waypoint-codex 0.10.11 → 0.10.12

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "waypoint-codex",
3
- "version": "0.10.11",
3
+ "version": "0.10.12",
4
4
  "description": "Codex-native repository operating system: scaffolding, docs routing, repo-local skills, doctor, and sync.",
5
5
  "license": "MIT",
6
6
  "type": "module",
@@ -51,6 +51,7 @@ If something important lives only in your head or in the chat transcript, the re
51
51
  - Rebuild `.waypoint/TRACKS_INDEX.md` whenever tracker files change.
52
52
  - When spawning reviewer agents or other subagents, explicitly set `fork_context: false`, `model` to `gpt-5.4`, and `reasoning_effort` to `high` unless the user explicitly requests a different model or lower reasoning.
53
53
  - Use the repo-local skills and reviewer agents instead of improvising from scratch.
54
+ - If you created a PR earlier in the current session and need to push more work, first confirm that PR is still open. If it is closed, create a fresh branch from `origin/main` and open a fresh PR instead of pushing more commits to the old PR branch.
54
55
  - Treat reviewer agents as one-shot workers: once a reviewer returns findings, read the result and close it. If another review pass is needed later, spawn a fresh reviewer instead of reusing the same thread.
55
56
  - Do not kill long-running subagents or reviewer agents just because they are slow.
56
57
  - When waiting on reviewers, subagents, CI, automated review, or external jobs, wait as long as required. There is no fixed timeout where waiting itself becomes the problem.
@@ -100,6 +100,7 @@ Working rules:
100
100
  - Before presenting a non-trivial implementation plan to the user, run `plan-reviewer` and iterate on the plan until it has no meaningful review findings left
101
101
  - Treat `plan-reviewer`, `code-reviewer`, and `code-health-reviewer` as one-shot agents: once a reviewer returns findings, close it; if another pass is needed later, spawn a fresh reviewer instead of reusing the old thread
102
102
  - Before pushing or opening/updating a PR for substantial work, use `pre-pr-hygiene`
103
+ - If you created a PR earlier in the current session and need to push more work, first confirm that PR is still open. If it is closed, create a fresh branch from `origin/main` and open a fresh PR instead of pushing more commits to the old PR branch
103
104
  - Use `pr-review` once a PR has active review comments or automated review in progress
104
105
  - Treat the generated context bundle as required session bootstrap, not optional reference material
105
106
  - After plan approval, own the execution through implementation, verification, review, and repo-memory updates before surfacing a final completion report