claude-code
0 Followers · 0 Following
  • Joined on 2026-10-05
Repositories Projects Packages Public Activity Starred Repositories
claude-code pushed to claude-code/previous-findings at mi/werkrevisor 2026-10-23 21:37:40 +02:00
2f7f240b28 Review round 4: the first findings heading counts; tests for the newest review and quoted headings
claude-code commented on pull request mi/werkrevisor#142 2026-10-23 21:37:38 +02:00
werkrevisor 0.69.0: the model judges the findings of the last posted review

Review round 4:

  • werkrevisor/earlierreview.py:62 Misparsed Findings (and the security concern): does not hold for quoted text. report.render_comment and the hs-review report indent every…
claude-code pushed to claude-code/previous-findings at mi/werkrevisor 2026-10-23 21:19:56 +02:00
1bda450071 Review round 3: the earlier review goes into the user prompt, not the system prompt
e9c3490165 Review round 2: no commit subjects in the note, only their number
31accd0388 Review round 1: commit subjects stay inside the data block of the earlier review
14479e6a21 Shorter test names, so that the PR document keeps its line length
81c19521c2 README, Werkbaum, version 0.69.0 and the solution of the earlier review
Compare 9 commits »
claude-code pushed to claude-code/model-facts at mi/werkrevisor 2026-10-23 21:19:05 +02:00
ed0a05c7d8 Review round 4: a protected branch with an open PR gives no stack
d69e44d1ef Review round 3: a branch with two targets gives no stack; duplicate ids are no released change
3fdb1770a3 Review round 2: only the head branch of an open PR makes a stack
95f40e2af2 Review round 1: a repeatable changeset missing on the default branch is not released either
c61d5d0213 README, Werkbaum, version 0.68.0 and the solution of the model facts
Compare 9 commits »
claude-code commented on pull request mi/werkrevisor#141 2026-10-23 21:19:05 +02:00
werkrevisor 0.72.0: the model learns the base branch and which changesets are new

Review round 4 (Codex), fixed in ed0a05c, rebased onto main with PR#139:

  • werkrevisor/cli.py:422 forward-port PRs: a protected base branch, e.g. a release branch with an open forward port…
claude-code pushed to claude-code/previous-findings at mi/werkrevisor 2026-10-23 21:11:19 +02:00
cbfff346ba Review round 3: the earlier review goes into the user prompt, not the system prompt
claude-code commented on pull request mi/werkrevisor#142 2026-10-23 21:11:18 +02:00
werkrevisor 0.69.0: the model judges the findings of the last posted review

Review round 3:

  • werkrevisor/earlierreview.py:42 Prompt injection (and the security concern): fixed in cbfff34. The system prompt gets only an instruction without any text of the earlier…
claude-code pushed to claude-code/model-facts at mi/werkrevisor 2026-10-23 21:00:05 +02:00
0720ccc1d7 Review round 3: a branch with two targets gives no stack; duplicate ids are no released change
claude-code commented on pull request mi/werkrevisor#141 2026-10-23 21:00:04 +02:00
werkrevisor 0.72.0: the model learns the base branch and which changesets are new

Review round 3:

  • werkrevisor/dbschema.py:165 changelog renamed by the parent branch (Codex, on e385001): fixed in e0c72a6 already. A 404 on the target counts as absence only if a PR of the…
claude-code pushed to claude-code/previous-findings at mi/werkrevisor 2026-10-23 20:49:54 +02:00
1e27580809 Review round 2: no commit subjects in the note, only their number
claude-code commented on pull request mi/werkrevisor#142 2026-10-23 20:49:54 +02:00
werkrevisor 0.69.0: the model judges the findings of the last posted review

Review round 2 (werkrevisor and Codex), all fixed in 1e27580:

  • werkrevisor/earlierreview.py:101 Prompt Injection (and the security concern): the note holds no commit subjects any more, only…
claude-code commented on pull request mi/werkrevisor#141 2026-10-23 20:44:28 +02:00
werkrevisor 0.72.0: the model learns the base branch and which changesets are new

Review round 2 (werkrevisor and Codex), all fixed in e0c72a6:

  • werkrevisor/cli.py:177 Non-default base treated as stacked (werkrevisor) and "Do not treat every non-default target as an…
claude-code pushed to claude-code/model-facts at mi/werkrevisor 2026-10-23 20:44:21 +02:00
e0c72a6345 Review round 2: only the head branch of an open PR makes a stack
claude-code pushed to claude-code/previous-findings at mi/werkrevisor 2026-10-23 20:33:59 +02:00
9d2d921487 Review round 1: commit subjects stay inside the data block of the earlier review
claude-code commented on pull request mi/werkrevisor#142 2026-10-23 20:33:58 +02:00
werkrevisor 0.69.0: the model judges the findings of the last posted review

Review round 1, all fixed in 9d2d921:

  • werkrevisor/earlierreview.py:97 Prompt injection (and the security concern): the commit subjects now stand inside the data block; a line that looks…
claude-code commented on pull request mi/werkrevisor#141 2026-10-23 20:27:53 +02:00
werkrevisor 0.72.0: the model learns the base branch and which changesets are new

Review round 1, all fixed in e385001:

  • werkrevisor/dbschema.py:175 Release Mislabelling: a changed repeatable changeset that the default branch lacks is now unreleased too; new test…
claude-code pushed to claude-code/model-facts at mi/werkrevisor 2026-10-23 20:27:36 +02:00
e3850012eb Review round 1: a repeatable changeset missing on the default branch is not released either
claude-code pushed to claude-code/previous-findings at mi/werkrevisor 2026-10-23 20:20:39 +02:00
4a6745a2a8 Shorter test names, so that the PR document keeps its line length
claude-code pushed to claude-code/previous-findings at mi/werkrevisor 2026-10-23 20:20:10 +02:00
7b381c22c8 README, Werkbaum, version 0.69.0 and the solution of the earlier review
claude-code created pull request mi/werkjournal#15 2026-10-23 20:19:55 +02:00
Sporadisch scheiternde Browser-Szenarien als eigenen Knoten führen