Tests for what the desk sends
The desk's observation names, its masking and its warnings are an interface other things depend on. Tests keep them from changing by accident.
Project files used on this pageThis lesson builds on a project from earlier lessons. The code below imports these files. Click a file to see its code, or follow the link to the lesson that wrote it. To run the code yourself, keep them in the same folder.
View the code here
privacy.py
import re
from langfuse.types import MaskOtelSpansResult, OtelSpanPatch
CARD = re.compile(r"\b\d(?:[ -]?\d){12,15}\b")
def mask_cards(*, params):
patches = {}
for span_id, span in params.spans.items():
changed = {key: CARD.sub("[card]", value) for key, value in span.attributes.items() if isinstance(value, str) and CARD.search(value)}
if changed:
patches[span_id] = OtelSpanPatch(set_attributes=changed)
return MaskOtelSpansResult(span_patches=patches)
shop_model.py
"""A stand-in chat model for the shop's support desk: no key, no network."""
import re
def reply(messages):
"""Answer the last message, and count words as tokens the way a chat model reports usage."""
rules = messages[0]["content"].lower() if messages[0]["role"] == "system" else ""
last = messages[-1]["content"]
lookup = re.search(r"Lookup: (\S+) (.+)", last)
if "refund" in last.lower():
text = "Refunds need approval, so a person will review your request."
elif lookup and "never share" in rules:
text = "I cannot share order details."
elif lookup and lookup.group(2) == "not found":
text = f"I could not find order {lookup.group(1)}. Please check the number."
elif lookup:
text = f"Order {lookup.group(1)} {lookup.group(2)}."
else:
text = "Could you send your order number?"
if "thank" in rules:
text = "Thanks for waiting. " + text
used = sum(len(message["content"].split()) for message in messages)
return text, {"input": used, "output": len(text.split())}
support_desk.py
"""The shop's support desk as a traced service."""
import re
from langfuse import get_client, observe, propagate_attributes
ORDERS = {"A17": "shipped on 3 March"}
FALLBACK = "You answer customers of a small online shop in one short sentence."
model = None # an OpenAI-compatible client, set by the program that runs the desk
@observe(name="lookup-order", as_type="tool")
def lookup_order(order_id):
status = ORDERS.get(order_id, "not found")
if status == "not found":
get_client().update_current_span(level="WARNING", status_message=f"no order {order_id}")
return status
@observe(name="answer-ticket", as_type="agent")
def answer(ticket):
prompt = get_client().get_prompt("desk-system", fallback=FALLBACK)
order = re.search(r"[A-Z]\d{2}", ticket)
facts = f"\nLookup: {order.group()} {lookup_order(order.group())}" if order else ""
messages = [{"role": "system", "content": prompt.compile()}, {"role": "user", "content": ticket + facts}]
response = model.chat.completions.create(model="shop-model", messages=messages,
name="write-reply", langfuse_prompt=prompt)
return response.choices[0].message.content
def handle(ticket_number, ticket, customer, chat):
langfuse = get_client()
trace_id = langfuse.create_trace_id(seed=ticket_number)
with langfuse.start_as_current_observation(name="support-ticket", input=ticket,
trace_context={"trace_id": trace_id}) as span:
with propagate_attributes(user_id=customer, session_id=chat, tags=["desk"]):
text = answer(ticket)
span.update(output=text)
return text
def record_feedback(ticket_number, helpful, comment=None):
langfuse = get_client()
langfuse.create_score(
trace_id=langfuse.create_trace_id(seed=ticket_number), score_id=f"{ticket_number}-feedback",
name="user-feedback", value=1 if helpful else 0, data_type="BOOLEAN", comment=comment,
)
local_langfuse.py
"""A stand-in for the Langfuse server, on your own machine.
The Langfuse SDK sends observations to /api/public/otel/v1/traces and uses a
REST API for scores, prompts and datasets. This server answers those requests
on 127.0.0.1 and keeps what it receives in lists you can print. Given a model
function, it also answers like OpenAI's chat API. start() blocks every
connection to another computer for the rest of the program.
"""
import json
import socket
import threading
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from urllib.parse import parse_qs, unquote, urlparse
from opentelemetry.proto.collector.trace.v1.trace_service_pb2 import ExportTraceServiceRequest
SPANS, SCORES, REQUESTS = [], [], [] # observations, scores, "METHOD /path" of each request
PROMPTS, DATASETS = {}, {} # prompt name -> its versions, dataset name -> dataset
MODEL = None # answers /v1/chat/completions when set
NOW = "2026-03-03T09:00:00Z"
def _value(v):
kind = v.WhichOneof("value")
if kind == "array_value":
return [_value(item) for item in v.array_value.values]
return getattr(v, kind) if kind else None
def _spans(body):
request = ExportTraceServiceRequest()
request.ParseFromString(body)
for resource in request.resource_spans:
for scope in resource.scope_spans:
for span in scope.spans:
SPANS.append({
"name": span.name, "id": span.span_id.hex(), "trace": span.trace_id.hex(),
"parent": span.parent_span_id.hex(), "scope": scope.scope.name,
"attributes": {a.key: _value(a.value) for a in span.attributes},
})
return {}
def _scores(batch):
for event in batch:
if event["type"] == "score-create":
SCORES.append(event["body"])
return {"successes": [{"id": e["id"], "status": 201} for e in batch], "errors": []}
def _prompt(name, query, body):
versions = PROMPTS.setdefault(name, [])
if body is not None: # a new version: it takes "latest" and any labels it asks for
labels = body.get("labels", []) + ["latest"]
for old in versions:
old["labels"] = [label for label in old["labels"] if label not in labels]
versions.append({"name": name, "type": body.get("type", "text"), "prompt": body["prompt"],
"config": body.get("config") or {}, "labels": labels, "tags": [],
"version": len(versions) + 1})
return versions[-1]
if "version" in query:
return versions[int(query["version"]) - 1]
label = query.get("label", "production")
return next(v for v in versions if label in v["labels"])
def _relabel(path, body):
name, _, version = path.split("/")[-3:]
versions = PROMPTS[unquote(name)]
for old in versions:
old["labels"] = [label for label in old["labels"] if label not in body["newLabels"]]
versions[int(version) - 1]["labels"] += body["newLabels"]
return versions[int(version) - 1]
def _dataset(path, query, body):
if path == "/api/public/v2/datasets":
DATASETS[body["name"]] = {"id": body["name"], "name": body["name"], "items": [],
"metadata": body.get("metadata"), "projectId": "local",
"createdAt": NOW, "updatedAt": NOW}
return DATASETS[body["name"]]
if path.startswith("/api/public/v2/datasets/"):
return DATASETS[unquote(path.rsplit("/", 1)[1])]
if path == "/api/public/dataset-items" and body is not None:
dataset = DATASETS[body["datasetName"]]
item = {"id": body.get("id") or f"item-{len(dataset['items']) + 1}", "status": "ACTIVE",
"input": body.get("input"), "expectedOutput": body.get("expectedOutput"),
"metadata": body.get("metadata"), "sourceTraceId": body.get("sourceTraceId"),
"datasetId": dataset["id"], "datasetName": dataset["name"],
"createdAt": NOW, "updatedAt": NOW, "mediaReferences": []}
dataset["items"].append(item)
return item
if path == "/api/public/dataset-items":
items = DATASETS[query["datasetName"]]["items"]
return {"data": items, "meta": {"page": 1, "limit": 50, "totalItems": len(items), "totalPages": 1}}
return {"id": "run-item", "datasetRunId": body["runName"], "datasetRunName": body["runName"],
"datasetItemId": body["datasetItemId"], "traceId": body["traceId"],
"observationId": body.get("observationId"), "createdAt": NOW, "updatedAt": NOW}
def _chat(body):
text, usage = MODEL(body["messages"])
return {"id": "chatcmpl-1", "object": "chat.completion", "created": 0, "model": body["model"],
"choices": [{"index": 0, "finish_reason": "stop", "message": {"role": "assistant", "content": text}}],
"usage": {"prompt_tokens": usage["input"], "completion_tokens": usage["output"],
"total_tokens": usage["input"] + usage["output"]}}
class Handler(BaseHTTPRequestHandler):
def _handle(self):
url = urlparse(self.path)
query = {key: values[0] for key, values in parse_qs(url.query).items()}
raw = self.rfile.read(int(self.headers.get("Content-Length") or 0))
body = json.loads(raw) if raw and "json" in self.headers.get("Content-Type", "") else None
REQUESTS.append(f"{self.command} {url.path}")
try:
if url.path.endswith("/otel/v1/traces"):
return self._reply(200, _spans(raw))
if url.path == "/api/public/ingestion":
return self._reply(207, _scores(body["batch"]))
if url.path == "/api/public/projects":
return self._reply(200, {"data": [{"id": "local", "name": "shop-desk", "metadata": {},
"organization": {"id": "local", "name": "local"}}]})
if url.path.startswith("/api/public/v2/prompts/") and self.command == "PATCH":
return self._reply(200, _relabel(url.path, body))
if url.path.startswith("/api/public/v2/prompts"):
name = body["name"] if body else unquote(url.path.rsplit("/", 1)[1])
return self._reply(200, _prompt(name, query, body))
if "dataset" in url.path:
return self._reply(200, _dataset(url.path, query, body))
if url.path.endswith("/chat/completions") and MODEL:
return self._reply(200, _chat(body))
except (KeyError, StopIteration):
pass
self._reply(404, {"message": f"not found: {url.path}"})
do_GET = do_POST = do_PATCH = _handle
def _reply(self, code, data):
self.send_response(code)
self.send_header("Content-Type", "application/json")
self.end_headers()
self.wfile.write(json.dumps(data).encode())
def log_message(self, *args):
pass
def _local_only():
"""Refuse to look up or connect to any other computer, so nothing leaves by mistake."""
lookup, connect = socket.getaddrinfo, socket.socket.connect
def guarded_lookup(host, *args, **kwargs):
if host not in ("127.0.0.1", "localhost", "::1"):
raise ConnectionRefusedError(f"blocked a connection to {host}: this lab stays on your machine")
return lookup(host, *args, **kwargs)
def guarded_connect(sock, address):
if isinstance(address, tuple) and address[0] not in ("127.0.0.1", "::1"):
raise ConnectionRefusedError(f"blocked a connection to {address[0]}: this lab stays on your machine")
return connect(sock, address)
socket.getaddrinfo, socket.socket.connect = guarded_lookup, guarded_connect
def start(model=None):
"""Start the server in the background and return its address."""
global MODEL
_local_only()
MODEL = model
server = ThreadingHTTPServer(("127.0.0.1", 0), Handler)
threading.Thread(target=server.serve_forever, daemon=True).start()
return f"http://127.0.0.1:{server.server_address[1]}"
def tree(*fields):
"""Print the observations received so far, each under its parent, with any fields asked for."""
ids = {span["id"] for span in SPANS}
def walk(span, depth):
attributes = span["attributes"]
line = " " * depth + f"{span['name']} ({attributes.get('langfuse.observation.type', 'span')})"
for field in fields:
line += f" {field}={attributes.get('langfuse.observation.' + field)!r}"
print(line)
for child in SPANS:
if child["parent"] == span["id"]:
walk(child, depth + 1)
for root in [span for span in SPANS if span["parent"] not in ids]:
walk(root, 0)
The fixture sets the desk up the way app.py does, masking included, once for the file.
import json
import pytest
from langfuse import Langfuse
from langfuse.openai import OpenAI
import local_langfuse
import support_desk
from privacy import mask_cards
from shop_model import reply@pytest.fixture(scope="module")
def langfuse():
url = local_langfuse.start(model=reply)
client = Langfuse(public_key="pk-lf-local", secret_key="sk-lf-local", base_url=url, mask_otel_spans=mask_cards)
support_desk.model = OpenAI(base_url=f"{url}/v1", api_key="not-a-real-key")
client.create_prompt(name="desk-system", prompt=support_desk.FALLBACK, labels=["production"])
return clientEach test starts from an empty server, so one test cannot see another's observations.
def spans_for(langfuse, number, ticket):
local_langfuse.SPANS.clear()
support_desk.handle(number, ticket, customer="cust-1", chat="chat-1")
langfuse.flush()
return local_langfuse.SPANSThe first test pins the shape of a trace: the names, in order, that filters and dashboards rely on.
def test_trace_shape(langfuse):
names = [span["name"] for span in spans_for(langfuse, "t-1", "Where is my order A17?")]
assert names == ["lookup-order", "write-reply", "answer-ticket", "support-ticket"]
def test_card_numbers_never_leave(langfuse):
spans = spans_for(langfuse, "t-2", "Card 4111 1111 1111 1111 was charged twice on A17")
assert spans and "4111" not in json.dumps([span["attributes"] for span in spans])The second searches every exported attribute for the card number, which is the only way to be sure masking covered the model call as well as the ticket.
def test_feedback_lands_on_the_ticket_trace(langfuse):
trace = spans_for(langfuse, "t-3", "Is B22 on its way?")[0]["trace"]
support_desk.record_feedback("t-3", helpful=False)
langfuse.flush()
assert local_langfuse.SCORES[-1]["traceId"] == tracepytest -q -p no:warnings test_support_desk.pyOutput
... [100%] 3 passed in 1.41s
Both pass against the stand-in server, with no key and no network, so they can run on every change.
Try it yourself
- Rename an observation in the desk and watch the first test fail.
- Add a test that a missing order produces a warning.
- Add a test that the customer's id reaches every observation.
This is what real progress feels like.