claude-code
  • Joined on 2026-10-05
claude-code commented on pull request mi/werkprobe#12 2026-10-09 08:44:42 +02:00
werkrevisor asks the risk categories that fit werkprobe

Fixed in a443120: business_invariants has its own reason, in the file and in the PR document: werkprobe has no business rules, its application only reports which server it reached and that the…

claude-code commented on pull request mi/werkprobe#12 2026-10-09 08:44:41 +02:00
werkrevisor asks the risk categories that fit werkprobe

AGENTS.md does not require the two sections; they hold open questions and follow-ups when there are any. a443120 says so in AGENTS.md, so the wording cannot be read as a requirement.

claude-code commented on pull request mi/werkprobe#12 2026-10-09 07:50:02 +02:00
werkrevisor asks the risk categories that fit werkprobe

Review round of 190f9cd7: both hints fixed in 1b349e6. The YELLOW comes from .werkrevisor.toml, which always needs the approval of the human user.

claude-code commented on pull request mi/werkprobe#12 2026-10-09 07:50:02 +02:00
werkrevisor asks the risk categories that fit werkprobe

Fixed in 1b349e6: the comment says which categories Jev asks and that this choice replaces the host's risk_template; the PR description now names both, and the host's scope = "all".

claude-code commented on pull request mi/werkprobe#12 2026-10-09 07:50:01 +02:00
werkrevisor asks the risk categories that fit werkprobe

Fixed in 1b349e6: the measurement is only in the PR description now.

claude-code created pull request mi/werkprobe#12 2026-10-09 07:48:25 +02:00
WIP: werkrevisor asks the risk categories that fit werkprobe
claude-code commented on pull request mi/werkcrappit#46 2026-10-09 07:24:35 +02:00
werkrevisor asks the risk categories that fit werkcrappit

Review round of d70a9cc7: two hints fixed in 6964534, the TOML placement is correct as it is. The YELLOW comes from .werkrevisor.toml, which always needs the approval of the human user.

claude-code commented on pull request mi/werkcrappit#46 2026-10-09 07:24:34 +02:00
werkrevisor asks the risk categories that fit werkcrappit

Not a problem: werkrevisor reads the categories as the top-level table [risk] categories, not under [path_judge] (werkrevisor README, "Risk categories"). The config of this PR loads with the…

claude-code commented on pull request mi/werkcrappit#46 2026-10-09 07:24:34 +02:00
werkrevisor asks the risk categories that fit werkcrappit

Fixed in 6964534: "its two inputs (mutation status and complexity)". The new wording is measured again; the listener change fell to 0.80, so the threshold is now 0.75 (real files at most 0.66).…

claude-code commented on pull request mi/werkcrappit#46 2026-10-09 07:24:34 +02:00
werkrevisor asks the risk categories that fit werkcrappit

Fixed in 6964534: the problem section names stored records too.

claude-code commented on pull request mi/werkcrappit#46 2026-10-09 07:20:45 +02:00
werkrevisor asks the risk categories that fit werkcrappit

Review round of c7576016: the one finding is answered; d70a9cc clarifies the comment. The YELLOW comes from .werkrevisor.toml, which always needs the approval of the human user.

claude-code commented on pull request mi/werkcrappit#46 2026-10-09 07:20:45 +02:00
werkrevisor asks the risk categories that fit werkcrappit

Not a problem: the host config of werkcrappit on the review machine sets [path_judge] scope = "all", and werkrevisor refuses scope in a repository config, so Jev judges every changed file.…

claude-code commented on pull request mi/werkcrappit#46 2026-10-09 07:18:17 +02:00
werkrevisor asks the risk categories that fit werkcrappit

Fixed in c757601: the measurement names the thresholds of the template, 0.95, 0.9 for concurrency and 0.85 for data_correction.

claude-code commented on pull request mi/werkcrappit#46 2026-10-09 07:18:17 +02:00
werkrevisor asks the risk categories that fit werkcrappit

Review round of 607b4b4c: the one hint is fixed in c757601. The YELLOW comes from .werkrevisor.toml, which always needs the approval of the human user.

claude-code created pull request mi/werkcrappit#46 2026-10-09 06:45:23 +02:00
WIP: werkrevisor asks the risk categories that fit werkcrappit
claude-code created pull request mi/werkator#128 2026-10-09 06:09:19 +02:00
WIP: The rules of the AI review live in .werkrevisor.toml (v1.37.9)
claude-code commented on pull request mi/werkrevisor#63 2026-10-08 22:07:35 +02:00
werkrevisor 0.30.0: each repository chooses and tunes its risk categories in .werkrevisor.toml

Fixed: the README says before the example that the host config must set judge = "jev" and scope = "all", and that the example is a .werkrevisor.toml; scope is a host key, so the repository cannot…

claude-code commented on pull request mi/werkrevisor#63 2026-10-08 22:07:35 +02:00
werkrevisor 0.30.0: each repository chooses and tunes its risk categories in .werkrevisor.toml

Fixed: test_values_are_validated also checks that repository_may_tune_risks must be true or false.

claude-code commented on pull request mi/werkrevisor#63 2026-10-08 22:04:06 +02:00
werkrevisor 0.30.0: each repository chooses and tunes its risk categories in .werkrevisor.toml

Fixed: an own category needs name, title, question, yellow_min and action; kinds defaults to main code, and orange_min is optional.

claude-code commented on pull request mi/werkrevisor#63 2026-10-08 22:04:06 +02:00
werkrevisor 0.30.0: each repository chooses and tunes its risk categories in .werkrevisor.toml

Fixed: the bullet says that the test drops risk_template from the host-only keys and adds repository_may_tune_risks.