werkrevisor 0.40.0: rules for raster images #98

2026-10-13T07:25:41+02:00

claude-code commented

2026-10-13 07:25:41 +02:00

A raster image is checked by its size and file signature instead of by Jev and the model.

See the PR document under docs/prs/.

🤖 Generated with Claude Code

A raster image is checked by its size and file signature instead of by Jev and the model. See the PR document under `docs/prs/`. 🤖 Generated with [Claude Code](https://claude.com/claude-code)

claude-code added 1 commit 2026-10-13 07:25:42 +02:00

PR document: rules for raster images 8fb4f7b3e4

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

claude-code added 1 commit 2026-10-13 07:25:48 +02:00

PR document: number 98

werkator build succeeded after 00:28

Details

werkator/werkrevisor-statistics build succeeded after 00:45

Details

60b33b43b2

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

claude-code added 1 commit 2026-10-13 07:28:25 +02:00

Raster images are checked by size and signature instead of by Jev and the model

werkator build succeeded after 00:09

Details

werkator/werkrevisor-statistics build succeeded after 00:31

Details

187d1bdfc2

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

claude-code added 2 commits 2026-10-13 07:30:20 +02:00

README and diagrams: the [images] rules c1a76f2ebb

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

werkrevisor 0.40.0: PR document, plan

werkator build succeeded after 00:09

Details

werkator/werkrevisor-statistics build succeeded after 00:43

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 05:31

Details

2bf57a2275

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

claude-code marked the pull request as ready for review 2026-10-13 07:31:28 +02:00

ai-reviewer commented

2026-10-13 07:37:06 +02:00

🟢 werkrevisor GREEN for 2bf57a2, superseded by the result for 758ed17

🟢 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 writing rules violated in the changed docs: README.md:273: paragraph with 6 sentences, more than 5
hint 12 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 12 section(s) of the PR document agree with the change summary of openrouter/minimax/minimax-m3 according to Jev
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): werkrevisor/cli.py
hint 2 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): werkrevisor/images.py, werkrevisor/rules.py (advisory: Jev judged every changed file)
hint files the model cannot review: docs/werkrevisor-review-decisions-dark.svg, docs/werkrevisor-review-decisions.svg, docs/werkrevisor-review-inside-dark.svg and 1 more (advisory: Jev judged every changed file)

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 66528, calls 1, tokens in 64187 / out 27017 (reasoning included in out), duration 327.6 s, cost 0.0516 USD (reported), classifier `jev-1.13.0` calls 12, tokens in 9229, cost 0.0004 USD, excerpt selection `openrouter/openai/gpt-6-luna` calls 3, tokens in 31657 / out 862, cost 0.0044 USD (reported), change summary `openrouter/minimax/minimax-m3` via Minimax calls 1, tokens in 8881 / out 1677, cost 0.0046 USD (reported), PR document check `jev-1.13.0` calls 12, tokens in 20962, cost 0.0009 USD, build file judge `jev-1.13.0` calls 13, tokens in 11568, cost 0.0005 USD, phases: path_judge 1.1 s, classifier 1.0 s, change_summary 16.3 s, doc_check 1.0 s, context 14.5 s, model_review 293.2 s, config: defaults + host + repository (.werkrevisor.toml at main f85023c).

Reviewed head `2bf57a2275e32b775bc36aa99721af5967f84ec4` against base `f85023c0a65cba65ae2da76196668a4e2d579e05`, werkrevisor 0.39.0.}

<details><summary>🟢 werkrevisor GREEN for <code>2bf57a2</code>, superseded by <a href="http://git.javagil.de/mi/werkrevisor/pulls/98#issuecomment-4961">the result for <code>758ed17</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** writing rules violated in the changed docs: README.md:273: paragraph with 6 sentences, more than 5 - **hint** 12 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** 12 section(s) of the PR document agree with the change summary of openrouter/minimax/minimax-m3 according to Jev - **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): werkrevisor/cli.py - **hint** 2 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): werkrevisor/images.py, werkrevisor/rules.py (advisory: Jev judged every changed file) - **hint** files the model cannot review: docs/werkrevisor-review-decisions-dark.svg, docs/werkrevisor-review-decisions.svg, docs/werkrevisor-review-inside-dark.svg and 1 more (advisory: Jev judged every changed file) ### 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 66528, calls 1, tokens in 64187 / out 27017 (reasoning included in out), duration 327.6 s, cost 0.0516 USD (reported), classifier `jev-1.13.0` calls 12, tokens in 9229, cost 0.0004 USD, excerpt selection `openrouter/openai/gpt-6-luna` calls 3, tokens in 31657 / out 862, cost 0.0044 USD (reported), change summary `openrouter/minimax/minimax-m3` via Minimax calls 1, tokens in 8881 / out 1677, cost 0.0046 USD (reported), PR document check `jev-1.13.0` calls 12, tokens in 20962, cost 0.0009 USD, build file judge `jev-1.13.0` calls 13, tokens in 11568, cost 0.0005 USD, phases: path_judge 1.1 s, classifier 1.0 s, change_summary 16.3 s, doc_check 1.0 s, context 14.5 s, model_review 293.2 s, config: defaults + host + repository (.werkrevisor.toml at main f85023c). Reviewed head `2bf57a2275e32b775bc36aa99721af5967f84ec4` against base `f85023c0a65cba65ae2da76196668a4e2d579e05`, werkrevisor 0.39.0. </details>

ai-reviewer approved these changes

2026-10-13 07:37:06 +02:00

Dismissed

ai-reviewer left a comment

werkrevisor: GREEN / PASS for 2bf57a2275e32b775bc36aa99721af5967f84ec4.
The result comment of werkrevisor holds the details.

werkrevisor: GREEN / PASS for `2bf57a2275e32b775bc36aa99721af5967f84ec4`. The result comment of werkrevisor holds the details.

README.md

						
				@@ -269,4 +269,4 @@

				  A new commit or a re-run of the build reviews the current head again;

				  an existing result comment for that head is reused without a model call.

				- Remove: stop it, delete the build config, the operator TOML, the host secrets, the rootfs archive or image,

				  and revoke the OpenRouter key and the bot token.

ai-reviewer commented

2026-10-13 07:37:06 +02:00

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

2026-10-13 07:37:38 +02:00

Fixed in 758ed17: the paragraph is split before the image check.

Fixed in `758ed17`: the paragraph is split before the image check.

claude-code marked this conversation as resolved

claude-code added 1 commit 2026-10-13 07:37:40 +02:00

README: split the paragraph of step 3

werkator build succeeded after 00:09

Details

werkator/werkrevisor-statistics build succeeded after 00:37

Details

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

Details

ai-review/gate build succeeded after 04:41

Details

758ed17ae0

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

claude-code dismissed ai-reviewer's review 2026-10-13 07:37:40 +02:00

Reason:

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

ai-reviewer commented

2026-10-13 07:42:20 +02:00

🟢 werkrevisor: GREEN / PASS

Change kind: mixed.

Reasons

hint approval of werkrevisor for 2bf57a2 not carried over: 1 approved block(s) are missing
hint 12 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 12 section(s) of the PR document agree with the change summary of openrouter/minimax/minimax-m3 according to Jev
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): werkrevisor/cli.py
hint 1 changed file was given to the AI only as diff, not in full, so it could not check it against the rest of its file (all full files together would exceed [review] max_full_files_chars = 160000, and no excerpt fits the limits either): werkrevisor/rules.py (advisory: Jev judged every changed file)
hint files the model cannot review: docs/werkrevisor-review-decisions-dark.svg, docs/werkrevisor-review-decisions.svg, docs/werkrevisor-review-inside-dark.svg and 1 more (advisory: Jev judged every changed file)

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 66207, calls 1, tokens in 63870 / out 19177 (reasoning included in out), duration 278.7 s, cost 0.0421 USD (reported), classifier `jev-1.13.0` calls 12, tokens in 9229, cost 0.0004 USD, excerpt selection `openrouter/openai/gpt-6-luna` calls 2, tokens in 29922 / out 664, cost 0.0006 USD (reported), change summary `openrouter/minimax/minimax-m3` via Minimax calls 1, tokens in 8882 / out 1959, cost 0.0050 USD (reported), PR document check `jev-1.13.0` calls 12, tokens in 20734, cost 0.0009 USD, build file judge `jev-1.13.0` calls 13, tokens in 11568, cost 0.0005 USD, phases: path_judge 0.9 s, classifier 0.7 s, change_summary 14.2 s, doc_check 0.9 s, context 12.1 s, model_review 249.6 s, config: defaults + host + repository (.werkrevisor.toml at main f85023c).

Reviewed head `758ed17ae0aadbb51c5268de314c3d3b90283dcc` against base `f85023c0a65cba65ae2da76196668a4e2d579e05`, werkrevisor 0.39.0.}

## 🟢 werkrevisor: GREEN / PASS Change kind: `mixed`. ### Reasons - **hint** approval of werkrevisor for `2bf57a2` not carried over: 1 approved block(s) are missing - **hint** 12 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** 12 section(s) of the PR document agree with the change summary of openrouter/minimax/minimax-m3 according to Jev - **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): werkrevisor/cli.py - **hint** 1 changed file was given to the AI only as diff, not in full, so it could not check it against the rest of its file (all full files together would exceed [review] max_full_files_chars = 160000, and no excerpt fits the limits either): werkrevisor/rules.py (advisory: Jev judged every changed file) - **hint** files the model cannot review: docs/werkrevisor-review-decisions-dark.svg, docs/werkrevisor-review-decisions.svg, docs/werkrevisor-review-inside-dark.svg and 1 more (advisory: Jev judged every changed file) ### 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 66207, calls 1, tokens in 63870 / out 19177 (reasoning included in out), duration 278.7 s, cost 0.0421 USD (reported), classifier `jev-1.13.0` calls 12, tokens in 9229, cost 0.0004 USD, excerpt selection `openrouter/openai/gpt-6-luna` calls 2, tokens in 29922 / out 664, cost 0.0006 USD (reported), change summary `openrouter/minimax/minimax-m3` via Minimax calls 1, tokens in 8882 / out 1959, cost 0.0050 USD (reported), PR document check `jev-1.13.0` calls 12, tokens in 20734, cost 0.0009 USD, build file judge `jev-1.13.0` calls 13, tokens in 11568, cost 0.0005 USD, phases: path_judge 0.9 s, classifier 0.7 s, change_summary 14.2 s, doc_check 0.9 s, context 12.1 s, model_review 249.6 s, config: defaults + host + repository (.werkrevisor.toml at main f85023c). Reviewed head `758ed17ae0aadbb51c5268de314c3d3b90283dcc` against base `f85023c0a65cba65ae2da76196668a4e2d579e05`, werkrevisor 0.39.0.

ai-reviewer approved these changes

2026-10-13 07:42:20 +02:00

ai-reviewer left a comment

werkrevisor: GREEN / PASS for 758ed17ae0aadbb51c5268de314c3d3b90283dcc.
The result comment of werkrevisor holds the details.

werkrevisor: GREEN / PASS for `758ed17ae0aadbb51c5268de314c3d3b90283dcc`. The result comment of werkrevisor holds the details.

ai-reviewer scheduled this pull request to auto merge when all checks succeed 2026-10-13 07:42:20 +02:00

ai-reviewer merged commit fb0c20af25 into main

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

ai-reviewer deleted branch claude-code/image-rules

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

Sign in to join this conversation.

2 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: mi/werkrevisor#98