Context Fragmentation
Anti-pattern: the LLM cannot hold multiple interconnected constraints in mind simultaneously the way human working memory can; it processes each constraint locally and loses the cross-constraint view.
Problem
The model's attention mechanism, though it accesses all input tokens, does not replicate the human ability to hold a small number of interconnected variables in immediate joint focus. Each constraint gets attended to locally; the joint constraint structure is not represented. The agent satisfies each constraint individually and violates them jointly. Differs from lost-in-the-middle (positional bias) by being about simultaneous holding of constraints, not about position.
Solution
Pair with: strategic-preparation-phase (enumerate constraints explicitly), generate-and-test-strategy (verify against explicit list), large-reasoning-model-paradigm (LRMs handle this better via deliberation). For severe cases, decompose into sub-problems whose constraint sub-webs are small enough to hold.
When to use
- Never as a steady state. Cite when reviewing tasks with constraint webs routed to standard LLMs without preparation step.
- Use as the failure-mode label in design reviews.
- Surface in agent capability mapping.
Open the full interactive page →
Diagram, neighbourhood map, code examples, related patterns and full provenance.