Plugins

Semantic context watcher for DSH agents: maintains a journey ledger with flash summarization and MinHash novelty detection, folds milestones, and can inject long-term context with a three-level stall response; injection and the stall-2/3 responses are off by default.

Registers the Akasha Book memory server over stdio and exposes its 22 akasha_* tools to DeepSeek Harness, covering lookup, briefs, revision chains, audits and session recall. 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.

Schedules Akasha sleep distillation on idle or timer, and injects a wake note for new sessions plus a per-turn memory pulse; the optional idle-resume behaviour is off by default. 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.

Records host events — turn ends, tool results, agent errors, idle transitions and assistant output — as append-only JSONL for Akasha metrics, recall checks and output audit. 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.

Write guard for the Akasha Book store: blocks tool calls that write into the memory data directory, and injects the store usage contract and self-layer sections into the system prompt. 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.

Adds a permanent Delete session action to the sidebar session menu, behind a confirmation dialog that reports the log size, running turns, subagents, background jobs and reminders bound to the session; the id is then released from the live, archive and workspace registries, so the row stays gone on refresh instead of folding back in.

Mirrors other coding agents' sessions into DeepSeek Harness as continuable tasks, one workspace per application.

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.

Agent persona management, agent memory, edit-and-regenerate for past messages: create and manage agents, each with its own identity, long-term memory, global memory and chat history.

Watchdog for quota exhaustion: on a 429 or quota error it creates a recurring schedule that re-sends a continue-the-task prompt until a turn closes normally, so a long task resumes without manual restarts; /keep-running list and /keep-running cancel <id> manage those schedules. Requires @deepseek-ai/dsh-schedule to be mounted first (it registers the schedules).

Live multi-way tree of the current session's agents in the DeepSeek Harness conversation view and right sidebar, with status, plan progress, tokens, cost (requires dsh-cost-meter), and runtime on every card.

Runs a chosen power action (shutdown / restart / hibernate / sleep / lock / logoff) once every Agent session and background job has gone idle: the plugin samples in-process sessions once per second, counts running sessions as always busy, checks running background jobs through a configurable option (considerJobs, on by default, shown with its live count in Settings), waits a confirm window and then a cancellable countdown, and shows a draggable bottom-right card with the current phase and remaining seconds; the enable toggle never survives a host restart, any newly started session or Cancel aborts the countdown, and if the agents service is unavailable the machine is treated as busy so nothing ever fires. Windows only (the built-in shutdown / rundll32 actions); every action except none degrades to none elsewhere.

A social deduction game played against your own model configurations. A table has N seats (six by default, one of them yours) and some of the rest are played by agents bound to different provider, model, temperature, system prompt and disguise settings; you interrogate them and cross-check the answers to work out which seats are not human. Seat identity and each agent model configuration stay hidden in the host state until a seat is judged, then the disguise parameters are revealed. Every round exports a per-seat conversation JSONL plus the judgment record, and the same seed with the same move script replays byte-identical, so runs with different models or disguise strengths can be diffed.

Adds a dshmarket entry to the DSH sidebar footer, sharing a row with the Agents-Anywhere remote-control entry and sitting to its right, and opens the market panel in an overlay.

Deterministic prompt-injection interception: tool results from file reads, repo searches and web fetches are scanned before they enter model context; high-severity findings quarantine-wrap or block, and credential-material files quarantine on the path alone.

Deterministic write gate: scope policy denies out-of-scope write/edit calls before they touch the disk, residue rules scan the written text, and every decision lands in a content-hashed JSONL ledger; can reuse the repo's agent-pr-gate.yaml so CI and session enforce one policy.

Signed chain-of-custody for sessions: every watched tool result appends a hash-chained, ed25519-signed record, with commits bound into the chain — tampering with any line or truncating the tail fails deterministic replay verification.

Agent Studio for DSH Web: configure models, prompts, per-plugin tool bindings and Skills; trial-run with editable tool results and run history; preserve session capability snapshots; export standalone presets; draft Agents with a guided creator preset.

Persistent Bots and group rooms inside DSH. Each Bot keeps its own model, permission preset, workspace and session across restarts; a Bot can also be backed by an installed local agent CLI (Codex CLI, Claude Code, ACP agents) using that CLI's own login and models. Unaddressed messages can be triaged by the room leader, the room accumulates a shared experience card, and every answer is a run in a durable ledger the sidebar panel replays. New Bots default to the full-access permission (any command, any file; the form asks you to confirm the risk), so choose read-only or workspace-write to confine one; Codex CLI and Claude Code Bots at full access run without their own sandbox or permission prompts.

Multi-agent delivery workflow for dsh: a commander dispatches to fixed and temporary agents through a persisted task state machine, with a canvas and roster in the right sidebar.

Strict verification for every task: plan 2-7 steps, execute them with worker subagents, verify each deliverable with an independent memoryless verifier subagent, and fix in at most three cycles before reporting honestly.

A mandatory 7-step plan on every request, each step with a binary acceptance criterion, executed through worker subagents and validated by independent memoryless verifier subagents that report PASS or FAIL with evidence.

Publishes HTML pages and Markdown documents written by the agent to GitHub Pages as shareable links, with tools to update them in place, list, read back, and delete them; adds an Artifacts sidebar panel and a bundled page-design skill.

Code retrieval engine exposed as an MCP server: four tools (code_search, code_outline, code_index, index_status) over a SQLite FTS5 index with BM25 ranking, CJK bigram indexing, declaration-aware tree-sitter chunking, incremental reindexing, and a three-layer secret filter. The bigram index matches Chinese-language queries against English code, and the default path needs no vector store or embedding model. Requires a local Python 3.10-3.12 engine installed by scripts/install.sh, and CODERAG_ROOT set in the profile patch.