Files
nofx/telegram/agent/agent_test.go
T
tinkle-community 9c5c976d9a feat: Claw402 x402 payment provider + Telegram agent + x402 refactoring (#1409)
* feat(telegram): add AI agent bot with streaming and account context

- Add Telegram bot with long-polling and AI agent loop (api_call tool)
- SSE streaming with real-time message editing and  placeholder
- Account state injection at conversation start (models, exchanges,
  strategies, traders, per-trader PnL and statistics)
- Lane semaphore per chat serializes concurrent messages (60s timeout)
- Idle timeout watchdog (60s) prevents hung streaming connections
- Look-ahead buffer prevents partial <api_call> tag leaking to user
- Fix PUT /strategies/:id to merge config (read-then-merge pattern)
- Add route registry with full API schema for LLM documentation
- Add TelegramConfig store and Web UI config modal
- Add GetAnyEnabled to AIModel store for bot LLM client selection

* fix(telegram): eliminate narration, add full-setup workflow and tests

- Rewrite NO NARRATION rule: response is EITHER api_call tag alone OR
  final text reply — no text before api_call under any circumstances
- Ban all narration patterns: 现在我将/好的/正在/I will/Let me etc.
- Add 'create strategy + create trader + start' full setup workflow
- Add 12 automated tests covering:
  - No narration leaking to user (5 narration variants tested)
  - api_call tag never leaks to user
  - Full setup workflow: POST strategy → verify → POST trader → start
  - Start existing trader workflow
  - Max iterations safety, tag stripping, parser edge cases

* refactor(agent): replace XML api_call with native function calling

Migrate the Telegram bot agent from an XML tag hack (<api_call>) to
OpenAI-native function calling via CallWithRequestFull.

Key changes:
- mcp/interface.go: add parseMCPResponseFull to clientHooks interface
- mcp/client.go: route callWithRequestFull through hooks for overridability
- mcp/claude_client.go: override parseMCPResponseFull for Claude response
  format (tool_use blocks instead of choices[].message.tool_calls)
- telegram/agent/agent.go: rewrite Run() to use CallWithRequestFull;
  define api_request tool with JSON Schema; implement tool-call loop
  with role="tool" result messages; remove XML parsing entirely
- telegram/agent/apicall.go: remove parseAPICall (dead code)
- telegram/agent/prompt.go: simplify — remove XML format instructions,
  replace with concise api_request tool usage instructions
- telegram/agent/agent_test.go: rebuild all tests using LLMResponse
  objects; add TestNarrationStructurallyImpossible, TestOnChunkCalledWithFinalReply,
  TestToolCallIDPropagated; remove XML-specific tests

Architecture advantage: with native function calling, the LLM returns
EITHER ToolCalls OR Content — never both. Narration is now structurally
impossible at the protocol level, not just enforced by prompt rules.

All 11 agent tests pass. mcp package tests pass.

* refactor(mcp): route buildRequestBodyFromRequest through hooks + full Anthropic format

Problem: callWithRequest/Full/Stream all called client.buildRequestBodyFromRequest
directly (not via hooks), so ClaudeClient could never override it. This meant
tool calling sent OpenAI format to Anthropic (wrong field names, wrong roles).

Changes:

mcp/interface.go
- Add buildRequestBodyFromRequest(*Request) map[string]any to clientHooks
- Improve comments: document what each hook group does and why

mcp/client.go
- All three paths (callWithRequest, callWithRequestFull, CallWithRequestStream)
  now call client.hooks.buildRequestBodyFromRequest — ClaudeClient picks up

mcp/claude_client.go
- Full rewrite with format comparison table in package doc
- buildRequestBodyFromRequest: produces correct Anthropic wire format
    * system prompt → top-level "system" field
    * tools: parameters → input_schema, no "type:function" wrapper
    * tool_choice "auto" → {"type":"auto"} object
    * assistant tool calls → content[{type:tool_use, id, name, input}]
    * role=tool results → role=user content[{type:tool_result,...}]
    * consecutive tool results merged into single user turn
- convertMessagesToAnthropic: handles all three message types
- parseMCPResponseFull: extracts text + tool_use blocks
- parseMCPResponse: delegates to parseMCPResponseFull

All mcp and agent tests pass.

* fix(telegram): fix claude client dispatch + strategy creation workflow

- telegram/bot.go: clientForProvider now returns NewClaudeClient() for
  'claude' provider (was incorrectly falling back to DeepSeekClient which
  uses OpenAI wire format, breaking Anthropic API calls)

- api/server.go: fix scan_interval_minutes schema default (3, not 60);
  POST /api/strategies now clearly states config is OPTIONAL with complete
  working defaults; POST /api/traders removes redundant GET workflow note

- telegram/agent/prompt.go: simplify strategy creation — just POST {name}
  without config (backend applies full working defaults automatically);
  only include config when user requests custom settings

* test(mcp): add ClaudeClient wire format tests

Tests cover all Anthropic-specific format conversions:
- system prompt lifted to top-level field
- tools use input_schema (not parameters)
- tool_choice is object {type:auto} not string
- assistant tool calls → content[{type:tool_use}]
- consecutive tool results merged into single user turn
- parseMCPResponseFull: text, tool_use, and error cases
- x-api-key header (not Authorization: Bearer)
- /messages endpoint URL

* fix(telegram): clientForProvider returns correct client for all 7 providers

Previously qwen/kimi/grok/gemini all fell back to DeepSeekClient.
Each provider now gets its own dedicated client with correct default
base URL and model. All 7 providers now fully supported:
openai, deepseek, claude, qwen, kimi, grok, gemini

* fix(telegram): newLLMClient uses bound user's model, not any user's model

GetAnyEnabled() searched across all users in DB — if user B has an
enabled model, bot could use their API key while acting as user A.

Now uses GetDefault(botUserID) which only looks up the bound user's
enabled model, matching the same user scope as all API calls.

* fix(auth): single-user deployment by default, no open registration

Registration logic redesigned:
- Empty DB (first-time setup): registration always open, no config needed
- After first user exists: registration closed by default
- Multi-user opt-in: set REGISTRATION_ENABLED=true + MAX_USERS=N in .env

Config defaults changed:
- RegistrationEnabled: true → false (closed after first user)
- MaxUsers: 10 → 1 (single-user deployment default)

This eliminates the confusion of multiple users appearing in a personal
deployment where Telegram is bound to a single admin account.

* feat(solo): beginner-friendly onboarding — smart setup guide + direct config commands

start.sh:
- Interactive Telegram Bot Token prompt on first run
- Token format validation (must match 12345:ABC... pattern)
- Friendly step-by-step startup instructions after launch

telegram/bot.go:
- /start now shows context-aware setup guide based on actual config state:
  - No AI model → explains how to configure, lists all providers
  - AI model OK but no exchange → guides to configure exchange via chat
  - All configured → full capabilities welcome message
- New: direct setup commands ('配置 deepseek sk-xxx') bypass LLM entirely
  so AI model can be configured even before any model exists (bootstrap fix)
- All messages now in Chinese (匹配用户语言)

telegram/agent/prompt.go:
- Added first-time setup detection section
- Agent told to never ask user to visit web UI — everything via chat

* feat(i18n): bilingual EN/ZH setup guide with language selection

store/telegram_config.go:
- Add Language field to TelegramConfig (persisted in DB)
- Add SetLanguage(lang) and GetLanguage() methods
- Default language: English (en)

telegram/bot.go:
- First /start triggers language selection (1=English, 2=中文)
- /lang command to change language at any time
- awaitingLang state machine handles language choice before any other input
- buildSetupGuide() now fully bilingual (EN/ZH), context-aware:
  Step 1: configure AI model (no model yet)
  Step 2: configure exchange (model OK, no exchange)
  Ready: show full capabilities
- tryHandleSetupCommand() bilingual: 'configure/配置 <provider> <key>'
- helpMessage(lang) fully bilingual
- All error/status messages bilingual

Default: English. isLangDefault() detects whether user has explicitly
chosen a language vs falling back to the 'en' default.

* fix(telegram): use Markdown rendering + simplify language selection condition

- sendMarkdownMsg() helper: sends with ParseMode=Markdown, falls back to plain text
- All formatted messages (langSelectionMsg, buildSetupGuide, helpMessage) now render
  bold text and code blocks correctly in Telegram
- Simplify /start language check: isLangDefault(st) alone is sufficient
  (lang == 'en' && isLangDefault was redundant — GetLanguage returns 'en' when empty)

* fix(start.sh): translate all user-facing text to English

Entire script was in Chinese. Now English-first throughout:
- startup banner, prompts, success/error messages
- setup_telegram(): English instructions and validation messages
- start(): English next-steps after launch
- stop/restart/clean/update/regenerate-keys/show_help: all English

* fix(telegram): remove 'default' user fallback — resolve user dynamically

- botUserID no longer captured once at startup (was 'default' if no user yet)
- resolveBotUser() reads first registered user from DB on demand:
  * called on every /start (handles: registered after bot launch)
  * called before every AI message (handles mid-session registration)
- If no user registered: clear English error 'No account found. Please register on the web UI first'
- start.sh: fix set_env_var appending without newline (token was concatenated to prev line)

* refactor(telegram): clean onboarding — web UI for setup, Telegram for operations

- /start shows clean status: 'setup required → open web UI' or 'ready → examples'
- Removed tryHandleSetupCommand (no more CLI-style 'configure deepseek sk-xxx')
- Removed automatic language selection on /start (use /lang anytime instead)
- newLLMClient returns nil when no model → clear guard, not fallback
- statusMsg() replaces buildSetupGuide(): two states only (missing config / ready)
- Bot is now purely an operations interface; config lives in the web UI

* refactor: single-user web-based setup — replace env config with Settings UI

Move from multi-user env-var config to single-user web-first architecture:
- Add SetupPage for first-time initialization (replaces /register)
- Add SettingsPage for AI models, exchanges, Telegram, and password management
- Enrich all API route schemas with exact ID usage documentation
- Add PUT /user/password endpoint for in-app password changes
- Remove REGISTRATION_ENABLED, MAX_USERS, TELEGRAM_BOT_TOKEN from env config
- Simplify LoginPage design, remove admin mode and registration links
- Telegram bot now resolves user email for identity display
- start.sh no longer runs interactive Telegram setup

* feat: add blockRun (x402 USDC) support to all AI model consumers

- telegram/bot.go: add blockrun-base, blockrun-sol, minimax to
  clientForProvider; fix newLLMClient to prefer TelegramConfig.ModelID
  over GetDefault; log USDC payment provider usage
- debate/engine.go: add blockrun-base, blockrun-sol to InitializeClients
- api/strategy.go: add blockrun-base, blockrun-sol to runRealAITest
- backtest/ai_client.go: add blockrun-base, blockrun-sol to configureMCPClient

* feat: add Claw402 (claw402.ai) x402 USDC payment provider

Add Claw402Client for claw402.ai's x402 micropayment gateway (Base USDC).
Supports 15+ AI models (GPT-5.4, Claude Opus, DeepSeek, Qwen, Grok, etc.)
with per-model endpoint routing.

- mcp/claw402.go: new client with model→endpoint mapping, x402 v2 payment flow
- mcp/blockrun_base.go: extract shared signX402Payment() for reuse
- Register "claw402" provider in all 6 consumer switch statements:
  api/server.go, api/strategy.go, trader/auto_trader.go,
  telegram/bot.go, debate/engine.go, backtest/ai_client.go

* feat: redesign Claw402 model config UI — friendly wallet setup, USDC guide, official logo, nginx no-cache for index.html

* refactor: centralize x402 payment flow into shared mcp/x402.go

Extract duplicated doRequestWithPayment/call/CallWithRequestFull/buildRequest/
setAuthHeader (~165 lines x3) into shared helpers in mcp/x402.go. Consolidate
shared types (x402v2PaymentRequired, x402AcceptOption, x402Resource) and remove
duplicate Solana types. Fix validAfter to 0 (official SDK standard), drain 402
body before retry, log Payment-Response tx hash, check Payment-Required before
X-Payment-Required.

* fix: stop PR template bot from overwriting user-written descriptions

The pr-template-suggester workflow was triggered on opened/edited/synchronize
events and forcefully replaced the PR body with a template when body < 100 chars.
This caused user-written descriptions to be overwritten.

Replace with a lightweight labeler (OpenClaw-style) that:
- Only adds labels (backend/frontend/docs, size: XS/S/M/L/XL)
- Never modifies the PR body
- Simplified unified PR template at .github/pull_request_template.md

* chore: simplify PR template (OpenClaw-style)
2026-03-11 16:01:42 +08:00

440 lines
14 KiB
Go

package agent
import (
"fmt"
"net/http"
"net/http/httptest"
"strings"
"testing"
"time"
"nofx/mcp"
)
// mockLLM implements mcp.AIClient using pre-programmed LLMResponse objects.
// Native function calling: CallWithRequestFull is the primary method;
// CallWithRequest and CallWithRequestStream are stubs kept for interface compliance.
type mockLLM struct {
responses []*mcp.LLMResponse
calls int
lastMsgs []mcp.Message
}
func (m *mockLLM) SetAPIKey(_, _, _ string) {}
func (m *mockLLM) SetTimeout(_ time.Duration) {}
func (m *mockLLM) CallWithMessages(_, _ string) (string, error) { return "", nil }
func (m *mockLLM) CallWithRequest(req *mcp.Request) (string, error) {
r, err := m.next()
if err != nil {
return "", err
}
return r.Content, nil
}
func (m *mockLLM) CallWithRequestStream(req *mcp.Request, onChunk func(string)) (string, error) {
r, err := m.next()
if err != nil {
return "", err
}
if onChunk != nil {
onChunk(r.Content)
}
return r.Content, nil
}
func (m *mockLLM) CallWithRequestFull(req *mcp.Request) (*mcp.LLMResponse, error) {
m.lastMsgs = req.Messages
return m.next()
}
func (m *mockLLM) next() (*mcp.LLMResponse, error) {
if m.calls < len(m.responses) {
r := m.responses[m.calls]
m.calls++
return r, nil
}
return &mcp.LLMResponse{Content: "OK"}, nil
}
// toolCall builds a mock LLM response that contains a single tool invocation.
func toolCall(id, method, path string, body string) *mcp.LLMResponse {
if body == "" {
body = "{}"
}
return &mcp.LLMResponse{
ToolCalls: []mcp.ToolCall{{
ID: id,
Type: "function",
Function: mcp.ToolCallFunction{
Name: "api_request",
Arguments: fmt.Sprintf(`{"method":%q,"path":%q,"body":%s}`, method, path, body),
},
}},
}
}
// textReply builds a mock LLM response with a plain-text final answer.
func textReply(content string) *mcp.LLMResponse {
return &mcp.LLMResponse{Content: content}
}
func mockGetLLM(llm *mockLLM) func() mcp.AIClient {
return func() mcp.AIClient { return llm }
}
const testPrompt = "You are a test assistant."
// mockAPIServer creates a test HTTP server with configurable route handlers.
func mockAPIServer(handlers map[string]string) (*httptest.Server, int) {
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
key := r.Method + " " + r.URL.Path
if body, ok := handlers[key]; ok {
w.Write([]byte(body)) //nolint:errcheck
return
}
// Also try path-only match (for GET)
if body, ok := handlers[r.URL.Path]; ok {
w.Write([]byte(body)) //nolint:errcheck
return
}
w.WriteHeader(http.StatusNotFound)
w.Write([]byte(`{"error":"not found"}`)) //nolint:errcheck
}))
var port int
fmt.Sscanf(srv.Listener.Addr().String(), "127.0.0.1:%d", &port)
return srv, port
}
// ── Basic agent behaviour ──────────────────────────────────────────────────
// TestAgentDirectReply: LLM replies with text (no tool calls) — one LLM call.
func TestAgentDirectReply(t *testing.T) {
llm := &mockLLM{responses: []*mcp.LLMResponse{textReply("Hello! How can I help you?")}}
a := New(8080, "tok", "test-user", mockGetLLM(llm), testPrompt)
reply := a.Run("hello", nil)
if reply != "Hello! How can I help you?" {
t.Fatalf("unexpected reply: %q", reply)
}
if llm.calls != 1 {
t.Fatalf("expected 1 LLM call, got %d", llm.calls)
}
}
// TestAgentAPICall: LLM makes one tool call, gets result, gives final reply — two LLM calls.
func TestAgentAPICall(t *testing.T) {
srv, port := mockAPIServer(map[string]string{
"/api/my-traders": `[{"trader_id":"t1","trader_name":"BTC Trader","is_running":false}]`,
})
defer srv.Close()
llm := &mockLLM{responses: []*mcp.LLMResponse{
toolCall("c1", "GET", "/api/my-traders", "{}"),
textReply("You have one trader: BTC Trader."),
}}
a := New(port, "tok", "test-user", mockGetLLM(llm), testPrompt)
reply := a.Run("list my traders", nil)
if reply != "You have one trader: BTC Trader." {
t.Fatalf("unexpected reply: %q", reply)
}
if llm.calls != 2 {
t.Fatalf("expected 2 LLM calls, got %d", llm.calls)
}
}
// TestAgentMultiStep: LLM chains two tool calls before final reply — three LLM calls.
func TestAgentMultiStep(t *testing.T) {
srv, port := mockAPIServer(map[string]string{
"/api/account": `{"total_equity":1000}`,
"/api/positions": `[]`,
})
defer srv.Close()
llm := &mockLLM{responses: []*mcp.LLMResponse{
toolCall("c1", "GET", "/api/account", "{}"),
toolCall("c2", "GET", "/api/positions", "{}"),
textReply("Account looks healthy and no open positions."),
}}
a := New(port, "tok", "test-user", mockGetLLM(llm), testPrompt)
reply := a.Run("show me account status", nil)
if llm.calls != 3 {
t.Fatalf("expected 3 LLM calls (2 tool + 1 final), got %d", llm.calls)
}
if reply != "Account looks healthy and no open positions." {
t.Fatalf("unexpected final reply: %q", reply)
}
}
// TestAgentAPIResultInContext: tool result must appear as a tool message in the next LLM call.
func TestAgentAPIResultInContext(t *testing.T) {
srv, port := mockAPIServer(map[string]string{
"/api/account": `{"balance":1234.56}`,
})
defer srv.Close()
llm := &mockLLM{responses: []*mcp.LLMResponse{
toolCall("c1", "GET", "/api/account", "{}"),
textReply("Balance is 1234.56 USDT."),
}}
a := New(port, "tok", "test-user", mockGetLLM(llm), testPrompt)
a.Run("show balance", nil)
// The last request must contain a tool-result message with the balance data.
found := false
for _, msg := range llm.lastMsgs {
if msg.Role == "tool" && strings.Contains(msg.Content, "balance") {
found = true
break
}
}
if !found {
t.Fatalf("tool result message not found in subsequent LLM context; messages: %+v", llm.lastMsgs)
}
}
// ── Narration-free architecture tests ─────────────────────────────────────
// TestNarrationStructurallyImpossible: when ToolCalls are present in the response,
// any Content field is ignored and never surfaced to the user.
// In real LLM APIs, Content is always empty alongside ToolCalls, but we verify
// our agent handles a malformed response defensively.
func TestNarrationStructurallyImpossible(t *testing.T) {
srv, port := mockAPIServer(map[string]string{
"/api/strategies": `[{"id":"s1","name":"BTC Trend"}]`,
})
defer srv.Close()
// Simulate a (malformed) response that has both Content and ToolCalls.
malformed := &mcp.LLMResponse{
Content: "现在我将为您查询策略。", // narration — must NOT reach user
ToolCalls: []mcp.ToolCall{{
ID: "c1",
Type: "function",
Function: mcp.ToolCallFunction{
Name: "api_request",
Arguments: `{"method":"GET","path":"/api/strategies","body":{}}`,
},
}},
}
llm := &mockLLM{responses: []*mcp.LLMResponse{
malformed,
textReply("你有1个策略:BTC Trend。"),
}}
a := New(port, "tok", "test-user", mockGetLLM(llm), testPrompt)
reply := a.Run("查询我的策略", nil)
if strings.Contains(reply, "现在我将") {
t.Fatalf("narration leaked into final reply: %q", reply)
}
if reply != "你有1个策略:BTC Trend。" {
t.Fatalf("unexpected reply: %q", reply)
}
}
// TestOnChunkCalledWithFinalReply: onChunk receives the complete final reply.
func TestOnChunkCalledWithFinalReply(t *testing.T) {
srv, port := mockAPIServer(map[string]string{
"/api/account": `{"equity":500}`,
})
defer srv.Close()
llm := &mockLLM{responses: []*mcp.LLMResponse{
toolCall("c1", "GET", "/api/account", "{}"),
textReply("Equity: 500 USDT."),
}}
a := New(port, "tok", "test-user", mockGetLLM(llm), testPrompt)
var chunks []string
reply := a.Run("show equity", func(chunk string) {
chunks = append(chunks, chunk)
})
if reply != "Equity: 500 USDT." {
t.Fatalf("unexpected reply: %q", reply)
}
// Should have received ⏳ for the tool call, then the final reply.
if len(chunks) < 2 {
t.Fatalf("expected at least 2 chunks (⏳ + final), got: %v", chunks)
}
lastChunk := chunks[len(chunks)-1]
if lastChunk != "Equity: 500 USDT." {
t.Fatalf("last chunk should be final reply, got: %q", lastChunk)
}
}
// ── Workflow tests ─────────────────────────────────────────────────────────
// TestCreateStrategyWorkflow: simulates creating a BTC trend strategy.
// Verifies: POST strategy → GET verify → final reply shows strategy info.
func TestCreateStrategyWorkflow(t *testing.T) {
srv, port := mockAPIServer(map[string]string{
"POST /api/strategies": `{"id":"s1","name":"BTC趋势"}`,
"GET /api/strategies/s1": `{"id":"s1","name":"BTC趋势","config":{"coin_source":{"source_type":"static","static_coins":["BTC/USDT"]},"leverage":5}}`,
})
defer srv.Close()
llm := &mockLLM{responses: []*mcp.LLMResponse{
toolCall("c1", "POST", "/api/strategies", `{"name":"BTC趋势","config":{}}`),
toolCall("c2", "GET", "/api/strategies/s1", "{}"),
textReply("策略已创建:BTC趋势,币种 BTC/USDT,杠杆 5x。"),
}}
a := New(port, "tok", "test-user", mockGetLLM(llm), testPrompt)
reply := a.Run("帮我配置个btc趋势交易的策略", nil)
if llm.calls != 3 {
t.Fatalf("expected 3 LLM calls, got %d", llm.calls)
}
if reply == "" {
t.Fatalf("empty final reply")
}
}
// TestFullSetupWorkflow: create strategy → verify → create trader → start trader.
// This is the "帮我配置策略并跑起来" workflow.
func TestFullSetupWorkflow(t *testing.T) {
calls := map[string]int{}
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
key := r.Method + " " + r.URL.Path
calls[key]++
switch key {
case "POST /api/strategies":
w.Write([]byte(`{"id":"s1","name":"BTC趋势"}`)) //nolint:errcheck
case "GET /api/strategies/s1":
w.Write([]byte(`{"id":"s1","name":"BTC趋势","config":{}}`)) //nolint:errcheck
case "POST /api/traders":
w.Write([]byte(`{"id":"tr1","name":"BTC趋势交易员"}`)) //nolint:errcheck
case "POST /api/traders/tr1/start":
w.Write([]byte(`{"ok":true}`)) //nolint:errcheck
default:
w.WriteHeader(http.StatusNotFound)
}
}))
defer srv.Close()
var port int
fmt.Sscanf(srv.Listener.Addr().String(), "127.0.0.1:%d", &port)
llm := &mockLLM{responses: []*mcp.LLMResponse{
toolCall("c1", "POST", "/api/strategies", `{"name":"BTC趋势"}`),
toolCall("c2", "GET", "/api/strategies/s1", "{}"),
toolCall("c3", "POST", "/api/traders", `{"name":"BTC趋势交易员","strategy_id":"s1"}`),
toolCall("c4", "POST", "/api/traders/tr1/start", "{}"),
textReply("策略和交易员已创建并启动!BTC趋势交易员正在运行。"),
}}
a := New(port, "tok", "test-user", mockGetLLM(llm), testPrompt)
reply := a.Run("帮我配置个btc趋势交易的策略交易 跑起来", nil)
if llm.calls != 5 {
t.Fatalf("expected 5 LLM calls, got %d", llm.calls)
}
if calls["POST /api/strategies"] != 1 {
t.Errorf("expected 1 POST /api/strategies, got %d", calls["POST /api/strategies"])
}
if calls["POST /api/traders"] != 1 {
t.Errorf("expected 1 POST /api/traders, got %d", calls["POST /api/traders"])
}
if calls["POST /api/traders/tr1/start"] != 1 {
t.Errorf("expected 1 POST /api/traders/tr1/start, got %d", calls["POST /api/traders/tr1/start"])
}
if reply == "" {
t.Fatalf("empty final reply")
}
}
// TestStartExistingTrader: when trader already exists, just start it.
func TestStartExistingTrader(t *testing.T) {
calls := map[string]int{}
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
key := r.Method + " " + r.URL.Path
calls[key]++
switch key {
case "GET /api/my-traders":
w.Write([]byte(`[{"trader_id":"tr1","trader_name":"BTC Trader","is_running":false}]`)) //nolint:errcheck
case "POST /api/traders/tr1/start":
w.Write([]byte(`{"ok":true}`)) //nolint:errcheck
default:
w.WriteHeader(http.StatusNotFound)
}
}))
defer srv.Close()
var port int
fmt.Sscanf(srv.Listener.Addr().String(), "127.0.0.1:%d", &port)
llm := &mockLLM{responses: []*mcp.LLMResponse{
toolCall("c1", "GET", "/api/my-traders", "{}"),
toolCall("c2", "POST", "/api/traders/tr1/start", "{}"),
textReply("交易员 BTC Trader 已启动。"),
}}
a := New(port, "tok", "test-user", mockGetLLM(llm), testPrompt)
reply := a.Run("启动交易员", nil)
if calls["POST /api/traders/tr1/start"] != 1 {
t.Errorf("expected trader to be started, got %d start calls", calls["POST /api/traders/tr1/start"])
}
if reply != "交易员 BTC Trader 已启动。" {
t.Fatalf("unexpected reply: %q", reply)
}
}
// ── Safety limit ───────────────────────────────────────────────────────────
// TestMaxIterations: agent terminates after maxIterations and returns fallback message.
func TestMaxIterations(t *testing.T) {
srv, port := mockAPIServer(map[string]string{
"/api/account": `{"ok":true}`,
})
defer srv.Close()
// Always returns another tool call — should hit max iterations.
responses := make([]*mcp.LLMResponse, maxIterations+2)
for i := range responses {
responses[i] = toolCall(fmt.Sprintf("c%d", i), "GET", "/api/account", "{}")
}
llm := &mockLLM{responses: responses}
a := New(port, "tok", "test-user", mockGetLLM(llm), testPrompt)
reply := a.Run("loop forever", nil)
if reply == "" {
t.Fatalf("expected a fallback reply, got empty string")
}
// Agent should have made exactly maxIterations tool-call LLM calls.
if llm.calls != maxIterations {
t.Fatalf("expected %d LLM calls (max iterations), got %d", maxIterations, llm.calls)
}
}
// TestToolCallIDPropagated: tool result messages carry the correct ToolCallID.
func TestToolCallIDPropagated(t *testing.T) {
srv, port := mockAPIServer(map[string]string{
"/api/account": `{"balance":999}`,
})
defer srv.Close()
llm := &mockLLM{responses: []*mcp.LLMResponse{
toolCall("call-xyz-123", "GET", "/api/account", "{}"),
textReply("Balance is 999."),
}}
a := New(port, "tok", "test-user", mockGetLLM(llm), testPrompt)
a.Run("check balance", nil)
// Find the tool result message and verify ToolCallID matches.
found := false
for _, msg := range llm.lastMsgs {
if msg.Role == "tool" && msg.ToolCallID == "call-xyz-123" {
found = true
break
}
}
if !found {
t.Fatalf("tool result with ToolCallID='call-xyz-123' not found in messages: %+v", llm.lastMsgs)
}
}