XFCD
XF Contradiction Detection

Surfaces contradictions in your memory tree — you resolve, the tree stays honest.

Memory compounds. Memory also contradicts itself. Two sessions ago you said use pgvector; last week you said use Pinecone; now Claude pulls the wrong one. XFCD reads the memory tree, identifies contradictions, and hands you a resolution UX that lets you approve, override, or skip. What you approve becomes the current truth — what you override gets demoted.

Part of Memory Layer

Connect with GitHub — it's free

What it does

1

Scans the XFMT tree for contradictions.

Every stored fact is evaluated against prior facts in the same semantic neighborhood. Direct contradictions (‘yes X / no X’), preference flips (‘use A / use B’), and architectural drift (‘we decided Y / we're replacing Y’) all surface as contradiction candidates.

2

HIL approval loop — you own the resolution.

XFCD never auto-resolves on first detection. You get a recommendation per contradiction with evidence from both sides, and choose approve / override / skip. Skip keeps both active. Override demotes one. Approve establishes the new truth.

3

Trains XFPA — confidence-graduated auto-apply.

Patterns of approval train XFPA. Once a rule's confidence exceeds threshold, future contradictions of that class auto-apply without HIL — while the uncertain cases still escalate. The guardrails fade where they've earned trust, never where they haven't.

How it works

1

You run /xfcd or XFCD fires automatically on memory writes.

2

Candidates surface with recommendation + both-sides evidence.

3

Approve / override / skip per candidate.

4

Approved resolutions update the tree; overrides demote the weaker entry.

5

XFPA learns your pattern and graduates auto-apply as confidence builds.

Other modules