quickstart-resources/tests/smoke-test.sh
Alex Akimov 470d1ba328
Some checks failed
Smoke Tests / test (push) Has been cancelled
Fix the tool-use loop in the Go, Rust, and Ruby clients and add a tool-loop smoke test (#200)
* Fix the tool-use loop in the Go, Rust, and Ruby clients and add a tool-loop smoke test

## Motivation and Context

Only the Python and TypeScript clients implemented a correct tool-use loop. The other three
had bugs that break ordinary multi-step requests:

- **Go, Rust, Ruby** did a single tool round and then called Claude once more *without*
  `tools`, so any request that needs a second tool call stalled. Go silently dropped
  `tool_use` blocks from that final response.
- **Ruby** called Claude once per `tool_use` block, each time with a single `tool_result`.
  Parallel tool calls produced a malformed message sequence and an API 400.
- **max_tokens** was 1000 in TypeScript and Ruby, 1024 in Go, and unset in Rust. Sonnet 5
  thinks adaptively, so 1000 tokens is regularly exhausted mid-thought. Python already used
  10000 with a comment explaining why.
- **Ruby** never forwarded MCP `isError` as `is_error`, so the model could not tell a failed
  tool call from a successful one. Rust cannot set the flag either (see below).
- **TypeScript** forwarded raw MCP content blocks to Anthropic. The two block shapes differ,
  so a non-text result would have failed.

The existing smoke test never noticed because it only checks that each client calls
`tools/list`. None of these bugs was reachable without an API key.

### What changed

All five clients now run the same loop: call tools until Claude answers without one, send
every `tool_result` of a turn in one user message, pass `tools` on every call, and stop
after `MAX_TOOL_TURNS = 10`. `max_tokens` is 10000 everywhere, with the same comment.
Python and TypeScript also keep the last response's text when the turn cap is hit; it used
to be dropped.

Rust keeps the `genai` crate. Its tool-response type has no `is_error` field, so an error
result is marked with an `Error:` prefix in the text and the limitation is commented.

### New smoke test

`tests/helpers/tool-loop-test.ts` starts a fake Anthropic Messages API on a loopback port,
points a client at it through `ANTHROPIC_BASE_URL`, pipes in one query, and checks every
request the client sends. It scripts two parallel tool calls, then a call to a tool the mock
server lacks (an `isError` result), then a final answer, and asserts that tools are passed
each time, `max_tokens` is 10000, all `tool_result`s arrive in one message with matching
ids, and the error is forwarded. `smoke-test.sh` runs it for Python, TypeScript, Go, and
Ruby.

The Rust client is excluded for now: `genai` reads no endpoint variable, and the client
negotiates protocol `2025-11-25`, under which the mock's array-rooted tool is refused at call
time. Both will be addressed in a follow-up that brings all examples to current SDK versions.

## How Has This Been Tested?

- `./tests/smoke-test.sh` passes for every example.
- The new tool-loop test passes all 19 checks for Python, TypeScript, Go, and Ruby.
- The Rust client was driven through the same scripted conversation with a temporary
  endpoint resolver (not committed) and passes.
- As a negative check, the Ruby client from `main` was run through the new test. It fails 10
  of 19 checks, on exactly the bugs listed above.
- Go and Ruby were built and run in `golang:1.25` and `ruby:3.4` containers.

## Breaking Changes

None. The clients' command lines, output format, and no-key behavior are unchanged.

## Types of changes

- [x] Bug fix (non-breaking change which fixes an issue)
- [ ] New feature (non-breaking change which adds functionality)
- [ ] Breaking change (fix or feature that would cause existing functionality to change)
- [x] Documentation update

## Checklist

- [x] I have read the [MCP Documentation](https://modelcontextprotocol.io)
- [x] My code follows the repository's style guidelines
- [x] New and existing tests pass locally
- [x] I have added appropriate error handling
- [x] I have added or updated documentation as needed

## Additional context

Two pre-existing issues surfaced while testing and are left for a follow-up:

- The Rust client (rmcp 3.1.2) negotiates `2025-11-25`. The TypeScript mock server and the
  Python weather server both reject its calls to array-rooted tools under that revision.
  Even current rmcp defaults to `2025-11-25`, so the client must request `2026-07-28`
  explicitly.
- The Go SDK's tool-result helper sends content as a list of text blocks rather than a
  string. The API accepts both, so it is unchanged.

AI assistance: the analysis, code changes, test helper, and this description were prepared
partially manually, partially with Claude Code and reviewed by me.

* Improvements

* Address comments
2026-09-19 18:25:02 -07:00

247 lines
8.1 KiB
Shell
Executable file

#!/bin/bash
set -e
# Source utilities
source "$(dirname "$0")/utils.sh"
print_header "MCP Quickstart Smoke Tests"
# Get project root
PROJECT_ROOT=$(get_project_root)
TESTS_DIR="${PROJECT_ROOT}/tests"
# Setup common test variables
TEST_CLIENT="${PROJECT_ROOT}/tests/helpers/build/mcp-test-client.js"
MOCK_SERVER="${PROJECT_ROOT}/tests/helpers/build/mock-mcp-server.js"
TOOL_LOOP_TEST="${PROJECT_ROOT}/tests/helpers/build/tool-loop-test.js"
# Track test results
FAILED_TESTS=()
PASSED_TESTS=()
# Build test helpers
ensure_helpers_built
# Helper function to run a test and track results
run_test() {
local test_name=$1
echo ""
print_header "Testing ${test_name}"
if "${@:2}"; then
PASSED_TESTS+=("${test_name}")
print_success "${test_name} test passed"
else
FAILED_TESTS+=("${test_name}")
print_error "${test_name} test failed"
fi
}
# Test: Python weather server
test_weather_server_python() {
check_dependency uv || return 1
local server_dir="${PROJECT_ROOT}/weather-server-python"
node "${TEST_CLIENT}" uv --directory "${server_dir}" run weather.py
}
# Test: TypeScript weather server
test_weather_server_typescript() {
check_dependency node || return 1
check_dependency npm || return 1
local server_dir="${PROJECT_ROOT}/weather-server-typescript"
ensure_built "${server_dir}" "" || return 1
node "${TEST_CLIENT}" node "${server_dir}/build/index.js"
}
# Test: Rust weather server
test_weather_server_rust() {
check_dependency cargo || return 1
local server_dir="${PROJECT_ROOT}/weather-server-rust"
ensure_built "${server_dir}" weather || return 1
# Determine which binary to use
local server_bin
server_bin=$(resolve_binary "${server_dir}/target/release/weather" \
|| resolve_binary "${server_dir}/target/debug/weather") || {
print_error "no weather binary found in ${server_dir}/target"
return 1
}
node "${TEST_CLIENT}" "${server_bin}"
}
# Test: Go weather server
test_weather_server_go() {
check_dependency go || return 1
local server_dir="${PROJECT_ROOT}/weather-server-go"
ensure_built "${server_dir}" server || return 1
local server_bin
server_bin=$(resolve_binary "${server_dir}/server") || {
print_error "no server binary found in ${server_dir}"
return 1
}
node "${TEST_CLIENT}" "${server_bin}"
}
# Test: Ruby weather server
test_weather_server_ruby() {
check_dependency ruby || return 1
check_dependency bundle || return 1
local server_dir="${PROJECT_ROOT}/weather-server-ruby"
ensure_bundled "${server_dir}" || return 1
(cd "${server_dir}" && node "${TEST_CLIENT}" bundle exec ruby weather.rb)
}
# The client tests drive the no-API-key path, where each client prints a notice
# and exits. Empty rather than unset: dotenv skips a name already present in
# ENV, so a key in the environment or a local .env would start the chat loop.
# Test: Python MCP client
test_mcp_client_python() {
check_dependency uv || return 1
local client_dir="${PROJECT_ROOT}/mcp-client-python"
ANTHROPIC_API_KEY= uv --directory "${client_dir}" run python "${client_dir}/client.py" "${MOCK_SERVER}" >/dev/null 2>&1
}
# Test: TypeScript MCP client
test_mcp_client_typescript() {
check_dependency node || return 1
check_dependency npm || return 1
local client_dir="${PROJECT_ROOT}/mcp-client-typescript"
ensure_built "${client_dir}" "" || return 1
ANTHROPIC_API_KEY= node "${client_dir}/build/index.js" "${MOCK_SERVER}" >/dev/null 2>&1
}
# Test: Ruby MCP client
test_mcp_client_ruby() {
check_dependency ruby || return 1
check_dependency bundle || return 1
local client_dir="${PROJECT_ROOT}/mcp-client-ruby"
ensure_bundled "${client_dir}" || return 1
(cd "${client_dir}" && ANTHROPIC_API_KEY= bundle exec ruby client.rb "${MOCK_SERVER}") >/dev/null 2>&1
}
# Test: Go MCP client
test_mcp_client_go() {
check_dependency go || return 1
local client_dir="${PROJECT_ROOT}/mcp-client-go"
ensure_built "${client_dir}" mcp-client-go || return 1
local client_bin
client_bin=$(resolve_binary "${client_dir}/mcp-client-go") || {
print_error "no mcp-client-go binary found in ${client_dir}"
return 1
}
ANTHROPIC_API_KEY= "${client_bin}" node "${MOCK_SERVER}" >/dev/null 2>&1
}
# Test: Rust MCP client
test_mcp_client_rust() {
check_dependency cargo || return 1
local client_dir="${PROJECT_ROOT}/mcp-client-rust"
ensure_built "${client_dir}" mcp-client-rust || return 1
local client_bin
client_bin=$(resolve_binary "${client_dir}/target/release/mcp-client-rust" \
|| resolve_binary "${client_dir}/target/debug/mcp-client-rust") || {
print_error "no mcp-client-rust binary found in ${client_dir}/target"
return 1
}
ANTHROPIC_API_KEY= "${client_bin}" node "${MOCK_SERVER}" >/dev/null 2>&1
}
# The tool-loop tests drive the chat loop itself, which the no-key tests never
# reach. The helper starts a fake Anthropic API on a loopback port, points the
# client at it through ANTHROPIC_BASE_URL, and scripts one query as two
# parallel tool calls, then a failing one, then an answer. It checks every
# request the client sends; see tests/README.md for what is checked.
# Test: Python MCP client tool loop
test_tool_loop_python() {
check_dependency uv || return 1
local client_dir="${PROJECT_ROOT}/mcp-client-python"
node "${TOOL_LOOP_TEST}" uv --directory "${client_dir}" run python "${client_dir}/client.py" "${MOCK_SERVER}"
}
# Test: TypeScript MCP client tool loop
test_tool_loop_typescript() {
check_dependency node || return 1
check_dependency npm || return 1
local client_dir="${PROJECT_ROOT}/mcp-client-typescript"
ensure_built "${client_dir}" "" || return 1
node "${TOOL_LOOP_TEST}" node "${client_dir}/build/index.js" "${MOCK_SERVER}"
}
# Test: Ruby MCP client tool loop
test_tool_loop_ruby() {
check_dependency ruby || return 1
check_dependency bundle || return 1
local client_dir="${PROJECT_ROOT}/mcp-client-ruby"
ensure_bundled "${client_dir}" || return 1
(cd "${client_dir}" && node "${TOOL_LOOP_TEST}" bundle exec ruby client.rb "${MOCK_SERVER}")
}
# Test: Go MCP client tool loop
test_tool_loop_go() {
check_dependency go || return 1
local client_dir="${PROJECT_ROOT}/mcp-client-go"
ensure_built "${client_dir}" mcp-client-go || return 1
local client_bin
client_bin=$(resolve_binary "${client_dir}/mcp-client-go") || {
print_error "no mcp-client-go binary found in ${client_dir}"
return 1
}
node "${TOOL_LOOP_TEST}" "${client_bin}" node "${MOCK_SERVER}"
}
# The Rust client has no tool-loop test yet. Its genai crate reads no
# environment variable for the API endpoint, so the fake API cannot be reached
# without adding code to the example, and it negotiates protocol 2025-11-25,
# under which the mock's array-rooted tool is refused at call time.
# Run all tests
print_header "Running smoke tests"
run_test "weather-server-python" test_weather_server_python
run_test "weather-server-typescript" test_weather_server_typescript
run_test "weather-server-rust" test_weather_server_rust
run_test "weather-server-go" test_weather_server_go
run_test "weather-server-ruby" test_weather_server_ruby
run_test "mcp-client-python" test_mcp_client_python
run_test "mcp-client-typescript" test_mcp_client_typescript
run_test "mcp-client-ruby" test_mcp_client_ruby
run_test "mcp-client-go" test_mcp_client_go
run_test "mcp-client-rust" test_mcp_client_rust
run_test "mcp-client-python tool loop" test_tool_loop_python
run_test "mcp-client-typescript tool loop" test_tool_loop_typescript
run_test "mcp-client-ruby tool loop" test_tool_loop_ruby
run_test "mcp-client-go tool loop" test_tool_loop_go
# Print summary
echo ""
print_header "Test Summary"
echo "Passed: ${#PASSED_TESTS[@]}"
for test in "${PASSED_TESTS[@]}"; do
print_success "${test}"
done
if [ ${#FAILED_TESTS[@]} -gt 0 ]; then
echo ""
echo "Failed: ${#FAILED_TESTS[@]}"
for test in "${FAILED_TESTS[@]}"; do
print_error "${test}"
done
echo ""
print_error "Some tests failed"
exit 1
else
echo ""
print_success "All tests passed!"
exit 0
fi