Plugins

Local-first knowledge base for DeepSeek Harness: imports Word/PPT/Excel/PDF (text or scanned), EPUB and MOBI/AZW3, builds Markdown parts with page anchors, OCR quality/confidence and column-aware PDF reading order; adds an LLM-maintained wiki layer (schema.md rules, auto index.md, append-only log.md, typed notes with sources and backlinks), adds source-trust labels (high/medium/low) with trust-aware ranking and low-trust warnings, and supports ranked search, cross-KB query, precise reading/editing, and md/jsonl/zip export. MOBI/AZW3 need Calibre; legacy .doc/.ppt need Word/PowerPoint (Windows) or LibreOffice (Linux); scanned-PDF OCR downloads models on first use.

Context observability and control for DeepSeek Harness: cross-session token analytics, session-level budget/prompt/tool controls, and optional agent scaffolds. It reuses the official tokenMeter, compaction, systemPrompt, and tools.restrict seams; monitoring is read-only.

Lightweight crash-recovery for dsh: after a restart, it detects sessions whose last turn was killed mid-flight and re-injects a continuation prompt that first demands the agent verify real-world state before acting, so side-effecting operations are not blindly repeated. It only reacts to the genuine crash marker (turn/end reason 'interrupted', synthesized on cold read by session repair), so it never misfires on user cancels, rate limits or model errors - which is why it needs no error classification, backoff or configuration UI. Unlike general-purpose auto-continue plugins, it also covers the case where a subagent was interrupted mid-run: the parent turn has already ended normally while it waits, so a naive check sees nothing to resume and the whole subagent tree dies silently; this plugin detects the interrupted child and wakes the parent instead. Single host file, zero external dependencies, seven config constants.

Live context-pressure meter in the composer dock. When usage nears the limit it asks the current model for a handoff brief, starts that brief in a fresh session and switches you there, so long work can continue without hitting the window.

Delete a DSH conversation from its sidebar menu or the conversation header, optionally cascading into that conversation's associated memory nodes when you tick the box (the confirmation dialog shows the hit count before you commit); deletes land in a plugin recycle bin with restore, every action is appended to an audit log, and batch deletes are rate-limited with per-conversation rollback.

Prepares context summaries in the background and applies them at safe step boundaries, with native compaction fallback and a per-conversation history of summaries, application status, timings, and token usage.

Indexes session transcripts into the Akasha session layer as turns end, records successful compactions, and adds a per-turn rhythm line to the runtime context. Companions: Hindsight (repo memory), OpenViking (user memory), and the built-in session search (see repo README). Setup: clone the repo, copy core/ aside, then replace <AKASHA_DIR> in cordis.patch.yml with its absolute path (or set the AKASHA_DIR env var); plugins fail loudly while the placeholder remains.

Registers /compact_queue, a compaction command that does not drop the request when the session is busy: it compacts immediately when idle, otherwise queues the request in that session and runs it at the session's next idle window, with a 2-second fallback tick beside the agent status event so the trigger is not missed, a 30-minute wait cap, and /compact_queue cancel to withdraw a queued request or abort a running one. Each session keeps its own queue state from a single command registration, completion and failure arrive as a collapsed notice that does not wake the model, and every ManualCompactionError code except busy is terminal so a failure is not retried. Host half only; the core /compact command is left untouched.

Adds an "edit question" action to every user message: editing re-sends the prompt from that turn, re-attaches the original images (extra ones can be pasted in), and optionally archives the original session.

A human-in-the-loop curation workbench inside a DSH session: mark whole turns or single messages to keep verbatim or to summarize, rewrite user, assistant, tool-result and injected-context messages in place without a model call, then compress the marked ranges with model-written summaries or the official /compact. A local JSON backup is written before every write to the session.

Connects an existing local MiniMax Code sign-in to DeepSeek Harness through a loopback reverse proxy without storing an API key or signing out.

Stops compaction summaries and session titles from burning their output budget on reasoning, by lowering the thinking level and raising the token floor for auxiliary calls only.

Native multi-platform accounts and model routing with staggered check-ins, event notifications, and quota forecasts. Its background worker needs a standalone Node >=22.23.3 with node:sqlite (enforced by engines.node); Qwen Office coding additionally needs Python with cryptography and wasmtime.

Manages a relay station's many groups and rates for DSH, switching the station's billing group in place and refreshing the model list and rate on stations that expose /v1/token/group; stations without it fall back to read-only and keep serving models.

Bridges the third-party providers saved in a local cc-switch app into DeepSeek Harness: Anthropic-format tool groups become adapter routes, Codex groups are handed to the built-in pi-ai adapter, and a settings page picks which groups to import and in which order.

Grok model provider for DeepSeek Harness with model discovery, image and video generation, text-to-speech tools, and durable local media tasks over an OpenAI-compatible gateway.

Connects the MiniMax Code models to DSH - reusing the desktop app's sign-in or signing in on its own - with Anthropic-compatible model access, a live model catalog, the daily check-in that grants the free credits, and a credit balance that follows the model you selected.

LocalAI provider for language models, embeddings, reranking, speech, and image generation with LocalAI-specific controls in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.

Jina provider for embeddings and reranking in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.

Cohere provider for language models, embeddings, and reranking through Cohere's native APIs in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.

Anthropic provider using the native Messages API for language models in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.

Declares image input on relay routes whose endpoint omits modality metadata, so models that can see photos stop being rejected as text-only. This also overrides routes that are explicitly declared text-only.

Multi-model deliberation pipeline for DeepSeek Harness: independent proposals, blind peer review, program-executed evidence verification, immutable revision and independent acceptance on a fresh context.

Coastal light and dark palette for the DeepSeek Harness web GUI, built as a token-only ThemeRuntime overlay covering all 107 official alias tokens.