docs: clarify LangChain ban ≠ Langfuse (observability allowed + in use)#2204
Open
Mikecranesync wants to merge 1 commit into
Open
docs: clarify LangChain ban ≠ Langfuse (observability allowed + in use)#2204Mikecranesync wants to merge 1 commit into
Mikecranesync wants to merge 1 commit into
Conversation
… 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
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
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):
CLAUDE.mdPRD §4 Create Azure Bot resource for Teams adapter #3.claude/CLAUDE.mdcode-change rules.claude/skills/mira-platform/SKILL.mdPLT-070 (the FATAL gate an agent actually checks)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.