
tools (e.g., "allen vier Tools") or remove/adjust references so both the
decision paragraph and the evaluation matrix consistently state the same count;
apply the same correction at the other occurrence around line 65 and verify the
matrix/alternative headings (including "Claude App") and any summary text match
the chosen count.

ℹ️ Review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yml

Review profile: CHILL

Plan: Pro

Run ID: f4a552ae-4678-4965-bdca-7220ae3750e6

📥 Commits

Reviewing files that changed from the base of the PR and between b5e6196 and 02467d3.

📒 Files selected for processing (2)
  • docs/anchor-evaluations.adoc
  • docs/specs/adrs/adr-006-code-review-tooling.adoc

Without systematic evaluation, our catalog is a collection of untested assumptions.

link:../evaluation-report.html[**View the latest evaluation results →**]
link:evaluation-report.html[**View the latest evaluation results →**]
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟠 Major

Linkziel ist relativ falsch und bricht im generierten Website-Pfad.

Der neue Pfad zeigt im Build auf docs/evaluation-report.html, die Datei liegt aber auf Root-Level (/evaluation-report.html). Bitte ../ wiederherstellen.

🔧 Vorschlag
-link:evaluation-report.html[**View the latest evaluation results →**]
+link:../evaluation-report.html[**View the latest evaluation results →**]
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.

In `@docs/anchor-evaluations.adoc` at line 15, Die Link-Ziel-Angabe in der
AsciiDoc-Zeile link:evaluation-report.html[**View the latest evaluation results
→**] ist relativ falsch und führt im gebauten Site-Pfad auf
docs/evaluation-report.html statt auf die Root-Datei; ändere das Ziel zurück auf
../evaluation-report.html (also wieder "../" vor den Dateinamen) damit der Link
korrekt auf /evaluation-report.html zeigt.


== Status

**Proposed** - 2026-03-24
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor

Bitte AsciiDoc-Bold statt Markdown-Bold verwenden.

In .adoc sollten Hervorhebungen mit *text* geschrieben werden, nicht mit **text**.

As per coding guidelines: “Use bullet lists with * … and use *bold* for bold text (not **bold**)”.

Also applies to: 16-18, 54-59, 103-104

🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.

In `@docs/specs/adrs/adr-006-code-review-tooling.adoc` at line 7, Replace
Markdown-style double-asterisk bold markers with AsciiDoc single-asterisk bold
markers: change instances like "**Proposed**" to "*Proposed*", and similarly
convert all "**...**" occurrences in the file (including the ranges noted around
lines 16-18, 54-59, 103-104) to "*...*"; also ensure bullet lists use single
asterisks (`* item`) rather than Markdown dashes or double-asterisk formats so
the document follows the AsciiDoc convention.


_Noch nicht entschieden — Evaluation läuft._

Der nächste inhaltliche PR wird parallel von allen drei Tools reviewed.
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟠 Major

Entscheidungstext und Matrix widersprechen sich bei der Anzahl der Tools.

In Line 51 steht „allen drei Tools“, die ADR vergleicht aber vier Alternativen (inkl. Claude App). Bitte auf eine konsistente Anzahl bringen, sonst ist der Evaluationsumfang unklar.

Also applies to: 65-65

🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.

In `@docs/specs/adrs/adr-006-code-review-tooling.adoc` at line 51, The decision
text "Der nächste inhaltliche PR wird parallel von allen drei Tools reviewed."
contradicts the ADR's matrix which lists four alternatives (including Claude
App); update the sentence to reflect the correct number of tools (e.g., "allen
vier Tools") or remove/adjust references so both the decision paragraph and the
evaluation matrix consistently state the same count; apply the same correction
at the other occurrence around line 65 and verify the matrix/alternative
headings (including "Claude App") and any summary text match the chosen count.

@rdmueller rdmueller merged commit ceee4d0 into LLM-Coding:main Mar 24, 2026
6 of 7 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants