feat(tools): resilient web search and fetch across all providers (#836)

- Add exponential backoff retry to DuckDuckGo adapter (3 attempts with
  jitter) to handle transient rate-limiting and connection errors.
- Add native fetch() fallback in WebFetch when axios hangs with custom
  DNS lookup in bundled contexts.
- Prevent broken native-path fallback for web search on OpenAI shim
  providers (minimax, moonshot, nvidia-nim, etc.) that do not support
  Anthropic's web_search_20250305 tool.
- Cherry-pick existing fixes:
  - a48bd56: cover codex/minimax/nvidia-nim in getSmallFastModel()
  - 31f0b68: 45s budget + raw-markdown fallback for secondary model
  - 446c1e8: sparse Codex /responses payload parsing
  - ae3f0b2: echo reasoning_content on assistant tool-call messages
- Fix domainCheck.test.ts mock modules to include isFirstPartyAnthropicBaseUrl
  and isGithubNativeAnthropicMode exports.

Co-authored-by: OpenClaude <openclaude@gitlawb.com>

src/utils/model/model.openai-shim-providers.test.ts

@@ -1,7 +1,13 @@
-import { afterEach, beforeEach, expect, test } from 'bun:test'
+import { afterEach, beforeEach, expect, mock, test } from 'bun:test'
 
 import { saveGlobalConfig } from '../config.js'
-import { getUserSpecifiedModelSetting } from './model.js'
+import {
+  getDefaultHaikuModel,
+  getDefaultOpusModel,
+  getDefaultSonnetModel,
+  getSmallFastModel,
+  getUserSpecifiedModelSetting,
+} from './model.js'
 
 const SAVED_ENV = {
   CLAUDE_CODE_USE_OPENAI: process.env.CLAUDE_CODE_USE_OPENAI,
@@ -28,6 +34,11 @@ function restoreEnv(key: keyof typeof SAVED_ENV): void {
 }
 
 beforeEach(() => {
+  // Other test files (notably modelOptions.github.test.ts) install a
+  // persistent mock.module for './providers.js' that overrides getAPIProvider
+  // globally. Without mock.restore() here, those overrides bleed into this
+  // suite and the provider-kind branches we're testing become unreachable.
+  mock.restore()
   delete process.env.CLAUDE_CODE_USE_OPENAI
   delete process.env.CLAUDE_CODE_USE_GEMINI
   delete process.env.CLAUDE_CODE_USE_GITHUB
@@ -113,3 +124,76 @@ test('github provider still reads OPENAI_MODEL (regression guard)', () => {
   expect(model).toBe('github:copilot')
 })
 
+// ---------------------------------------------------------------------------
+// Default model helpers — must not fall through to claude-haiku-4-5 etc. for
+// OpenAI-shim providers whose endpoints don't speak Anthropic model names.
+// Hitting that fallthrough caused WebFetch to hang for 60s on MiniMax/Codex
+// because queryHaiku() shipped an unknown model id to the shim endpoint.
+// ---------------------------------------------------------------------------
+
+test('getSmallFastModel returns OPENAI_MODEL for MiniMax (regression: WebFetch hang)', () => {
+  process.env.MINIMAX_API_KEY = 'minimax-test'
+  process.env.OPENAI_MODEL = 'MiniMax-M2.5-highspeed'
+
+  expect(getSmallFastModel()).toBe('MiniMax-M2.5-highspeed')
+})
+
+test('getSmallFastModel returns OPENAI_MODEL for Codex (regression)', () => {
+  process.env.CLAUDE_CODE_USE_OPENAI = '1'
+  process.env.OPENAI_BASE_URL = 'https://chatgpt.com/backend-api/codex'
+  process.env.OPENAI_MODEL = 'codexspark'
+  process.env.CODEX_API_KEY = 'codex-test'
+  process.env.CHATGPT_ACCOUNT_ID = 'acct_test'
+
+  expect(getSmallFastModel()).toBe('codexspark')
+})
+
+test('getSmallFastModel returns OPENAI_MODEL for NVIDIA NIM (regression)', () => {
+  process.env.NVIDIA_NIM = '1'
+  process.env.CLAUDE_CODE_USE_OPENAI = '1'
+  process.env.OPENAI_MODEL = 'nvidia/llama-3.1-nemotron-70b-instruct'
+
+  expect(getSmallFastModel()).toBe('nvidia/llama-3.1-nemotron-70b-instruct')
+})
+
+test('getDefaultOpusModel returns OPENAI_MODEL for MiniMax', () => {
+  process.env.MINIMAX_API_KEY = 'minimax-test'
+  process.env.OPENAI_MODEL = 'MiniMax-M2.7'
+
+  expect(getDefaultOpusModel()).toBe('MiniMax-M2.7')
+})
+
+test('getDefaultSonnetModel returns OPENAI_MODEL for NVIDIA NIM', () => {
+  process.env.NVIDIA_NIM = '1'
+  process.env.CLAUDE_CODE_USE_OPENAI = '1'
+  process.env.OPENAI_MODEL = 'nvidia/llama-3.1-nemotron-70b-instruct'
+
+  expect(getDefaultSonnetModel()).toBe('nvidia/llama-3.1-nemotron-70b-instruct')
+})
+
+test('getDefaultHaikuModel returns OPENAI_MODEL for MiniMax', () => {
+  process.env.MINIMAX_API_KEY = 'minimax-test'
+  process.env.OPENAI_MODEL = 'MiniMax-M2.5-highspeed'
+
+  expect(getDefaultHaikuModel()).toBe('MiniMax-M2.5-highspeed')
+})
+
+test('default helpers do not leak claude-* names to shim providers', () => {
+  // Umbrella guard: for each OpenAI-shim provider, none of the default-model
+  // helpers may return an Anthropic-branded model name. That was the source
+  // of the WebFetch 60s hang — MiniMax received "claude-haiku-4-5" and sat
+  // on the connection.
+  process.env.MINIMAX_API_KEY = 'minimax-test'
+  process.env.OPENAI_MODEL = 'MiniMax-M2.7'
+
+  for (const fn of [
+    getSmallFastModel,
+    getDefaultOpusModel,
+    getDefaultSonnetModel,
+    getDefaultHaikuModel,
+  ]) {
+    const model = fn()
+    expect(model.toLowerCase()).not.toContain('claude')
+  }
+})
+

src/utils/model/model.ts

@@ -52,10 +52,25 @@ export function getSmallFastModel(): ModelName {
   if (getAPIProvider() === 'openai') {
     return process.env.OPENAI_MODEL || 'gpt-4o-mini'
   }
+  // Codex provider — OPENAI_MODEL is always set for Codex profiles; only fall
+  // back to a codex-spark alias when an override env strips it.
+  if (getAPIProvider() === 'codex') {
+    return process.env.OPENAI_MODEL || 'codexspark'
+  }
   // For GitHub Copilot provider
   if (getAPIProvider() === 'github') {
     return process.env.OPENAI_MODEL || 'github:copilot'
   }
+  // NVIDIA NIM — OPENAI_MODEL carries the user's active NIM model; use a
+  // small Meta Llama variant as the conservative fallback.
+  if (getAPIProvider() === 'nvidia-nim') {
+    return process.env.OPENAI_MODEL || 'meta/llama-3.1-8b-instruct'
+  }
+  // MiniMax — OPENAI_MODEL carries the active MiniMax model; fall back to
+  // the fastest tier (M2.5-highspeed) when missing.
+  if (getAPIProvider() === 'minimax') {
+    return process.env.OPENAI_MODEL || 'MiniMax-M2.5-highspeed'
+  }
   return getDefaultHaikuModel()
 }
 
@@ -171,6 +186,14 @@ export function getDefaultOpusModel(): ModelName {
   if (getAPIProvider() === 'github') {
     return process.env.OPENAI_MODEL || 'github:copilot'
   }
+  // NVIDIA NIM
+  if (getAPIProvider() === 'nvidia-nim') {
+    return process.env.OPENAI_MODEL || 'nvidia/llama-3.1-nemotron-70b-instruct'
+  }
+  // MiniMax — flagship tier for "opus"-equivalent.
+  if (getAPIProvider() === 'minimax') {
+    return process.env.OPENAI_MODEL || 'MiniMax-M2.7'
+  }
   // 3P providers (Bedrock, Vertex, Foundry) — kept as a separate branch
   // even when values match, since 3P availability lags firstParty and
   // these will diverge again at the next model launch.
@@ -205,6 +228,14 @@ export function getDefaultSonnetModel(): ModelName {
   if (getAPIProvider() === 'github') {
     return process.env.OPENAI_MODEL || 'github:copilot'
   }
+  // NVIDIA NIM
+  if (getAPIProvider() === 'nvidia-nim') {
+    return process.env.OPENAI_MODEL || 'nvidia/llama-3.1-nemotron-70b-instruct'
+  }
+  // MiniMax — mid tier for "sonnet"-equivalent.
+  if (getAPIProvider() === 'minimax') {
+    return process.env.OPENAI_MODEL || 'MiniMax-M2.5'
+  }
   // Default to Sonnet 4.5 for 3P since they may not have 4.6 yet
   if (getAPIProvider() !== 'firstParty') {
     return getModelStrings().sonnet45
@@ -237,6 +268,14 @@ export function getDefaultHaikuModel(): ModelName {
   if (getAPIProvider() === 'gemini') {
     return process.env.GEMINI_MODEL || 'gemini-2.0-flash-lite'
   }
+  // NVIDIA NIM
+  if (getAPIProvider() === 'nvidia-nim') {
+    return process.env.OPENAI_MODEL || 'meta/llama-3.1-8b-instruct'
+  }
+  // MiniMax — fastest tier for "haiku"-equivalent.
+  if (getAPIProvider() === 'minimax') {
+    return process.env.OPENAI_MODEL || 'MiniMax-M2.5-highspeed'
+  }
 
   // Haiku 4.5 is available on all platforms (first-party, Foundry, Bedrock, Vertex)
   return getModelStrings().haiku45

src/utils/model/providers.ts

@@ -19,7 +19,12 @@ export function getAPIProvider(): APIProvider {
   if (isEnvTruthy(process.env.NVIDIA_NIM)) {
     return 'nvidia-nim'
   }
-  if (isEnvTruthy(process.env.MINIMAX_API_KEY)) {
+  // MiniMax is signalled by a real API key, not a '1'/'true' flag. Using
+  // isEnvTruthy() here silently treated every MiniMax user as 'firstParty'
+  // (or 'openai' once they set CLAUDE_CODE_USE_OPENAI via the profile),
+  // making every provider-kind-specific branch for 'minimax' elsewhere in
+  // the codebase unreachable. Presence check is the correct signal.
+  if (typeof process.env.MINIMAX_API_KEY === 'string' && process.env.MINIMAX_API_KEY.trim() !== '') {
     return 'minimax'
   }
   return isEnvTruthy(process.env.CLAUDE_CODE_USE_GEMINI)