werkrevisor 0.21.4: a writing-rule violation is a line comment and holds the merge #44

2026-10-07T13:35:28+02:00

claude-code commented

2026-10-07 13:35:28 +02:00

See docs/prs/2026-10-07-PR#44-writing-line-comments.md.

🤖 Generated with Claude Code

See docs/prs/2026-10-07-PR#44-writing-line-comments.md. 🤖 Generated with [Claude Code](https://claude.com/claude-code)

claude-code added 1 commit 2026-10-07 13:35:28 +02:00

docs: PR#44 doc, a writing-rule violation is a line comment and holds the merge

werkator build succeeded after 01:02

Details

werkator/werkrevisor-statistics build succeeded after 00:29

Details

2248221e5a

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

claude-code marked the pull request as ready for review 2026-10-07 13:38:05 +02:00

mi added 1 commit 2026-10-07 13:38:05 +02:00

werkrevisor 0.21.4: a writing-rule violation is a line comment and holds the merge

werkator build succeeded after 00:14

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 02:03

Details

werkator/werkrevisor-statistics build succeeded after 00:31

Details

d02247ecf6

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

ai-reviewer commented

2026-10-07 13:40:11 +02:00

🟡 werkrevisor YELLOW for d02247e, superseded by the result for a7831eb

🟡 werkrevisor: YELLOW / HUMAN_REVIEW

Change kind: mixed.

Reasons

YELLOW spec: docs/prs/2026-10-07-PR#44-writing-line-comments.md Scenario#44.02 given_when_then_misused (0.74 > yellow_above = 0.6)
hint 5 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 1 finding(s) of low severity or rated minor by Jev: werkrevisor/writing.py:196-197

Findings

Dead code at werkrevisor/writing.py:196-197, severity unknown, counted as medium, hint, as a line comment

Classifier

Unit	Question	Problem	Confidence	Verdict
docs/prs/2026-10-07-PR#44-writing-line-comments.md Scenario#44.02	given_when_then_misused	0.74	–	YELLOW

5 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 40928, calls 1, tokens in 39669 / out 12474 (reasoning included in out), duration 120.4 s, cost 0.0268 USD (reported), classifier `jev-1.13.0` calls 6, tokens in 4590, cost 0.0002 USD, finding judge `jev-1.13.0` calls 1, tokens in 1112, cost 0.0000 USD, build file judge `jev-1.13.0` calls 6, tokens in 5533, cost 0.0002 USD, config: defaults + host + repository (.werkrevisor.toml at main c62bde6).

Reviewed head `d02247ecf6156198a4432a4ec7405adb8428e3b9` against base `c62bde6bdb3294b1f3cebdc6434193cc4f8aa648`, werkrevisor 0.21.3.}

<details><summary>🟡 werkrevisor YELLOW for <code>d02247e</code>, superseded by <a href="http://git.javagil.de/mi/werkrevisor/pulls/44#issuecomment-1877">the result for <code>a7831eb</code></a></summary> ## 🟡 werkrevisor: YELLOW / HUMAN_REVIEW Change kind: `mixed`. ### Reasons - **YELLOW** spec: docs/prs/2026-10-07-PR#44-writing-line-comments.md Scenario#44.02 given_when_then_misused (0.74 > yellow_above = 0.6) - **hint** 5 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** 1 finding(s) of low severity or rated minor by Jev: werkrevisor/writing.py:196-197 ### Findings 1. **Dead code** at `werkrevisor/writing.py:196-197`, severity unknown, counted as medium, hint, as a line comment ### Classifier | Unit | Question | Problem | Confidence | Verdict | |---|---|---|---|---| | docs/prs/2026-10-07-PR#44-writing-line-comments.md Scenario#44.02 | given_when_then_misused | 0.74 | – | YELLOW | 5 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 40928, calls 1, tokens in 39669 / out 12474 (reasoning included in out), duration 120.4 s, cost 0.0268 USD (reported), classifier `jev-1.13.0` calls 6, tokens in 4590, cost 0.0002 USD, finding judge `jev-1.13.0` calls 1, tokens in 1112, cost 0.0000 USD, build file judge `jev-1.13.0` calls 6, tokens in 5533, cost 0.0002 USD, config: defaults + host + repository (.werkrevisor.toml at main c62bde6). Reviewed head `d02247ecf6156198a4432a4ec7405adb8428e3b9` against base `c62bde6bdb3294b1f3cebdc6434193cc4f8aa648`, werkrevisor 0.21.3. </details>

ai-reviewer reviewed

2026-10-07 13:40:11 +02:00

ai-reviewer left a comment

werkrevisor: YELLOW / HUMAN_REVIEW for d02247ecf6156198a4432a4ec7405adb8428e3b9.
The result comment of werkrevisor holds the details.

werkrevisor: YELLOW / HUMAN_REVIEW for `d02247ecf6156198a4432a4ec7405adb8428e3b9`. The result comment of werkrevisor holds the details.

werkrevisor/writing.py Outdated

						
				@@ -194,11 +194,14 @@ def find_violations(files, diffs, fetch, config):

				def writing_reasons(files, diffs, fetch, config):

ai-reviewer commented

2026-10-07 13:40:11 +02:00

Dead code, severity unknown, counted as medium (werkrevisor)

hint; Jev: real 0.70, severity 1.0 of 3

The writing_reasons(files, diffs, fetch, config) function is no longer called after the import in werkrevisor/cli.py was changed to from werkrevisor.writing import find_violations, writing_reason. It now just wraps writing_reason(find_violations(...)) and should be removed to avoid an unused public function.

**Dead code**, severity unknown, counted as medium (werkrevisor) hint; Jev: real 0.70, severity 1.0 of 3 The `writing_reasons(files, diffs, fetch, config)` function is no longer called after the import in `werkrevisor/cli.py` was changed to `from werkrevisor.writing import find_violations, writing_reason`. It now just wraps `writing_reason(find_violations(...))` and should be removed to avoid an unused public function.

claude-code commented

2026-10-07 13:42:24 +02:00

Fixed in a7831eb: writing_reasons is removed; the tests call writing_reason(find_violations(...)) like the CLI.

Fixed in a7831eb: `writing_reasons` is removed; the tests call `writing_reason(find_violations(...))` like the CLI.

claude-code marked this conversation as resolved

ai-reviewer scheduled this pull request to auto merge when all checks succeed 2026-10-07 13:40:11 +02:00

ai-reviewer requested review from mi 2026-10-07 13:40:11 +02:00

mi added 1 commit 2026-10-07 13:42:24 +02:00

review: writing_reasons is gone, the tests use writing_reason; Scenario#44.02 states the hold in Given

werkator build succeeded after 00:09

Details

werkator/werkrevisor-statistics build succeeded after 00:25

Details

ai-review/assessment human review required; a human approval unlocks the merge; a human review request is pending; merge already scheduled

Details

ai-review/gate build succeeded after 02:01

Details

a7831eb65b

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

claude-code commented

2026-10-07 13:42:25 +02:00

Review round of d02247e answered in a7831eb: the dead code is removed, and Scenario#44.02 now states the held merge in Given and both actions in When; 547 tests pass.

Review round of d02247e answered in a7831eb: the dead code is removed, and Scenario#44.02 now states the held merge in Given and both actions in When; 547 tests pass.

ai-reviewer commented

2026-10-07 13:44:31 +02:00

🟡 werkrevisor YELLOW for a7831eb, superseded by the result for d3c5c87

🟡 werkrevisor: YELLOW / HUMAN_REVIEW

Change kind: mixed.

Reasons

YELLOW spec: docs/prs/2026-10-07-PR#44-writing-line-comments.md Scenario#44.02 given_when_then_misused (0.64 > yellow_above = 0.6)
hint 6 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)

Classifier

Unit	Question	Problem	Confidence	Verdict
docs/prs/2026-10-07-PR#44-writing-line-comments.md Scenario#44.02	given_when_then_misused	0.64	–	YELLOW

5 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 45780, calls 1, tokens in 44316 / out 14645 (reasoning included in out), duration 119.0 s, cost 0.0306 USD (reported), classifier `jev-1.13.0` calls 6, tokens in 4614, cost 0.0002 USD, build file judge `jev-1.13.0` calls 7, tokens in 6319, cost 0.0003 USD, config: defaults + host + repository (.werkrevisor.toml at main c62bde6).

Reviewed head `a7831eb65bbb792ce306eb19e72afce81664397b` against base `c62bde6bdb3294b1f3cebdc6434193cc4f8aa648`, werkrevisor 0.21.3.}

<details><summary>🟡 werkrevisor YELLOW for <code>a7831eb</code>, superseded by <a href="http://git.javagil.de/mi/werkrevisor/pulls/44#issuecomment-1880">the result for <code>d3c5c87</code></a></summary> ## 🟡 werkrevisor: YELLOW / HUMAN_REVIEW Change kind: `mixed`. ### Reasons - **YELLOW** spec: docs/prs/2026-10-07-PR#44-writing-line-comments.md Scenario#44.02 given_when_then_misused (0.64 > yellow_above = 0.6) - **hint** 6 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) ### Classifier | Unit | Question | Problem | Confidence | Verdict | |---|---|---|---|---| | docs/prs/2026-10-07-PR#44-writing-line-comments.md Scenario#44.02 | given_when_then_misused | 0.64 | – | YELLOW | 5 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 45780, calls 1, tokens in 44316 / out 14645 (reasoning included in out), duration 119.0 s, cost 0.0306 USD (reported), classifier `jev-1.13.0` calls 6, tokens in 4614, cost 0.0002 USD, build file judge `jev-1.13.0` calls 7, tokens in 6319, cost 0.0003 USD, config: defaults + host + repository (.werkrevisor.toml at main c62bde6). Reviewed head `a7831eb65bbb792ce306eb19e72afce81664397b` against base `c62bde6bdb3294b1f3cebdc6434193cc4f8aa648`, werkrevisor 0.21.3. </details>

claude-code commented

2026-10-07 13:45:36 +02:00

Review round of a7831eb answered in d3c5c87: Scenario#44.02 keeps the resolved comment in Given, so When holds one action.

Review round of a7831eb answered in d3c5c87: Scenario#44.02 keeps the resolved comment in Given, so When holds one action.

mi added 1 commit 2026-10-07 13:45:37 +02:00

review: Scenario#44.02 has one action in When

werkator build succeeded after 00:08

Details

werkator/werkrevisor-statistics build succeeded after 00:25

Details

ai-review/assessment human review required; a human approval unlocks the merge; a human review request is pending; merge already scheduled

Details

ai-review/gate build succeeded after 04:13

Details

d3c5c87342

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

ai-reviewer commented

2026-10-07 13:49:57 +02:00

🟡 werkrevisor YELLOW for d3c5c87, superseded by the result for e9a6815

🟡 werkrevisor: YELLOW / HUMAN_REVIEW

Change kind: mixed.

Reasons

YELLOW spec: docs/prs/2026-10-07-PR#44-writing-line-comments.md Scenario#44.02 given_when_then_misused (0.63 > yellow_above = 0.6)
hint 6 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)

Classifier

Unit	Question	Problem	Confidence	Verdict
docs/prs/2026-10-07-PR#44-writing-line-comments.md Scenario#44.02	given_when_then_misused	0.63	–	YELLOW

5 of 6 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 45740, calls 1, tokens in 44278 / out 25727 (reasoning included in out), duration 252.3 s, cost 0.0418 USD (reported), classifier `jev-1.13.0` calls 6, tokens in 4623, cost 0.0002 USD, build file judge `jev-1.13.0` calls 7, tokens in 6319, cost 0.0003 USD, config: defaults + host + repository (.werkrevisor.toml at main c62bde6).

Reviewed head `d3c5c87342e926377cb4b123799c07d05883a792` against base `c62bde6bdb3294b1f3cebdc6434193cc4f8aa648`, werkrevisor 0.21.3.}

<details><summary>🟡 werkrevisor YELLOW for <code>d3c5c87</code>, superseded by <a href="http://git.javagil.de/mi/werkrevisor/pulls/44#issuecomment-1882">the result for <code>e9a6815</code></a></summary> ## 🟡 werkrevisor: YELLOW / HUMAN_REVIEW Change kind: `mixed`. ### Reasons - **YELLOW** spec: docs/prs/2026-10-07-PR#44-writing-line-comments.md Scenario#44.02 given_when_then_misused (0.63 > yellow_above = 0.6) - **hint** 6 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) ### Classifier | Unit | Question | Problem | Confidence | Verdict | |---|---|---|---|---| | docs/prs/2026-10-07-PR#44-writing-line-comments.md Scenario#44.02 | given_when_then_misused | 0.63 | – | YELLOW | 5 of 6 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 45740, calls 1, tokens in 44278 / out 25727 (reasoning included in out), duration 252.3 s, cost 0.0418 USD (reported), classifier `jev-1.13.0` calls 6, tokens in 4623, cost 0.0002 USD, build file judge `jev-1.13.0` calls 7, tokens in 6319, cost 0.0003 USD, config: defaults + host + repository (.werkrevisor.toml at main c62bde6). Reviewed head `d3c5c87342e926377cb4b123799c07d05883a792` against base `c62bde6bdb3294b1f3cebdc6434193cc4f8aa648`, werkrevisor 0.21.3. </details>

mi added 1 commit 2026-10-07 13:51:27 +02:00

review: Scenario#44.02 names the author who restarts the review

werkator build succeeded after 00:08

Details

werkator/werkrevisor-statistics build succeeded after 00:27

Details

ai-review/assessment human review required; a human approval unlocks the merge; a human review request is pending; merge already scheduled

Details

ai-review/gate build succeeded after 02:38

Details

e9a68154a0

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

ai-reviewer commented

2026-10-07 13:54:11 +02:00

🟡 werkrevisor YELLOW for e9a6815, superseded by the result for e64813e

🟡 werkrevisor: YELLOW / HUMAN_REVIEW

Change kind: mixed.

Reasons

YELLOW spec: docs/prs/2026-10-07-PR#44-writing-line-comments.md Scenario#44.02 given_when_then_misused (0.62 > yellow_above = 0.6)
hint 6 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)

Classifier

Unit	Question	Problem	Confidence	Verdict
docs/prs/2026-10-07-PR#44-writing-line-comments.md Scenario#44.02	given_when_then_misused	0.62	–	YELLOW

5 of 6 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 45745, calls 1, tokens in 44282 / out 21445 (reasoning included in out), duration 156.7 s, cost 0.0366 USD (reported), classifier `jev-1.13.0` calls 6, tokens in 4627, cost 0.0002 USD, build file judge `jev-1.13.0` calls 7, tokens in 6319, cost 0.0003 USD, config: defaults + host + repository (.werkrevisor.toml at main c62bde6).

Reviewed head `e9a68154a014cc4d5f2ce5efc1cc522a1ff88092` against base `c62bde6bdb3294b1f3cebdc6434193cc4f8aa648`, werkrevisor 0.21.3.}

<details><summary>🟡 werkrevisor YELLOW for <code>e9a6815</code>, superseded by <a href="http://git.javagil.de/mi/werkrevisor/pulls/44#issuecomment-1885">the result for <code>e64813e</code></a></summary> ## 🟡 werkrevisor: YELLOW / HUMAN_REVIEW Change kind: `mixed`. ### Reasons - **YELLOW** spec: docs/prs/2026-10-07-PR#44-writing-line-comments.md Scenario#44.02 given_when_then_misused (0.62 > yellow_above = 0.6) - **hint** 6 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) ### Classifier | Unit | Question | Problem | Confidence | Verdict | |---|---|---|---|---| | docs/prs/2026-10-07-PR#44-writing-line-comments.md Scenario#44.02 | given_when_then_misused | 0.62 | – | YELLOW | 5 of 6 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 45745, calls 1, tokens in 44282 / out 21445 (reasoning included in out), duration 156.7 s, cost 0.0366 USD (reported), classifier `jev-1.13.0` calls 6, tokens in 4627, cost 0.0002 USD, build file judge `jev-1.13.0` calls 7, tokens in 6319, cost 0.0003 USD, config: defaults + host + repository (.werkrevisor.toml at main c62bde6). Reviewed head `e9a68154a014cc4d5f2ce5efc1cc522a1ff88092` against base `c62bde6bdb3294b1f3cebdc6434193cc4f8aa648`, werkrevisor 0.21.3. </details>

claude-code commented

2026-10-07 14:28:27 +02:00

Reworded with @mi in e64813e: the feature defines a hint, Scenario#44.02 covers a resolved hint of any source, with one state per Given line and one event in When, verified by the writing test and the hint test of PR#32; the writing test now also asserts the held merge before the hint is resolved.

Reworded with @mi in e64813e: the feature defines a hint, Scenario#44.02 covers a resolved hint of any source, with one state per Given line and one event in When, verified by the writing test and the hint test of PR#32; the writing test now also asserts the held merge before the hint is resolved.

mi added 1 commit 2026-10-07 14:28:28 +02:00

review: Scenario#44.02 speaks of a hint in general, with Given states and one When; the test checks the held merge first

werkator build succeeded after 00:08

Details

werkator/werkrevisor-statistics build succeeded after 00:25

Details

ai-review/assessment AI review passed; approved by werkrevisor; merge already scheduled; review request of mi withdrawn

Details

ai-review/gate build succeeded after 01:30

Details

e64813e1bf

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

ai-reviewer commented

2026-10-07 14:29:57 +02:00

🟢 werkrevisor: GREEN / PASS

Change kind: mixed.

Reasons

hint 6 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)

Classifier

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

_{Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 45971, calls 1, tokens in 44506 / out 16389 (reasoning included in out), duration 88.7 s, cost 0.0330 USD (reported), classifier `jev-1.13.0` calls 7, tokens in 5359, cost 0.0002 USD, build file judge `jev-1.13.0` calls 7, tokens in 6355, cost 0.0003 USD, config: defaults + host + repository (.werkrevisor.toml at main c62bde6).

Reviewed head `e64813e1bf7ebac0c6678076685c20628817b04d` against base `c62bde6bdb3294b1f3cebdc6434193cc4f8aa648`, werkrevisor 0.21.3.}

## 🟢 werkrevisor: GREEN / PASS Change kind: `mixed`. ### Reasons - **hint** 6 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) ### Classifier 7 of 7 units passed all questions (1 PR document(s)). 3 answers ignored because of a confidence below [classifier] min_confidence. Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 45971, calls 1, tokens in 44506 / out 16389 (reasoning included in out), duration 88.7 s, cost 0.0330 USD (reported), classifier `jev-1.13.0` calls 7, tokens in 5359, cost 0.0002 USD, build file judge `jev-1.13.0` calls 7, tokens in 6355, cost 0.0003 USD, config: defaults + host + repository (.werkrevisor.toml at main c62bde6). Reviewed head `e64813e1bf7ebac0c6678076685c20628817b04d` against base `c62bde6bdb3294b1f3cebdc6434193cc4f8aa648`, werkrevisor 0.21.3.

ai-reviewer approved these changes

2026-10-07 14:29:57 +02:00

ai-reviewer left a comment

werkrevisor: GREEN / PASS for e64813e1bf7ebac0c6678076685c20628817b04d.
The result comment of werkrevisor holds the details.

werkrevisor: GREEN / PASS for `e64813e1bf7ebac0c6678076685c20628817b04d`. The result comment of werkrevisor holds the details.

ai-reviewer removed review request for mi 2026-10-07 14:29:58 +02:00

ai-reviewer merged commit adcb1f1e41 into main

2026-10-07 14:29:59 +02:00

ai-reviewer deleted branch claude-code/writing-line-comments

2026-10-07 14:29:59 +02:00

Sign in to join this conversation.

3 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: mi/werkrevisor#44

				`@@ -194,11 +194,14 @@ def find_violations(files, diffs, fetch, config):`


				`def writing_reasons(files, diffs, fetch, config):`