Unverified50% confidenceFactExact time
context-mode's answer to information loss is indexing: when an intent is passed in and the output exceeds 5KB, the output is chunked into SQLite FTS5 and only the best-matching passages are returned.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/17/2026
First Seen
Valid until: 1/15/2027
Sources
Related Entities
Related Claims
UnverifiedIn multi-turn conversations, elliptical queries with anaphora perform poorly when used directly for vector retrieval, so query rewriting using an LLM to rewrite them into self-contained queries is a common approach62% similarUnverifiedAfter use, ScopeCairn must run the scan command to rebuild the index, otherwise the next context query will be based on outdated data.62% similarUnverifiedBy adding to the prompt 'you are seeing part of this database; if you need more information, refuse to answer', schemagate reduced incorrect answers from 16% to 5% in a 100-question pilot.61% similarUnverifiedQuery caching, result caching, and materialized views all presuppose that "the same question" produces "the same bytes", and that presupposition collapses when queries are generated by an LLM.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1054912API
curl https://kongchang.com/api/v1/knowledge/claims/1054912MCP
get_claim(id=1054912)