falling-ts/dsh-force-compact
Forces context compression when running low-context llama.cpp models such as Qwen3.8-27B, improving model efficiency and usage smoothness, together with well-refined compaction prompts.
About this plugin
A DSH Cordis function plugin that keeps the agent's working context lean by design: serve Qwen3.8‑27B on a self-hosted llama.cpp with a modest context, and the plugin shrinks the conversation itself — a large-window feel with no API cost and no data egress.
$ dsh plugin --profile web add @falling-ts/dsh-force-compact$ dsh plugin --profile web add github:falling-ts/dsh-force-compactHealth breakdown
62 / 100Score reflects license, community signals, documentation and distribution. It is not a code audit — review the source before installing.
Security
Key metrics
Related
Related plugins
Session-level superagent: watch one GitHub repository and wake this session when an issue or pull request changes; requires a logged-in gh CLI, and the credential never reaches the model.
In-place conversation rewind in the same session window without forking (Claude Code /rewind semantics): a per-message ↶ button cuts the model context back to any user message, with an optional Claude-Code-style file restore from disk-persisted before-backups.
DSH BTW is a community-maintained DeepSeek Harness plugin, not an official DeepSeek AI product. Type /btw your question in the current conversation to get a context-aware answer in an independent bubble without interrupting the main task. Supports DSH Web and desktop apps that include DSH Web.
Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models. Within a turn it supports skeletonized information compression with a low original-text retrieval rate; at the tail of a turn it supports a turn-tail intent summary implemented purely by content substitution; context content stays safe, and the whole process runs inside the official JSONL compression.
Settings-page manager for archived DeepSeek Harness sessions: restore an archived session to its previous workspace position or permanently delete it (direct physical deletion, no backup layer). Adds a red permanently-delete item to the session context menu and three agent tools. Deleting an open session works immediately; the leftover in-memory copy is hidden behind an archive tombstone until the next restart.
DSH session manager: delete with trash/restore/purge, restore archived sessions, recent-activity stats, continue/pause, open log folder, unread markers, fork into a new chat, workspace grouping and sorting, context compaction threshold.