## The problem
Issue langchain-ai/langchain#35691 (closed, 98 comments): ### Checked other resources
- [x] This is a feature request, not a bug report or usage question.
- [x] I added a clear and descriptive title that summarizes the feature request.
- [x] I used the GitHub search to find a similar feature request and didn't find it.
- [x] I checked the LangChain documentation and API reference to see if this feature already exists.
- [x] This is not related to the langchain-community package.
### Package (Required)
- [x] langchain
- [ ] langchain-openai
- [ ] langchain-anthropic
- [ ] langchain-classic
- [x] langchain-core
- [ ] langchain-model-profiles
- [ ]...
## What fixed it
The ComplianceCallbackHandler RFC was closed by a maintainer with a clear verdict: LangChain won't bless a specific signing scheme, notary service, policy engine, or vendor abstraction in core, and tamper-evident audit trails don't need a core change. BaseCallbackHandler is public and stable, so ship compliance handling as a third-party package. If you hit a concrete, vendor-neutral gap in the callback API that blocks building it externally, open a focused issue with a minimal repro.