feat: 对其他 provider 提供 langfuse 监控

.npmrc

@@ -0,0 +1 @@
+registry=https://registry.npmjs.org/

build.ts

@@ -11,6 +11,7 @@ rmSync(outdir, { recursive: true, force: true })
 // Default features that match the official CLI build.
 // Additional features can be enabled via FEATURE_<NAME>=1 env vars.
 const DEFAULT_BUILD_FEATURES = [
+  'BUDDY', 'TRANSCRIPT_CLASSIFIER', 'BRIDGE_MODE',
   'AGENT_TRIGGERS_REMOTE',
   'CHICAGO_MCP',
   'VOICE_MODE',

package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-code-best",
-  "version": "1.4.2",
+  "version": "1.4.4",
   "description": "Reverse-engineered Anthropic Claude Code CLI — interactive AI coding assistant in the terminal",
   "type": "module",
   "author": "claude-code-best <claude-code-best@proton.me>",
@@ -37,6 +37,7 @@
   "files": [
     "dist",
     "scripts/postinstall.cjs",
+    "scripts/run-parallel.mjs",
     "scripts/setup-chrome-mcp.mjs"
   ],
   "scripts": {
@@ -72,20 +73,20 @@
     "@ant/computer-use-mcp": "workspace:*",
     "@ant/computer-use-swift": "workspace:*",
     "@anthropic-ai/bedrock-sdk": "^0.26.4",
-    "@anthropic-ai/claude-agent-sdk": "^0.2.87",
+    "@anthropic-ai/claude-agent-sdk": "^0.2.114",
     "@anthropic-ai/foundry-sdk": "^0.2.3",
     "@anthropic-ai/mcpb": "^2.1.2",
     "@anthropic-ai/sandbox-runtime": "^0.0.44",
     "@anthropic-ai/sdk": "^0.80.0",
     "@anthropic-ai/vertex-sdk": "^0.14.4",
     "@anthropic/ink": "workspace:*",
-    "@aws-sdk/client-bedrock": "^3.1020.0",
-    "@aws-sdk/client-bedrock-runtime": "^3.1020.0",
-    "@aws-sdk/client-sts": "^3.1020.0",
-    "@aws-sdk/credential-provider-node": "^3.972.28",
-    "@aws-sdk/credential-providers": "^3.1020.0",
+    "@aws-sdk/client-bedrock": "^3.1032.0",
+    "@aws-sdk/client-bedrock-runtime": "^3.1032.0",
+    "@aws-sdk/client-sts": "^3.1032.0",
+    "@aws-sdk/credential-provider-node": "^3.972.32",
+    "@aws-sdk/credential-providers": "^3.1032.0",
     "@azure/identity": "^4.13.1",
-    "@biomejs/biome": "^2.4.10",
+    "@biomejs/biome": "^2.4.12",
     "@claude-code-best/agent-tools": "workspace:*",
     "@claude-code-best/builtin-tools": "workspace:*",
     "@claude-code-best/mcp-client": "workspace:*",
@@ -96,7 +97,7 @@
     "@modelcontextprotocol/sdk": "^1.29.0",
     "@opentelemetry/api": "^1.9.1",
     "@opentelemetry/api-logs": "^0.214.0",
-    "@opentelemetry/core": "^2.6.1",
+    "@opentelemetry/core": "^2.7.0",
     "@opentelemetry/exporter-logs-otlp-grpc": "^0.214.0",
     "@opentelemetry/exporter-logs-otlp-http": "^0.214.0",
     "@opentelemetry/exporter-logs-otlp-proto": "^0.214.0",
@@ -107,14 +108,14 @@
     "@opentelemetry/exporter-trace-otlp-grpc": "^0.214.0",
     "@opentelemetry/exporter-trace-otlp-http": "^0.214.0",
     "@opentelemetry/exporter-trace-otlp-proto": "^0.214.0",
-    "@opentelemetry/resources": "^2.6.1",
+    "@opentelemetry/resources": "^2.7.0",
     "@opentelemetry/sdk-logs": "^0.214.0",
-    "@opentelemetry/sdk-metrics": "^2.6.1",
-    "@opentelemetry/sdk-trace-base": "^2.6.1",
+    "@opentelemetry/sdk-metrics": "^2.7.0",
+    "@opentelemetry/sdk-trace-base": "^2.7.0",
     "@opentelemetry/semantic-conventions": "^1.40.0",
-    "@sentry/node": "^10.47.0",
-    "@smithy/core": "^3.23.13",
-    "@smithy/node-http-handler": "^4.5.1",
+    "@sentry/node": "^10.49.0",
+    "@smithy/core": "^3.23.15",
+    "@smithy/node-http-handler": "^4.5.3",
     "@types/bun": "^1.3.12",
     "@types/cacache": "^20.0.1",
     "@types/he": "^1.2.3",
@@ -136,7 +137,7 @@
     "asciichart": "^1.5.25",
     "audio-capture-napi": "workspace:*",
     "auto-bind": "^5.0.1",
-    "axios": "^1.14.0",
+    "axios": "^1.15.0",
     "bidi-js": "^1.0.3",
     "cacache": "^20.0.4",
     "chalk": "^5.6.2",
@@ -151,7 +152,7 @@
     "execa": "^9.6.1",
     "fflate": "^0.8.2",
     "figures": "^6.1.0",
-    "fuse.js": "^7.1.0",
+    "fuse.js": "^7.3.0",
     "get-east-asian-width": "^1.5.0",
     "google-auth-library": "^10.6.2",
     "he": "^1.2.0",
@@ -161,21 +162,21 @@
     "image-processor-napi": "workspace:*",
     "indent-string": "^5.0.0",
     "jsonc-parser": "^3.3.1",
-    "knip": "^6.1.1",
-    "lodash-es": "^4.17.23",
-    "lru-cache": "^11.2.7",
-    "marked": "^17.0.5",
+    "knip": "^6.4.1",
+    "lodash-es": "^4.18.1",
+    "lru-cache": "^11.3.5",
+    "marked": "^17.0.6",
     "modifiers-napi": "workspace:*",
-    "openai": "^6.33.0",
+    "openai": "^6.34.0",
     "p-map": "^7.0.4",
     "picomatch": "^4.0.4",
     "plist": "^3.1.0",
     "proper-lockfile": "^4.1.2",
     "qrcode": "^1.5.4",
-    "react": "^19.2.4",
+    "react": "^19.2.5",
     "react-compiler-runtime": "^1.0.0",
     "react-reconciler": "^0.33.0",
-    "rollup": "^4.60.1",
+    "rollup": "^4.60.2",
     "semver": "^7.7.4",
     "sharp": "^0.34.5",
     "shell-quote": "^1.8.3",
@@ -184,10 +185,10 @@
     "strip-ansi": "^7.2.0",
     "supports-hyperlinks": "^4.4.0",
     "tree-kill": "^1.2.2",
-    "turndown": "^7.2.2",
-    "type-fest": "^5.5.0",
-    "typescript": "^6.0.2",
-    "undici": "^7.24.6",
+    "turndown": "^7.2.4",
+    "type-fest": "^5.6.0",
+    "typescript": "^6.0.3",
+    "undici": "^7.25.0",
     "url-handler-napi": "workspace:*",
     "usehooks-ts": "^3.1.1",
     "vite": "^8.0.8",

packages/remote-control-server/src/config.ts

@@ -18,6 +18,6 @@ export const config = {
 } as const;
 
 export function getBaseUrl(): string {
-  if (config.baseUrl) return config.baseUrl;
-  return `http://localhost:${config.port}`;
+  const url = config.baseUrl || `http://localhost:${config.port}`;
+  return url.replace(/\/+$/, "");
 }

packages/remote-control-server/src/index.ts

@@ -33,6 +33,17 @@ const app = new Hono();
 
 // Middleware
 app.use("*", logger());
+app.use("*", async (c, next) => {
+  // Normalize double slashes in path (e.g. //v1/environments/bridge → /v1/environments/bridge)
+  const path = new URL(c.req.url).pathname;
+  if (path.includes("//")) {
+    const normalized = path.replace(/\/+/g, "/");
+    const url = new URL(c.req.url);
+    url.pathname = normalized;
+    return app.fetch(new Request(url.toString(), c.req.raw));
+  }
+  await next();
+});
 app.use("/web/*", cors());
 
 // Health check

scripts/rcs-ccb.sh

@@ -1 +1,2 @@
-ACP_RCS_URL=http://localhost:3000 ACP_RCS_TOKEN=test-my-key acp-link ccb-bun -- --acp
+# ACP_RCS_URL=http://localhost:3000 ACP_RCS_TOKEN=test-my-key acp-link ccb-bun -- --acp
+ACP_RCS_URL=https://remote-control.claude-code-best.win/ ACP_RCS_TOKEN=test-my-key acp-link ccb-bun -- --acp

src/services/api/gemini/index.ts

@@ -18,6 +18,8 @@ import type { SDKAssistantMessageError } from '../../../entrypoints/agentSdkType
 import type { SystemPrompt } from '../../../utils/systemPromptType.js'
 import type { ThinkingConfig } from '../../../utils/thinking.js'
 import type { Options } from '../claude.js'
+import { recordLLMObservation } from '../../../services/langfuse/tracing.js'
+import { convertMessagesToLangfuse, convertOutputToLangfuse, convertToolsToLangfuse } from '../../../services/langfuse/convert.js'
 import { streamGeminiGenerateContent } from './client.js'
 import { anthropicMessagesToGemini, resolveGeminiModel, adaptGeminiStreamToAnthropic, anthropicToolsToGemini, anthropicToolChoiceToGemini, GEMINI_THOUGHT_SIGNATURE_FIELD } from '@ant/model-provider'
 
@@ -100,6 +102,7 @@ export async function* queryModelGemini(
 
     const adaptedStream = adaptGeminiStreamToAnthropic(stream, geminiModel)
     const contentBlocks: Record<number, any> = {}
+    const collectedMessages: AssistantMessage[] = []
     let partialMessage: any = undefined
     let ttftMs = 0
     const start = Date.now()
@@ -160,6 +163,7 @@ export async function* queryModelGemini(
             uuid: randomUUID(),
             timestamp: new Date().toISOString(),
           }
+          collectedMessages.push(message)
           yield message
           break
         }
@@ -174,6 +178,22 @@ export async function* queryModelGemini(
         ...(event.type === 'message_start' ? { ttftMs } : undefined),
       } as StreamEvent
     }
+
+    // Record LLM observation in Langfuse (no-op if not configured)
+    recordLLMObservation(options.langfuseTrace ?? null, {
+      model: geminiModel,
+      provider: 'gemini',
+      input: convertMessagesToLangfuse(messagesForAPI, systemPrompt),
+      output: convertOutputToLangfuse(collectedMessages),
+      usage: {
+        input_tokens: 0,
+        output_tokens: 0,
+      },
+      startTime: new Date(start),
+      endTime: new Date(),
+      completionStartTime: ttftMs > 0 ? new Date(start + ttftMs) : undefined,
+      tools: convertToolsToLangfuse(toolSchemas as unknown[]),
+    })
   } catch (error) {
     const errorMessage = error instanceof Error ? error.message : String(error)
     logForDebugging(`[Gemini] Error: ${errorMessage}`, { level: 'error' })

src/services/api/grok/index.ts

@@ -14,6 +14,8 @@ import { toolToAPISchema } from '../../../utils/api.js'
 import { logForDebugging } from '../../../utils/debug.js'
 import { addToTotalSessionCost } from '../../../cost-tracker.js'
 import { calculateUSDCost } from '../../../utils/modelCost.js'
+import { recordLLMObservation } from '../../../services/langfuse/tracing.js'
+import { convertMessagesToLangfuse, convertOutputToLangfuse, convertToolsToLangfuse } from '../../../services/langfuse/convert.js'
 import type { Options } from '../claude.js'
 import { randomUUID } from 'crypto'
 import {
@@ -92,6 +94,7 @@ export async function* queryModelGrok(
     const adaptedStream = adaptOpenAIStreamToAnthropic(stream as AsyncIterable<ChatCompletionChunk>, grokModel)
 
     const contentBlocks: Record<number, any> = {}
+    const collectedMessages: AssistantMessage[] = []
     let partialMessage: any = undefined
     let usage = {
       input_tokens: 0,
@@ -157,6 +160,7 @@ export async function* queryModelGrok(
             uuid: randomUUID(),
             timestamp: new Date().toISOString(),
           }
+          collectedMessages.push(m)
           yield m
           break
         }
@@ -182,6 +186,24 @@ export async function* queryModelGrok(
         ...(event.type === 'message_start' ? { ttftMs } : undefined),
       } as StreamEvent
     }
+
+    // Record LLM observation in Langfuse (no-op if not configured)
+    recordLLMObservation(options.langfuseTrace ?? null, {
+      model: grokModel,
+      provider: 'grok',
+      input: convertMessagesToLangfuse(messagesForAPI, systemPrompt),
+      output: convertOutputToLangfuse(collectedMessages),
+      usage: {
+        input_tokens: usage.input_tokens,
+        output_tokens: usage.output_tokens,
+        cache_creation_input_tokens: usage.cache_creation_input_tokens,
+        cache_read_input_tokens: usage.cache_read_input_tokens,
+      },
+      startTime: new Date(start),
+      endTime: new Date(),
+      completionStartTime: ttftMs > 0 ? new Date(start + ttftMs) : undefined,
+      tools: convertToolsToLangfuse(toolSchemas as unknown[]),
+    })
   } catch (error) {
     const errorMessage = error instanceof Error ? error.message : String(error)
     logForDebugging(`[Grok] Error: ${errorMessage}`, { level: 'error' })

src/services/api/openai/index.ts

@@ -24,6 +24,8 @@ import { logForDebugging } from '../../../utils/debug.js'
 import { addToTotalSessionCost } from '../../../cost-tracker.js'
 import { calculateUSDCost } from '../../../utils/modelCost.js'
 import { isOpenAIThinkingEnabled, resolveOpenAIMaxTokens, buildOpenAIRequestBody } from './requestBody.js'
+import { recordLLMObservation } from '../../../services/langfuse/tracing.js'
+import { convertMessagesToLangfuse, convertOutputToLangfuse, convertToolsToLangfuse } from '../../../services/langfuse/convert.js'
 export { isOpenAIThinkingEnabled, resolveOpenAIMaxTokens, buildOpenAIRequestBody }
 import { getModelMaxOutputTokens } from '../../../utils/context.js'
 import type { Options } from '../claude.js'
@@ -246,6 +248,7 @@ export async function* queryModelOpenAI(
 
     // Accumulate content blocks and usage, same as the Anthropic path in claude.ts
     const contentBlocks: Record<number, any> = {}
+    const collectedMessages: AssistantMessage[] = []
     let partialMessage: any
     let stopReason: string | null = null
     let usage = {
@@ -323,6 +326,9 @@ export async function* queryModelOpenAI(
               partialMessage, contentBlocks, tools, agentId: options.agentId,
               usage, stopReason, maxTokens,
             })) {
+              if (output.type === 'assistant') {
+                collectedMessages.push(output)
+              }
               yield output
             }
             // Reset partialMessage so the post-loop safety fallback does not
@@ -346,6 +352,24 @@ export async function* queryModelOpenAI(
       } as StreamEvent
     }
 
+    // Record LLM observation in Langfuse (no-op if not configured)
+    recordLLMObservation(options.langfuseTrace ?? null, {
+      model: openaiModel,
+      provider: 'openai',
+      input: convertMessagesToLangfuse(messagesForAPI, systemPrompt),
+      output: convertOutputToLangfuse(collectedMessages),
+      usage: {
+        input_tokens: usage.input_tokens,
+        output_tokens: usage.output_tokens,
+        cache_creation_input_tokens: usage.cache_creation_input_tokens,
+        cache_read_input_tokens: usage.cache_read_input_tokens,
+      },
+      startTime: new Date(start),
+      endTime: new Date(),
+      completionStartTime: ttftMs > 0 ? new Date(start + ttftMs) : undefined,
+      tools: convertToolsToLangfuse(toolSchemas as unknown[]),
+    })
+
     // Safety: if stream ended without message_stop, assemble and yield whatever we have
     if (partialMessage) {
       for (const output of assembleFinalAssistantOutputs({