@joekytc/dsh-swarm
A governed swarm of six specialist DSH agents (orchestrator, planner, knowledge-base bridge, developer and two reviewers) that turns a requirement into a strict phase pipeline with machine-verified delivery evidence, review-gated merges, a full audit-log event stream and a live kanban tab; design inspired by the Hermes Agent kanban
Install
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add @joekytc/dsh-swarmREADME
Read the full README ↗Configuration
All keys are optional; schema lives in src/config.ts. Most users only need the first three — keep the rest at their defaults.
The 「模型链」 (model chain) card in the config panel: every role gets its own model — pick provider, model and reasoning effort per role; roles you leave untouched show 「继承」 (inherit) and follow the default.

| Key | Default | Description |
|---|---|---|
storageDir | $DSH_HOME/storages/kanban | Event log (events.jsonl), orchestration state, per-task workspaces, dispatcher.log. Value must use the unquoted !!js dshHomePath("storages/kanban") form — quoting degrades it into a literal string |
wikiVault.baseUrl | '' (empty) | wiki-vault HTTP service for KB reads/writes — required for KB features; set to your own server |
wikiVault.pagePrefix | projects/ | Namespace prefix for generated wiki pages |
roles.models. | {} | Per-role model: { provider, model, reasoningEffort?, fallbacks?[] } |
roles.models..reasoningEffort | high | Default reasoning effort for all roles |
roles.models..fallbacks | [] | Silent fallback candidates (audited via [model-fallback] comment) |
dispatcher.staleTimeoutSeconds | 14400 | Heartbeat timeout; running task without heartbeat is reclaimed |
dispatcher.maxRetries | 3 | Failure retries before circuit → blocked(gave_up) |
dispatcher.heartbeatIntervalSeconds | 300 | Watchdog heartbeat period |
dispatcher.maxProtocolViolations | 2 | Protocol-violation guardrail: once consecutive violations reach this many, the next one is final (gave_up) |
dispatcher.maxReworksPerRole | { pt: 3, dt: 3 } | Max review rework rounds before review/gave-up + [review-final] |
prefixRoutes.plan | /plan: | Command-mode phase-0 planning prefix |
prefixRoutes.openspec | /openspec: | Command-mode approve-and-execute prefix |
prefixRoutes.learning | /learning | Lessons / retrospective prefix |
prefixRoutes.send | /sms | Free-delivery prefix (DM with -s) |
memory.enabled | true | Memory recall index; false makes planning_memory_recall return a disabled notice |
memory.maxIndexEntries | 8 | Max recalled memory entries (1–20) |
ui.enabled | true | Declared switch; not consumed yet — the tab registers unconditionally |
ui.contentMinWidth | 715 | Declared lower width bound (px); not consumed by the client yet — the tab follows the host conversation width |
ui.contentMaxWidth | 780 | Declared upper width bound (px); not consumed by the client yet |
ui.sseHeartbeatSeconds | 20 | SSE heartbeat interval |
gates.enabled | true | TDD measurement gate; false → silent skip (no event) |
gates.timeoutMs | 600000 | Per-command gate timeout (ms), SIGKILL at the deadline |
gates.forbidden | ['rm -rf /', 'git push'] | Command-blacklist substrings (defence in depth) |
evidenceReplay.enabled | false | L3 replay of model-written commands — not a sandbox, see Issue evidence check |
evidenceReplay.timeoutMs | 600000 | Per-replay command timeout (ms) |
evidenceReplay.allowPrefixes | ['npx --no-install vitest', 'npm test', 'npm run build', 'npm run typecheck', 'tsc', 'eslint'] | Allowlisted tool prefixes (word-boundary match) |
imDelivery.enabled | false | WeCom delivery via dsh-im (W3 wrap-up / chain blocked / review gave-up) |
imDelivery.botId | '' | Empty = auto-discover the only wecom bot |
imDelivery.targetId | '' | Empty = auto-discover the only saved group target |
imDelivery.dmTargetId | '' | DM target for /sms -s |
imDelivery.fallbackBotId | '' | Bot used when preset-based matching finds nothing |
reviewEngine.mode | delegate | delegate or managed — see Review engine (ocr) |
reviewEngine.managed.provider | '' | Model-chain provider id used in managed mode |
reviewEngine.managed.model | '' | Model-chain model id used in managed mode |
wikiWritePresets | ['swarm', 'kanban-w', 'ptc'] | Presets allowed to call wiki_write (page paths are still whitelisted by namespace) |
Configuration notes
- Mode, provider and model are all chosen on the 「评审引擎(ocr)」 card; the provider/model dropdowns share the same catalog as the model chain;
- After picking, click 「应用到 ocr」 (Apply to ocr) — the system writes the wiring into ocr's custom config (
dsh-managed); the API key is resolved from the dsh model config and written into ocr, never shown in plain text in the panel; if resolution fails it degrades gracefully and points you to a manualocr config providerin a terminal; - When managed is not ready, the ocr tool refuses the managed call and returns delegate guidance; the reviewer switches to delegate mode — nothing is blocked.
Official docs: Installation · Model configuration · Delegate mode