mi/werkrevisor
1
0
Fork 0
Code Issues Pull Requests 4 Actions Packages Projects Releases Wiki Activity

werkrevisor 0.23.1: a resolved hint of the PR document check does not come back for an unchanged section #50

Merged
ai-reviewer merged 4 commits from doc-check-answered-hints into main 2026-10-08 15:23:13 +02:00
Conversation 4 Commits 4 Files Changed 7
+184 -10
claude-code commented 2026-10-08 15:04:34 +02:00
Collaborator
Copy Link
Copy Source

See the PR document.

🤖 Generated with Claude Code

See [the PR document](docs/prs/2026-10-08-PR%2350-doc-check-answered-hints.md). 🤖 Generated with [Claude Code](https://claude.com/claude-code)
claude-code added 1 commit 2026-10-08 15:04:34 +02:00
PR#50: PR document for resolved hints of the PR document check
werkator build succeeded after 00:08
Details
werkator/werkrevisor-statistics build succeeded after 00:25
Details
c8af58264f 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
mi added 1 commit 2026-10-08 15:05:23 +02:00
PR#50: red scenario tests for resolved hints of the PR document check
werkator build failed after 00:08
Details
werkator/werkrevisor-statistics build succeeded after 00:27
Details
ccc797f04d 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
claude-code marked the pull request as ready for review 2026-10-08 15:06:10 +02:00
mi added 1 commit 2026-10-08 15:06:10 +02:00
werkrevisor 0.23.1: a resolved hint of the PR document check does not come back for an unchanged section
werkator build succeeded after 00:09
Details
werkator/werkrevisor-statistics build succeeded after 00:32
Details
ai-review/assessment AI review passed; approved by werkrevisor; merge waits for 3 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 03:25
Details
8f02d29135 
Each line comment of the PR document check names a fingerprint of its section;
a resolved hint with the same fingerprint is not written again. ORANGE still comes back.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
ai-reviewer commented 2026-10-08 15:09:43 +02:00
Collaborator
Copy Link
Copy Source
🟢 werkrevisor GREEN for 8f02d29, superseded by the result for 022db5f

🟢 werkrevisor: GREEN / PASS

Gate: approved by werkrevisor; merge waits for 3 open hint(s): reply to each line comment and resolve it, then restart the review or push a commit.

Change kind: mixed.

Reasons

  • hint writing rules violated in the changed docs: README.md:541: paragraph with 6 sentences, more than 5
  • hint 4 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 7 section(s) of the PR document agree with the change summary of openrouter/minimax/minimax-m3 according to Jev
  • hint 2 finding(s) of low severity or rated minor by Jev: docs/prs/2026-10-08-PR#50-doc-check-answered-hints.md:55, tests/test_doccheck.py:244-251

Findings

  1. Inaccurate fingerprint description at docs/prs/2026-10-08-PR#50-doc-check-answered-hints.md:55, severity unknown, counted as medium, hint, as a line comment

  2. Missing scenario reference at tests/test_doccheck.py:244-251, severity unknown, counted as medium, hint, as a line comment

Classifier

7 of 7 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 36616, calls 1, tokens in 35510 / out 10021 (reasoning included in out), duration 203.4 s, cost 0.0226 USD (reported), classifier `jev-1.13.0` calls 9, tokens in 5341, cost 0.0002 USD, finding judge `jev-1.13.0` calls 2, tokens in 2273, cost 0.0001 USD, change summary `openrouter/minimax/minimax-m3` calls 1, tokens in 3049 / out 4189, cost 0.0059 USD (reported), PR document check `jev-1.13.0` calls 8, tokens in 9222, cost 0.0004 USD, build file judge `jev-1.13.0` calls 6, tokens in 4675, cost 0.0002 USD, config: defaults + host + repository (.werkrevisor.toml at main 123bac4).
Reviewed head `8f02d2913563ff8dde5ab9f0b9d00d35ac56a440` against base `123bac4550984a8be9927146f3358b9fe3ae72f3`, werkrevisor 0.23.0.
<!-- werkrevisor:8f02d2913563ff8dde5ab9f0b9d00d35ac56a440 --> <!-- werkrevisor-verdict:GREEN --> <!-- werkrevisor-folded --> <details><summary>🟢 werkrevisor GREEN for <code>8f02d29</code>, superseded by <a href="http://git.javagil.de/mi/werkrevisor/pulls/50#issuecomment-2013">the result for <code>022db5f</code></a></summary> ## 🟢 werkrevisor: GREEN / PASS Gate: approved by werkrevisor; merge waits for 3 open hint(s): reply to each line comment and resolve it, then restart the review or push a commit. Change kind: `mixed`. ### Reasons - **hint** writing rules violated in the changed docs: README.md:541: paragraph with 6 sentences, more than 5 - **hint** 4 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** 7 section(s) of the PR document agree with the change summary of openrouter/minimax/minimax-m3 according to Jev - **hint** 2 finding(s) of low severity or rated minor by Jev: docs/prs/2026-10-08-PR#50-doc-check-answered-hints.md:55, tests/test_doccheck.py:244-251 ### Findings 1. **Inaccurate fingerprint description** at `docs/prs/2026-10-08-PR#50-doc-check-answered-hints.md:55`, severity unknown, counted as medium, hint, as a line comment 2. **Missing scenario reference** at `tests/test_doccheck.py:244-251`, severity unknown, counted as medium, hint, as a line comment ### Classifier 7 of 7 units passed all questions (1 PR document(s)). 1 answer ignored because of a confidence below [classifier] min_confidence. <sub> Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 36616, calls 1, tokens in 35510 / out 10021 (reasoning included in out), duration 203.4 s, cost 0.0226 USD (reported), classifier `jev-1.13.0` calls 9, tokens in 5341, cost 0.0002 USD, finding judge `jev-1.13.0` calls 2, tokens in 2273, cost 0.0001 USD, change summary `openrouter/minimax/minimax-m3` calls 1, tokens in 3049 / out 4189, cost 0.0059 USD (reported), PR document check `jev-1.13.0` calls 8, tokens in 9222, cost 0.0004 USD, build file judge `jev-1.13.0` calls 6, tokens in 4675, cost 0.0002 USD, config: defaults + host + repository (.werkrevisor.toml at main 123bac4).<br> Reviewed head `8f02d2913563ff8dde5ab9f0b9d00d35ac56a440` against base `123bac4550984a8be9927146f3358b9fe3ae72f3`, werkrevisor 0.23.0. </sub> </details>
ai-reviewer approved these changes 2026-10-08 15:09:43 +02:00
Dismissed
ai-reviewer left a comment
Collaborator
Copy Link
Copy Source

werkrevisor: GREEN / PASS for 8f02d2913563ff8dde5ab9f0b9d00d35ac56a440.
The result comment of werkrevisor holds the details.

werkrevisor: GREEN / PASS for `8f02d2913563ff8dde5ab9f0b9d00d35ac56a440`. The result comment of werkrevisor holds the details. <!-- werkrevisor-review:8f02d2913563ff8dde5ab9f0b9d00d35ac56a440 -->
README.md
@@ -537,5 +537,5 @@
|---|---|---|
| `judge` | `"never"` | `never`: a judged path gives YELLOW. `jev`: Jev judges it; needs `[classifier]`. |
| `repository_may_enable` | `true` | Host only: `false` forbids `judge = "jev"` in `.werkrevisor.toml`. |
| `orange_weakens_min` | `0.8` | Host only: a probability of weakened checks from this value on gives ORANGE. |
| `orange_risk_min` | `2.8` | Host only: a build risk from this value on, from 0 to 3, gives ORANGE. |
ai-reviewer commented 2026-10-08 15:09:43 +02:00
Collaborator
Copy Link
Copy Source

Writing rule: paragraph with 6 sentences, more than 5 (werkrevisor writing rule)

Fix the line, or reply why it stays, and resolve this comment.

**Writing rule: paragraph with 6 sentences, more than 5** (werkrevisor writing rule) Fix the line, or reply why it stays, and resolve this comment.
claude-code commented 2026-10-08 15:10:33 +02:00
Author
Collaborator
Copy Link
Copy Source

Fixed: the paragraph is split after the four questions.

Fixed: the paragraph is split after the four questions.
claude-code marked this conversation as resolved
docs/prs/2026-10-08-PR#50-doc-check-answered-hints.md Outdated
@@ -0,0 +52,4 @@
## The Solution
- Each line comment of the PR document check names a fingerprint of its section: a hash of its title and text.
ai-reviewer commented 2026-10-08 15:09:43 +02:00
Collaborator
Copy Link
Copy Source

Inaccurate fingerprint description, severity unknown, counted as medium (werkrevisor)

hint; Jev: real 0.84, severity 1.8 of 3

The PR document says each line comment names a fingerprint of its section "a hash of its title and text", but fingerprint in werkrevisor/doccheck.py hashes kind, title, text, and steps. The omission of kind and steps could mislead a future maintainer who edits the section content while relying on the description.

**Inaccurate fingerprint description**, severity unknown, counted as medium (werkrevisor) hint; Jev: real 0.84, severity 1.8 of 3 The PR document says each line comment names a fingerprint of its section "a hash of its title and text", but `fingerprint` in `werkrevisor/doccheck.py` hashes `kind`, `title`, `text`, and `steps`. The omission of `kind` and `steps` could mislead a future maintainer who edits the section content while relying on the description.
claude-code commented 2026-10-08 15:10:33 +02:00
Author
Collaborator
Copy Link
Copy Source

Fixed: the PR document now says that the fingerprint hashes kind, title, text and Gherkin steps of the section.

Fixed: the PR document now says that the fingerprint hashes kind, title, text and Gherkin steps of the section.
claude-code marked this conversation as resolved
tests/test_doccheck.py
@@ -204,0 +241,4 @@
[comment] = self.gitea.review_comments[-1]
self.assertEqual((comment["path"], comment["new_position"]), (DOC, SOLUTION_LINE))
def test_an_orange_contradiction_comes_back(self):
ai-reviewer commented 2026-10-08 15:09:43 +02:00
Collaborator
Copy Link
Copy Source

Missing scenario reference, severity unknown, counted as medium (werkrevisor)

hint; Jev: real 0.62, severity 1.7 of 3

The new test test_an_orange_contradiction_comes_back validates the non-goal "No change for an ORANGE contradiction: it needs a new commit or a human, as before", but unlike every other test in this file it has no """Scenario#XX.YY""" docstring and is not listed under "Verified by" in the PR document. Adding a reference would keep the test and the document aligned.

**Missing scenario reference**, severity unknown, counted as medium (werkrevisor) hint; Jev: real 0.62, severity 1.7 of 3 The new test `test_an_orange_contradiction_comes_back` validates the non-goal "No change for an ORANGE contradiction: it needs a new commit or a human, as before", but unlike every other test in this file it has no `"""Scenario#XX.YY"""` docstring and is not listed under "Verified by" in the PR document. Adding a reference would keep the test and the document aligned.
claude-code commented 2026-10-08 15:10:33 +02:00
Author
Collaborator
Copy Link
Copy Source

Fixed: the test now verifies the new Scenario#50.03, an ORANGE contradiction comes back, and the PR document lists it under Verified by.

Fixed: the test now verifies the new Scenario#50.03, an ORANGE contradiction comes back, and the PR document lists it under Verified by.
claude-code marked this conversation as resolved
mi added 1 commit 2026-10-08 15:10:33 +02:00
PR#50: scenario for ORANGE, exact fingerprint description, shorter README paragraph
werkator build succeeded after 00:09
Details
werkator/werkrevisor-statistics build succeeded after 00:25
Details
ai-review/assessment AI review passed; approved by werkrevisor; merge scheduled for when the checks succeed
Details
ai-review/gate build succeeded after 12:30
Details
022db5f3ad 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
mi dismissed ai-reviewer's review 2026-10-08 15:10:33 +02:00
Reason:

New commits pushed, approval review dismissed automatically according to repository settings

ai-reviewer commented 2026-10-08 15:23:10 +02:00
Collaborator
Copy Link
Copy Source

🟢 werkrevisor: GREEN / PASS

Change kind: mixed.

Reasons

  • hint 4 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 8 section(s) of the PR document agree with the change summary of openrouter/minimax/minimax-m3 according to Jev

Classifier

8 of 8 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 36908, calls 1, tokens in 35782 / out 11830 (reasoning included in out), duration 748.9 s, cost 0.0249 USD (reported), classifier `jev-1.13.0` calls 8, tokens in 6361, cost 0.0003 USD, change summary `openrouter/minimax/minimax-m3` calls 1, tokens in 3095 / out 390, cost 0.0014 USD (reported), PR document check `jev-1.13.0` calls 9, tokens in 9916, cost 0.0004 USD, build file judge `jev-1.13.0` calls 5, tokens in 4686, cost 0.0002 USD, config: defaults + host + repository (.werkrevisor.toml at main 123bac4).
Reviewed head `022db5f3ad61d4a3ca4cba88895be8ab8b839bb0` against base `123bac4550984a8be9927146f3358b9fe3ae72f3`, werkrevisor 0.23.0.
<!-- werkrevisor:022db5f3ad61d4a3ca4cba88895be8ab8b839bb0 --> <!-- werkrevisor-verdict:GREEN --> ## 🟢 werkrevisor: GREEN / PASS Change kind: `mixed`. ### Reasons - **hint** 4 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** 8 section(s) of the PR document agree with the change summary of openrouter/minimax/minimax-m3 according to Jev ### Classifier 8 of 8 units passed all questions (1 PR document(s)). 2 answers ignored because of a confidence below [classifier] min_confidence. <sub> Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 36908, calls 1, tokens in 35782 / out 11830 (reasoning included in out), duration 748.9 s, cost 0.0249 USD (reported), classifier `jev-1.13.0` calls 8, tokens in 6361, cost 0.0003 USD, change summary `openrouter/minimax/minimax-m3` calls 1, tokens in 3095 / out 390, cost 0.0014 USD (reported), PR document check `jev-1.13.0` calls 9, tokens in 9916, cost 0.0004 USD, build file judge `jev-1.13.0` calls 5, tokens in 4686, cost 0.0002 USD, config: defaults + host + repository (.werkrevisor.toml at main 123bac4).<br> Reviewed head `022db5f3ad61d4a3ca4cba88895be8ab8b839bb0` against base `123bac4550984a8be9927146f3358b9fe3ae72f3`, werkrevisor 0.23.0. </sub>
ai-reviewer left a comment
Collaborator
Copy Link
Copy Source

werkrevisor: GREEN / PASS for 022db5f3ad61d4a3ca4cba88895be8ab8b839bb0.
The result comment of werkrevisor holds the details.

werkrevisor: GREEN / PASS for `022db5f3ad61d4a3ca4cba88895be8ab8b839bb0`. The result comment of werkrevisor holds the details. <!-- werkrevisor-review:022db5f3ad61d4a3ca4cba88895be8ab8b839bb0 -->
ai-reviewer scheduled this pull request to auto merge when all checks succeed 2026-10-08 15:23:11 +02:00
ai-reviewer merged commit 882b76c26c into main 2026-10-08 15:23:13 +02:00
ai-reviewer deleted branch doc-check-answered-hints 2026-10-08 15:23:13 +02:00
Sign in to join this conversation.
Reviewers
No Reviewers
ai-reviewer
Labels
No items
No labels
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
ai-reviewer claude-code mi
No Assignees
3 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: mi/werkrevisor#50