dsh-subagent-model-policy
Session-scoped subagent model selection policy, model pools, concurrency limits, and execution evidence for DeepSeek Harness.
Install
No clear install command was found in the current repository evidence.
Plugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Manage session-scoped subagent model selection policies with fixed model or agent-selected subsets
- Filter candidate model pools based on host-authorized models and capabilities
- Enforce session-level subagent concurrency and recursion depth caps alongside host quotas
- Track and display verifiable execution evidence and response routing in an Execution Insights panel
- Provide subagent delegation tools (subagent_policy, delegate_with_policy) for structured agent invocation
- Integrate seamlessly into DeepSeek Harness right sidebar and session title bar UI
Useful For
- Constraining subagents to specific efficient or specialized LLM models during complex task delegation
- Preventing runaway recursion and excessive parallel subagent executions in a session
- Auditing subagent routing and model invocations using real assistant response evidence
- Setting default subagent delegation policies for newly spawned chat sessions
Who It Fits
- DeepSeek Harness users delegating complex multi-step workflows to subagents
- Developers seeking granular model control and execution auditing for subagent teams
- Power users managing LLM token consumption and model quotas during agent tasks
Documented Limitations
- Does not manage API keys, credentials, or host-level model authorizations
- Cannot expand permissions beyond models already enabled in host settings
- Native delegation commands that cannot specify target models may be rejected if policies require exact matches
- Policies are session-scoped and do not support cross-session shared policy repositories or project-wide defaults
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 1 runtime, 0 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- ChenMuDX/dsh-subagent-model-policy
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 5a531c3 · 2026-11-12
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 2GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-11-12
- Last release
- 2026-11-10
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed security.
View plugin →Native SQLite-backed task management and project board bundle with Web UI and Agent workflow tools for DeepSeek Harness.
View plugin →Knowledge graph memory and context engine for DeepSeek Harness with cross-session recall.
View plugin →