werkrevisor 0.30.1: no classifier section without units #64

2026-10-09T11:49:47+02:00

claude-code commented

2026-10-09 11:49:47 +02:00

🤖 Generated with Claude Code

See [the PR document](docs/prs/2026-10-09-PR%2364-empty-classifier-section.md). 🤖 Generated with [Claude Code](https://claude.com/claude-code)

claude-code added 1 commit 2026-10-09 11:49:47 +02:00

PR document: no classifier section without units

werkator build succeeded after 00:11

Details

werkator/werkrevisor-statistics build succeeded after 00:33

Details

467229a96c

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

mi added 1 commit 2026-10-09 11:50:50 +02:00

No classifier section in the result comment when no unit was judged (0.30.1)

werkator build succeeded after 00:10

Details

werkator/werkrevisor-statistics build succeeded after 00:34

Details

c2411d82ac

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

mi added 1 commit 2026-10-09 11:51:05 +02:00

Werkbaum: werkcrappit and werkprobe choose their risk categories; no classifier section without units

werkator build succeeded after 00:10

Details

werkator/werkrevisor-statistics build succeeded after 00:30

Details

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

Details

ai-review/gate build succeeded after 01:15

Details

b1172788da

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

claude-code marked the pull request as ready for review 2026-10-09 11:52:09 +02:00

ai-reviewer commented

2026-10-09 11:53:31 +02:00

🟢 werkrevisor GREEN for b117278, superseded by the result for e9052f1

🟢 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 the PR document may contradict the change summary according to Jev: docs/prs/2026-10-09-PR#64-empty-classifier-section.md:43

Findings

[medium] Requirement conflicts with the change summary at docs/prs/2026-10-09-PR#64-empty-classifier-section.md:43, hint, as a line comment

Classifier

6 of 6 units passed all questions (1 PR document(s)).
2 answers ignored because of a confidence below [classifier] min_confidence.

_{Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 20390, calls 1, tokens in 19653 / out 8207 (reasoning included in out), duration 72.0 s, cost 0.0157 USD (reported), classifier `jev-1.13.0` calls 6, tokens in 4646, cost 0.0002 USD, change summary `openrouter/minimax/minimax-m3` via Minimax calls 1, tokens in 1850 / out 885, cost 0.0016 USD (reported), PR document check `jev-1.13.0` calls 6, tokens in 7514, cost 0.0003 USD, build file judge `jev-1.13.0` calls 4, tokens in 2226, cost 0.0001 USD, phases: path_judge 0.3 s, classifier 0.5 s, change_summary 9.3 s, doc_check 0.4 s, context 0.2 s, model_review 61.0 s, config: defaults + host + repository (.werkrevisor.toml at main 9c7ab5a).

Reviewed head `b1172788da343ea67127f3b5bdf814182bb77fe9` against base `9c7ab5aa831c18c51000ed5299171aa16597ac36`, werkrevisor 0.30.0.}

<details><summary>🟢 werkrevisor GREEN for <code>b117278</code>, superseded by <a href="http://git.javagil.de/mi/werkrevisor/pulls/64#issuecomment-2412">the result for <code>e9052f1</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** the PR document may contradict the change summary according to Jev: docs/prs/2026-10-09-PR#64-empty-classifier-section.md:43 ### Findings 1. **[medium] Requirement conflicts with the change summary** at `docs/prs/2026-10-09-PR#64-empty-classifier-section.md:43`, hint, as a line comment ### Classifier 6 of 6 units passed all questions (1 PR document(s)). 2 answers ignored because of a confidence below [classifier] min_confidence. Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 20390, calls 1, tokens in 19653 / out 8207 (reasoning included in out), duration 72.0 s, cost 0.0157 USD (reported), classifier `jev-1.13.0` calls 6, tokens in 4646, cost 0.0002 USD, change summary `openrouter/minimax/minimax-m3` via Minimax calls 1, tokens in 1850 / out 885, cost 0.0016 USD (reported), PR document check `jev-1.13.0` calls 6, tokens in 7514, cost 0.0003 USD, build file judge `jev-1.13.0` calls 4, tokens in 2226, cost 0.0001 USD, phases: path_judge 0.3 s, classifier 0.5 s, change_summary 9.3 s, doc_check 0.4 s, context 0.2 s, model_review 61.0 s, config: defaults + host + repository (.werkrevisor.toml at main 9c7ab5a). Reviewed head `b1172788da343ea67127f3b5bdf814182bb77fe9` against base `9c7ab5aa831c18c51000ed5299171aa16597ac36`, werkrevisor 0.30.0. </details>

ai-reviewer approved these changes

2026-10-09 11:53:31 +02:00

Dismissed

ai-reviewer left a comment

werkrevisor: GREEN / PASS for b1172788da343ea67127f3b5bdf814182bb77fe9.
The result comment of werkrevisor holds the details.

werkrevisor: GREEN / PASS for `b1172788da343ea67127f3b5bdf814182bb77fe9`. The result comment of werkrevisor holds the details.

docs/prs/2026-10-09-PR#64-empty-classifier-section.md

						
				@@ -0,0 +40,4 @@

				- [test_classifier.ClassifierFlowTest.test_no_section_without_units](../../tests/test_classifier.py)

				#### Scenario#64.02: a PR with a PR document still shows the section

ai-reviewer commented

2026-10-09 11:53:31 +02:00

[medium] Requirement conflicts with the change summary (werkrevisor)

hint

Jev compared this Scenario#64.02 with a summary that openrouter/minimax/minimax-m3 wrote from the diff alone: requirement conflicts with the change summary 0.65.
Fix the PR document or the code, or reply why the section holds, and resolve this comment.
The summary says:

render_table() now returns an empty list early when there are no judged units, flagged or ignored items, suppressing the '### Classifier' section when it would only contain '0 of 0 units passed all questions'.
Added test_no_section_without_units (Scenario#64.01) verifying that with no flagged/ignored units no '### Classifier' section or 'units passed all questions' string appears in the comment; also added the Scenario#64.02 docstring to test_docs_only_can_pass_without_llm.
Project version bumped from 0.30.0 to 0.30.1 in both werkrevisor/__init__.py and statistics/build.gradle.kts.
Documented the new 'No classifier section without units' checklist item (PR#64), expanded the per-repository risk-category status to a partial [^] with werkator (all 16 categories, PR#128), werkcrappit (11 categories off plus metric_integrity, PR#46) and werkprobe (8 categories off, PR#12), added new #triage.risk.werkcrappit and #triage.risk.plugincompat sections, and noted werkator, werkprobe and werkcrappit now select jvm-spring-backend in their .werkrevisor.toml since 2026-10-09.
Section fingerprint 28f168fc28ef.

**[medium] Requirement conflicts with the change summary** (werkrevisor) hint Jev compared this Scenario#64.02 with a summary that openrouter/minimax/minimax-m3 wrote from the diff alone: requirement conflicts with the change summary 0.65. Fix the PR document or the code, or reply why the section holds, and resolve this comment. The summary says: - render_table() now returns an empty list early when there are no judged units, flagged or ignored items, suppressing the '### Classifier' section when it would only contain '0 of 0 units passed all questions'. - Added test_no_section_without_units (Scenario#64.01) verifying that with no flagged/ignored units no '### Classifier' section or 'units passed all questions' string appears in the comment; also added the Scenario#64.02 docstring to test_docs_only_can_pass_without_llm. - Project version bumped from 0.30.0 to 0.30.1 in both werkrevisor/__init__.py and statistics/build.gradle.kts. - Documented the new 'No classifier section without units' checklist item (PR#64), expanded the per-repository risk-category status to a partial [^] with werkator (all 16 categories, PR#128), werkcrappit (11 categories off plus metric_integrity, PR#46) and werkprobe (8 categories off, PR#12), added new #triage.risk.werkcrappit and #triage.risk.plugincompat sections, and noted werkator, werkprobe and werkcrappit now select jvm-spring-backend in their .werkrevisor.toml since 2026-10-09. Section fingerprint `28f168fc28ef`.

claude-code commented

2026-10-09 11:54:07 +02:00

The section holds: the summary confirms Scenario#64.02. render_table returns early only when nothing was judged, flagged or ignored; with a PR document the units are judged, so the section stays, as test_docs_only_can_pass_without_llm checks with "6 of 6 units passed all questions (1 PR document(s))".

The section holds: the summary confirms Scenario#64.02. `render_table` returns early only when nothing was judged, flagged or ignored; with a PR document the units are judged, so the section stays, as `test_docs_only_can_pass_without_llm` checks with "6 of 6 units passed all questions (1 PR document(s))".

claude-code marked this conversation as resolved

claude-code commented

2026-10-09 11:54:07 +02:00

Review round of b1172788: the one hint is answered; the scenario holds. An empty commit restarts the review.

Review round of `b1172788`: the one hint is answered; the scenario holds. An empty commit restarts the review.

mi added 1 commit 2026-10-09 11:54:10 +02:00

Restart the review after the answered hint

werkator/werkrevisor-statistics build succeeded after 00:29

Details

werkator build succeeded after 00:09

Details

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

Details

ai-review/gate build succeeded after 02:42

Details

e9052f1ff6

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

ai-reviewer commented

2026-10-09 11:56:51 +02:00

🟢 werkrevisor: GREEN / PASS

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

Classifier

6 of 6 units passed all questions (1 PR document(s)).
2 answers ignored because of a confidence below [classifier] min_confidence.

_{Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 20394, calls 1, tokens in 19656 / out 16543 (reasoning included in out), duration 159.3 s, cost 0.0257 USD (reported), classifier `jev-1.13.0` calls 6, tokens in 4646, cost 0.0002 USD, change summary `openrouter/minimax/minimax-m3` via Minimax calls 1, tokens in 1850 / out 800, cost 0.0011 USD (reported), PR document check `jev-1.13.0` calls 6, tokens in 7436, cost 0.0003 USD, build file judge `jev-1.13.0` calls 4, tokens in 2226, cost 0.0001 USD, phases: path_judge 0.2 s, classifier 0.5 s, change_summary 6.7 s, doc_check 0.5 s, context 0.2 s, model_review 150.8 s, config: defaults + host + repository (.werkrevisor.toml at main 9c7ab5a).

Reviewed head `e9052f1ff6a8038d93648749b3e1cdefa5356196` against base `9c7ab5aa831c18c51000ed5299171aa16597ac36`, werkrevisor 0.30.0.}

## 🟢 werkrevisor: GREEN / PASS 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 ### Classifier 6 of 6 units passed all questions (1 PR document(s)). 2 answers ignored because of a confidence below [classifier] min_confidence. Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 20394, calls 1, tokens in 19656 / out 16543 (reasoning included in out), duration 159.3 s, cost 0.0257 USD (reported), classifier `jev-1.13.0` calls 6, tokens in 4646, cost 0.0002 USD, change summary `openrouter/minimax/minimax-m3` via Minimax calls 1, tokens in 1850 / out 800, cost 0.0011 USD (reported), PR document check `jev-1.13.0` calls 6, tokens in 7436, cost 0.0003 USD, build file judge `jev-1.13.0` calls 4, tokens in 2226, cost 0.0001 USD, phases: path_judge 0.2 s, classifier 0.5 s, change_summary 6.7 s, doc_check 0.5 s, context 0.2 s, model_review 150.8 s, config: defaults + host + repository (.werkrevisor.toml at main 9c7ab5a). Reviewed head `e9052f1ff6a8038d93648749b3e1cdefa5356196` against base `9c7ab5aa831c18c51000ed5299171aa16597ac36`, werkrevisor 0.30.0.

ai-reviewer approved these changes

2026-10-09 11:56:52 +02:00

ai-reviewer left a comment

werkrevisor: GREEN / PASS for e9052f1ff6a8038d93648749b3e1cdefa5356196.
The result comment of werkrevisor holds the details.

werkrevisor: GREEN / PASS for `e9052f1ff6a8038d93648749b3e1cdefa5356196`. The result comment of werkrevisor holds the details.

ai-reviewer scheduled this pull request to auto merge when all checks succeed 2026-10-09 11:56:52 +02:00

ai-reviewer merged commit e65eea0026 into main

2026-10-09 11:56:54 +02:00

ai-reviewer deleted branch claude-code/classifier-empty-section

2026-10-09 11:56:54 +02:00

Sign in to join this conversation.

3 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: mi/werkrevisor#64