fix: Fix deferred tools handling in OpenAI compatibility layer

src/services/api/openai/index.ts

@@ -1,15 +1,26 @@
 import type { BetaToolUnion } from '@anthropic-ai/sdk/resources/beta/messages/messages.mjs'
 import type { SystemPrompt } from '../../../utils/systemPromptType.js'
-import type { Message, StreamEvent, SystemAPIErrorMessage, AssistantMessage } from '../../../types/message.js'
+import type {
+  Message,
+  StreamEvent,
+  SystemAPIErrorMessage,
+  AssistantMessage,
+} from '../../../types/message.js'
 import type { Tools } from '../../../Tool.js'
 import { getOpenAIClient } from './client.js'
 import { anthropicMessagesToOpenAI } from './convertMessages.js'
-import { anthropicToolsToOpenAI, anthropicToolChoiceToOpenAI } from './convertTools.js'
+import {
+  anthropicToolsToOpenAI,
+  anthropicToolChoiceToOpenAI,
+} from './convertTools.js'
 import { adaptOpenAIStreamToAnthropic } from './streamAdapter.js'
 import { resolveOpenAIModel } from './modelMapping.js'
 import { normalizeMessagesForAPI } from '../../../utils/messages.js'
 import { toolToAPISchema } from '../../../utils/api.js'
-import { getEmptyToolPermissionContext } from '../../../Tool.js'
+import {
+  getEmptyToolPermissionContext,
+  toolMatchesName,
+} from '../../../Tool.js'
 import { logForDebugging } from '../../../utils/debug.js'
 import { addToTotalSessionCost } from '../../../cost-tracker.js'
 import { calculateUSDCost } from '../../../utils/modelCost.js'
@@ -19,6 +30,14 @@ import {
   createAssistantAPIErrorMessage,
   normalizeContentFromAPI,
 } from '../../../utils/messages.js'
+import {
+  isToolSearchEnabled,
+  extractDiscoveredToolNames,
+} from '../../../utils/toolSearch.js'
+import {
+  isDeferredTool,
+  TOOL_SEARCH_TOOL_NAME,
+} from '../../../tools/ToolSearchTool/prompt.js'
 
 /**
  * OpenAI-compatible query path. Converts Anthropic-format messages/tools to
@@ -43,41 +62,97 @@ export async function* queryModelOpenAI(
     // 2. Normalize messages using shared preprocessing
     const messagesForAPI = normalizeMessagesForAPI(messages, tools)
 
-    // 3. Build tool schemas
+    // 3. Check if tool search is enabled (similar to Anthropic path)
+    const useToolSearch = await isToolSearchEnabled(
+      options.model,
+      tools,
+      options.getToolPermissionContext ||
+        (async () => getEmptyToolPermissionContext()),
+      options.agents || [],
+      options.querySource,
+    )
+
+    // 4. Build deferred tools set (similar to Anthropic path)
+    const deferredToolNames = new Set<string>()
+    if (useToolSearch) {
+      for (const t of tools) {
+        if (isDeferredTool(t)) deferredToolNames.add(t.name)
+      }
+    }
+
+    // 5. Filter tools (similar to Anthropic path)
+    let filteredTools = tools
+    if (useToolSearch && deferredToolNames.size > 0) {
+      const discoveredToolNames = extractDiscoveredToolNames(messages)
+
+      filteredTools = tools.filter(tool => {
+        // Always include non-deferred tools
+        if (!deferredToolNames.has(tool.name)) return true
+        // Always include ToolSearchTool (so it can discover more tools)
+        if (toolMatchesName(tool, TOOL_SEARCH_TOOL_NAME)) return true
+        // Only include deferred tools that have been discovered
+        return discoveredToolNames.has(tool.name)
+      })
+    }
+
+    // 6. Build tool schemas with deferLoading flag
     const toolSchemas = await Promise.all(
-      tools.map(tool =>
+      filteredTools.map(tool =>
         toolToAPISchema(tool, {
           getToolPermissionContext: options.getToolPermissionContext,
           tools,
           agents: options.agents,
           allowedAgentTypes: options.allowedAgentTypes,
           model: options.model,
+          deferLoading: useToolSearch && deferredToolNames.has(tool.name),
         }),
       ),
     )
-    // Filter out non-standard tools (server tools like advisor)
+
+    // 7. Filter out non-standard tools (server tools like advisor)
     const standardTools = toolSchemas.filter(
       (t): t is BetaToolUnion & { type: string } => {
         const anyT = t as Record<string, unknown>
-        return anyT.type !== 'advisor_20260301' && anyT.type !== 'computer_20250124'
+        return (
+          anyT.type !== 'advisor_20260301' && anyT.type !== 'computer_20250124'
+        )
       },
     )
 
-    // 4. Convert messages and tools to OpenAI format
-    const openaiMessages = anthropicMessagesToOpenAI(messagesForAPI, systemPrompt)
+    // 8. Convert messages and tools to OpenAI format
+    const openaiMessages = anthropicMessagesToOpenAI(
+      messagesForAPI,
+      systemPrompt,
+    )
     const openaiTools = anthropicToolsToOpenAI(standardTools)
     const openaiToolChoice = anthropicToolChoiceToOpenAI(options.toolChoice)
 
-    // 5. Get client and make streaming request
+    // 9. Log tool filtering details
+    if (useToolSearch) {
+      const includedDeferredTools = filteredTools.filter(t =>
+        deferredToolNames.has(t.name),
+      ).length
+      logForDebugging(
+        `[OpenAI] Tool search enabled: ${includedDeferredTools}/${deferredToolNames.size} deferred tools included, total tools=${openaiTools.length}`,
+      )
+    } else {
+      logForDebugging(
+        `[OpenAI] Tool search disabled, total tools=${openaiTools.length}`,
+      )
+    }
+
+    // 10. Get client and make streaming request
     const client = getOpenAIClient({
       maxRetries: 0,
       fetchOverride: options.fetchOverride,
       source: options.querySource,
     })
 
-    logForDebugging(`[OpenAI] Calling model=${openaiModel}, messages=${openaiMessages.length}, tools=${openaiTools.length}`)
+    logForDebugging(
+      `[OpenAI] Calling model=${openaiModel}, messages=${openaiMessages.length}, tools=${openaiTools.length}`,
+    )
 
-    // 6. Call OpenAI API with streaming
+    // 11. Call OpenAI API with streaming
     const stream = await client.chat.completions.create(
       {
         model: openaiModel,
@@ -103,7 +178,7 @@ export async function* queryModelOpenAI(
 
     // Accumulate content blocks and usage, same as the Anthropic path in claude.ts
     const contentBlocks: Record<number, any> = {}
-    let partialMessage: any = undefined
+    let partialMessage: any
     let usage = {
       input_tokens: 0,
       output_tokens: 0,
@@ -121,7 +196,7 @@ export async function* queryModelOpenAI(
           if ((event as any).message?.usage) {
             usage = {
               ...usage,
-              ...((event as any).message.usage),
+              ...(event as any).message.usage,
             }
           }
           break
@@ -164,11 +239,7 @@ export async function* queryModelOpenAI(
           const m: AssistantMessage = {
             message: {
               ...partialMessage,
-              content: normalizeContentFromAPI(
-                [block],
-                tools,
-                options.agentId,
-              ),
+              content: normalizeContentFromAPI([block], tools, options.agentId),
             },
             requestId: undefined,
             type: 'assistant',
@@ -192,7 +263,10 @@ export async function* queryModelOpenAI(
       }
 
       // Track cost and token usage (matching the Anthropic path in claude.ts)
-      if (event.type === 'message_stop' && usage.input_tokens + usage.output_tokens > 0) {
+      if (
+        event.type === 'message_stop' &&
+        usage.input_tokens + usage.output_tokens > 0
+      ) {
         const costUSD = calculateUSDCost(openaiModel, usage as any)
         addToTotalSessionCost(costUSD, usage as any, options.model)
       }