dsh-py-codeact
Python-based CodeAct execution loop for DeepSeek Harness with persistent IPython session state and bridged harness tools.
Install
$ dsh plugin --profile <name> add dsh-py-codeactPlugin 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
- Persistent IPython session maintaining variable bindings, history, and magics across cells
- Bridged tool execution exposing harness and MCP tools via virtual `__dsh__.tools` module
- Exclusive CodeAct mode restricting the model-facing tool schema to Python while enforcing sub-call execution guards
- Rich trajectory tracking logging bridged tool invocations as native SUBTOOL session events
- Custom UI card rendering syntax-highlighted Python code execution in DeepSeek Harness
- Intelligent runtime features including redundant-import warnings, readable repr formatting, and async cancellation
Useful For
- Data analysis and multi-step computational workflows requiring state persistence between reasoning steps
- Complex automation tasks that dynamically compose multiple harness and MCP tools inside Python scripts
- Programmatic agent loops operating in exclusive CodeAct mode for reduced prompt overhead and structured execution
Who It Fits
- DeepSeek Harness agent developers
- Data scientists and Python automation engineers using DSH
- AI workflow designers seeking persistent REPL execution
Documented Limitations
- Direct subprocess writes to standard file descriptors (fd 1/2) are not captured directly unless captured at Python level
- Interpreter state cannot be reconstructed from session replays alone
- Provides process-level isolation rather than a hardened security sandbox; model code has Python shell-level capabilities
- Requires `uv` installed for initial PEP 723 environment resolution on cold start
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, 2 development, 9 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
- CNSeniorious000/dsh-py-codeact
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 71592ff · 2026-09-18
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
- 1GitHub stars
- Forks
- 0
- Open issues
- 9
- Last commit
- 2026-09-17
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed safety and session audit.
View plugin →Native SQLite-backed local project taskboard plugin and UI for DeepSeek Harness with Agent claim and review flows.
View plugin →Compatibility bridge and host ABI enabling unmodified Pi plugins to run natively on DeepSeek Harness.
View plugin →