dsh-tree-task-flow
Three-level tree workflow plugin for DeepSeek Harness that collapses intermediate execution context upon task completion.
Install
$ dsh plugin --profile web add dsh-tree-task-flowPlugin 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
- Organizes complex tasks into a fixed 3-level tree hierarchy (Goal -> Task -> Subtask)
- Folds intermediate execution logs from the context surface while retaining node results
- Provides 6 specialized tools (tree_task_status, tree_task_create, tree_task_plan, tree_task_done, tree_task_update, tree_task_drop)
- Provides direct slash commands (/task-tree pause, resume, done, drop, reset) that bypass model latency
- Integrates seamlessly into the DSH web UI above the chat input box with pause/resume and tree expansion
- Supports session-isolated state persistence and fail-safe fallback append operations
Useful For
- Long-running autonomous agent tasks requiring clean and persistent context management
- Multi-step software development, debugging, and code refactoring workflows
- Complex research and multi-phase data analysis where intermediate tool noise needs pruning
Who It Fits
- Developers running long-horizon multi-step tasks in DeepSeek Harness
- Power users looking to minimize context bloat and token consumption during complex workflows
Documented Limitations
- Hierarchical depth is fixed to 3 levels (subtasks cannot be further decomposed)
- Result strings are strictly required on task completion; blank results will be rejected
- Requires DeepSeek Harness web profile with Node.js 22.19+ and Cordis runtime
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 0 runtime, 0 development, 1 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
- viyiviyi/dsh-tree-task-flow
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 167603c · 2026-11-05
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
- 3GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-10-15
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Native SQLite-backed task management and project board bundle with Web UI and Agent workflow tools for DeepSeek Harness.
View plugin →Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →A bundle combining a runtime injector and task-aware reasoning-mode router presets for DeepSeek Harness.
View plugin →Comprehensive long-term memory, self-evolution, skills, task management, and multi-agent dispatch bundle for DeepSeek Harness.
View plugin →