Enforce shared Oxford spelling#31
Conversation
Generate parent and rendered-project typos configuration from the shared estate dictionary plus narrow local overlays. Add pinned local and CI gates, contract and behavioural coverage, and correct the spelling findings exposed in generated guidance.
|
Warning Review limit reachedYou’ve reached a temporary PR review limit under our Fair Usage Limits Policy. Next review available in: 59 minutes Your organization has reached its usage spending cap. Adjust your spending cap in the billing tab. How can I continue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews. How do review limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please refer docs for additional details. Review details⚙️ Run configurationConfiguration used: Organization UI Review profile: ASSERTIVE Plan: Pro Plus Run ID: 📒 Files selected for processing (33)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
There was a problem hiding this comment.
Sorry @leynos, your pull request is larger than the review limit of 150000 diff characters
Keep parentheses around multi-exception clauses in the shared spelling helper. Python 3.14 accepts the compact form produced locally, but generated projects and hosted CI support Python 3.13.
|
@coderabbitai review |
There was a problem hiding this comment.
Sorry @leynos, your pull request is larger than the review limit of 150000 diff characters
✅ Action performedReview finished.
|
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 562d5efe6f
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| run: make typecheck | ||
|
|
||
| - name: Check spelling | ||
| run: make spelling |
There was a problem hiding this comment.
When this rendered workflow runs on generated projects, make spelling regenerates the tracked typos.toml before checking Markdown, but the job never verifies that the checkout stayed clean. If a PR updates typos.local.toml or runs after the shared base advances without committing the regenerated typos.toml, CI will silently modify the runner's copy and still pass, leaving the repository with stale spelling policy.
Useful? React with 👍 / 👎.
| saved = _read_metadata(metadata) | ||
| request = _https_request(source, _conditional_headers(saved)) |
There was a problem hiding this comment.
When callers switch from one HTTPS dictionary source to another, this reuses ETag/Last-Modified values read for the old URL because saved["source"] is never compared with source. If the new URL returns 304 or a 200 whose Last-Modified is not newer than the old metadata, _refresh_http returns current and keeps the old cache; the local-source path already avoids this by matching the source name, so the HTTP path should clear validators unless they belong to the requested URL.
Useful? React with 👍 / 👎.
1 participant
Summary
This branch rolls the shared en-GB-oxendict spelling foundation into both the
Copier template repository and every rendered Python or Rust-enabled project.
It conditionally refreshes the estate dictionary into ignored cache files,
merges narrow local policy, commits deterministic
typos.tomloutput, pinstyposat one Makefile source of truth, and enforces spelling locally and inGitHub Actions.
The change also corrects all spelling findings in maintained template prose.
Two verbatim exports of upstream Copier documentation remain unchanged and are
excluded only in the parent overlay. The Microsoft Learn citation title is
likewise ignored by an exact pattern rather than rewritten.
No linked issue or roadmap task was found for this estate rollout.
Review walkthrough
for the shared-base decision and trade-offs.
and core refresh helper, then confirm their copies under
template/scripts/are byte-identical.
plus CI workflow
for the pinned, serialized spelling gates.
and generated-project contracts for cache identity, offline reuse,
deterministic TOML, drift, property invariants, the real pinned binary, and
Copier output.
particular attention to preserved upstream names and quotations.
Validation
make check-fmt: passed.make lint: passed; Ruff and 100% Interrogate coverage are green.make typecheck: passed.make spelling: passed withtypos1.48.0.make test: passed; 41 tests passed and two opt-inacttests skipped.mbake validate Makefile: passed.markdownlint-cli2: passed for all ten changed prose files.nixie --no-sandbox: passed.git diff --check: passed.The repository-wide Markdown lint command also reports 497 pre-existing
findings in the two verbatim Copier documentation exports; neither file is
changed by this branch, and the bounded changed-file Markdown gate is green.