Plugins

Codex-style review of session file changes: per-turn cards (optionally taking over the shell edited cards) whose totals are the turn net diff, a review tab with syntax-highlighted diffs that never wrap, real line numbers, open-at-line and a draggable split, a hover preview of the whole file with three lines of context around each change, one-click per-turn revert, and the on-disk record size with a clear button in the review toolbar. Records are sharded per session, with content-addressed snapshot blobs that dedupe and are garbage collected. Light/dark presets follow the DSH theme, typography follows DSH and installed skins (or any font on the machine, with a px stepper), and a settings switch injects a think-in-Simplified-Chinese rule into the global AGENTS.md.

Local-first persistent memory for DeepSeek Harness: bounded pre-step hot-memory injection, exact and Chinese-bigram BM25 cold recall, six agent tools, approval-gated lease-lock writes with recovery receipts, and read-only governance and trajectory-review candidates.

Structured output for DSH: a no-label title card, then tables/lists/steps; per-session toggle and style.md override.

DSH side of the dsh-ecolink memory ecosystem: bridges chat.deepseek.com and DeepSeek Harness through a browser extension that harvests DSM-format memory tags and injects recalled memories into web chats, a zero-dependency local service that writes a shared memory pool, and this adapter, which injects memories pre-step and offers /ecolink-push write-back; compression is transactional (staging pool with commit/rollback).

Per-message delete for DSH: remove a user message, one reply step, or a whole assistant reply from the derived model context through the official surface-replace contract, and hide it from the visible transcript without rewriting the append-only log.

Custom modes / assistant manager: give each mode its own system prompt in the settings page — a custom prompt that is a plain file the agent loop re-reads before every model step, so an edit applies to the running session on its next step — and start it from the official standard / PTC / minimal / Cordis composition, toggling the plugin rows it mounts one by one (a custom plugin composition per mode), renaming it as you like. Several assistants coexist with their own prompts, so one machine can keep a coding assistant, a chat companion and a roleplay (RP) persona side by side — a multi-agent setup you pick from per new session. Rows left untouched stay byte-identical to the shipped ones, platform conditions included.

WeChat official account AI writing pipeline: six-step article runs (topic, outline, draft, gates, render, images) with a launch brief contract, a hot-topic board with per-item AI digests, RRULE scheduling to the draft box, a workbench UI plus chat tools and a /wewrite command, and fail-closed host approval before any draft-box push.

RSS/Atom subscription tools (list/add/remove/fetch/check/search/opml_import/opml_export/health) with cross-feed keyword search, cursor-based incremental fetch and OPML import/export, persisted to settings. A step-by-step first-run guide (3 steps) now opens inside its settings panel.

Douyin assistant plugin: picks a daily round of videos, reads comments, writes a dated report, can like and comment with an @ mention (both off by default), and publishes clips rendered by your own ComfyUI. Windows only; needs Python 3 and a system Chrome, and the first run needs the install-main-dependencies step plus a QR-code login.

Per-session execution gears for the DSH composer: an OVERDRIVE toggle turns Turbo on for the current session only, the Fast and Max gears swap the agent's planning and verification policy and may lower the request's reasoning effort, and the Host keeps the authoritative mode plus per-turn latency, step count, tool calls and whether a verification command ran.

Floating glass status bar for DSH on Windows 11 x64: an always-on-top capsule that mirrors session progress, the current step and pending approvals from a local DSH web profile, with peek and detail views; approval cards stay read-only until DSH returns its own decision receipt, and connecting to the official Desktop app is experimental and unverified.

Shows a DSH session as a conversation canvas — every turn is a node, any turn forks a real child session, and a compacted context folds into one green node you can keep talking from; the left rail groups canvases by DSH workspace and renames them in step with the session titles.

Fine-grained LLM verification for DSH agents: pairwise rewards over score-token logprobs, Probabilistic Pivot Tournament best-of-N selection, and per-step progress tracking.

Virtual product team agent preset: user-led conversation walks you through the full 12-step pipeline from idea to shipped, promoted and operated product, with staged gates and per-stage skills.

Citation tools for agents: exact DOI lookup, Crossref bibliographic search, GB/T 7714 / APA / MLA / Chicago formatting, BibTeX generation, bounded-concurrency DOI validation and health self-check. A step-by-step first-run guide (3 steps) now opens inside its settings panel.

Adds a "Task Planning" agent preset that asks requirements in versioned rounds, then writes step-by-step plans and prompts without implementing them itself.

Agent state machine plugin with a todo ledger, stall guard, phase trails and a process-isolated per-step Python worker with GUI automation lanes. Windows only; needs Python 3.10+ on PATH, and pyautogui, mss and pywinauto for the GUI lanes.

Turns each long dsh conversation into a three-level trail (topic to progress steps to milestone timeline) and shows it in a draggable overlay, where one click jumps back to the matching message in the transcript. Topics are distilled by the DeepSeek model with a zero-cost rule-based fallback, can be renamed, locked, merged by drag and drop, and support per-conversation notes plus a vector drawing board.

Real browser tools for DeepSeek Harness: browse and extract web content, fill forms, manage multiple tabs, and execute multi-step tasks, with incremental DOM, session isolation, screenshots, action-result checks, and archived evidence recall.

dsh-ecolink DSH 适配层:直读本地记忆池、pre-step 注入(打分+预算+会话去重)、#记忆名 过滤,打通网页端记忆生态

Freshness gate for the agent's test, typecheck, lint and build claims: each verification run becomes a receipt on tools/post-execute, file edits are tracked, and on agent/turn-stopping a claim whose latest receipt is stale, failed or has no readable result steers one more step naming the receipt and the files edited since.

Governed long-term memory for DeepSeek Harness: append-only evidence ledger with write guards, 7-tier authority claims, supersede chains, and budgeted pre-step injection with per-domain quotas.

Unified image generation router for DeepSeek Harness (DSH): auto-discovers image models from any OpenAI-compatible endpoint, provides draw_image and draw_list_sources tools, supports SenseNova, StepFun, Agnes, Qwen, Flux, SD, Imagen and more.

CalDAV calendar tools (list/create/update/delete/search/health) for Google/iCloud/Nextcloud/custom endpoints, with RRULE expansion, a month/week/agenda panel inside the settings page, in-panel connection setup that is tested before saving, and drag-to-reschedule in the week view (15-minute snapping, undo). A step-by-step first-run guide (4 steps) now opens inside its settings panel.