werkator 1.43.5: the AI review reports nothing about generated sections #165

2026-10-18T20:55:17+02:00

claude-code commented

2026-10-18 20:55:17 +02:00

Adds the generated-section hint of werkrevisor 0.49.1 to the review instructions in .werkrevisor.toml.

See docs/prs/.

🤖 Generated with Claude Code

Adds the generated-section hint of werkrevisor 0.49.1 to the review instructions in `.werkrevisor.toml`. See docs/prs/. 🤖 Generated with [Claude Code](https://claude.com/claude-code)

claude-code added 1 commit 2026-10-18 20:55:18 +02:00

PR document: the AI review reports nothing about generated sections

werkator build succeeded after 03:24

Details

85e766cb99

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

claude-code added 1 commit 2026-10-18 20:55:31 +02:00

werkator 1.43.5: the AI review reports nothing about generated sections

werkator build succeeded after 04:02

Details

ai-review/assessment human review required; a human approval unlocks the merge; review requested from mi; merge scheduled for when the checks succeed

Details

ai-review/gate build succeeded after 00:44

Details

ai-review/codex Codex review passed

79dd2ed5fb

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

claude-code marked the pull request as ready for review 2026-10-18 21:04:34 +02:00

ai-reviewer commented

2026-10-18 21:05:22 +02:00

🟡 werkrevisor: YELLOW / HUMAN_REVIEW

Change kind: mixed.

Reasons

YELLOW risky paths changed: .werkrevisor.toml (built in)
hint 1 changed file(s) that neither weaken the checks, touch security nor show a risk category of jvm-spring-backend according to Jev
hint 1 build change(s) of low risk according to Jev: build.gradle.kts (weakens checks 0.03, risk 0.00, security 0.01)
hint 1 changed file was given to the AI as excerpt of the selected lines and 5 lines around each changed line, not in full (each larger than [review] max_full_file_chars = 80000): src/main/resources/templates/releases.html

Classifier

5 of 5 units passed all questions (1 PR document(s)).
1 answer ignored because of a confidence below [classifier] min_confidence.

_{Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 18411, calls 1, tokens in 17688 / out 1624 (reasoning included in out), duration 21.2 s, cost 0.0072 USD (reported), classifier `jev-1.13.0` calls 5, tokens in 3322, cost 0.0001 USD, excerpt selection `openrouter/openai/gpt-6-luna` calls 1, tokens in 32143 / out 95, cost 0.0041 USD (reported), build file judge `jev-1.13.0` calls 2, tokens in 2143, cost 0.0001 USD, phases: path_judge 0.3 s, classifier 0.4 s, context 3.7 s, model_review 15.6 s, config: defaults + host + repository (.werkrevisor.toml at main 6badbce).

Reviewed head `79dd2ed5fb54d897cce65f6f74dc4f305fa75f62` against base `6badbcee7a43f6c7f38630dba1fde1905717a4da`, werkrevisor 0.52.0.}

## 🟡 werkrevisor: YELLOW / HUMAN_REVIEW Change kind: `mixed`. ### Reasons - **YELLOW** risky paths changed: .werkrevisor.toml (built in) - **hint** 1 changed file(s) that neither weaken the checks, touch security nor show a risk category of jvm-spring-backend according to Jev - **hint** 1 build change(s) of low risk according to Jev: build.gradle.kts (weakens checks 0.03, risk 0.00, security 0.01) - **hint** 1 changed file was given to the AI as excerpt of the selected lines and 5 lines around each changed line, not in full (each larger than [review] max_full_file_chars = 80000): src/main/resources/templates/releases.html ### Classifier 5 of 5 units passed all questions (1 PR document(s)). 1 answer ignored because of a confidence below [classifier] min_confidence. Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 18411, calls 1, tokens in 17688 / out 1624 (reasoning included in out), duration 21.2 s, cost 0.0072 USD (reported), classifier `jev-1.13.0` calls 5, tokens in 3322, cost 0.0001 USD, excerpt selection `openrouter/openai/gpt-6-luna` calls 1, tokens in 32143 / out 95, cost 0.0041 USD (reported), build file judge `jev-1.13.0` calls 2, tokens in 2143, cost 0.0001 USD, phases: path_judge 0.3 s, classifier 0.4 s, context 3.7 s, model_review 15.6 s, config: defaults + host + repository (.werkrevisor.toml at main 6badbce). Reviewed head `79dd2ed5fb54d897cce65f6f74dc4f305fa75f62` against base `6badbcee7a43f6c7f38630dba1fde1905717a4da`, werkrevisor 0.52.0.

ai-reviewer scheduled this pull request to auto merge when all checks succeed 2026-10-18 21:05:23 +02:00

ai-reviewer requested review from mi 2026-10-18 21:05:23 +02:00

ai-reviewer commented

2026-10-18 21:06:27 +02:00

Codex review: critical

The change narrows the required AI review by suppressing findings in generated documentation sections, which weakens review coverage outside what application tests verify. The repository also explicitly requires human review for every change to .werkrevisor.toml.

No findings.

The merge waits for the status ai-review/codex: every line comment resolved, and the approval of a human for a critical PR or for a finding that is only here.

_{Model `gpt-6-astra`, effort high, tokens in 83248 (cached 66432) / out 334, 21.6 s, 4 commands; reviewed head `79dd2ed5fb54d897cce65f6f74dc4f305fa75f62`.}

## Codex review: critical The change narrows the required AI review by suppressing findings in generated documentation sections, which weakens review coverage outside what application tests verify. The repository also explicitly requires human review for every change to .werkrevisor.toml. No findings. The merge waits for the status `ai-review/codex`: every line comment resolved, and the approval of a human for a critical PR or for a finding that is only here. Model `gpt-6-astra`, effort high, tokens in 83248 (cached 66432) / out 334, 21.6 s, 4 commands; reviewed head `79dd2ed5fb54d897cce65f6f74dc4f305fa75f62`.

mi approved these changes

2026-10-19 06:29:58 +02:00

ai-reviewer merged commit 512150c6ac into main

2026-10-19 06:30:29 +02:00

ai-reviewer deleted branch claude-code/generated-sections

2026-10-19 06:30:29 +02:00

Sign in to join this conversation.

3 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: mi/werkator#165