Plugins

Manual context compaction for DeepSeek Harness: keep the latest N conversation items with stop or batch mode and a per-session compaction archive — embedded in the context meter popup when the meter panel slot exists, or a composer button otherwise.

Chat branch tree plugin for DeepSeek Harness: mind-map of conversation branches, group folders, archiving and compaction preview.

High-fidelity, faithful, bilingual, recursive compaction backend for DeepSeek Harness — a drop-in upgrade over dsh-compaction-basic.

Reports the semantic blast radius of agent code edits: which symbols changed, who calls them, and which of those callers have no covering test.

Auto-compact a DSH conversation after the current task finishes, at a user-set context threshold. Settings-page switch + slider included.

Visual percentage and token settings for official DeepSeek Harness compaction

Live account quota/balance widget for DeepSeek Harness web: DeepSeek API balance plus Kimi For Coding plan usage (weekly + 5h windows, remaining and reset countdowns) in one compact card.

File-based self-evolving memory for DeepSeek Harness v2: compression & extraction over official compaction, daily episodic layer, dream consolidation to semantic files (user/agent/memory/dream + project), catalog disclosure injection, no confidence machin

Pure-incremental directive-driven compaction for DeepSeek Harness: /compact-directive <requirement> summarizes the session middle per your requirement, /trim-directive <requirement> trims the whole conversation per your requirement

The pet that grows with your agent: 5 evolution stages earned from real signals (verified rules, completed sessions, tool calls, compactions), agent-state mirroring, and one-click growth share cards. Zero dependencies, 100% local.

Compaction backend replacing LLM summarization with a deterministic semantic extractor (keeps code/paths/commands, drops chatter) plus 28.4x KV-compression accounting.

Session context triage for long DeepSeek Harness sessions: deterministic screeners trim stale, duplicate, failed, and oversized content through the official ctx.compaction seam.

Model-authored context pruning for DeepSeek Harness through the official compaction API.

Mobile adaptation for the DSH Web UI on narrow screens: reveal drawer with the chat layer on top, drag gestures, bottom-sheet settings panel, composer and header fixes, zero desktop impact.

Post-compaction premise-drift guard: injects a one-shot notice when a compaction summary drops a critical literal anchor.

File-backed working memory: memorize/recall key premises verbatim in a session notes file so they survive context compaction losslessly.