docs(langchain): add LangChain rationale docs + index the family#4
Merged
Conversation
… family Rationale docs for all 15 LangChain LC-* rules under docs/Policy/langchain/ (tool_definition, shell_safety, code_execution, ssrf, tool_behavior, agent_safety, repo_hygiene). Front-matter severity/confidence/scope match the shipped trustabl-rules pack; shared threat models (shell/code/SSRF) cross- reference the OpenAI docs. Make `langchain` a first-class index category: add it to gen_index.py's SDK_ORDER / SDK_LABEL / SDK_FULL, regenerate the master POLICY_INDEX.md (now 117 rules), and add langchain/POLICY_INDEX.md. check_rulebook.py --strict and gen_index.py --check both pass with zero warnings.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Rationale docs for the 15 LangChain
LC-*rules, pluslangchainadded as a first-class index category.Coordinated 3-repo change (merge together):
What's here
docs/Policy/langchain/{tool_definition,shell_safety,code_execution,ssrf,tool_behavior,agent_safety,repo_hygiene}.md— one rationale doc per topic, covering all 15LC-*rules. Front-matterseverity/confidence/scopematch the shipped pack; the shared shell/code/SSRF threat models cross-reference the existing OpenAI docs.tools/gen_index.py—langchainadded toSDK_ORDER/SDK_LABEL/SDK_FULLso it is a first-class index category.POLICY_INDEX.md(regenerated, now 117 rules) and a newlangchain/POLICY_INDEX.md.Gates
check_rulebook.py --strictandgen_index.py --checkboth pass with 0 warnings against the rule pack (with the trustabl-rules#7 langchain pack present).