context-compaction 9

One DeepSeek Harness Codex capability bundle for ChatGPT login, LLM access, Web Search, and durable Image Creation

Bounded context compaction, session-scoped summary reuse, explicit memory controls, and diagnostic-preserving tool pruning for DeepSeek Harness.

A persistent multi-step task stack for DeepSeek Harness agents: focus_task / focus_complete / read_focus plus a /focus command, with zero automatic prompt injection

Structured handoff compaction and official session-history retrieval for DeepSeek Harness

Model-autonomous context compaction for DeepSeek Harness: mind_map surveys the agent's own context surface (seqs, token weights, clear-boundary markers and the clear-mind playbook), clear_mind replaces a chosen span with a model-written checkpoint through

Observational memory for DeepSeek Harness: background observers distill session work into observations and durable reflections, so long sessions survive compaction with their decisions intact.

Put DSH's automatic context compaction trigger where you want it, per provider/model. Stops DeepSeek Harness from condensing a conversation far earlier than the configured threshold on models with smaller context windows.

Six-layer agent memory for the DeepSeek Harness: identity / behavior / cognitive / information / experience / skill layers plus working memory, backed by per-workspace SQLite (FTS5 + vector) with behavior-rule enforcement, LLM consolidation, skill & exper

Visual percentage and token settings for official DeepSeek Harness compaction