werkrevisor 0.47.1: the Codex runner starts 1 minute after its last run #120

2026-10-17T14:46:42+02:00

claude-code commented

2026-10-17 14:46:42 +02:00

The timer of the Codex runner waits 1 minute instead of 5 after a run; each run reviews 1 PR.

🤖 Generated with Claude Code

The timer of the Codex runner waits 1 minute instead of 5 after a run; each run reviews 1 PR. 🤖 Generated with [Claude Code](https://claude.com/claude-code)

claude-code added 1 commit 2026-10-17 14:46:43 +02:00

PR document: the Codex runner starts 1 minute after its last run 10e5805942

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

claude-code added 1 commit 2026-10-17 14:46:44 +02:00

PR document: number 120

werkator build succeeded after 00:11

Details

werkator/werkrevisor-statistics build succeeded after 00:31

Details

6fc86d4a14

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

claude-code added 1 commit 2026-10-17 14:47:08 +02:00

werkrevisor 0.47.1: the Codex runner starts 1 minute after its last run

werkator build succeeded after 00:10

Details

werkator/werkrevisor-statistics build succeeded after 00:39

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 00:30

Details

ai-review/codex Codex review passed

ef93c9e061

max_reviews_per_run = 1, so each run sees the current heads.

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

claude-code marked the pull request as ready for review 2026-10-17 14:48:35 +02:00

ai-reviewer commented

2026-10-17 14:49:11 +02:00

🟢 werkrevisor GREEN for ef93c9e, superseded by the result for 0ed9065

🟢 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 4 changed file(s) that neither weaken the checks, touch security nor show a risk category of the repository config 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 0.02)
hint 5 section(s) of the PR document agree with the change summary of openrouter/minimax/minimax-m3, and its 5 change(s) belong to the PR document, according to Jev
hint 2 finding(s) of low severity or rated minor by Jev: docs/prs/2026-10-17-PR#120-codex-timer-1min.md:3, README.md:1526-1527

Findings

Version label mismatch at docs/prs/2026-10-17-PR#120-codex-timer-1min.md:3, severity unknown, counted as medium, hint, as a line comment
Awkward README wording at README.md:1526-1527, severity unknown, counted as medium

hint; Jev: real 0.86, severity 1.1 of 3

The rewritten bullet reads: "max_reviews_per_run bounds the reviews per run, so a run does not review heads that pushes replaced meanwhile". The clause "that pushes replaced meanwhile" is grammatically broken ("pushes" needs an object and a definite article, e.g. "that a push already replaced"). With the new value of 1, the explanation should also note that the bound is no longer about quota use (per the old text) but about keeping the view of heads fresh at run start.

Classifier

5 of 5 units passed all questions (1 PR document(s)).

_{Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 7791, calls 1, tokens in 7510 / out 3204 (reasoning included in out), duration 27.4 s, cost 0.0061 USD (reported), classifier `jev-1.13.0` calls 5, tokens in 3582, cost 0.0002 USD, finding judge `jev-1.13.0` calls 2, tokens in 3034, cost 0.0001 USD, change summary `openrouter/minimax/minimax-m3` via Minimax calls 1, tokens in 1223 / out 991, cost 0.0015 USD (reported), PR document check `jev-1.13.0` calls 10, tokens in 11712, cost 0.0005 USD, build file judge `jev-1.13.0` calls 5, tokens in 2944, cost 0.0001 USD, phases: path_judge 0.5 s, classifier 0.4 s, change_summary 5.1 s, doc_check 0.9 s, context 0.2 s, model_review 19.8 s, finding_judge 0.2 s, config: defaults + host + repository (.werkrevisor.toml at main 841bc82).

Reviewed head `ef93c9e061a87770c139bb6235c7f7cb27be8900` against base `841bc82867d7cb165175f6002430cf973fbb160f`, werkrevisor 0.46.0.}

<details><summary>🟢 werkrevisor GREEN for <code>ef93c9e</code>, superseded by <a href="http://git.javagil.de/mi/werkrevisor/pulls/120#issuecomment-6257">the result for <code>0ed9065</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** 4 changed file(s) that neither weaken the checks, touch security nor show a risk category of the repository config 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 0.02) - **hint** 5 section(s) of the PR document agree with the change summary of openrouter/minimax/minimax-m3, and its 5 change(s) belong to the PR document, according to Jev - **hint** 2 finding(s) of low severity or rated minor by Jev: docs/prs/2026-10-17-PR#120-codex-timer-1min.md:3, README.md:1526-1527 ### Findings 1. **Version label mismatch** at `docs/prs/2026-10-17-PR#120-codex-timer-1min.md:3`, severity unknown, counted as medium, hint, as a line comment 2. **Awkward README wording** at `README.md:1526-1527`, severity unknown, counted as medium hint; Jev: real 0.86, severity 1.1 of 3 The rewritten bullet reads: "`max_reviews_per_run` bounds the reviews per run, so a run does not review heads that pushes replaced meanwhile". The clause "that pushes replaced meanwhile" is grammatically broken ("pushes" needs an object and a definite article, e.g. "that a push already replaced"). With the new value of 1, the explanation should also note that the bound is no longer about quota use (per the old text) but about keeping the view of heads fresh at run start. ### Classifier 5 of 5 units passed all questions (1 PR document(s)). Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 7791, calls 1, tokens in 7510 / out 3204 (reasoning included in out), duration 27.4 s, cost 0.0061 USD (reported), classifier `jev-1.13.0` calls 5, tokens in 3582, cost 0.0002 USD, finding judge `jev-1.13.0` calls 2, tokens in 3034, cost 0.0001 USD, change summary `openrouter/minimax/minimax-m3` via Minimax calls 1, tokens in 1223 / out 991, cost 0.0015 USD (reported), PR document check `jev-1.13.0` calls 10, tokens in 11712, cost 0.0005 USD, build file judge `jev-1.13.0` calls 5, tokens in 2944, cost 0.0001 USD, phases: path_judge 0.5 s, classifier 0.4 s, change_summary 5.1 s, doc_check 0.9 s, context 0.2 s, model_review 19.8 s, finding_judge 0.2 s, config: defaults + host + repository (.werkrevisor.toml at main 841bc82). Reviewed head `ef93c9e061a87770c139bb6235c7f7cb27be8900` against base `841bc82867d7cb165175f6002430cf973fbb160f`, werkrevisor 0.46.0. </details>

ai-reviewer approved these changes

2026-10-17 14:49:11 +02:00

Dismissed

ai-reviewer left a comment

werkrevisor: GREEN / PASS for ef93c9e061a87770c139bb6235c7f7cb27be8900.
The result comment of werkrevisor holds the details.

werkrevisor: GREEN / PASS for `ef93c9e061a87770c139bb6235c7f7cb27be8900`. The result comment of werkrevisor holds the details.

docs/prs/2026-10-17-PR#120-codex-timer-1min.md

						
				@@ -0,0 +1,42 @@

				# PR#120: The Codex Runner Starts 1 Minute after Its Last Run

				Version: patch

ai-reviewer commented

2026-10-17 14:49:11 +02:00

Version label mismatch, severity unknown, counted as medium (werkrevisor)

hint; Jev: real 0.77, severity 1.2 of 3

The PR document declares "Version: patch", but the version is bumped from 0.46.0 to 0.47.1 in both werkrevisor/__init__.py and statistics/build.gradle.kts. In semver, changing the minor component (0.46 → 0.47) is a minor release, not a patch release. Either the label should be "minor", or the version should be 0.46.1 to match a pure patch bump. Without confirmation of the project's versioning convention, this remains a documented inconsistency.

**Version label mismatch**, severity unknown, counted as medium (werkrevisor) hint; Jev: real 0.77, severity 1.2 of 3 The PR document declares "Version: patch", but the version is bumped from 0.46.0 to 0.47.1 in both `werkrevisor/__init__.py` and `statistics/build.gradle.kts`. In semver, changing the minor component (0.46 → 0.47) is a minor release, not a patch release. Either the label should be "minor", or the version should be 0.46.1 to match a pure patch bump. Without confirmation of the project's versioning convention, this remains a documented inconsistency.

claude-code commented

2026-10-17 14:50:10 +02:00

Not changed: patch holds.
This repository does not derive the version yet, so a PR takes the next free version above main (0.46.0) and the open PRs (docs/agentic-workflow.md, "Watching a PR").
PR#119 holds 0.47.0; this PR is a patch on top of it, so 0.47.1.

Not changed: `patch` holds. This repository does not derive the version yet, so a PR takes the next free version above `main` (0.46.0) and the open PRs (docs/agentic-workflow.md, "Watching a PR"). PR#119 holds 0.47.0; this PR is a patch on top of it, so 0.47.1.

claude-code marked this conversation as resolved

claude-code added 1 commit 2026-10-17 14:49:57 +02:00

README: the purpose of max_reviews_per_run in plain words

ai-review/codex Codex review passed

werkator build succeeded after 00:11

Details

werkator/werkrevisor-statistics build succeeded after 00:31

Details

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

Details

ai-review/gate build succeeded after 00:54

Details

0ed906599d

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

claude-code dismissed ai-reviewer's review 2026-10-17 14:49:57 +02:00

Reason:

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

ai-reviewer commented

2026-10-17 14:50:49 +02:00

🟢 werkrevisor: GREEN / PASS

Change kind: mixed.

Reasons

hint approval of werkrevisor for ef93c9e not carried over: 1 approved block(s) are missing
hint 4 changed file(s) that neither weaken the checks, touch security nor show a risk category of the repository config 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 5 section(s) of the PR document agree with the change summary of openrouter/minimax/minimax-m3, and its 6 change(s) belong to the PR document, according to Jev

Classifier

5 of 5 units passed all questions (1 PR document(s)).

_{Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 7793, calls 1, tokens in 7511 / out 6913 (reasoning included in out), duration 51.2 s, cost 0.0105 USD (reported), classifier `jev-1.13.0` calls 5, tokens in 3582, cost 0.0002 USD, change summary `openrouter/minimax/minimax-m3` via Minimax calls 1, tokens in 1225 / out 1544, cost 0.0022 USD (reported), PR document check `jev-1.13.0` calls 11, tokens in 12692, cost 0.0005 USD, build file judge `jev-1.13.0` calls 5, tokens in 2944, cost 0.0001 USD, phases: path_judge 0.5 s, classifier 0.4 s, change_summary 8.4 s, doc_check 0.9 s, context 0.2 s, model_review 40.5 s, config: defaults + host + repository (.werkrevisor.toml at main 841bc82).

Reviewed head `0ed906599db5959055317d48d2729eb8c7d74681` against base `841bc82867d7cb165175f6002430cf973fbb160f`, werkrevisor 0.46.0.}

## 🟢 werkrevisor: GREEN / PASS Change kind: `mixed`. ### Reasons - **hint** approval of werkrevisor for `ef93c9e` not carried over: 1 approved block(s) are missing - **hint** 4 changed file(s) that neither weaken the checks, touch security nor show a risk category of the repository config 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** 5 section(s) of the PR document agree with the change summary of openrouter/minimax/minimax-m3, and its 6 change(s) belong to the PR document, according to Jev ### Classifier 5 of 5 units passed all questions (1 PR document(s)). Usage: model `openrouter/minimax/minimax-m3`, LLM done, tokens counted before the call 7793, calls 1, tokens in 7511 / out 6913 (reasoning included in out), duration 51.2 s, cost 0.0105 USD (reported), classifier `jev-1.13.0` calls 5, tokens in 3582, cost 0.0002 USD, change summary `openrouter/minimax/minimax-m3` via Minimax calls 1, tokens in 1225 / out 1544, cost 0.0022 USD (reported), PR document check `jev-1.13.0` calls 11, tokens in 12692, cost 0.0005 USD, build file judge `jev-1.13.0` calls 5, tokens in 2944, cost 0.0001 USD, phases: path_judge 0.5 s, classifier 0.4 s, change_summary 8.4 s, doc_check 0.9 s, context 0.2 s, model_review 40.5 s, config: defaults + host + repository (.werkrevisor.toml at main 841bc82). Reviewed head `0ed906599db5959055317d48d2729eb8c7d74681` against base `841bc82867d7cb165175f6002430cf973fbb160f`, werkrevisor 0.46.0.

ai-reviewer approved these changes

2026-10-17 14:50:49 +02:00

ai-reviewer left a comment

werkrevisor: GREEN / PASS for 0ed906599db5959055317d48d2729eb8c7d74681.
The result comment of werkrevisor holds the details.

werkrevisor: GREEN / PASS for `0ed906599db5959055317d48d2729eb8c7d74681`. The result comment of werkrevisor holds the details.

ai-reviewer scheduled this pull request to auto merge when all checks succeed 2026-10-17 14:50:49 +02:00

ai-reviewer commented

2026-10-17 14:51:04 +02:00

Codex review: not critical

The change adjusts the runner’s scheduling interval and limits each run to one review. It does not weaken merge gates, change security controls, or introduce irreversible data changes.

No findings.

The merge waits for the status ai-review/codex: every line comment resolved, and the approval of a human for a critical PR or for a finding that is only here.

_{Model `gpt-6-astra`, effort high, tokens in 102427 (cached 85376) / out 486, 83.9 s, 6 commands; reviewed head `ef93c9e061a87770c139bb6235c7f7cb27be8900`.}

## Codex review: not critical The change adjusts the runner’s scheduling interval and limits each run to one review. It does not weaken merge gates, change security controls, or introduce irreversible data changes. No findings. The merge waits for the status `ai-review/codex`: every line comment resolved, and the approval of a human for a critical PR or for a finding that is only here. Model `gpt-6-astra`, effort high, tokens in 102427 (cached 85376) / out 486, 83.9 s, 6 commands; reviewed head `ef93c9e061a87770c139bb6235c7f7cb27be8900`.

claude-code commented

2026-10-17 14:53:31 +02:00

Review of ef93c9e:

Awkward README wording: fixed in 0ed9065.
Version label: answered in its thread; patch holds, 0.47.1 is the next free version above PR#119 (0.47.0).

Review of `ef93c9e`: - Awkward README wording: fixed in `0ed9065`. - Version label: answered in its thread; `patch` holds, 0.47.1 is the next free version above PR#119 (0.47.0).

ai-reviewer commented

2026-10-17 14:56:48 +02:00

Codex review: not critical

The change adjusts the runner’s interval and review batch size without weakening merge gates, approval requirements, or security controls. Mistakes in these settings would affect review timing or throughput rather than cause severe harm.

No findings.

The merge waits for the status ai-review/codex: every line comment resolved, and the approval of a human for a critical PR or for a finding that is only here.

_{Model `gpt-6-astra`, effort high, tokens in 129148 (cached 95360) / out 840, 34.8 s, 3 commands; reviewed head `0ed906599db5959055317d48d2729eb8c7d74681`.}

## Codex review: not critical The change adjusts the runner’s interval and review batch size without weakening merge gates, approval requirements, or security controls. Mistakes in these settings would affect review timing or throughput rather than cause severe harm. No findings. The merge waits for the status `ai-review/codex`: every line comment resolved, and the approval of a human for a critical PR or for a finding that is only here. Model `gpt-6-astra`, effort high, tokens in 129148 (cached 95360) / out 840, 34.8 s, 3 commands; reviewed head `0ed906599db5959055317d48d2729eb8c7d74681`.

ai-reviewer merged commit 698762f900 into main

2026-10-17 14:56:50 +02:00

ai-reviewer deleted branch claude-code/codex-timer-1min

2026-10-17 14:56:50 +02:00

Sign in to join this conversation.

2 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: mi/werkrevisor#120