Files
python-sdk/pkg/hanzo-tools-shell
zeekay aad145dec0 Name the generator we actually run
Our SDKs are generated by openapi-generator on our own CI. The docs said a
hosted third-party service, which we retired: hanzoai/openapi's LLM.md and its
regenerate-sdks.yml both already said so, while its README still called that
service "canonical" and told a reader to fetch an API key for it out of KMS.

Two sources disagreeing is how somebody follows the wrong one, and the wrong one
here sends them looking for a credential that should not exist.

The same claim had spread to what customers and agents read: five pages on
docs.hanzo.ai and six agent skills advertised a vendor we do not use, and
hip-0040 -- the standard for multi-language SDKs -- argued FOR it by name. The
argument survives without the brand, because it was never about the vendor: one
spec beats N hand-written clients. python-sdk's mock script also pulled that
vendor's fork of prism-cli; it takes upstream @stoplight/prism-cli now.

What is deliberately left alone is every occurrence that is not about us: a
filament material in a 3D-printer integration, a browser of that name in three
user-agent parsers, tokenizer vocabulary where the string is a token id, and
citations recording where Mux, Perigon and Stigg publish their own specs.
Renaming any of those breaks something real.
2026-08-13 14:30:19 -07:00
..

hanzo-tools-shell

Shell execution tools for Hanzo MCP with DAG support and Shellflow DSL.

Installation

pip install hanzo-tools-shell

Tools

dag - DAG Execution Engine

Execute commands with directed acyclic graph semantics.

# Serial execution (default)
dag(["ls", "pwd", "git status"])

# Parallel execution
dag(["npm install", "cargo build"], parallel=True)

# Mixed DAG with parallel blocks
dag([
    "mkdir -p dist",
    {"parallel": ["cp a.txt dist/", "cp b.txt dist/"]},
    "zip -r out.zip dist/"
])

# Tool invocations
dag([{"tool": "search", "input": {"pattern": "TODO"}}])

# Named nodes with dependencies
dag([
    {"id": "build", "run": "make build"},
    {"id": "test", "run": "make test", "after": ["build"]},
])

zsh - Primary Shell with Shellflow DSL

Execute shell commands with optional Shellflow syntax.

# Simple command
zsh("ls -la")

# Shellflow DSL syntax
zsh("mkdir dist ; { cp a dist/ & cp b dist/ } ; zip out")

# With shell parameter
zsh("echo $BASH_VERSION", shell="bash")

Shellflow Syntax:

  • A ; B - Sequential execution
  • { A & B } - Parallel execution
  • A ; { B & C } ; D - Mixed DAG

ps - Process Management

Monitor and control background processes.

ps()                     # List all processes
ps(id="abc123")          # Get specific process
ps(kill="abc123")        # Kill process (SIGTERM)
ps(logs="abc123", n=50)  # Last 50 lines of output

Additional Tools

  • shell - Smart shell (zsh > bash fallback)
  • bash - Explicit bash execution
  • npx - Node package execution with auto-backgrounding
  • uvx - Python package execution with auto-backgrounding
  • open - Open files/URLs in system apps
  • curl - HTTP client without shell escaping issues
  • jq - JSON processor
  • wget - File/site downloads

Auto-Backgrounding

Commands that exceed the timeout (default 60s) are automatically backgrounded:

dag(["long-running-command"], timeout=30)
# If command exceeds 30s, it continues in background
# Use ps --logs <id> to view output

Performance

Shellflow DSL is optimized for high throughput:

  • Simple commands: ~7M ops/sec
  • Sequential: ~2.2M ops/sec
  • Mixed DAG: ~100k ops/sec

License

MIT