deepseek-harness-jev-pre-compaction
A pre-compaction advisor for DeepSeek Harness. Runs before the standard
compaction-basic
backend, using TypeSafe JEV to safely prune low-value tool results from model context. Original session events stay in the append-only log; only the model-visible view is replaced with compact markers or archive pointers to reduce context bloat.
Where Jev makes the decision
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
Why it matters
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
Claims & evidence
Author and repository text is preserved where clear; missing languages are enriched automatically. Checks establish source-level Jev integration, not runtime, safety, or performance validation.
About Jev
Jev is TypeSafe AI's System One decision model: it returns typed scores and choices (not free text), so agents can route, filter and gate at low latency and cost.
Source: wjw66/deepseek-harness-jev-pre-compaction — 5 stars, MIT. Listed by Awesome Jev.