Plugins

A DSH context-compaction plugin: when the route supports images, it renders the middle of a session history into locally generated 1-bit bitmap frames for the vision model, while the exact head and tail, a bounded exact-token index and a FILES index stay as text.

Kifu-style context compression for long DSH sessions: each step folds new turns into a DAG (node = position, edge = attempted fix), injects only a ~417-token hot list (2000-edge fixture, L5 tier), and adds failure memory plus position-repetition detection. Each span is summarized exactly once, so what is retained does not decay with the number of compactions.

Folds oversized tool results into on-disk spill files with deterministic head and tail markers, indexes compaction summaries in a searchable ledger, and extracts cross-session memories with per-project scoping. Any folded content is restored byte-for-byte on demand through one tool call.

Context indicator for the DeepSeek Harness composer: segmented occupancy, compression points, and the native auto-compaction line (flashes red when crossed). Supports preview-then-confirm compaction (/bc), seamless handoff (the old session becomes "History N" while the new one keeps the name; a relay bar above the composer shows the full handoff chain with two-way jumps), and message pinning with stale-pin labels. Thresholds, colors, and auto-archive after handoff are configurable in Settings.

Set an earlier automatic-compaction threshold per model on DeepSeek Harness: /autocompact writes a session-only override keyed by exact provider/model (off falls back to the backend defaults, default clears it), a Settings → Autocompact page manages the persisted per-model thresholds every session inherits, and a composer status entry shows the current reading.

Injects a small continuity pointer at the start of a new session, naming the previous session and any handoff file, and reuses DSH's own compaction summary when there is no handoff file.

Notifies you about 11 configurable DSH agent events (task completion, questions, denied approvals, background subagents/goals/jobs, team tasks, context compaction, triggered schedules, plugin startup and permission changes) as browser Web Notifications through a bundled service worker, falling back to Windows toast or Linux D-Bus, with three silence levels and click-to-open.

Stops DeepSeek Harness from compacting (summarizing) your conversation far too early. Without it, compaction fires around half-full on smaller context windows; with it, compaction waits until the window is as full as you want (80% by default), settable per provider/model. It only changes when compaction happens — what a summary keeps is still DSH’s decision.

GLM Mode agent preset for zhipuai/glm-5.3-flash: PTC/Code Mode tool presentation, a reasoning loop guard and a tool spin guard (live-incident driven), and GLM-specific auto-compaction at 75%/22%.

Game-style floating HUD: balance HP bar, context MP bar, official peak/valley pricing with countdown, auto-compaction under 5% remaining, and memory-carrying new conversation.

Preview conversation context and selectively keep, summarize, or omit exchange groups before applying persistent compaction through Harness session services.

Project-level memory built around a ledger whose structure the AI designs per project; the plugin only handles detection, injection, write-back, archiving and git. Memories are split by meaning: the active ledger holds current state, the turn journal is append-only, and decisions, the goal tree and lessons are one-card-per-file (with a multi-dimension index over the card folders); the fundamental principles file can be changed only by the user. There is a single compaction mode: before compacting, the AI sorts the work into three buckets - what must stay in context and is re-injected verbatim, what is written to the project's _stash/ for later lookup, and what is dropped. When a conversation is opened in a container workspace holding several projects, it can be locked to one sub-project (the lock lives in the plugin's own home and survives restarts; it leaves no marker in your project). Also an activity log with five levels, where L4 stores the user's own words verbatim (never injected, queryable on demand). Before each compaction a verbatim capsule (user quotes, raw errors, changed files) is written to disk, and both the capsule and its source material survive a restart; a handoff document lets a new conversation resume the previous one. 21 tools, 12 subcommands, 39 settings (one of them switches whether the settings panel or each project's manifest wins). Runs locally, no runtime dependencies.

Model-driven context-window rollover bundle for the DeepSeek Harness: fresh working context, durable model-managed notes, a small verbatim recent tail, and targeted history recovery — no summarization.

Context curation for DeepSeek Harness: content-aware tool-output slimming, dead-log sweep, pinned user requirements and in-flight work, archive-then-compact with an audit trail.

Input-bar prompt optimizer: rewrites drafts with 6 strategies × 3 languages plus custom instructions, optional goal/todo/compaction-summary/tool-result and chat context, a confirm dialog, last-5 history and three-tier settings persistence.

A Taffy mood mascot for the DeepSeek Harness Web UI: the corner GIF reacts live to agent state — approval pending / approved / rejected / begging, thinking, tool runs, interrupts, ask_user_question waiting, compaction, long-task fatigue, idle-ignored approval, idle / sleeping — with SSE-pushed state, drag positioning, middle-click console, tool-card mirror console, per-mood locking, persisted appearance settings and per-day bucket statistics.

Analyzes conversation images through mode-specific prompts (caption, UI, document, grounding, topology, etc.) and injects structured evidence with coordinate primitives (boxes, points, refs) as text, with session-level caching for reuse across replay and compaction.

Enhanced auto-compaction defaults for DeepSeek Harness agent presets: apply tuned threshold/retention budgets and per-model policies with one command, idempotent with backups and rollback.

Windowed handoffs on top of DSH native compaction: each compaction appends a bounded window message (goal, todos, recent user instructions, notes), with session-private notes, paged history recall and a /ctx switch; notes and history tools appear after the first rotation.

DSH SMOOTH: config-only bundle for a lighter DSH UI - compact transcript and usage views, 16 px font and 200 ms job polling out of the box - plus a troubleshooting SKILL.md and opt-in recipes (appended by hand to your own cordis.patch.yml or the profile) to remove the Agents-Anywhere "Reconnect" button, slim the tool list, drop legacy sub-agent bundles and make compaction thresholds take effect. User patches still win; rollback = remove the bundle.

Layered context compression for DeepSeek Harness: folds old turns into model-written L1–L3 summary blocks, maps what each layer holds, and wakes the model when the context crosses a size line or keeps growing. By default it requires DSH's experimental Session Search plugin (session_event_read / session_event_search); without it the tools stay disabled unless requireSessionQuery is turned off.

Layered long-term memory for DeepSeek Harness - a merge of AirPineApplea/feiyu-memory 4.0.2, dsh-soul-md and dsh-shallow-memory (do not install it alongside those plugins): a diary distilled from finished turns, a hand-written feelings diary, a persona card with version history, a hand-note injected in full every turn, and a short-TTL note layer, each capped separately so per-turn injection stays small; ships agent tools and a sidebar panel for recall, editing, compaction, and backup or restore from a local file, WebDAV or a gzip archive.

DSH plugin: mark messages as invalid so an operator annotation digest steers what a compaction checkpoint absorbs. Cache-preserving: appends after the cached prefix, never rewrites history.