tenuo 0.1.0a10

Capability tokens for AI agents - Python SDK

Tenuo Python SDK

Capability tokens for AI agents

v0.1.0-alpha.9 — See CHANGELOG for breaking changes.

Python bindings for Tenuo, providing cryptographically-enforced capability attenuation for AI agent workflows.

Installation

pip install tenuo

AgentDojo Benchmark: 100% Attack Block Rate

Tested against GPT-5.1 prompt injection attacks—240 successful injections, 0 escaped. Details →

Quick Start

The Safe Path (Recommended)

Keep keys separate from warrants:

from tenuo import Warrant, SigningKey, Pattern

# Warrant from orchestrator - Warrant() accepts base64 string
warrant = Warrant(received_warrant_string)

# Explicit key at call site - keys never in state
key = SigningKey.from_env("MY_SERVICE_KEY")
headers = warrant.headers(key, "search", {"query": "test"})

# Delegation with attenuation
child = warrant.grant(
    to=worker_pubkey,
    allow="search",
    query=Pattern("safe*"),
    ttl=300,
    key=key
)

BoundWarrant (For Repeated Operations)

When you need to make many calls with the same warrant+key:

from tenuo import Warrant, SigningKey

warrant = Warrant(received_string)  # Reconstruct from base64
key = SigningKey.from_env("MY_KEY")

# Bind key for repeated use
bound = warrant.bind(key)

for item in items:
    headers = bound.headers("process", {"item": item})
    # ...

# Validate before use
result = bound.validate("search", {"query": "test"})
if result:
    # Authorized!
    pass

# ⚠️ BoundWarrant is non-serializable (contains key)
# Use bound.warrant to get the plain Warrant for storage

Low-Level API (Full Control)

# ┌─────────────────────────────────────────────────────────────────┐
# │  CONTROL PLANE / ORCHESTRATOR                                   │
# │  Issues warrants to agents. Only needs agent's PUBLIC key.      │
# └─────────────────────────────────────────────────────────────────┘
from tenuo import SigningKey, Warrant, Pattern, Range, PublicKey

issuer_key = SigningKey.from_env("ISSUER_KEY")
agent_pubkey = PublicKey.from_env("AGENT_PUBKEY")  # From registration

warrant = (Warrant.mint_builder()
    .capability("manage_infrastructure", {
        "cluster": Pattern("staging-*"),
        "replicas": Range.max_value(15)
    })
    .holder(agent_pubkey)
    .ttl(3600)
    .mint(issuer_key))

# Send warrant to agent: send_to_agent(str(warrant))

# ┌─────────────────────────────────────────────────────────────────┐
# │  AGENT / WORKER                                                 │
# │  Receives warrant, uses own private key for Proof-of-Possession │
# └─────────────────────────────────────────────────────────────────┘
from tenuo import SigningKey, Warrant

agent_key = SigningKey.from_env("AGENT_KEY")  # Agent's private key (never shared)
warrant = Warrant(received_warrant_string)    # Deserialize from orchestrator

args = {"cluster": "staging-web", "replicas": 5}
pop_sig = warrant.sign(agent_key, "manage_infrastructure", args)
authorized = warrant.authorize(
    tool="manage_infrastructure",
    args=args,
    signature=bytes(pop_sig)
)

Installation Options

pip install tenuo                # Core only
pip install tenuo[fastapi]       # + FastAPI integration
pip install tenuo[langchain]     # + LangChain
pip install tenuo[langgraph]     # + LangGraph (includes LangChain)
pip install tenuo[mcp]           # + MCP client (Python ≥3.10)
pip install tenuo[dev]           # Development tools

Key Management

Loading Keys

from tenuo import SigningKey

# From environment variable (auto-detects base64/hex)
key = SigningKey.from_env("TENUO_ROOT_KEY")

# From file (auto-detects format)
key = SigningKey.from_file("/run/secrets/tenuo-key")

# Generate new
key = SigningKey.generate()

Key Management

KeyRegistry (Thread-Safe Singleton)

Manage multiple keys by ID. Useful for multi-agent, multi-tenant, or service-to-service scenarios.

from tenuo import KeyRegistry, SigningKey

registry = KeyRegistry.get_instance()

# Register keys at startup
registry.register("worker", SigningKey.from_env("WORKER_KEY"))
registry.register("orchestrator", SigningKey.from_env("ORCH_KEY"))

# Retrieve by ID
key = registry.get("worker")

# Multi-tenant: namespace keys per tenant
registry.register("api", tenant_a_key, namespace="tenant-a")
registry.register("api", tenant_b_key, namespace="tenant-b")
key = registry.get("api", namespace="tenant-a")

Use cases:

• LangGraph: Keep keys out of state (checkpointing-safe)
• Multi-tenant SaaS: Isolate keys per tenant
• Service mesh: Different keys per downstream service
• Key rotation: Register current and previous keys

Keyring (For Key Rotation)

from tenuo import Keyring, SigningKey

keyring = Keyring(
    root=SigningKey.from_env("CURRENT_KEY"),
    previous=[SigningKey.from_env("OLD_KEY")]
)

# All public keys for verification (current + previous)
all_pubkeys = keyring.all_public_keys

FastAPI Integration

from fastapi import FastAPI, Depends
from tenuo.fastapi import TenuoGuard, SecurityContext, configure_tenuo

app = FastAPI()
configure_tenuo(app, trusted_issuers=[issuer_pubkey])

@app.get("/search")
async def search(
    query: str,
    ctx: SecurityContext = Depends(TenuoGuard("search"))
):
    # ctx.warrant is verified
    # ctx.args contains extracted arguments
    return {"results": [...]}

LangChain Integration

from tenuo import Warrant, SigningKey
from tenuo.langchain import guard

# Create bound warrant
keypair = SigningKey.generate()  # In production: SigningKey.from_env("MY_KEY")
warrant = (Warrant.mint_builder()
    .tools(["search"])
    .mint(keypair))
bound = warrant.bind(keypair)

# Protect tools
from langchain_community.tools import DuckDuckGoSearchRun
protected_tools = guard([DuckDuckGoSearchRun()], bound)

# Use in agent
agent = create_openai_tools_agent(llm, protected_tools, prompt)

Using @guard Decorator

Protect your own functions with @guard. Authorization is evaluated at call time, not decoration time - the same function can have different permissions with different warrants:

from tenuo import guard

@guard(tool="read_file")
def read_file(path: str) -> str:
    return open(path).read()

# BoundWarrant as context manager - sets both warrant and key
bound = warrant.bind(keypair)
with bound:
    content = read_file("/tmp/test.txt")  # ✅ Authorized
    content = read_file("/etc/passwd")    # ❌ Blocked

# Different warrant, different permissions
with other_warrant.bind(keypair):
    content = read_file("/etc/passwd")    # Could be ✅ if this warrant allows it

LangGraph Integration

from tenuo import KeyRegistry
from tenuo.langgraph import guard, TenuoToolNode, load_tenuo_keys

# Load keys from TENUO_KEY_* environment variables
load_tenuo_keys()

# Wrap pure nodes
def my_agent(state):
    return {"messages": [...]}

graph.add_node("agent", guard(my_agent, key_id="worker"))
graph.add_node("tools", TenuoToolNode([search, calculator]))

# Run with warrant in state (str() returns base64)
state = {"warrant": str(warrant), "messages": [...]}
config = {"configurable": {"tenuo_key_id": "worker"}}
result = graph.invoke(state, config=config)

Nodes That Need Warrant Access

from tenuo.langgraph import tenuo_node
from tenuo import BoundWarrant

@tenuo_node
def smart_router(state, bound_warrant: BoundWarrant):
    if bound_warrant.allows("search"):
        return {"next": "researcher"}
    return {"next": "fallback"}

Debugging

why_denied() - Understand Failures

result = warrant.why_denied("read_file", {"path": "/etc/passwd"})
if result.denied:
    print(f"Code: {result.deny_code}")
    print(f"Field: {result.field}")
    print(f"Suggestion: {result.suggestion}")

diagnose() - Inspect Warrants

from tenuo import diagnose

diagnose(warrant)
# Prints: ID, TTL, constraints, tools, etc.

Convenience Properties

# Time remaining
warrant.ttl_remaining  # timedelta
warrant.ttl            # alias for ttl_remaining

# Status
warrant.is_expired     # bool
warrant.is_terminal    # bool (can't delegate further)

# Human-readable
warrant.capabilities   # dict of tool -> constraints

MCP Integration

(Requires Python ≥3.10)

from tenuo.mcp import SecureMCPClient

async with SecureMCPClient("python", ["mcp_server.py"]) as client:
    tools = await client.get_protected_tools()
    
    async with mint(Capability("read_file", path=Pattern("/data/*"))):
        result = await tools["read_file"](path="/data/file.txt")

Security Considerations

BoundWarrant Serialization

BoundWarrant contains a private key and cannot be serialized:

bound = warrant.bind(key)

# ❌ This raises TypeError
pickle.dumps(bound)
json.dumps(bound)

# ✅ Extract warrant for storage (str() returns base64)
state["warrant"] = str(bound.warrant)
# Reconstruct later with Warrant(string)

allows() vs validate()

# ✅ allows() = Logic Check (Math only)
# Good for UI logic, conditional routing, fail-fast
if bound.allows("delete"):
    show_delete_button()

if bound.allows("delete", {"target": "users"}):
    print("Deletion would be permitted by constraints")

# ✅ validate() = Full Security Check (Math + Crypto)
# Proves you hold the key and validates the PoP signature
result = bound.validate("delete", {"target": "users"})
if result:
    delete_database()
else:
    print(f"Failed: {result.reason}")

Error Details Not Exposed

Authorization errors are opaque by default:

# Client sees: "Authorization denied (ref: abc123)"
# Logs show: "[abc123] Constraint failed: path=/etc/passwd, expected=Pattern(/data/*)"

Examples

# Basic usage
python examples/basic_usage.py

# FastAPI integration
python examples/fastapi_integration.py

# LangGraph protected
python examples/langgraph_protected.py

# MCP integration
python examples/mcp_integration.py

Documentation

• Quickstart — Get running in 5 minutes
• FastAPI — Zero-boilerplate API protection
• LangChain — Tool protection
• LangGraph — Multi-agent security
• Security — Threat model, best practices
• API Reference — Full SDK docs

License

MIT OR Apache-2.0