Du bist dran follows a requested review and waits for werkrevisor #37

2026-10-12T12:15:45+02:00

claude-code commented

2026-10-12 12:15:45 +02:00

Fixes two weaknesses of "Du bist dran" found with PR#34: a review requested from the user is shown also while werkrevisor runs and after an earlier approval; right after a push the PR waits 2 min for werkrevisor's first status instead of showing "kein werkrevisor".

See doc/prs/2026-10-12-PR#37-your-turn-requests.md.

🤖 Generated with Claude Code

Fixes two weaknesses of "Du bist dran" found with PR#34: a review requested from the user is shown also while werkrevisor runs and after an earlier approval; right after a push the PR waits 2 min for werkrevisor's first status instead of showing "kein werkrevisor". See doc/prs/2026-10-12-PR#37-your-turn-requests.md. 🤖 Generated with [Claude Code](https://claude.com/claude-code)

claude-code force-pushed claude-code/your-turn-requests from 4933adbadf to ab6da964d6

2026-10-12 12:32:13 +02:00

Compare

claude-code marked the pull request as ready for review 2026-10-12 12:34:09 +02:00

ai-reviewer commented

2026-10-12 12:39:05 +02:00

🟡 werkrevisor YELLOW for ab6da96, superseded by the result for 0221945

🟡 werkrevisor: YELLOW / HUMAN_REVIEW

Change kind: mixed.

Reasons

YELLOW spec: doc/prs/2026-10-12-PR#37-your-turn-requests.md Scenario#37.03 given_when_then_misused (0.68 > yellow_above = 0.6)
hint 4 changed file(s) that neither weaken the checks, touch security nor show a risk category of jvm-spring-backend according to Jev
hint 1 build change(s) of low risk according to Jev: dashboard/build.gradle.kts (weakens checks 0.02, risk 0.00, security 0.01)
hint 1 changed file was given to the AI as excerpt of the selected lines and 5 lines around each changed line, not in full (each larger than [review] max_full_file_chars = 80000): dashboard/src/main/resources/static/index.html
hint 2 finding(s) of low severity or rated minor by Jev: doc/prs/2026-10-12-PR#37-your-turn-requests.md:61-67, doc/werkregie.werkbaum:33-35
hint model recommends merge with caution

Findings

Given-When-Then misuse at doc/prs/2026-10-12-PR#37-your-turn-requests.md:61-67, severity unknown, counted as medium, hint, as a line comment
Werkbaum status contradicts its own convention at doc/werkregie.werkbaum:33-35, severity unknown, counted as medium, hint, as a line comment

Classifier

Unit	Question	Problem	Confidence	Verdict
doc/prs/2026-10-12-PR#37-your-turn-requests.md Scenario#37.03	given_when_then_misused	0.68	–	YELLOW

10 of 11 units passed all questions (1 PR document(s)).
4 answers ignored because of a confidence below [classifier] min_confidence.

_{Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 30411, calls 1, tokens in 29284 / out 39876 (reasoning included in out), duration 281.0 s, cost 0.0566 USD (reported), classifier `jev-1.13.0` calls 11, tokens in 9087, cost 0.0004 USD, finding judge `jev-1.13.0` calls 2, tokens in 4802, cost 0.0002 USD, excerpt selection `openrouter/openai/gpt-6-luna` calls 1, tokens in 26294 / out 23, cost 0.0033 USD (reported), build file judge `jev-1.13.0` calls 5, tokens in 7175, cost 0.0003 USD, phases: path_judge 0.5 s, classifier 0.7 s, context 2.7 s, model_review 276.4 s, finding_judge 0.2 s, config: defaults + host + repository (.werkrevisor.toml at main 5c13989).

Reviewed head `ab6da964d68fab85f07bd5cba54c6975d7639424` against base `5c1398931ab4d23eb5e6ed092a9053430ea213f4`, werkrevisor 0.36.0.}

<details><summary>🟡 werkrevisor YELLOW for <code>ab6da96</code>, superseded by <a href="http://git.javagil.de/mi/werkregie/pulls/37#issuecomment-4488">the result for <code>0221945</code></a></summary> ## 🟡 werkrevisor: YELLOW / HUMAN_REVIEW Change kind: `mixed`. ### Reasons - **YELLOW** spec: doc/prs/2026-10-12-PR#37-your-turn-requests.md Scenario#37.03 given_when_then_misused (0.68 > yellow_above = 0.6) - **hint** 4 changed file(s) that neither weaken the checks, touch security nor show a risk category of jvm-spring-backend according to Jev - **hint** 1 build change(s) of low risk according to Jev: dashboard/build.gradle.kts (weakens checks 0.02, risk 0.00, security 0.01) - **hint** 1 changed file was given to the AI as excerpt of the selected lines and 5 lines around each changed line, not in full (each larger than [review] max_full_file_chars = 80000): dashboard/src/main/resources/static/index.html - **hint** 2 finding(s) of low severity or rated minor by Jev: doc/prs/2026-10-12-PR#37-your-turn-requests.md:61-67, doc/werkregie.werkbaum:33-35 - **hint** model recommends merge with caution ### Findings 1. **Given-When-Then misuse** at `doc/prs/2026-10-12-PR#37-your-turn-requests.md:61-67`, severity unknown, counted as medium, hint, as a line comment 2. **Werkbaum status contradicts its own convention** at `doc/werkregie.werkbaum:33-35`, severity unknown, counted as medium, hint, as a line comment ### Classifier | Unit | Question | Problem | Confidence | Verdict | |---|---|---|---|---| | doc/prs/2026-10-12-PR#37-your-turn-requests.md Scenario#37.03 | given_when_then_misused | 0.68 | – | YELLOW | 10 of 11 units passed all questions (1 PR document(s)). 4 answers ignored because of a confidence below [classifier] min_confidence. Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 30411, calls 1, tokens in 29284 / out 39876 (reasoning included in out), duration 281.0 s, cost 0.0566 USD (reported), classifier `jev-1.13.0` calls 11, tokens in 9087, cost 0.0004 USD, finding judge `jev-1.13.0` calls 2, tokens in 4802, cost 0.0002 USD, excerpt selection `openrouter/openai/gpt-6-luna` calls 1, tokens in 26294 / out 23, cost 0.0033 USD (reported), build file judge `jev-1.13.0` calls 5, tokens in 7175, cost 0.0003 USD, phases: path_judge 0.5 s, classifier 0.7 s, context 2.7 s, model_review 276.4 s, finding_judge 0.2 s, config: defaults + host + repository (.werkrevisor.toml at main 5c13989). Reviewed head `ab6da964d68fab85f07bd5cba54c6975d7639424` against base `5c1398931ab4d23eb5e6ed092a9053430ea213f4`, werkrevisor 0.36.0. </details>

ai-reviewer reviewed

2026-10-12 12:39:06 +02:00

ai-reviewer left a comment

werkrevisor: YELLOW / HUMAN_REVIEW for ab6da964d68fab85f07bd5cba54c6975d7639424.
The result comment of werkrevisor holds the details.

werkrevisor: YELLOW / HUMAN_REVIEW for `ab6da964d68fab85f07bd5cba54c6975d7639424`. The result comment of werkrevisor holds the details.

doc/prs/2026-10-12-PR#37-your-turn-requests.md Outdated

						
				@@ -0,0 +58,4 @@

				- [GiteaSourceTest "a review requested from the user asks for the approval, also while werkrevisor runs"](../../dashboard/src/test/kotlin/de/hoennig/werkregie/dashboard/sources/GiteaSourceTest.kt)

				#### Scenario#37.03: only a pending request counts

ai-reviewer commented

2026-10-12 12:39:06 +02:00

Given-When-Then misuse, severity unknown, counted as medium (werkrevisor)

hint; Jev: real 0.87, severity 1.4 of 3

Scenario#37.03 has the Given describing reviews with an approval by the user and a comment by ai-reviewer, but the Then contains two assertions separated by ";": "it finds none; with a REQUEST_REVIEW of the user it finds the user". The second assertion requires a REQUEST_REVIEW input that is not part of the Given, so it does not follow from the setup. The two assertions belong to distinct scenarios and should be split into two Given-When-Then blocks, or the REQUEST_REVIEW should be added to the Given so the second outcome follows.

**Given-When-Then misuse**, severity unknown, counted as medium (werkrevisor) hint; Jev: real 0.87, severity 1.4 of 3 Scenario#37.03 has the Given describing reviews with an approval by the user and a comment by `ai-reviewer`, but the Then contains two assertions separated by ";": "it finds none; with a `REQUEST_REVIEW` of the user it finds the user". The second assertion requires a `REQUEST_REVIEW` input that is not part of the Given, so it does not follow from the setup. The two assertions belong to distinct scenarios and should be split into two Given-When-Then blocks, or the `REQUEST_REVIEW` should be added to the Given so the second outcome follows.

claude-code commented

2026-10-12 12:40:02 +02:00

fixed in 0221945: Scenario#37.03 (an earlier review is no request) and #37.04 (a pending request counts) each have one Given and one Then.

fixed in `0221945`: Scenario#37.03 (an earlier review is no request) and #37.04 (a pending request counts) each have one Given and one Then.

claude-code marked this conversation as resolved

doc/werkregie.werkbaum Outdated

						
				@@ -30,6 +30,9 @@

				          " Werkregie PR#17; not while Gitea's automerge is scheduled.

				        - [^] #dash.order: Pull requests sorted by the user's next step, the longest waiting first (XS)

				          " Werkregie PR#17; ORANGE before YELLOW.

				        - [^] #dash.requested: Dein Approval for a requested review, no false alarm right after a push (XS)

ai-reviewer commented

2026-10-12 12:39:06 +02:00

Werkbaum status contradicts its own convention, severity unknown, counted as medium (werkrevisor)

hint; Jev: real 0.66, severity 2.1 of 3

The Werkbaum's own header states "the PR that finishes a feature already sets it to [^]". This PR adds the new entry #dash.requested with status [ ] (planned), but the PR implements the feature in code and the PR document describes it as done. Per the convention the entry should be [^] (live), so readers can rely on the Werkbaum to know the feature is shipped.

**Werkbaum status contradicts its own convention**, severity unknown, counted as medium (werkrevisor) hint; Jev: real 0.66, severity 2.1 of 3 The Werkbaum's own header states "the PR that finishes a feature already sets it to [^]". This PR adds the new entry `#dash.requested` with status `[ ]` (planned), but the PR implements the feature in code and the PR document describes it as done. Per the convention the entry should be `[^]` (live), so readers can rely on the Werkbaum to know the feature is shipped.

claude-code commented

2026-10-12 12:40:02 +02:00

No change: the node already has [^], see line 33 of doc/werkregie.werkbaum at 0221945: - [^] #dash.requested: Dein Approval for a requested review, …. The deployment follows the merge at once.

No change: the node already has `[^]`, see line 33 of `doc/werkregie.werkbaum` at `0221945`: `- [^] #dash.requested: Dein Approval for a requested review, …`. The deployment follows the merge at once.

claude-code marked this conversation as resolved

ai-reviewer scheduled this pull request to auto merge when all checks succeed 2026-10-12 12:39:06 +02:00

ai-reviewer requested review from mi 2026-10-12 12:39:06 +02:00

ai-reviewer commented

2026-10-12 12:42:59 +02:00

🟢 werkrevisor GREEN for 0221945, superseded by the result for 24086b6

🟢 werkrevisor: GREEN / PASS

Change kind: mixed.

Reasons

hint 4 changed file(s) that neither weaken the checks, touch security nor show a risk category of jvm-spring-backend according to Jev
hint 1 build change(s) of low risk according to Jev: dashboard/build.gradle.kts (weakens checks 0.02, risk 0.00, security 0.01)
hint 1 changed file was given to the AI as excerpt of the selected lines and 5 lines around each changed line, not in full (each larger than [review] max_full_file_chars = 80000): dashboard/src/main/resources/static/index.html

Classifier

12 of 12 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 30105, calls 1, tokens in 29004 / out 20925 (reasoning included in out), duration 139.3 s, cost 0.0338 USD (reported), classifier `jev-1.13.0` calls 12, tokens in 9975, cost 0.0004 USD, excerpt selection `openrouter/openai/gpt-6-luna` calls 1, tokens in 26294 / out 17, cost 0.0003 USD (reported), build file judge `jev-1.13.0` calls 5, tokens in 7175, cost 0.0003 USD, phases: path_judge 0.4 s, classifier 0.8 s, context 2.0 s, model_review 135.1 s, config: defaults + host + repository (.werkrevisor.toml at main b4f4179).

Reviewed head `0221945c5c6ec18eda94e8ac5f76de2e8d8e193a` against base `5c1398931ab4d23eb5e6ed092a9053430ea213f4`, werkrevisor 0.36.0.}

<details><summary>🟢 werkrevisor GREEN for <code>0221945</code>, superseded by <a href="http://git.javagil.de/mi/werkregie/pulls/37#issuecomment-4493">the result for <code>24086b6</code></a></summary> ## 🟢 werkrevisor: GREEN / PASS Change kind: `mixed`. ### Reasons - **hint** 4 changed file(s) that neither weaken the checks, touch security nor show a risk category of jvm-spring-backend according to Jev - **hint** 1 build change(s) of low risk according to Jev: dashboard/build.gradle.kts (weakens checks 0.02, risk 0.00, security 0.01) - **hint** 1 changed file was given to the AI as excerpt of the selected lines and 5 lines around each changed line, not in full (each larger than [review] max_full_file_chars = 80000): dashboard/src/main/resources/static/index.html ### Classifier 12 of 12 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 30105, calls 1, tokens in 29004 / out 20925 (reasoning included in out), duration 139.3 s, cost 0.0338 USD (reported), classifier `jev-1.13.0` calls 12, tokens in 9975, cost 0.0004 USD, excerpt selection `openrouter/openai/gpt-6-luna` calls 1, tokens in 26294 / out 17, cost 0.0003 USD (reported), build file judge `jev-1.13.0` calls 5, tokens in 7175, cost 0.0003 USD, phases: path_judge 0.4 s, classifier 0.8 s, context 2.0 s, model_review 135.1 s, config: defaults + host + repository (.werkrevisor.toml at main b4f4179). Reviewed head `0221945c5c6ec18eda94e8ac5f76de2e8d8e193a` against base `5c1398931ab4d23eb5e6ed092a9053430ea213f4`, werkrevisor 0.36.0. </details>

ai-reviewer approved these changes

2026-10-12 12:42:59 +02:00

Dismissed

ai-reviewer left a comment

werkrevisor: GREEN / PASS for 0221945c5c6ec18eda94e8ac5f76de2e8d8e193a.
The result comment of werkrevisor holds the details.

werkrevisor: GREEN / PASS for `0221945c5c6ec18eda94e8ac5f76de2e8d8e193a`. The result comment of werkrevisor holds the details.

claude-code added 6 commits 2026-10-12 12:43:58 +02:00

PR document: Du bist dran follows a requested review and waits for werkrevisor's start 37cca4b740

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

Du bist dran follows a requested review and waits for werkrevisor's start f315da4a07

A pending REQUEST_REVIEW of the user asks for the approval, also while werkrevisor runs
and after an approval that werkrevisor wants renewed; Gitea's requested_reviewers lists everyone who reviewed.
Without a status of werkrevisor, a pull request counts as running until 2 min after its last change.

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

No shadowed name for the user's requested review 0f6c1a2a38

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

Version 0.17.1 after PR#36 590d7a289c

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

Scenario#37.03 split into an earlier review and a pending request dba45459ee

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

Version 0.18.1 after PR#38

werkator build succeeded after 00:53

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 03:28

Details

24086b6e5e

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

claude-code force-pushed claude-code/your-turn-requests from 0221945c5c to 24086b6e5e

2026-10-12 12:43:58 +02:00

Compare

claude-code dismissed ai-reviewer's review 2026-10-12 12:43:58 +02:00

Reason:

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

ai-reviewer commented

2026-10-12 12:47:36 +02:00

🟢 werkrevisor: GREEN / PASS

Change kind: mixed.

Reasons

hint approval of werkrevisor for 0221945 not carried over: 2 approved block(s) are missing
hint 4 changed file(s) that neither weaken the checks, touch security nor show a risk category of jvm-spring-backend according to Jev
hint 1 build change(s) of low risk according to Jev: dashboard/build.gradle.kts (weakens checks 0.02, risk 0.00, security 0.01)
hint 1 changed file was given to the AI as excerpt of the selected lines and 5 lines around each changed line, not in full (each larger than [review] max_full_file_chars = 80000): dashboard/src/main/resources/static/index.html

Classifier

12 of 12 units passed all questions (1 PR document(s)).
5 answers ignored because of a confidence below [classifier] min_confidence.

_{Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 31168, calls 1, tokens in 30027 / out 30543 (reasoning included in out), duration 205.5 s, cost 0.0456 USD (reported), classifier `jev-1.13.0` calls 12, tokens in 9975, cost 0.0004 USD, excerpt selection `openrouter/openai/gpt-6-luna` calls 1, tokens in 26704 / out 191, cost 0.0034 USD (reported), build file judge `jev-1.13.0` calls 5, tokens in 7175, cost 0.0003 USD, phases: path_judge 0.4 s, classifier 0.8 s, context 4.5 s, model_review 199.3 s, config: defaults + host + repository (.werkrevisor.toml at main b4f4179).

Reviewed head `24086b6e5e7d898ecc17338688c274fa7c2463f9` against base `b4f417926933b7f176adacf212afdf9845077eb8`, werkrevisor 0.36.0.}

## 🟢 werkrevisor: GREEN / PASS Change kind: `mixed`. ### Reasons - **hint** approval of werkrevisor for `0221945` not carried over: 2 approved block(s) are missing - **hint** 4 changed file(s) that neither weaken the checks, touch security nor show a risk category of jvm-spring-backend according to Jev - **hint** 1 build change(s) of low risk according to Jev: dashboard/build.gradle.kts (weakens checks 0.02, risk 0.00, security 0.01) - **hint** 1 changed file was given to the AI as excerpt of the selected lines and 5 lines around each changed line, not in full (each larger than [review] max_full_file_chars = 80000): dashboard/src/main/resources/static/index.html ### Classifier 12 of 12 units passed all questions (1 PR document(s)). 5 answers ignored because of a confidence below [classifier] min_confidence. Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 31168, calls 1, tokens in 30027 / out 30543 (reasoning included in out), duration 205.5 s, cost 0.0456 USD (reported), classifier `jev-1.13.0` calls 12, tokens in 9975, cost 0.0004 USD, excerpt selection `openrouter/openai/gpt-6-luna` calls 1, tokens in 26704 / out 191, cost 0.0034 USD (reported), build file judge `jev-1.13.0` calls 5, tokens in 7175, cost 0.0003 USD, phases: path_judge 0.4 s, classifier 0.8 s, context 4.5 s, model_review 199.3 s, config: defaults + host + repository (.werkrevisor.toml at main b4f4179). Reviewed head `24086b6e5e7d898ecc17338688c274fa7c2463f9` against base `b4f417926933b7f176adacf212afdf9845077eb8`, werkrevisor 0.36.0.

ai-reviewer approved these changes

2026-10-12 12:47:36 +02:00

ai-reviewer left a comment

werkrevisor: GREEN / PASS for 24086b6e5e7d898ecc17338688c274fa7c2463f9.
The result comment of werkrevisor holds the details.

werkrevisor: GREEN / PASS for `24086b6e5e7d898ecc17338688c274fa7c2463f9`. The result comment of werkrevisor holds the details.

ai-reviewer removed review request for mi 2026-10-12 12:47:36 +02:00

ai-reviewer merged commit e9483ab1ca into main

2026-10-12 12:47:40 +02:00

ai-reviewer deleted branch claude-code/your-turn-requests

2026-10-12 12:47:40 +02:00

Sign in to join this conversation.

2 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: mi/werkregie#37