fix: normalizeMessagesForAPI 不再跨 tool_result 边界合并同 ID assistant 消息 (CC-1215)

ACP 模式下 extended thinking + tool_use 同一 turn 时，StreamingToolExecutor
在两个同 message.id 的 AssistantMessage 之间插入 tool_result，导致向后遍历
合并跨越边界，产生重复 tool_use ID → 孤立 tool_result → 连续 user 消息 → 400。

修改向后遍历停止条件：遇到非 assistant 消息（含 tool_result）即停止，不再跳过。

README.md

@@ -10,12 +10,11 @@
 
 > Which Claude do you like? The open source one is the best.
 
-牢 A (Anthropic) 官方 [Claude Code](https://docs.anthropic.com/en/docs/claude-code) CLI 工具的源码反编译/逆向还原项目。目标是将 Claude Code 大部分功能及工程化能力复现 (问就是老佛爷已经付过钱了)。虽然很难绷, 但是它叫做 CCB(踩踩背)... 而且, 我们实现了企业版或者需要登陆 Claude 账号才能使用的特性, 实现技术普惠
+牢 A (Anthropic) 官方 [Claude Code](https://docs.anthropic.com/en/docs/claude-code) 完整复原的工程化项目。虽然很难绷, 但是它叫做 CCB(踩踩背)... 而且, 我们实现了企业版或者需要登陆 Claude 账号才能使用的特性, 并在此基础上扩展了更多好玩的特性。
 
-> 我们将会在五一期间进行整个代码仓库的 lint 规范化, 这个期间提交的 PR 可能会有非常多的冲突, 所以大的功能请尽量在这之前提交哈
+[Peri Code](https://github.com/KonghaYao/peri)：Claude Code 兼容的 Rust Agent，多年大模型经验匠心制作，国内大模型（DeepSeek/GLM）精调，CPU/内存极致优化，在开发版/树莓派上也能跑 CC 一样的体验。
-
-[文档在这里, 支持投稿 PR](https://ccb.agent-aura.top/) | [留影文档在这里](./Friends.md) | [Discord 群组](https://discord.gg/uApuzJWGKX)
 
+[文档在这里](https://ccb.agent-aura.top/) | [留影文档在这里](./Friends.md) | [Discord 群组，群主在线答疑](https://discord.gg/uApuzJWGKX)
 
 | 特性                        | 说明                                                                                                                         | 文档                                                                                                                                      |
 | --------------------------- | ---------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
@@ -150,7 +149,6 @@ bun run build
 
 需要填写的字段：
 
-
 | 📌 字段      | 📝 说明       | 💡 示例                      |
 | ------------ | ------------- | ---------------------------- |
 | Base URL     | API 服务地址  | `https://api.example.com/v1` |

src/services/skillSearch/localSearch.ts

@@ -385,7 +385,7 @@ export function searchSkills(
   index: SkillIndexEntry[],
   limit = 5,
 ): SearchResult[] {
-  if (index.length === 0 || !query.trim()) return []
+  if (index.length === 0 || !query?.trim()) return []
 
   const queryTokens = tokenizeAndStem(query)
   if (queryTokens.length === 0) return []

src/utils/__tests__/messages.test.ts

@@ -610,3 +610,179 @@ describe('ensureToolResultPairing', () => {
     expect(lastMsg.type).toBe('user')
   })
 })
+
+// ─── CC-1215: normalizeMessagesForAPI must not merge assistants across tool_results ──
+
+describe('normalizeMessagesForAPI – thinking + tool_use same turn (CC-1215)', () => {
+  test('does not merge same-id assistants across a tool_result boundary', () => {
+    // Simulate the streaming sequence when extended thinking + tool_use appear
+    // in the same turn, and StreamingToolExecutor inserts a tool_result
+    // between the two assistant content-block messages.
+    const sharedMessageId = 'msg_shared_001'
+    const toolUseId = 'toolu_cc1215'
+
+    // assistant[thinking] — first content_block_stop yield
+    const thinkingMsg = createAssistantMessage({
+      content: [
+        { type: 'thinking', thinking: 'Let me think...', signature: 'sig1' },
+      ],
+    })
+    thinkingMsg.message.id = sharedMessageId
+
+    // user[tool_result] — from StreamingToolExecutor completing fast
+    const toolResultMsg = createUserMessage({
+      content: [
+        {
+          type: 'tool_result',
+          tool_use_id: toolUseId,
+          content: '/home/user',
+        },
+      ],
+    })
+
+    // assistant[tool_use] — second content_block_stop yield
+    const toolUseMsg = createAssistantMessage({
+      content: [
+        {
+          type: 'tool_use',
+          id: toolUseId,
+          name: 'Bash',
+          input: { command: 'pwd' },
+        },
+      ],
+    })
+    toolUseMsg.message.id = sharedMessageId
+
+    const messages: Message[] = [
+      makeUserMsg('Run pwd'),
+      thinkingMsg,
+      toolResultMsg,
+      toolUseMsg,
+    ]
+
+    const result = normalizeMessagesForAPI(messages)
+
+    // Before the fix, the backward walk would skip the tool_result and merge
+    // thinking + tool_use into one assistant. This produced duplicate tool_use
+    // IDs after ensureToolResultPairing ran, leading to orphaned tool_results
+    // and consecutive user messages → API 400.
+    //
+    // After the fix, the backward walk stops at the tool_result, so the two
+    // assistants remain separate. The result should have 4 messages:
+    //   user, assistant[thinking], user[tool_result], assistant[tool_use]
+    expect(result).toHaveLength(4)
+    expect(result[0]!.type).toBe('user')
+    expect(result[1]!.type).toBe('assistant')
+    expect(result[2]!.type).toBe('user')
+    expect(result[3]!.type).toBe('assistant')
+
+    // The thinking assistant should NOT have been merged with the tool_use one
+    const thinkingAssistant = result[1] as AssistantMessage
+    const thinkingContent = thinkingAssistant.message.content as Array<{
+      type: string
+    }>
+    expect(thinkingContent.some(b => b.type === 'tool_use')).toBe(false)
+
+    const toolUseAssistant = result[3] as AssistantMessage
+    const toolUseContent = toolUseAssistant.message.content as Array<{
+      type: string
+    }>
+    expect(toolUseContent.some(b => b.type === 'tool_use')).toBe(true)
+  })
+
+  test('still merges consecutive same-id assistants without intervening tool_result', () => {
+    const sharedMessageId = 'msg_shared_002'
+
+    const thinkingMsg = createAssistantMessage({
+      content: [{ type: 'thinking', thinking: 'Hmm', signature: 'sig2' }],
+    })
+    thinkingMsg.message.id = sharedMessageId
+
+    const toolUseMsg = createAssistantMessage({
+      content: [
+        {
+          type: 'tool_use',
+          id: 'toolu_merge',
+          name: 'Bash',
+          input: { command: 'ls' },
+        },
+      ],
+    })
+    toolUseMsg.message.id = sharedMessageId
+
+    // No tool_result between them — they should still be merged
+    const messages: Message[] = [
+      makeUserMsg('List files'),
+      thinkingMsg,
+      toolUseMsg,
+    ]
+
+    const result = normalizeMessagesForAPI(messages)
+
+    // Should be: user, assistant[thinking + tool_use]
+    expect(result).toHaveLength(2)
+    expect(result[0]!.type).toBe('user')
+
+    const merged = result[1] as AssistantMessage
+    const content = merged.message.content as Array<{ type: string }>
+    expect(content.some(b => b.type === 'thinking')).toBe(true)
+    expect(content.some(b => b.type === 'tool_use')).toBe(true)
+  })
+
+  test('full pipeline: normalize + ensureToolResultPairing produces valid role alternation', () => {
+    const sharedMessageId = 'msg_shared_003'
+    const toolUseId = 'toolu_pipeline'
+
+    const thinkingMsg = createAssistantMessage({
+      content: [
+        { type: 'thinking', thinking: 'Planning...', signature: 'sig3' },
+      ],
+    })
+    thinkingMsg.message.id = sharedMessageId
+
+    const toolResultMsg = createUserMessage({
+      content: [
+        {
+          type: 'tool_result',
+          tool_use_id: toolUseId,
+          content: 'file.txt',
+        },
+      ],
+    })
+
+    const toolUseMsg = createAssistantMessage({
+      content: [
+        {
+          type: 'tool_use',
+          id: toolUseId,
+          name: 'Bash',
+          input: { command: 'ls' },
+        },
+      ],
+    })
+    toolUseMsg.message.id = sharedMessageId
+
+    // Full pipeline: normalize → ensureToolResultPairing
+    const normalized = normalizeMessagesForAPI([
+      makeUserMsg('Run ls'),
+      thinkingMsg,
+      toolResultMsg,
+      toolUseMsg,
+    ])
+    const result = ensureToolResultPairing(normalized)
+
+    // Verify strict role alternation: user → assistant → user → assistant → ...
+    for (let i = 1; i < result.length; i++) {
+      const prev = result[i - 1]!
+      const curr = result[i]!
+      if (prev.type === 'user' && curr.type === 'user') {
+        expect.unreachable(`Consecutive user messages at index ${i - 1}-${i}`)
+      }
+      if (prev.type === 'assistant' && curr.type === 'assistant') {
+        expect.unreachable(
+          `Consecutive assistant messages at index ${i - 1}-${i}`,
+        )
+      }
+    }
+  })
+})

src/utils/apiPreconnect.ts

@@ -25,6 +25,7 @@
 
 import { getOauthConfig } from '../constants/oauth.js'
 import { isEnvTruthy } from './envUtils.js'
+import { isEssentialTrafficOnly } from './privacyLevel.js'
 
 let fired = false
 
@@ -32,6 +33,10 @@ export function preconnectAnthropicApi(): void {
   if (fired) return
   fired = true
 
+  // Also skip when non-essential traffic is disabled via
+  // CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC / DISABLE_TELEMETRY / proxy env.
+  if (isEssentialTrafficOnly()) return
+
   // Skip if using a cloud provider — different endpoint + auth
   if (
     isEnvTruthy(process.env.CLAUDE_CODE_USE_BEDROCK) ||

src/utils/messages.ts

@@ -2541,21 +2541,26 @@ export function normalizeMessagesForAPI(
           }
 
           // Find a previous assistant message with the same message ID and merge.
-          // Walk backwards, skipping tool results and different-ID assistants,
+          // Walk backwards, skipping different-ID assistants, since concurrent
-          // since concurrent agents (teammates) can interleave streaming content
+          // agents (teammates) can interleave streaming content blocks from
-          // blocks from multiple API responses with different message IDs.
+          // multiple API responses with different message IDs.
+          //
+          // Do NOT skip tool_result messages — when claude.ts yields separate
+          // AssistantMessages for thinking and tool_use blocks (same message.id),
+          // a StreamingToolExecutor tool_result can land between them. Merging
+          // across that boundary produces duplicate tool_use IDs that downstream
+          // ensureToolResultPairing strips, leaving orphaned tool_results and
+          // ultimately consecutive user messages → API 400 (CC-1215).
           for (let i = result.length - 1; i >= 0; i--) {
             const msg = result[i]!
 
-            if (msg.type !== 'assistant' && !isToolResultMessage(msg)) {
+            if (msg.type !== 'assistant') {
               break
             }
 
-            if (msg.type === 'assistant') {
+            if (msg.message.id === normalizedMessage.message.id) {
-              if (msg.message.id === normalizedMessage.message.id) {
+              result[i] = mergeAssistantMessages(msg, normalizedMessage)
-                result[i] = mergeAssistantMessages(msg, normalizedMessage)
+              return
-                return
-              }
             }
           }
 

src/utils/model/model.ts

@@ -120,6 +120,19 @@ export function getBestModel(): ModelName {
   return getDefaultOpusModel()
 }
 
+/**
+ * Resolve the provider's primary model from its env var (e.g. OPENAI_MODEL).
+ * Returns undefined for providers that don't have a primary-model env var
+ * (Bedrock, Vertex, Foundry, firstParty).
+ */
+function getProviderPrimaryModel(): ModelName | undefined {
+  const provider = getAPIProvider()
+  if (provider === 'openai') return process.env.OPENAI_MODEL
+  if (provider === 'gemini') return process.env.GEMINI_MODEL
+  if (provider === 'grok') return process.env.GROK_MODEL
+  return undefined
+}
+
 // @[MODEL LAUNCH]: Update the default Opus model (3P providers may lag so keep defaults unchanged).
 export function getDefaultOpusModel(): ModelName {
   const provider = getAPIProvider()
@@ -138,10 +151,12 @@ export function getDefaultOpusModel(): ModelName {
   if (process.env.ANTHROPIC_DEFAULT_OPUS_MODEL) {
     return process.env.ANTHROPIC_DEFAULT_OPUS_MODEL
   }
-  // 3P providers (Bedrock, Vertex, Foundry) all publish Opus 4.7 in sync
+  // 3P providers: if user set a primary model (e.g. OPENAI_MODEL=glm-5.1),
-  // with firstParty as of 2026-04-17 (AWS Bedrock, Google Vertex AI, and
+  // fall back to it instead of a hardcoded Anthropic model. This prevents
-  // Microsoft Foundry announcements and model catalogs all confirm). The
+  // sideQuery / background tasks from sending requests to Anthropic's API
-  // branch is kept as a structural hook in case a future launch lags on 3P.
+  // when the user configured a third-party provider.
+  const primaryModel = getProviderPrimaryModel()
+  if (primaryModel) return primaryModel
   if (provider !== 'firstParty') {
     return getModelStrings().opus47
   }
@@ -166,7 +181,11 @@ export function getDefaultSonnetModel(): ModelName {
   if (process.env.ANTHROPIC_DEFAULT_SONNET_MODEL) {
     return process.env.ANTHROPIC_DEFAULT_SONNET_MODEL
   }
-  // Default to Sonnet 4.5 for 3P since they may not have 4.6 yet
+  // 3P providers: fall back to user's primary model instead of a hardcoded
+  // Anthropic model name. Prevents background API calls from being routed to
+  // Anthropic when the user configured a third-party endpoint.
+  const primaryModel = getProviderPrimaryModel()
+  if (primaryModel) return primaryModel
   if (provider !== 'firstParty') {
     return getModelStrings().sonnet45
   }
@@ -191,6 +210,10 @@ export function getDefaultHaikuModel(): ModelName {
   if (process.env.ANTHROPIC_DEFAULT_HAIKU_MODEL) {
     return process.env.ANTHROPIC_DEFAULT_HAIKU_MODEL
   }
+  // 3P providers: fall back to user's primary model instead of a hardcoded
+  // Anthropic model name.
+  const primaryModel = getProviderPrimaryModel()
+  if (primaryModel) return primaryModel
 
   // Haiku 4.5 is available on all platforms (first-party, Foundry, Bedrock, Vertex)
   return getModelStrings().haiku45

src/utils/performanceShim.ts

@@ -135,6 +135,9 @@ const shim = {
   clearResourceTimings: (() => {}) as typeof performance.clearResourceTimings,
   setResourceTimingBufferSize:
     (() => {}) as typeof performance.setResourceTimingBufferSize,
+  // Node.js v22 undici internal calls this after every fetch — must exist to
+  // avoid TypeError: markResourceTiming is not a function
+  markResourceTiming: (() => {}) as any,
   // Delegate read-only properties to the original
   get timeOrigin() {
     return original.timeOrigin
@@ -148,7 +151,7 @@ const shim = {
   toJSON() {
     return original.toJSON()
   },
-} as typeof performance
+} as unknown as typeof performance
 
 /**
  * Install the shim onto globalThis.performance. Safe to call multiple times.

src/utils/sideQuery.ts

@@ -33,6 +33,19 @@ import { errorMessage } from './errors.js'
 import { computeFingerprint } from './fingerprint.js'
 import { getAPIProvider } from './model/providers.js'
 import { normalizeModelStringForAPI } from './model/model.js'
+import { getOpenAIClient } from '../services/api/openai/client.js'
+import { getGrokClient } from '../services/api/grok/client.js'
+import {
+  anthropicMessagesToOpenAI,
+  resolveOpenAIModel,
+  anthropicToolsToOpenAI,
+  anthropicToolChoiceToOpenAI,
+  resolveGrokModel,
+  resolveGeminiModel,
+  anthropicToolsToGemini,
+  anthropicToolChoiceToGemini,
+} from '@ant/model-provider'
+import type { SystemPrompt } from './systemPromptType.js'
 
 type MessageParam = Anthropic.MessageParam
 type TextBlockParam = Anthropic.TextBlockParam
@@ -99,6 +112,46 @@ function extractFirstUserMessageText(messages: MessageParam[]): string {
   return textBlock?.type === 'text' ? textBlock.text : ''
 }
 
+/**
+ * Extract system prompt text from the `system` option.
+ */
+function extractSystemText(system?: string | TextBlockParam[]): string {
+  if (!system) return ''
+  if (typeof system === 'string') return system
+  return system
+    .filter((b): b is { type: 'text'; text: string } => 'text' in b && !!b.text)
+    .map(b => b.text)
+    .join('\n\n')
+}
+
+/**
+ * Convert Anthropic MessageParam[] to a list of {role, content} objects
+ * suitable for OpenAI-compatible chat.completions APIs.
+ */
+function messageParamsToOpenAIRoleContent(
+  messages: MessageParam[],
+): Array<{ role: 'user' | 'assistant'; content: string }> {
+  const result: Array<{ role: 'user' | 'assistant'; content: string }> = []
+  for (const m of messages) {
+    if (m.role !== 'user' && m.role !== 'assistant') continue
+    const text =
+      typeof m.content === 'string'
+        ? m.content
+        : Array.isArray(m.content)
+          ? m.content
+              .filter(
+                (b): b is { type: 'text'; text: string } => b.type === 'text',
+              )
+              .map(b => b.text)
+              .join('\n')
+          : ''
+    if (text) {
+      result.push({ role: m.role as 'user' | 'assistant', content: text })
+    }
+  }
+  return result
+}
+
 /**
  * Lightweight API wrapper for "side queries" outside the main conversation loop.
  *
@@ -112,6 +165,7 @@ function extractFirstUserMessageText(messages: MessageParam[]): string {
  * - Proper betas for the model
  * - API metadata
  * - Model string normalization (strips [1m] suffix for API)
+ * - Third-party provider routing (OpenAI, Grok, Gemini)
  *
  * @example
  * // Permission explainer
@@ -142,6 +196,14 @@ export async function sideQuery(opts: SideQueryOptions): Promise<BetaMessage> {
     stop_sequences,
   } = opts
 
+  const provider = getAPIProvider()
+  if (provider === 'openai' || provider === 'grok') {
+    return sideQueryViaOpenAICompatible(opts)
+  }
+  if (provider === 'gemini') {
+    return sideQueryViaGemini(opts)
+  }
+
   const client = await getAnthropicClient({
     maxRetries,
     model,
@@ -198,7 +260,6 @@ export async function sideQuery(opts: SideQueryOptions): Promise<BetaMessage> {
   }
 
   const normalizedModel = normalizeModelStringForAPI(model)
-  const provider = getAPIProvider()
   const start = Date.now()
   const traceName = `side-query:${opts.querySource}`
 
@@ -328,3 +389,352 @@ export async function sideQuery(opts: SideQueryOptions): Promise<BetaMessage> {
 
   return response
 }
+
+/**
+ * OpenAI-compatible side query for OpenAI and Grok providers.
+ * Both use the OpenAI SDK with different base URLs.
+ *
+ * Converts Anthropic-format params to OpenAI Chat Completions, sends a
+ * non-streaming request, and wraps the response back into a BetaMessage
+ * shape so callers remain provider-agnostic.
+ *
+ * Supports tools and tool_choice for structured output (e.g. yoloClassifier,
+ * permissionExplainer).
+ */
+async function sideQueryViaOpenAICompatible(
+  opts: SideQueryOptions,
+): Promise<BetaMessage> {
+  const {
+    model,
+    system,
+    messages,
+    tools,
+    tool_choice,
+    max_tokens = 1024,
+    temperature,
+    signal,
+  } = opts
+
+  const provider = getAPIProvider()
+  const normalizedModel = normalizeModelStringForAPI(model)
+
+  // Resolve model name and client per provider
+  let openaiModel: string
+  // eslint-disable-next-line @typescript-eslint/no-redundant-type-constituents
+  let client: import('openai').default
+  if (provider === 'grok') {
+    openaiModel = resolveGrokModel(normalizedModel)
+    client = getGrokClient({ maxRetries: opts.maxRetries ?? 2 })
+  } else {
+    openaiModel = resolveOpenAIModel(normalizedModel)
+    client = getOpenAIClient({ maxRetries: opts.maxRetries ?? 2 })
+  }
+
+  // Build system prompt text
+  const systemText = extractSystemText(system)
+
+  // Build OpenAI messages: system first, then user/assistant
+  const openaiMessages: Array<{
+    role: 'system' | 'user' | 'assistant'
+    content: string
+  }> = []
+  if (systemText) {
+    openaiMessages.push({ role: 'system', content: systemText })
+  }
+  openaiMessages.push(...messageParamsToOpenAIRoleContent(messages))
+
+  // Convert tools and tool_choice if provided
+  const openaiTools =
+    tools && tools.length > 0
+      ? anthropicToolsToOpenAI(tools as BetaToolUnion[])
+      : undefined
+  const openaiToolChoice = tool_choice
+    ? anthropicToolChoiceToOpenAI(tool_choice)
+    : undefined
+
+  const start = Date.now()
+
+  const requestParams: Record<string, unknown> = {
+    model: openaiModel,
+    messages: openaiMessages,
+    max_tokens,
+  }
+  if (temperature !== undefined) requestParams.temperature = temperature
+  if (openaiTools && openaiTools.length > 0) {
+    requestParams.tools = openaiTools
+    if (openaiToolChoice) requestParams.tool_choice = openaiToolChoice
+  }
+
+  const response = await client.chat.completions.create(
+    requestParams as unknown as import('openai/resources/chat/completions/completions.mjs').ChatCompletionCreateParamsNonStreaming,
+    { signal },
+  )
+
+  const choice = response.choices[0]
+  const message = choice?.message
+
+  // Build content blocks for BetaMessage
+  const contentBlocks: Array<
+    | { type: 'text'; text: string }
+    | { type: 'tool_use'; id: string; name: string; input: unknown }
+  > = []
+
+  if (message?.content) {
+    contentBlocks.push({ type: 'text', text: message.content })
+  }
+
+  if (message?.tool_calls) {
+    for (const tc of message.tool_calls) {
+      // ChatCompletionMessageToolCall is a union — only function-type has .function
+      if (tc.type === 'function' && 'function' in tc) {
+        const fn = (tc as { function: { name: string; arguments: string } })
+          .function
+        contentBlocks.push({
+          type: 'tool_use',
+          id: tc.id ?? `toolu_${Date.now()}`,
+          name: fn.name,
+          input: JSON.parse(fn.arguments || '{}'),
+        })
+      }
+    }
+  }
+
+  const now = Date.now()
+  const requestId = response.id
+  const lastCompletion = getLastApiCompletionTimestamp()
+  logEvent('tengu_api_success', {
+    requestId:
+      requestId as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS,
+    querySource:
+      opts.querySource as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS,
+    model:
+      openaiModel as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS,
+    inputTokens: response.usage?.prompt_tokens ?? 0,
+    outputTokens: response.usage?.completion_tokens ?? 0,
+    cachedInputTokens: 0,
+    uncachedInputTokens: response.usage?.prompt_tokens ?? 0,
+    durationMsIncludingRetries: now - start,
+    timeSinceLastApiCallMs:
+      lastCompletion !== null ? now - lastCompletion : undefined,
+  })
+  setLastApiCompletionTimestamp(now)
+
+  const stopReason =
+    choice?.finish_reason === 'tool_calls'
+      ? 'tool_use'
+      : choice?.finish_reason === 'length'
+        ? 'max_tokens'
+        : 'end_turn'
+
+  return {
+    id: response.id,
+    type: 'message',
+    role: 'assistant',
+    content: contentBlocks as BetaMessage['content'],
+    model: openaiModel,
+    stop_reason: stopReason as BetaMessage['stop_reason'],
+    stop_sequence: null,
+    usage: {
+      input_tokens: response.usage?.prompt_tokens ?? 0,
+      output_tokens: response.usage?.completion_tokens ?? 0,
+    },
+  } as BetaMessage
+}
+
+/**
+ * Gemini side query. Converts Anthropic-format params to Gemini
+ * generateContent format, sends a non-streaming request via fetch,
+ * and wraps the response back into a BetaMessage shape.
+ */
+async function sideQueryViaGemini(
+  opts: SideQueryOptions,
+): Promise<BetaMessage> {
+  const {
+    model,
+    system,
+    messages,
+    tools,
+    tool_choice,
+    max_tokens = 1024,
+    temperature,
+    signal,
+  } = opts
+
+  const normalizedModel = normalizeModelStringForAPI(model)
+  const geminiModel = resolveGeminiModel(normalizedModel)
+
+  // Build Gemini contents from Anthropic MessageParam[]
+  const contents: Array<{
+    role: 'user' | 'model'
+    parts: Array<{ text: string }>
+  }> = []
+  for (const m of messages) {
+    if (m.role !== 'user' && m.role !== 'assistant') continue
+    const text =
+      typeof m.content === 'string'
+        ? m.content
+        : Array.isArray(m.content)
+          ? m.content
+              .filter(
+                (b): b is { type: 'text'; text: string } => b.type === 'text',
+              )
+              .map(b => b.text)
+              .join('\n')
+          : ''
+    if (text) {
+      contents.push({
+        role: m.role === 'assistant' ? 'model' : 'user',
+        parts: [{ text }],
+      })
+    }
+  }
+
+  // Build system instruction
+  const systemText = extractSystemText(system)
+  const systemInstruction = systemText
+    ? { parts: [{ text: systemText }] }
+    : undefined
+
+  // Convert tools and tool_choice
+  const geminiTools =
+    tools && tools.length > 0
+      ? anthropicToolsToGemini(tools as BetaToolUnion[])
+      : undefined
+  const geminiToolConfig = tool_choice
+    ? anthropicToolChoiceToGemini(tool_choice)
+    : undefined
+
+  const baseUrl = (
+    process.env.GEMINI_BASE_URL ||
+    'https://generativelanguage.googleapis.com/v1beta'
+  ).replace(/\/+$/, '')
+  const modelPath = geminiModel.startsWith('models/')
+    ? geminiModel
+    : `models/${geminiModel}`
+  const url = `${baseUrl}/${modelPath}:generateContent`
+
+  const body: Record<string, unknown> = {
+    contents,
+    ...(systemInstruction && { systemInstruction }),
+    ...(geminiTools && geminiTools.length > 0 && { tools: geminiTools }),
+    ...(geminiToolConfig && {
+      toolConfig: { functionCallingConfig: geminiToolConfig },
+    }),
+    ...(temperature !== undefined && {
+      generationConfig: { temperature },
+    }),
+    ...(max_tokens !== undefined && {
+      generationConfig: {
+        ...(temperature !== undefined && { temperature }),
+        maxOutputTokens: max_tokens,
+      },
+    }),
+  }
+
+  // Merge generationConfig if both temperature and max_tokens are set
+  if (temperature !== undefined && max_tokens !== undefined) {
+    body.generationConfig = { temperature, maxOutputTokens: max_tokens }
+  }
+
+  const start = Date.now()
+
+  const res = await fetch(url, {
+    method: 'POST',
+    headers: {
+      'Content-Type': 'application/json',
+      'x-goog-api-key': process.env.GEMINI_API_KEY || '',
+    },
+    body: JSON.stringify(body),
+    signal,
+  })
+
+  if (!res.ok) {
+    const errorBody = await res.text()
+    throw new Error(
+      `Gemini API request failed (${res.status} ${res.statusText}): ${errorBody || 'empty response body'}`,
+    )
+  }
+
+  const geminiResponse = (await res.json()) as {
+    candidates?: Array<{
+      content?: {
+        role?: string
+        parts?: Array<{
+          text?: string
+          functionCall?: { name?: string; args?: Record<string, unknown> }
+        }>
+      }
+      finishReason?: string
+    }>
+    usageMetadata?: {
+      promptTokenCount?: number
+      candidatesTokenCount?: number
+      totalTokenCount?: number
+    }
+    id?: string
+  }
+
+  // Build content blocks from Gemini response
+  const contentBlocks: Array<
+    | { type: 'text'; text: string }
+    | { type: 'tool_use'; id: string; name: string; input: unknown }
+  > = []
+
+  const candidate = geminiResponse.candidates?.[0]
+  const parts = candidate?.content?.parts
+  if (parts) {
+    for (const part of parts) {
+      if (part.text) {
+        contentBlocks.push({ type: 'text', text: part.text })
+      }
+      if (part.functionCall) {
+        contentBlocks.push({
+          type: 'tool_use',
+          id: `toolu_${Date.now()}_${Math.random().toString(36).slice(2, 8)}`,
+          name: part.functionCall.name ?? '',
+          input: part.functionCall.args ?? {},
+        })
+      }
+    }
+  }
+
+  const now = Date.now()
+  const lastCompletion = getLastApiCompletionTimestamp()
+  logEvent('tengu_api_success', {
+    requestId: (geminiResponse.id ??
+      '') as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS,
+    querySource:
+      opts.querySource as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS,
+    model:
+      geminiModel as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS,
+    inputTokens: geminiResponse.usageMetadata?.promptTokenCount ?? 0,
+    outputTokens: geminiResponse.usageMetadata?.candidatesTokenCount ?? 0,
+    cachedInputTokens: 0,
+    uncachedInputTokens: geminiResponse.usageMetadata?.promptTokenCount ?? 0,
+    durationMsIncludingRetries: now - start,
+    timeSinceLastApiCallMs:
+      lastCompletion !== null ? now - lastCompletion : undefined,
+  })
+  setLastApiCompletionTimestamp(now)
+
+  const stopReason =
+    candidate?.finishReason === 'STOP'
+      ? 'end_turn'
+      : candidate?.finishReason === 'MAX_TOKENS'
+        ? 'max_tokens'
+        : 'end_turn'
+
+  return {
+    id: geminiResponse.id ?? `gemini_${Date.now()}`,
+    type: 'message',
+    role: 'assistant',
+    content: contentBlocks as BetaMessage['content'],
+    model: geminiModel,
+    stop_reason: stopReason as BetaMessage['stop_reason'],
+    stop_sequence: null,
+    usage: {
+      input_tokens: geminiResponse.usageMetadata?.promptTokenCount ?? 0,
+      output_tokens: geminiResponse.usageMetadata?.candidatesTokenCount ?? 0,
+    },
+  } as BetaMessage
+}