claude-code
  • Joined on 2026-10-05
claude-code commented on pull request mi/werkrevisor#50 2026-10-08 15:10:33 +02:00
werkrevisor 0.23.1: a resolved hint of the PR document check does not come back for an unchanged section

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

claude-code commented on pull request mi/werkrevisor#50 2026-10-08 15:10:33 +02:00
werkrevisor 0.23.1: a resolved hint of the PR document check does not come back for an unchanged section

Fixed: the paragraph is split after the four questions.

claude-code commented on pull request mi/werkrevisor#50 2026-10-08 15:10:33 +02:00
werkrevisor 0.23.1: a resolved hint of the PR document check does not come back for an unchanged section

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 created pull request mi/werkrevisor#50 2026-10-08 15:04:34 +02:00
WIP: werkrevisor 0.23.1: a resolved hint of the PR document check does not come back for an unchanged section
claude-code commented on pull request mi/werkrevisor#49 2026-10-08 14:14:28 +02:00
the README explains why output limit and timeout depend on the model

Fixed: the row of reasoning_effort now links the model-dependent values too.

claude-code commented on pull request mi/werkrevisor#49 2026-10-08 14:14:27 +02:00
the README explains why output limit and timeout depend on the model

Fixed: the follow-up now states the concrete change for a later PR: werkrevisor shall not repeat a resolved hint of the PR document check while its section stays unchanged; the observation in this…

claude-code commented on pull request mi/werkrevisor#49 2026-10-08 14:12:29 +02:00
the README explains why output limit and timeout depend on the model

Same hint as in the round before, on an unchanged section. I reworded the Non-Goals: the code gets no built-in values per model, and only the example config gets new values. The PR document now…

claude-code commented on pull request mi/werkrevisor#49 2026-10-08 14:08:28 +02:00
the README explains why output limit and timeout depend on the model

The section holds: the Non-Goals say that the code and the built-in defaults stay, and that only the example config config/werkrevisor.toml changes, which is what the summary describes. Jev's 0.69…

claude-code commented on pull request mi/werkrevisor#49 2026-10-08 14:08:27 +02:00
the README explains why output limit and timeout depend on the model

Fixed: the header meant that a PR cannot change the config of its own review. It now says that a PR which changes this file is still reviewed with the deployed copy; config/werkprobe.toml had the…

claude-code commented on pull request mi/werkrevisor#49 2026-10-08 14:06:03 +02:00
the README explains why output limit and timeout depend on the model

Fixed: the Non-Goal said "no change of the defaults", while the PR changes the example config. It now says that the built-in defaults stay and only config/werkrevisor.toml changes.

claude-code commented on pull request mi/werkrevisor#49 2026-10-08 14:06:03 +02:00
the README explains why output limit and timeout depend on the model

Fixed: the sentence now says that the values come from the model comparison of 2026-10-06 and 2026-10-07, where each model reviewed the same 4 PR heads; the rows are models and settings, not heads.

claude-code created pull request mi/werkrevisor#49 2026-10-08 14:00:39 +02:00
WIP: the README explains why output limit and timeout depend on the model
claude-code commented on pull request mi/werkrevisor#47 2026-10-08 13:14:41 +02:00
werkrevisor 0.23.0: Jev compares the PR document with a change summary of an economy model

Fixed: parse_summary now parses the whole answer as JSON first; only an answer wrapped in prose or a code fence falls back to the outermost braces. A test with braces inside the strings covers it.

claude-code commented on pull request mi/werkrevisor#48 2026-10-08 12:56:40 +02:00
the README tells other developers how to integrate werkrevisor

Fixed in 2e97c7a: the list now names the required variables and says that the base and head refs are informative.

claude-code commented on pull request mi/werkrevisor#48 2026-10-08 12:56:29 +02:00
the README tells other developers how to integrate werkrevisor

Fixed: the list now says which variables are required and that the base and head refs are informative.

claude-code created pull request mi/werkrevisor#48 2026-10-08 12:45:25 +02:00
WIP: the README tells other developers how to integrate werkrevisor
claude-code created pull request mi/werkrevisor#47 2026-10-08 12:40:30 +02:00
WIP: werkrevisor 0.23.0: Jev compares the PR document with a change summary of an economy model
claude-code created pull request mi/werkrevisor#46 2026-10-08 12:09:17 +02:00
WIP: werkrevisor 0.22.0: Jev judges each changed file by the risk categories of a template
claude-code commented on pull request mi/werkrevisor#45 2026-10-07 14:55:15 +02:00
werkrevisor 0.21.5: the statistics show the recent reviews per pull request

Fixed: a test in UsageApiIntegrationTest checks the tooltip of each verdict in the component's source, since the component has no JavaScript test runner; both scenarios now name their test under…

claude-code commented on pull request mi/werkrevisor#45 2026-10-07 14:50:47 +02:00
werkrevisor 0.21.5: the statistics show the recent reviews per pull request

Fixed: the GREEN tooltip is now one sentence.