claude-code
  • Joined on 2026-10-05
claude-code commented on pull request mi/werkrevisor#88 2026-10-11 21:38:15 +02:00
werkrevisor 0.34.0: a runner on the workstation adds a review by the Codex CLI

Answer to the review of 8e89649:

  • tests lost or disabled in tests/test_codex_eval.py: no test is lost. The four tests of PR#87 moved with their code to tests/test_codex.py (`werkrevis…
claude-code pushed to claude-code/codex-runner at mi/werkrevisor 2026-10-11 21:34:36 +02:00
8e89649515 PR document: the full rule for a human approval, a scenario of its own for RED heads
claude-code commented on pull request mi/werkrevisor#88 2026-10-11 21:34:34 +02:00
werkrevisor 0.34.0: a runner on the workstation adds a review by the Codex CLI

Fixed in 8e89649: both bullets now name the critical PR and the finding outside the diff, as gate_state does.

claude-code commented on pull request mi/werkrevisor#88 2026-10-11 21:28:22 +02:00
werkrevisor 0.34.0: a runner on the workstation adds a review by the Codex CLI

Fixed in 16af857: the comparison uses the first 250 characters, as Gitea keeps them; the test covers a description of 300 characters.

claude-code commented on pull request mi/werkrevisor#88 2026-10-11 21:28:21 +02:00
werkrevisor 0.34.0: a runner on the workstation adds a review by the Codex CLI

Fixed in 16af857: the runner reviews only a head that werkrevisor rated GREEN, YELLOW or ORANGE; the test covers a RED head.

claude-code pushed to claude-code/codex-runner at mi/werkrevisor 2026-10-11 21:28:21 +02:00
16af857e26 The runner skips RED heads and compares the shortened status text; scenario 88.07 without two actions
claude-code pushed to claude-code/codex-runner at mi/werkrevisor 2026-10-11 21:22:10 +02:00
45743f10d2 A Codex answer needs every field of the schema; tests of tools/codex-eval; scenario 88.07 without an earlier run
claude-code commented on pull request mi/werkrevisor#88 2026-10-11 21:22:09 +02:00
werkrevisor 0.34.0: a runner on the workstation adds a review by the Codex CLI

Fixed in 45743f1: the Given now names only the state before the run, a PR whose only unresolved line comment comes from Codex, as the test sets it up.

claude-code commented on pull request mi/werkrevisor#88 2026-10-11 21:22:08 +02:00
werkrevisor 0.34.0: a runner on the workstation adds a review by the Codex CLI

Fixed in 45743f1: valid_answer also requires critical_reason, title and explanation as strings; the test covers a missing title and a missing explanation.

claude-code commented on pull request mi/werkrevisor#88 2026-10-11 21:15:18 +02:00
werkrevisor 0.34.0: a runner on the workstation adds a review by the Codex CLI

Fixed in 98a07b9: the test now adds a real Codex review with a line comment before werkrevisor runs, instead of rewriting a writing-rule comment.

claude-code commented on pull request mi/werkrevisor#88 2026-10-11 21:15:18 +02:00
werkrevisor 0.34.0: a runner on the workstation adds a review by the Codex CLI

Fixed in 98a07b9, with one correction: the sandbox of Codex already blocks the network of its commands; a probe inside the runner setup ended curl https://example.org with exit 6. The real gap…

claude-code commented on pull request mi/werkrevisor#88 2026-10-11 21:15:17 +02:00
werkrevisor 0.34.0: a runner on the workstation adds a review by the Codex CLI

Fixed in 98a07b9: values of the login from 8 characters on are secrets now; the test covers a value of 10 characters, and it fails with the old limit of 16. Shorter values of auth.json are…

claude-code pushed to claude-code/codex-runner at mi/werkrevisor 2026-10-11 21:15:10 +02:00
98a07b945c Codex runs in bwrap without the secrets of the workstation; short login values are secrets too
claude-code pushed to claude-code/codex-runner at mi/werkrevisor 2026-10-11 21:08:13 +02:00
342e224810 PR document: scenario 88.07 in plainer words
claude-code pushed to claude-code/codex-runner at mi/werkrevisor 2026-10-11 21:03:58 +02:00
a42e5a0c47 PR document: scenario 88.07 names the state of the PR
claude-code commented on pull request mi/werkrevisor#88 2026-10-11 20:57:04 +02:00
werkrevisor 0.34.0: a runner on the workstation adds a review by the Codex CLI

Fixed in af6613e: a WIP PR gets no status at all; only a PR without "WIP: " and without a result of werkrevisor gets pending in gate mode, as run_pr does.

claude-code pushed to claude-code/codex-runner at mi/werkrevisor 2026-10-11 20:56:57 +02:00
af6613e2cf PR document: clearer scenarios 88.02, 88.05 and 88.07
claude-code pushed to claude-code/codex-runner at mi/werkrevisor 2026-10-11 20:49:23 +02:00
659d873695 werkrevisor 0.34.0: README, PR document and plan for the Codex runner
ec5d17d4a8 The PR workflow diagram shows the optional Codex review
Compare 2 commits »
claude-code pushed to claude-code/codex-runner at mi/werkrevisor 2026-10-11 20:46:39 +02:00
12a7fd51d4 tools/codex-runner reviews ready PRs with the Codex CLI after werkrevisor
claude-code pushed to claude-code/claude-app-links at mi/werkregie 2026-10-11 20:45:12 +02:00
6e4df2375e Claude Code sessions and the Claude logo open Claude Desktop; version 0.11.3