dsh-task-orchestrator
Plan-first task orchestration plugin for DeepSeek Harness with isolated workers, queue concurrency limits, and role-based model controls.
Install
$ dsh plugin --profile web add https://github.com/hasan-aghayev/dsh-task-orchestrator/releases/download/v1.2.0/dsh-task-orchestrator-1.2.0.tgzPlugin 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
- Plan-first task orchestration via native DSH TODO and the task_orchestrate tool
- Isolated subagent execution using spawn contexts with custom tool allow-lists and token budgets
- Dependency-aware task queue supporting up to two concurrent streams by default with context-aware scheduling
- Role-specific model provider, model selection, and reasoning effort controls for orchestrator, worker, and reviewer
- Versioned state checkpointing via native todo/write snapshots to handle retries and recover interrupted runs
- Mandatory final reviewer task dependency ensuring quality control before run completion
- Web Settings UI with atomic profile saving, catalog refresh, and slider-based context budget configuration
Useful For
- Executing complex multi-step developer tasks requiring isolated parallel research and code editing
- Coordinating multi-agent workflows with distinct reasoning budgets and role-specialized models
- Managing concurrency and context consumption across multiple subagents in resource-constrained environments
- Automating verifiable work pipelines where deliverables must pass an independent reviewer stage
Who It Fits
- Developers orchestrating complex multi-agent tasks inside DeepSeek Harness
- Engineers requiring structured delegation, token governance, and isolated subagent scopes
- Teams seeking automated multi-role execution with independent review checks
Documented Limitations
- Workers operate within a shared workspace; the plugin does not create separate git worktrees
- Parallel writes are disabled by default, and filesystem security depends on profile-level permissions and tool allow-lists
- The lexical complexity detector may overlook brief but difficult requests unless task_orchestrate is explicitly invoked
- Report compaction uses bounded string truncation rather than semantic summarization
- Does not measure physical GPU VRAM or override provider-native tokenizers
- Assigned models must already be configured in the DSH profile; the plugin does not install model runtimes
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, 31 development, 12 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.
package.json declares a prepare lifecycle script that may run during relevant package installation workflows.
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
- hasan-aghayev/dsh-task-orchestrator
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 1a768d8 · 2026-10-08
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
- 0GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-10-01
- Last release
- 2026-09-30
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 →Native SQLite-backed task management and project board bundle with Web UI and Agent workflow tools for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed security.
View plugin →Multi-agent team collaboration plugin for DeepSeek Harness enabling coordinated sub-agents, dependency-aware task graphs, and web UI monitoring.
View plugin →