Run your notes Agent

Learn QitOS with complete, executable notes-project code.

What you will build

Create a notes project, call tools to extract two titles and word counts, run it through a Session, and inspect the recorded result with qita. You need basic Python, but no model credentials or Docker; the fake provider is an explicit scripted double.

Prepare the project

python3 -m venv .venv
source .venv/bin/activate
python -m pip install "qitos @ git+https://github.com/WhitzardAgent/WhitzardOS.git@f7d4b2d666a156d361da496a41868278f84ffabf"
python -m pip install pytest
qit new --agent-name notes_agent --output-dir . --no-input
cd notes_agent

Save the complete files below in this directory. No repository clone, editable install, or copied tests are needed.

Notes and tools

NOTES is the entire input. The decorator turns a Python function into a registrable tool; it only reads memory. Its returned dictionary is the actual tool output, checked by assertions later.

NOTES = (
    "Session: A durable session can resume after a process exits.",
    "Artifact: Large tool outputs can be retained outside model context.",
)


@function_tool(read_only=True, concurrency_safe=True)
def summarize_note(index: int) -> dict:
    """Extract a title and word count from a synthetic in-memory note."""
    text = NOTES[index]
    return {"title": text.split(":", 1)[0], "words": len(text.split())}

Explicit fake provider

This provider scripts two tool calls followed by a final answer; there is no model reasoning. It lets you observe the framework’s tool round trips before switching to a real provider in Configuration.

class FakeProvider:
    """Scripted responses; this does not summarize or reason like a real model."""
    model = "notes-fake"
    qitos_protocol = "react_text_v1"

    def __init__(self, start=0):
        self.stage = start

    def call_raw(self, messages, **options):
        if self.stage < len(NOTES):
            content = f"Thought: inspect a note\nAction: summarize_note(index={self.stage})"
        else:
            content = "Final Answer: Indexed 2 notes: Session, Artifact."
        self.stage += 1
        return {"choices": [{"message": {"content": content}}]}

Configuration and composition

Save the complete files on this page in the generated notes_agent/ root and replace agent.yaml. Configuration selects SQLite and the journal; the program registers only a trusted pure function. unsafe_host does not provide isolation: do not add file or shell tools to it.

def configuration(root):
    config = load_agent_config(Path(__file__).with_name("agent.yaml"))
    return replace(config, runtime=replace(
        config.runtime, data_root=str(root / "data"),
        environment=replace(config.runtime.environment, workspace=str(root)),
        session=replace(config.runtime.session, path=str(root / "sessions.sqlite3")),
        trajectory=replace(config.runtime.trajectory, output=str(root / "trajectory.journal")),
    ))


def compose(root, *, start=0, pause=False):
    config = configuration(root)
    if pause:
        config = replace(config, lifecycle={"policy": "pause"})
    composition = build_agent_composition(
        config, model_override=FakeProvider(start), extensions={"pause": PauseAfterTool},
    )
    composition.tool_registry.register(summarize_note)
    return composition

Run and assertions

The with block closes owned resources; composition.session creates a Session and run returns EngineResult. Check the actual tool outputs before checking final text. Filter by tool name because records also include environment observations.

def run(root):
    root.mkdir(parents=True, exist_ok=False)
    with compose(root) as composition:
        session = composition.session("Index both synthetic notes")
        result = session.run()
        outputs = [action.output for record in result.records for action in record.action_results
                   if action.tool_name == "summarize_note"]
        assert [output["title"] for output in outputs] == ["Session", "Artifact"]
        assert result.state.final_result == "Indexed 2 notes: Session, Artifact."
        config = composition.config.to_dict()
        config["runtime"]["environment"] = {"type": "unsafe_host", "workspace": str(root)}
        (root / "agent.json").write_text(json.dumps(config), encoding="utf-8")
        control = {"session_id": session.session_id.value, "run_id": result.run_id}
        (root / "control.json").write_text(json.dumps(control), encoding="utf-8")
        print(json.dumps({**control, "result": result.state.final_result, "outputs": outputs}))

Run and verify

python -m pip install .
python -m pytest -q tests
python notes.py --root notes-run

Expected output fragments (generated IDs vary). Each run verifies tool results or persistence assertions and exits 0 on success.

Indexed 2 notes: Session, Artifact.

Inspect the saved Session

session_id=$(python -c 'import json; print(json.load(open("notes-run/control.json"))["session_id"])')
qit session inspect --config notes-run/agent.json --session-id "$session_id"
qita inspect session "$session_id" --logdir ./notes-run

Behavior and support boundaries

State and tools are separate from provider output. build_agent_composition loads the canonical choices; composition.session creates a Session; session.run returns an EngineResult. The with block closes owned resources.

Exercise and answer

Change the first title to Recovery. Update the expected title and scripted final response together; the word count remains computed by the tool.

Common errors and cleanup

ModuleNotFoundError: activate the environment with the specified installation and save every file on this page. Existing run root: choose a new --root instead of overwriting evidence. Assertion failure: inspect the first failed tool or typed error, not only the final text. After all processes and the board stop, remove only this lesson’s newly created run directories if no longer needed; retain SQLite, journals and reports you want to debug.

Complete files: save in the project root

notes.py

"""Synthetic notes; fake model, real tools, composition, Session and journal."""
import argparse
from dataclasses import replace
import json
from pathlib import Path

from qitos.config import build_agent_composition, load_agent_config
from qitos.core.function_tool_decorator import function_tool
from qitos.engine.runtime import LifecyclePolicy

# docs:start fixture
NOTES = (
    "Session: A durable session can resume after a process exits.",
    "Artifact: Large tool outputs can be retained outside model context.",
)


@function_tool(read_only=True, concurrency_safe=True)
def summarize_note(index: int) -> dict:
    """Extract a title and word count from a synthetic in-memory note."""
    text = NOTES[index]
    return {"title": text.split(":", 1)[0], "words": len(text.split())}
# docs:end fixture


# docs:start provider
class FakeProvider:
    """Scripted responses; this does not summarize or reason like a real model."""
    model = "notes-fake"
    qitos_protocol = "react_text_v1"

    def __init__(self, start=0):
        self.stage = start

    def call_raw(self, messages, **options):
        if self.stage < len(NOTES):
            content = f"Thought: inspect a note\nAction: summarize_note(index={self.stage})"
        else:
            content = "Final Answer: Indexed 2 notes: Session, Artifact."
        self.stage += 1
        return {"choices": [{"message": {"content": content}}]}
# docs:end provider


class PauseAfterTool(LifecyclePolicy):
    policy_id = "notes.pause_after_tool"

    def should_pause(self, context):
        return context.step_id == 0


# docs:start composition
def configuration(root):
    config = load_agent_config(Path(__file__).with_name("agent.yaml"))
    return replace(config, runtime=replace(
        config.runtime, data_root=str(root / "data"),
        environment=replace(config.runtime.environment, workspace=str(root)),
        session=replace(config.runtime.session, path=str(root / "sessions.sqlite3")),
        trajectory=replace(config.runtime.trajectory, output=str(root / "trajectory.journal")),
    ))


def compose(root, *, start=0, pause=False):
    config = configuration(root)
    if pause:
        config = replace(config, lifecycle={"policy": "pause"})
    composition = build_agent_composition(
        config, model_override=FakeProvider(start), extensions={"pause": PauseAfterTool},
    )
    composition.tool_registry.register(summarize_note)
    return composition
# docs:end composition


# docs:start run
def run(root):
    root.mkdir(parents=True, exist_ok=False)
    with compose(root) as composition:
        session = composition.session("Index both synthetic notes")
        result = session.run()
        outputs = [action.output for record in result.records for action in record.action_results
                   if action.tool_name == "summarize_note"]
        assert [output["title"] for output in outputs] == ["Session", "Artifact"]
        assert result.state.final_result == "Indexed 2 notes: Session, Artifact."
        config = composition.config.to_dict()
        config["runtime"]["environment"] = {"type": "unsafe_host", "workspace": str(root)}
        (root / "agent.json").write_text(json.dumps(config), encoding="utf-8")
        control = {"session_id": session.session_id.value, "run_id": result.run_id}
        (root / "control.json").write_text(json.dumps(control), encoding="utf-8")
        print(json.dumps({**control, "result": result.state.final_result, "outputs": outputs}))
# docs:end run


if __name__ == "__main__":
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("--root", type=Path, default=Path("notes-run"))
    run(parser.parse_args().root.resolve())

agent.yaml

schema: qitos.agent
agent:
  name: notes_agent
  protocol: react_text_v1
model:
  provider: openai_compatible
  model: notes-fake
  credential:
    ref: notes-provider
  request:
    max_tokens: 512
    timeout_seconds: 30
    retries: 0
tools:
  preset: none
runtime:
  environment:
    type: unsafe_host
    workspace: .
  session:
    mode: durable
    store: sqlite
    path: ./notes-run/sessions.sqlite3
  trajectory:
    enabled: true
    output: ./notes-run/trajectory.journal
budgets:
  max_steps: 6
  max_requests: 6
  max_runtime_seconds: 30
failure_policy:
  tool: fail_closed

Next step and API

API Reference · Configuration · Learning path · Next

Source file (optional; all required code is already on this page).