Rework docs strategy: parallel maintenance, remove Vale, add audit/sync skills#1
Merged
Merged
Conversation
README is now the canonical, complete reference (all 12 components plus a components-reference table). The LangChain provider page is generated from it by the sync-langchain-docs skill (README -> MDX), replacing the deleted docs/provider.mdx as canonical; sync.py is trimmed to docs-repo path resolution (--path/--repo). Add Vale prose linting in lockstep with the docs-repo house style: .vale.ini and .github/vale/styles/ copied from langchain-ai/docs, a 'make lint_prose' target, a gitignored PostToolUse hook (.claude/) that lints README.md after edits, and CLAUDE.md documenting the 'lint the README after any change' convention. Docs-parity tests are retargeted from provider.mdx to README (test_readme_parity.py, test_readme_examples.py unit+integration, tests/readme.py helpers); tests/docs.py and test_docs_parity.py are removed. Also includes pending working-tree changes to the package, tests, and examples (client-only base refinements, tool kwargs, the dql_explorer web app, and the quickstart notebook). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
…throughout user-facing code The langchain-ai/docs CI flags langchain_core imports that have langchain re-export equivalents (messages, tools). Fixes the docs PR check by sourcing from langchain.messages / langchain.tools in README, examples, and tests. langchain added to the test dep group so the ChatDiffbot README block stays executable in the unit suite. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Remove Vale config (.vale.ini, .github/vale/styles/) and the lint-readme PostToolUse hook — prose linting now runs in the docs repo only, with findings propagated back here manually - Remove lint_prose Makefile target - Update CLAUDE.md Documentation section to describe four equally-weighted docs surfaces (README, providers hub, tools page, retrievers page) with no single source of truth - Rewrite sync-langchain-docs skill: reads all four files before acting, updates whichever need it, links instead of duplicating within langchain-docs - Add audit-langchain-docs skill: runs docs-repo Vale, checks API coverage and import freshness, propagates fixes back to README.md and Python source - README: drop prose-linting section; update Authentication section wording Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
.vale.ini,.github/vale/styles/,lint_proseMakefile target,lint-readmehook) — prose validation now runs in the docs repo, with findings propagated back here via the audit skillCLAUDE.mdto describe four equally-weighted docs surfaces (README, providers hub, tools page, retrievers page) with no single source of truthsync-langchain-docsskill: reads all four docs files before acting, updates whichever need it, enforces link-don't-duplicate within langchain-docsaudit-langchain-docsskill: runs docs-repo Vale, checks API coverage and import freshness, propagates fixes back to README and Python sourcelangchain_core.messages/langchain_core.toolstolangchain.messages/langchain.toolsexamples/README.mdTest plan
make lintpassesmake typingpassesmake testpasses🤖 Generated with Claude Code