ai-review/assessment AI review passed; approved by werkrevisor; merge waits for 1 open hint(s): reply to each line comment and resolve it, then restart the review or push a commit
The tables per day, week and month show PRs and the cost per PR instead of reviews;
an inline SVG chart per period shows the cost, the number of PRs and the cost per PR.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Gate: approved by werkrevisor; merge waits for 1 open hint(s): reply to each line comment and resolve it, then restart the review or push a commit.
Change kind: mixed.
Reasons
hint 3 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 6 section(s) of the PR document agree with the change summary of openrouter/minimax/minimax-m3 according to Jev
hint 1 finding(s) of low severity or rated minor by Jev: statistics/src/main/resources/static/werkrevisor-dashboard.js:101-103
Findings
Docs/code mismatch at statistics/src/main/resources/static/werkrevisor-dashboard.js:101-103, severity unknown, counted as medium, hint, as a line comment
Classifier
6 of 6 units passed all questions (1 PR document(s)).
Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 29514, calls 1, tokens in 28550 / out 12272 (reasoning included in out), duration 96.6 s, cost 0.0233 USD (reported), classifier `jev-1.13.0` calls 6, tokens in 4666, cost 0.0002 USD, finding judge `jev-1.13.0` calls 1, tokens in 1822, cost 0.0001 USD, change summary `openrouter/minimax/minimax-m3` via Minimax calls 1, tokens in 4247 / out 1090, cost 0.0025 USD (reported), PR document check `jev-1.13.0` calls 6, tokens in 7504, cost 0.0003 USD, build file judge `jev-1.13.0` calls 4, tokens in 5329, cost 0.0002 USD, phases: path_judge 0.3 s, classifier 0.5 s, change_summary 7.8 s, doc_check 0.6 s, context 0.3 s, model_review 86.4 s, finding_judge 0.3 s, config: defaults + host + repository (.werkrevisor.toml at main 6410fa5).
Reviewed head `0bc07c3e4247248ef53fa83bbd923d2682b26281` against base `6410fa5f183118125b4b173d88ea981770e659a1`, werkrevisor 0.27.0.
<!-- werkrevisor:0bc07c3e4247248ef53fa83bbd923d2682b26281 -->
<!-- werkrevisor-verdict:GREEN -->
<!-- werkrevisor-folded -->
<details><summary>🟢 werkrevisor GREEN for <code>0bc07c3</code>, superseded by <a href="http://git.javagil.de/mi/werkrevisor/pulls/57#issuecomment-2145">the result for <code>74a0729</code></a></summary>
## 🟢 werkrevisor: GREEN / PASS
Gate: approved by werkrevisor; merge waits for 1 open hint(s): reply to each line comment and resolve it, then restart the review or push a commit.
Change kind: `mixed`.
### Reasons
- **hint** 3 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** 6 section(s) of the PR document agree with the change summary of openrouter/minimax/minimax-m3 according to Jev
- **hint** 1 finding(s) of low severity or rated minor by Jev: statistics/src/main/resources/static/werkrevisor-dashboard.js:101-103
### Findings
1. **Docs/code mismatch** at `statistics/src/main/resources/static/werkrevisor-dashboard.js:101-103`, severity unknown, counted as medium, hint, as a line comment
### Classifier
6 of 6 units passed all questions (1 PR document(s)).
<sub>
Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 29514, calls 1, tokens in 28550 / out 12272 (reasoning included in out), duration 96.6 s, cost 0.0233 USD (reported), classifier `jev-1.13.0` calls 6, tokens in 4666, cost 0.0002 USD, finding judge `jev-1.13.0` calls 1, tokens in 1822, cost 0.0001 USD, change summary `openrouter/minimax/minimax-m3` via Minimax calls 1, tokens in 4247 / out 1090, cost 0.0025 USD (reported), PR document check `jev-1.13.0` calls 6, tokens in 7504, cost 0.0003 USD, build file judge `jev-1.13.0` calls 4, tokens in 5329, cost 0.0002 USD, phases: path_judge 0.3 s, classifier 0.5 s, change_summary 7.8 s, doc_check 0.6 s, context 0.3 s, model_review 86.4 s, finding_judge 0.3 s, config: defaults + host + repository (.werkrevisor.toml at main 6410fa5).<br>
Reviewed head `0bc07c3e4247248ef53fa83bbd923d2682b26281` against base `6410fa5f183118125b4b173d88ea981770e659a1`, werkrevisor 0.27.0.
</sub>
</details>
werkrevisor: GREEN / PASS for 0bc07c3e4247248ef53fa83bbd923d2682b26281.
The result comment of werkrevisor holds the details.
werkrevisor: GREEN / PASS for `0bc07c3e4247248ef53fa83bbd923d2682b26281`.
The result comment of werkrevisor holds the details.
<!-- werkrevisor-review:0bc07c3e4247248ef53fa83bbd923d2682b26281 -->
Docs/code mismatch, severity unknown, counted as medium (werkrevisor)
hint; Jev: real 0.79, severity 2.1 of 3
The comment in trendChart (line 101), the PR document (line 53), the README (line 953), and the werkbaum (line 102) all state the chart "starts at the oldest period with reviews on", but the code checks p.sums.reviews > 0 || p.sums.costUsd > 0, so a period with only billed calls (cost > 0, reviews = 0) is also included. Either the docs should mention that billed-only periods count, or the condition should be tightened to reviews > 0 to match the documentation.
**Docs/code mismatch**, severity unknown, counted as medium (werkrevisor)
hint; Jev: real 0.79, severity 2.1 of 3
The comment in `trendChart` (line 101), the PR document (line 53), the README (line 953), and the werkbaum (line 102) all state the chart "starts at the oldest period with reviews on", but the code checks `p.sums.reviews > 0 || p.sums.costUsd > 0`, so a period with only billed calls (cost > 0, reviews = 0) is also included. Either the docs should mention that billed-only periods count, or the condition should be tightened to `reviews > 0` to match the documentation.
Fixed: billed calls before the service recorded reviews are costs too, so the chart keeps them; the comment, the README, the PR document and the Werkbaum now say "the oldest period with reviews or costs".
Fixed: billed calls before the service recorded reviews are costs too, so the chart keeps them; the comment, the README, the PR document and the Werkbaum now say "the oldest period with reviews or costs".
werkrevisor: GREEN / PASS for 74a0729c4f8ca4c70f6ba1fc3c5c193c44674464.
The result comment of werkrevisor holds the details.
werkrevisor: GREEN / PASS for `74a0729c4f8ca4c70f6ba1fc3c5c193c44674464`.
The result comment of werkrevisor holds the details.
<!-- werkrevisor-review:74a0729c4f8ca4c70f6ba1fc3c5c193c44674464 -->
ai-reviewer
scheduled this pull request to auto merge when all checks succeed 2026-10-08 19:04:15 +02:00
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
See the PR document.
🤖 Generated with Claude Code
🟢 werkrevisor GREEN for
0bc07c3, superseded by the result for74a0729🟢 werkrevisor: GREEN / PASS
Gate: approved by werkrevisor; merge waits for 1 open hint(s): reply to each line comment and resolve it, then restart the review or push a commit.
Change kind:
mixed.Reasons
Findings
statistics/src/main/resources/static/werkrevisor-dashboard.js:101-103, severity unknown, counted as medium, hint, as a line commentClassifier
6 of 6 units passed all questions (1 PR document(s)).
Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 29514, calls 1, tokens in 28550 / out 12272 (reasoning included in out), duration 96.6 s, cost 0.0233 USD (reported), classifier `jev-1.13.0` calls 6, tokens in 4666, cost 0.0002 USD, finding judge `jev-1.13.0` calls 1, tokens in 1822, cost 0.0001 USD, change summary `openrouter/minimax/minimax-m3` via Minimax calls 1, tokens in 4247 / out 1090, cost 0.0025 USD (reported), PR document check `jev-1.13.0` calls 6, tokens in 7504, cost 0.0003 USD, build file judge `jev-1.13.0` calls 4, tokens in 5329, cost 0.0002 USD, phases: path_judge 0.3 s, classifier 0.5 s, change_summary 7.8 s, doc_check 0.6 s, context 0.3 s, model_review 86.4 s, finding_judge 0.3 s, config: defaults + host + repository (.werkrevisor.toml at main6410fa5).Reviewed head `0bc07c3e4247248ef53fa83bbd923d2682b26281` against base `6410fa5f183118125b4b173d88ea981770e659a1`, werkrevisor 0.27.0.
werkrevisor: GREEN / PASS for
0bc07c3e4247248ef53fa83bbd923d2682b26281.The result comment of werkrevisor holds the details.
@@ -74,0 +98,4 @@// One SVG per table: bars for the cost per period, a dashed line for the cost per pull request,// a line for the number of pull requests, each on its own y axis; the oldest period stands left.function trendChart(periods) {// From the oldest period with reviews on, so that empty months do not squeeze the data to the right edge.Docs/code mismatch, severity unknown, counted as medium (werkrevisor)
hint; Jev: real 0.79, severity 2.1 of 3
The comment in
trendChart(line 101), the PR document (line 53), the README (line 953), and the werkbaum (line 102) all state the chart "starts at the oldest period with reviews on", but the code checksp.sums.reviews > 0 || p.sums.costUsd > 0, so a period with only billed calls (cost > 0, reviews = 0) is also included. Either the docs should mention that billed-only periods count, or the condition should be tightened toreviews > 0to match the documentation.Fixed: billed calls before the service recorded reviews are costs too, so the chart keeps them; the comment, the README, the PR document and the Werkbaum now say "the oldest period with reviews or costs".
New commits pushed, approval review dismissed automatically according to repository settings
🟢 werkrevisor: GREEN / PASS
Change kind:
mixed.Reasons
Classifier
6 of 6 units passed all questions (1 PR document(s)).
Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 29535, calls 1, tokens in 28570 / out 15776 (reasoning included in out), duration 118.7 s, cost 0.0261 USD (reported), classifier `jev-1.13.0` calls 6, tokens in 4668, cost 0.0002 USD, change summary `openrouter/minimax/minimax-m3` via Minimax calls 1, tokens in 4256 / out 1308, cost 0.0028 USD (reported), PR document check `jev-1.13.0` calls 6, tokens in 7812, cost 0.0003 USD, build file judge `jev-1.13.0` calls 4, tokens in 5334, cost 0.0002 USD, phases: path_judge 0.3 s, classifier 0.5 s, change_summary 8.6 s, doc_check 0.6 s, context 0.2 s, model_review 108.2 s, config: defaults + host + repository (.werkrevisor.toml at main6410fa5).Reviewed head `74a0729c4f8ca4c70f6ba1fc3c5c193c44674464` against base `6410fa5f183118125b4b173d88ea981770e659a1`, werkrevisor 0.27.0.
werkrevisor: GREEN / PASS for
74a0729c4f8ca4c70f6ba1fc3c5c193c44674464.The result comment of werkrevisor holds the details.