dsh-shadow-mind
DeepSeek Harness 的并行认知运行时，移植自 pi-shadow-mind
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add dsh-shadow-mind@0.1.4Shadow Mind 以 dsh-shadow-mind 发布，当前版本为 0.1.4。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
Parallel cognitive runtime for DeepSeek Harness (DSH / Cordis).
This package is a DSH port of the original pi-shadow-mind project, which runs multiple "Shadow Mind" agents beside a main agent to provide independent reviews, fact-checking, and parallel cognitive work.
Status: functional prototype / early port. Core heartbeat scheduling, read-only shadow agents, and management tools work end-to-end. Several advanced features from
pi-shadow-mindare not yet fully migrated. See Gaps vs pi-shadow-mind below.
config.json via model tools./shadow pause and /shadow resume; new user input increments the epoch and cancels running shadows from the previous epoch.DSH plugins are loaded through a Cordis composition (profile or agent preset).
dsh plugin --profile web add dsh-shadow-mind
For local development, point to the package directory instead:
dsh plugin --profile web add /path/to/dsh-shadow-mind
The package ships a cordis.patch.yml. dsh plugin --profile web add applies it automatically, so no manual cordis.yml editing is needed.
Restart DSH and the plugin will be loaded. The package exports a default Cordis plugin factory from dist/index.js.
Shadow definitions and global config live in:
~/.dsh/agent/shadow-minds/
├── config.json
├── grounded-reviewer.md
├── requirement-keeper.md
└── ...
Example config.json:
{
"heartbeat_probability": 0.33,
"max_parallel_shadows": 2,
"default_shadow_timeout_seconds": 120,
"headless_drain_timeout_seconds": 30,
"result_batch_window_ms": 5000,
"default_shadow_model": null,
"default_thinking_level": "low",
"random_seed": null
}
Example shadow definition grounded-reviewer.md:
---
id: grounded-reviewer
name: Project Grounding Checker
enabled: true
activation_probability: 0.6
run_with_model: openai/gpt-5-mini
thinking_level: low
tools:
- read
- grep
- glob
---
Check whether the main agent's claims are supported by the current workspace. If nothing is worth reporting, reply exactly: NOT_RELEVANT.
Use the single /shadow umbrella command:
/shadow status
/shadow probe <id> [tools]
/shadow list
/shadow clean
/shadow auto <on|off>
/shadow pause
/shadow resume
These are registered as model-callable tools:
list_shadowscreate_shadowupdate_shadowdelete_shadowenable_shadowdisable_shadowtrigger_shadowread_shadow_configwrite_shadow_configThe following features from the original pi-shadow-mind are not yet fully migrated:
| Feature | Status |
|---|---|
| Independent Shadow AgentSession | Partial: DSH continuable subagents are used instead of a separate Pi AgentSession. |
report_to_main tool | Missing: DSH native background notices are used instead. Report batching and steer/followUp are not yet replicated. |
Tool allowlist resolution (resolveShadowTools) | Simplified: missing-tool reporting and report_to_main injection are not implemented. |
| Per-shadow model auth check | Missing: run_with_model is passed as agentOptions, but auth validation is not performed. |
Per-shadow timeout_seconds | Not enforced: DSH subagent spec does not expose a direct per-run timeout. |
Per-shadow thinking_level | Not applied: DSH uses reasoning effort, which is not yet mapped. |
| Shutdown drain / headless mode | Missing: no waitForSettled or headless drain. |
| Debug session logs | Skipped: per-user request, no JSONL session logs are written. |
| UI status panel / message renderer | Partial: a Client indicator exists in the dynamic prototype; the real package currently only exposes /shadow. |
| Test suite | Missing: original tests were removed during the port and not yet rewritten for DSH. |
See the original DESIGN.md for the full design (this is the original pi-shadow-mind design; it describes goals that are only partially implemented in this DSH port).
npm install
npm run typecheck
npm run build
MIT