Skip to content

docs: clarify LangChain ban ≠ Langfuse (observability allowed + in use)#2204

Open
Mikecranesync wants to merge 1 commit into
mainfrom
docs/langchain-not-langfuse
Open

docs: clarify LangChain ban ≠ Langfuse (observability allowed + in use)#2204
Mikecranesync wants to merge 1 commit into
mainfrom
docs/langchain-not-langfuse

Conversation

@Mikecranesync

Copy link
Copy Markdown
Owner

Why

This session nearly deleted the (sanctioned, wired) Langfuse integration after confusing the No LangChain hard constraint with a ban on Langfuse. They're different tools — LangChain is a banned LLM-orchestration framework; Langfuse is observability/tracing that's allowed and in active use (mira-bots/shared/langfuse_setup.py, every architecture doc, the inference-routing skill).

What

One-line clarifier at the 3 highest-traffic enforcement points (not all ~30 mentions — that'd be noise):

Each now says: the ban is LLM-orchestration frameworks only; Langfuse ≠ LangChain, allowed, in use, don't flag/remove it under this rule.

Docs only. No version bump. The LangChain ban itself is unchanged.

… use)

A session confused the "No LangChain" hard constraint with a ban on Langfuse and
nearly removed the (sanctioned, wired) observability tool. Make the distinction
explicit at the three highest-traffic enforcement points so it can't recur:
root CLAUDE.md PRD §4, .claude/CLAUDE.md code-change rules, and the mira-platform
PLT-070 FATAL gate. LangChain = banned LLM-orchestration framework; Langfuse =
allowed observability/tracing (mira-bots/shared/langfuse_setup.py). Docs only.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CS9fxC3gdSUJDJqHw1uMiu
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant