Du bist dran shows the author session of a stuck agent pull request #74

Merged

ai-reviewer merged 10 commits from claude-code/wake-session into main 2026-10-14 18:26:18 +02:00

Conversation 3 Commits 10 Files Changed 19

+552 -10

claude-code commented 2026-10-14 16:19:21 +02:00

Collaborator

Copy Link

Copy Source

See doc/prs/ for the PR document.

🤖 Generated with Claude Code

See doc/prs/ for the PR document. 🤖 Generated with [Claude Code](https://claude.com/claude-code)

claude-code added 1 commit 2026-10-14 16:19:22 +02:00

PR document: the relay resumes a resting agent session whose pull request needs it ... 1613ec6246

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

claude-code added 1 commit 2026-10-14 16:19:24 +02:00

PR document named after PR#74 ... c2f662de6c

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

claude-code changed title from WIP: The relay resumes a resting agent session whose pull request needs it to WIP: Du bist dran shows the author session of a stuck agent pull request 2026-10-14 16:34:01 +02:00

claude-code added 1 commit 2026-10-14 16:34:01 +02:00

PR document: Du bist dran shows the author session; the automatic resume is dropped after the probe ... 13052e1bbb

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

claude-code added 1 commit 2026-10-14 16:37:49 +02:00

Du bist dran shows the author session of a stuck agent pull request ... 6d75f2beee

The relay reports each session by the branch it last worked on, older than the window too;
the snapshot attaches the latest one in a checkout of the repository to a stuck pull request,
with a message to copy.

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

claude-code added 1 commit 2026-10-14 16:38:27 +02:00

Version 0.45.0; README, PR document and plan for the author session ... ad8018df45

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

claude-code added 1 commit 2026-10-14 16:45:56 +02:00

The branch of a transcript in a class of its own; terminal sessions tested; no demo yet ... c0d9bc1fde

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

claude-code added 1 commit 2026-10-14 17:56:10 +02:00

Merge main with PR#75; version 0.46.0 ... e297bef909

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

claude-code added 1 commit 2026-10-14 18:06:45 +02:00

The head branch of a pull request read once; the fetch test expects it ... 6fc470b162

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

claude-code added 1 commit 2026-10-14 18:07:18 +02:00

Merge main with PR#76; version 0.47.0 ... b9416022de

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

claude-code marked the pull request as ready for review 2026-10-14 18:18:15 +02:00

ai-reviewer commented 2026-10-14 18:21:10 +02:00

Collaborator

Copy Link

Copy Source

🟡 werkrevisor YELLOW for b941602, superseded by the result for 1ccf426

🟡 werkrevisor: YELLOW / HUMAN_REVIEW

Change kind: mixed.

Reasons

• YELLOW spec: doc/prs/2026-10-14-PR#74-wake-session.md section 'Follow-up PRs' hard_to_understand (0.60 > yellow_above = 0.5)
• hint 15 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 4 changed files were given to the AI only as diff, not in full, so it could not check them against the rest of their file (all full files together would exceed [review] max_full_files_chars = 160000, and no excerpt fits the limits either): dashboard/src/test/kotlin/de/hoennig/werkregie/dashboard/relay/RelayClientTest.kt, dashboard/src/test/kotlin/de/hoennig/werkregie/dashboard/sources/ClaudeCodeSourceTest.kt, dashboard/src/test/kotlin/de/hoennig/werkregie/dashboard/sources/GiteaSourceFetchTest.kt and 1 more (advisory: Jev judged every changed file)

Classifier

Unit	Question	Problem	Confidence	Verdict
doc/prs/2026-10-14-PR#74-wake-session.md section 'Follow-up PRs'	hard_to_understand	0.60	0.68	YELLOW

13 of 14 units passed all questions (1 PR document(s)).
6 answers ignored because of a confidence below [classifier] min_confidence.

_{Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 70987, calls 1, tokens in 68577 / out 21404 (reasoning included in out), duration 172.4 s, cost 0.0462 USD (reported), classifier `jev-1.13.0` calls 14, tokens in 11612, cost 0.0005 USD, excerpt selection `openrouter/openai/gpt-6-luna` calls 5, tokens in 51888 / out 617, cost 0.0068 USD (reported), build file judge `jev-1.13.0` calls 16, tokens in 22416, cost 0.0009 USD, phases: path_judge 1.0 s, classifier 0.9 s, context 13.4 s, model_review 156.7 s, config: defaults + host + repository (.werkrevisor.toml at main 97e974b).
Reviewed head `b9416022de245eb3f873edc8981466bf3a4e59e2` against base `97e974bc8147a4699e95095bb6356050a21315f1`, werkrevisor 0.41.2.}

<!-- werkrevisor:b9416022de245eb3f873edc8981466bf3a4e59e2 --> <!-- werkrevisor-verdict:YELLOW --> <!-- werkrevisor-blocks:6c58e3929c5b6c13b08639525beee62f,0efc1e11d3251668a36859ce5bcd983a,ce00ceb618cbecc1419eb110bd3931ee,537b671de8d88e9c856d361337fcdf50,b7aaba5d22a92808233b0bc342965313,9d1f4de8843e8e4447166f142508c86b,fb59c215c1ccadbd4376c10c427b70c1,93b900c30308558e212cb3737c82c06d,bba90ecb31fbe9ceba418f70d5a48734,0b84eb81ad8c3a8f43fe4b719f78a6f0,7fa2d579c58c5909ae932eb227964b95,859d9d7bcb5f25de66477e37703ad8a4,df875a455bc130b44db180eac2d599bf,fc2ff9e2a74658a550f34b9e21ce2a03,f22c25a6271be856181b5f2a286a47a9,48a2a9dcff0c7823579c3ec3a717c888,39735a12c75b879ec452c16112bcd54e,c8f3c46ba91f7bc4cc9b61ae30d7658b,649456a132370fc4676c43db71088c69,8d49bd1805bccfdcdbce392471d4ed23,836ca5b206c9b59bb7c5d333da441c6a,e7737e5114cab10931e520ea82f8ebaf,dcff245d302294503efdcea0fc5814ef,475e86079d529d9a39ef63c89fe18ee2,a52dac158c223d34a722a26ee47fa4c7,2f78d6fe27bc9649a1c1729ca34d2348,d11426539c09d5e288870b473aa2c32a,09c8e86bdde7fe02708a74cedcecc184,4f3eba8e585d2310f591ba8f2dda7408,492a7b6e90a281b080f62484aac5211d,d2539dd27e2289a296c7738770e562f9,23aa6bada4c1452afed0c4d4e98ed6bd,97c02495c96c26a080076f46dac31a39,5e708fd4e695ce632a26fa43b25094e6,634c72ebdc6618df29897394c788a7f9,3dc1f956350905412b0e8cd827189134,b6af552c2af855919c161a246bad9d8e,857714da29a17dc19f0033ceeb5f559b,408bde5951876ce8eb59b342d37c4e3a,2aa0017c6f55da0935bc9485302cebad,b6b55ac5bafae83ac0ba73cfdde3e07a --> <!-- werkrevisor-folded --> <details><summary>🟡 werkrevisor YELLOW for <code>b941602</code>, superseded by <a href="http://git.javagil.de/mi/werkregie/pulls/74#issuecomment-5727">the result for <code>1ccf426</code></a></summary> ## 🟡 werkrevisor: YELLOW / HUMAN_REVIEW Change kind: `mixed`. ### Reasons - **YELLOW** spec: doc/prs/2026-10-14-PR#74-wake-session.md section 'Follow-up PRs' hard_to_understand (0.60 > yellow_above = 0.5) - **hint** 15 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** 4 changed files were given to the AI only as diff, not in full, so it could not check them against the rest of their file (all full files together would exceed [review] max_full_files_chars = 160000, and no excerpt fits the limits either): dashboard/src/test/kotlin/de/hoennig/werkregie/dashboard/relay/RelayClientTest.kt, dashboard/src/test/kotlin/de/hoennig/werkregie/dashboard/sources/ClaudeCodeSourceTest.kt, dashboard/src/test/kotlin/de/hoennig/werkregie/dashboard/sources/GiteaSourceFetchTest.kt and 1 more (advisory: Jev judged every changed file) ### Classifier | Unit | Question | Problem | Confidence | Verdict | |---|---|---|---|---| | doc/prs/2026-10-14-PR#74-wake-session.md section 'Follow-up PRs' | hard_to_understand | 0.60 | 0.68 | YELLOW | 13 of 14 units passed all questions (1 PR document(s)). 6 answers ignored because of a confidence below [classifier] min_confidence. _{Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 70987, calls 1, tokens in 68577 / out 21404 (reasoning included in out), duration 172.4 s, cost 0.0462 USD (reported), classifier `jev-1.13.0` calls 14, tokens in 11612, cost 0.0005 USD, excerpt selection `openrouter/openai/gpt-6-luna` calls 5, tokens in 51888 / out 617, cost 0.0068 USD (reported), build file judge `jev-1.13.0` calls 16, tokens in 22416, cost 0.0009 USD, phases: path_judge 1.0 s, classifier 0.9 s, context 13.4 s, model_review 156.7 s, config: defaults + host + repository (.werkrevisor.toml at main 97e974b).<br> Reviewed head `b9416022de245eb3f873edc8981466bf3a4e59e2` against base `97e974bc8147a4699e95095bb6356050a21315f1`, werkrevisor 0.41.2.} </details>

ai-reviewer scheduled this pull request to auto merge when all checks succeed 2026-10-14 18:21:10 +02:00

ai-reviewer requested review from mi 2026-10-14 18:21:10 +02:00

claude-code added 1 commit 2026-10-14 18:21:40 +02:00

PR document: the follow-up PRs said in full sentences ... 1ccf426204

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

ai-reviewer commented 2026-10-14 18:24:17 +02:00

Collaborator

Copy Link

Copy Source

🟢 werkrevisor: GREEN / PASS

Change kind: mixed.

Reasons

• hint 15 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 1 changed file was given to the AI as excerpt of the selected lines and 5 lines around each changed line, not in full (all full files together would exceed [review] max_full_files_chars = 160000): dashboard/src/test/kotlin/de/hoennig/werkregie/dashboard/relay/RelayClientTest.kt
• hint 4 changed files were given to the AI only as diff, not in full, so it could not check them against the rest of their file (all full files together would exceed [review] max_full_files_chars = 160000, and no excerpt fits the limits either): dashboard/src/test/kotlin/de/hoennig/werkregie/dashboard/AuthorsTest.kt, dashboard/src/test/kotlin/de/hoennig/werkregie/dashboard/sources/ClaudeCodeSourceTest.kt, dashboard/src/test/kotlin/de/hoennig/werkregie/dashboard/sources/GiteaSourceFetchTest.kt and 1 more (advisory: Jev judged every changed file)

Classifier

14 of 14 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 71352, calls 1, tokens in 68933 / out 10299 (reasoning included in out), duration 155.7 s, cost 0.0330 USD (reported), classifier `jev-1.13.0` calls 14, tokens in 11664, cost 0.0005 USD, excerpt selection `openrouter/openai/gpt-6-luna` calls 6, tokens in 54915 / out 1290, cost 0.0015 USD (reported), build file judge `jev-1.13.0` calls 16, tokens in 22416, cost 0.0009 USD, phases: path_judge 1.0 s, classifier 0.9 s, context 22.4 s, model_review 130.8 s, config: defaults + host + repository (.werkrevisor.toml at main 97e974b).
Reviewed head `1ccf426204760eedb6e8f049ca00532a3cbbfe5c` against base `97e974bc8147a4699e95095bb6356050a21315f1`, werkrevisor 0.41.2.}

<!-- werkrevisor:1ccf426204760eedb6e8f049ca00532a3cbbfe5c --> <!-- werkrevisor-verdict:GREEN --> <!-- werkrevisor-blocks:6c58e3929c5b6c13b08639525beee62f,0efc1e11d3251668a36859ce5bcd983a,ce00ceb618cbecc1419eb110bd3931ee,537b671de8d88e9c856d361337fcdf50,b7aaba5d22a92808233b0bc342965313,9d1f4de8843e8e4447166f142508c86b,fb59c215c1ccadbd4376c10c427b70c1,93b900c30308558e212cb3737c82c06d,bba90ecb31fbe9ceba418f70d5a48734,0b84eb81ad8c3a8f43fe4b719f78a6f0,7fa2d579c58c5909ae932eb227964b95,859d9d7bcb5f25de66477e37703ad8a4,df875a455bc130b44db180eac2d599bf,fc2ff9e2a74658a550f34b9e21ce2a03,f22c25a6271be856181b5f2a286a47a9,48a2a9dcff0c7823579c3ec3a717c888,39735a12c75b879ec452c16112bcd54e,c8f3c46ba91f7bc4cc9b61ae30d7658b,649456a132370fc4676c43db71088c69,8d49bd1805bccfdcdbce392471d4ed23,836ca5b206c9b59bb7c5d333da441c6a,e7737e5114cab10931e520ea82f8ebaf,dcff245d302294503efdcea0fc5814ef,475e86079d529d9a39ef63c89fe18ee2,a52dac158c223d34a722a26ee47fa4c7,2f78d6fe27bc9649a1c1729ca34d2348,d11426539c09d5e288870b473aa2c32a,09c8e86bdde7fe02708a74cedcecc184,4f3eba8e585d2310f591ba8f2dda7408,492a7b6e90a281b080f62484aac5211d,d2539dd27e2289a296c7738770e562f9,23aa6bada4c1452afed0c4d4e98ed6bd,97c02495c96c26a080076f46dac31a39,5e708fd4e695ce632a26fa43b25094e6,634c72ebdc6618df29897394c788a7f9,3dc1f956350905412b0e8cd827189134,b6af552c2af855919c161a246bad9d8e,857714da29a17dc19f0033ceeb5f559b,d7c3494ff003af9c3df7a14b2530be95,2aa0017c6f55da0935bc9485302cebad,b6b55ac5bafae83ac0ba73cfdde3e07a --> ## 🟢 werkrevisor: GREEN / PASS Change kind: `mixed`. ### Reasons - **hint** 15 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** 1 changed file was given to the AI as excerpt of the selected lines and 5 lines around each changed line, not in full (all full files together would exceed [review] max_full_files_chars = 160000): dashboard/src/test/kotlin/de/hoennig/werkregie/dashboard/relay/RelayClientTest.kt - **hint** 4 changed files were given to the AI only as diff, not in full, so it could not check them against the rest of their file (all full files together would exceed [review] max_full_files_chars = 160000, and no excerpt fits the limits either): dashboard/src/test/kotlin/de/hoennig/werkregie/dashboard/AuthorsTest.kt, dashboard/src/test/kotlin/de/hoennig/werkregie/dashboard/sources/ClaudeCodeSourceTest.kt, dashboard/src/test/kotlin/de/hoennig/werkregie/dashboard/sources/GiteaSourceFetchTest.kt and 1 more (advisory: Jev judged every changed file) ### Classifier 14 of 14 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 71352, calls 1, tokens in 68933 / out 10299 (reasoning included in out), duration 155.7 s, cost 0.0330 USD (reported), classifier `jev-1.13.0` calls 14, tokens in 11664, cost 0.0005 USD, excerpt selection `openrouter/openai/gpt-6-luna` calls 6, tokens in 54915 / out 1290, cost 0.0015 USD (reported), build file judge `jev-1.13.0` calls 16, tokens in 22416, cost 0.0009 USD, phases: path_judge 1.0 s, classifier 0.9 s, context 22.4 s, model_review 130.8 s, config: defaults + host + repository (.werkrevisor.toml at main 97e974b).<br> Reviewed head `1ccf426204760eedb6e8f049ca00532a3cbbfe5c` against base `97e974bc8147a4699e95095bb6356050a21315f1`, werkrevisor 0.41.2.}

ai-reviewer approved these changes 2026-10-14 18:24:17 +02:00

ai-reviewer left a comment

Collaborator

Copy Link

Copy Source

werkrevisor: GREEN / PASS for 1ccf426204760eedb6e8f049ca00532a3cbbfe5c.
The result comment of werkrevisor holds the details.

werkrevisor: GREEN / PASS for `1ccf426204760eedb6e8f049ca00532a3cbbfe5c`. The result comment of werkrevisor holds the details. <!-- werkrevisor-review:1ccf426204760eedb6e8f049ca00532a3cbbfe5c -->

ai-reviewer removed review request for mi 2026-10-14 18:24:17 +02:00

ai-reviewer merged commit 28579c4fe9 into main 2026-10-14 18:26:18 +02:00

ai-reviewer deleted branch claude-code/wake-session 2026-10-14 18:26:18 +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

2 Participants

Notifications

Subscribe

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: mi/werkregie#74