petfishframework 0.1.3

petfishFramework — a general AI Agent framework

petfishFramework

A lightweight Python framework for reliable, auditable, budget-aware, and permission-aware AI agents.

Status: Alpha — API may change. Core runtime works; see Roadmap.

Quick Start (Zero Cost — No API Key)

pip install petfishframework

from petfishframework import Agent, ReAct
from petfishframework.tools.calculator import Calculator
from petfishframework.models.fake import FakeModel

# FakeModel — runs without any API key, perfect for testing
model = FakeModel.script_tool_then_answer(
    tool_name="calculator",
    tool_args={"expression": "17 * 23"},
    final_answer="391",
)

agent = Agent(
    model=model,
    reasoning=ReAct(),
    tools=(Calculator(),),
)

result = agent.run("What is 17 * 23?")
print(result.answer)  # "391"
print(result.usage.total_tokens)
print(len(result.trajectory.steps), "steps")

Quick Start (Real LLM)

pip install "petfishframework[openai]"

from petfishframework import Agent, ReAct
from petfishframework.tools.calculator import Calculator
from petfishframework.models.openai import OpenAIModel

agent = Agent(
    model=OpenAIModel(model="gpt-4o-mini"),  # or model="openai:gpt-4o-mini"
    reasoning=ReAct(),
    tools=(Calculator(),),
)

result = agent.run("What is 17 * 23?")
print(result.answer)  # "391"

Set OPENAI_API_KEY in .env or environment. Works with OpenAI-compatible APIs (SiliconFlow, etc.) via OPENAI_BASE_URL.

Budget Control (Runtime Hard Limits)

from petfishframework import Budget

# Budget is execution-scoped — pass to run() or session(), not Agent()
result = agent.run(
    "Complex calculation task",
    budget=Budget(max_tokens=1000, max_tool_calls=5, max_steps=10),
)
# Exceeding any limit raises BudgetExceeded

Permission Gate (Runtime Access Control)

from petfishframework.permissions.model import (
    Decision, DecisionEffect, PermissionPolicy,
)

class DenyExpensiveTools:
    """Custom policy: deny tools tagged 'expensive'."""
    def evaluate(self, subject, action, resource, context):
        if "expensive" in resource.tags:
            return Decision(effect=DecisionEffect.DENY, reason="too expensive")
        return Decision(effect=DecisionEffect.ALLOW)

agent = Agent(
    model=model,
    reasoning=ReAct(),
    tools=(Calculator(),),
    permission_policy=DenyExpensiveTools(),
)
# Tool calls pass through the Environment chokepoint — denied calls never execute

Replay & Audit (Event-Sourced Sessions)

session = agent.session("What is 17 * 23?")
result = session.run()

# Every step is recorded — model calls, tool calls, permission decisions
for event in session.replay():
    print(f"{event.type}: {event.data}")

# Events come from session.replay(), not from Result
# Result has: answer, usage, trajectory
# Session has: events, replay(), checkpoint()

Core Concepts

Concept	Role
Agent	Immutable recipe (model + reasoning + tools)
Session	Event-sourced execution (auditable, replayable)
Environment	Single chokepoint (all calls audited, budget-metered, permission-gated)
Budget	Hard execution limits (tokens, cost, steps, tool calls)
Permission	SARC access control with 6 DecisionEffects
Replay	AUDIT (event log), RESUME (checkpoint), RERUN (fresh)
Pass^k	Reliability metric (k repetitions + perturbation suite)

Features

• 3 reasoning strategies: ReAct, LATS (MCTS search), LLM+P (symbolic planning)
• 3 model adapters: OpenAI, Anthropic, FakeModel (deterministic testing)
• 3 routing axes: ToolRegistry (auto tool selection), Adaptive-RAG (retrieval), ReasoningStrategy
• MCP client: real stdio transport, tool discovery from external MCP servers
• Multi-agent: AgentAsTool (supervisor delegates to specialist agents)
• Structured output: JSON → dataclass (zero regex scoring)
• Conversation memory: cross-session recall via ConversationStore
• Async + streaming: dual sync/async interface

Documentation

• Usage Guide — full lifecycle, 18 sections
• API Reference — 989-line definitive reference
• Architecture — 5 core decisions
• Benchmark Results — 3-tier strategy
• Examples — quickstart, tools+retrieval, multi-agent

Roadmap

• v0.1.x (current): Core runtime works, quickstart verified ✅
• v0.2.x: Enterprise agent examples, structured audit reports
• v0.3.x: Policy engine (YAML), MASK enforcement, credential broker
• v0.4.x: Production hardening, deployment guides

Development

git clone https://github.com/kylecui/petfishFramework.git
cd petfishFramework
uv sync --all-extras
uv run pytest              # 187 tests
uv run ruff check src/ tests/

See CONTRIBUTING.md for details.

License

MIT — © 2026 Kyle Cui