Merge pull request 'M2.1: marchwarden ask CLI command' (#11) from feat/cli-ask into main

Reviewed-on: #11
Reviewed-by: archeious <archeious@unbiasedgeek.com>
This commit is contained in:
archeious 2026-04-08 20:54:59 +00:00
commit b2b7026eb2
3 changed files with 334 additions and 0 deletions

201
cli/main.py Normal file
View file

@ -0,0 +1,201 @@
"""Marchwarden CLI shim.
Talks to the web researcher MCP server over stdio and pretty-prints
ResearchResult contracts to the terminal.
"""
import asyncio
import json
import sys
from typing import Optional
import click
from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client
from rich.console import Console
from rich.panel import Panel
from rich.table import Table
from rich.text import Text
from researchers.web.models import ResearchResult
# ---------------------------------------------------------------------------
# MCP client
# ---------------------------------------------------------------------------
async def call_research_tool(
question: str,
depth: str,
max_iterations: int,
token_budget: int,
) -> ResearchResult:
"""Spawn the web researcher MCP server and call its `research` tool."""
params = StdioServerParameters(
command=sys.executable,
args=["-m", "researchers.web.server"],
)
async with stdio_client(params) as (read, write):
async with ClientSession(read, write) as session:
await session.initialize()
result = await session.call_tool(
"research",
arguments={
"question": question,
"depth": depth,
"max_iterations": max_iterations,
"token_budget": token_budget,
},
)
# FastMCP returns the tool's string return as a TextContent block.
payload = result.content[0].text
return ResearchResult.model_validate_json(payload)
# ---------------------------------------------------------------------------
# Pretty printing
# ---------------------------------------------------------------------------
def render_result(result: ResearchResult, console: Console) -> None:
"""Render a ResearchResult to the console using rich."""
# Answer
console.print(
Panel(
result.answer,
title="[bold cyan]Answer[/bold cyan]",
border_style="cyan",
)
)
# Citations
if result.citations:
table = Table(title="Citations", show_lines=True, expand=True)
table.add_column("#", style="dim", width=3)
table.add_column("Title / Locator", overflow="fold")
table.add_column("Excerpt", overflow="fold")
table.add_column("Conf", justify="right", width=5)
for i, c in enumerate(result.citations, 1):
header = f"[bold]{c.title or c.locator}[/bold]\n[dim]{c.locator}[/dim]"
table.add_row(str(i), header, c.raw_excerpt, f"{c.confidence:.2f}")
console.print(table)
else:
console.print("[dim]No citations.[/dim]")
# Gaps grouped by category
if result.gaps:
gap_table = Table(title="Gaps", show_lines=True, expand=True)
gap_table.add_column("Category", style="yellow")
gap_table.add_column("Topic")
gap_table.add_column("Detail", overflow="fold")
for g in result.gaps:
gap_table.add_row(g.category.value, g.topic, g.detail)
console.print(gap_table)
# Discovery events
if result.discovery_events:
de_table = Table(title="Discovery Events", show_lines=True, expand=True)
de_table.add_column("Type", style="magenta")
de_table.add_column("Suggested Researcher")
de_table.add_column("Query", overflow="fold")
de_table.add_column("Reason", overflow="fold")
for d in result.discovery_events:
de_table.add_row(
d.type, d.suggested_researcher or "-", d.query, d.reason
)
console.print(de_table)
# Open questions
if result.open_questions:
oq_table = Table(title="Open Questions", show_lines=True, expand=True)
oq_table.add_column("Priority", style="green")
oq_table.add_column("Question", overflow="fold")
oq_table.add_column("Context", overflow="fold")
for q in result.open_questions:
oq_table.add_row(q.priority, q.question, q.context)
console.print(oq_table)
# Confidence + factors
cf = result.confidence_factors
conf_text = Text()
conf_text.append(f"Overall: {result.confidence:.2f}\n", style="bold")
conf_text.append(f"Corroborating sources: {cf.num_corroborating_sources}\n")
conf_text.append(f"Source authority: {cf.source_authority}\n")
conf_text.append(f"Contradiction detected: {cf.contradiction_detected}\n")
conf_text.append(f"Query specificity match: {cf.query_specificity_match:.2f}\n")
conf_text.append(f"Budget exhausted: {cf.budget_exhausted}\n")
conf_text.append(f"Recency: {cf.recency or 'unknown'}")
console.print(Panel(conf_text, title="Confidence", border_style="green"))
# Cost
cm = result.cost_metadata
cost_text = Text()
cost_text.append(f"Tokens: {cm.tokens_used}\n")
cost_text.append(f"Iterations: {cm.iterations_run}\n")
cost_text.append(f"Wall time: {cm.wall_time_sec:.2f}s\n")
cost_text.append(f"Model: {cm.model_id}")
console.print(Panel(cost_text, title="Cost", border_style="blue"))
# Trace footer
console.print(f"\n[dim]trace_id: {result.trace_id}[/dim]")
# ---------------------------------------------------------------------------
# Click app
# ---------------------------------------------------------------------------
@click.group()
def cli() -> None:
"""Marchwarden — agentic research CLI."""
@cli.command()
@click.argument("question")
@click.option(
"--depth",
type=click.Choice(["shallow", "balanced", "deep"]),
default="balanced",
show_default=True,
)
@click.option(
"--budget",
"token_budget",
type=int,
default=20_000,
show_default=True,
help="Token budget for the research loop.",
)
@click.option(
"--max-iterations",
type=int,
default=5,
show_default=True,
)
def ask(
question: str,
depth: str,
token_budget: int,
max_iterations: int,
) -> None:
"""Ask the web researcher a QUESTION."""
console = Console()
console.print(f"[dim]Researching:[/dim] {question}\n")
try:
result = asyncio.run(
call_research_tool(
question=question,
depth=depth,
max_iterations=max_iterations,
token_budget=token_budget,
)
)
except Exception as e:
console.print(f"[bold red]Error:[/bold red] {e}")
sys.exit(1)
render_result(result, console)
if __name__ == "__main__":
cli()

View file

@ -19,6 +19,7 @@ dependencies = [
"tavily-python>=0.3.0",
"httpx>=0.24.0",
"click>=8.0",
"rich>=13.0",
]
[project.optional-dependencies]

132
tests/test_cli.py Normal file
View file

@ -0,0 +1,132 @@
"""Tests for the marchwarden CLI."""
from unittest.mock import patch
from click.testing import CliRunner
from cli.main import cli, render_result
from researchers.web.models import (
Citation,
ConfidenceFactors,
CostMetadata,
DiscoveryEvent,
Gap,
GapCategory,
OpenQuestion,
ResearchResult,
)
from rich.console import Console
def _fixture_result() -> ResearchResult:
return ResearchResult(
answer="Tomatoes, peppers, squash, and beans grow well in Utah.",
citations=[
Citation(
source="web",
locator="https://extension.usu.edu/yard-and-garden",
title="USU Extension — Yard and Garden",
snippet="USU recommends warm-season crops for Utah's climate.",
raw_excerpt="Tomatoes, peppers, and squash thrive in Utah summers.",
confidence=0.9,
),
],
gaps=[
Gap(
topic="Microclimate variation",
category=GapCategory.SCOPE_EXCEEDED,
detail="Did not investigate elevation-specific recommendations.",
),
],
discovery_events=[
DiscoveryEvent(
type="related_research",
suggested_researcher="docs",
query="Utah USDA hardiness zones",
reason="Zone-specific guidance would improve answer.",
),
],
open_questions=[
OpenQuestion(
question="What are the best cool-season crops?",
context="Answer focused on warm-season crops.",
priority="medium",
),
],
confidence=0.82,
confidence_factors=ConfidenceFactors(
num_corroborating_sources=3,
source_authority="high",
contradiction_detected=False,
query_specificity_match=0.85,
budget_exhausted=False,
recency="current",
),
cost_metadata=CostMetadata(
tokens_used=4321,
iterations_run=3,
wall_time_sec=12.5,
budget_exhausted=False,
model_id="claude-sonnet-4-6",
),
trace_id="trace-abc-123",
)
class TestRenderResult:
def test_renders_all_sections(self):
console = Console(record=True, width=120)
render_result(_fixture_result(), console)
out = console.export_text()
assert "Tomatoes" in out
assert "USU Extension" in out
assert "scope_exceeded" in out
assert "related_research" in out
assert "cool-season" in out
assert "Confidence" in out
assert "claude-sonnet-4-6" in out
assert "trace-abc-123" in out
class TestAskCommand:
def test_ask_invokes_mcp_and_renders(self):
runner = CliRunner()
fixture = _fixture_result()
async def fake_call(question, depth, max_iterations, token_budget):
assert question == "What grows in Utah?"
assert depth == "shallow"
assert max_iterations == 2
assert token_budget == 5000
return fixture
with patch("cli.main.call_research_tool", side_effect=fake_call):
result = runner.invoke(
cli,
[
"ask",
"What grows in Utah?",
"--depth",
"shallow",
"--max-iterations",
"2",
"--budget",
"5000",
],
)
assert result.exit_code == 0, result.output
assert "Tomatoes" in result.output
assert "trace-abc-123" in result.output
def test_ask_handles_error(self):
runner = CliRunner()
async def boom(**kwargs):
raise RuntimeError("mcp went sideways")
with patch("cli.main.call_research_tool", side_effect=boom):
result = runner.invoke(cli, ["ask", "anything"])
assert result.exit_code == 1
assert "mcp went sideways" in result.output