werkrevisor 0.22.0: Jev judges each changed file by the risk categories of a template #46

2026-10-08T12:09:17+02:00

claude-code commented

2026-10-08 12:09:17 +02:00

🤖 Generated with Claude Code

See [the PR document](docs/prs/2026-10-08-PR%2346-risk-categories.md). 🤖 Generated with [Claude Code](https://claude.com/claude-code)

claude-code added 1 commit 2026-10-08 12:09:17 +02:00

PR#46: PR document for risk categories per changed file

werkator build succeeded after 00:24

Details

werkator/werkrevisor-statistics build succeeded after 00:34

Details

2e1ebc0bbb

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

mi added 1 commit 2026-10-08 12:11:31 +02:00

PR#46: risk templates and red scenario tests

werkator build failed after 00:19

Details

werkator/werkrevisor-statistics build succeeded after 00:29

Details

c8ff25a4c3

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

mi added 1 commit 2026-10-08 12:18:02 +02:00

werkrevisor 0.22.0: Jev judges each changed file by the risk categories of a template

werkator build succeeded after 00:08

Details

werkator/werkrevisor-statistics build succeeded after 00:35

Details

ai-review/assessment AI review passed; approved by werkrevisor; merge scheduled for when the checks succeed

Details

ai-review/gate build succeeded after 02:25

Details

c8b62ab853

A host-only [path_judge] risk_template adds 15 categories per ecosystem on top of
weakens_checks and security; each category gives YELLOW, ORANGE or a hint and names the way out.

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

claude-code marked the pull request as ready for review 2026-10-08 12:18:06 +02:00

ai-reviewer commented

2026-10-08 12:20:34 +02:00

🟢 werkrevisor: GREEN / PASS

Change kind: mixed.

Reasons

hint 9 changed file(s) that neither weaken the checks nor touch security according to Jev
hint 1 build change(s) of low risk according to Jev: statistics/build.gradle.kts (weakens checks 0.02, risk 0.00, security 0.01)
hint 3 changed files were given to the AI only as diff, not in full, so it could not check them against the rest of their file (all full files together would exceed [review] max_full_files_chars = 160000, and no excerpt fits the limits either): werkrevisor/risk/__init__.py, werkrevisor/risk/jvm-spring-backend.toml, werkrevisor/risk/typescript-frontend.toml (advisory: Jev judged every changed file)

Classifier

15 of 15 units passed all questions (1 PR document(s)).
7 answers ignored because of a confidence below [classifier] min_confidence.

_{Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 63078, calls 1, tokens in 60998 / out 20757 (reasoning included in out), duration 142.6 s, cost 0.0432 USD (reported), classifier `jev-1.13.0` calls 15, tokens in 13340, cost 0.0006 USD, excerpt selection `openrouter/openai/gpt-6-luna` calls 3, tokens in 7856 / out 134, cost 0.0010 USD (reported), build file judge `jev-1.13.0` calls 10, tokens in 12161, cost 0.0005 USD, config: defaults + host + repository (.werkrevisor.toml at main 2241ea5).

Reviewed head `c8b62ab853562971fbc46c06506c90f8d9782f0e` against base `2241ea51f3def3ed059f5c09906a948aafe78d82`, werkrevisor 0.21.5.}

## 🟢 werkrevisor: GREEN / PASS Change kind: `mixed`. ### Reasons - **hint** 9 changed file(s) that neither weaken the checks nor touch security according to Jev - **hint** 1 build change(s) of low risk according to Jev: statistics/build.gradle.kts (weakens checks 0.02, risk 0.00, security 0.01) - **hint** 3 changed files were given to the AI only as diff, not in full, so it could not check them against the rest of their file (all full files together would exceed [review] max_full_files_chars = 160000, and no excerpt fits the limits either): werkrevisor/risk/__init__.py, werkrevisor/risk/jvm-spring-backend.toml, werkrevisor/risk/typescript-frontend.toml (advisory: Jev judged every changed file) ### Classifier 15 of 15 units passed all questions (1 PR document(s)). 7 answers ignored because of a confidence below [classifier] min_confidence. <sub> Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 63078, calls 1, tokens in 60998 / out 20757 (reasoning included in out), duration 142.6 s, cost 0.0432 USD (reported), classifier `jev-1.13.0` calls 15, tokens in 13340, cost 0.0006 USD, excerpt selection `openrouter/openai/gpt-6-luna` calls 3, tokens in 7856 / out 134, cost 0.0010 USD (reported), build file judge `jev-1.13.0` calls 10, tokens in 12161, cost 0.0005 USD, config: defaults + host + repository (.werkrevisor.toml at main 2241ea5).<br> Reviewed head `c8b62ab853562971fbc46c06506c90f8d9782f0e` against base `2241ea51f3def3ed059f5c09906a948aafe78d82`, werkrevisor 0.21.5. </sub>

ai-reviewer approved these changes

2026-10-08 12:20:34 +02:00

ai-reviewer left a comment

werkrevisor: GREEN / PASS for c8b62ab853562971fbc46c06506c90f8d9782f0e.
The result comment of werkrevisor holds the details.

werkrevisor: GREEN / PASS for `c8b62ab853562971fbc46c06506c90f8d9782f0e`. The result comment of werkrevisor holds the details.

ai-reviewer scheduled this pull request to auto merge when all checks succeed 2026-10-08 12:20:34 +02:00

ai-reviewer merged commit e095e77ff7 into main

2026-10-08 12:20:37 +02:00

ai-reviewer deleted branch risk-categories

2026-10-08 12:20:37 +02:00

Sign in to join this conversation.

3 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: mi/werkrevisor#46