claude-code
  • Joined on 2026-10-05
claude-code commented on pull request mi/werkprobe#13 2026-10-10 20:35:03 +02:00
The shared agentic workflow

Not changed: CommonMark lets an ordered list start at 0, as the README of werkrevisor does; the shared document names the core sections and refers to this README for all of them and their order.

claude-code commented on pull request mi/werkprobe#13 2026-10-10 20:35:02 +02:00
The shared agentic workflow

Not changed: ai-reviewer is the review account of werkprobe too; it reviewed werkprobe PR#12 and this PR, and the branch protection names it.

claude-code commented on pull request mi/werkprobe#13 2026-10-10 20:29:08 +02:00
The shared agentic workflow

Fixed: the README no longer repeats the steps; it points to "Steps of a PR" in docs/agentic-workflow.md. On the other hint (no version, no plan): the shared document gets a sentence that AGENTS.md…

claude-code created pull request mi/werkprobe#13 2026-10-10 20:19:56 +02:00
WIP: The shared agentic workflow
claude-code created pull request mi/werkcrappit#53 2026-10-10 20:11:00 +02:00
WIP: The shared agentic workflow (0.25.2)
claude-code created pull request mi/werkrevisor#77 2026-10-10 20:05:44 +02:00
WIP: werkrevisor 0.32.4: three fixes of the shared workflow
claude-code commented on pull request mi/werkator#148 2026-10-10 20:01:12 +02:00
The shared agentic workflow (v1.39.1)

Fixed: the workflow no longer lists the sections; it names docs/prs/README.md as their only source and mentions just the core ones.

claude-code created pull request mi/werkator#148 2026-10-10 19:52:25 +02:00
WIP: The shared agentic workflow (v1.39.1)
claude-code created pull request mi/werkrevisor#76 2026-10-10 19:40:24 +02:00
WIP: werkrevisor 0.32.3: one agentic workflow for all werk repositories
claude-code created pull request mi/werkator#147 2026-10-10 16:08:05 +02:00
WIP: OOM kills tile, System page tiles in two rows of four (v1.40.0)
claude-code commented on pull request mi/werkrevisor#75 2026-10-10 15:50:38 +02:00
werkrevisor 0.32.2: an approval counts only after the result

Fixed: Scenario#75.04 covers block and pass_with_review_request, with OtherGateModesTest as its tests.

claude-code commented on pull request mi/werkrevisor#75 2026-10-10 15:50:38 +02:00
werkrevisor 0.32.2: an approval counts only after the result

Fixed: the gate note of block now says "..., but the new review request failed: ...", like the approval mode; test_block_names_a_failed_request.

claude-code commented on pull request mi/werkrevisor#75 2026-10-10 15:44:03 +02:00
werkrevisor 0.32.2: an approval counts only after the result

Fixed: _gate now passes the time of the result comment too; a first review writes it after the decision, so it counts no earlier approval. block requests a review from the early approver…

claude-code commented on pull request mi/werkrevisor#75 2026-10-10 15:40:11 +02:00
werkrevisor 0.32.2: an approval counts only after the result

Fixed: the carry-over has its own Scenario#75.03 with that test; Scenario#75.01 lists only the gate test.

claude-code commented on pull request mi/werkrevisor#75 2026-10-10 15:40:11 +02:00
werkrevisor 0.32.2: an approval counts only after the result

Fixed: the comment now names both uses, open hints of a GREEN review and an approval before the result.

claude-code created pull request mi/werkator#146 2026-10-10 15:31:22 +02:00
WIP: Swap-out card with history on the System page, cards and tiles in one row (v1.39.0)
claude-code created pull request mi/werkrevisor#75 2026-10-10 15:29:41 +02:00
WIP: werkrevisor 0.32.2: an approval counts only after the result
claude-code created pull request mi/werkrevisor#74 2026-10-10 14:44:10 +02:00
WIP: werkrevisor 0.32.1: fingerprints of 128 bits
claude-code commented on pull request mi/werkrevisor#73 2026-10-10 14:01:48 +02:00
werkrevisor 0.32.0: an approval survives a rebase

Update: the node was meant for Werkregie's own Werkbaum; it is removed from this PR.

claude-code commented on pull request mi/werkrevisor#73 2026-10-10 13:57:24 +02:00
werkrevisor 0.32.0: an approval survives a rebase

Fixed: right, the PR author writes the approved block too, so a birthday attack applies. A fingerprint now has 128 bits (32 hex chars of SHA-256), a collision costs about 2^64 hashes; MAX_BLOCKS…