fix(security): remove unauthenticated file-based permission polling

Remove the legacy file-based permission polling from useSwarmPermissionPoller
that read from ~/.claude/teams/{name}/permissions/resolved/ — an unauthenticated
directory where any local process could forge approval files to auto-approve
tool uses for swarm teammates.

The file polling was dead code:
- The useSwarmPermissionPoller() hook was never mounted by any component
- resolvePermission() (the file writer) was never imported outside its module
- Permission responses are delivered exclusively via the mailbox system:
  Leader: sendPermissionResponseViaMailbox() → writeToMailbox()
  Worker: useInboxPoller → processMailboxPermissionResponse()

Changes:
- Remove file polling loop, processResponse(), and React hook imports from
  useSwarmPermissionPoller.ts (now a pure callback registry module)
- Mark 7 file-based functions as @deprecated in permissionSync.ts
- Add 4 regression tests verifying the removal

No exported functions removed — only deprecated. All 5 consumer modules
verified: they import only mailbox-based functions that remain unchanged.

.env.example

@@ -225,6 +225,30 @@ ANTHROPIC_API_KEY=sk-ant-your-key-here
 # GOOGLE_CLOUD_PROJECT=your-gcp-project-id
 
 
+# -----------------------------------------------------------------------------
+# Option 9: NVIDIA NIM
+# -----------------------------------------------------------------------------
+# NVIDIA NIM provides hosted inference endpoints for NVIDIA models.
+# Get your API key from https://build.nvidia.com/
+#
+# CLAUDE_CODE_USE_OPENAI=1
+# NVIDIA_API_KEY=nvapi-your-key-here
+# OPENAI_BASE_URL=https://integrate.api.nvidia.com/v1
+# OPENAI_MODEL=nvidia/llama-3.1-nemotron-70b-instruct
+
+
+# -----------------------------------------------------------------------------
+# Option 10: MiniMax
+# -----------------------------------------------------------------------------
+# MiniMax API provides text generation models.
+# Get your API key from https://platform.minimax.io/
+#
+# CLAUDE_CODE_USE_OPENAI=1
+# MINIMAX_API_KEY=your-minimax-key-here
+# OPENAI_BASE_URL=https://api.minimax.io/v1
+# OPENAI_MODEL=MiniMax-M2.5
+
+
 # =============================================================================
 # OPTIONAL TUNING
 # =============================================================================

.github/workflows/release.yml

@@ -11,6 +11,7 @@ concurrency:
 
 jobs:
   release-please:
+    if: ${{ github.repository == 'Gitlawb/openclaude' }}
     name: Release Please
     runs-on: ubuntu-latest
     permissions:

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "0.3.0"
+  ".": "0.5.2"
 }

CHANGELOG.md

@@ -1,5 +1,59 @@
 # Changelog
 
+## [0.5.2](https://github.com/Gitlawb/openclaude/compare/v0.5.1...v0.5.2) (2026-04-20)
+
+
+### Bug Fixes
+
+* **api:** replace phrase-based reasoning sanitizer with tag-based filter ([#779](https://github.com/Gitlawb/openclaude/issues/779)) ([336ddcc](https://github.com/Gitlawb/openclaude/commit/336ddcc50d59d79ebff50993f2673652aecb0d7d))
+
+## [0.5.1](https://github.com/Gitlawb/openclaude/compare/v0.5.0...v0.5.1) (2026-04-20)
+
+
+### Bug Fixes
+
+* enforce Bash path constraints after sandbox allow ([#777](https://github.com/Gitlawb/openclaude/issues/777)) ([7002cb3](https://github.com/Gitlawb/openclaude/commit/7002cb302b78ea2a19da3f26226de24e2903fa1d))
+* enforce MCP OAuth callback state before errors ([#775](https://github.com/Gitlawb/openclaude/issues/775)) ([739b8d1](https://github.com/Gitlawb/openclaude/commit/739b8d1f40fde0e401a5cbd2b9a55d88bd5124ad))
+* require trusted approval for sandbox override ([#778](https://github.com/Gitlawb/openclaude/issues/778)) ([aab4890](https://github.com/Gitlawb/openclaude/commit/aab489055c53dd64369414116fe93226d2656273))
+
+## [0.5.0](https://github.com/Gitlawb/openclaude/compare/v0.4.0...v0.5.0) (2026-04-20)
+
+
+### Features
+
+* add OPENCLAUDE_DISABLE_STRICT_TOOLS env var to opt out of strict MCP tool schema normalization ([#770](https://github.com/Gitlawb/openclaude/issues/770)) ([e6e8d9a](https://github.com/Gitlawb/openclaude/commit/e6e8d9a24897e4c9ef08b72df20fabbf8ef27f38))
+* mask provider api key input ([#772](https://github.com/Gitlawb/openclaude/issues/772)) ([13e9f22](https://github.com/Gitlawb/openclaude/commit/13e9f22a83a2b0f85f557b1e12c9442ba61241e4))
+
+
+### Bug Fixes
+
+* allow provider recovery during startup ([#765](https://github.com/Gitlawb/openclaude/issues/765)) ([f828171](https://github.com/Gitlawb/openclaude/commit/f828171ef1ab94e2acf73a28a292799e4e26cc0d))
+* **api:** drop orphan tool results to satisfy strict role sequence ([#745](https://github.com/Gitlawb/openclaude/issues/745)) ([b786b76](https://github.com/Gitlawb/openclaude/commit/b786b765f01f392652eaf28ed3579a96b7260a53))
+* **help:** prevent /help tab crash from undefined descriptions ([#732](https://github.com/Gitlawb/openclaude/issues/732)) ([3d1979f](https://github.com/Gitlawb/openclaude/commit/3d1979ff066db32415e0c8321af916d81f5f2621))
+* **mcp:** sync required array with properties in tool schemas ([#754](https://github.com/Gitlawb/openclaude/issues/754)) ([002a8f1](https://github.com/Gitlawb/openclaude/commit/002a8f1f6de2fcfc917165d828501d3047bad61f))
+* remove cached mcpClient in diagnostic tracking to prevent stale references ([#727](https://github.com/Gitlawb/openclaude/issues/727)) ([2c98be7](https://github.com/Gitlawb/openclaude/commit/2c98be700274a4241963b5f43530bf3bd8f8963f))
+* use raw context window for auto-compact percentage display ([#748](https://github.com/Gitlawb/openclaude/issues/748)) ([55c5f26](https://github.com/Gitlawb/openclaude/commit/55c5f262a9a5a8be0aa9ae8dc6c7dafc465eb2c6))
+
+## [0.4.0](https://github.com/Gitlawb/openclaude/compare/v0.3.0...v0.4.0) (2026-04-17)
+
+
+### Features
+
+* add Alibaba Coding Plan (DashScope) provider support ([#509](https://github.com/Gitlawb/openclaude/issues/509)) ([43ac6db](https://github.com/Gitlawb/openclaude/commit/43ac6dba75537282da1e2ad8f855082bc4e25f1e))
+* add NVIDIA NIM and MiniMax provider support ([#552](https://github.com/Gitlawb/openclaude/issues/552)) ([51191d6](https://github.com/Gitlawb/openclaude/commit/51191d61326e1f8319d70b3a3c0d9229e185a564))
+* add ripgrep to Dockerfile for faster file searching ([#688](https://github.com/Gitlawb/openclaude/issues/688)) ([12dd375](https://github.com/Gitlawb/openclaude/commit/12dd3755c619cc27af3b151ae8fdb9d425a7b9a2))
+* **api:** classify openai-compatible provider failures ([#708](https://github.com/Gitlawb/openclaude/issues/708)) ([80a00ac](https://github.com/Gitlawb/openclaude/commit/80a00acc2c6dc4657a78de7366f7a9ebc920bfbb))
+* **vscode:** add full chat interface to OpenClaude extension ([#608](https://github.com/Gitlawb/openclaude/issues/608)) ([fbcd928](https://github.com/Gitlawb/openclaude/commit/fbcd928f7f8511da795aea3ad318bddf0ab9a1a7))
+
+
+### Bug Fixes
+
+* focus "Done" option after completing provider manager actions ([#718](https://github.com/Gitlawb/openclaude/issues/718)) ([d6f5130](https://github.com/Gitlawb/openclaude/commit/d6f5130c204d8ffe582212466768706cd7fd6774))
+* **models:** prevent /models crash from non-string saved model values ([#691](https://github.com/Gitlawb/openclaude/issues/691)) ([6b2121d](https://github.com/Gitlawb/openclaude/commit/6b2121da12189fa7ce1f33394d18abd24cf8a01b))
+* prevent crash in commands tab when description is undefined ([#730](https://github.com/Gitlawb/openclaude/issues/730)) ([eed77e6](https://github.com/Gitlawb/openclaude/commit/eed77e6579866a98384dcc948a0ad6406614ede3))
+* strip comments before scanning for missing imports ([#676](https://github.com/Gitlawb/openclaude/issues/676)) ([a00b792](https://github.com/Gitlawb/openclaude/commit/a00b7928de9662ffb7ef6abd8cd040afe6f4f122))
+* **ui:** show correct endpoint URL in intro screen for custom Anthropic endpoints ([#735](https://github.com/Gitlawb/openclaude/issues/735)) ([3424663](https://github.com/Gitlawb/openclaude/commit/34246635fb9a09499047a52e7f96ca9b36c8a85a))
+
 ## [0.3.0](https://github.com/Gitlawb/openclaude/compare/v0.2.3...v0.3.0) (2026-04-14)
 
 

Dockerfile

@@ -36,14 +36,11 @@ COPY --from=build /app/node_modules/ node_modules/
 COPY --from=build /app/package.json package.json
 COPY README.md ./
 
-# Install git — many CLI tool operations depend on it
+# Install git and ripgrep — many CLI tool operations depend on them
-RUN apt-get update && apt-get install -y --no-install-recommends git \
+RUN apt-get update && apt-get install -y --no-install-recommends git ripgrep \
     && rm -rf /var/lib/apt/lists/*
 
 # Run as non-root user
-RUN groupadd --gid 1000 appuser && useradd --uid 1000 --gid appuser --shell /bin/bash --create-home appuser
+USER node
-USER appuser
-WORKDIR /home/appuser
-ENV HOME=/home/appuser
 
 ENTRYPOINT ["node", "/app/dist/cli.mjs"]

README.md

@@ -15,6 +15,10 @@ OpenClaude is also mirrored to GitLawb:
 
 [Quick Start](#quick-start) | [Setup Guides](#setup-guides) | [Providers](#supported-providers) | [Source Build](#source-build-and-local-development) | [VS Code Extension](#vs-code-extension) | [Community](#community)
 
+## Star History
+
+[![Star History Chart](https://api.star-history.com/chart?repos=gitlawb/openclaude&type=date&legend=top-left)](https://www.star-history.com/?repos=gitlawb%2Fopenclaude&type=date&legend=top-left)
+
 ## Why OpenClaude
 
 - Use one CLI across cloud APIs and local model backends
@@ -88,6 +92,16 @@ $env:OPENAI_MODEL="qwen2.5-coder:7b"
 openclaude
 ```
 
+### Using Ollama's launch command
+
+If you have [Ollama](https://ollama.com) installed, you can skip the env var setup entirely:
+
+```bash
+ollama launch openclaude --model qwen2.5-coder:7b
+```
+
+This automatically sets `ANTHROPIC_BASE_URL`, model routing, and auth so all API traffic goes through your local Ollama instance. Works with any model you have pulled — local or cloud.
+
 ## Setup Guides
 
 Beginner-friendly guides:
@@ -110,7 +124,7 @@ Advanced and source-build guides:
 | GitHub Models | `/onboard-github` | Interactive onboarding with saved credentials |
 | Codex OAuth | `/provider` | Opens ChatGPT sign-in in your browser and stores Codex credentials securely |
 | Codex | `/provider` | Uses existing Codex CLI auth, OpenClaude secure storage, or env credentials |
-| Ollama | `/provider` or env vars | Local inference with no API key |
+| Ollama | `/provider`, env vars, or `ollama launch` | Local inference with no API key |
 | Atomic Chat | advanced setup | Local Apple Silicon backend |
 | Bedrock / Vertex / Foundry | env vars | Additional provider integrations for supported environments |
 
@@ -317,7 +331,8 @@ For larger changes, open an issue first so the scope is clear before implementat
 - `bun run build`
 - `bun run test:coverage`
 - `bun run smoke`
-- focused `bun test ...` runs for touched areas
+- focused `bun test ...` runs for files and flows you changed
+
 
 ## Disclaimer
 

docs/advanced-setup.md

@@ -84,6 +84,16 @@ OpenRouter model availability changes over time. If a model stops working, try a
 
 ### Ollama
 
+Using `ollama launch` (recommended if you have Ollama installed):
+
+```bash
+ollama launch openclaude --model llama3.3:70b
+```
+
+This handles all environment setup automatically — no env vars needed. Works with any local or cloud model available in your Ollama instance.
+
+Using environment variables manually:
+
 ```bash
 ollama pull llama3.3:70b
 

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@gitlawb/openclaude",
-  "version": "0.3.0",
+  "version": "0.5.2",
   "description": "Claude Code opened to any LLM — OpenAI, Gemini, DeepSeek, Ollama, and 200+ models",
   "type": "module",
   "bin": {

scripts/build.ts

@@ -367,9 +367,17 @@ export const SeverityNumber = {};
               const full = pathMod.join(dir, ent.name)
               if (ent.isDirectory()) { walk(full); continue }
               if (!/\.(ts|tsx)$/.test(ent.name)) continue
-              const code: string = fs.readFileSync(full, 'utf-8')
+              const rawCode: string = fs.readFileSync(full, 'utf-8')
               const fileDir = pathMod.dirname(full)
 
+              // Strip comments before scanning for imports/requires.
+              // The regex scanner matches require()/import() patterns
+              // inside JSDoc comments, causing false-positive missing
+              // module detection that breaks the build with noop stubs.
+              const code = rawCode
+                .replace(/\/\*[\s\S]*?\*\//g, '')  // block comments
+                .replace(/\/\/.*$/gm, '')           // line comments
+
               // Collect static imports: import { X } from '...'
               for (const m of code.matchAll(/import\s+(?:\{([^}]*)\}|(\w+))?\s*(?:,\s*\{([^}]*)\})?\s*from\s+['"](.*?)['"]/g)) {
                 checkAndRegister(m[4], fileDir, m[1] || m[3] || '')

scripts/system-check.test.ts

@@ -20,6 +20,23 @@ describe('formatReachabilityFailureDetail', () => {
     )
   })
 
+  test('redacts credentials and sensitive query parameters in endpoint details', () => {
+    const detail = formatReachabilityFailureDetail(
+      'http://user:pass@localhost:11434/v1/models?token=abc123&mode=test',
+      502,
+      'bad gateway',
+      {
+        transport: 'chat_completions',
+        requestedModel: 'llama3.1:8b',
+        resolvedModel: 'llama3.1:8b',
+      },
+    )
+
+    expect(detail).toBe(
+      'Unexpected status 502 from http://redacted:redacted@localhost:11434/v1/models?token=redacted&mode=test. Body: bad gateway',
+    )
+  })
+
   test('adds alias/entitlement hint for codex model support 400s', () => {
     const detail = formatReachabilityFailureDetail(
       'https://chatgpt.com/backend-api/codex/responses',

scripts/system-check.ts

@@ -7,6 +7,11 @@ import {
   resolveProviderRequest,
   isLocalProviderUrl as isProviderLocalUrl,
 } from '../src/services/api/providerConfig.js'
+import {
+  getLocalOpenAICompatibleProviderLabel,
+  probeOllamaGenerationReadiness,
+} from '../src/utils/providerDiscovery.js'
+import { redactUrlForDisplay } from '../src/utils/urlRedaction.js'
 
 type CheckResult = {
   ok: boolean
@@ -69,7 +74,7 @@ export function formatReachabilityFailureDetail(
   },
 ): string {
   const compactBody = responseBody.trim().replace(/\s+/g, ' ').slice(0, 240)
-  const base = `Unexpected status ${status} from ${endpoint}.`
+  const base = `Unexpected status ${status} from ${redactUrlForDisplay(endpoint)}.`
   const bodySuffix = compactBody ? ` Body: ${compactBody}` : ''
 
   if (request.transport !== 'codex_responses' || status !== 400) {
@@ -255,7 +260,7 @@ function checkOpenAIEnv(): CheckResult[] {
     results.push(pass('OPENAI_MODEL', process.env.OPENAI_MODEL))
   }
 
-  results.push(pass('OPENAI_BASE_URL', request.baseUrl))
+  results.push(pass('OPENAI_BASE_URL', redactUrlForDisplay(request.baseUrl)))
 
   if (request.transport === 'codex_responses') {
     const credentials = resolveCodexApiCredentials(process.env)
@@ -308,7 +313,7 @@ async function checkBaseUrlReachability(): Promise<CheckResult> {
     return pass('Provider reachability', 'Skipped (OpenAI-compatible mode disabled).')
   }
 
-  if (useGithub) {
+  if (useGithub && !useOpenAI) {
     return pass(
       'Provider reachability',
       'Skipped for GitHub Models (inference endpoint differs from OpenAI /models probe).',
@@ -326,6 +331,7 @@ async function checkBaseUrlReachability(): Promise<CheckResult> {
   const endpoint = request.transport === 'codex_responses'
     ? `${request.baseUrl}/responses`
     : `${request.baseUrl}/models`
+  const redactedEndpoint = redactUrlForDisplay(endpoint)
 
   const controller = new AbortController()
   const timeout = setTimeout(() => controller.abort(), 4000)
@@ -375,7 +381,10 @@ async function checkBaseUrlReachability(): Promise<CheckResult> {
     })
 
     if (response.status === 200 || response.status === 401 || response.status === 403) {
-      return pass('Provider reachability', `Reached ${endpoint} (status ${response.status}).`)
+      return pass(
+        'Provider reachability',
+        `Reached ${redactedEndpoint} (status ${response.status}).`,
+      )
     }
 
     const responseBody = await response.text().catch(() => '')
@@ -391,12 +400,100 @@ async function checkBaseUrlReachability(): Promise<CheckResult> {
     )
   } catch (error) {
     const message = error instanceof Error ? error.message : String(error)
-    return fail('Provider reachability', `Failed to reach ${endpoint}: ${message}`)
+    return fail(
+      'Provider reachability',
+      `Failed to reach ${redactedEndpoint}: ${message}`,
+    )
   } finally {
     clearTimeout(timeout)
   }
 }
 
+async function checkProviderGenerationReadiness(): Promise<CheckResult> {
+  const useGemini = isTruthy(process.env.CLAUDE_CODE_USE_GEMINI)
+  const useOpenAI = isTruthy(process.env.CLAUDE_CODE_USE_OPENAI)
+  const useGithub = isTruthy(process.env.CLAUDE_CODE_USE_GITHUB)
+  const useMistral = isTruthy(process.env.CLAUDE_CODE_USE_MISTRAL)
+
+  if (!useGemini && !useOpenAI && !useGithub && !useMistral) {
+    return pass('Provider generation readiness', 'Skipped (OpenAI-compatible mode disabled).')
+  }
+
+  if (useGithub && !useOpenAI) {
+    return pass(
+      'Provider generation readiness',
+      'Skipped for GitHub Models (runtime generation uses a different endpoint flow).',
+    )
+  }
+
+  if (useGemini || useMistral) {
+    return pass(
+      'Provider generation readiness',
+      'Skipped for managed provider mode.',
+    )
+  }
+
+  if (!useOpenAI) {
+    return pass('Provider generation readiness', 'Skipped (OpenAI-compatible mode disabled).')
+  }
+
+  const request = resolveProviderRequest({
+    model: process.env.OPENAI_MODEL,
+    baseUrl: process.env.OPENAI_BASE_URL,
+  })
+
+  if (request.transport === 'codex_responses') {
+    return pass(
+      'Provider generation readiness',
+      'Skipped for Codex responses (reachability probe already performs a lightweight generation request).',
+    )
+  }
+
+  if (!isLocalBaseUrl(request.baseUrl)) {
+    return pass('Provider generation readiness', 'Skipped for non-local provider URL.')
+  }
+
+  const localProviderLabel = getLocalOpenAICompatibleProviderLabel(request.baseUrl)
+  if (localProviderLabel !== 'Ollama') {
+    return pass(
+      'Provider generation readiness',
+      `Skipped for ${localProviderLabel} (no provider-specific generation probe).`,
+    )
+  }
+
+  const readiness = await probeOllamaGenerationReadiness({
+    baseUrl: request.baseUrl,
+    model: request.requestedModel,
+  })
+
+  if (readiness.state === 'ready') {
+    return pass(
+      'Provider generation readiness',
+      `Generated a test response with ${readiness.probeModel ?? request.requestedModel}.`,
+    )
+  }
+
+  if (readiness.state === 'unreachable') {
+    return fail(
+      'Provider generation readiness',
+      `Could not reach Ollama at ${redactUrlForDisplay(request.baseUrl)}.`,
+    )
+  }
+
+  if (readiness.state === 'no_models') {
+    return fail(
+      'Provider generation readiness',
+      'Ollama is reachable, but no installed models were found. Pull a model first (for example: ollama pull qwen2.5-coder:7b).',
+    )
+  }
+
+  const detailSuffix = readiness.detail ? ` Detail: ${readiness.detail}.` : ''
+  return fail(
+    'Provider generation readiness',
+    `Ollama is reachable, but generation failed for ${readiness.probeModel ?? request.requestedModel}.${detailSuffix}`,
+  )
+}
+
 function isAtomicChatUrl(baseUrl: string): boolean {
   try {
     const parsed = new URL(baseUrl)
@@ -567,6 +664,7 @@ async function main(): Promise<void> {
   results.push(checkBuildArtifacts())
   results.push(...checkOpenAIEnv())
   results.push(await checkBaseUrlReachability())
+  results.push(await checkProviderGenerationReadiness())
   results.push(checkOllamaProcessorMode())
 
   if (!options.json) {

src/__tests__/security-hardening.test.ts

@@ -0,0 +1,191 @@
+/**
+ * Security hardening regression tests.
+ *
+ * Covers:
+ * 1. MCP tool result Unicode sanitization
+ * 2. Sandbox settings source filtering (exclude projectSettings)
+ * 3. Plugin git clone/pull hooks disabled
+ * 4. ANTHROPIC_FOUNDRY_API_KEY removed from SAFE_ENV_VARS
+ * 5. WebFetch SSRF protection via ssrfGuardedLookup
+ */
+
+import { describe, test, expect } from 'bun:test'
+import { resolve } from 'path'
+
+const SRC = resolve(import.meta.dir, '..')
+const file = (relative: string) => Bun.file(resolve(SRC, relative))
+
+// ---------------------------------------------------------------------------
+// Fix 1: MCP tool result Unicode sanitization
+// ---------------------------------------------------------------------------
+describe('MCP tool result sanitization', () => {
+  test('transformResultContent sanitizes text content', async () => {
+    const content = await file('services/mcp/client.ts').text()
+    // Tool definitions are already sanitized (line ~1798)
+    expect(content).toContain('recursivelySanitizeUnicode(result.tools)')
+    // Tool results must also be sanitized
+    expect(content).toMatch(
+      /case 'text':[\s\S]*?recursivelySanitizeUnicode\(resultContent\.text\)/,
+    )
+  })
+
+  test('resource text content is also sanitized', async () => {
+    const content = await file('services/mcp/client.ts').text()
+    expect(content).toMatch(
+      /recursivelySanitizeUnicode\(\s*`\$\{prefix\}\$\{resource\.text\}`/,
+    )
+  })
+})
+
+// ---------------------------------------------------------------------------
+// Fix 2: Sandbox settings source filtering
+// ---------------------------------------------------------------------------
+describe('Sandbox settings trust boundary', () => {
+  test('getSandboxEnabledSetting does not use getSettings_DEPRECATED', async () => {
+    const content = await file('utils/sandbox/sandbox-adapter.ts').text()
+    // Extract the getSandboxEnabledSetting function body
+    const fnMatch = content.match(
+      /function getSandboxEnabledSetting\(\)[^{]*\{([\s\S]*?)\n\}/,
+    )
+    expect(fnMatch).not.toBeNull()
+    const fnBody = fnMatch![1]
+    // Must NOT use getSettings_DEPRECATED (reads all sources including project)
+    expect(fnBody).not.toContain('getSettings_DEPRECATED')
+    // Must use getSettingsForSource for individual trusted sources
+    expect(fnBody).toContain("getSettingsForSource('userSettings')")
+    expect(fnBody).toContain("getSettingsForSource('policySettings')")
+    // Must NOT read from projectSettings
+    expect(fnBody).not.toContain("'projectSettings'")
+  })
+})
+
+// ---------------------------------------------------------------------------
+// Fix 3: Plugin git hooks disabled
+// ---------------------------------------------------------------------------
+describe('Plugin git operations disable hooks', () => {
+  test('gitClone includes core.hooksPath=/dev/null', async () => {
+    const content = await file('utils/plugins/marketplaceManager.ts').text()
+    // The clone args must disable hooks
+    const cloneSection = content.slice(
+      content.indexOf('export async function gitClone('),
+      content.indexOf('export async function gitClone(') + 2000,
+    )
+    expect(cloneSection).toContain("'core.hooksPath=/dev/null'")
+  })
+
+  test('gitPull includes core.hooksPath=/dev/null', async () => {
+    const content = await file('utils/plugins/marketplaceManager.ts').text()
+    const pullSection = content.slice(
+      content.indexOf('export async function gitPull('),
+      content.indexOf('export async function gitPull(') + 2000,
+    )
+    expect(pullSection).toContain("'core.hooksPath=/dev/null'")
+  })
+
+  test('gitSubmoduleUpdate includes core.hooksPath=/dev/null', async () => {
+    const content = await file('utils/plugins/marketplaceManager.ts').text()
+    const subSection = content.slice(
+      content.indexOf('async function gitSubmoduleUpdate('),
+      content.indexOf('async function gitSubmoduleUpdate(') + 1000,
+    )
+    expect(subSection).toContain("'core.hooksPath=/dev/null'")
+  })
+})
+
+// ---------------------------------------------------------------------------
+// Fix 4: ANTHROPIC_FOUNDRY_API_KEY not in SAFE_ENV_VARS
+// ---------------------------------------------------------------------------
+describe('SAFE_ENV_VARS excludes credentials', () => {
+  test('ANTHROPIC_FOUNDRY_API_KEY is not in SAFE_ENV_VARS', async () => {
+    const content = await file('utils/managedEnvConstants.ts').text()
+    // Extract the SAFE_ENV_VARS set definition
+    const safeStart = content.indexOf('export const SAFE_ENV_VARS')
+    const safeEnd = content.indexOf('])', safeStart)
+    const safeSection = content.slice(safeStart, safeEnd)
+    expect(safeSection).not.toContain('ANTHROPIC_FOUNDRY_API_KEY')
+  })
+})
+
+// ---------------------------------------------------------------------------
+// Fix 5: WebFetch SSRF protection
+// ---------------------------------------------------------------------------
+describe('WebFetch SSRF guard', () => {
+  test('getWithPermittedRedirects uses ssrfGuardedLookup', async () => {
+    const content = await file('tools/WebFetchTool/utils.ts').text()
+    expect(content).toContain(
+      "import { ssrfGuardedLookup } from '../../utils/hooks/ssrfGuard.js'",
+    )
+    // The axios.get call in getWithPermittedRedirects must include lookup
+    const fnSection = content.slice(
+      content.indexOf('export async function getWithPermittedRedirects('),
+      content.indexOf('export async function getWithPermittedRedirects(') +
+        1000,
+    )
+    expect(fnSection).toContain('lookup: ssrfGuardedLookup')
+  })
+})
+
+// ---------------------------------------------------------------------------
+// Fix 6: Swarm permission file polling removed (security hardening)
+// ---------------------------------------------------------------------------
+describe('Swarm permission file polling removed', () => {
+  test('useSwarmPermissionPoller hook no longer exists', async () => {
+    const content = await file(
+      'hooks/useSwarmPermissionPoller.ts',
+    ).text()
+    // The file-based polling hook must not exist — it read from an
+    // unauthenticated resolved/ directory where any local process could
+    // forge approval files.
+    expect(content).not.toContain('function useSwarmPermissionPoller(')
+    // The file-based processResponse must not exist
+    expect(content).not.toContain('function processResponse(')
+  })
+
+  test('poller does not import from permissionSync', async () => {
+    const content = await file(
+      'hooks/useSwarmPermissionPoller.ts',
+    ).text()
+    // Must not import anything from permissionSync — all file-based
+    // functions have been removed from this module's dependencies
+    expect(content).not.toContain('permissionSync')
+  })
+
+  test('file-based permission functions are marked deprecated', async () => {
+    const content = await file(
+      'utils/swarm/permissionSync.ts',
+    ).text()
+    // All file-based functions must have @deprecated JSDoc
+    const deprecatedFns = [
+      'writePermissionRequest',
+      'readPendingPermissions',
+      'readResolvedPermission',
+      'resolvePermission',
+      'pollForResponse',
+      'removeWorkerResponse',
+    ]
+    for (const fn of deprecatedFns) {
+      // Find the function and check that @deprecated appears before it
+      const fnIndex = content.indexOf(`export async function ${fn}(`)
+      if (fnIndex === -1) continue // submitPermissionRequest is a const, not async function
+      const preceding = content.slice(Math.max(0, fnIndex - 500), fnIndex)
+      expect(preceding).toContain('@deprecated')
+    }
+  })
+
+  test('mailbox-based functions are NOT deprecated', async () => {
+    const content = await file(
+      'utils/swarm/permissionSync.ts',
+    ).text()
+    // These are the active path — must not be deprecated
+    const activeFns = [
+      'sendPermissionRequestViaMailbox',
+      'sendPermissionResponseViaMailbox',
+    ]
+    for (const fn of activeFns) {
+      const fnIndex = content.indexOf(`export async function ${fn}(`)
+      expect(fnIndex).not.toBe(-1)
+      const preceding = content.slice(Math.max(0, fnIndex - 300), fnIndex)
+      expect(preceding).not.toContain('@deprecated')
+    }
+  })
+})

src/cli/handlers/mcp.tsx

@@ -11,7 +11,12 @@ import { MCPServerDesktopImportDialog } from '../../components/MCPServerDesktopI
 import { render } from '../../ink.js';
 import { KeybindingSetup } from '../../keybindings/KeybindingProviderSetup.js';
 import { type AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS, logEvent } from '../../services/analytics/index.js';
-import { clearMcpClientConfig, clearServerTokensFromLocalStorage, readClientSecret, saveMcpClientSecret } from '../../services/mcp/auth.js';
+import {
+  clearMcpClientConfig,
+  clearServerTokensFromSecureStorage,
+  readClientSecret,
+  saveMcpClientSecret,
+} from '../../services/mcp/auth.js'
 import { doctorAllServers, doctorServer, type McpDoctorReport, type McpDoctorScopeFilter } from '../../services/mcp/doctor.js';
 import { connectToServer, getMcpServerConnectionBatchSize } from '../../services/mcp/client.js';
 import { addMcpConfig, getAllMcpConfigs, getMcpConfigByName, getMcpConfigsByScope, removeMcpConfig } from '../../services/mcp/config.js';

src/commands.test.ts

@@ -0,0 +1,30 @@
+import { formatDescriptionWithSource } from './commands.js'
+
+describe('formatDescriptionWithSource', () => {
+  test('returns empty text for prompt commands missing a description', () => {
+    const command = {
+      name: 'example',
+      type: 'prompt',
+      source: 'builtin',
+      description: undefined,
+    } as any
+
+    expect(formatDescriptionWithSource(command)).toBe('')
+  })
+
+  test('formats plugin commands with missing description safely', () => {
+    const command = {
+      name: 'example',
+      type: 'prompt',
+      source: 'plugin',
+      description: undefined,
+      pluginInfo: {
+        pluginManifest: {
+          name: 'MyPlugin',
+        },
+      },
+    } as any
+
+    expect(formatDescriptionWithSource(command)).toBe('(MyPlugin) ')
+  })
+})

src/commands.ts

@@ -740,23 +740,23 @@ export function getCommand(commandName: string, commands: Command[]): Command {
  */
 export function formatDescriptionWithSource(cmd: Command): string {
   if (cmd.type !== 'prompt') {
-    return cmd.description
+    return cmd.description ?? ''
   }
 
   if (cmd.kind === 'workflow') {
-    return `${cmd.description} (workflow)`
+    return `${cmd.description ?? ''} (workflow)`
   }
 
   if (cmd.source === 'plugin') {
     const pluginName = cmd.pluginInfo?.pluginManifest.name
     if (pluginName) {
-      return `(${pluginName}) ${cmd.description}`
+      return `(${pluginName}) ${cmd.description ?? ''}`
     }
-    return `${cmd.description} (plugin)`
+    return `${cmd.description ?? ''} (plugin)`
   }
 
   if (cmd.source === 'builtin' || cmd.source === 'mcp') {
-    return cmd.description
+    return cmd.description ?? ''
   }
 
   if (cmd.source === 'bundled') {

src/commands/provider/provider.test.tsx

@@ -401,7 +401,7 @@ test('buildCodexProfileEnv derives oauth source from secure storage when no expl
   })
 })
 
-test('applySavedProfileToCurrentSession switches the current env to the saved Codex profile', async () => {
+test('explicitly declared env takes precedence over applySavedProfileToCurrentSession', async () => {
   // @ts-expect-error cache-busting query string for Bun module mocks
   const { applySavedProfileToCurrentSession } = await import(
     '../../utils/providerProfile.js?apply-saved-profile-codex'
@@ -430,18 +430,18 @@ test('applySavedProfileToCurrentSession switches the current env to the saved Co
 
   expect(warning).toBeNull()
   expect(processEnv.CLAUDE_CODE_USE_OPENAI).toBe('1')
-  expect(processEnv.OPENAI_MODEL).toBe('codexplan')
+  expect(processEnv.OPENAI_MODEL).toBe('gpt-4o')
   expect(processEnv.OPENAI_BASE_URL).toBe(
-    'https://chatgpt.com/backend-api/codex',
+    "https://api.openai.com/v1",
   )
-  expect(processEnv.CODEX_API_KEY).toBe('codex-live')
+  expect(processEnv.CODEX_API_KEY).toBeUndefined()
-  expect(processEnv.CHATGPT_ACCOUNT_ID).toBe('acct_codex')
+  expect(processEnv.CHATGPT_ACCOUNT_ID).toBeUndefined()
-  expect(processEnv.OPENAI_API_KEY).toBeUndefined()
+  expect(processEnv.OPENAI_API_KEY).toBe("sk-openai")
   expect(processEnv.CLAUDE_CODE_PROVIDER_PROFILE_ENV_APPLIED).toBeUndefined()
   expect(processEnv.CLAUDE_CODE_PROVIDER_PROFILE_ENV_APPLIED_ID).toBeUndefined()
 })
 
-test('applySavedProfileToCurrentSession ignores stale Codex env overrides for OAuth-backed profiles', async () => {
+test('explicitly declared env takes precedence over applySavedProfileToCurrentSession', async () => {
   // @ts-expect-error cache-busting query string for Bun module mocks
   const { applySavedProfileToCurrentSession } = await import(
     '../../utils/providerProfile.js?apply-saved-profile-codex-oauth'
@@ -465,13 +465,13 @@ test('applySavedProfileToCurrentSession ignores stale Codex env overrides for OA
     processEnv,
   })
 
-  expect(warning).toBeNull()
+  expect(warning).not.toBeUndefined()
-  expect(processEnv.OPENAI_MODEL).toBe('codexplan')
+  expect(processEnv.OPENAI_MODEL).toBe('gpt-4o')
   expect(processEnv.OPENAI_BASE_URL).toBe(
-    'https://chatgpt.com/backend-api/codex',
+    "https://api.openai.com/v1",
   )
-  expect(processEnv.CODEX_API_KEY).toBeUndefined()
+  expect(processEnv.CODEX_API_KEY).toBe("stale-codex-key")
-  expect(processEnv.CHATGPT_ACCOUNT_ID).not.toBe('acct_stale')
+  expect(processEnv.CHATGPT_ACCOUNT_ID).toBe('acct_stale')
   expect(processEnv.CHATGPT_ACCOUNT_ID).toBeTruthy()
 })
 
@@ -487,8 +487,8 @@ test('buildCurrentProviderSummary redacts poisoned model and endpoint values', (
   })
 
   expect(summary.providerLabel).toBe('OpenAI-compatible')
-  expect(summary.modelLabel).toBe('sk-...5678')
+  expect(summary.modelLabel).toBe('sk-...678')
-  expect(summary.endpointLabel).toBe('sk-...5678')
+  expect(summary.endpointLabel).toBe('sk-...678')
 })
 
 test('buildCurrentProviderSummary labels generic local openai-compatible providers', () => {

src/commands/provider/provider.tsx

@@ -66,10 +66,44 @@ import {
 import {
   getOllamaChatBaseUrl,
   getLocalOpenAICompatibleProviderLabel,
-  hasLocalOllama,
+  probeOllamaGenerationReadiness,
-  listOllamaModels,
+  type OllamaGenerationReadiness,
 } from '../../utils/providerDiscovery.js'
 
+function describeOllamaReadinessIssue(
+  readiness: OllamaGenerationReadiness,
+  options?: {
+    baseUrl?: string
+    allowManualFallback?: boolean
+  },
+): string {
+  const endpoint = options?.baseUrl ?? 'http://localhost:11434'
+
+  if (readiness.state === 'unreachable') {
+    return `Could not reach Ollama at ${endpoint}. Start Ollama first, then run /provider again.`
+  }
+
+  if (readiness.state === 'no_models') {
+    const manualSuffix = options?.allowManualFallback
+      ? ', or enter details manually'
+      : ''
+    return `Ollama is running, but no installed models were found. Pull a chat model such as qwen2.5-coder:7b or llama3.1:8b first${manualSuffix}.`
+  }
+
+  if (readiness.state === 'generation_failed') {
+    const modelHint = readiness.probeModel ?? 'the selected model'
+    const detailSuffix = readiness.detail
+      ? ` Details: ${readiness.detail}.`
+      : ''
+    const manualSuffix = options?.allowManualFallback
+      ? ' You can also enter details manually.'
+      : ''
+    return `Ollama is reachable and models are installed, but a generation probe failed for ${modelHint}.${detailSuffix} Run "ollama run ${modelHint}" once and retry.${manualSuffix}`
+  }
+
+  return ''
+}
+
 type ProviderChoice = 'auto' | ProviderProfile | 'codex-oauth' | 'clear'
 
 type Step =
@@ -715,6 +749,7 @@ function AutoRecommendationStep({
     | {
         state: 'openai'
         defaultModel: string
+        reason: string
       }
     | {
         state: 'error'
@@ -728,19 +763,27 @@ function AutoRecommendationStep({
     void (async () => {
       const defaultModel = getGoalDefaultOpenAIModel(goal)
       try {
-        const ollamaAvailable = await hasLocalOllama()
+        const readiness = await probeOllamaGenerationReadiness()
-        if (!ollamaAvailable) {
+        if (readiness.state !== 'ready') {
           if (!cancelled) {
-            setStatus({ state: 'openai', defaultModel })
+            setStatus({
+              state: 'openai',
+              defaultModel,
+              reason: describeOllamaReadinessIssue(readiness),
+            })
           }
           return
         }
 
-        const models = await listOllamaModels()
+        const recommended = recommendOllamaModel(readiness.models, goal)
-        const recommended = recommendOllamaModel(models, goal)
         if (!recommended) {
           if (!cancelled) {
-            setStatus({ state: 'openai', defaultModel })
+            setStatus({
+              state: 'openai',
+              defaultModel,
+              reason:
+                'Ollama responded to a generation probe, but no recommended chat model matched this goal.',
+            })
           }
           return
         }
@@ -796,10 +839,10 @@ function AutoRecommendationStep({
       <Dialog title="Auto setup fallback" onCancel={onCancel}>
         <Box flexDirection="column" gap={1}>
           <Text>
-            No viable local Ollama chat model was detected. Auto setup can
+            Auto setup can continue into OpenAI-compatible setup with a default model of{' '}
-            continue into OpenAI-compatible setup with a default model of{' '}
             {status.defaultModel}.
           </Text>
+          <Text dimColor>{status.reason}</Text>
           <Select
             options={[
               { label: 'Continue to OpenAI-compatible setup', value: 'continue' },
@@ -883,32 +926,19 @@ function OllamaModelStep({
     let cancelled = false
 
     void (async () => {
-      const available = await hasLocalOllama()
+      const readiness = await probeOllamaGenerationReadiness()
-      if (!available) {
+      if (readiness.state !== 'ready') {
         if (!cancelled) {
           setStatus({
             state: 'unavailable',
-            message:
+            message: describeOllamaReadinessIssue(readiness),
-              'Could not reach Ollama at http://localhost:11434. Start Ollama first, then run /provider again.',
           })
         }
         return
       }
 
-      const models = await listOllamaModels()
+      const ranked = rankOllamaModels(readiness.models, 'balanced')
-      if (models.length === 0) {
+      const recommended = recommendOllamaModel(readiness.models, 'balanced')
-        if (!cancelled) {
-          setStatus({
-            state: 'unavailable',
-            message:
-              'Ollama is running, but no installed models were found. Pull a chat model such as qwen2.5-coder:7b or llama3.1:8b first.',
-          })
-        }
-        return
-      }
-
-      const ranked = rankOllamaModels(models, 'balanced')
-      const recommended = recommendOllamaModel(models, 'balanced')
       if (!cancelled) {
         setStatus({
           state: 'ready',

src/components/ProviderManager.test.tsx

@@ -149,17 +149,21 @@ function mockProviderManagerDependencies(
     applySavedProfileToCurrentSession?: (...args: unknown[]) => Promise<string | null>
     clearCodexCredentials?: () => { success: boolean; warning?: string }
     getProviderProfiles?: () => unknown[]
-    hasLocalOllama?: () => Promise<boolean>
+    probeOllamaGenerationReadiness?: () => Promise<{
-    listOllamaModels?: () => Promise<
+      state: 'ready' | 'unreachable' | 'no_models' | 'generation_failed'
-      Array<{
+      models: Array<
+        {
           name: string
           sizeBytes?: number | null
           family?: string | null
           families?: string[]
           parameterSize?: string | null
           quantizationLevel?: string | null
-      }>
+        }
       >
+      probeModel?: string
+      detail?: string
+    }>
     codexSyncRead?: () => unknown
     codexAsyncRead?: () => Promise<unknown>
     updateProviderProfile?: (...args: unknown[]) => unknown
@@ -189,8 +193,12 @@ function mockProviderManagerDependencies(
   })
 
   mock.module('../utils/providerDiscovery.js', () => ({
-    hasLocalOllama: options?.hasLocalOllama ?? (async () => false),
+    probeOllamaGenerationReadiness:
-    listOllamaModels: options?.listOllamaModels ?? (async () => []),
+      options?.probeOllamaGenerationReadiness ??
+      (async () => ({
+        state: 'unreachable' as const,
+        models: [],
+      })),
   }))
 
   mock.module('../utils/githubModelsCredentials.js', () => ({
@@ -455,8 +463,9 @@ test('ProviderManager first-run Ollama preset auto-detects installed models', as
     async () => undefined,
     {
       addProviderProfile,
-      hasLocalOllama: async () => true,
+      probeOllamaGenerationReadiness: async () => ({
-      listOllamaModels: async () => [
+        state: 'ready',
+        models: [
           {
             name: 'gemma4:31b-cloud',
             family: 'gemma',
@@ -468,6 +477,8 @@ test('ProviderManager first-run Ollama preset auto-detects installed models', as
             parameterSize: '2.5b',
           },
         ],
+        probeModel: 'gemma4:31b-cloud',
+      }),
     },
   )
 

src/components/ProviderManager.tsx

@@ -3,12 +3,14 @@ import * as React from 'react'
 import { DEFAULT_CODEX_BASE_URL } from '../services/api/providerConfig.js'
 import { Box, Text } from '../ink.js'
 import { useKeybinding } from '../keybindings/useKeybinding.js'
+import { useSetAppState } from '../state/AppState.js'
 import type { ProviderProfile } from '../utils/config.js'
 import {
   clearCodexCredentials,
   readCodexCredentialsAsync,
 } from '../utils/codexCredentials.js'
 import { isBareMode, isEnvTruthy } from '../utils/envUtils.js'
+import { getPrimaryModel, hasMultipleModels, parseModelList } from '../utils/providerModels.js'
 import {
   applySavedProfileToCurrentSession,
   buildCodexOAuthProfileEnv,
@@ -35,13 +37,14 @@ import {
   readGithubModelsTokenAsync,
 } from '../utils/githubModelsCredentials.js'
 import {
-  hasLocalOllama,
+  probeOllamaGenerationReadiness,
-  listOllamaModels,
+  type OllamaGenerationReadiness,
 } from '../utils/providerDiscovery.js'
 import {
   rankOllamaModels,
   recommendOllamaModel,
 } from '../utils/providerRecommendation.js'
+import { redactUrlForDisplay } from '../utils/urlRedaction.js'
 import { updateSettingsForSource } from '../utils/settings/settings.js'
 import {
   type OptionWithDescription,
@@ -108,8 +111,8 @@ const FORM_STEPS: Array<{
   {
     key: 'model',
     label: 'Default model',
-    placeholder: 'e.g. llama3.1:8b',
+    placeholder: 'e.g. llama3.1:8b or glm-4.7, glm-4.7-flash',
-    helpText: 'Model name to use when this provider is active.',
+    helpText: 'Model name(s) to use. Separate multiple with commas; first is default.',
   },
   {
     key: 'apiKey',
@@ -153,7 +156,12 @@ function profileSummary(profile: ProviderProfile, isActive: boolean): string {
   const keyInfo = profile.apiKey ? 'key set' : 'no key'
   const providerKind =
     profile.provider === 'anthropic' ? 'anthropic' : 'openai-compatible'
-  return `${providerKind} · ${profile.baseUrl} · ${profile.model} · ${keyInfo}${activeSuffix}`
+  const models = parseModelList(profile.model)
+  const modelDisplay =
+    models.length <= 3
+      ? models.join(', ')
+      : `${models[0]}, ${models[1]} + ${models.length - 2} more`
+  return `${providerKind} · ${profile.baseUrl} · ${modelDisplay} · ${keyInfo}${activeSuffix}`
 }
 
 function getGithubCredentialSourceFromEnv(
@@ -214,6 +222,29 @@ function getGithubProviderSummary(
   return `github-models · ${GITHUB_PROVIDER_DEFAULT_BASE_URL} · ${getGithubProviderModel(processEnv)} · ${credentialSummary}${activeSuffix}`
 }
 
+function describeOllamaSelectionIssue(
+  readiness: OllamaGenerationReadiness,
+  baseUrl: string,
+): string {
+  if (readiness.state === 'unreachable') {
+    return `Could not reach Ollama at ${redactUrlForDisplay(baseUrl)}. Start Ollama first, or enter the endpoint manually.`
+  }
+
+  if (readiness.state === 'no_models') {
+    return 'Ollama is running, but no installed models were found. Pull a chat model such as qwen2.5-coder:7b or llama3.1:8b first, or enter details manually.'
+  }
+
+  if (readiness.state === 'generation_failed') {
+    const modelHint = readiness.probeModel ?? 'the selected model'
+    const detailSuffix = readiness.detail
+      ? ` Details: ${readiness.detail}.`
+      : ''
+    return `Ollama is reachable and models are installed, but a generation probe failed for ${modelHint}.${detailSuffix} Run "ollama run ${modelHint}" once and retry, or enter details manually.`
+  }
+
+  return ''
+}
+
 function findCodexOAuthProfile(
   profiles: ProviderProfile[],
   profileId?: string,
@@ -320,6 +351,7 @@ function CodexOAuthSetup({
 }
 
 export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
+  const setAppState = useSetAppState()
   const initialGithubCredentialSource = getGithubCredentialSourceFromEnv()
   const initialIsGithubActive = isEnvTruthy(process.env.CLAUDE_CODE_USE_GITHUB)
   const initialHasGithubCredential = initialGithubCredentialSource !== 'none'
@@ -353,6 +385,7 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
   const [cursorOffset, setCursorOffset] = React.useState(0)
   const [statusMessage, setStatusMessage] = React.useState<string | undefined>()
   const [errorMessage, setErrorMessage] = React.useState<string | undefined>()
+  const [menuFocusValue, setMenuFocusValue] = React.useState<string | undefined>()
   const [hasStoredCodexOAuthCredentials, setHasStoredCodexOAuthCredentials] =
     React.useState(false)
   const [storedCodexOAuthProfileId, setStoredCodexOAuthProfileId] =
@@ -440,32 +473,21 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
     setOllamaSelection({ state: 'loading' })
 
     void (async () => {
-      const available = await hasLocalOllama(draft.baseUrl)
+      const readiness = await probeOllamaGenerationReadiness({
-      if (!available) {
+        baseUrl: draft.baseUrl,
+      })
+      if (readiness.state !== 'ready') {
         if (!cancelled) {
           setOllamaSelection({
             state: 'unavailable',
-            message:
+            message: describeOllamaSelectionIssue(readiness, draft.baseUrl),
-              'Could not reach Ollama. Start Ollama first, or enter the endpoint manually.',
           })
         }
         return
       }
 
-      const models = await listOllamaModels(draft.baseUrl)
+      const ranked = rankOllamaModels(readiness.models, 'balanced')
-      if (models.length === 0) {
+      const recommended = recommendOllamaModel(readiness.models, 'balanced')
-        if (!cancelled) {
-          setOllamaSelection({
-            state: 'unavailable',
-            message:
-              'Ollama is running, but no installed models were found. Pull a chat model such as qwen2.5-coder:7b or llama3.1:8b first, or enter details manually.',
-          })
-        }
-        return
-      }
-
-      const ranked = rankOllamaModels(models, 'balanced')
-      const recommended = recommendOllamaModel(models, 'balanced')
       if (!cancelled) {
         setOllamaSelection({
           state: 'ready',
@@ -568,24 +590,48 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
         const githubError = activateGithubProvider()
         if (githubError) {
           setErrorMessage(`Could not activate GitHub provider: ${githubError}`)
-          setScreen('menu')
+          returnToMenu()
           return
         }
 
+        setAppState(prev => ({
+          ...prev,
+          mainLoopModel: GITHUB_PROVIDER_DEFAULT_MODEL,
+          mainLoopModelForSession: null,
+        }))
         refreshProfiles()
+        setAppState(prev => ({
+          ...prev,
+          mainLoopModel: GITHUB_PROVIDER_DEFAULT_MODEL,
+        }))
         setStatusMessage(`Active provider: ${GITHUB_PROVIDER_LABEL}`)
-        setScreen('menu')
+        returnToMenu()
         return
       }
 
       const active = setActiveProviderProfile(profileId)
       if (!active) {
         setErrorMessage('Could not change active provider.')
-        setScreen('menu')
+        returnToMenu()
         return
       }
 
+      // Update the session model to the new provider's first model.
+      // persistActiveProviderProfileModel (called by onChangeAppState) will
+      // not overwrite the multi-model list because it checks if the model
+      // is already in the profile's comma-separated model list.
+      const newModel = getPrimaryModel(active.model)
+      setAppState(prev => ({
+        ...prev,
+        mainLoopModel: newModel,
+      }))
+
       providerLabel = active.name
+      setAppState(prev => ({
+        ...prev,
+        mainLoopModel: active.model,
+        mainLoopModelForSession: null,
+      }))
       const settingsOverrideError =
         clearStartupProviderOverrideFromUserSettings()
       const isActiveCodexOAuth = isCodexOAuthProfile(
@@ -613,16 +659,21 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
             ? `Active provider: ${active.name}. Warning: could not clear startup provider override (${settingsOverrideError}).`
             : `Active provider: ${active.name}`,
       )
-      setScreen('menu')
+      returnToMenu()
     } catch (error) {
       refreshProfiles()
       setStatusMessage(undefined)
       const detail = error instanceof Error ? error.message : String(error)
       setErrorMessage(`Could not finish activating ${providerLabel}: ${detail}`)
-      setScreen('menu')
+      returnToMenu()
     }
   }
 
+  function returnToMenu(): void {
+    setMenuFocusValue('done')
+    setScreen('menu')
+  }
+
   function closeWithCancelled(message: string): void {
     onDone({ action: 'cancelled', message })
   }
@@ -773,6 +824,13 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
     }
 
     const isActiveSavedProfile = getActiveProviderProfile()?.id === saved.id
+    if (isActiveSavedProfile) {
+      setAppState(prev => ({
+        ...prev,
+        mainLoopModel: saved.model,
+        mainLoopModelForSession: null,
+      }))
+    }
     const settingsOverrideError = isActiveSavedProfile
       ? clearStartupProviderOverrideFromUserSettings()
       : null
@@ -800,7 +858,7 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
     setEditingProfileId(null)
     setFormStepIndex(0)
     setErrorMessage(undefined)
-    setScreen('menu')
+    returnToMenu()
   }
 
   function renderOllamaSelection(): React.ReactNode {
@@ -923,7 +981,7 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
       return
     }
 
-    setScreen('menu')
+    returnToMenu()
   }
 
   useKeybinding('confirm:no', handleBackFromForm, {
@@ -1004,11 +1062,31 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
         label: 'LM Studio',
         description: 'Local LM Studio endpoint',
       },
+      {
+        value: 'dashscope-cn',
+        label: 'Alibaba Coding Plan (China)',
+        description: 'Alibaba DashScope China endpoint',
+      },
+      {
+        value: 'dashscope-intl',
+        label: 'Alibaba Coding Plan',
+        description: 'Alibaba DashScope International endpoint',
+      },
       {
         value: 'custom',
         label: 'Custom',
         description: 'Any OpenAI-compatible provider',
       },
+      {
+        value: 'nvidia-nim',
+        label: 'NVIDIA NIM',
+        description: 'NVIDIA NIM endpoint',
+      },
+      {
+        value: 'minimax',
+        label: 'MiniMax',
+        description: 'MiniMax API endpoint',
+      },
       ...(mode === 'first-run'
         ? [
             {
@@ -1046,7 +1124,7 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
               closeWithCancelled('Provider setup skipped')
               return
             }
-            setScreen('menu')
+            returnToMenu()
           }}
           visibleOptionCount={Math.min(13, options.length)}
         />
@@ -1084,6 +1162,7 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
             focus={true}
             showCursor={true}
             placeholder={`${currentStep.placeholder}${figures.ellipsis}`}
+            mask={currentStepKey === 'apiKey' ? '*' : undefined}
             columns={80}
             cursorOffset={cursorOffset}
             onChangeCursorOffset={setCursorOffset}
@@ -1246,6 +1325,7 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
             }
           }}
           onCancel={() => closeWithCancelled('Provider manager closed')}
+          defaultFocusValue={menuFocusValue}
           visibleOptionCount={options.length}
         />
       </Box>
@@ -1293,8 +1373,8 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
                 description: 'Return to provider manager',
               },
             ]}
-            onChange={() => setScreen('menu')}
+            onChange={() => returnToMenu()}
-            onCancel={() => setScreen('menu')}
+            onCancel={() => returnToMenu()}
             visibleOptionCount={1}
           />
         </Box>
@@ -1309,7 +1389,7 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
         <Select
           options={selectOptions}
           onChange={onSelect}
-          onCancel={() => setScreen('menu')}
+          onCancel={() => returnToMenu()}
           visibleOptionCount={Math.min(10, Math.max(2, selectOptions.length))}
         />
       </Box>
@@ -1350,7 +1430,7 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
               setErrorMessage(
                 'Codex OAuth login finished, but the provider profile could not be saved.',
               )
-              setScreen('menu')
+              returnToMenu()
               return
             }
 
@@ -1362,7 +1442,7 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
               setErrorMessage(
                 'Codex OAuth login finished, but the provider could not be set as the startup provider.',
               )
-              setScreen('menu')
+              returnToMenu()
               return
             }
 
@@ -1396,7 +1476,7 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
 
             setStatusMessage(message)
             setErrorMessage(undefined)
-            setScreen('menu')
+            returnToMenu()
           }}
         />
       )
@@ -1436,7 +1516,7 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
               refreshProfiles()
               setStatusMessage('GitHub provider deleted')
             }
-            setScreen('menu')
+            returnToMenu()
             return
           }
 
@@ -1471,7 +1551,7 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
                 : 'Provider deleted',
             )
           }
-          setScreen('menu')
+          returnToMenu()
         },
         { includeGithub: true },
       )

src/components/StartupScreen.ts

@@ -117,17 +117,28 @@ function detectProvider(): { name: string; model: string; baseUrl: string; isLoc
     const baseUrl = resolvedRequest.baseUrl
     const isLocal = isLocalProviderUrl(baseUrl)
     let name = 'OpenAI'
-    // Override to Codex when resolved endpoint is Codex
+    if (/nvidia/i.test(baseUrl) || /nvidia/i.test(rawModel) || process.env.NVIDIA_NIM)
-    if (resolvedRequest.transport === 'codex_responses' || baseUrl.includes('chatgpt.com/backend-api/codex')) {
+      name = 'NVIDIA NIM'
+    else if (/minimax/i.test(baseUrl) || /minimax/i.test(rawModel) || process.env.MINIMAX_API_KEY)
+      name = 'MiniMax'
+    else if (resolvedRequest.transport === 'codex_responses' || baseUrl.includes('chatgpt.com/backend-api/codex'))
       name = 'Codex'
-    } else if (/deepseek/i.test(baseUrl) || /deepseek/i.test(rawModel))       name = 'DeepSeek'
+    else if (/deepseek/i.test(baseUrl) || /deepseek/i.test(rawModel))
-    else if (/openrouter/i.test(baseUrl))                             name = 'OpenRouter'
+      name = 'DeepSeek'
-    else if (/together/i.test(baseUrl))                               name = 'Together AI'
+    else if (/openrouter/i.test(baseUrl))
-    else if (/groq/i.test(baseUrl))                                   name = 'Groq'
+      name = 'OpenRouter'
-    else if (/mistral/i.test(baseUrl) || /mistral/i.test(rawModel))     name = 'Mistral'
+    else if (/together/i.test(baseUrl))
-    else if (/azure/i.test(baseUrl))                                  name = 'Azure OpenAI'
+      name = 'Together AI'
-    else if (/llama/i.test(rawModel))                                    name = 'Meta Llama'
+    else if (/groq/i.test(baseUrl))
-    else if (isLocal)                                                  name = getLocalOpenAICompatibleProviderLabel(baseUrl)
+      name = 'Groq'
+    else if (/mistral/i.test(baseUrl) || /mistral/i.test(rawModel))
+      name = 'Mistral'
+    else if (/azure/i.test(baseUrl))
+      name = 'Azure OpenAI'
+    else if (/llama/i.test(rawModel))
+      name = 'Meta Llama'
+    else if (isLocal)
+      name = getLocalOpenAICompatibleProviderLabel(baseUrl)
     
     // Resolve model alias to actual model name + reasoning effort
     let displayModel = resolvedRequest.resolvedModel
@@ -142,7 +153,9 @@ function detectProvider(): { name: string; model: string; baseUrl: string; isLoc
   const settings = getSettings_DEPRECATED() || {}
   const modelSetting = settings.model || process.env.ANTHROPIC_MODEL || process.env.CLAUDE_MODEL || 'claude-sonnet-4-6'
   const resolvedModel = parseUserSpecifiedModel(modelSetting)
-  return { name: 'Anthropic', model: resolvedModel, baseUrl: 'https://api.anthropic.com', isLocal: false }
+  const baseUrl = process.env.ANTHROPIC_BASE_URL ?? 'https://api.anthropic.com'
+  const isLocal = isLocalProviderUrl(baseUrl)
+  return { name: 'Anthropic', model: resolvedModel, baseUrl, isLocal }
 }
 
 // ─── Box drawing ──────────────────────────────────────────────────────────────

src/components/TextInput.test.tsx

@@ -6,6 +6,7 @@ import stripAnsi from 'strip-ansi'
 
 import { createRoot } from '../ink.js'
 import { AppStateProvider } from '../state/AppState.js'
+import { maskTextWithVisibleEdges } from '../utils/Cursor.js'
 import TextInput from './TextInput.js'
 import VimTextInput from './VimTextInput.js'
 
@@ -199,6 +200,13 @@ test('TextInput renders typed characters before delayed parent value commits', a
   expect(output).not.toContain('Type here...')
 })
 
+test('maskTextWithVisibleEdges preserves only the first and last three chars', () => {
+  expect(maskTextWithVisibleEdges('sk-secret-12345678', '*')).toBe(
+    'sk-************678',
+  )
+  expect(maskTextWithVisibleEdges('abcdef', '*')).toBe('******')
+})
+
 test('VimTextInput preserves rapid typed characters before delayed parent value commits', async () => {
   const { stdout, stdin, getOutput } = createTestStreams()
   const root = await createRoot({

src/components/memory/memoryFileSelectorPaths.test.ts

@@ -53,17 +53,20 @@ describe('getProjectMemoryPathForSelector', () => {
   })
 
   test('defaults to a new AGENTS.md in the current cwd when no project file is loaded', () => {
-    expect(getProjectMemoryPathForSelector([], '/repo/packages/app')).toBe(
+    const cwd = join('/repo', 'packages', 'app')
-      '/repo/packages/app/AGENTS.md',
+    expect(getProjectMemoryPathForSelector([], cwd)).toBe(
+      join(cwd, 'AGENTS.md'),
     )
   })
 
   test('ignores loaded project instruction files outside the current cwd ancestry', () => {
+    const outsideRepoPath = join('/other-worktree', 'AGENTS.md')
+    const cwd = join('/repo', 'packages', 'app')
     expect(
       getProjectMemoryPathForSelector(
-        [projectFile('/other-worktree/AGENTS.md')],
+        [projectFile(outsideRepoPath)],
-        '/repo/packages/app',
+        cwd,
       ),
-    ).toBe('/repo/packages/app/AGENTS.md')
+    ).toBe(join(cwd, 'AGENTS.md'))
   })
 })

src/constants/promptIdentity.test.ts

@@ -1,5 +1,16 @@
 import { afterEach, expect, test } from 'bun:test'
 
+// MACRO is replaced at build time by Bun.define but not in test mode.
+// Define it globally so tests that import modules using MACRO don't crash.
+;(globalThis as Record<string, unknown>).MACRO = {
+  VERSION: '99.0.0',
+  DISPLAY_VERSION: '0.0.0-test',
+  BUILD_TIME: new Date().toISOString(),
+  ISSUES_EXPLAINER: 'report the issue at https://github.com/anthropics/claude-code/issues',
+  PACKAGE_URL: '@gitlawb/openclaude',
+  NATIVE_PACKAGE_URL: undefined,
+}
+
 import { getSystemPrompt, DEFAULT_AGENT_PROMPT } from './prompts.js'
 import { CLI_SYSPROMPT_PREFIXES, getCLISyspromptPrefix } from './system.js'
 import { CLAUDE_CODE_GUIDE_AGENT } from '../tools/AgentTool/built-in/claudeCodeGuideAgent.js'

src/entrypoints/cli.tsx

@@ -5,7 +5,7 @@ import {
 } from '../utils/providerProfile.js'
 import {
   getProviderValidationError,
-  validateProviderEnvOrExit,
+  validateProviderEnvForStartupOrExit,
 } from '../utils/providerValidation.js'
 
 // OpenClaude: polyfill globalThis.File for Node < 20.
@@ -132,7 +132,7 @@ async function main(): Promise<void> {
     hydrateGithubModelsTokenFromSecureStorage()
   }
 
-  await validateProviderEnvOrExit()
+  await validateProviderEnvForStartupOrExit()
 
   // Print the gradient startup screen before the Ink UI loads
   const { printStartupScreen } = await import('../components/StartupScreen.js')

src/entrypoints/mcp.test.ts

@@ -0,0 +1,75 @@
+import { describe, it, expect, mock } from 'bun:test'
+import { getCombinedTools, loadReexposedMcpTools } from './mcp.js'
+import type { Tool as InternalTool } from '../Tool.js'
+import type { MCPServerConnection } from '../services/mcp/types.js'
+import type { Tool } from '@modelcontextprotocol/sdk/types.js'
+
+// Mock the MCP client service to control the tools and connections returned
+const mockGetMcpToolsCommandsAndResources = mock(async (onConnectionAttempt: any) => {})
+mock.module('../services/mcp/client.js', () => ({
+  getMcpToolsCommandsAndResources: mockGetMcpToolsCommandsAndResources
+}))
+
+describe('getCombinedTools', () => {
+  it('deduplicates builtins when mcpTools have the same name, prioritizing mcpTools', () => {
+    const builtinBash = { name: 'Bash', isMcp: false } as unknown as InternalTool
+    const builtinRead = { name: 'Read', isMcp: false } as unknown as InternalTool
+    const mcpBash = { name: 'Bash', isMcp: true } as unknown as InternalTool
+
+    const builtins = [builtinBash, builtinRead]
+    const mcpTools = [mcpBash]
+
+    const result = getCombinedTools(builtins, mcpTools)
+
+    expect(result).toHaveLength(2)
+    expect(result[0]).toBe(mcpBash)
+    expect(result[1]).toBe(builtinRead)
+  })
+})
+
+describe('loadReexposedMcpTools', () => {
+  it('loads tools and clients regardless of connection state (including needs-auth)', async () => {
+    // Setup the mock to simulate yielding a needs-auth server and a connected server
+    mockGetMcpToolsCommandsAndResources.mockImplementation(async (onConnectionAttempt) => {
+      const needsAuthClient = {
+        name: 'auth-server',
+        type: 'needs-auth',
+        config: {}
+      } as MCPServerConnection
+
+      const authTool = {
+        name: 'mcp__auth-server__authenticate',
+        isMcp: true
+      } as unknown as InternalTool
+
+      const connectedClient = {
+        name: 'connected-server',
+        type: 'connected',
+        config: {},
+        client: {}
+      } as MCPServerConnection
+
+      const connectedTool = {
+        name: 'mcp__connected-server__do_thing',
+        isMcp: true
+      } as unknown as InternalTool
+
+      // Simulate the callback behavior
+      onConnectionAttempt({ client: needsAuthClient, tools: [authTool], commands: [] })
+      onConnectionAttempt({ client: connectedClient, tools: [connectedTool], commands: [] })
+    })
+
+    const { mcpClients, mcpTools } = await loadReexposedMcpTools()
+
+    expect(mcpClients).toHaveLength(2)
+    expect(mcpClients[0].type).toBe('needs-auth')
+    expect(mcpClients[1].type).toBe('connected')
+
+    expect(mcpTools).toHaveLength(2)
+    expect(mcpTools[0].name).toBe('mcp__auth-server__authenticate')
+    expect(mcpTools[1].name).toBe('mcp__connected-server__do_thing')
+
+    // Reset mock for other tests
+    mockGetMcpToolsCommandsAndResources.mockReset()
+  })
+})

src/entrypoints/mcp.ts

@@ -7,6 +7,7 @@ process.env.CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS ??= 'true'
 
 import { Server } from '@modelcontextprotocol/sdk/server/index.js'
 import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js'
+import { ZodError } from 'zod'
 import {
   CallToolRequestSchema,
   type CallToolResult,
@@ -17,9 +18,12 @@ import {
 import { getDefaultAppState } from 'src/state/AppStateStore.js'
 import review from '../commands/review.js'
 import type { Command } from '../commands.js'
+import { getMcpToolsCommandsAndResources } from '../services/mcp/client.js'
+import type { MCPServerConnection } from '../services/mcp/types.js'
 import {
   findToolByName,
   getEmptyToolPermissionContext,
+  type Tool as InternalTool,
   type ToolUseContext,
 } from '../Tool.js'
 import { getTools } from '../tools.js'
@@ -39,6 +43,32 @@ type ToolOutput = Tool['outputSchema']
 
 const MCP_COMMANDS: Command[] = [review]
 
+export function getCombinedTools(
+  builtins: InternalTool[],
+  mcpTools: InternalTool[],
+): InternalTool[] {
+  const mcpToolNames = new Set(mcpTools.map(t => t.name))
+  const deduplicatedBuiltins = builtins.filter(t => !mcpToolNames.has(t.name))
+
+  return [...mcpTools, ...deduplicatedBuiltins]
+}
+
+export async function loadReexposedMcpTools(): Promise<{
+  mcpClients: MCPServerConnection[]
+  mcpTools: InternalTool[]
+}> {
+  const mcpClients: MCPServerConnection[] = []
+  const mcpTools: InternalTool[] = []
+
+  // Load configured MCP clients and their tools
+  await getMcpToolsCommandsAndResources(({ client, tools: clientTools }) => {
+    mcpClients.push(client)
+    mcpTools.push(...clientTools)
+  })
+
+  return { mcpClients, mcpTools }
+}
+
 export async function startMCPServer(
   cwd: string,
   debug: boolean,
@@ -63,12 +93,13 @@ export async function startMCPServer(
     },
   )
 
+  const { mcpClients, mcpTools } = await loadReexposedMcpTools()
+
   server.setRequestHandler(
     ListToolsRequestSchema,
     async (): Promise<ListToolsResult> => {
-      // TODO: Also re-expose any MCP tools
       const toolPermissionContext = getEmptyToolPermissionContext()
-      const tools = getTools(toolPermissionContext)
+      const tools = getCombinedTools(getTools(toolPermissionContext), mcpTools)
       return {
         tools: await Promise.all(
           tools.map(async tool => {
@@ -94,7 +125,7 @@ export async function startMCPServer(
                 tools,
                 agents: [],
               }),
-              inputSchema: zodToJsonSchema(tool.inputSchema) as ToolInput,
+              inputSchema: (tool.inputJSONSchema ?? zodToJsonSchema(tool.inputSchema)) as ToolInput,
               outputSchema,
             }
           }),
@@ -107,8 +138,7 @@ export async function startMCPServer(
     CallToolRequestSchema,
     async ({ params: { name, arguments: args } }): Promise<CallToolResult> => {
       const toolPermissionContext = getEmptyToolPermissionContext()
-      // TODO: Also re-expose any MCP tools
+      const tools = getCombinedTools(getTools(toolPermissionContext), mcpTools)
-      const tools = getTools(toolPermissionContext)
       const tool = findToolByName(tools, name)
       if (!tool) {
         throw new Error(`Tool ${name} not found`)
@@ -123,7 +153,7 @@ export async function startMCPServer(
           tools,
           mainLoopModel: getMainLoopModel(),
           thinkingConfig: { type: 'disabled' },
-          mcpClients: [],
+          mcpClients,
           mcpResources: {},
           isNonInteractiveSession: true,
           debug,
@@ -140,13 +170,16 @@ export async function startMCPServer(
         updateAttributionState: () => {},
       }
 
-      // TODO: validate input types with zod
       try {
         if (!tool.isEnabled()) {
           throw new Error(`Tool ${name} is not enabled`)
         }
+
+        // Validate input types with zod
+        const parsedArgs = tool.inputSchema.parse(args ?? {})
+
         const validationResult = await tool.validateInput?.(
-          (args as never) ?? {},
+          (parsedArgs as never) ?? {},
           toolUseContext,
         )
         if (validationResult && !validationResult.result) {
@@ -155,7 +188,7 @@ export async function startMCPServer(
           )
         }
         const finalResult = await tool.call(
-          (args ?? {}) as never,
+          (parsedArgs ?? {}) as never,
           toolUseContext,
           hasPermissionsToUseTool,
           createAssistantMessage({
@@ -163,20 +196,50 @@ export async function startMCPServer(
           }),
         )
 
+        let content: CallToolResult['content']
+        const data = finalResult.data as string | { type: string; text?: string; source?: { type: string; media_type: string; data: string } }[] | unknown
+
+        if (typeof data === 'string') {
+          content = [{ type: 'text', text: data }]
+        } else if (Array.isArray(data)) {
+          content = data.map((block: any) => {
+            if (block.type === 'text') {
+              return { type: 'text', text: block.text || '' }
+            } else if (block.type === 'image' && block.source) {
               return {
-          content: [
+                type: 'image',
-            {
+                data: block.source.data,
-              type: 'text' as const,
+                mimeType: block.source.media_type,
-              text:
+              }
-                typeof finalResult === 'string'
+            } else {
-                  ? finalResult
+              // eslint-disable-next-line custom-rules/no-top-level-side-effects, no-console
-                  : jsonStringify(finalResult.data),
+              console.warn(`Unmapped content block type from tool ${name}: ${block.type || 'unknown'}`)
-            },
+              return { type: 'text', text: jsonStringify(block) }
-          ],
+            }
+          }) as CallToolResult['content']
+        } else {
+          content = [{ type: 'text', text: jsonStringify(data) }]
+        }
+
+        return {
+          content,
+          isError: !!(finalResult as any).isError,
         }
       } catch (error) {
         logError(error)
 
+        if (error instanceof ZodError) {
+          return {
+            isError: true,
+            content: [
+              {
+                type: 'text',
+                text: `Tool ${name} input is invalid:\n${error.errors.map(e => `- ${e.path.join('.')}: ${e.message}`).join('\n')}`,
+              },
+            ],
+          }
+        }
+
         const parts =
           error instanceof Error ? getErrorParts(error) : [String(error)]
         const errorText = parts.filter(Boolean).join('\n').trim() || 'Error'
@@ -201,3 +264,4 @@ export async function startMCPServer(
 
   return await runServer()
 }
+

src/entrypoints/sandboxTypes.ts

@@ -114,8 +114,8 @@ export const SandboxSettingsSchema = lazySchema(() =>
         .boolean()
         .optional()
         .describe(
-          'Allow commands to run outside the sandbox via the dangerouslyDisableSandbox parameter. ' +
+          'Allow trusted, user-initiated commands to run outside the sandbox. ' +
-            'When false, the dangerouslyDisableSandbox parameter is completely ignored and all commands must run sandboxed. ' +
+            'When false, sandbox override requests are ignored and all commands must run sandboxed. ' +
             'Default: true.',
         ),
       network: SandboxNetworkConfigSchema(),

src/hooks/useOfficialMarketplaceNotification.tsx

@@ -19,7 +19,7 @@ async function _temp() {
     logForDebugging("Showing marketplace config save failure notification");
     notifs.push({
       key: "marketplace-config-save-failed",
-      jsx: <Text color="error">Failed to save marketplace retry info · Check ~/.claude.json permissions</Text>,
+      jsx: <Text color="error">Failed to save marketplace retry info · Check ~/.openclaude.json permissions</Text>,
       priority: "immediate",
       timeoutMs: 10000
     });

src/hooks/useSwarmPermissionPoller.ts

@@ -1,34 +1,23 @@
 /**
- * Swarm Permission Poller Hook
+ * Swarm Permission Callback Registry
  *
- * This hook polls for permission responses from the team leader when running
+ * Manages callback registrations for permission requests and responses
- * as a worker agent in a swarm. When a response is received, it calls the
+ * in agent swarms. Responses are delivered exclusively via the mailbox
- * appropriate callback (onAllow/onReject) to continue execution.
+ * system (useInboxPoller → processMailboxPermissionResponse).
  *
- * This hook should be used in conjunction with the worker-side integration
+ * The legacy file-based polling (resolved/ directory) has been removed
- * in useCanUseTool.ts, which creates pending requests that this hook monitors.
+ * because it created an unauthenticated attack surface — any local process
+ * could forge approval files. The mailbox path is the sole active channel.
  */
 
-import { useCallback, useEffect, useRef } from 'react'
-import { useInterval } from 'usehooks-ts'
 import { logForDebugging } from '../utils/debug.js'
-import { errorMessage } from '../utils/errors.js'
 import {
   type PermissionUpdate,
   permissionUpdateSchema,
 } from '../utils/permissions/PermissionUpdateSchema.js'
-import {
-  isSwarmWorker,
-  type PermissionResponse,
-  pollForResponse,
-  removeWorkerResponse,
-} from '../utils/swarm/permissionSync.js'
-import { getAgentName, getTeamName } from '../utils/teammate.js'
-
-const POLL_INTERVAL_MS = 500
 
 /**
- * Validate permissionUpdates from external sources (mailbox IPC, disk polling).
+ * Validate permissionUpdates from external sources (mailbox IPC).
  * Malformed entries from buggy/old teammate processes are filtered out rather
  * than propagated unchecked into callback.onAllow().
  */
@@ -225,106 +214,9 @@ export function processSandboxPermissionResponse(params: {
   return true
 }
 
-/**
+// Legacy file-based polling (useSwarmPermissionPoller, processResponse)
- * Process a permission response by invoking the registered callback
+// has been removed. Permission responses are now delivered exclusively
- */
+// via the mailbox system:
-function processResponse(response: PermissionResponse): boolean {
+//   Leader: sendPermissionResponseViaMailbox() → writeToMailbox()
-  const callback = pendingCallbacks.get(response.requestId)
+//   Worker: useInboxPoller → processMailboxPermissionResponse()
-
+// See: fix(security) — remove unauthenticated file-based permission channel
-  if (!callback) {
-    logForDebugging(
-      `[SwarmPermissionPoller] No callback registered for request ${response.requestId}`,
-    )
-    return false
-  }
-
-  logForDebugging(
-    `[SwarmPermissionPoller] Processing response for request ${response.requestId}: ${response.decision}`,
-  )
-
-  // Remove from registry before invoking callback
-  pendingCallbacks.delete(response.requestId)
-
-  if (response.decision === 'approved') {
-    const permissionUpdates = parsePermissionUpdates(response.permissionUpdates)
-    const updatedInput = response.updatedInput
-    callback.onAllow(updatedInput, permissionUpdates)
-  } else {
-    callback.onReject(response.feedback)
-  }
-
-  return true
-}
-
-/**
- * Hook that polls for permission responses when running as a swarm worker.
- *
- * This hook:
- * 1. Only activates when isSwarmWorker() returns true
- * 2. Polls every 500ms for responses
- * 3. When a response is found, invokes the registered callback
- * 4. Cleans up the response file after processing
- */
-export function useSwarmPermissionPoller(): void {
-  const isProcessingRef = useRef(false)
-
-  const poll = useCallback(async () => {
-    // Don't poll if not a swarm worker
-    if (!isSwarmWorker()) {
-      return
-    }
-
-    // Prevent concurrent polling
-    if (isProcessingRef.current) {
-      return
-    }
-
-    // Don't poll if no callbacks are registered
-    if (pendingCallbacks.size === 0) {
-      return
-    }
-
-    isProcessingRef.current = true
-
-    try {
-      const agentName = getAgentName()
-      const teamName = getTeamName()
-
-      if (!agentName || !teamName) {
-        return
-      }
-
-      // Check each pending request for a response
-      for (const [requestId, _callback] of pendingCallbacks) {
-        const response = await pollForResponse(requestId, agentName, teamName)
-
-        if (response) {
-          // Process the response
-          const processed = processResponse(response)
-
-          if (processed) {
-            // Clean up the response from the worker's inbox
-            await removeWorkerResponse(requestId, agentName, teamName)
-          }
-        }
-      }
-    } catch (error) {
-      logForDebugging(
-        `[SwarmPermissionPoller] Error during poll: ${errorMessage(error)}`,
-      )
-    } finally {
-      isProcessingRef.current = false
-    }
-  }, [])
-
-  // Only poll if we're a swarm worker
-  const shouldPoll = isSwarmWorker()
-  useInterval(() => void poll(), shouldPoll ? POLL_INTERVAL_MS : null)
-
-  // Initial poll on mount
-  useEffect(() => {
-    if (isSwarmWorker()) {
-      void poll()
-    }
-  }, [poll])
-}

src/ink/termio/osc.test.ts

@@ -11,14 +11,16 @@ const execFileNoThrowMock = mock(
   async () => ({ code: 0, stdout: '', stderr: '' }),
 )
 
-mock.module('../../utils/execFileNoThrow.js', () => ({
+function installOscMocks(): void {
+  mock.module('../../utils/execFileNoThrow.js', () => ({
     execFileNoThrow: execFileNoThrowMock,
     execFileNoThrowWithCwd: execFileNoThrowMock,
-}))
+  }))
 
-mock.module('../../utils/tempfile.js', () => ({
+  mock.module('../../utils/tempfile.js', () => ({
     generateTempFilePath: generateTempFilePathMock,
-}))
+  }))
+}
 
 async function importFreshOscModule() {
   return import(`./osc.ts?ts=${Date.now()}-${Math.random()}`)
@@ -45,6 +47,7 @@ async function waitForExecCall(
 
 describe('Windows clipboard fallback', () => {
   beforeEach(() => {
+    installOscMocks()
     execFileNoThrowMock.mockClear()
     generateTempFilePathMock.mockClear()
     process.env = { ...originalEnv }
@@ -62,14 +65,12 @@ describe('Windows clipboard fallback', () => {
     const { setClipboard } = await importFreshOscModule()
 
     await setClipboard('Привет мир')
-    await flushClipboardCopy()
+    const windowsCall = await waitForExecCall('powershell')
 
     expect(execFileNoThrowMock.mock.calls.some(([cmd]) => cmd === 'clip')).toBe(
       false,
     )
-    expect(
+    expect(windowsCall).toBeDefined()
-      execFileNoThrowMock.mock.calls.some(([cmd]) => cmd === 'powershell'),
-    ).toBe(true)
   })
 
   test('passes Windows clipboard text through a UTF-8 temp file instead of stdin', async () => {
@@ -97,6 +98,7 @@ describe('Windows clipboard fallback', () => {
 
 describe('clipboard path behavior remains stable', () => {
   beforeEach(() => {
+    installOscMocks()
     execFileNoThrowMock.mockClear()
     process.env = { ...originalEnv }
     delete process.env['SSH_CONNECTION']

src/migrations/resetAutoModeOptInForDefaultOffer.ts

@@ -12,7 +12,7 @@ import {
  * One-shot migration: clear skipAutoPermissionPrompt for users who accepted
  * the old 2-option AutoModeOptInDialog but don't have auto as their default.
  * Re-surfaces the dialog so they see the new "make it my default mode" option.
- * Guard lives in GlobalConfig (~/.claude.json), not settings.json, so it
+ * Guard lives in GlobalConfig (~/.openclaude.json), not settings.json, so it
  * survives settings resets and doesn't re-arm itself.
  *
  * Only runs when tengu_auto_mode_config.enabled === 'enabled'. For 'opt-in'

src/screens/REPL.tsx

@@ -3873,7 +3873,7 @@ export function REPL({
   // empty to non-empty, not on every length change -- otherwise a render loop
   // (concurrent onQuery thrashing, etc.) spams saveGlobalConfig, which hits
   // ELOCKED under concurrent sessions and falls back to unlocked writes.
-  // That write storm is the primary trigger for ~/.claude.json corruption
+  // That write storm is the primary trigger for ~/.openclaude.json corruption
   // (GH #3117).
   const hasCountedQueueUseRef = useRef(false);
   useEffect(() => {

src/services/analytics/growthbook.ts

@@ -334,7 +334,7 @@ async function processRemoteEvalPayload(
   // Empty object is truthy — without the length check, `{features: {}}`
   // (transient server bug, truncated response) would pass, clear the maps
   // below, return true, and syncRemoteEvalToDisk would wholesale-write `{}`
-  // to disk: total flag blackout for every process sharing ~/.claude.json.
+  // to disk: total flag blackout for every process sharing ~/.openclaude.json.
   if (!payload?.features || Object.keys(payload.features).length === 0) {
     return false
   }

src/services/api/claude.ts

@@ -23,6 +23,7 @@ import { randomUUID } from 'crypto'
 import {
   getAPIProvider,
   isFirstPartyAnthropicBaseUrl,
+  isGithubNativeAnthropicMode,
 } from 'src/utils/model/providers.js'
 import {
   getAttributionHeader,
@@ -334,8 +335,13 @@ export function getPromptCachingEnabled(model: string): boolean {
   // Prompt caching is an Anthropic-specific feature. Third-party providers
   // do not understand cache_control blocks and strict backends (e.g. Azure
   // Foundry) reject or flag requests that contain them.
+  //
+  // Exception: when the GitHub provider is configured in native Anthropic API
+  // mode (CLAUDE_CODE_GITHUB_ANTHROPIC_API=1), requests are sent in Anthropic
+  // format, so cache_control blocks are supported.
   const provider = getAPIProvider()
-  if (provider !== 'firstParty' && provider !== 'bedrock' && provider !== 'vertex') {
+  const isNativeGithub = isGithubNativeAnthropicMode(model)
+  if (provider !== 'firstParty' && provider !== 'bedrock' && provider !== 'vertex' && !isNativeGithub) {
     return false
   }
 

src/services/api/client.ts

@@ -14,6 +14,7 @@ import { getSmallFastModel } from 'src/utils/model/model.js'
 import {
   getAPIProvider,
   isFirstPartyAnthropicBaseUrl,
+  isGithubNativeAnthropicMode,
 } from 'src/utils/model/providers.js'
 import { getProxyFetchOptions } from 'src/utils/proxy.js'
 import {
@@ -174,6 +175,25 @@ export async function getAnthropicClient({
       providerOverride,
     }) as unknown as Anthropic
   }
+  // GitHub provider in native Anthropic API mode: send requests in Anthropic
+  // format so cache_control blocks are honoured and prompt caching works.
+  // Requires the GitHub endpoint (OPENAI_BASE_URL) to support Anthropic's
+  // messages API — set CLAUDE_CODE_GITHUB_ANTHROPIC_API=1 to opt in.
+  if (isGithubNativeAnthropicMode(model)) {
+    const githubBaseUrl =
+      process.env.OPENAI_BASE_URL?.replace(/\/$/, '') ??
+      'https://api.githubcopilot.com'
+    const githubToken =
+      process.env.GITHUB_TOKEN ?? process.env.GH_TOKEN ?? ''
+    const nativeArgs: ConstructorParameters<typeof Anthropic>[0] = {
+      ...ARGS,
+      baseURL: githubBaseUrl,
+      authToken: githubToken,
+      // No apiKey — we authenticate via Bearer token (authToken)
+      apiKey: null,
+    }
+    return new Anthropic(nativeArgs)
+  }
   if (
     isEnvTruthy(process.env.CLAUDE_CODE_USE_OPENAI) ||
     isEnvTruthy(process.env.CLAUDE_CODE_USE_GITHUB) ||

src/services/api/codexShim.test.ts

@@ -547,7 +547,7 @@ describe('Codex request translation', () => {
     ])
   })
 
-  test('strips leaked reasoning preamble from completed Codex text responses', () => {
+  test('strips <think> tag block from completed Codex text responses', () => {
     const message = convertCodexResponseToAnthropicMessage(
       {
         id: 'resp_1',
@@ -560,7 +560,7 @@ describe('Codex request translation', () => {
               {
                 type: 'output_text',
                 text:
-                  'The user just said "hey" - a simple greeting. I should respond briefly and friendly.\n\nHey! How can I help you today?',
+                  '<think>user wants a greeting, respond briefly</think>Hey! How can I help you today?',
               },
             ],
           },
@@ -578,6 +578,37 @@ describe('Codex request translation', () => {
     ])
   })
 
+  test('strips unterminated <think> tag at block boundary in Codex completed response', () => {
+    const message = convertCodexResponseToAnthropicMessage(
+      {
+        id: 'resp_1',
+        model: 'gpt-5.4',
+        output: [
+          {
+            type: 'message',
+            role: 'assistant',
+            content: [
+              {
+                type: 'output_text',
+                text:
+                  'Here is the answer.\n<think>wait, let me reconsider the user request',
+              },
+            ],
+          },
+        ],
+        usage: { input_tokens: 12, output_tokens: 4 },
+      },
+      'gpt-5.4',
+    )
+
+    expect(message.content).toEqual([
+      {
+        type: 'text',
+        text: 'Here is the answer.',
+      },
+    ])
+  })
+
   test('translates Codex SSE text stream into Anthropic events', async () => {
     const responseText = [
       'event: response.output_item.added',
@@ -609,7 +640,7 @@ describe('Codex request translation', () => {
     ])
   })
 
-  test('strips leaked reasoning preamble from Codex SSE text stream', async () => {
+  test('strips <think> tag block from Codex SSE text stream', async () => {
     const responseText = [
       'event: response.output_item.added',
       'data: {"type":"response.output_item.added","item":{"id":"msg_1","type":"message","status":"in_progress","content":[],"role":"assistant"},"output_index":0,"sequence_number":0}',
@@ -618,13 +649,13 @@ describe('Codex request translation', () => {
       'data: {"type":"response.content_part.added","content_index":0,"item_id":"msg_1","output_index":0,"part":{"type":"output_text","text":""},"sequence_number":1}',
       '',
       'event: response.output_text.delta',
-      'data: {"type":"response.output_text.delta","content_index":0,"delta":"The user just said \\"hey\\" - a simple greeting. I should respond briefly and friendly.\\n\\nHey! How can I help you today?","item_id":"msg_1","output_index":0,"sequence_number":2}',
+      'data: {"type":"response.output_text.delta","content_index":0,"delta":"<think>user wants a greeting, respond briefly</think>Hey! How can I help you today?","item_id":"msg_1","output_index":0,"sequence_number":2}',
       '',
       'event: response.output_item.done',
-      'data: {"type":"response.output_item.done","item":{"id":"msg_1","type":"message","status":"completed","content":[{"type":"output_text","text":"The user just said \\"hey\\" - a simple greeting. I should respond briefly and friendly.\\n\\nHey! How can I help you today?"}],"role":"assistant"},"output_index":0,"sequence_number":3}',
+      'data: {"type":"response.output_item.done","item":{"id":"msg_1","type":"message","status":"completed","content":[{"type":"output_text","text":"<think>user wants a greeting, respond briefly</think>Hey! How can I help you today?"}],"role":"assistant"},"output_index":0,"sequence_number":3}',
       '',
       'event: response.completed',
-      'data: {"type":"response.completed","response":{"id":"resp_1","status":"completed","model":"gpt-5.4","output":[{"type":"message","role":"assistant","content":[{"type":"output_text","text":"The user just said \\"hey\\" - a simple greeting. I should respond briefly and friendly.\\n\\nHey! How can I help you today?"}]}],"usage":{"input_tokens":2,"output_tokens":1}},"sequence_number":4}',
+      'data: {"type":"response.completed","response":{"id":"resp_1","status":"completed","model":"gpt-5.4","output":[{"type":"message","role":"assistant","content":[{"type":"output_text","text":"<think>user wants a greeting, respond briefly</think>Hey! How can I help you today?"}]}],"usage":{"input_tokens":2,"output_tokens":1}},"sequence_number":4}',
       '',
     ].join('\n')
 
@@ -646,6 +677,50 @@ describe('Codex request translation', () => {
       }
     }
 
-    expect(textDeltas).toEqual(['Hey! How can I help you today?'])
+    expect(textDeltas.join('')).toBe('Hey! How can I help you today?')
+  })
+
+  test('preserves prose without tags (no phrase-based false positive)', async () => {
+    // Regression test: older phrase-based sanitizer would incorrectly strip text
+    // starting with "I should" or "The user". The tag-based approach leaves it alone.
+    const responseText = [
+      'event: response.output_item.added',
+      'data: {"type":"response.output_item.added","item":{"id":"msg_1","type":"message","status":"in_progress","content":[],"role":"assistant"},"output_index":0,"sequence_number":0}',
+      '',
+      'event: response.content_part.added',
+      'data: {"type":"response.content_part.added","content_index":0,"item_id":"msg_1","output_index":0,"part":{"type":"output_text","text":""},"sequence_number":1}',
+      '',
+      'event: response.output_text.delta',
+      'data: {"type":"response.output_text.delta","content_index":0,"delta":"I should note that the user role requires a briefly concise friendly response format.","item_id":"msg_1","output_index":0,"sequence_number":2}',
+      '',
+      'event: response.output_item.done',
+      'data: {"type":"response.output_item.done","item":{"id":"msg_1","type":"message","status":"completed","content":[{"type":"output_text","text":"I should note that the user role requires a briefly concise friendly response format."}],"role":"assistant"},"output_index":0,"sequence_number":3}',
+      '',
+      'event: response.completed',
+      'data: {"type":"response.completed","response":{"id":"resp_1","status":"completed","model":"gpt-5.4","output":[{"type":"message","role":"assistant","content":[{"type":"output_text","text":"I should note that the user role requires a briefly concise friendly response format."}]}],"usage":{"input_tokens":2,"output_tokens":1}},"sequence_number":4}',
+      '',
+    ].join('\n')
+
+    const stream = new ReadableStream({
+      start(controller) {
+        controller.enqueue(new TextEncoder().encode(responseText))
+        controller.close()
+      },
+    })
+
+    const textDeltas: string[] = []
+    for await (const event of codexStreamToAnthropic(
+      new Response(stream),
+      'gpt-5.4',
+    )) {
+      const delta = (event as { delta?: { type?: string; text?: string } }).delta
+      if (delta?.type === 'text_delta' && typeof delta.text === 'string') {
+        textDeltas.push(delta.text)
+      }
+    }
+
+    expect(textDeltas.join('')).toBe(
+      'I should note that the user role requires a briefly concise friendly response format.',
+    )
   })
 })

src/services/api/codexShim.ts

@@ -1,14 +1,14 @@
 import { APIError } from '@anthropic-ai/sdk'
+import { fetchWithProxyRetry } from './fetchWithProxyRetry.js'
 import type {
   ResolvedCodexCredentials,
   ResolvedProviderRequest,
 } from './providerConfig.js'
 import { sanitizeSchemaForOpenAICompat } from './openaiSchemaSanitizer.js'
 import {
-  looksLikeLeakedReasoningPrefix,
+  createThinkTagFilter,
-  shouldBufferPotentialReasoningPrefix,
+  stripThinkTags,
-  stripLeakedReasoningPreamble,
+} from './thinkTagSanitizer.js'
-} from './reasoningLeakSanitizer.js'
 
 export interface AnthropicUsage {
   input_tokens: number
@@ -559,12 +559,15 @@ export async function performCodexRequest(options: {
   }
   headers.originator ??= 'openclaude'
 
-  const response = await fetch(`${options.request.baseUrl}/responses`, {
+  const response = await fetchWithProxyRetry(
+    `${options.request.baseUrl}/responses`,
+    {
       method: 'POST',
       headers,
       body: JSON.stringify(body),
       signal: options.signal,
-  })
+    },
+  )
 
   if (!response.ok) {
     const errorBody = await response.text().catch(() => 'unknown error')
@@ -730,34 +733,29 @@ export async function* codexStreamToAnthropic(
     { index: number; toolUseId: string }
   >()
   let activeTextBlockIndex: number | null = null
-  let activeTextBuffer = ''
+  const thinkFilter = createThinkTagFilter()
-  let textBufferMode: 'none' | 'pending' | 'strip' = 'none'
   let nextContentBlockIndex = 0
   let sawToolUse = false
   let finalResponse: Record<string, any> | undefined
 
   const closeActiveTextBlock = async function* () {
     if (activeTextBlockIndex === null) return
-    if (textBufferMode !== 'none') {
+    const tail = thinkFilter.flush()
-      const sanitized = stripLeakedReasoningPreamble(activeTextBuffer)
+    if (tail) {
-      if (sanitized) {
       yield {
         type: 'content_block_delta',
         index: activeTextBlockIndex,
         delta: {
           type: 'text_delta',
-            text: sanitized,
+          text: tail,
         },
       }
     }
-    }
     yield {
       type: 'content_block_stop',
       index: activeTextBlockIndex,
     }
     activeTextBlockIndex = null
-    activeTextBuffer = ''
-    textBufferMode = 'none'
   }
 
   const startTextBlockIfNeeded = async function* () {
@@ -833,43 +831,17 @@ export async function* codexStreamToAnthropic(
 
     if (event.event === 'response.output_text.delta') {
       yield* startTextBlockIfNeeded()
-      activeTextBuffer += payload.delta ?? ''
       if (activeTextBlockIndex !== null) {
-        if (
+        const visible = thinkFilter.feed(payload.delta ?? '')
-          textBufferMode === 'strip' ||
+        if (visible) {
-          looksLikeLeakedReasoningPrefix(activeTextBuffer)
-        ) {
-          textBufferMode = 'strip'
-          continue
-        }
-
-        if (textBufferMode === 'pending') {
-          if (shouldBufferPotentialReasoningPrefix(activeTextBuffer)) {
-            continue
-          }
           yield {
             type: 'content_block_delta',
             index: activeTextBlockIndex,
             delta: {
               type: 'text_delta',
-              text: activeTextBuffer,
+              text: visible,
             },
           }
-          textBufferMode = 'none'
-          continue
-        }
-
-        if (shouldBufferPotentialReasoningPrefix(activeTextBuffer)) {
-          textBufferMode = 'pending'
-          continue
-        }
-        yield {
-          type: 'content_block_delta',
-          index: activeTextBlockIndex,
-          delta: {
-            type: 'text_delta',
-            text: payload.delta ?? '',
-          },
         }
       }
       continue
@@ -965,7 +937,7 @@ export function convertCodexResponseToAnthropicMessage(
         if (part?.type === 'output_text') {
           content.push({
             type: 'text',
-            text: stripLeakedReasoningPreamble(part.text ?? ''),
+            text: stripThinkTags(part.text ?? ''),
           })
         }
       }

src/services/api/errors.openaiCompatibility.test.ts

@@ -0,0 +1,44 @@
+import { APIError } from '@anthropic-ai/sdk'
+import { expect, test } from 'bun:test'
+
+import { getAssistantMessageFromError } from './errors.js'
+
+function getFirstText(message: ReturnType<typeof getAssistantMessageFromError>): string {
+  const first = message.message.content[0]
+  if (!first || typeof first !== 'object' || !('text' in first)) {
+    return ''
+  }
+  return typeof first.text === 'string' ? first.text : ''
+}
+
+test('maps endpoint_not_found category markers to actionable setup guidance', () => {
+  const error = APIError.generate(
+    404,
+    undefined,
+    'OpenAI API error 404: Not Found [openai_category=endpoint_not_found] Hint: Confirm OPENAI_BASE_URL includes /v1.',
+    new Headers(),
+  )
+
+  const message = getAssistantMessageFromError(error, 'qwen2.5-coder:7b')
+  const text = getFirstText(message)
+
+  expect(message.isApiErrorMessage).toBe(true)
+  expect(text).toContain('Provider endpoint was not found')
+  expect(text).toContain('OPENAI_BASE_URL')
+  expect(text).toContain('/v1')
+})
+
+test('maps tool_call_incompatible category markers to model/tool guidance', () => {
+  const error = APIError.generate(
+    400,
+    undefined,
+    'OpenAI API error 400: tool_calls are not supported [openai_category=tool_call_incompatible]',
+    new Headers(),
+  )
+
+  const message = getAssistantMessageFromError(error, 'qwen2.5-coder:7b')
+  const text = getFirstText(message)
+
+  expect(text).toContain('rejected tool-calling payloads')
+  expect(text).toContain('/model')
+})

src/services/api/errors.ts

@@ -50,9 +50,110 @@ import {
 } from '../claudeAiLimits.js'
 import { shouldProcessRateLimits } from '../rateLimitMocking.js' // Used for /mock-limits command
 import { extractConnectionErrorDetails, formatAPIError } from './errorUtils.js'
+import {
+  extractOpenAICategoryMarker,
+  type OpenAICompatibilityFailureCategory,
+} from './openaiErrorClassification.js'
 
 export const API_ERROR_MESSAGE_PREFIX = 'API Error'
 
+function stripOpenAICompatibilityMetadata(message: string): string {
+  return message
+    .replace(/\s*\[openai_category=[a-z_]+\]\s*/g, ' ')
+    .replace(/\s{2,}/g, ' ')
+    .trim()
+}
+
+function mapOpenAICompatibilityFailureToAssistantMessage(options: {
+  category: OpenAICompatibilityFailureCategory
+  model: string
+  rawMessage: string
+}): AssistantMessage {
+  const switchCmd = getIsNonInteractiveSession() ? '--model' : '/model'
+  const compactHint = getIsNonInteractiveSession()
+    ? 'Reduce prompt size or start a new session.'
+    : 'Run /compact or start a new session with /new.'
+
+  switch (options.category) {
+    case 'localhost_resolution_failed':
+    case 'connection_refused':
+      return createAssistantAPIErrorMessage({
+        content:
+          'Could not connect to the local OpenAI-compatible provider. Ensure the local server is running, then use OPENAI_BASE_URL=http://127.0.0.1:11434/v1 for Ollama.',
+        error: 'unknown',
+      })
+
+    case 'endpoint_not_found':
+      return createAssistantAPIErrorMessage({
+        content:
+          'Provider endpoint was not found. Confirm OPENAI_BASE_URL targets an OpenAI-compatible /v1 endpoint (for Ollama: http://127.0.0.1:11434/v1).',
+        error: 'invalid_request',
+      })
+
+    case 'model_not_found':
+      return createAssistantAPIErrorMessage({
+        content: `The selected model (${options.model}) is not available on this provider. Run ${switchCmd} to choose another model, or verify installed local models (for Ollama: ollama list).`,
+        error: 'invalid_request',
+      })
+
+    case 'auth_invalid':
+      return createAssistantAPIErrorMessage({
+        content: `${API_ERROR_MESSAGE_PREFIX}: Authentication failed for your OpenAI-compatible provider. Verify OPENAI_API_KEY and endpoint-specific auth requirements.`,
+        error: 'authentication_failed',
+      })
+
+    case 'rate_limited':
+      return createAssistantAPIErrorMessage({
+        content: `${API_ERROR_MESSAGE_PREFIX}: Provider rate limit reached. Retry in a few seconds.`,
+        error: 'rate_limit',
+      })
+
+    case 'request_timeout':
+      return createAssistantAPIErrorMessage({
+        content: `${API_ERROR_MESSAGE_PREFIX}: Provider request timed out. Local models may be loading or overloaded; retry shortly or increase API_TIMEOUT_MS.`,
+        error: 'unknown',
+      })
+
+    case 'context_overflow':
+      return createAssistantAPIErrorMessage({
+        content: `The conversation exceeded the provider context limit. ${compactHint}`,
+        error: 'invalid_request',
+      })
+
+    case 'tool_call_incompatible':
+      return createAssistantAPIErrorMessage({
+        content: `The selected provider/model rejected tool-calling payloads. Try ${switchCmd} to pick a tool-capable model or continue without tools.`,
+        error: 'invalid_request',
+      })
+
+    case 'malformed_provider_response':
+      return createAssistantAPIErrorMessage({
+        content: `${API_ERROR_MESSAGE_PREFIX}: Provider returned a malformed response. Confirm endpoint compatibility and check local proxy/network middleware.`,
+        error: 'unknown',
+        errorDetails: stripOpenAICompatibilityMetadata(options.rawMessage),
+      })
+
+    case 'provider_unavailable':
+      return createAssistantAPIErrorMessage({
+        content: `${API_ERROR_MESSAGE_PREFIX}: Provider is temporarily unavailable. Retry in a moment.`,
+        error: 'unknown',
+      })
+
+    case 'network_error':
+    case 'unknown':
+      return createAssistantAPIErrorMessage({
+        content: `${API_ERROR_MESSAGE_PREFIX}: ${stripOpenAICompatibilityMetadata(options.rawMessage)}`,
+        error: 'unknown',
+      })
+
+    default:
+      return createAssistantAPIErrorMessage({
+        content: `${API_ERROR_MESSAGE_PREFIX}: ${stripOpenAICompatibilityMetadata(options.rawMessage)}`,
+        error: 'unknown',
+      })
+  }
+}
+
 export function startsWithApiErrorPrefix(text: string): boolean {
   return (
     text.startsWith(API_ERROR_MESSAGE_PREFIX) ||
@@ -457,6 +558,19 @@ export function getAssistantMessageFromError(
     })
   }
 
+  // OpenAI-compatible transport and HTTP failures include structured category
+  // markers from openaiShim.ts for actionable end-user remediation.
+  if (error instanceof APIError) {
+    const openaiCategory = extractOpenAICategoryMarker(error.message)
+    if (openaiCategory) {
+      return mapOpenAICompatibilityFailureToAssistantMessage({
+        category: openaiCategory,
+        model,
+        rawMessage: error.message,
+      })
+    }
+  }
+
   // Check for emergency capacity off switch for Opus PAYG users
   if (
     error instanceof Error &&

src/services/api/fetchWithProxyRetry.test.ts

@@ -0,0 +1,86 @@
+import { afterEach, beforeEach, expect, test } from 'bun:test'
+
+import { _resetKeepAliveForTesting } from '../../utils/proxy.js'
+import {
+  fetchWithProxyRetry,
+  isRetryableFetchError,
+} from './fetchWithProxyRetry.js'
+
+type FetchType = typeof globalThis.fetch
+
+const originalFetch = globalThis.fetch
+const originalEnv = {
+  HTTP_PROXY: process.env.HTTP_PROXY,
+  HTTPS_PROXY: process.env.HTTPS_PROXY,
+}
+
+function restoreEnv(key: 'HTTP_PROXY' | 'HTTPS_PROXY', value: string | undefined): void {
+  if (value === undefined) {
+    delete process.env[key]
+  } else {
+    process.env[key] = value
+  }
+}
+
+beforeEach(() => {
+  process.env.HTTP_PROXY = 'http://127.0.0.1:15236'
+  delete process.env.HTTPS_PROXY
+  _resetKeepAliveForTesting()
+})
+
+afterEach(() => {
+  globalThis.fetch = originalFetch
+  restoreEnv('HTTP_PROXY', originalEnv.HTTP_PROXY)
+  restoreEnv('HTTPS_PROXY', originalEnv.HTTPS_PROXY)
+  _resetKeepAliveForTesting()
+})
+
+test('isRetryableFetchError matches Bun socket-closed failures', () => {
+  expect(
+    isRetryableFetchError(
+      new Error(
+        'The socket connection was closed unexpectedly. For more information, pass `verbose: true` in the second argument to fetch()',
+      ),
+    ),
+  ).toBe(true)
+})
+
+test('fetchWithProxyRetry retries once with keepalive disabled after socket closure', async () => {
+  const calls: Array<RequestInit | undefined> = []
+
+  globalThis.fetch = (async (_input, init) => {
+    calls.push(init)
+    if (calls.length === 1) {
+      throw new Error(
+        'The socket connection was closed unexpectedly. For more information, pass `verbose: true` in the second argument to fetch()',
+      )
+    }
+    return new Response('ok')
+  }) as FetchType
+
+  const response = await fetchWithProxyRetry('https://example.com/search', {
+    method: 'POST',
+  })
+
+  expect(await response.text()).toBe('ok')
+  expect(calls).toHaveLength(2)
+  expect((calls[0] as RequestInit & { proxy?: string }).proxy).toBe(
+    'http://127.0.0.1:15236',
+  )
+  expect((calls[0] as RequestInit).keepalive).toBeUndefined()
+  expect((calls[1] as RequestInit).keepalive).toBe(false)
+})
+
+test('fetchWithProxyRetry does not retry non-network errors', async () => {
+  let attempts = 0
+
+  globalThis.fetch = (async () => {
+    attempts += 1
+    throw new Error('400 bad request')
+  }) as FetchType
+
+  await expect(fetchWithProxyRetry('https://example.com')).rejects.toThrow(
+    '400 bad request',
+  )
+  expect(attempts).toBe(1)
+})

src/services/api/fetchWithProxyRetry.ts

@@ -0,0 +1,44 @@
+import { disableKeepAlive, getProxyFetchOptions } from '../../utils/proxy.js'
+
+const RETRYABLE_FETCH_ERROR_PATTERN =
+  /socket connection was closed unexpectedly|ECONNRESET|EPIPE|socket hang up|Connection reset by peer|fetch failed/i
+
+export function isRetryableFetchError(error: unknown): boolean {
+  if (!(error instanceof Error)) {
+    return false
+  }
+  if (error.name === 'AbortError') {
+    return false
+  }
+  return RETRYABLE_FETCH_ERROR_PATTERN.test(error.message)
+}
+
+export async function fetchWithProxyRetry(
+  input: string | URL | Request,
+  init?: RequestInit,
+  options?: { forAnthropicAPI?: boolean; maxAttempts?: number },
+): Promise<Response> {
+  const maxAttempts = Math.max(1, options?.maxAttempts ?? 2)
+  let lastError: unknown
+
+  for (let attempt = 1; attempt <= maxAttempts; attempt++) {
+    try {
+      return await fetch(input, {
+        ...init,
+        ...getProxyFetchOptions({
+          forAnthropicAPI: options?.forAnthropicAPI,
+        }),
+      })
+    } catch (error) {
+      lastError = error
+      if (attempt >= maxAttempts || !isRetryableFetchError(error)) {
+        throw error
+      }
+      disableKeepAlive()
+    }
+  }
+
+  throw lastError instanceof Error
+    ? lastError
+    : new Error('Fetch failed without an error object')
+}

src/services/api/openaiErrorClassification.test.ts

@@ -0,0 +1,97 @@
+import { expect, test } from 'bun:test'
+
+import {
+  buildOpenAICompatibilityErrorMessage,
+  classifyOpenAIHttpFailure,
+  classifyOpenAINetworkFailure,
+  extractOpenAICategoryMarker,
+  formatOpenAICategoryMarker,
+} from './openaiErrorClassification.js'
+
+test('classifies localhost ECONNREFUSED as connection_refused', () => {
+  const error = Object.assign(new TypeError('fetch failed'), {
+    code: 'ECONNREFUSED',
+  })
+
+  const failure = classifyOpenAINetworkFailure(error, {
+    url: 'http://localhost:11434/v1/chat/completions',
+  })
+
+  expect(failure.category).toBe('connection_refused')
+  expect(failure.retryable).toBe(true)
+  expect(failure.code).toBe('ECONNREFUSED')
+  expect(failure.hint).toContain('local server is running')
+})
+
+test('classifies localhost ENOTFOUND as localhost_resolution_failed', () => {
+  const error = Object.assign(new TypeError('getaddrinfo ENOTFOUND localhost'), {
+    code: 'ENOTFOUND',
+  })
+
+  const failure = classifyOpenAINetworkFailure(error, {
+    url: 'http://localhost:11434/v1/chat/completions',
+  })
+
+  expect(failure.category).toBe('localhost_resolution_failed')
+  expect(failure.retryable).toBe(true)
+  expect(failure.code).toBe('ENOTFOUND')
+  expect(failure.hint).toContain('127.0.0.1')
+})
+
+test('classifies model-not-found 404 responses', () => {
+  const failure = classifyOpenAIHttpFailure({
+    status: 404,
+    body: 'The model qwen2.5-coder:7b was not found',
+  })
+
+  expect(failure.category).toBe('model_not_found')
+  expect(failure.retryable).toBe(false)
+})
+
+test('classifies generic 404 responses as endpoint_not_found', () => {
+  const failure = classifyOpenAIHttpFailure({
+    status: 404,
+    body: 'Not Found',
+  })
+
+  expect(failure.category).toBe('endpoint_not_found')
+  expect(failure.hint).toContain('/v1')
+})
+
+test('classifies context-overflow responses', () => {
+  const failure = classifyOpenAIHttpFailure({
+    status: 500,
+    body: 'request too large: maximum context length exceeded',
+  })
+
+  expect(failure.category).toBe('context_overflow')
+  expect(failure.retryable).toBe(false)
+})
+
+test('classifies tool compatibility failures', () => {
+  const failure = classifyOpenAIHttpFailure({
+    status: 400,
+    body: 'tool_calls are not supported by this model',
+  })
+
+  expect(failure.category).toBe('tool_call_incompatible')
+})
+
+test('embeds and extracts category markers in formatted messages', () => {
+  const marker = formatOpenAICategoryMarker('endpoint_not_found')
+  expect(marker).toBe('[openai_category=endpoint_not_found]')
+
+  const formatted = buildOpenAICompatibilityErrorMessage('OpenAI API error 404: Not Found', {
+    category: 'endpoint_not_found',
+    hint: 'Confirm OPENAI_BASE_URL includes /v1.',
+  })
+
+  expect(formatted).toContain('[openai_category=endpoint_not_found]')
+  expect(formatted).toContain('Hint: Confirm OPENAI_BASE_URL includes /v1.')
+  expect(extractOpenAICategoryMarker(formatted)).toBe('endpoint_not_found')
+})
+
+test('ignores unknown category markers during extraction', () => {
+  const malformed = 'OpenAI API error 500 [openai_category=totally_fake_category]'
+  expect(extractOpenAICategoryMarker(malformed)).toBeUndefined()
+})

src/services/api/openaiErrorClassification.ts

@@ -0,0 +1,352 @@
+export type OpenAICompatibilityFailureCategory =
+  | 'connection_refused'
+  | 'localhost_resolution_failed'
+  | 'request_timeout'
+  | 'network_error'
+  | 'auth_invalid'
+  | 'rate_limited'
+  | 'model_not_found'
+  | 'endpoint_not_found'
+  | 'context_overflow'
+  | 'tool_call_incompatible'
+  | 'malformed_provider_response'
+  | 'provider_unavailable'
+  | 'unknown'
+
+export type OpenAICompatibilityFailure = {
+  source: 'network' | 'http'
+  category: OpenAICompatibilityFailureCategory
+  retryable: boolean
+  message: string
+  hint?: string
+  code?: string
+  status?: number
+}
+
+const OPENAI_CATEGORY_MARKER_PREFIX = '[openai_category='
+
+const LOCALHOST_HOSTNAMES = new Set(['localhost', '127.0.0.1', '::1'])
+
+const OPENAI_COMPATIBILITY_FAILURE_CATEGORIES: ReadonlySet<OpenAICompatibilityFailureCategory> =
+  new Set<OpenAICompatibilityFailureCategory>([
+    'connection_refused',
+    'localhost_resolution_failed',
+    'request_timeout',
+    'network_error',
+    'auth_invalid',
+    'rate_limited',
+    'model_not_found',
+    'endpoint_not_found',
+    'context_overflow',
+    'tool_call_incompatible',
+    'malformed_provider_response',
+    'provider_unavailable',
+    'unknown',
+  ])
+
+function isOpenAICompatibilityFailureCategory(
+  value: string,
+): value is OpenAICompatibilityFailureCategory {
+  return OPENAI_COMPATIBILITY_FAILURE_CATEGORIES.has(
+    value as OpenAICompatibilityFailureCategory,
+  )
+}
+
+function getErrorCode(error: unknown): string | undefined {
+  let current: unknown = error
+  const maxDepth = 5
+
+  for (let depth = 0; depth < maxDepth; depth++) {
+    if (
+      current &&
+      typeof current === 'object' &&
+      'code' in current &&
+      typeof (current as { code?: unknown }).code === 'string'
+    ) {
+      return (current as { code: string }).code
+    }
+
+    if (
+      current &&
+      typeof current === 'object' &&
+      'cause' in current &&
+      (current as { cause?: unknown }).cause !== current
+    ) {
+      current = (current as { cause?: unknown }).cause
+      continue
+    }
+
+    break
+  }
+
+  return undefined
+}
+
+function getHostname(url: string): string | null {
+  try {
+    return new URL(url).hostname.toLowerCase()
+  } catch {
+    return null
+  }
+}
+
+function isLocalhostLikeHostname(hostname: string | null): boolean {
+  if (!hostname) return false
+  if (LOCALHOST_HOSTNAMES.has(hostname)) return true
+  return /^127\./.test(hostname)
+}
+
+function isContextOverflowMessage(body: string): boolean {
+  const lower = body.toLowerCase()
+  return (
+    lower.includes('too many tokens') ||
+    lower.includes('request too large') ||
+    lower.includes('context length') ||
+    lower.includes('maximum context') ||
+    lower.includes('input length') ||
+    lower.includes('payload too large') ||
+    lower.includes('prompt is too long')
+  )
+}
+
+function isToolCompatibilityMessage(body: string): boolean {
+  const lower = body.toLowerCase()
+  return (
+    lower.includes('tool_calls') ||
+    lower.includes('tool_call') ||
+    lower.includes('tool_use') ||
+    lower.includes('tool_result') ||
+    lower.includes('function calling') ||
+    lower.includes('function call')
+  )
+}
+
+function isMalformedProviderResponse(body: string): boolean {
+  const lower = body.toLowerCase()
+  return (
+    lower.includes('<!doctype html') ||
+    lower.includes('<html') ||
+    lower.includes('invalid json') ||
+    lower.includes('malformed') ||
+    lower.includes('unexpected token') ||
+    lower.includes('cannot parse') ||
+    lower.includes('not valid json')
+  )
+}
+
+function isModelNotFoundMessage(body: string): boolean {
+  const lower = body.toLowerCase()
+  return (
+    lower.includes('model') &&
+    (
+      lower.includes('not found') ||
+      lower.includes('does not exist') ||
+      lower.includes('unknown model') ||
+      lower.includes('unavailable model')
+    )
+  )
+}
+
+export function formatOpenAICategoryMarker(
+  category: OpenAICompatibilityFailureCategory,
+): string {
+  return `${OPENAI_CATEGORY_MARKER_PREFIX}${category}]`
+}
+
+export function extractOpenAICategoryMarker(
+  message: string,
+): OpenAICompatibilityFailureCategory | undefined {
+  const match = message.match(/\[openai_category=([a-z_]+)]/)
+  const category = match?.[1]
+
+  if (!category || !isOpenAICompatibilityFailureCategory(category)) {
+    return undefined
+  }
+
+  return category
+}
+
+export function buildOpenAICompatibilityErrorMessage(
+  baseMessage: string,
+  failure: Pick<OpenAICompatibilityFailure, 'category' | 'hint'>,
+): string {
+  const marker = formatOpenAICategoryMarker(failure.category)
+  const hint = failure.hint ? ` Hint: ${failure.hint}` : ''
+  return `${baseMessage} ${marker}${hint}`
+}
+
+export function classifyOpenAINetworkFailure(
+  error: unknown,
+  options: { url: string },
+): OpenAICompatibilityFailure {
+  const message = error instanceof Error ? error.message : String(error)
+  const lowerMessage = message.toLowerCase()
+  const code = getErrorCode(error)
+  const hostname = getHostname(options.url)
+  const isLocalHost = isLocalhostLikeHostname(hostname)
+
+  if (
+    code === 'ETIMEDOUT' ||
+    code === 'UND_ERR_CONNECT_TIMEOUT' ||
+    lowerMessage.includes('timeout') ||
+    lowerMessage.includes('timed out') ||
+    lowerMessage.includes('aborterror')
+  ) {
+    return {
+      source: 'network',
+      category: 'request_timeout',
+      retryable: true,
+      message,
+      code,
+      hint: 'The provider took too long to respond. Check local model load time or increase API timeout.',
+    }
+  }
+
+  if (
+    isLocalHost &&
+    (
+      code === 'ENOTFOUND' ||
+      code === 'EAI_AGAIN' ||
+      lowerMessage.includes('getaddrinfo') ||
+      (code === undefined && lowerMessage.includes('fetch failed'))
+    )
+  ) {
+    return {
+      source: 'network',
+      category: 'localhost_resolution_failed',
+      retryable: true,
+      message,
+      code,
+      hint: 'Localhost failed for this request. Retry with 127.0.0.1 and confirm Ollama is serving on the configured port.',
+    }
+  }
+
+  if (code === 'ECONNREFUSED') {
+    return {
+      source: 'network',
+      category: 'connection_refused',
+      retryable: true,
+      message,
+      code,
+      hint: isLocalHost
+        ? 'Connection to the local provider was refused. Ensure the local server is running and listening on the configured port.'
+        : 'Connection was refused by the provider endpoint. Ensure the server is running and the port is correct.',
+    }
+  }
+
+  return {
+    source: 'network',
+    category: 'network_error',
+    retryable: true,
+    message,
+    code,
+    hint: 'Network transport failed before a provider response was received.',
+  }
+}
+
+export function classifyOpenAIHttpFailure(options: {
+  status: number
+  body: string
+}): OpenAICompatibilityFailure {
+  const body = options.body ?? ''
+
+  if (options.status === 401 || options.status === 403) {
+    return {
+      source: 'http',
+      category: 'auth_invalid',
+      retryable: false,
+      status: options.status,
+      message: body,
+      hint: 'Authentication failed. Verify API key, token source, and endpoint-specific auth headers.',
+    }
+  }
+
+  if (options.status === 429) {
+    return {
+      source: 'http',
+      category: 'rate_limited',
+      retryable: true,
+      status: options.status,
+      message: body,
+      hint: 'Provider rate-limited the request. Retry after backoff.',
+    }
+  }
+
+  if (options.status === 404 && isModelNotFoundMessage(body)) {
+    return {
+      source: 'http',
+      category: 'model_not_found',
+      retryable: false,
+      status: options.status,
+      message: body,
+      hint: 'The selected model is not installed or not available on this endpoint.',
+    }
+  }
+
+  if (options.status === 404) {
+    return {
+      source: 'http',
+      category: 'endpoint_not_found',
+      retryable: false,
+      status: options.status,
+      message: body,
+      hint: 'Endpoint was not found. Confirm OPENAI_BASE_URL includes /v1 for OpenAI-compatible local providers.',
+    }
+  }
+
+  if (
+    options.status === 413 ||
+    ((options.status === 400 || options.status >= 500) &&
+      isContextOverflowMessage(body))
+  ) {
+    return {
+      source: 'http',
+      category: 'context_overflow',
+      retryable: false,
+      status: options.status,
+      message: body,
+      hint: 'Prompt context exceeded model/server limits. Reduce context or increase provider context length.',
+    }
+  }
+
+  if (options.status === 400 && isToolCompatibilityMessage(body)) {
+    return {
+      source: 'http',
+      category: 'tool_call_incompatible',
+      retryable: false,
+      status: options.status,
+      message: body,
+      hint: 'Provider/model rejected tool-calling payload. Retry without tools or use a tool-capable model.',
+    }
+  }
+
+  if (options.status >= 400 && isMalformedProviderResponse(body)) {
+    return {
+      source: 'http',
+      category: 'malformed_provider_response',
+      retryable: false,
+      status: options.status,
+      message: body,
+      hint: 'Provider returned malformed or non-JSON response where JSON was expected.',
+    }
+  }
+
+  if (options.status >= 500) {
+    return {
+      source: 'http',
+      category: 'provider_unavailable',
+      retryable: true,
+      status: options.status,
+      message: body,
+      hint: 'Provider reported a server-side failure. Retry after a short delay.',
+    }
+  }
+
+  return {
+    source: 'http',
+    category: 'unknown',
+    retryable: false,
+    status: options.status,
+    message: body,
+  }
+}

src/services/api/openaiShim.diagnostics.test.ts

@@ -0,0 +1,286 @@
+import { afterEach, expect, mock, test } from 'bun:test'
+
+const originalFetch = globalThis.fetch
+const originalEnv = {
+  OPENAI_BASE_URL: process.env.OPENAI_BASE_URL,
+  OPENAI_API_KEY: process.env.OPENAI_API_KEY,
+  OPENAI_MODEL: process.env.OPENAI_MODEL,
+}
+
+function restoreEnv(key: string, value: string | undefined): void {
+  if (value === undefined) {
+    delete process.env[key]
+  } else {
+    process.env[key] = value
+  }
+}
+
+afterEach(() => {
+  globalThis.fetch = originalFetch
+  restoreEnv('OPENAI_BASE_URL', originalEnv.OPENAI_BASE_URL)
+  restoreEnv('OPENAI_API_KEY', originalEnv.OPENAI_API_KEY)
+  restoreEnv('OPENAI_MODEL', originalEnv.OPENAI_MODEL)
+  mock.restore()
+})
+
+test('logs classified transport diagnostics with category and code', async () => {
+  const debugSpy = mock(() => {})
+  mock.module('../../utils/debug.js', () => ({
+    logForDebugging: debugSpy,
+  }))
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { createOpenAIShimClient } = await import(`./openaiShim.ts?ts=${nonce}`)
+
+  process.env.OPENAI_BASE_URL = 'http://localhost:11434/v1'
+  process.env.OPENAI_API_KEY = 'ollama'
+
+  const transportError = Object.assign(new TypeError('fetch failed'), {
+    code: 'ECONNREFUSED',
+  })
+
+  globalThis.fetch = mock(async () => {
+    throw transportError
+  }) as typeof globalThis.fetch
+
+  const client = createOpenAIShimClient({}) as {
+    beta: {
+      messages: {
+        create: (params: Record<string, unknown>) => Promise<unknown>
+      }
+    }
+  }
+
+  await expect(
+    client.beta.messages.create({
+      model: 'qwen2.5-coder:7b',
+      messages: [{ role: 'user', content: 'hello' }],
+      max_tokens: 64,
+      stream: false,
+    }),
+  ).rejects.toThrow('openai_category=connection_refused')
+
+  const transportLog = debugSpy.mock.calls.find(call =>
+    typeof call?.[0] === 'string' && call[0].includes('transport failure'),
+  )
+
+  expect(transportLog).toBeDefined()
+  expect(String(transportLog?.[0])).toContain('category=connection_refused')
+  expect(String(transportLog?.[0])).toContain('code=ECONNREFUSED')
+  expect(transportLog?.[1]).toEqual({ level: 'warn' })
+})
+
+test('redacts credentials in transport diagnostic URL logs', async () => {
+  const debugSpy = mock(() => {})
+  mock.module('../../utils/debug.js', () => ({
+    logForDebugging: debugSpy,
+  }))
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { createOpenAIShimClient } = await import(`./openaiShim.ts?ts=${nonce}`)
+
+  process.env.OPENAI_BASE_URL = 'http://user:supersecret@localhost:11434/v1'
+  process.env.OPENAI_API_KEY = 'supersecret'
+
+  const transportError = Object.assign(new TypeError('fetch failed'), {
+    code: 'ECONNREFUSED',
+  })
+
+  globalThis.fetch = mock(async () => {
+    throw transportError
+  }) as typeof globalThis.fetch
+
+  const client = createOpenAIShimClient({}) as {
+    beta: {
+      messages: {
+        create: (params: Record<string, unknown>) => Promise<unknown>
+      }
+    }
+  }
+
+  await expect(
+    client.beta.messages.create({
+      model: 'qwen2.5-coder:7b',
+      messages: [{ role: 'user', content: 'hello' }],
+      max_tokens: 64,
+      stream: false,
+    }),
+  ).rejects.toThrow('openai_category=connection_refused')
+
+  const transportLog = debugSpy.mock.calls.find(call =>
+    typeof call?.[0] === 'string' && call[0].includes('transport failure'),
+  )
+
+  expect(transportLog).toBeDefined()
+  const logLine = String(transportLog?.[0])
+  expect(logLine).toContain('url=http://redacted:redacted@localhost:11434/v1/chat/completions')
+  expect(logLine).not.toContain('user:supersecret')
+  expect(logLine).not.toContain('supersecret@')
+})
+test('logs self-heal localhost fallback with redacted from/to URLs', async () => {
+  const debugSpy = mock(() => {})
+  mock.module('../../utils/debug.js', () => ({
+    logForDebugging: debugSpy,
+  }))
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { createOpenAIShimClient } = await import(`./openaiShim.ts?ts=${nonce}`)
+
+  process.env.OPENAI_BASE_URL = 'http://user:supersecret@localhost:11434/v1'
+  process.env.OPENAI_API_KEY = 'supersecret'
+
+  globalThis.fetch = mock(async (input: string | Request) => {
+    const url = typeof input === 'string' ? input : input.url
+    if (url.includes('localhost')) {
+      throw Object.assign(new TypeError('fetch failed'), {
+        code: 'ENOTFOUND',
+      })
+    }
+
+    return new Response(
+      JSON.stringify({
+        id: 'chatcmpl-1',
+        model: 'qwen2.5-coder:7b',
+        choices: [
+          {
+            message: {
+              role: 'assistant',
+              content: 'ok',
+            },
+            finish_reason: 'stop',
+          },
+        ],
+        usage: {
+          prompt_tokens: 5,
+          completion_tokens: 2,
+          total_tokens: 7,
+        },
+      }),
+      {
+        status: 200,
+        headers: {
+          'Content-Type': 'application/json',
+        },
+      },
+    )
+  }) as typeof globalThis.fetch
+
+  const client = createOpenAIShimClient({}) as {
+    beta: {
+      messages: {
+        create: (params: Record<string, unknown>) => Promise<unknown>
+      }
+    }
+  }
+
+  await expect(
+    client.beta.messages.create({
+      model: 'qwen2.5-coder:7b',
+      messages: [{ role: 'user', content: 'hello' }],
+      max_tokens: 64,
+      stream: false,
+    }),
+  ).resolves.toBeDefined()
+
+  const fallbackLog = debugSpy.mock.calls.find(call =>
+    typeof call?.[0] === 'string' &&
+    call[0].includes('self-heal retry reason=localhost_resolution_failed'),
+  )
+
+  expect(fallbackLog).toBeDefined()
+  const logLine = String(fallbackLog?.[0])
+  expect(logLine).toContain('from=http://redacted:redacted@localhost:11434/v1/chat/completions')
+  expect(logLine).toContain('to=http://redacted:redacted@127.0.0.1:11434/v1/chat/completions')
+  expect(logLine).not.toContain('supersecret')
+})
+
+test('logs self-heal toolless retry for local tool-call incompatibility', async () => {
+  const debugSpy = mock(() => {})
+  mock.module('../../utils/debug.js', () => ({
+    logForDebugging: debugSpy,
+  }))
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { createOpenAIShimClient } = await import(`./openaiShim.ts?ts=${nonce}`)
+
+  process.env.OPENAI_BASE_URL = 'http://localhost:11434/v1'
+  process.env.OPENAI_API_KEY = 'ollama'
+
+  let callCount = 0
+  globalThis.fetch = mock(async () => {
+    callCount += 1
+    if (callCount === 1) {
+      return new Response('tool_calls are not supported', {
+        status: 400,
+        headers: {
+          'Content-Type': 'text/plain',
+        },
+      })
+    }
+
+    return new Response(
+      JSON.stringify({
+        id: 'chatcmpl-1',
+        model: 'qwen2.5-coder:7b',
+        choices: [
+          {
+            message: {
+              role: 'assistant',
+              content: 'ok',
+            },
+            finish_reason: 'stop',
+          },
+        ],
+        usage: {
+          prompt_tokens: 7,
+          completion_tokens: 3,
+          total_tokens: 10,
+        },
+      }),
+      {
+        status: 200,
+        headers: {
+          'Content-Type': 'application/json',
+        },
+      },
+    )
+  }) as typeof globalThis.fetch
+
+  const client = createOpenAIShimClient({}) as {
+    beta: {
+      messages: {
+        create: (params: Record<string, unknown>) => Promise<unknown>
+      }
+    }
+  }
+
+  await expect(
+    client.beta.messages.create({
+      model: 'qwen2.5-coder:7b',
+      messages: [{ role: 'user', content: 'hello' }],
+      tools: [
+        {
+          name: 'Read',
+          description: 'Read file',
+          input_schema: {
+            type: 'object',
+            properties: {
+              filePath: { type: 'string' },
+            },
+            required: ['filePath'],
+          },
+        },
+      ],
+      max_tokens: 64,
+      stream: false,
+    }),
+  ).resolves.toBeDefined()
+
+  const fallbackLog = debugSpy.mock.calls.find(call =>
+    typeof call?.[0] === 'string' &&
+    call[0].includes('self-heal retry reason=tool_call_incompatible mode=toolless'),
+  )
+
+  expect(fallbackLog).toBeDefined()
+  expect(fallbackLog?.[1]).toEqual({ level: 'warn' })
+})

src/services/api/openaiShim.test.ts

@@ -2513,7 +2513,7 @@ test('non-streaming: real content takes precedence over reasoning_content', asyn
   ])
 })
 
-test('non-streaming: strips leaked reasoning preamble from assistant content', async () => {
+test('non-streaming: strips <think> tag block from assistant content', async () => {
   globalThis.fetch = (async () => {
     return new Response(
       JSON.stringify({
@@ -2524,7 +2524,7 @@ test('non-streaming: strips leaked reasoning preamble from assistant content', a
             message: {
               role: 'assistant',
               content:
-                'The user just said "hey" - a simple greeting. I should respond briefly and friendly.\n\nHey! How can I help you today?',
+                '<think>user wants a greeting, respond briefly</think>Hey! How can I help you today?',
             },
             finish_reason: 'stop',
           },
@@ -2645,7 +2645,7 @@ test('streaming: thinking block closed before tool call', async () => {
   expect(thinkingStart?.content_block?.type).toBe('thinking')
 })
 
-test('streaming: strips leaked reasoning preamble from assistant content deltas', async () => {
+test('streaming: strips <think> tag block from assistant content deltas', async () => {
   globalThis.fetch = (async () => {
     const chunks = makeStreamChunks([
       {
@@ -2658,7 +2658,7 @@ test('streaming: strips leaked reasoning preamble from assistant content deltas'
             delta: {
               role: 'assistant',
               content:
-                'The user just said "hey" - a simple greeting. I should respond briefly and friendly.\n\nHey! How can I help you today?',
+                '<think>user wants a greeting, respond briefly</think>Hey! How can I help you today?',
             },
             finish_reason: null,
           },
@@ -2700,10 +2700,10 @@ test('streaming: strips leaked reasoning preamble from assistant content deltas'
     }
   }
 
-  expect(textDeltas).toEqual(['Hey! How can I help you today?'])
+  expect(textDeltas.join('')).toBe('Hey! How can I help you today?')
 })
 
-test('streaming: strips leaked reasoning preamble when split across multiple content chunks', async () => {
+test('streaming: strips <think> tag split across multiple content chunks', async () => {
   globalThis.fetch = (async () => {
     const chunks = makeStreamChunks([
       {
@@ -2715,7 +2715,7 @@ test('streaming: strips leaked reasoning preamble when split across multiple con
             index: 0,
             delta: {
               role: 'assistant',
-              content: 'The user said "hey" - this is a simple greeting. ',
+              content: '<think>user wants a greeting,',
             },
             finish_reason: null,
           },
@@ -2729,8 +2729,21 @@ test('streaming: strips leaked reasoning preamble when split across multiple con
           {
             index: 0,
             delta: {
-              content:
+              content: ' respond briefly</th',
-                'I should respond in a friendly, concise way.\n\nHey! How can I help you today?',
+            },
+            finish_reason: null,
+          },
+        ],
+      },
+      {
+        id: 'chatcmpl-1',
+        object: 'chat.completion.chunk',
+        model: 'gpt-5-mini',
+        choices: [
+          {
+            index: 0,
+            delta: {
+              content: 'ink>Hey! How can I help you today?',
             },
             finish_reason: null,
           },
@@ -2773,5 +2786,434 @@ test('streaming: strips leaked reasoning preamble when split across multiple con
     }
   }
 
-  expect(textDeltas).toEqual(['Hey! How can I help you today?'])
+  expect(textDeltas.join('')).toBe('Hey! How can I help you today?')
+})
+
+test('streaming: preserves prose without tags (no phrase-based false positive)', async () => {
+  // Regression: older phrase-based sanitizer would strip "I should..." prose.
+  // The tag-based approach leaves legitimate assistant output alone.
+  globalThis.fetch = (async () => {
+    const chunks = makeStreamChunks([
+      {
+        id: 'chatcmpl-1',
+        object: 'chat.completion.chunk',
+        model: 'gpt-5-mini',
+        choices: [
+          {
+            index: 0,
+            delta: {
+              role: 'assistant',
+              content:
+                'I should note that the user role requires a briefly concise friendly response format.',
+            },
+            finish_reason: null,
+          },
+        ],
+      },
+      {
+        id: 'chatcmpl-1',
+        object: 'chat.completion.chunk',
+        model: 'gpt-5-mini',
+        choices: [
+          {
+            index: 0,
+            delta: {},
+            finish_reason: 'stop',
+          },
+        ],
+      },
+    ])
+
+    return makeSseResponse(chunks)
+  }) as FetchType
+
+  const client = createOpenAIShimClient({}) as OpenAIShimClient
+  const result = await client.beta.messages
+    .create({
+      model: 'gpt-5-mini',
+      system: 'test system',
+      messages: [{ role: 'user', content: 'hey' }],
+      max_tokens: 64,
+      stream: true,
+    })
+    .withResponse()
+
+  const textDeltas: string[] = []
+  for await (const event of result.data) {
+    const delta = (event as { delta?: { type?: string; text?: string } }).delta
+    if (delta?.type === 'text_delta' && typeof delta.text === 'string') {
+      textDeltas.push(delta.text)
+    }
+  }
+
+  expect(textDeltas.join('')).toBe(
+    'I should note that the user role requires a briefly concise friendly response format.',
+  )
+})
+
+test('classifies localhost transport failures with actionable category marker', async () => {
+  process.env.OPENAI_BASE_URL = 'http://localhost:11434/v1'
+
+  const transportError = Object.assign(new TypeError('fetch failed'), {
+    code: 'ECONNREFUSED',
+  })
+
+  globalThis.fetch = (async () => {
+    throw transportError
+  }) as FetchType
+
+  const client = createOpenAIShimClient({}) as OpenAIShimClient
+
+  await expect(
+    client.beta.messages.create({
+      model: 'qwen2.5-coder:7b',
+      messages: [{ role: 'user', content: 'hello' }],
+      max_tokens: 64,
+      stream: false,
+    }),
+  ).rejects.toThrow('openai_category=connection_refused')
+
+  await expect(
+    client.beta.messages.create({
+      model: 'qwen2.5-coder:7b',
+      messages: [{ role: 'user', content: 'hello' }],
+      max_tokens: 64,
+      stream: false,
+    }),
+  ).rejects.toThrow('local server is running')
+})
+
+test('propagates AbortError without wrapping it as transport failure', async () => {
+  process.env.OPENAI_BASE_URL = 'http://localhost:11434/v1'
+
+  const abortError = new DOMException('The operation was aborted.', 'AbortError')
+  globalThis.fetch = (async () => {
+    throw abortError
+  }) as FetchType
+
+  const controller = new AbortController()
+  controller.abort()
+
+  const client = createOpenAIShimClient({}) as OpenAIShimClient
+
+  await expect(
+    client.beta.messages.create(
+      {
+        model: 'qwen2.5-coder:7b',
+        messages: [{ role: 'user', content: 'hello' }],
+        max_tokens: 64,
+        stream: false,
+      },
+      { signal: controller.signal },
+    ),
+  ).rejects.toBe(abortError)
+})
+
+test('classifies chat-completions endpoint 404 failures with endpoint_not_found marker', async () => {
+  process.env.OPENAI_BASE_URL = 'http://localhost:11434'
+
+  globalThis.fetch = (async () =>
+    new Response('Not Found', {
+      status: 404,
+      headers: {
+        'Content-Type': 'text/plain',
+      },
+    })) as FetchType
+
+  const client = createOpenAIShimClient({}) as OpenAIShimClient
+
+  await expect(
+    client.beta.messages.create({
+      model: 'qwen2.5-coder:7b',
+      messages: [{ role: 'user', content: 'hello' }],
+      max_tokens: 64,
+      stream: false,
+    }),
+  ).rejects.toThrow('openai_category=endpoint_not_found')
+})
+test('self-heals localhost resolution failures by retrying local loopback base URL', async () => {
+  process.env.OPENAI_BASE_URL = 'http://localhost:11434/v1'
+
+  const requestUrls: string[] = []
+  globalThis.fetch = (async (input, _init) => {
+    const url = typeof input === 'string' ? input : input.url
+    requestUrls.push(url)
+
+    if (url.includes('localhost')) {
+      const error = Object.assign(new TypeError('fetch failed'), {
+        code: 'ENOTFOUND',
+      })
+      throw error
+    }
+
+    return new Response(
+      JSON.stringify({
+        id: 'chatcmpl-1',
+        model: 'qwen2.5-coder:7b',
+        choices: [
+          {
+            message: {
+              role: 'assistant',
+              content: 'hello from loopback',
+            },
+            finish_reason: 'stop',
+          },
+        ],
+        usage: {
+          prompt_tokens: 4,
+          completion_tokens: 3,
+          total_tokens: 7,
+        },
+      }),
+      {
+        status: 200,
+        headers: {
+          'Content-Type': 'application/json',
+        },
+      },
+    )
+  }) as FetchType
+
+  const client = createOpenAIShimClient({}) as OpenAIShimClient
+
+  await expect(
+    client.beta.messages.create({
+      model: 'qwen2.5-coder:7b',
+      messages: [{ role: 'user', content: 'hello' }],
+      max_tokens: 64,
+      stream: false,
+    }),
+  ).resolves.toBeDefined()
+
+  expect(requestUrls[0]).toBe('http://localhost:11434/v1/chat/completions')
+  expect(requestUrls).toContain('http://127.0.0.1:11434/v1/chat/completions')
+})
+
+test('self-heals local endpoint_not_found by retrying with /v1 base URL', async () => {
+  process.env.OPENAI_BASE_URL = 'http://localhost:11434'
+
+  const requestUrls: string[] = []
+  globalThis.fetch = (async (input, _init) => {
+    const url = typeof input === 'string' ? input : input.url
+    requestUrls.push(url)
+
+    if (url === 'http://localhost:11434/chat/completions') {
+      return new Response('Not Found', {
+        status: 404,
+        headers: {
+          'Content-Type': 'text/plain',
+        },
+      })
+    }
+
+    return new Response(
+      JSON.stringify({
+        id: 'chatcmpl-1',
+        model: 'qwen2.5-coder:7b',
+        choices: [
+          {
+            message: {
+              role: 'assistant',
+              content: 'hello from /v1',
+            },
+            finish_reason: 'stop',
+          },
+        ],
+        usage: {
+          prompt_tokens: 5,
+          completion_tokens: 2,
+          total_tokens: 7,
+        },
+      }),
+      {
+        status: 200,
+        headers: {
+          'Content-Type': 'application/json',
+        },
+      },
+    )
+  }) as FetchType
+
+  const client = createOpenAIShimClient({}) as OpenAIShimClient
+
+  await expect(
+    client.beta.messages.create({
+      model: 'qwen2.5-coder:7b',
+      messages: [{ role: 'user', content: 'hello' }],
+      max_tokens: 64,
+      stream: false,
+    }),
+  ).resolves.toBeDefined()
+
+  expect(requestUrls).toEqual([
+    'http://localhost:11434/chat/completions',
+    'http://localhost:11434/v1/chat/completions',
+  ])
+})
+
+test('self-heals tool-call incompatibility by retrying local Ollama requests without tools', async () => {
+  process.env.OPENAI_BASE_URL = 'http://localhost:11434/v1'
+
+  const requestBodies: Array<Record<string, unknown>> = []
+  globalThis.fetch = (async (_input, init) => {
+    const requestBody = JSON.parse(String(init?.body)) as Record<string, unknown>
+    requestBodies.push(requestBody)
+
+    if (requestBodies.length === 1) {
+      return new Response('tool_calls are not supported', {
+        status: 400,
+        headers: {
+          'Content-Type': 'text/plain',
+        },
+      })
+    }
+
+    return new Response(
+      JSON.stringify({
+        id: 'chatcmpl-1',
+        model: 'qwen2.5-coder:7b',
+        choices: [
+          {
+            message: {
+              role: 'assistant',
+              content: 'fallback without tools',
+            },
+            finish_reason: 'stop',
+          },
+        ],
+        usage: {
+          prompt_tokens: 8,
+          completion_tokens: 4,
+          total_tokens: 12,
+        },
+      }),
+      {
+        status: 200,
+        headers: {
+          'Content-Type': 'application/json',
+        },
+      },
+    )
+  }) as FetchType
+
+  const client = createOpenAIShimClient({}) as OpenAIShimClient
+
+  await expect(
+    client.beta.messages.create({
+      model: 'qwen2.5-coder:7b',
+      messages: [{ role: 'user', content: 'hello' }],
+      tools: [
+        {
+          name: 'Read',
+          description: 'Read a file',
+          input_schema: {
+            type: 'object',
+            properties: {
+              filePath: { type: 'string' },
+            },
+            required: ['filePath'],
+          },
+        },
+      ],
+      max_tokens: 64,
+      stream: false,
+    }),
+  ).resolves.toBeDefined()
+
+  expect(requestBodies).toHaveLength(2)
+  expect(Array.isArray(requestBodies[0]?.tools)).toBe(true)
+  expect(requestBodies[0]?.tool_choice).toBeUndefined()
+  expect(
+    requestBodies[1]?.tools === undefined ||
+      (Array.isArray(requestBodies[1]?.tools) && requestBodies[1]?.tools.length === 0),
+  ).toBe(true)
+  expect(requestBodies[1]?.tool_choice).toBeUndefined()
+})
+
+test('preserves valid tool_result and drops orphan tool_result', async () => {
+  let requestBody: Record<string, unknown> | undefined
+
+  globalThis.fetch = (async (_input, init) => {
+    requestBody = JSON.parse(String(init?.body))
+
+    return new Response(
+      JSON.stringify({
+        id: 'chatcmpl-1',
+        model: 'mistral-large-latest',
+        choices: [
+          {
+            message: {
+              role: 'assistant',
+              content: 'done',
+            },
+            finish_reason: 'stop',
+          },
+        ],
+        usage: {
+          prompt_tokens: 12,
+          completion_tokens: 4,
+          total_tokens: 16,
+        },
+      }),
+      {
+        headers: {
+          'Content-Type': 'application/json',
+        },
+      },
+    )
+  }) as FetchType
+
+  const client = createOpenAIShimClient({}) as OpenAIShimClient
+
+  await client.beta.messages.create({
+    model: 'mistral-large-latest',
+    system: 'test system',
+    messages: [
+      { role: 'user', content: 'Search and then I will interrupt' },
+      {
+        role: 'assistant',
+        content: [
+          {
+            type: 'tool_use',
+            id: 'valid_call_1',
+            name: 'Search',
+            input: { query: 'openclaude' },
+          },
+        ],
+      },
+      {
+        role: 'user',
+        content: [
+          {
+            type: 'tool_result',
+            tool_use_id: 'valid_call_1',
+            content: 'Found it!',
+          },
+          {
+            type: 'tool_result',
+            tool_use_id: 'orphan_call_2',
+            content: 'Interrupted result',
+          },
+          {
+            role: 'user',
+            content: 'What happened?',
+          },
+        ],
+      },
+    ],
+    max_tokens: 64,
+    stream: false,
+  })
+
+  const messages = requestBody?.messages as Array<Record<string, unknown>>
+
+  // Should have: system, user, assistant (tool_use), tool (valid_call_1), user
+  // Should NOT have: tool (orphan_call_2)
+
+  const toolMessages = messages.filter(m => m.role === 'tool')
+  expect(toolMessages.length).toBe(1)
+  expect(toolMessages[0].tool_call_id).toBe('valid_call_1')
+
+  const orphanMessage = toolMessages.find(m => m.tool_call_id === 'orphan_call_2')
+  expect(orphanMessage).toBeUndefined()
 })

src/services/api/openaiShim.ts

@@ -32,10 +32,9 @@ import { resolveGeminiCredential } from '../../utils/geminiAuth.js'
 import { hydrateGeminiAccessTokenFromSecureStorage } from '../../utils/geminiCredentials.js'
 import { hydrateGithubModelsTokenFromSecureStorage } from '../../utils/githubModelsCredentials.js'
 import {
-  looksLikeLeakedReasoningPrefix,
+  createThinkTagFilter,
-  shouldBufferPotentialReasoningPrefix,
+  stripThinkTags,
-  stripLeakedReasoningPreamble,
+} from './thinkTagSanitizer.js'
-} from './reasoningLeakSanitizer.js'
 import {
   codexStreamToAnthropic,
   collectCodexCompletedResponse,
@@ -47,12 +46,20 @@ import {
   type AnthropicUsage,
   type ShimCreateParams,
 } from './codexShim.js'
+import { fetchWithProxyRetry } from './fetchWithProxyRetry.js'
 import {
+  getLocalProviderRetryBaseUrls,
+  getGithubEndpointType,
   isLocalProviderUrl,
   resolveRuntimeCodexCredentials,
   resolveProviderRequest,
-  getGithubEndpointType,
+  shouldAttemptLocalToollessRetry,
 } from './providerConfig.js'
+import {
+  buildOpenAICompatibilityErrorMessage,
+  classifyOpenAIHttpFailure,
+  classifyOpenAINetworkFailure,
+} from './openaiErrorClassification.js'
 import { sanitizeSchemaForOpenAICompat } from '../../utils/schemaSanitizer.js'
 import { redactSecretValueForDisplay } from '../../utils/providerProfile.js'
 import {
@@ -82,6 +89,19 @@ const COPILOT_HEADERS: Record<string, string> = {
   'Copilot-Integration-Id': 'vscode-chat',
 }
 
+const SENSITIVE_URL_QUERY_PARAM_NAMES = [
+  'api_key',
+  'key',
+  'token',
+  'access_token',
+  'refresh_token',
+  'signature',
+  'sig',
+  'secret',
+  'password',
+  'authorization',
+]
+
 function isGithubModelsMode(): boolean {
   return isEnvTruthy(process.env.CLAUDE_CODE_USE_GITHUB)
 }
@@ -131,6 +151,34 @@ function formatRetryAfterHint(response: Response): string {
   return ra ? ` (Retry-After: ${ra})` : ''
 }
 
+function shouldRedactUrlQueryParam(name: string): boolean {
+  const lower = name.toLowerCase()
+  return SENSITIVE_URL_QUERY_PARAM_NAMES.some(token => lower.includes(token))
+}
+
+function redactUrlForDiagnostics(url: string): string {
+  try {
+    const parsed = new URL(url)
+    if (parsed.username) {
+      parsed.username = 'redacted'
+    }
+    if (parsed.password) {
+      parsed.password = 'redacted'
+    }
+
+    for (const key of parsed.searchParams.keys()) {
+      if (shouldRedactUrlQueryParam(key)) {
+        parsed.searchParams.set(key, 'redacted')
+      }
+    }
+
+    const serialized = parsed.toString()
+    return redactSecretValueForDisplay(serialized, process.env as SecretValueSource) ?? serialized
+  } catch {
+    return redactSecretValueForDisplay(url, process.env as SecretValueSource) ?? url
+  }
+}
+
 function sleepMs(ms: number): Promise<void> {
   return new Promise(resolve => setTimeout(resolve, ms))
 }
@@ -302,6 +350,7 @@ function convertMessages(
   system: unknown,
 ): OpenAIMessage[] {
   const result: OpenAIMessage[] = []
+  const knownToolCallIds = new Set<string>()
 
   // System message first
   const sysText = convertSystemPrompt(system)
@@ -321,13 +370,21 @@ function convertMessages(
         const toolResults = content.filter((b: { type?: string }) => b.type === 'tool_result')
         const otherContent = content.filter((b: { type?: string }) => b.type !== 'tool_result')
 
-        // Emit tool results as tool messages
+        // Emit tool results as tool messages, but ONLY if we have a matching tool_use ID.
+        // Mistral/OpenAI strictly require tool messages to follow an assistant message with tool_calls.
+        // If the user interrupted (ESC) and a synthetic tool_result was generated without a recorded tool_use,
+        // emitting it here would cause a "role must alternate" or "unexpected role" error.
         for (const tr of toolResults) {
+          const id = tr.tool_use_id ?? 'unknown'
+          if (knownToolCallIds.has(id)) {
             result.push({
               role: 'tool',
-            tool_call_id: tr.tool_use_id ?? 'unknown',
+              tool_call_id: id,
               content: convertToolResultContent(tr.content, tr.is_error),
             })
+          } else {
+            logForDebugging(`Dropping orphan tool_result for ID: ${id} to prevent API error`)
+          }
         }
 
         // Emit remaining user content
@@ -368,9 +425,11 @@ function convertMessages(
               input?: unknown
               extra_content?: Record<string, unknown>
               signature?: string
-            }, index) => {
+            }) => {
+              const id = tu.id ?? `call_${crypto.randomUUID().replace(/-/g, '')}`
+              knownToolCallIds.add(id)
               const toolCall: NonNullable<OpenAIMessage['tool_calls']>[number] = {
-                id: tu.id ?? `call_${crypto.randomUUID().replace(/-/g, '')}`,
+                id,
                 type: 'function' as const,
                 function: {
                   name: tu.name ?? 'unknown',
@@ -395,7 +454,6 @@ function convertMessages(
 
                 // Merge into existing google-specific metadata if present
                 const existingGoogle = (toolCall.extra_content?.google as Record<string, unknown>) ?? {}
-
                 toolCall.extra_content = {
                   ...toolCall.extra_content,
                   google: {
@@ -550,7 +608,10 @@ function convertTools(
         function: {
           name: t.name,
           description: t.description ?? '',
-          parameters: normalizeSchemaForOpenAI(schema, !isGemini),
+          parameters: normalizeSchemaForOpenAI(
+            schema,
+            !isGemini && !isEnvTruthy(process.env.OPENCLAUDE_DISABLE_STRICT_TOOLS),
+          ),
         },
       }
     })
@@ -658,8 +719,7 @@ async function* openaiStreamToAnthropic(
   let hasEmittedContentStart = false
   let hasEmittedThinkingStart = false
   let hasClosedThinking = false
-  let activeTextBuffer = ''
+  const thinkFilter = createThinkTagFilter()
-  let textBufferMode: 'none' | 'pending' | 'strip' = 'none'
   let lastStopReason: 'tool_use' | 'max_tokens' | 'end_turn' | null = null
   let hasEmittedFinalUsage = false
   let hasProcessedFinishReason = false
@@ -738,14 +798,12 @@ async function* openaiStreamToAnthropic(
   const closeActiveContentBlock = async function* () {
     if (!hasEmittedContentStart) return
 
-    if (textBufferMode !== 'none') {
+    const tail = thinkFilter.flush()
-      const sanitized = stripLeakedReasoningPreamble(activeTextBuffer)
+    if (tail) {
-      if (sanitized) {
       yield {
         type: 'content_block_delta',
         index: contentBlockIndex,
-          delta: { type: 'text_delta', text: sanitized },
+        delta: { type: 'text_delta', text: tail },
-        }
       }
     }
 
@@ -755,8 +813,6 @@ async function* openaiStreamToAnthropic(
     }
     contentBlockIndex++
     hasEmittedContentStart = false
-    activeTextBuffer = ''
-    textBufferMode = 'none'
   }
 
   try {
@@ -813,7 +869,6 @@ async function* openaiStreamToAnthropic(
             contentBlockIndex++
             hasClosedThinking = true
           }
-          activeTextBuffer += delta.content
           if (!hasEmittedContentStart) {
             yield {
               type: 'content_block_start',
@@ -823,38 +878,13 @@ async function* openaiStreamToAnthropic(
             hasEmittedContentStart = true
           }
 
-          if (
+          const visible = thinkFilter.feed(delta.content)
-            textBufferMode === 'strip' ||
+          if (visible) {
-            looksLikeLeakedReasoningPrefix(activeTextBuffer)
-          ) {
-            textBufferMode = 'strip'
-            continue
-          }
-
-          if (textBufferMode === 'pending') {
-            if (shouldBufferPotentialReasoningPrefix(activeTextBuffer)) {
-              continue
-            }
             yield {
               type: 'content_block_delta',
               index: contentBlockIndex,
-              delta: {
+              delta: { type: 'text_delta', text: visible },
-                type: 'text_delta',
-                text: activeTextBuffer,
-              },
             }
-            textBufferMode = 'none'
-            continue
-          }
-
-          if (shouldBufferPotentialReasoningPrefix(activeTextBuffer)) {
-            textBufferMode = 'pending'
-            continue
-          }
-          yield {
-            type: 'content_block_delta',
-            index: contentBlockIndex,
-            delta: { type: 'text_delta', text: delta.content },
           }
         }
 
@@ -1360,8 +1390,12 @@ class OpenAIShimMessages {
       ...filterAnthropicHeaders(options?.headers),
     }
 
-    const isGemini = isEnvTruthy(process.env.CLAUDE_CODE_USE_GEMINI)
+    const isGemini = isGeminiMode()
-    const apiKey = this.providerOverride?.apiKey ?? process.env.OPENAI_API_KEY ?? ''
+    const isMiniMax = !!process.env.MINIMAX_API_KEY
+    const apiKey =
+      this.providerOverride?.apiKey ??
+      process.env.OPENAI_API_KEY ??
+      (isMiniMax ? process.env.MINIMAX_API_KEY : '')
     // Detect Azure endpoints by hostname (not raw URL) to prevent bypass via
     // path segments like https://evil.com/cognitiveservices.azure.com/
     let isAzure = false
@@ -1395,42 +1429,192 @@ class OpenAIShimMessages {
       headers['X-GitHub-Api-Version'] = '2022-11-28'
     }
 
-    // Build the chat completions URL
+    const buildChatCompletionsUrl = (baseUrl: string): string => {
-    // Azure Cognitive Services / Azure OpenAI require a deployment-specific path
+      // Azure Cognitive Services / Azure OpenAI require a deployment-specific
-    // and an api-version query parameter.
+      // path and an api-version query parameter.
-    // Standard format: {base}/openai/deployments/{model}/chat/completions?api-version={version}
-    // Non-Azure: {base}/chat/completions
-    let chatCompletionsUrl: string
       if (isAzure) {
         const apiVersion = process.env.AZURE_OPENAI_API_VERSION ?? '2024-12-01-preview'
         const deployment = request.resolvedModel ?? process.env.OPENAI_MODEL ?? 'gpt-4o'
-      // If base URL already contains /deployments/, use it as-is with api-version
+
-      if (/\/deployments\//i.test(request.baseUrl)) {
+        // If base URL already contains /deployments/, use it as-is with api-version.
-        const base = request.baseUrl.replace(/\/+$/, '')
+        if (/\/deployments\//i.test(baseUrl)) {
-        chatCompletionsUrl = `${base}/chat/completions?api-version=${apiVersion}`
+          const normalizedBase = baseUrl.replace(/\/+$/, '')
-      } else {
+          return `${normalizedBase}/chat/completions?api-version=${apiVersion}`
-        // Strip trailing /v1 or /openai/v1 if present, then build Azure path
-        const base = request.baseUrl.replace(/\/(openai\/)?v1\/?$/, '').replace(/\/+$/, '')
-        chatCompletionsUrl = `${base}/openai/deployments/${deployment}/chat/completions?api-version=${apiVersion}`
-      }
-    } else {
-      chatCompletionsUrl = `${request.baseUrl}/chat/completions`
         }
 
-    const fetchInit = {
+        // Strip trailing /v1 or /openai/v1 if present, then build Azure path.
+        const normalizedBase = baseUrl
+          .replace(/\/(openai\/)?v1\/?$/, '')
+          .replace(/\/+$/, '')
+
+        return `${normalizedBase}/openai/deployments/${deployment}/chat/completions?api-version=${apiVersion}`
+      }
+
+      return `${baseUrl}/chat/completions`
+    }
+
+    const localRetryBaseUrls = isLocal
+      ? getLocalProviderRetryBaseUrls(request.baseUrl)
+      : []
+
+    let activeBaseUrl = request.baseUrl
+    let chatCompletionsUrl = buildChatCompletionsUrl(activeBaseUrl)
+    const attemptedLocalBaseUrls = new Set<string>([activeBaseUrl])
+    let didRetryWithoutTools = false
+
+    const promoteNextLocalBaseUrl = (
+      reason: 'endpoint_not_found' | 'localhost_resolution_failed',
+    ): boolean => {
+      for (const candidateBaseUrl of localRetryBaseUrls) {
+        if (attemptedLocalBaseUrls.has(candidateBaseUrl)) {
+          continue
+        }
+
+        const previousUrl = chatCompletionsUrl
+        attemptedLocalBaseUrls.add(candidateBaseUrl)
+        activeBaseUrl = candidateBaseUrl
+        chatCompletionsUrl = buildChatCompletionsUrl(activeBaseUrl)
+
+        logForDebugging(
+          `[OpenAIShim] self-heal retry reason=${reason} method=POST from=${redactUrlForDiagnostics(previousUrl)} to=${redactUrlForDiagnostics(chatCompletionsUrl)} model=${request.resolvedModel}`,
+          { level: 'warn' },
+        )
+
+        return true
+      }
+
+      return false
+    }
+
+    let serializedBody = JSON.stringify(body)
+
+    const refreshSerializedBody = (): void => {
+      serializedBody = JSON.stringify(body)
+    }
+
+    const buildFetchInit = () => ({
       method: 'POST' as const,
       headers,
-      body: JSON.stringify(body),
+      body: serializedBody,
       signal: options?.signal,
+    })
+
+    const maxSelfHealAttempts = isLocal
+      ? localRetryBaseUrls.length + 1
+      : 0
+    const maxAttempts = (isGithub ? GITHUB_429_MAX_RETRIES : 1) + maxSelfHealAttempts
+
+    const throwClassifiedTransportError = (
+      error: unknown,
+      requestUrl: string,
+      preclassifiedFailure?: ReturnType<typeof classifyOpenAINetworkFailure>,
+    ): never => {
+      if (options?.signal?.aborted) {
+        throw error
+      }
+
+      const failure =
+        preclassifiedFailure ??
+        classifyOpenAINetworkFailure(error, {
+          url: requestUrl,
+        })
+      const redactedUrl = redactUrlForDiagnostics(requestUrl)
+      const safeMessage =
+        redactSecretValueForDisplay(
+          failure.message,
+          process.env as SecretValueSource,
+        ) || 'Request failed'
+
+      logForDebugging(
+        `[OpenAIShim] transport failure category=${failure.category} retryable=${failure.retryable} code=${failure.code ?? 'unknown'} method=POST url=${redactedUrl} model=${request.resolvedModel} message=${safeMessage}`,
+        { level: 'warn' },
+      )
+
+      throw APIError.generate(
+        503,
+        undefined,
+        buildOpenAICompatibilityErrorMessage(
+          `OpenAI API transport error: ${safeMessage}${failure.code ? ` (code=${failure.code})` : ''}`,
+          failure,
+        ),
+        new Headers(),
+      )
+    }
+
+    const throwClassifiedHttpError = (
+      status: number,
+      errorBody: string,
+      parsedBody: object | undefined,
+      responseHeaders: Headers,
+      requestUrl: string,
+      rateHint = '',
+      preclassifiedFailure?: ReturnType<typeof classifyOpenAIHttpFailure>,
+    ): never => {
+      const failure =
+        preclassifiedFailure ??
+        classifyOpenAIHttpFailure({
+          status,
+          body: errorBody,
+        })
+      const redactedUrl = redactUrlForDiagnostics(requestUrl)
+
+      logForDebugging(
+        `[OpenAIShim] request failed category=${failure.category} retryable=${failure.retryable} status=${status} method=POST url=${redactedUrl} model=${request.resolvedModel}`,
+        { level: 'warn' },
+      )
+
+      throw APIError.generate(
+        status,
+        parsedBody,
+        buildOpenAICompatibilityErrorMessage(
+          `OpenAI API error ${status}: ${errorBody}${rateHint}`,
+          failure,
+        ),
+        responseHeaders,
+      )
     }
 
-    const maxAttempts = isGithub ? GITHUB_429_MAX_RETRIES : 1
     let response: Response | undefined
     for (let attempt = 0; attempt < maxAttempts; attempt++) {
-      response = await fetch(chatCompletionsUrl, fetchInit)
+      try {
+        response = await fetchWithProxyRetry(
+          chatCompletionsUrl,
+          buildFetchInit(),
+        )
+      } catch (error) {
+        const isAbortError =
+          options?.signal?.aborted === true ||
+          (typeof DOMException !== 'undefined' &&
+            error instanceof DOMException &&
+            error.name === 'AbortError') ||
+          (typeof error === 'object' &&
+            error !== null &&
+            'name' in error &&
+            error.name === 'AbortError')
+
+        if (isAbortError) {
+          throw error
+        }
+
+        const failure = classifyOpenAINetworkFailure(error, {
+          url: chatCompletionsUrl,
+        })
+
+        if (
+          isLocal &&
+          failure.category === 'localhost_resolution_failed' &&
+          promoteNextLocalBaseUrl('localhost_resolution_failed')
+        ) {
+          continue
+        }
+
+        throwClassifiedTransportError(error, chatCompletionsUrl, failure)
+      }
+
       if (response.ok) {
         return response
       }
+
       if (
         isGithub &&
         response.status === 429 &&
@@ -1500,34 +1684,87 @@ class OpenAIShimMessages {
             }
           }
 
-          const responsesResponse = await fetch(responsesUrl, {
+          let responsesResponse: Response
+          try {
+            responsesResponse = await fetchWithProxyRetry(responsesUrl, {
               method: 'POST',
               headers,
               body: JSON.stringify(responsesBody),
               signal: options?.signal,
             })
+          } catch (error) {
+            throwClassifiedTransportError(error, responsesUrl)
+          }
+
           if (responsesResponse.ok) {
             return responsesResponse
           }
           const responsesErrorBody = await responsesResponse.text().catch(() => 'unknown error')
+          const responsesFailure = classifyOpenAIHttpFailure({
+            status: responsesResponse.status,
+            body: responsesErrorBody,
+          })
           let responsesErrorResponse: object | undefined
           try { responsesErrorResponse = JSON.parse(responsesErrorBody) } catch { /* raw text */ }
-          throw APIError.generate(
+          throwClassifiedHttpError(
             responsesResponse.status,
+            responsesErrorBody,
             responsesErrorResponse,
-            `OpenAI API error ${responsesResponse.status}: ${responsesErrorBody}`,
             responsesResponse.headers,
+            responsesUrl,
+            '',
+            responsesFailure,
           )
         }
       }
 
+      const failure = classifyOpenAIHttpFailure({
+        status: response.status,
+        body: errorBody,
+      })
+
+      if (
+        isLocal &&
+        failure.category === 'endpoint_not_found' &&
+        promoteNextLocalBaseUrl('endpoint_not_found')
+      ) {
+        continue
+      }
+
+      const hasToolsPayload =
+        Array.isArray(body.tools) &&
+        body.tools.length > 0
+
+      if (
+        !didRetryWithoutTools &&
+        failure.category === 'tool_call_incompatible' &&
+        shouldAttemptLocalToollessRetry({
+          baseUrl: activeBaseUrl,
+          hasTools: hasToolsPayload,
+        })
+      ) {
+        didRetryWithoutTools = true
+        delete body.tools
+        delete body.tool_choice
+        refreshSerializedBody()
+
+        logForDebugging(
+          `[OpenAIShim] self-heal retry reason=tool_call_incompatible mode=toolless method=POST url=${redactUrlForDiagnostics(chatCompletionsUrl)} model=${request.resolvedModel}`,
+          { level: 'warn' },
+        )
+        continue
+      }
+
       let errorResponse: object | undefined
       try { errorResponse = JSON.parse(errorBody) } catch { /* raw text */ }
-      throw APIError.generate(
+      throwClassifiedHttpError(
         response.status,
+        errorBody,
         errorResponse,
-        `OpenAI API error ${response.status}: ${errorBody}${rateHint}`,
         response.headers as unknown as Headers,
+        chatCompletionsUrl,
+        rateHint,
+        failure,
       )
     }
 
@@ -1584,7 +1821,7 @@ class OpenAIShimMessages {
     if (typeof rawContent === 'string' && rawContent) {
       content.push({
         type: 'text',
-        text: stripLeakedReasoningPreamble(rawContent),
+        text: stripThinkTags(rawContent),
       })
     } else if (Array.isArray(rawContent) && rawContent.length > 0) {
       const parts: string[] = []
@@ -1602,7 +1839,7 @@ class OpenAIShimMessages {
       if (joined) {
         content.push({
           type: 'text',
-          text: stripLeakedReasoningPreamble(joined),
+          text: stripThinkTags(joined),
         })
       }
     }

src/services/api/providerConfig.envDiagnostics.test.ts

@@ -0,0 +1,107 @@
+import { afterEach, expect, mock, test } from 'bun:test'
+
+const originalEnv = {
+  CLAUDE_CODE_USE_OPENAI: process.env.CLAUDE_CODE_USE_OPENAI,
+  CLAUDE_CODE_USE_MISTRAL: process.env.CLAUDE_CODE_USE_MISTRAL,
+  OPENAI_BASE_URL: process.env.OPENAI_BASE_URL,
+  OPENAI_MODEL: process.env.OPENAI_MODEL,
+  OPENAI_API_BASE: process.env.OPENAI_API_BASE,
+  MISTRAL_BASE_URL: process.env.MISTRAL_BASE_URL,
+  MISTRAL_MODEL: process.env.MISTRAL_MODEL,
+}
+
+function restoreEnv(key: string, value: string | undefined): void {
+  if (value === undefined) {
+    delete process.env[key]
+  } else {
+    process.env[key] = value
+  }
+}
+
+afterEach(() => {
+  restoreEnv('CLAUDE_CODE_USE_OPENAI', originalEnv.CLAUDE_CODE_USE_OPENAI)
+  restoreEnv('CLAUDE_CODE_USE_MISTRAL', originalEnv.CLAUDE_CODE_USE_MISTRAL)
+  restoreEnv('OPENAI_BASE_URL', originalEnv.OPENAI_BASE_URL)
+  restoreEnv('OPENAI_MODEL', originalEnv.OPENAI_MODEL)
+  restoreEnv('OPENAI_API_BASE', originalEnv.OPENAI_API_BASE)
+  restoreEnv('MISTRAL_BASE_URL', originalEnv.MISTRAL_BASE_URL)
+  restoreEnv('MISTRAL_MODEL', originalEnv.MISTRAL_MODEL)
+  mock.restore()
+})
+
+test('logs a warning when OPENAI_BASE_URL is literal undefined', async () => {
+  const debugSpy = mock(() => {})
+  mock.module('../../utils/debug.js', () => ({
+    logForDebugging: debugSpy,
+  }))
+
+  process.env.CLAUDE_CODE_USE_OPENAI = '1'
+  process.env.OPENAI_BASE_URL = 'undefined'
+  process.env.OPENAI_MODEL = 'gpt-4o'
+  delete process.env.OPENAI_API_BASE
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { resolveProviderRequest } = await import(`./providerConfig.ts?ts=${nonce}`)
+
+  const resolved = resolveProviderRequest()
+
+  expect(resolved.baseUrl).toBe('https://api.openai.com/v1')
+
+  const warningCall = debugSpy.mock.calls.find(call =>
+    typeof call?.[0] === 'string' &&
+    call[0].includes('OPENAI_BASE_URL') &&
+    call[0].includes('"undefined"'),
+  )
+
+  expect(warningCall).toBeDefined()
+  expect(warningCall?.[1]).toEqual({ level: 'warn' })
+})
+
+test('does not warn for OPENAI_API_BASE when OPENAI_BASE_URL is active', async () => {
+  const debugSpy = mock(() => {})
+  mock.module('../../utils/debug.js', () => ({
+    logForDebugging: debugSpy,
+  }))
+
+  process.env.CLAUDE_CODE_USE_OPENAI = '1'
+  delete process.env.CLAUDE_CODE_USE_MISTRAL
+  process.env.OPENAI_BASE_URL = 'http://127.0.0.1:11434/v1'
+  process.env.OPENAI_MODEL = 'qwen2.5-coder:7b'
+  process.env.OPENAI_API_BASE = 'undefined'
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { resolveProviderRequest } = await import(`./providerConfig.ts?ts=${nonce}`)
+
+  const resolved = resolveProviderRequest()
+
+  expect(resolved.baseUrl).toBe('http://127.0.0.1:11434/v1')
+
+  const aliasWarning = debugSpy.mock.calls.find(call =>
+    typeof call?.[0] === 'string' &&
+    call[0].includes('OPENAI_API_BASE') &&
+    call[0].includes('"undefined"'),
+  )
+
+  expect(aliasWarning).toBeUndefined()
+})
+
+test('uses OPENAI_API_BASE as fallback in mistral mode when MISTRAL_BASE_URL is unset', async () => {
+  const debugSpy = mock(() => {})
+  mock.module('../../utils/debug.js', () => ({
+    logForDebugging: debugSpy,
+  }))
+
+  delete process.env.CLAUDE_CODE_USE_OPENAI
+  process.env.CLAUDE_CODE_USE_MISTRAL = '1'
+  delete process.env.MISTRAL_BASE_URL
+  process.env.MISTRAL_MODEL = 'mistral-medium-latest'
+  process.env.OPENAI_API_BASE = 'http://127.0.0.1:11434/v1'
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { resolveProviderRequest } = await import(`./providerConfig.ts?ts=${nonce}`)
+
+  const resolved = resolveProviderRequest()
+
+  expect(resolved.baseUrl).toBe('http://127.0.0.1:11434/v1')
+  expect(debugSpy.mock.calls).toHaveLength(0)
+})

src/services/api/providerConfig.local.test.ts

@@ -2,8 +2,10 @@ import { afterEach, expect, test } from 'bun:test'
 
 import {
   getAdditionalModelOptionsCacheScope,
+  getLocalProviderRetryBaseUrls,
   isLocalProviderUrl,
   resolveProviderRequest,
+  shouldAttemptLocalToollessRetry,
 } from './providerConfig.js'
 
 const originalEnv = {
@@ -83,3 +85,42 @@ test('skips local model cache scope for remote openai-compatible providers', ()
 
   expect(getAdditionalModelOptionsCacheScope()).toBeNull()
 })
+
+test('derives local retry base URLs with /v1 and loopback fallback candidates', () => {
+  expect(getLocalProviderRetryBaseUrls('http://localhost:11434')).toEqual([
+    'http://localhost:11434/v1',
+    'http://127.0.0.1:11434',
+    'http://127.0.0.1:11434/v1',
+  ])
+})
+
+test('does not derive local retry base URLs for remote providers', () => {
+  expect(getLocalProviderRetryBaseUrls('https://api.openai.com/v1')).toEqual([])
+})
+
+test('enables local toolless retry for likely Ollama endpoints with tools', () => {
+  expect(
+    shouldAttemptLocalToollessRetry({
+      baseUrl: 'http://localhost:11434/v1',
+      hasTools: true,
+    }),
+  ).toBe(true)
+})
+
+test('disables local toolless retry when no tools are present', () => {
+  expect(
+    shouldAttemptLocalToollessRetry({
+      baseUrl: 'http://localhost:11434/v1',
+      hasTools: false,
+    }),
+  ).toBe(false)
+})
+
+test('disables local toolless retry for non-Ollama local endpoints', () => {
+  expect(
+    shouldAttemptLocalToollessRetry({
+      baseUrl: 'http://localhost:1234/v1',
+      hasTools: true,
+    }),
+  ).toBe(false)
+})

src/services/api/providerConfig.ts

@@ -8,17 +8,20 @@ import {
   readCodexCredentials,
   type CodexCredentialBlob,
 } from '../../utils/codexCredentials.js'
+import { logForDebugging } from '../../utils/debug.js'
 import { isEnvTruthy } from '../../utils/envUtils.js'
 import {
   asTrimmedString,
   parseChatgptAccountId,
 } from './codexOAuthShared.js'
+import { DEFAULT_GEMINI_BASE_URL } from 'src/utils/providerProfile.js'
 
 export const DEFAULT_OPENAI_BASE_URL = 'https://api.openai.com/v1'
 export const DEFAULT_CODEX_BASE_URL = 'https://chatgpt.com/backend-api/codex'
 export const DEFAULT_MISTRAL_BASE_URL = 'https://api.mistral.ai/v1'
 /** Default GitHub Copilot API model when user selects copilot / github:copilot */
 export const DEFAULT_GITHUB_MODELS_API_MODEL = 'gpt-4o'
+const warnedUndefinedEnvNames = new Set<string>()
 
 const CODEX_ALIAS_MODELS: Record<
   string,
@@ -129,7 +132,33 @@ function isPrivateIpv6Address(hostname: string): boolean {
 function asEnvUrl(value: string | undefined): string | undefined {
   if (!value) return undefined
   const trimmed = value.trim()
-  if (!trimmed || trimmed === 'undefined') return undefined
+  if (!trimmed) return undefined
+  if (trimmed === 'undefined') {
+    return undefined
+  }
+  return trimmed
+}
+
+function asNamedEnvUrl(
+  value: string | undefined,
+  envName: string,
+): string | undefined {
+  if (!value) return undefined
+
+  const trimmed = value.trim()
+  if (!trimmed) return undefined
+
+  if (trimmed === 'undefined') {
+    if (!warnedUndefinedEnvNames.has(envName)) {
+      warnedUndefinedEnvNames.add(envName)
+      logForDebugging(
+        `[provider-config] Environment variable ${envName} is the literal string "undefined"; ignoring it.`,
+        { level: 'warn' },
+      )
+    }
+    return undefined
+  }
+
   return trimmed
 }
 
@@ -276,6 +305,101 @@ export function isLocalProviderUrl(baseUrl: string | undefined): boolean {
   }
 }
 
+function trimTrailingSlash(value: string): string {
+  return value.replace(/\/+$/, '')
+}
+
+function normalizePathWithV1(pathname: string): string {
+  const trimmed = trimTrailingSlash(pathname)
+  if (!trimmed || trimmed === '/') {
+    return '/v1'
+  }
+
+  if (trimmed.toLowerCase().endsWith('/v1')) {
+    return trimmed
+  }
+
+  return `${trimmed}/v1`
+}
+
+function isLikelyOllamaEndpoint(baseUrl: string): boolean {
+  try {
+    const parsed = new URL(baseUrl)
+    const hostname = parsed.hostname.toLowerCase()
+    const pathname = parsed.pathname.toLowerCase()
+
+    if (parsed.port === '11434') {
+      return true
+    }
+
+    return (
+      hostname.includes('ollama') ||
+      pathname.includes('ollama')
+    )
+  } catch {
+    return false
+  }
+}
+
+export function getLocalProviderRetryBaseUrls(baseUrl: string): string[] {
+  if (!isLocalProviderUrl(baseUrl)) {
+    return []
+  }
+
+  try {
+    const parsed = new URL(baseUrl)
+    const original = trimTrailingSlash(parsed.toString())
+    const seen = new Set<string>([original])
+    const candidates: string[] = []
+
+    const addCandidate = (hostname: string, pathname: string): void => {
+      const next = new URL(parsed.toString())
+      next.hostname = hostname
+      next.pathname = pathname
+      next.search = ''
+      next.hash = ''
+
+      const normalized = trimTrailingSlash(next.toString())
+      if (seen.has(normalized)) {
+        return
+      }
+
+      seen.add(normalized)
+      candidates.push(normalized)
+    }
+
+    const v1Pathname = normalizePathWithV1(parsed.pathname)
+    if (v1Pathname !== trimTrailingSlash(parsed.pathname)) {
+      addCandidate(parsed.hostname, v1Pathname)
+    }
+
+    const hostname = parsed.hostname.toLowerCase().replace(/^\[|\]$/g, '')
+    if (hostname === 'localhost' || hostname === '::1') {
+      addCandidate('127.0.0.1', parsed.pathname || '/')
+      addCandidate('127.0.0.1', v1Pathname)
+    }
+
+    return candidates
+  } catch {
+    return []
+  }
+}
+
+export function shouldAttemptLocalToollessRetry(options: {
+  baseUrl: string
+  hasTools: boolean
+}): boolean {
+  if (!options.hasTools) {
+    return false
+  }
+
+  if (!isLocalProviderUrl(options.baseUrl)) {
+    return false
+  }
+
+  return isLikelyOllamaEndpoint(options.baseUrl)
+}
+
 export function isCodexBaseUrl(baseUrl: string | undefined): boolean {
   if (!baseUrl) return false
   try {
@@ -353,23 +477,55 @@ export function resolveProviderRequest(options?: {
 }): ResolvedProviderRequest {
   const isGithubMode = isEnvTruthy(process.env.CLAUDE_CODE_USE_GITHUB)
   const isMistralMode = isEnvTruthy(process.env.CLAUDE_CODE_USE_MISTRAL)
+  const isGeminiMode = isEnvTruthy(process.env.CLAUDE_CODE_USE_GEMINI)
   const requestedModel =
     options?.model?.trim() ||
     (isMistralMode
       ? process.env.MISTRAL_MODEL?.trim()
       : process.env.OPENAI_MODEL?.trim()) ||
+    (isGeminiMode
+      ? process.env.GEMINI_MODEL?.trim()
+      : process.env.OPENAI_MODEL?.trim()) ||
     options?.fallbackModel?.trim() ||
     (isGithubMode ? 'github:copilot' : 'gpt-4o')
   const descriptor = parseModelDescriptor(requestedModel)
   const explicitBaseUrl = asEnvUrl(options?.baseUrl)
+
+  const normalizedMistralEnvBaseUrl = asNamedEnvUrl(
+    process.env.MISTRAL_BASE_URL,
+    'MISTRAL_BASE_URL',
+  )
+
+  const normalizedGeminiEnvBaseUrl = asNamedEnvUrl(
+    process.env.GEMINI_BASE_URL,
+    'GEMINI_BASE_URL',
+  )
+
+  const primaryEnvBaseUrl = isMistralMode
+    ? normalizedMistralEnvBaseUrl
+    : isGeminiMode
+    ? normalizedGeminiEnvBaseUrl
+    : asNamedEnvUrl(process.env.OPENAI_BASE_URL, 'OPENAI_BASE_URL')
+
+  // In Mistral mode, a literal "undefined" MISTRAL_BASE_URL is treated as
+  // misconfiguration and falls back to OPENAI_API_BASE, then
+  // DEFAULT_MISTRAL_BASE_URL for a safe default endpoint.
+  const fallbackEnvBaseUrl = isMistralMode
+    ? (primaryEnvBaseUrl === undefined
+      ? asNamedEnvUrl(process.env.OPENAI_API_BASE, 'OPENAI_API_BASE') ?? DEFAULT_MISTRAL_BASE_URL
+      : undefined)
+    : isGeminiMode
+    ? (primaryEnvBaseUrl === undefined
+      ? asNamedEnvUrl(process.env.OPENAI_API_BASE, 'OPENAI_API_BASE') ?? DEFAULT_GEMINI_BASE_URL
+      : undefined)
+    : (primaryEnvBaseUrl === undefined
+      ? asNamedEnvUrl(process.env.OPENAI_API_BASE, 'OPENAI_API_BASE')
+      : undefined)
+
   const envBaseUrlRaw =
     explicitBaseUrl ??
-    asEnvUrl(
+    primaryEnvBaseUrl ??
-      isMistralMode
+    fallbackEnvBaseUrl
-        ? (process.env.MISTRAL_BASE_URL ?? DEFAULT_MISTRAL_BASE_URL)
-        : process.env.OPENAI_BASE_URL
-    ) ??
-    asEnvUrl(process.env.OPENAI_API_BASE)
 
   const isCodexModelForGithub = isGithubMode && isCodexAlias(requestedModel)
   const envBaseUrl =

src/services/api/reasoningLeakSanitizer.test.ts

@@ -1,46 +0,0 @@
-import { describe, expect, test } from 'bun:test'
-
-import {
-  looksLikeLeakedReasoningPrefix,
-  shouldBufferPotentialReasoningPrefix,
-  stripLeakedReasoningPreamble,
-} from './reasoningLeakSanitizer.ts'
-
-describe('reasoning leak sanitizer', () => {
-  test('strips explicit internal reasoning preambles', () => {
-    const text =
-      'The user just said "hey" - a simple greeting. I should respond briefly and friendly.\n\nHey! How can I help you today?'
-
-    expect(looksLikeLeakedReasoningPrefix(text)).toBe(true)
-    expect(stripLeakedReasoningPreamble(text)).toBe(
-      'Hey! How can I help you today?',
-    )
-  })
-
-  test('does not strip normal user-facing advice that mentions "the user should"', () => {
-    const text =
-      'The user should reset their password immediately.\n\nHere are the steps...'
-
-    expect(looksLikeLeakedReasoningPrefix(text)).toBe(false)
-    expect(shouldBufferPotentialReasoningPrefix(text)).toBe(false)
-    expect(stripLeakedReasoningPreamble(text)).toBe(text)
-  })
-
-  test('does not strip legitimate first-person advice about responding to an incident', () => {
-    const text =
-      'I need to respond to this security incident immediately. The system is compromised.\n\nHere are the remediation steps...'
-
-    expect(looksLikeLeakedReasoningPrefix(text)).toBe(false)
-    expect(shouldBufferPotentialReasoningPrefix(text)).toBe(false)
-    expect(stripLeakedReasoningPreamble(text)).toBe(text)
-  })
-
-  test('does not strip legitimate first-person advice about answering a support ticket', () => {
-    const text =
-      'I need to answer the support ticket before end of day. The customer is waiting.\n\nHere is the response I drafted...'
-
-    expect(looksLikeLeakedReasoningPrefix(text)).toBe(false)
-    expect(shouldBufferPotentialReasoningPrefix(text)).toBe(false)
-    expect(stripLeakedReasoningPreamble(text)).toBe(text)
-  })
-})

src/services/api/reasoningLeakSanitizer.ts

@@ -1,54 +0,0 @@
-const EXPLICIT_REASONING_START_RE =
-  /^\s*(i should\b|i need to\b|let me think\b|the task\b|the request\b)/i
-
-const EXPLICIT_REASONING_META_RE =
-  /\b(user|request|question|prompt|message|task|greeting|small talk|briefly|friendly|concise)\b/i
-
-const USER_META_START_RE =
-  /^\s*the user\s+(just\s+)?(said|asked|is asking|wants|wanted|mentioned|seems|appears)\b/i
-
-const USER_REASONING_RE =
-  /^\s*the user\s+(just\s+)?(said|asked|is asking|wants|wanted|mentioned|seems|appears)\b[\s\S]*\b(i should|i need to|let me think|respond|reply|answer|greeting|small talk|briefly|friendly|concise)\b/i
-
-export function shouldBufferPotentialReasoningPrefix(text: string): boolean {
-  const normalized = text.trim()
-  if (!normalized) return false
-
-  if (looksLikeLeakedReasoningPrefix(normalized)) {
-    return true
-  }
-
-  const hasParagraphBoundary = /\n\s*\n/.test(normalized)
-  if (hasParagraphBoundary) {
-    return false
-  }
-
-  return (
-    EXPLICIT_REASONING_START_RE.test(normalized) ||
-    USER_META_START_RE.test(normalized)
-  )
-}
-
-export function looksLikeLeakedReasoningPrefix(text: string): boolean {
-  const normalized = text.trim()
-  if (!normalized) return false
-  return (
-    (EXPLICIT_REASONING_START_RE.test(normalized) &&
-      EXPLICIT_REASONING_META_RE.test(normalized)) ||
-    USER_REASONING_RE.test(normalized)
-  )
-}
-
-export function stripLeakedReasoningPreamble(text: string): string {
-  const normalized = text.replace(/\r\n/g, '\n')
-  const parts = normalized.split(/\n\s*\n/)
-  if (parts.length < 2) return text
-
-  const first = parts[0]?.trim() ?? ''
-  if (!looksLikeLeakedReasoningPrefix(first)) {
-    return text
-  }
-
-  const remainder = parts.slice(1).join('\n\n').trim()
-  return remainder || text
-}

src/services/api/thinkTagSanitizer.test.ts

@@ -0,0 +1,183 @@
+import { describe, expect, test } from 'bun:test'
+
+import {
+  createThinkTagFilter,
+  stripThinkTags,
+} from './thinkTagSanitizer.ts'
+
+describe('stripThinkTags — whole-text cleanup', () => {
+  test('strips closed think pair', () => {
+    expect(stripThinkTags('<think>reasoning</think>Hello')).toBe('Hello')
+  })
+
+  test('strips closed thinking pair', () => {
+    expect(stripThinkTags('<thinking>x</thinking>Out')).toBe('Out')
+  })
+
+  test('strips closed reasoning pair', () => {
+    expect(stripThinkTags('<reasoning>x</reasoning>Out')).toBe('Out')
+  })
+
+  test('strips REASONING_SCRATCHPAD pair', () => {
+    expect(stripThinkTags('<REASONING_SCRATCHPAD>plan</REASONING_SCRATCHPAD>Answer'))
+      .toBe('Answer')
+  })
+
+  test('is case-insensitive', () => {
+    expect(stripThinkTags('<THINKING>x</THINKING>out')).toBe('out')
+    expect(stripThinkTags('<Think>x</Think>out')).toBe('out')
+  })
+
+  test('handles attributes on open tag', () => {
+    expect(stripThinkTags('<think id="plan-1">reason</think>ok')).toBe('ok')
+  })
+
+  test('strips unterminated open tag at block boundary', () => {
+    expect(stripThinkTags('<think>reasoning that never closes')).toBe('')
+  })
+
+  test('strips unterminated open tag after newline', () => {
+    // Block-boundary match consumes the leading newline, same as hermes.
+    expect(stripThinkTags('Answer: 42\n<think>second-guess myself'))
+      .toBe('Answer: 42')
+  })
+
+  test('strips orphan close tag', () => {
+    expect(stripThinkTags('trailing </think>done')).toBe('trailing done')
+  })
+
+  test('strips multiple blocks', () => {
+    expect(stripThinkTags('<think>a</think>B<think>c</think>D')).toBe('BD')
+  })
+
+  test('handles reasoning mid-response after content', () => {
+    expect(stripThinkTags('Answer: 42\n<think>double-check</think>\nDone'))
+      .toBe('Answer: 42\n\nDone')
+  })
+
+  test('handles nested-looking tags (lazy match + orphan cleanup)', () => {
+    expect(stripThinkTags('<think><think>x</think></think>y')).toBe('y')
+  })
+
+  test('preserves legitimate non-think tags', () => {
+    expect(stripThinkTags('use <div> and <span>')).toBe('use <div> and <span>')
+  })
+
+  test('preserves text without any tags', () => {
+    expect(stripThinkTags('Hello, world. I should respond briefly.')).toBe(
+      'Hello, world. I should respond briefly.',
+    )
+  })
+
+  test('handles empty input', () => {
+    expect(stripThinkTags('')).toBe('')
+  })
+})
+
+describe('createThinkTagFilter — streaming state machine', () => {
+  test('passes through plain text', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('Hello, ')).toBe('Hello, ')
+    expect(f.feed('world!')).toBe('world!')
+    expect(f.flush()).toBe('')
+  })
+
+  test('strips a complete think block in one chunk', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('pre<think>reason</think>post')).toBe('prepost')
+    expect(f.flush()).toBe('')
+  })
+
+  test('handles open tag split across deltas', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('before<th')).toBe('before')
+    expect(f.feed('ink>reason</think>after')).toBe('after')
+    expect(f.flush()).toBe('')
+  })
+
+  test('handles close tag split across deltas', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('<think>reason</th')).toBe('')
+    expect(f.feed('ink>keep')).toBe('keep')
+    expect(f.flush()).toBe('')
+  })
+
+  test('handles tag split on bare < boundary', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('leading <')).toBe('leading ')
+    expect(f.feed('think>inner</think>tail')).toBe('tail')
+    expect(f.flush()).toBe('')
+  })
+
+  test('preserves partial non-tag < at boundary when next char rules it out', () => {
+    const f = createThinkTagFilter()
+    // "<d" — 'd' cannot start any of our tag names, so emit immediately
+    expect(f.feed('pre<d')).toBe('pre<d')
+    expect(f.feed('iv>rest')).toBe('iv>rest')
+    expect(f.flush()).toBe('')
+  })
+
+  test('case-insensitive streaming', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('<THINKING>x</THINKING>out')).toBe('out')
+    expect(f.flush()).toBe('')
+  })
+
+  test('unterminated open tag — flush drops remainder', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('<think>reasoning with no close ')).toBe('')
+    expect(f.feed('and more reasoning')).toBe('')
+    expect(f.flush()).toBe('')
+    expect(f.isInsideBlock()).toBe(false)
+  })
+
+  test('multiple blocks in single feed', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('<think>a</think>B<think>c</think>D')).toBe('BD')
+    expect(f.flush()).toBe('')
+  })
+
+  test('flush after clean stream emits nothing extra', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('complete message')).toBe('complete message')
+    expect(f.flush()).toBe('')
+  })
+
+  test('flush of bare < at end emits it (not a tag prefix)', () => {
+    const f = createThinkTagFilter()
+    // bare '<' held back; flush emits it since it has no tag-name chars
+    expect(f.feed('x <')).toBe('x ')
+    expect(f.flush()).toBe('<')
+  })
+
+  test('flush of partial tag-name prefix at end drops it', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('x <thi')).toBe('x ')
+    expect(f.flush()).toBe('')
+  })
+
+  test('handles attributes on streaming open tag', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('<think type="plan">reason</think>ok')).toBe('ok')
+    expect(f.flush()).toBe('')
+  })
+
+  test('mid-delta transition: content, reasoning, content', () => {
+    const f = createThinkTagFilter()
+    expect(f.feed('Answer: 42\n<think>')).toBe('Answer: 42\n')
+    expect(f.feed('double-check')).toBe('')
+    expect(f.feed('</think>\nDone')).toBe('\nDone')
+    expect(f.flush()).toBe('')
+  })
+
+  test('orphan close tag mid-stream is stripped on flush via safety-net behavior', () => {
+    // Filter alone treats orphan close as "we're not inside", so it emits as-is.
+    // Safety net (stripThinkTags on final text) removes orphans.
+    const f = createThinkTagFilter()
+    const chunk1 = f.feed('trailing ')
+    const chunk2 = f.feed('</think>done')
+    const final = chunk1 + chunk2 + f.flush()
+    // Orphan close appears in stream output; safety net cleans it
+    expect(stripThinkTags(final)).toBe('trailing done')
+  })
+})

src/services/api/thinkTagSanitizer.ts

@@ -0,0 +1,162 @@
+/**
+ * Think-tag sanitizer for reasoning content leaks.
+ *
+ * Some OpenAI-compatible reasoning models (MiniMax M2.7, GLM-4.5/5, DeepSeek, Kimi K2,
+ * self-hosted vLLM builds) emit chain-of-thought inline inside the `content` field using
+ * XML-like tags instead of the separate `reasoning_content` channel. Example:
+ *
+ *   <think>the user wants foo, let me check bar</think>Here is the answer: ...
+ *
+ * This module strips those blocks structurally (tag-based), independent of English
+ * phrasings. Three layers:
+ *
+ *   1. `createThinkTagFilter()` — streaming state machine. Feeds deltas, emits only
+ *      the visible (non-reasoning) portion, and buffers partial tags across chunk
+ *      boundaries so `</th` + `ink>` still parses correctly.
+ *
+ *   2. `stripThinkTags()` — whole-text cleanup. Removes closed pairs, unterminated
+ *      opens at block boundaries, and orphan open/close tags. Used for non-streaming
+ *      responses and as a safety net after stream close.
+ *
+ *   3. Flush discards buffered partial tags at stream end (false-negative bias —
+ *      prefer losing a partial reasoning fragment over leaking it).
+ */
+
+const TAG_NAMES = [
+  'think',
+  'thinking',
+  'reasoning',
+  'thought',
+  'reasoning_scratchpad',
+] as const
+
+const TAG_ALT = TAG_NAMES.join('|')
+
+const OPEN_TAG_RE = new RegExp(`<\\s*(?:${TAG_ALT})\\b[^>]*>`, 'i')
+const CLOSE_TAG_RE = new RegExp(`<\\s*/\\s*(?:${TAG_ALT})\\s*>`, 'i')
+
+const CLOSED_PAIR_RE_G = new RegExp(
+  `<\\s*(${TAG_ALT})\\b[^>]*>[\\s\\S]*?<\\s*/\\s*\\1\\s*>`,
+  'gi',
+)
+const UNTERMINATED_OPEN_RE = new RegExp(
+  `(?:^|\\n)[ \\t]*<\\s*(?:${TAG_ALT})\\b[^>]*>[\\s\\S]*$`,
+  'i',
+)
+const ORPHAN_TAG_RE_G = new RegExp(
+  `<\\s*/?\\s*(?:${TAG_ALT})\\b[^>]*>\\s*`,
+  'gi',
+)
+
+const MAX_PARTIAL_TAG = 64
+
+/**
+ * Remove reasoning/thinking blocks from a complete text body.
+ *
+ * Handles:
+ *   - Closed pairs: <think>...</think> (lazy match, anywhere in text)
+ *   - Unterminated open tags at a block boundary: strips from the tag to end of string
+ *   - Orphan open or close tags (no matching partner)
+ *
+ * False-negative bias: prefers leaving a few tag characters in rare edge cases over
+ * stripping legitimate content.
+ */
+export function stripThinkTags(text: string): string {
+  if (!text) return text
+  let out = text
+  out = out.replace(CLOSED_PAIR_RE_G, '')
+  out = out.replace(UNTERMINATED_OPEN_RE, '')
+  out = out.replace(ORPHAN_TAG_RE_G, '')
+  return out
+}
+
+export interface ThinkTagFilter {
+  feed(chunk: string): string
+  flush(): string
+  isInsideBlock(): boolean
+}
+
+/**
+ * Streaming state machine. Feed deltas, emits visible (non-reasoning) text.
+ * Handles tags split across chunk boundaries by holding back a short tail buffer
+ * whenever the current buffer ends with what looks like a partial tag.
+ */
+export function createThinkTagFilter(): ThinkTagFilter {
+  let inside = false
+  let buffer = ''
+
+  function findPartialTagStart(s: string): number {
+    const lastLt = s.lastIndexOf('<')
+    if (lastLt === -1) return -1
+    if (s.indexOf('>', lastLt) !== -1) return -1
+    const tail = s.slice(lastLt)
+    if (tail.length > MAX_PARTIAL_TAG) return -1
+
+    const m = /^<\s*\/?\s*([a-zA-Z_]\w*)?\s*$/.exec(tail)
+    if (!m) return -1
+    const partialName = (m[1] ?? '').toLowerCase()
+    if (!partialName) return lastLt
+    if (TAG_NAMES.some(name => name.startsWith(partialName))) return lastLt
+    return -1
+  }
+
+  function feed(chunk: string): string {
+    if (!chunk) return ''
+    buffer += chunk
+    let out = ''
+
+    while (buffer.length > 0) {
+      if (!inside) {
+        const open = OPEN_TAG_RE.exec(buffer)
+        if (open) {
+          out += buffer.slice(0, open.index)
+          buffer = buffer.slice(open.index + open[0].length)
+          inside = true
+          continue
+        }
+
+        const partialStart = findPartialTagStart(buffer)
+        if (partialStart === -1) {
+          out += buffer
+          buffer = ''
+        } else {
+          out += buffer.slice(0, partialStart)
+          buffer = buffer.slice(partialStart)
+        }
+        return out
+      }
+
+      const close = CLOSE_TAG_RE.exec(buffer)
+      if (close) {
+        buffer = buffer.slice(close.index + close[0].length)
+        inside = false
+        continue
+      }
+
+      const partialStart = findPartialTagStart(buffer)
+      if (partialStart === -1) {
+        buffer = ''
+      } else {
+        buffer = buffer.slice(partialStart)
+      }
+      return out
+    }
+
+    return out
+  }
+
+  function flush(): string {
+    const held = buffer
+    const wasInside = inside
+    buffer = ''
+    inside = false
+
+    if (wasInside) return ''
+    if (!held) return ''
+
+    if (/^<\s*\/?\s*[a-zA-Z_]/.test(held)) return ''
+    return held
+  }
+
+  return { feed, flush, isInsideBlock: () => inside }
+}

src/services/autoFix/autoFixRunner.test.ts

@@ -70,7 +70,7 @@ describe('runAutoFixCheck', () => {
 
   test('handles timeout gracefully', async () => {
     const result = await runAutoFixCheck({
-      lint: 'sleep 10',
+      lint: 'node -e "setTimeout(() => {}, 10000)"',
       timeout: 100,
 
       cwd: '/tmp',

src/services/autoFix/autoFixRunner.ts

@@ -46,14 +46,31 @@ async function runCommand(
 
     const killTree = () => {
       try {
-        if (!isWindows && proc.pid) {
+        if (isWindows && proc.pid) {
+          // shell=true on Windows can leave child commands running unless we
+          // terminate the full process tree.
+          const killer = spawn('taskkill', ['/pid', String(proc.pid), '/T', '/F'], {
+            windowsHide: true,
+            stdio: 'ignore',
+          })
+          killer.unref()
+          return
+        }
+
+        if (proc.pid) {
           // Kill the entire process group
           process.kill(-proc.pid, 'SIGTERM')
-        } else {
+          return
-          proc.kill('SIGTERM')
         }
+
+        proc.kill('SIGTERM')
       } catch {
-        // Process may have already exited
+        // Process may have already exited; fallback to direct child kill.
+        try {
+          proc.kill('SIGTERM')
+        } catch {
+          // Ignore final fallback errors.
+        }
       }
     }
 

src/services/compact/autoCompact.ts

@@ -110,9 +110,14 @@ export function calculateTokenWarningState(
     ? autoCompactThreshold
     : getEffectiveContextWindowSize(model)
 
+  // Use the raw context window (without output reservation) for the percentage
+  // display, so users see remaining context relative to the model's full capacity.
+  // The threshold (which subtracts buffer) should only affect when we warn/compact,
+  // not what percentage we display.
+  const rawContextWindow = getContextWindowForModel(model, getSdkBetas())
   const percentLeft = Math.max(
     0,
-    Math.round(((threshold - tokenUsage) / threshold) * 100),
+    Math.round(((rawContextWindow - tokenUsage) / rawContextWindow) * 100),
   )
 
   const warningThreshold = threshold - WARNING_THRESHOLD_BUFFER_TOKENS

src/services/diagnosticTracking.test.ts

@@ -0,0 +1,152 @@
+import { describe, test, expect, beforeEach, afterEach } from 'bun:test'
+import { DiagnosticTrackingService } from './diagnosticTracking.js'
+import type { MCPServerConnection } from './mcp/types.js'
+
+// Mock the IDE client utility
+const mockGetConnectedIdeClient = (clients: MCPServerConnection[]) => 
+  clients.find(client => client.type === 'connected')
+
+describe('DiagnosticTrackingService', () => {
+  let service: DiagnosticTrackingService
+  let mockClients: MCPServerConnection[]
+  let mockIdeClient: MCPServerConnection
+
+  beforeEach(() => {
+    // Get fresh instance for each test
+    service = DiagnosticTrackingService.getInstance()
+    
+    // Setup mock clients
+    mockIdeClient = {
+      type: 'connected',
+      name: 'test-ide',
+      capabilities: {},
+      config: {},
+      cleanup: async () => {},
+      client: {
+        request: async () => ({}),
+        setNotificationHandler: () => {},
+        close: async () => {},
+      },
+    } as unknown as MCPServerConnection
+
+    mockClients = [
+      { type: 'disconnected', name: 'test-disconnected', config: {} } as unknown as MCPServerConnection,
+      mockIdeClient,
+    ]
+  })
+
+  afterEach(async () => {
+    await service.shutdown()
+  })
+
+  describe('handleQueryStart', () => {
+    test('should store MCP clients and initialize service', async () => {
+      await service.handleQueryStart(mockClients)
+
+      // Service should be initialized
+      expect(service).toBeDefined()
+
+      // Should be able to get IDE client from stored clients
+      // We can't directly test private methods, but we can test the behavior
+      const result = await service.getNewDiagnosticsCompat()
+      expect(result).toEqual([]) // Should return empty when no diagnostics
+    })
+
+    test('should reset service if already initialized', async () => {
+      // Initialize first
+      await service.handleQueryStart(mockClients)
+      
+      // Call again - should reset without error
+      await service.handleQueryStart(mockClients)
+      
+      // Should still work
+      const result = await service.getNewDiagnosticsCompat()
+      expect(result).toEqual([])
+    })
+  })
+
+  describe('backward-compatible methods', () => {
+    beforeEach(async () => {
+      await service.handleQueryStart(mockClients)
+    })
+
+    test('beforeFileEditedCompat should work without explicit client', async () => {
+      // Should not throw error and should return undefined when no IDE client
+      const result = await service.beforeFileEditedCompat('/test/file.ts')
+      expect(result).toBeUndefined()
+    })
+
+    test('getNewDiagnosticsCompat should work without explicit client', async () => {
+      const result = await service.getNewDiagnosticsCompat()
+      expect(Array.isArray(result)).toBe(true)
+    })
+
+    test('ensureFileOpenedCompat should work without explicit client', async () => {
+      const result = await service.ensureFileOpenedCompat('/test/file.ts')
+      expect(result).toBeUndefined()
+    })
+  })
+
+  describe('new explicit client methods', () => {
+    test('beforeFileEdited should require client parameter', async () => {
+      // Should not work without client
+      const result = await service.beforeFileEdited('/test/file.ts', undefined as any)
+      expect(result).toBeUndefined()
+    })
+
+    test('getNewDiagnostics should require client parameter', async () => {
+      // Should not work without client
+      const result = await service.getNewDiagnostics(undefined as any)
+      expect(result).toEqual([])
+    })
+
+    test('ensureFileOpened should require client parameter', async () => {
+      // Should not work without client
+      const result = await service.ensureFileOpened('/test/file.ts', undefined as any)
+      expect(result).toBeUndefined()
+    })
+  })
+
+  describe('shutdown', () => {
+    test('should clear stored clients on shutdown', async () => {
+      await service.handleQueryStart(mockClients)
+      
+      // Verify service is working
+      const beforeResult = await service.getNewDiagnosticsCompat()
+      expect(Array.isArray(beforeResult)).toBe(true)
+      
+      // Shutdown
+      await service.shutdown()
+      
+      // After shutdown, compat methods should return empty results
+      const afterResult = await service.getNewDiagnosticsCompat()
+      expect(afterResult).toEqual([])
+    })
+  })
+
+  describe('integration with existing functionality', () => {
+    test('should maintain existing diagnostic tracking behavior', async () => {
+      await service.handleQueryStart(mockClients)
+      
+      // Test baseline tracking
+      await service.beforeFileEditedCompat('/test/file.ts')
+      
+      // Test getting new diagnostics (should be empty since no IDE client is actually connected)
+      const newDiagnostics = await service.getNewDiagnosticsCompat()
+      expect(Array.isArray(newDiagnostics)).toBe(true)
+    })
+
+    test('should handle missing IDE client gracefully', async () => {
+      // Test with no connected clients
+      const noIdeClients = [
+        { type: 'disconnected', name: 'test-disconnected-2', config: {} } as unknown as MCPServerConnection,
+      ]
+      
+      await service.handleQueryStart(noIdeClients)
+      
+      // Should handle gracefully
+      const result = await service.getNewDiagnosticsCompat()
+      expect(result).toEqual([])
+    })
+  })
+})

src/services/diagnosticTracking.ts

@@ -32,7 +32,7 @@ export class DiagnosticTrackingService {
   private baseline: Map<string, Diagnostic[]> = new Map()
 
   private initialized = false
-  private mcpClient: MCPServerConnection | undefined
+  private currentMcpClients: MCPServerConnection[] = []
 
   // Track when files were last processed/fetched
   private lastProcessedTimestamps: Map<string, number> = new Map()
@@ -48,18 +48,17 @@ export class DiagnosticTrackingService {
     return DiagnosticTrackingService.instance
   }
 
-  initialize(mcpClient: MCPServerConnection) {
+  initialize() {
     if (this.initialized) {
       return
     }
 
-    // TODO: Do not cache the connected mcpClient since it can change.
-    this.mcpClient = mcpClient
     this.initialized = true
   }
 
   async shutdown(): Promise<void> {
     this.initialized = false
+    this.currentMcpClients = []
     this.baseline.clear()
     this.rightFileDiagnosticsState.clear()
     this.lastProcessedTimestamps.clear()
@@ -75,6 +74,46 @@ export class DiagnosticTrackingService {
     this.lastProcessedTimestamps.clear()
   }
 
+  /**
+   * Get the current IDE client from stored MCP clients
+   */
+  private getCurrentIdeClient(): MCPServerConnection | undefined {
+    return getConnectedIdeClient(this.currentMcpClients)
+  }
+
+  /**
+   * Backward-compatible method that uses stored IDE client
+   */
+  async beforeFileEditedCompat(filePath: string): Promise<void> {
+    const ideClient = this.getCurrentIdeClient()
+    if (!ideClient) {
+      return
+    }
+    return await this.beforeFileEdited(filePath, ideClient)
+  }
+
+  /**
+   * Backward-compatible method that uses stored IDE client
+   */
+  async getNewDiagnosticsCompat(): Promise<DiagnosticFile[]> {
+    const ideClient = this.getCurrentIdeClient()
+    if (!ideClient) {
+      return []
+    }
+    return await this.getNewDiagnostics(ideClient)
+  }
+
+  /**
+   * Backward-compatible method that uses stored IDE client
+   */
+  async ensureFileOpenedCompat(fileUri: string): Promise<void> {
+    const ideClient = this.getCurrentIdeClient()
+    if (!ideClient) {
+      return
+    }
+    return await this.ensureFileOpened(fileUri, ideClient)
+  }
+
   private normalizeFileUri(fileUri: string): string {
     // Remove our protocol prefixes
     const protocolPrefixes = [
@@ -100,11 +139,11 @@ export class DiagnosticTrackingService {
    * Ensure a file is opened in the IDE before processing.
    * This is important for language services like diagnostics to work properly.
    */
-  async ensureFileOpened(fileUri: string): Promise<void> {
+  async ensureFileOpened(fileUri: string, mcpClient: MCPServerConnection): Promise<void> {
     if (
       !this.initialized ||
-      !this.mcpClient ||
+      !mcpClient ||
-      this.mcpClient.type !== 'connected'
+      mcpClient.type !== 'connected'
     ) {
       return
     }
@@ -121,7 +160,7 @@ export class DiagnosticTrackingService {
           selectToEndOfLine: false,
           makeFrontmost: false,
         },
-        this.mcpClient,
+        mcpClient,
       )
     } catch (error) {
       logError(error as Error)
@@ -132,11 +171,11 @@ export class DiagnosticTrackingService {
    * Capture baseline diagnostics for a specific file before editing.
    * This is called before editing a file to ensure we have a baseline to compare against.
    */
-  async beforeFileEdited(filePath: string): Promise<void> {
+  async beforeFileEdited(filePath: string, mcpClient: MCPServerConnection): Promise<void> {
     if (
       !this.initialized ||
-      !this.mcpClient ||
+      !mcpClient ||
-      this.mcpClient.type !== 'connected'
+      mcpClient.type !== 'connected'
     ) {
       return
     }
@@ -147,7 +186,7 @@ export class DiagnosticTrackingService {
       const result = await callIdeRpc(
         'getDiagnostics',
         { uri: `file://${filePath}` },
-        this.mcpClient,
+        mcpClient,
       )
       const diagnosticFile = this.parseDiagnosticResult(result)[0]
       if (diagnosticFile) {
@@ -185,11 +224,11 @@ export class DiagnosticTrackingService {
    * Get new diagnostics from file://, _claude_fs_right, and _claude_fs_ URIs that aren't in the baseline.
    * Only processes diagnostics for files that have been edited.
    */
-  async getNewDiagnostics(): Promise<DiagnosticFile[]> {
+  async getNewDiagnostics(mcpClient: MCPServerConnection): Promise<DiagnosticFile[]> {
     if (
       !this.initialized ||
-      !this.mcpClient ||
+      !mcpClient ||
-      this.mcpClient.type !== 'connected'
+      mcpClient.type !== 'connected'
     ) {
       return []
     }
@@ -200,7 +239,7 @@ export class DiagnosticTrackingService {
       const result = await callIdeRpc(
         'getDiagnostics',
         {}, // Empty params fetches all diagnostics
-        this.mcpClient,
+        mcpClient,
       )
       allDiagnosticFiles = this.parseDiagnosticResult(result)
     } catch (_error) {
@@ -328,13 +367,16 @@ export class DiagnosticTrackingService {
    * @param shouldQuery Whether a query is actually being made (not just a command)
    */
   async handleQueryStart(clients: MCPServerConnection[]): Promise<void> {
+    // Store the current MCP clients for later use
+    this.currentMcpClients = clients
+
     // Only proceed if we should query and have clients
     if (!this.initialized) {
       // Find the connected IDE client
       const connectedIdeClient = getConnectedIdeClient(clients)
 
       if (connectedIdeClient) {
-        this.initialize(connectedIdeClient)
+        this.initialize()
       }
     } else {
       // Reset diagnostic tracking for new query loops

src/services/github/deviceFlow.test.ts

@@ -1,4 +1,4 @@
-import { afterEach, beforeEach, describe, expect, mock, test } from 'bun:test'
+import { afterEach, describe, expect, mock, test } from 'bun:test'
 
 import {
   DEFAULT_GITHUB_DEVICE_SCOPE,
@@ -12,22 +12,15 @@ async function importFreshModule() {
   return import(`./deviceFlow.ts?ts=${Date.now()}-${Math.random()}`)
 }
 
-describe('requestDeviceCode', () => {
+afterEach(() => {
-  const originalFetch = globalThis.fetch
-
-  beforeEach(() => {
   mock.restore()
-    globalThis.fetch = originalFetch
+})
-  })
-
-  afterEach(() => {
-    globalThis.fetch = originalFetch
-  })
 
+describe('requestDeviceCode', () => {
   test('parses successful device code response', async () => {
     const { requestDeviceCode } = await importFreshModule()
 
-    globalThis.fetch = mock(() =>
+    const fetchImpl = mock(() =>
       Promise.resolve(
         new Response(
           JSON.stringify({
@@ -44,7 +37,7 @@ describe('requestDeviceCode', () => {
 
     const r = await requestDeviceCode({
       clientId: 'test-client',
-      fetchImpl: globalThis.fetch,
+      fetchImpl,
     })
     expect(r.device_code).toBe('abc')
     expect(r.user_code).toBe('ABCD-1234')
@@ -57,17 +50,17 @@ describe('requestDeviceCode', () => {
     const { requestDeviceCode, GitHubDeviceFlowError } =
       await importFreshModule()
 
-    globalThis.fetch = mock(() =>
+    const fetchImpl = mock(() =>
       Promise.resolve(new Response('bad', { status: 500 })),
     )
     await expect(
-      requestDeviceCode({ clientId: 'x', fetchImpl: globalThis.fetch }),
+      requestDeviceCode({ clientId: 'x', fetchImpl }),
     ).rejects.toThrow(GitHubDeviceFlowError)
   })
 
   test('uses OAuth-safe default scope', async () => {
     let capturedScope = ''
-    globalThis.fetch = mock((_url: RequestInfo | URL, init?: RequestInit) => {
+    const fetchImpl = mock((_url: RequestInfo | URL, init?: RequestInit) => {
       const body = init?.body
       if (body instanceof URLSearchParams) {
         capturedScope = body.get('scope') ?? ''
@@ -87,7 +80,7 @@ describe('requestDeviceCode', () => {
       )
     })
 
-    await requestDeviceCode({ clientId: 'test-client', fetchImpl: globalThis.fetch })
+    await requestDeviceCode({ clientId: 'test-client', fetchImpl })
     expect(capturedScope).toBe(DEFAULT_GITHUB_DEVICE_SCOPE)
     expect(capturedScope).toBe('read:user')
   })
@@ -96,7 +89,7 @@ describe('requestDeviceCode', () => {
     const scopesSeen: string[] = []
     let callCount = 0
 
-    globalThis.fetch = mock((_url: RequestInfo | URL, init?: RequestInit) => {
+    const fetchImpl = mock((_url: RequestInfo | URL, init?: RequestInit) => {
       const body = init?.body
       const scope =
         body instanceof URLSearchParams
@@ -132,7 +125,7 @@ describe('requestDeviceCode', () => {
     const result = await requestDeviceCode({
       clientId: 'test-client',
       scope: 'read:user,models:read',
-      fetchImpl: globalThis.fetch,
+      fetchImpl,
     })
 
     expect(result.device_code).toBe('abc')
@@ -142,17 +135,11 @@ describe('requestDeviceCode', () => {
 })
 
 describe('pollAccessToken', () => {
-  const originalFetch = globalThis.fetch
-
-  afterEach(() => {
-    globalThis.fetch = originalFetch
-  })
-
   test('returns token when GitHub responds with access_token immediately', async () => {
     const { pollAccessToken } = await importFreshModule()
 
     let calls = 0
-    globalThis.fetch = mock(() => {
+    const fetchImpl = mock(() => {
       calls++
       return Promise.resolve(
         new Response(JSON.stringify({ access_token: 'tok-xyz' }), {
@@ -163,7 +150,7 @@ describe('pollAccessToken', () => {
 
     const token = await pollAccessToken('dev-code', {
       clientId: 'cid',
-      fetchImpl: globalThis.fetch,
+      fetchImpl,
     })
     expect(token).toBe('tok-xyz')
     expect(calls).toBe(1)
@@ -172,7 +159,7 @@ describe('pollAccessToken', () => {
   test('throws on access_denied', async () => {
     const { pollAccessToken } = await importFreshModule()
 
-    globalThis.fetch = mock(() =>
+    const fetchImpl = mock(() =>
       Promise.resolve(
         new Response(JSON.stringify({ error: 'access_denied' }), {
           status: 200,
@@ -182,23 +169,17 @@ describe('pollAccessToken', () => {
     await expect(
       pollAccessToken('dc', {
         clientId: 'c',
-        fetchImpl: globalThis.fetch,
+        fetchImpl,
       }),
     ).rejects.toThrow(/denied/)
   })
 })
 
 describe('exchangeForCopilotToken', () => {
-  const originalFetch = globalThis.fetch
-
-  afterEach(() => {
-    globalThis.fetch = originalFetch
-  })
-
   test('parses successful Copilot token response', async () => {
     const { exchangeForCopilotToken } = await importFreshModule()
 
-    globalThis.fetch = mock(() =>
+    const fetchImpl = mock(() =>
       Promise.resolve(
         new Response(
           JSON.stringify({
@@ -214,7 +195,7 @@ describe('exchangeForCopilotToken', () => {
       ),
     )
 
-    const result = await exchangeForCopilotToken('oauth-token', globalThis.fetch)
+    const result = await exchangeForCopilotToken('oauth-token', fetchImpl)
     expect(result.token).toBe('copilot-token-xyz')
     expect(result.expires_at).toBe(1700000000)
     expect(result.refresh_in).toBe(3600)
@@ -225,24 +206,24 @@ describe('exchangeForCopilotToken', () => {
     const { exchangeForCopilotToken, GitHubDeviceFlowError } =
       await importFreshModule()
 
-    globalThis.fetch = mock(() =>
+    const fetchImpl = mock(() =>
       Promise.resolve(new Response('unauthorized', { status: 401 })),
     )
     await expect(
-      exchangeForCopilotToken('bad-token', globalThis.fetch),
+      exchangeForCopilotToken('bad-token', fetchImpl),
     ).rejects.toThrow(GitHubDeviceFlowError)
   })
 
   test('throws on malformed response', async () => {
     const { exchangeForCopilotToken } = await importFreshModule()
 
-    globalThis.fetch = mock(() =>
+    const fetchImpl = mock(() =>
       Promise.resolve(
         new Response(JSON.stringify({ invalid: 'data' }), { status: 200 }),
       ),
     )
     await expect(
-      exchangeForCopilotToken('oauth-token', globalThis.fetch),
+      exchangeForCopilotToken('oauth-token', fetchImpl),
     ).rejects.toThrow(/Malformed/)
   })
 })

src/services/mcp/auth.test.ts

@@ -0,0 +1,61 @@
+import assert from 'node:assert/strict'
+import test from 'node:test'
+
+import { validateOAuthCallbackParams } from './auth.js'
+
+test('OAuth callback rejects error parameters before state validation can be bypassed', () => {
+  const result = validateOAuthCallbackParams(
+    {
+      error: 'access_denied',
+      error_description: 'denied by provider',
+    },
+    'expected-state',
+  )
+
+  assert.deepEqual(result, { type: 'state_mismatch' })
+})
+
+test('OAuth callback accepts provider errors only when state matches', () => {
+  const result = validateOAuthCallbackParams(
+    {
+      state: 'expected-state',
+      error: 'access_denied',
+      error_description: 'denied by provider',
+      error_uri: 'https://example.test/error',
+    },
+    'expected-state',
+  )
+
+  assert.deepEqual(result, {
+    type: 'error',
+    error: 'access_denied',
+    errorDescription: 'denied by provider',
+    errorUri: 'https://example.test/error',
+    message:
+      'OAuth error: access_denied - denied by provider (See: https://example.test/error)',
+  })
+})
+
+test('OAuth callback accepts authorization codes only when state matches', () => {
+  assert.deepEqual(
+    validateOAuthCallbackParams(
+      {
+        state: 'expected-state',
+        code: 'auth-code',
+      },
+      'expected-state',
+    ),
+    { type: 'code', code: 'auth-code' },
+  )
+
+  assert.deepEqual(
+    validateOAuthCallbackParams(
+      {
+        state: 'wrong-state',
+        code: 'auth-code',
+      },
+      'expected-state',
+    ),
+    { type: 'state_mismatch' },
+  )
+})

src/services/mcp/auth.ts

@@ -124,6 +124,74 @@ function redactSensitiveUrlParams(url: string): string {
   }
 }
 
+type OAuthCallbackParamValue = string | string[] | null | undefined
+
+type OAuthCallbackValidationResult =
+  | { type: 'code'; code: string }
+  | {
+      type: 'error'
+      error: string
+      errorDescription: string
+      errorUri: string
+      message: string
+    }
+  | { type: 'missing_result' }
+  | { type: 'state_mismatch' }
+
+function getFirstOAuthCallbackParam(
+  value: OAuthCallbackParamValue,
+): string | undefined {
+  if (Array.isArray(value)) {
+    return value.find(item => item.length > 0)
+  }
+  return value && value.length > 0 ? value : undefined
+}
+
+export function validateOAuthCallbackParams(
+  params: {
+    code?: OAuthCallbackParamValue
+    state?: OAuthCallbackParamValue
+    error?: OAuthCallbackParamValue
+    error_description?: OAuthCallbackParamValue
+    error_uri?: OAuthCallbackParamValue
+  },
+  oauthState: string,
+): OAuthCallbackValidationResult {
+  const code = getFirstOAuthCallbackParam(params.code)
+  const state = getFirstOAuthCallbackParam(params.state)
+  const error = getFirstOAuthCallbackParam(params.error)
+  const errorDescription =
+    getFirstOAuthCallbackParam(params.error_description) ?? ''
+  const errorUri = getFirstOAuthCallbackParam(params.error_uri) ?? ''
+
+  if (state !== oauthState) {
+    return { type: 'state_mismatch' }
+  }
+
+  if (error) {
+    let message = `OAuth error: ${error}`
+    if (errorDescription) {
+      message += ` - ${errorDescription}`
+    }
+    if (errorUri) {
+      message += ` (See: ${errorUri})`
+    }
+    return {
+      type: 'error',
+      error,
+      errorDescription,
+      errorUri,
+      message,
+    }
+  }
+
+  if (code) {
+    return { type: 'code', code }
+  }
+
+  return { type: 'missing_result' }
+}
+
 /**
  * Some OAuth servers (notably Slack) return HTTP 200 for all responses,
  * signaling errors via the JSON body instead. The SDK's executeTokenRequest
@@ -1058,30 +1126,31 @@ export async function performMCPOAuthFlow(
         options.onWaitingForCallback((callbackUrl: string) => {
           try {
             const parsed = new URL(callbackUrl)
-            const code = parsed.searchParams.get('code')
+            const result = validateOAuthCallbackParams(
-            const state = parsed.searchParams.get('state')
+              {
-            const error = parsed.searchParams.get('error')
+                code: parsed.searchParams.get('code'),
-
+                state: parsed.searchParams.get('state'),
-            if (error) {
+                error: parsed.searchParams.get('error'),
-              const errorDescription =
+                error_description:
-                parsed.searchParams.get('error_description') || ''
+                  parsed.searchParams.get('error_description'),
-              cleanup()
+                error_uri: parsed.searchParams.get('error_uri'),
-              rejectOnce(
+              },
-                new Error(`OAuth error: ${error} - ${errorDescription}`),
+              oauthState,
             )
+
+            if (result.type === 'state_mismatch') {
+              // Ignore so a stray or malicious URL cannot cancel an active flow.
               return
             }
 
-            if (!code) {
+            if (result.type === 'missing_result') {
-              // Not a valid callback URL, ignore so the user can try again
+              // Not a valid callback URL, ignore so the user can try again.
               return
             }
 
-            if (state !== oauthState) {
+            if (result.type === 'error') {
               cleanup()
-              rejectOnce(
+              rejectOnce(new Error(result.message))
-                new Error('OAuth state mismatch - possible CSRF attack'),
-              )
               return
             }
 
@@ -1090,7 +1159,7 @@ export async function performMCPOAuthFlow(
               `Received auth code via manual callback URL`,
             )
             cleanup()
-            resolveOnce(code)
+            resolveOnce(result.code)
           } catch {
             // Invalid URL, ignore so the user can try again
           }
@@ -1101,53 +1170,49 @@ export async function performMCPOAuthFlow(
         const parsedUrl = parse(req.url || '', true)
 
         if (parsedUrl.pathname === '/callback') {
-          const code = parsedUrl.query.code as string
+          const result = validateOAuthCallbackParams(
-          const state = parsedUrl.query.state as string
+            parsedUrl.query,
-          const error = parsedUrl.query.error
+            oauthState,
-          const errorDescription = parsedUrl.query.error_description as string
+          )
-          const errorUri = parsedUrl.query.error_uri as string
 
           // Validate OAuth state to prevent CSRF attacks
-          if (!error && state !== oauthState) {
+          if (result.type === 'state_mismatch') {
             res.writeHead(400, { 'Content-Type': 'text/html' })
             res.end(
               `<h1>Authentication Error</h1><p>Invalid state parameter. Please try again.</p><p>You can close this window.</p>`,
             )
-            cleanup()
-            rejectOnce(new Error('OAuth state mismatch - possible CSRF attack'))
             return
           }
 
-          if (error) {
+          if (result.type === 'missing_result') {
+            res.writeHead(400, { 'Content-Type': 'text/html' })
+            res.end(
+              `<h1>Authentication Error</h1><p>Missing OAuth result. Please try again.</p><p>You can close this window.</p>`,
+            )
+            return
+          }
+
+          if (result.type === 'error') {
             res.writeHead(200, { 'Content-Type': 'text/html' })
             // Sanitize error messages to prevent XSS
-            const sanitizedError = xss(String(error))
+            const sanitizedError = xss(result.error)
-            const sanitizedErrorDescription = errorDescription
+            const sanitizedErrorDescription = result.errorDescription
-              ? xss(String(errorDescription))
+              ? xss(result.errorDescription)
               : ''
             res.end(
               `<h1>Authentication Error</h1><p>${sanitizedError}: ${sanitizedErrorDescription}</p><p>You can close this window.</p>`,
             )
             cleanup()
-            let errorMessage = `OAuth error: ${error}`
+            rejectOnce(new Error(result.message))
-            if (errorDescription) {
-              errorMessage += ` - ${errorDescription}`
-            }
-            if (errorUri) {
-              errorMessage += ` (See: ${errorUri})`
-            }
-            rejectOnce(new Error(errorMessage))
             return
           }
 
-          if (code) {
           res.writeHead(200, { 'Content-Type': 'text/html' })
           res.end(
             `<h1>Authentication Successful</h1><p>You can close this window. Return to Claude Code.</p>`,
           )
           cleanup()
-            resolveOnce(code)
+          resolveOnce(result.code)
-          }
         }
       })
 

src/services/mcp/client.ts

@@ -2524,7 +2524,7 @@ export async function transformResultContent(
       return [
         {
           type: 'text',
-          text: resultContent.text,
+          text: recursivelySanitizeUnicode(resultContent.text) as string,
         },
       ]
     case 'audio': {
@@ -2569,7 +2569,9 @@ export async function transformResultContent(
         return [
           {
             type: 'text',
-            text: `${prefix}${resource.text}`,
+            text: recursivelySanitizeUnicode(
+              `${prefix}${resource.text}`,
+            ) as string,
           },
         ]
       } else if ('blob' in resource) {

src/services/wiki/init.test.ts

@@ -26,10 +26,10 @@ test('initializeWiki creates the expected wiki scaffold', async () => {
 
   expect(result.alreadyExisted).toBe(false)
   expect(result.createdFiles).toEqual([
-    '.openclaude/wiki/schema.md',
+    join('.openclaude', 'wiki', 'schema.md'),
-    '.openclaude/wiki/index.md',
+    join('.openclaude', 'wiki', 'index.md'),
-    '.openclaude/wiki/log.md',
+    join('.openclaude', 'wiki', 'log.md'),
-    '.openclaude/wiki/pages/architecture.md',
+    join('.openclaude', 'wiki', 'pages', 'architecture.md'),
   ])
   expect(await readFile(paths.schemaFile, 'utf8')).toContain(
     '# OpenClaude Wiki Schema',

src/tools/BashTool/BashTool.tsx

@@ -240,21 +240,28 @@ For commands that are harder to parse at a glance (piped commands, obscure flags
 - curl -s url | jq '.data[]' → "Fetch JSON from URL and extract data array elements"`),
   run_in_background: semanticBoolean(z.boolean().optional()).describe(`Set to true to run this command in the background. Use Read to read the output later.`),
   dangerouslyDisableSandbox: semanticBoolean(z.boolean().optional()).describe('Set this to true to dangerously override sandbox mode and run commands without sandboxing.'),
+  _dangerouslyDisableSandboxApproved: z.boolean().optional().describe('Internal: user-approved sandbox override'),
   _simulatedSedEdit: z.object({
     filePath: z.string(),
     newContent: z.string()
   }).optional().describe('Internal: pre-computed sed edit result from preview')
 }));
 
-// Always omit _simulatedSedEdit from the model-facing schema. It is an internal-only
+// Always omit internal-only fields from the model-facing schema.
-// field set by SedEditPermissionRequest after the user approves a sed edit preview.
+// _simulatedSedEdit is set by SedEditPermissionRequest after the user approves a
-// Exposing it in the schema would let the model bypass permission checks and the
+// sed edit preview; exposing it would let the model bypass permission checks and
-// sandbox by pairing an innocuous command with an arbitrary file write.
+// the sandbox by pairing an innocuous command with an arbitrary file write.
+// dangerouslyDisableSandbox is also omitted because sandbox escape must be tied
+// to trusted user/internal provenance, not model-controlled tool input.
 // Also conditionally remove run_in_background when background tasks are disabled.
 const inputSchema = lazySchema(() => isBackgroundTasksDisabled ? fullInputSchema().omit({
   run_in_background: true,
+  dangerouslyDisableSandbox: true,
+  _dangerouslyDisableSandboxApproved: true,
   _simulatedSedEdit: true
 }) : fullInputSchema().omit({
+  dangerouslyDisableSandbox: true,
+  _dangerouslyDisableSandboxApproved: true,
   _simulatedSedEdit: true
 }));
 type InputSchema = ReturnType<typeof inputSchema>;

src/tools/BashTool/bashPermissions.test.ts

@@ -0,0 +1,59 @@
+import { afterEach, expect, test } from 'bun:test'
+
+import { getEmptyToolPermissionContext } from '../../Tool.js'
+import { SandboxManager } from '../../utils/sandbox/sandbox-adapter.js'
+import { bashToolHasPermission } from './bashPermissions.js'
+
+const originalSandboxMethods = {
+  isSandboxingEnabled: SandboxManager.isSandboxingEnabled,
+  isAutoAllowBashIfSandboxedEnabled:
+    SandboxManager.isAutoAllowBashIfSandboxedEnabled,
+  areUnsandboxedCommandsAllowed: SandboxManager.areUnsandboxedCommandsAllowed,
+  getExcludedCommands: SandboxManager.getExcludedCommands,
+}
+
+afterEach(() => {
+  SandboxManager.isSandboxingEnabled =
+    originalSandboxMethods.isSandboxingEnabled
+  SandboxManager.isAutoAllowBashIfSandboxedEnabled =
+    originalSandboxMethods.isAutoAllowBashIfSandboxedEnabled
+  SandboxManager.areUnsandboxedCommandsAllowed =
+    originalSandboxMethods.areUnsandboxedCommandsAllowed
+  SandboxManager.getExcludedCommands = originalSandboxMethods.getExcludedCommands
+})
+
+function makeToolUseContext() {
+  const toolPermissionContext = getEmptyToolPermissionContext()
+
+  return {
+    abortController: new AbortController(),
+    options: {
+      isNonInteractiveSession: false,
+    },
+    getAppState() {
+      return {
+        toolPermissionContext,
+      }
+    },
+  } as never
+}
+
+test('sandbox auto-allow still enforces Bash path constraints', async () => {
+  ;(globalThis as unknown as { MACRO: { VERSION: string } }).MACRO = {
+    VERSION: 'test',
+  }
+
+  SandboxManager.isSandboxingEnabled = () => true
+  SandboxManager.isAutoAllowBashIfSandboxedEnabled = () => true
+  SandboxManager.areUnsandboxedCommandsAllowed = () => true
+  SandboxManager.getExcludedCommands = () => []
+
+  const result = await bashToolHasPermission(
+    { command: 'cat ../../../../../etc/passwd' },
+    makeToolUseContext(),
+  )
+
+  expect(result.behavior).toBe('ask')
+  expect(result.message).toContain('was blocked')
+  expect(result.message).toContain('/etc/passwd')
+})

src/tools/BashTool/bashPermissions.ts

@@ -1814,7 +1814,10 @@ export async function bashToolHasPermission(
       input,
       appState.toolPermissionContext,
     )
-    if (sandboxAutoAllowResult.behavior !== 'passthrough') {
+    if (
+      sandboxAutoAllowResult.behavior === 'deny' ||
+      sandboxAutoAllowResult.behavior === 'ask'
+    ) {
       return sandboxAutoAllowResult
     }
   }

src/tools/BashTool/prompt.ts

@@ -179,9 +179,6 @@ function getSimpleSandboxSection(): string {
   const networkRestrictionConfig = SandboxManager.getNetworkRestrictionConfig()
   const allowUnixSockets = SandboxManager.getAllowUnixSockets()
   const ignoreViolations = SandboxManager.getIgnoreViolations()
-  const allowUnsandboxedCommands =
-    SandboxManager.areUnsandboxedCommandsAllowed()
-
   // Replace the per-UID temp dir literal (e.g. /private/tmp/claude-1001/) with
   // "$TMPDIR" so the prompt is identical across users — avoids busting the
   // cross-user global prompt cache. The sandbox already sets $TMPDIR at runtime.
@@ -225,38 +222,9 @@ function getSimpleSandboxSection(): string {
     )
   }
 
-  const sandboxOverrideItems: Array<string | string[]> =
-    allowUnsandboxedCommands
-      ? [
-          'You should always default to running commands within the sandbox. Do NOT attempt to set `dangerouslyDisableSandbox: true` unless:',
-          [
-            'The user *explicitly* asks you to bypass sandbox',
-            'A specific command just failed and you see evidence of sandbox restrictions causing the failure. Note that commands can fail for many reasons unrelated to the sandbox (missing files, wrong arguments, network issues, etc.).',
-          ],
-          'Evidence of sandbox-caused failures includes:',
-          [
-            '"Operation not permitted" errors for file/network operations',
-            'Access denied to specific paths outside allowed directories',
-            'Network connection failures to non-whitelisted hosts',
-            'Unix socket connection errors',
-          ],
-          'When you see evidence of sandbox-caused failure:',
-          [
-            "Immediately retry with `dangerouslyDisableSandbox: true` (don't ask, just do it)",
-            'Briefly explain what sandbox restriction likely caused the failure. Be sure to mention that the user can use the `/sandbox` command to manage restrictions.',
-            'This will prompt the user for permission',
-          ],
-          'Treat each command you execute with `dangerouslyDisableSandbox: true` individually. Even if you have recently run a command with this setting, you should default to running future commands within the sandbox.',
-          'Do not suggest adding sensitive paths like ~/.bashrc, ~/.zshrc, ~/.ssh/*, or credential files to the sandbox allowlist.',
-        ]
-      : [
-          'All commands MUST run in sandbox mode - the `dangerouslyDisableSandbox` parameter is disabled by policy.',
-          'Commands cannot run outside the sandbox under any circumstances.',
-          'If a command fails due to sandbox restrictions, work with the user to adjust sandbox settings instead.',
-        ]
-
   const items: Array<string | string[]> = [
-    ...sandboxOverrideItems,
+    'Commands MUST run in sandbox mode. If a command fails due to sandbox restrictions, explain the likely restriction and work with the user to adjust sandbox settings or run an explicit user-initiated shell command.',
+    'Do not suggest adding sensitive paths like ~/.bashrc, ~/.zshrc, ~/.ssh/*, or credential files to the sandbox allowlist.',
     'For temporary files, always use the `$TMPDIR` environment variable. TMPDIR is automatically set to the correct sandbox-writable directory in sandbox mode. Do NOT use `/tmp` directly - use `$TMPDIR` instead.',
   ]
 

src/tools/BashTool/shouldUseSandbox.test.ts

@@ -0,0 +1,74 @@
+import { afterEach, expect, test } from 'bun:test'
+
+import { SandboxManager } from '../../utils/sandbox/sandbox-adapter.js'
+import { BashTool } from './BashTool.js'
+import { PowerShellTool } from '../PowerShellTool/PowerShellTool.js'
+import { shouldUseSandbox } from './shouldUseSandbox.js'
+
+const originalSandboxMethods = {
+  isSandboxingEnabled: SandboxManager.isSandboxingEnabled,
+  areUnsandboxedCommandsAllowed: SandboxManager.areUnsandboxedCommandsAllowed,
+}
+
+afterEach(() => {
+  SandboxManager.isSandboxingEnabled =
+    originalSandboxMethods.isSandboxingEnabled
+  SandboxManager.areUnsandboxedCommandsAllowed =
+    originalSandboxMethods.areUnsandboxedCommandsAllowed
+})
+
+test('model-facing Bash schema rejects dangerouslyDisableSandbox', () => {
+  const result = BashTool.inputSchema.safeParse({
+    command: 'cat /etc/passwd',
+    dangerouslyDisableSandbox: true,
+  })
+
+  expect(result.success).toBe(false)
+})
+
+test('model-facing PowerShell schema rejects dangerouslyDisableSandbox', () => {
+  const result = PowerShellTool.inputSchema.safeParse({
+    command: 'Get-Content C:\\Windows\\System32\\drivers\\etc\\hosts',
+    dangerouslyDisableSandbox: true,
+  })
+
+  expect(result.success).toBe(false)
+})
+
+test('model-controlled dangerouslyDisableSandbox does not bypass sandbox', () => {
+  SandboxManager.isSandboxingEnabled = () => true
+  SandboxManager.areUnsandboxedCommandsAllowed = () => true
+
+  expect(
+    shouldUseSandbox({
+      command: 'cat /etc/passwd',
+      dangerouslyDisableSandbox: true,
+    }),
+  ).toBe(true)
+})
+
+test('trusted internal approval can disable sandbox when policy allows it', () => {
+  SandboxManager.isSandboxingEnabled = () => true
+  SandboxManager.areUnsandboxedCommandsAllowed = () => true
+
+  expect(
+    shouldUseSandbox({
+      command: 'cat /etc/passwd',
+      dangerouslyDisableSandbox: true,
+      _dangerouslyDisableSandboxApproved: true,
+    }),
+  ).toBe(false)
+})
+
+test('trusted internal approval cannot disable sandbox when policy forbids it', () => {
+  SandboxManager.isSandboxingEnabled = () => true
+  SandboxManager.areUnsandboxedCommandsAllowed = () => false
+
+  expect(
+    shouldUseSandbox({
+      command: 'cat /etc/passwd',
+      dangerouslyDisableSandbox: true,
+      _dangerouslyDisableSandboxApproved: true,
+    }),
+  ).toBe(true)
+})

src/tools/BashTool/shouldUseSandbox.ts

@@ -13,6 +13,7 @@ import {
 type SandboxInput = {
   command?: string
   dangerouslyDisableSandbox?: boolean
+  _dangerouslyDisableSandboxApproved?: boolean
 }
 
 // NOTE: excludedCommands is a user-facing convenience feature, not a security boundary.
@@ -141,9 +142,13 @@ export function shouldUseSandbox(input: Partial<SandboxInput>): boolean {
     return false
   }
 
-  // Don't sandbox if explicitly overridden AND unsandboxed commands are allowed by policy
+  // Only trusted internal callers may request an unsandboxed command. The
+  // model-facing Bash schema omits _dangerouslyDisableSandboxApproved, so a
+  // tool_use payload cannot disable the sandbox by setting
+  // dangerouslyDisableSandbox directly.
   if (
     input.dangerouslyDisableSandbox &&
+    input._dangerouslyDisableSandboxApproved &&
     SandboxManager.areUnsandboxedCommandsAllowed()
   ) {
     return false

src/tools/ConfigTool/prompt.ts

@@ -59,7 +59,7 @@ export function generatePrompt(): string {
 ## Configurable settings list
 The following settings are available for you to change:
 
-### Global Settings (stored in ~/.claude.json)
+### Global Settings (stored in ~/.openclaude.json)
 ${globalSettings.join('\n')}
 
 ### Project Settings (stored in settings.json)

src/tools/FileEditTool/FileEditTool.ts

@@ -422,7 +422,7 @@ export const FileEditTool = buildTool({
       activateConditionalSkillsForPaths([absoluteFilePath], cwd)
     }
 
-    await diagnosticTracker.beforeFileEdited(absoluteFilePath)
+    await diagnosticTracker.beforeFileEditedCompat(absoluteFilePath)
 
     // Ensure parent directory exists before the atomic read-modify-write section.
     // These awaits must stay OUTSIDE the critical section below — a yield between

src/tools/FileWriteTool/FileWriteTool.ts

@@ -244,7 +244,7 @@ export const FileWriteTool = buildTool({
     // Activate conditional skills whose path patterns match this file
     activateConditionalSkillsForPaths([fullFilePath], cwd)
 
-    await diagnosticTracker.beforeFileEdited(fullFilePath)
+    await diagnosticTracker.beforeFileEditedCompat(fullFilePath)
 
     // Ensure parent directory exists before the atomic read-modify-write section.
     // Must stay OUTSIDE the critical section below (a yield between the staleness

src/tools/MCPTool/MCPTool.ts

@@ -1,7 +1,8 @@
+import { Ajv } from 'ajv'
 import { z } from 'zod/v4'
-import { buildTool, type ToolDef } from '../../Tool.js'
+import { buildTool, type ToolDef, type ValidationResult } from '../../Tool.js'
 import { lazySchema } from '../../utils/lazySchema.js'
-import type { PermissionResult } from '../../utils/permissions/PermissionResult.js'
+import type { PermissionResult } from '../../types/permissions.js'
 import { isOutputLineTruncated } from '../../utils/terminal.js'
 import { DESCRIPTION, PROMPT } from './prompt.js'
 import {
@@ -37,6 +38,8 @@ export type Output = z.infer<OutputSchema>
 // Re-export MCPProgress from centralized types to break import cycles
 export type { MCPProgress } from '../../types/tools.js'
 
+const ajv = new Ajv({ strict: false })
+
 export const MCPTool = buildTool({
   isMcp: true,
   // Overridden in mcpClient.ts with the real MCP tool name + args
@@ -72,6 +75,27 @@ export const MCPTool = buildTool({
       message: 'MCPTool requires permission.',
     }
   },
+  async validateInput(input, context): Promise<ValidationResult> {
+    if (this.inputJSONSchema) {
+      try {
+        const validate = ajv.compile(this.inputJSONSchema)
+        if (!validate(input)) {
+          return {
+            result: false,
+            message: ajv.errorsText(validate.errors),
+            errorCode: 400,
+          }
+        }
+      } catch (error) {
+        return {
+          result: false,
+          message: `Failed to compile JSON schema for validation: ${error}`,
+          errorCode: 500,
+        }
+      }
+    }
+    return { result: true }
+  },
   renderToolUseMessage,
   // Overridden in mcpClient.ts
   userFacingName: () => 'mcp',
@@ -100,3 +124,4 @@ export const MCPTool = buildTool({
     }
   },
 } satisfies ToolDef<InputSchema, Output>)
+

src/tools/PowerShellTool/PowerShellTool.tsx

@@ -230,13 +230,20 @@ const fullInputSchema = lazySchema(() => z.strictObject({
   timeout: semanticNumber(z.number().optional()).describe(`Optional timeout in milliseconds (max ${getMaxTimeoutMs()})`),
   description: z.string().optional().describe('Clear, concise description of what this command does in active voice.'),
   run_in_background: semanticBoolean(z.boolean().optional()).describe(`Set to true to run this command in the background. Use Read to read the output later.`),
-  dangerouslyDisableSandbox: semanticBoolean(z.boolean().optional()).describe('Set this to true to dangerously override sandbox mode and run commands without sandboxing.')
+  dangerouslyDisableSandbox: semanticBoolean(z.boolean().optional()).describe('Set this to true to dangerously override sandbox mode and run commands without sandboxing.'),
+  _dangerouslyDisableSandboxApproved: z.boolean().optional().describe('Internal: user-approved sandbox override')
 }));
 
-// Conditionally remove run_in_background from schema when background tasks are disabled
+// Omit internal-only sandbox override fields from the model-facing schema.
+// Conditionally remove run_in_background from schema when background tasks are disabled.
 const inputSchema = lazySchema(() => isBackgroundTasksDisabled ? fullInputSchema().omit({
-  run_in_background: true
+  run_in_background: true,
-}) : fullInputSchema());
+  dangerouslyDisableSandbox: true,
+  _dangerouslyDisableSandboxApproved: true
+}) : fullInputSchema().omit({
+  dangerouslyDisableSandbox: true,
+  _dangerouslyDisableSandboxApproved: true
+}));
 type InputSchema = ReturnType<typeof inputSchema>;
 
 // Use fullInputSchema for the type to always include run_in_background
@@ -697,7 +704,8 @@ async function* runPowerShellCommand({
     description,
     timeout,
     run_in_background,
-    dangerouslyDisableSandbox
+    dangerouslyDisableSandbox,
+    _dangerouslyDisableSandboxApproved
   } = input;
   const timeoutMs = Math.min(timeout || getDefaultTimeoutMs(), getMaxTimeoutMs());
   let fullOutput = '';
@@ -749,7 +757,8 @@ async function* runPowerShellCommand({
       // The explicit platform check is redundant-but-obvious.
       shouldUseSandbox: getPlatform() === 'windows' ? false : shouldUseSandbox({
         command,
-        dangerouslyDisableSandbox
+        dangerouslyDisableSandbox,
+        _dangerouslyDisableSandboxApproved
       }),
       shouldAutoBackground
     });

src/tools/WebFetchTool/utils.ts

@@ -15,6 +15,7 @@ import {
 } from '../../utils/mcpOutputStorage.js'
 import { getSettings_DEPRECATED } from '../../utils/settings/settings.js'
 import { asSystemPrompt } from '../../utils/systemPromptType.js'
+import { ssrfGuardedLookup } from '../../utils/hooks/ssrfGuard.js'
 import { isPreapprovedHost } from './preapproved.js'
 import { makeSecondaryModelPrompt } from './prompt.js'
 
@@ -281,6 +282,7 @@ export async function getWithPermittedRedirects(
       maxRedirects: 0,
       responseType: 'arraybuffer',
       maxContentLength: MAX_HTTP_CONTENT_LENGTH,
+      lookup: ssrfGuardedLookup,
       headers: {
         Accept: 'text/markdown, text/html, */*',
         'User-Agent': getWebFetchUserAgent(),

src/tools/WebSearchTool/WebSearchTool.ts

@@ -9,6 +9,7 @@ import { z } from 'zod/v4'
 import { getFeatureValue_CACHED_MAY_BE_STALE } from '../../services/analytics/growthbook.js'
 import { queryModelWithStreaming } from '../../services/api/claude.js'
 import { collectCodexCompletedResponse } from '../../services/api/codexShim.js'
+import { fetchWithProxyRetry } from '../../services/api/fetchWithProxyRetry.js'
 import {
   resolveCodexApiCredentials,
   resolveProviderRequest,
@@ -314,7 +315,7 @@ async function runCodexWebSearch(
     body.reasoning = request.reasoning
   }
 
-  const response = await fetch(`${request.baseUrl}/responses`, {
+  const response = await fetchWithProxyRetry(`${request.baseUrl}/responses`, {
     method: 'POST',
     headers: {
       'Content-Type': 'application/json',

src/utils/Cursor.ts

@@ -148,6 +148,42 @@ type Position = {
   column: number
 }
 
+export function maskTextWithVisibleEdges(
+  value: string,
+  mask: string,
+  visiblePrefix = 3,
+  visibleSuffix = 3,
+): string {
+  if (!mask || !value) return value
+
+  const graphemes = Array.from(getGraphemeSegmenter().segment(value))
+  const secretGraphemeCount = graphemes.filter(
+    ({ segment }) => segment !== '\n',
+  ).length
+  const visibleCount = visiblePrefix + visibleSuffix
+
+  if (secretGraphemeCount <= visibleCount) {
+    return graphemes
+      .map(({ segment }) => (segment === '\n' ? segment : mask))
+      .join('')
+  }
+
+  let secretIndex = 0
+  return graphemes
+    .map(({ segment }) => {
+      if (segment === '\n') return segment
+
+      const nextSegment =
+        secretIndex < visiblePrefix ||
+        secretIndex >= secretGraphemeCount - visibleSuffix
+          ? segment
+          : mask
+      secretIndex += 1
+      return nextSegment
+    })
+    .join('')
+}
+
 export class Cursor {
   readonly offset: number
   constructor(
@@ -208,7 +244,12 @@ export class Cursor {
     maxVisibleLines?: number,
   ) {
     const { line, column } = this.getPosition()
-    const allLines = this.measuredText.getWrappedText()
+    const allLines = mask
+      ? new MeasuredText(
+          maskTextWithVisibleEdges(this.text, mask),
+          this.measuredText.columns,
+        ).getWrappedText()
+      : this.measuredText.getWrappedText()
 
     const startLine = this.getViewportStartLine(maxVisibleLines)
     const endLine =
@@ -221,23 +262,6 @@ export class Cursor {
       .map((text, i) => {
         const currentLine = i + startLine
         let displayText = text
-        if (mask) {
-          const graphemes = Array.from(getGraphemeSegmenter().segment(text))
-          if (currentLine === allLines.length - 1) {
-            // Last line: mask all but the trailing 6 chars so the user can
-            // confirm they pasted the right thing without exposing the full token
-            const visibleCount = Math.min(6, graphemes.length)
-            const maskCount = graphemes.length - visibleCount
-            const splitOffset =
-              graphemes.length > visibleCount ? graphemes[maskCount]!.index : 0
-            displayText = mask.repeat(maskCount) + text.slice(splitOffset)
-          } else {
-            // Earlier wrapped lines: fully mask. Previously only the last line
-            // was masked, leaking the start of the token on narrow terminals
-            // where the pasted OAuth code wraps across multiple lines.
-            displayText = mask.repeat(graphemes.length)
-          }
-        }
         // looking for the line with the cursor
         if (line !== currentLine) return displayText.trimEnd()
 

src/utils/api.test.ts

@@ -78,3 +78,28 @@ test('toolToAPISchema keeps skill required for SkillTool', async () => {
     required: ['skill'],
   })
 })
+
+test('toolToAPISchema removes extra required keys not in properties (MCP schema sanitization)', async () => {
+  const schema = await toolToAPISchema(
+    {
+      name: 'mcp__test__create_object',
+      inputSchema: z.strictObject({}),
+      inputJSONSchema: {
+        type: 'object',
+        properties: {
+          name: { type: 'string' },
+        },
+        required: ['name', 'attributes'],
+      },
+      prompt: async () => 'Create an object',
+    } as unknown as Tool,
+    {
+      getToolPermissionContext: async () => getEmptyToolPermissionContext(),
+      tools: [] as unknown as Tools,
+      agents: [],
+    },
+  )
+
+  const inputSchema = (schema as { input_schema: { required?: string[] } }).input_schema
+  expect(inputSchema.required).toEqual(['name'])
+})

src/utils/api.ts

@@ -111,11 +111,60 @@ function filterSwarmFieldsFromSchema(
       delete filteredProps[field]
     }
     filtered.properties = filteredProps
+
+    // Keep `required` in sync after removing properties
+    if (Array.isArray(filtered.required)) {
+      filtered.required = filtered.required.filter(
+        (key: string) => key in filteredProps,
+      )
+    }
   }
 
   return filtered
 }
 
+/**
+ * Ensure `required` only lists keys present in `properties`.
+ * MCP servers may emit schemas where these are out of sync, causing
+ * API 400 errors ("Extra required key supplied").
+ * Recurses into nested object schemas.
+ */
+function sanitizeSchemaRequired(
+  schema: Anthropic.Tool.InputSchema,
+): Anthropic.Tool.InputSchema {
+  if (!schema || typeof schema !== 'object') {
+    return schema
+  }
+
+  const result = { ...schema }
+  const props = result.properties as Record<string, unknown> | undefined
+
+  if (props && Array.isArray(result.required)) {
+    result.required = result.required.filter(
+      (key: string) => key in props,
+    )
+  }
+
+  // Recurse into nested object properties
+  if (props) {
+    const sanitizedProps = { ...props }
+    for (const [key, value] of Object.entries(sanitizedProps)) {
+      if (
+        value &&
+        typeof value === 'object' &&
+        (value as Record<string, unknown>).type === 'object'
+      ) {
+        sanitizedProps[key] = sanitizeSchemaRequired(
+          value as Anthropic.Tool.InputSchema,
+        )
+      }
+    }
+    result.properties = sanitizedProps
+  }
+
+  return result
+}
+
 export async function toolToAPISchema(
   tool: Tool,
   options: {
@@ -156,7 +205,7 @@ export async function toolToAPISchema(
     // Use tool's JSON schema directly if provided, otherwise convert Zod schema
     let input_schema = (
       'inputJSONSchema' in tool && tool.inputJSONSchema
-        ? tool.inputJSONSchema
+        ? sanitizeSchemaRequired(tool.inputJSONSchema as Anthropic.Tool.InputSchema)
         : zodToJsonSchema(tool.inputSchema)
     ) as Anthropic.Tool.InputSchema
 
@@ -613,10 +662,6 @@ export function normalizeToolInput<T extends Tool>(
         ...(timeout !== undefined && { timeout }),
         ...(description !== undefined && { description }),
         ...(run_in_background !== undefined && { run_in_background }),
-        ...('dangerouslyDisableSandbox' in parsed &&
-          parsed.dangerouslyDisableSandbox !== undefined && {
-            dangerouslyDisableSandbox: parsed.dangerouslyDisableSandbox,
-          }),
       } as z.infer<T['inputSchema']>
     }
     case FileEditTool.name: {

src/utils/attachments.ts

@@ -2882,7 +2882,7 @@ async function getDiagnosticAttachments(
   }
 
   // Get new diagnostics from the tracker (IDE diagnostics via MCP)
-  const newDiagnostics = await diagnosticTracker.getNewDiagnostics()
+  const newDiagnostics = await diagnosticTracker.getNewDiagnosticsCompat()
   if (newDiagnostics.length === 0) {
     return []
   }

src/utils/auth.ts

@@ -693,7 +693,7 @@ export function refreshAwsAuth(awsAuthRefresh: string): Promise<boolean> {
               'AWS auth refresh timed out after 3 minutes. Run your auth command manually in a separate terminal.',
             )
           : chalk.red(
-              'Error running awsAuthRefresh (in settings or ~/.claude.json):',
+              'Error running awsAuthRefresh (in settings or ~/.openclaude.json):',
             )
         // biome-ignore lint/suspicious/noConsole:: intentional console output
         console.error(message)
@@ -771,7 +771,7 @@ async function getAwsCredsFromCredentialExport(): Promise<{
       }
     } catch (e) {
       const message = chalk.red(
-        'Error getting AWS credentials from awsCredentialExport (in settings or ~/.claude.json):',
+        'Error getting AWS credentials from awsCredentialExport (in settings or ~/.openclaude.json):',
       )
       if (e instanceof Error) {
         // biome-ignore lint/suspicious/noConsole:: intentional console output
@@ -961,7 +961,7 @@ export function refreshGcpAuth(gcpAuthRefresh: string): Promise<boolean> {
               'GCP auth refresh timed out after 3 minutes. Run your auth command manually in a separate terminal.',
             )
           : chalk.red(
-              'Error running gcpAuthRefresh (in settings or ~/.claude.json):',
+              'Error running gcpAuthRefresh (in settings or ~/.openclaude.json):',
             )
         // biome-ignore lint/suspicious/noConsole:: intentional console output
         console.error(message)
@@ -1959,7 +1959,7 @@ export async function validateForceLoginOrg(): Promise<OrgValidationResult> {
 
   // Always fetch the authoritative org UUID from the profile endpoint.
   // Even keychain-sourced tokens verify server-side: the cached org UUID
-  // in ~/.claude.json is user-writable and cannot be trusted.
+  // in ~/.openclaude.json is user-writable and cannot be trusted.
   const { source } = getAuthTokenSource()
   const isEnvVarToken =
     source === 'CLAUDE_CODE_OAUTH_TOKEN' ||

src/utils/caCertsConfig.ts

@@ -28,7 +28,7 @@ import { getSettingsForSource } from './settings/settings.js'
  * is lazy-initialized) and ensure Node.js compatibility.
  *
  * This is safe to call before the trust dialog because we only read from
- * user-controlled files (~/.claude/settings.json and ~/.claude.json),
+ * user-controlled files (~/.claude/settings.json and ~/.openclaude.json),
  * not from project-level settings.
  */
 export function applyExtraCACertsFromConfig(): void {
@@ -52,7 +52,7 @@ export function applyExtraCACertsFromConfig(): void {
  * after the trust dialog. But we need the CA cert early to establish the TLS
  * connection to an HTTPS proxy during init().
  *
- * We read from global config (~/.claude.json) and user settings
+ * We read from global config (~/.openclaude.json) and user settings
  * (~/.claude/settings.json). These are user-controlled files that don't
  * require trust approval.
  */

src/utils/claudeInChrome/setup.ts

@@ -355,7 +355,7 @@ exec ${command}
  *
  * Only positive detections are persisted. A negative result from the
  * filesystem scan is not cached, because it may come from a machine that
- * shares ~/.claude.json but has no local Chrome (e.g. a remote dev
+ * shares ~/.openclaude.json but has no local Chrome (e.g. a remote dev
  * environment using the bridge), and caching it would permanently poison
  * auto-enable for every session on every machine that reads that config.
  */

src/utils/config.ts

@@ -155,7 +155,7 @@ export {
   NOTIFICATION_CHANNELS,
 } from './configConstants.js'
 
-import type { EDITOR_MODES, NOTIFICATION_CHANNELS } from './configConstants.js'
+import type { EDITOR_MODES, NOTIFICATION_CHANNELS, PROVIDERS } from './configConstants.js'
 
 export type NotificationChannel = (typeof NOTIFICATION_CHANNELS)[number]
 
@@ -181,10 +181,12 @@ export type DiffTool = 'terminal' | 'auto'
 
 export type OutputStyle = string
 
+export type Providers = typeof PROVIDERS[number]
+
 export type ProviderProfile = {
   id: string
   name: string
-  provider: 'openai' | 'anthropic'
+  provider: Providers
   baseUrl: string
   model: string
   apiKey?: string
@@ -916,7 +918,7 @@ let configCacheHits = 0
 let configCacheMisses = 0
 // Session-total count of actual disk writes to the global config file.
 // Exposed for internal-only dev diagnostics (see inc-4552) so anomalous write
-// rates surface in the UI before they corrupt ~/.claude.json.
+// rates surface in the UI before they corrupt ~/.openclaude.json.
 let globalConfigWriteCount = 0
 
 export function getGlobalConfigWriteCount(): number {
@@ -1255,7 +1257,7 @@ function saveConfigWithLock<A extends object>(
     const currentConfig = getConfig(file, createDefault)
     if (file === getGlobalClaudeFile() && wouldLoseAuthState(currentConfig)) {
       logForDebugging(
-        'saveConfigWithLock: re-read config is missing auth that cache has; refusing to write to avoid wiping ~/.claude.json. See GH #3117.',
+        'saveConfigWithLock: re-read config is missing auth that cache has; refusing to write to avoid wiping ~/.openclaude.json. See GH #3117.',
         { level: 'error' },
       )
       logEvent('tengu_config_auth_loss_prevented', {})

src/utils/configConstants.ts

@@ -19,3 +19,5 @@ export const EDITOR_MODES = ['normal', 'vim'] as const
 // 'in-process' = in-process teammates running in same process
 // 'auto' = automatically choose based on context (default)
 export const TEAMMATE_MODES = ['auto', 'tmux', 'in-process'] as const
+
+export const PROVIDERS = ['openai', 'anthropic', 'mistral', 'gemini'] as const

src/utils/context.test.ts

@@ -9,6 +9,7 @@ import {
 const originalEnv = {
   CLAUDE_CODE_USE_OPENAI: process.env.CLAUDE_CODE_USE_OPENAI,
   CLAUDE_CODE_MAX_OUTPUT_TOKENS: process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS,
+  OPENAI_MODEL: process.env.OPENAI_MODEL,
 }
 
 afterEach(() => {
@@ -23,11 +24,17 @@ afterEach(() => {
     process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS =
       originalEnv.CLAUDE_CODE_MAX_OUTPUT_TOKENS
   }
+  if (originalEnv.OPENAI_MODEL === undefined) {
+    delete process.env.OPENAI_MODEL
+  } else {
+    process.env.OPENAI_MODEL = originalEnv.OPENAI_MODEL
+  }
 })
 
 test('deepseek-chat uses provider-specific context and output caps', () => {
   process.env.CLAUDE_CODE_USE_OPENAI = '1'
   delete process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS
+  delete process.env.OPENAI_MODEL
 
   expect(getContextWindowForModel('deepseek-chat')).toBe(128_000)
   expect(getModelMaxOutputTokens('deepseek-chat')).toEqual({
@@ -40,6 +47,7 @@ test('deepseek-chat uses provider-specific context and output caps', () => {
 test('deepseek-chat clamps oversized max output overrides to the provider limit', () => {
   process.env.CLAUDE_CODE_USE_OPENAI = '1'
   process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS = '32000'
+  delete process.env.OPENAI_MODEL
 
   expect(getMaxOutputTokensForModel('deepseek-chat')).toBe(8_192)
 })
@@ -47,6 +55,7 @@ test('deepseek-chat clamps oversized max output overrides to the provider limit'
 test('gpt-4o uses provider-specific context and output caps', () => {
   process.env.CLAUDE_CODE_USE_OPENAI = '1'
   delete process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS
+  delete process.env.OPENAI_MODEL
 
   expect(getContextWindowForModel('gpt-4o')).toBe(128_000)
   expect(getModelMaxOutputTokens('gpt-4o')).toEqual({
@@ -59,6 +68,7 @@ test('gpt-4o uses provider-specific context and output caps', () => {
 test('gpt-4o clamps oversized max output overrides to the provider limit', () => {
   process.env.CLAUDE_CODE_USE_OPENAI = '1'
   process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS = '32000'
+  delete process.env.OPENAI_MODEL
 
   expect(getMaxOutputTokensForModel('gpt-4o')).toBe(16_384)
 })
@@ -66,6 +76,7 @@ test('gpt-4o clamps oversized max output overrides to the provider limit', () =>
 test('gpt-5.4 family uses provider-specific context and output caps', () => {
   process.env.CLAUDE_CODE_USE_OPENAI = '1'
   delete process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS
+  delete process.env.OPENAI_MODEL
 
   expect(getContextWindowForModel('gpt-5.4')).toBe(1_050_000)
   expect(getModelMaxOutputTokens('gpt-5.4')).toEqual({
@@ -98,6 +109,7 @@ test('gpt-5.4 family keeps large max output overrides within provider limits', (
 test('MiniMax-M2.7 uses explicit provider-specific context and output caps', () => {
   process.env.CLAUDE_CODE_USE_OPENAI = '1'
   delete process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS
+  delete process.env.OPENAI_MODEL
 
   expect(getContextWindowForModel('MiniMax-M2.7')).toBe(204_800)
   expect(getModelMaxOutputTokens('MiniMax-M2.7')).toEqual({
@@ -110,6 +122,7 @@ test('MiniMax-M2.7 uses explicit provider-specific context and output caps', ()
 test('unknown openai-compatible models use the 128k fallback window (not 8k, see #635)', () => {
   process.env.CLAUDE_CODE_USE_OPENAI = '1'
   delete process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS
+  delete process.env.OPENAI_MODEL
 
   expect(getContextWindowForModel('some-unknown-3p-model')).toBe(128_000)
 })
@@ -117,6 +130,7 @@ test('unknown openai-compatible models use the 128k fallback window (not 8k, see
 test('MiniMax-M2.5 and M2.1 use explicit provider-specific context and output caps', () => {
   process.env.CLAUDE_CODE_USE_OPENAI = '1'
   delete process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS
+  delete process.env.OPENAI_MODEL
 
   expect(getContextWindowForModel('MiniMax-M2.5')).toBe(204_800)
   expect(getContextWindowForModel('MiniMax-M2.5-highspeed')).toBe(204_800)
@@ -127,3 +141,116 @@ test('MiniMax-M2.5 and M2.1 use explicit provider-specific context and output ca
     upperLimit: 131_072,
   })
 })
+
+test('DashScope qwen3.6-plus uses provider-specific context and output caps', () => {
+  process.env.CLAUDE_CODE_USE_OPENAI = '1'
+  delete process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS
+
+  expect(getContextWindowForModel('qwen3.6-plus')).toBe(1_000_000)
+  expect(getModelMaxOutputTokens('qwen3.6-plus')).toEqual({
+    default: 65_536,
+    upperLimit: 65_536,
+  })
+  expect(getMaxOutputTokensForModel('qwen3.6-plus')).toBe(65_536)
+})
+
+test('DashScope qwen3.5-plus uses provider-specific context and output caps', () => {
+  process.env.CLAUDE_CODE_USE_OPENAI = '1'
+  delete process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS
+
+  expect(getContextWindowForModel('qwen3.5-plus')).toBe(1_000_000)
+  expect(getModelMaxOutputTokens('qwen3.5-plus')).toEqual({
+    default: 65_536,
+    upperLimit: 65_536,
+  })
+  expect(getMaxOutputTokensForModel('qwen3.5-plus')).toBe(65_536)
+})
+
+test('DashScope qwen3-coder-plus uses provider-specific context and output caps', () => {
+  process.env.CLAUDE_CODE_USE_OPENAI = '1'
+  delete process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS
+
+  expect(getContextWindowForModel('qwen3-coder-plus')).toBe(1_000_000)
+  expect(getModelMaxOutputTokens('qwen3-coder-plus')).toEqual({
+    default: 65_536,
+    upperLimit: 65_536,
+  })
+})
+
+test('DashScope qwen3-coder-next uses provider-specific context and output caps', () => {
+  process.env.CLAUDE_CODE_USE_OPENAI = '1'
+  delete process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS
+
+  expect(getContextWindowForModel('qwen3-coder-next')).toBe(262_144)
+  expect(getModelMaxOutputTokens('qwen3-coder-next')).toEqual({
+    default: 65_536,
+    upperLimit: 65_536,
+  })
+})
+
+test('DashScope qwen3-max uses provider-specific context and output caps', () => {
+  process.env.CLAUDE_CODE_USE_OPENAI = '1'
+  delete process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS
+
+  expect(getContextWindowForModel('qwen3-max')).toBe(262_144)
+  expect(getModelMaxOutputTokens('qwen3-max')).toEqual({
+    default: 32_768,
+    upperLimit: 32_768,
+  })
+})
+
+test('DashScope qwen3-max dated variant resolves to base entry via prefix match', () => {
+  process.env.CLAUDE_CODE_USE_OPENAI = '1'
+  delete process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS
+
+  expect(getContextWindowForModel('qwen3-max-2026-01-23')).toBe(262_144)
+  expect(getModelMaxOutputTokens('qwen3-max-2026-01-23')).toEqual({
+    default: 32_768,
+    upperLimit: 32_768,
+  })
+})
+
+test('DashScope kimi-k2.5 uses provider-specific context and output caps', () => {
+  process.env.CLAUDE_CODE_USE_OPENAI = '1'
+  delete process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS
+
+  expect(getContextWindowForModel('kimi-k2.5')).toBe(262_144)
+  expect(getModelMaxOutputTokens('kimi-k2.5')).toEqual({
+    default: 32_768,
+    upperLimit: 32_768,
+  })
+})
+
+test('DashScope glm-5 uses provider-specific context and output caps', () => {
+  process.env.CLAUDE_CODE_USE_OPENAI = '1'
+  delete process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS
+
+  expect(getContextWindowForModel('glm-5')).toBe(202_752)
+  expect(getModelMaxOutputTokens('glm-5')).toEqual({
+    default: 16_384,
+    upperLimit: 16_384,
+  })
+})
+
+test('DashScope glm-4.7 uses provider-specific context and output caps', () => {
+  process.env.CLAUDE_CODE_USE_OPENAI = '1'
+  delete process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS
+
+  expect(getContextWindowForModel('glm-4.7')).toBe(202_752)
+  expect(getModelMaxOutputTokens('glm-4.7')).toEqual({
+    default: 16_384,
+    upperLimit: 16_384,
+  })
+})
+
+test('DashScope models clamp oversized max output overrides to the provider limit', () => {
+  process.env.CLAUDE_CODE_USE_OPENAI = '1'
+  process.env.CLAUDE_CODE_MAX_OUTPUT_TOKENS = '100000'
+
+  expect(getMaxOutputTokensForModel('qwen3.6-plus')).toBe(65_536)
+  expect(getMaxOutputTokensForModel('qwen3.5-plus')).toBe(65_536)
+  expect(getMaxOutputTokensForModel('qwen3-coder-next')).toBe(65_536)
+  expect(getMaxOutputTokensForModel('qwen3-max')).toBe(32_768)
+  expect(getMaxOutputTokensForModel('kimi-k2.5')).toBe(32_768)
+  expect(getMaxOutputTokensForModel('glm-5')).toBe(16_384)
+})

src/utils/deepLink/registerProtocol.ts

@@ -253,7 +253,7 @@ async function resolveClaudePath(): Promise<string> {
  * Check whether the OS-level protocol handler is already registered AND
  * points at the expected `claude` binary. Reads the registration artifact
  * directly (symlink target, .desktop Exec line, registry value) rather than
- * a cached flag in ~/.claude.json, so:
+ * a cached flag in ~/.openclaude.json, so:
  *   - the check is per-machine (config can sync across machines; OS state can't)
  *   - stale paths self-heal (install-method change → re-register next session)
  *   - deleted artifacts self-heal
@@ -311,7 +311,7 @@ export async function ensureDeepLinkProtocolRegistered(): Promise<void> {
   // EACCES/ENOSPC are deterministic — retrying next session won't help.
   // Throttle to once per 24h so a read-only ~/.local/share/applications
   // doesn't generate a failure event on every startup. Marker lives in
-  // ~/.claude (per-machine, not synced) rather than ~/.claude.json (can sync).
+  // ~/.claude (per-machine, not synced) rather than ~/.openclaude.json (can sync).
   const failureMarkerPath = path.join(
     getClaudeConfigHomeDir(),
     '.deep-link-register-failed',

src/utils/env.test.ts

@@ -0,0 +1,62 @@
+import { afterEach, beforeEach, expect, test } from 'bun:test'
+import { mkdtempSync, rmSync, writeFileSync } from 'fs'
+import { tmpdir } from 'os'
+import { join } from 'path'
+
+const originalEnv = {
+  CLAUDE_CONFIG_DIR: process.env.CLAUDE_CONFIG_DIR,
+  CLAUDE_CODE_CUSTOM_OAUTH_URL: process.env.CLAUDE_CODE_CUSTOM_OAUTH_URL,
+  USER_TYPE: process.env.USER_TYPE,
+}
+
+let tempDir: string
+
+beforeEach(() => {
+  tempDir = mkdtempSync(join(tmpdir(), 'openclaude-env-test-'))
+  process.env.CLAUDE_CONFIG_DIR = tempDir
+  delete process.env.CLAUDE_CODE_CUSTOM_OAUTH_URL
+  delete process.env.USER_TYPE
+})
+
+afterEach(() => {
+  rmSync(tempDir, { recursive: true, force: true })
+  if (originalEnv.CLAUDE_CONFIG_DIR === undefined) {
+    delete process.env.CLAUDE_CONFIG_DIR
+  } else {
+    process.env.CLAUDE_CONFIG_DIR = originalEnv.CLAUDE_CONFIG_DIR
+  }
+  if (originalEnv.CLAUDE_CODE_CUSTOM_OAUTH_URL === undefined) {
+    delete process.env.CLAUDE_CODE_CUSTOM_OAUTH_URL
+  } else {
+    process.env.CLAUDE_CODE_CUSTOM_OAUTH_URL = originalEnv.CLAUDE_CODE_CUSTOM_OAUTH_URL
+  }
+  if (originalEnv.USER_TYPE === undefined) {
+    delete process.env.USER_TYPE
+  } else {
+    process.env.USER_TYPE = originalEnv.USER_TYPE
+  }
+})
+
+async function importFreshEnvModule() {
+  return import(`./env.js?ts=${Date.now()}-${Math.random()}`)
+}
+
+// getGlobalClaudeFile — three migration branches
+
+test('getGlobalClaudeFile: new install returns .openclaude.json when neither file exists', async () => {
+  const { getGlobalClaudeFile } = await importFreshEnvModule()
+  expect(getGlobalClaudeFile()).toBe(join(tempDir, '.openclaude.json'))
+})
+
+test('getGlobalClaudeFile: existing user keeps .claude.json when only legacy file exists', async () => {
+  writeFileSync(join(tempDir, '.claude.json'), '{}')
+  const { getGlobalClaudeFile } = await importFreshEnvModule()
+  expect(getGlobalClaudeFile()).toBe(join(tempDir, '.claude.json'))
+})
+
+test('getGlobalClaudeFile: migrated user uses .openclaude.json when both files exist', async () => {
+  writeFileSync(join(tempDir, '.claude.json'), '{}')
+  writeFileSync(join(tempDir, '.openclaude.json'), '{}')
+  const { getGlobalClaudeFile } = await importFreshEnvModule()
+  expect(getGlobalClaudeFile()).toBe(join(tempDir, '.openclaude.json'))
+})

src/utils/env.ts

@@ -21,8 +21,21 @@ export const getGlobalClaudeFile = memoize((): string => {
     return join(getClaudeConfigHomeDir(), '.config.json')
   }
 
-  const filename = `.claude${fileSuffixForOauthConfig()}.json`
+  const oauthSuffix = fileSuffixForOauthConfig()
-  return join(process.env.CLAUDE_CONFIG_DIR || homedir(), filename)
+  const configDir = process.env.CLAUDE_CONFIG_DIR || homedir()
+
+  // Default to .openclaude.json. Fall back to .claude.json only if the new
+  // file doesn't exist yet and the legacy one does (same migration pattern
+  // as resolveClaudeConfigHomeDir for the config directory).
+  const newFilename = `.openclaude${oauthSuffix}.json`
+  const legacyFilename = `.claude${oauthSuffix}.json`
+  if (
+    !getFsImplementation().existsSync(join(configDir, newFilename)) &&
+    getFsImplementation().existsSync(join(configDir, legacyFilename))
+  ) {
+    return join(configDir, legacyFilename)
+  }
+  return join(configDir, newFilename)
 })
 
 const hasInternetAccess = memoize(async (): Promise<boolean> => {

src/utils/json.ts

@@ -24,7 +24,7 @@ type CachedParse = { ok: true; value: unknown } | { ok: false }
 // lodash memoize default resolver = first arg only).
 // Skip caching above this size — the LRU stores the full string as the key,
 // so a 200KB config file would pin ~10MB in #keyList across 50 slots. Large
-// inputs like ~/.claude.json also change between reads (numStartups bumps on
+// inputs like ~/.openclaude.json also change between reads (numStartups bumps on
 // every CC startup), so the cache never hits anyway.
 const PARSE_CACHE_MAX_KEY_BYTES = 8 * 1024
 

src/utils/localInstaller.ts

@@ -44,9 +44,10 @@ function getCandidateLocalBinaryPaths(localInstallDir: string): string[] {
 }
 
 export function isManagedLocalInstallationPath(execPath: string): boolean {
+  const normalizedExecPath = execPath.replace(/\\+/g, '/')
   return (
-    execPath.includes('/.openclaude/local/node_modules/') ||
+    normalizedExecPath.includes('/.openclaude/local/node_modules/') ||
-    execPath.includes('/.claude/local/node_modules/')
+    normalizedExecPath.includes('/.claude/local/node_modules/')
   )
 }
 

src/utils/managedEnv.ts

@@ -131,7 +131,7 @@ export function applySafeConfigEnvironmentVariables(): void {
         : null
   }
 
-  // Global config (~/.claude.json) is user-controlled. In CCD mode,
+  // Global config (~/.openclaude.json) is user-controlled. In CCD mode,
   // filterSettingsEnv strips keys that were in the spawn env snapshot so
   // the desktop host's operational vars (OTEL, etc.) are not overridden.
   Object.assign(process.env, filterSettingsEnv(getGlobalConfig().env))

src/utils/managedEnvConstants.ts

@@ -123,7 +123,6 @@ export const SAFE_ENV_VARS = new Set([
   'ANTHROPIC_DEFAULT_SONNET_MODEL_DESCRIPTION',
   'ANTHROPIC_DEFAULT_SONNET_MODEL_NAME',
   'ANTHROPIC_DEFAULT_SONNET_MODEL_SUPPORTED_CAPABILITIES',
-  'ANTHROPIC_FOUNDRY_API_KEY',
   'ANTHROPIC_MODEL',
   'ANTHROPIC_SMALL_FAST_MODEL_AWS_REGION',
   'ANTHROPIC_SMALL_FAST_MODEL',

src/utils/model/configs.ts

@@ -37,6 +37,8 @@ export const CLAUDE_3_7_SONNET_CONFIG = {
   gemini: 'gemini-2.0-flash',
   github: 'github:copilot',
   codex: 'gpt-5.4',
+  'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
+  minimax: 'MiniMax-M2.5',
 } as const satisfies ModelConfig
 
 export const CLAUDE_3_5_V2_SONNET_CONFIG = {
@@ -48,6 +50,8 @@ export const CLAUDE_3_5_V2_SONNET_CONFIG = {
   gemini: 'gemini-2.0-flash',
   github: 'github:copilot',
   codex: 'gpt-5.4',
+  'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
+  minimax: 'MiniMax-M2.5',
 } as const satisfies ModelConfig
 
 export const CLAUDE_3_5_HAIKU_CONFIG = {
@@ -59,6 +63,8 @@ export const CLAUDE_3_5_HAIKU_CONFIG = {
   gemini: 'gemini-2.0-flash-lite',
   github: 'github:copilot',
   codex: 'gpt-5.4',
+  'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
+  minimax: 'MiniMax-M2.5',
 } as const satisfies ModelConfig
 
 export const CLAUDE_HAIKU_4_5_CONFIG = {
@@ -70,6 +76,8 @@ export const CLAUDE_HAIKU_4_5_CONFIG = {
   gemini: 'gemini-2.0-flash-lite',
   github: 'github:copilot',
   codex: 'gpt-5.4',
+  'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
+  minimax: 'MiniMax-M2.5',
 } as const satisfies ModelConfig
 
 export const CLAUDE_SONNET_4_CONFIG = {
@@ -81,6 +89,8 @@ export const CLAUDE_SONNET_4_CONFIG = {
   gemini: 'gemini-2.0-flash',
   github: 'github:copilot',
   codex: 'gpt-5.4',
+  'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
+  minimax: 'MiniMax-M2.5',
 } as const satisfies ModelConfig
 
 export const CLAUDE_SONNET_4_5_CONFIG = {
@@ -92,6 +102,8 @@ export const CLAUDE_SONNET_4_5_CONFIG = {
   gemini: 'gemini-2.0-flash',
   github: 'github:copilot',
   codex: 'gpt-5.4',
+  'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
+  minimax: 'MiniMax-M2.5',
 } as const satisfies ModelConfig
 
 export const CLAUDE_OPUS_4_CONFIG = {
@@ -103,6 +115,8 @@ export const CLAUDE_OPUS_4_CONFIG = {
   gemini: 'gemini-2.5-pro-preview-03-25',
   github: 'github:copilot',
   codex: 'gpt-5.4',
+  'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
+  minimax: 'MiniMax-M2.5',
 } as const satisfies ModelConfig
 
 export const CLAUDE_OPUS_4_1_CONFIG = {
@@ -114,6 +128,8 @@ export const CLAUDE_OPUS_4_1_CONFIG = {
   gemini: 'gemini-2.5-pro-preview-03-25',
   github: 'github:copilot',
   codex: 'gpt-5.4',
+  'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
+  minimax: 'MiniMax-M2.5',
 } as const satisfies ModelConfig
 
 export const CLAUDE_OPUS_4_5_CONFIG = {
@@ -125,6 +141,8 @@ export const CLAUDE_OPUS_4_5_CONFIG = {
   gemini: 'gemini-2.5-pro-preview-03-25',
   github: 'github:copilot',
   codex: 'gpt-5.4',
+  'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
+  minimax: 'MiniMax-M2.5',
 } as const satisfies ModelConfig
 
 export const CLAUDE_OPUS_4_6_CONFIG = {
@@ -136,6 +154,8 @@ export const CLAUDE_OPUS_4_6_CONFIG = {
   gemini: 'gemini-2.5-pro-preview-03-25',
   github: 'github:copilot',
   codex: 'gpt-5.4',
+  'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
+  minimax: 'MiniMax-M2.5',
 } as const satisfies ModelConfig
 
 export const CLAUDE_SONNET_4_6_CONFIG = {
@@ -147,6 +167,8 @@ export const CLAUDE_SONNET_4_6_CONFIG = {
   gemini: 'gemini-2.0-flash',
   github: 'github:copilot',
   codex: 'gpt-5.4',
+  'nvidia-nim': 'nvidia/llama-3.1-nemotron-70b-instruct',
+  minimax: 'MiniMax-M2.5',
 } as const satisfies ModelConfig
 
 // @[MODEL LAUNCH]: Register the new config here.

src/utils/model/minimaxModels.ts

@@ -0,0 +1,46 @@
+/**
+ * MiniMax model list for the /model picker.
+ * Full model catalog from MiniMax API.
+ */
+
+import type { ModelOption } from './modelOptions.js'
+import { getAPIProvider } from './providers.js'
+import { isEnvTruthy } from '../envUtils.js'
+
+export function isMiniMaxProvider(): boolean {
+  if (isEnvTruthy(process.env.MINIMAX_API_KEY)) {
+    return true
+  }
+  const baseUrl = process.env.OPENAI_BASE_URL ?? ''
+  if (baseUrl.includes('minimax')) {
+    return true
+  }
+  return getAPIProvider() === 'minimax'
+}
+
+function getMiniMaxModels(): ModelOption[] {
+  return [
+    // Latest Generation Models - use correct MiniMax naming with M prefix
+    { value: 'MiniMax-M2', label: 'MiniMax M2', description: 'MoE model - 131K context - Chat/Code/Reasoning' },
+    { value: 'MiniMax-M2.1', label: 'MiniMax M2.1', description: 'Enhanced - 200K context - Vision' },
+    { value: 'MiniMax-M2.5', label: 'MiniMax M2.5', description: 'Flagship - 256K context - Vision/Function-calling' },
+    { value: 'MiniMax-Text-01', label: 'MiniMax Text 01', description: 'Text-focused - 512K context - FREE' },
+    { value: 'MiniMax-Text-01-Preview', label: 'MiniMax Text 01 Preview', description: 'Preview - 256K context - FREE' },
+    { value: 'MiniMax-Vision-01', label: 'MiniMax Vision 01', description: 'Vision model - 32K context' },
+    { value: 'MiniMax-Vision-01-Fast', label: 'MiniMax Vision 01 Fast', description: 'Fast vision - 16K context - FREE' },
+    // Legacy free tier models
+    { value: 'abab6.5s-chat', label: 'ABAB 6.5S Chat', description: 'Legacy free - 16K context' },
+    { value: 'abab6.5-chat', label: 'ABAB 6.5 Chat', description: 'Legacy free - 32K context' },
+    { value: 'abab6.5g-chat', label: 'ABAB 6.5G Chat', description: 'Generation 6.5 - 32K context' },
+    { value: 'abab6-chat', label: 'ABAB 6 Chat', description: 'Legacy - 8K context' },
+  ]
+}
+
+let cachedMiniMaxOptions: ModelOption[] | null = null
+
+export function getCachedMiniMaxModelOptions(): ModelOption[] {
+  if (!cachedMiniMaxOptions) {
+    cachedMiniMaxOptions = getMiniMaxModels()
+  }
+  return cachedMiniMaxOptions
+}

src/utils/model/model.github.test.ts

@@ -0,0 +1,57 @@
+import { afterEach, beforeEach, expect, test } from 'bun:test'
+
+import { saveGlobalConfig } from '../config.js'
+import { getDefaultMainLoopModelSetting, getUserSpecifiedModelSetting } from './model.js'
+
+const env = {
+  CLAUDE_CODE_USE_GITHUB: process.env.CLAUDE_CODE_USE_GITHUB,
+  CLAUDE_CODE_USE_OPENAI: process.env.CLAUDE_CODE_USE_OPENAI,
+  CLAUDE_CODE_USE_GEMINI: process.env.CLAUDE_CODE_USE_GEMINI,
+  CLAUDE_CODE_USE_BEDROCK: process.env.CLAUDE_CODE_USE_BEDROCK,
+  CLAUDE_CODE_USE_VERTEX: process.env.CLAUDE_CODE_USE_VERTEX,
+  CLAUDE_CODE_USE_FOUNDRY: process.env.CLAUDE_CODE_USE_FOUNDRY,
+  OPENAI_MODEL: process.env.OPENAI_MODEL,
+}
+
+beforeEach(() => {
+  process.env.CLAUDE_CODE_USE_GITHUB = '1'
+  delete process.env.CLAUDE_CODE_USE_OPENAI
+  delete process.env.CLAUDE_CODE_USE_GEMINI
+  delete process.env.CLAUDE_CODE_USE_BEDROCK
+  delete process.env.CLAUDE_CODE_USE_VERTEX
+  delete process.env.CLAUDE_CODE_USE_FOUNDRY
+  delete process.env.OPENAI_MODEL
+  saveGlobalConfig(current => ({
+    ...current,
+    model: ({ bad: true } as unknown) as string,
+  }))
+})
+
+afterEach(() => {
+  process.env.CLAUDE_CODE_USE_GITHUB = env.CLAUDE_CODE_USE_GITHUB
+  process.env.CLAUDE_CODE_USE_OPENAI = env.CLAUDE_CODE_USE_OPENAI
+  process.env.CLAUDE_CODE_USE_GEMINI = env.CLAUDE_CODE_USE_GEMINI
+  process.env.CLAUDE_CODE_USE_BEDROCK = env.CLAUDE_CODE_USE_BEDROCK
+  process.env.CLAUDE_CODE_USE_VERTEX = env.CLAUDE_CODE_USE_VERTEX
+  process.env.CLAUDE_CODE_USE_FOUNDRY = env.CLAUDE_CODE_USE_FOUNDRY
+  process.env.OPENAI_MODEL = env.OPENAI_MODEL
+  saveGlobalConfig(current => ({
+    ...current,
+    model: undefined,
+  }))
+})
+
+test('github default model setting ignores non-string saved model', () => {
+  const model = getDefaultMainLoopModelSetting()
+  expect(typeof model).toBe('string')
+  expect(model).not.toBe('[object Object]')
+  expect(model.length).toBeGreaterThan(0)
+})
+
+test('user specified model ignores non-string saved model', () => {
+  const model = getUserSpecifiedModelSetting()
+  if (model !== undefined && model !== null) {
+    expect(typeof model).toBe('string')
+    expect(model).not.toBe('[object Object]')
+  }
+})

src/utils/model/model.ts

@@ -33,6 +33,12 @@ export type ModelShortName = string
 export type ModelName = string
 export type ModelSetting = ModelName | ModelAlias | null
 
+function normalizeModelSetting(value: unknown): ModelName | ModelAlias | undefined {
+  if (typeof value !== 'string') return undefined
+  const trimmed = value.trim()
+  return trimmed.length > 0 ? trimmed : undefined
+}
+
 export function getSmallFastModel(): ModelName {
   if (process.env.ANTHROPIC_SMALL_FAST_MODEL) return process.env.ANTHROPIC_SMALL_FAST_MODEL
   // For Gemini provider, use a fast model
@@ -82,6 +88,7 @@ export function getUserSpecifiedModelSetting(): ModelSetting | undefined {
     specifiedModel = modelOverride
   } else {
     const settings = getSettings_DEPRECATED() || {}
+    const setting = normalizeModelSetting(settings.model)
     // Read the model env var that matches the active provider to prevent
     // cross-provider leaks (e.g. ANTHROPIC_MODEL sent to the OpenAI API).
     const provider = getAPIProvider()
@@ -90,7 +97,7 @@ export function getUserSpecifiedModelSetting(): ModelSetting | undefined {
       (provider === 'mistral' ? process.env.MISTRAL_MODEL : undefined) ||
       (provider === 'openai' || provider === 'gemini' || provider === 'mistral' || provider === 'github' ? process.env.OPENAI_MODEL : undefined) ||
       (provider === 'firstParty' ? process.env.ANTHROPIC_MODEL : undefined) ||
-      settings.model ||
+      setting ||
       undefined
   }
 
@@ -264,7 +271,11 @@ export function getDefaultMainLoopModelSetting(): ModelName | ModelAlias {
   // GitHub Copilot provider: check settings.model first, then env, then default
   if (getAPIProvider() === 'github') {
     const settings = getSettings_DEPRECATED() || {}
-    return settings.model || process.env.OPENAI_MODEL || 'github:copilot'
+    return (
+      normalizeModelSetting(settings.model) ||
+      normalizeModelSetting(process.env.OPENAI_MODEL) ||
+      'github:copilot'
+    )
   }
   // Gemini provider: always use the configured Gemini model
   if (getAPIProvider() === 'gemini') {
@@ -595,7 +606,10 @@ export function getPublicModelName(model: ModelName): string {
 export function parseUserSpecifiedModel(
   modelInput: ModelName | ModelAlias,
 ): ModelName {
-  const modelInputTrimmed = modelInput.trim()
+  const modelInputTrimmed = normalizeModelSetting(modelInput)
+  if (!modelInputTrimmed) {
+    return getDefaultSonnetModel()
+  }
   const normalizedModel = modelInputTrimmed.toLowerCase()
 
   const has1mTag = has1mContext(normalizedModel)

src/utils/model/modelOptions.ts

@@ -33,8 +33,14 @@ import {
 } from './model.js'
 import { has1mContext } from '../context.js'
 import { getGlobalConfig } from '../config.js'
-import { getActiveOpenAIModelOptionsCache } from '../providerProfiles.js'
+import {
+  getActiveOpenAIModelOptionsCache,
+  getActiveProviderProfile,
+  getProfileModelOptions,
+} from '../providerProfiles.js'
 import { getCachedOllamaModelOptions, isOllamaProvider } from './ollamaModels.js'
+import { getCachedNvidiaNimModelOptions, isNvidiaNimProvider } from './nvidiaNimModels.js'
+import { getCachedMiniMaxModelOptions, isMiniMaxProvider } from './minimaxModels.js'
 import { getAntModels } from './antModels.js'
 
 // @[MODEL LAUNCH]: Update all the available and default model option strings below.
@@ -390,6 +396,26 @@ function getModelOptionsBase(fastMode = false): ModelOption[] {
     return [defaultOption]
   }
 
+  // When using NVIDIA NIM, show models from the NVIDIA catalog
+  if (isNvidiaNimProvider()) {
+    const defaultOption = getDefaultOptionForUser(fastMode)
+    const nvidiaModels = getCachedNvidiaNimModelOptions()
+    if (nvidiaModels.length > 0) {
+      return [defaultOption, ...nvidiaModels]
+    }
+    return [defaultOption]
+  }
+
+  // When using MiniMax, show models from the MiniMax catalog
+  if (isMiniMaxProvider()) {
+    const defaultOption = getDefaultOptionForUser(fastMode)
+    const minimaxModels = getCachedMiniMaxModelOptions()
+    if (minimaxModels.length > 0) {
+      return [defaultOption, ...minimaxModels]
+    }
+    return [defaultOption]
+  }
+
   if (process.env.USER_TYPE === 'ant') {
     // Build options from antModels config
     const antModelOptions: ModelOption[] = getAntModels().map(m => ({
@@ -454,6 +480,20 @@ function getModelOptionsBase(fastMode = false): ModelOption[] {
     ]
   }
 
+  // When a provider profile's env is applied, collect its models so they
+  // can be appended to the standard picker options below.
+  // We check PROFILE_ENV_APPLIED to avoid the ?? profiles[0] fallback in
+  // getActiveProviderProfile which would affect users with inactive profiles.
+  const profileEnvApplied = process.env.CLAUDE_CODE_PROVIDER_PROFILE_ENV_APPLIED === '1'
+  const profileModelOptions: ModelOption[] = []
+  if (profileEnvApplied) {
+    const activeProfile = getActiveProviderProfile()
+    if (activeProfile) {
+      const models = getProfileModelOptions(activeProfile)
+      profileModelOptions.push(...models)
+    }
+  }
+
   // PAYG 1P API: Default (Sonnet) + Sonnet 1M + Opus 4.6 + Opus 1M + Haiku
   if (getAPIProvider() === 'firstParty') {
     const payg1POptions = [getDefaultOptionForUser(fastMode)]
@@ -469,6 +509,7 @@ function getModelOptionsBase(fastMode = false): ModelOption[] {
       }
     }
     payg1POptions.push(getHaiku45Option())
+    payg1POptions.push(...profileModelOptions)
     return payg1POptions
   }
 
@@ -508,6 +549,7 @@ function getModelOptionsBase(fastMode = false): ModelOption[] {
   } else {
     payg3pOptions.push(getHaikuOption())
   }
+  payg3pOptions.push(...profileModelOptions)
   return payg3pOptions
 }
 

src/utils/model/nvidiaNimModels.ts

@@ -0,0 +1,161 @@
+/**
+ * NVIDIA NIM model list for the /model picker.
+ * Filtered to chat/instruct models only - embedding, reward, safety, vision, etc. excluded.
+ */
+
+import type { ModelOption } from './modelOptions.js'
+import { getAPIProvider } from './providers.js'
+import { isEnvTruthy } from '../envUtils.js'
+
+export function isNvidiaNimProvider(): boolean {
+  // Check if explicitly set via NVIDIA_NIM or via provider flag
+  if (isEnvTruthy(process.env.NVIDIA_NIM)) {
+    return true
+  }
+  // Also check if using NVIDIA NIM endpoint
+  const baseUrl = process.env.OPENAI_BASE_URL ?? ''
+  if (baseUrl.includes('nvidia') || baseUrl.includes('integrate.api.nvidia')) {
+    return true
+  }
+  return getAPIProvider() === 'nvidia-nim'
+}
+
+function getNvidiaNimModels(): ModelOption[] {
+  return [
+    // AGENTIC REASONING MODELS
+    { value: 'nvidia/cosmos-reason2-8b', label: 'Cosmos Reason 2 8B', description: 'Reasoning' },
+    { value: 'microsoft/phi-4-mini-flash-reasoning', label: 'Phi 4 Mini Flash Reasoning', description: 'Reasoning' },
+    { value: 'qwen/qwen3-next-80b-a3b-thinking', label: 'Qwen 3 Next 80B Thinking', description: 'Reasoning' },
+    { value: 'deepseek-ai/deepseek-r1-distill-qwen-32b', label: 'DeepSeek R1 Qwen 32B', description: 'Reasoning' },
+    { value: 'deepseek-ai/deepseek-r1-distill-qwen-14b', label: 'DeepSeek R1 Qwen 14B', description: 'Reasoning' },
+    { value: 'deepseek-ai/deepseek-r1-distill-qwen-7b', label: 'DeepSeek R1 Qwen 7B', description: 'Reasoning' },
+    { value: 'deepseek-ai/deepseek-r1-distill-llama-8b', label: 'DeepSeek R1 Llama 8B', description: 'Reasoning' },
+    { value: 'qwen/qwq-32b', label: 'QwQ 32B Reasoning', description: 'Reasoning' },
+    // CODE MODELS
+    { value: 'meta/codellama-70b', label: 'CodeLlama 70B', description: 'Code' },
+    { value: 'bigcode/starcoder2-15b', label: 'StarCoder2 15B', description: 'Code' },
+    { value: 'bigcode/starcoder2-7b', label: 'StarCoder2 7B', description: 'Code' },
+    { value: 'mistralai/codestral-22b-instruct-v0.1', label: 'Codestral 22B', description: 'Code' },
+    { value: 'mistralai/mamba-codestral-7b-v0.1', label: 'Mamba Codestral 7B', description: 'Code' },
+    { value: 'deepseek-ai/deepseek-coder-6.7b-instruct', label: 'DeepSeek Coder 6.7B', description: 'Code' },
+    { value: 'google/codegemma-7b', label: 'CodeGemma 7B', description: 'Code' },
+    { value: 'google/codegemma-1.1-7b', label: 'CodeGemma 1.1 7B', description: 'Code' },
+    { value: 'qwen/qwen2.5-coder-32b-instruct', label: 'Qwen 2.5 Coder 32B', description: 'Code' },
+    { value: 'qwen/qwen2.5-coder-7b-instruct', label: 'Qwen 2.5 Coder 7B', description: 'Code' },
+    { value: 'qwen/qwen3-coder-480b-a35b-instruct', label: 'Qwen 3 Coder 480B', description: 'Code' },
+    { value: 'ibm/granite-34b-code-instruct', label: 'Granite 34B Code', description: 'Code' },
+    { value: 'ibm/granite-8b-code-instruct', label: 'Granite 8B Code', description: 'Code' },
+    // NEMOTRON MODELS - NVIDIA Flagship
+    { value: 'nvidia/llama-3.1-nemotron-70b-instruct', label: 'Nemotron 70B Instruct', description: 'NVIDIA Flagship' },
+    { value: 'nvidia/llama-3.1-nemotron-51b-instruct', label: 'Nemotron 51B Instruct', description: 'NVIDIA Flagship' },
+    { value: 'nvidia/llama-3.1-nemotron-ultra-253b-v1', label: 'Nemotron Ultra 253B', description: 'NVIDIA Flagship' },
+    { value: 'nvidia/llama-3.3-nemotron-super-49b-v1', label: 'Nemotron Super 49B v1', description: 'NVIDIA Flagship' },
+    { value: 'nvidia/llama-3.3-nemotron-super-49b-v1.5', label: 'Nemotron Super 49B v1.5', description: 'NVIDIA Flagship' },
+    { value: 'nvidia/nemotron-4-340b-instruct', label: 'Nemotron 4 340B', description: 'NVIDIA Flagship' },
+    { value: 'nvidia/nemotron-3-super-120b-a12b', label: 'Nemotron 3 Super 120B', description: 'NVIDIA Flagship' },
+    { value: 'nvidia/nemotron-3-nano-30b-a3b', label: 'Nemotron 3 Nano 30B', description: 'NVIDIA Flagship' },
+    { value: 'nvidia/nemotron-mini-4b-instruct', label: 'Nemotron Mini 4B', description: 'NVIDIA Flagship' },
+    { value: 'nvidia/llama-3.1-nemotron-nano-8b-v1', label: 'Nemotron Nano 8B', description: 'NVIDIA Flagship' },
+    { value: 'nvidia/llama-3.1-nemotron-nano-4b-v1.1', label: 'Nemotron Nano 4B v1.1', description: 'NVIDIA Flagship' },
+    // CHATQA MODELS
+    { value: 'nvidia/llama3-chatqa-1.5-70b', label: 'Llama3 ChatQA 1.5 70B', description: 'Chat' },
+    { value: 'nvidia/llama3-chatqa-1.5-8b', label: 'Llama3 ChatQA 1.5 8B', description: 'Chat' },
+    // META LLAMA MODELS
+    { value: 'meta/llama-3.1-405b-instruct', label: 'Llama 3.1 405B', description: 'Meta Llama' },
+    { value: 'meta/llama-3.1-70b-instruct', label: 'Llama 3.1 70B', description: 'Meta Llama' },
+    { value: 'meta/llama-3.1-8b-instruct', label: 'Llama 3.1 8B', description: 'Meta Llama' },
+    { value: 'meta/llama-3.2-90b-vision-instruct', label: 'Llama 3.2 90B Vision', description: 'Meta Llama' },
+    { value: 'meta/llama-3.2-11b-vision-instruct', label: 'Llama 3.2 11B Vision', description: 'Meta Llama' },
+    { value: 'meta/llama-3.2-3b-instruct', label: 'Llama 3.2 3B', description: 'Meta Llama' },
+    { value: 'meta/llama-3.2-1b-instruct', label: 'Llama 3.2 1B', description: 'Meta Llama' },
+    { value: 'meta/llama-3.3-70b-instruct', label: 'Llama 3.3 70B', description: 'Meta Llama' },
+    { value: 'meta/llama-4-maverick-17b-128e-instruct', label: 'Llama 4 Maverick 17B', description: 'Meta Llama' },
+    { value: 'meta/llama-4-scout-17b-16e-instruct', label: 'Llama 4 Scout 17B', description: 'Meta Llama' },
+    // GOOGLE GEMMA MODELS (text only - no vision)
+    { value: 'google/gemma-4-31b-it', label: 'Gemma 4 31B', description: 'Google Gemma' },
+    { value: 'google/gemma-3-27b-it', label: 'Gemma 3 27B', description: 'Google Gemma' },
+    { value: 'google/gemma-3-12b-it', label: 'Gemma 3 12B', description: 'Google Gemma' },
+    { value: 'google/gemma-3-4b-it', label: 'Gemma 3 4B', description: 'Google Gemma' },
+    { value: 'google/gemma-3-1b-it', label: 'Gemma 3 1B', description: 'Google Gemma' },
+    { value: 'google/gemma-3n-e4b-it', label: 'Gemma 3N E4B', description: 'Google Gemma' },
+    { value: 'google/gemma-3n-e2b-it', label: 'Gemma 3N E2B', description: 'Google Gemma' },
+    { value: 'google/gemma-2-27b-it', label: 'Gemma 2 27B', description: 'Google Gemma' },
+    { value: 'google/gemma-2-9b-it', label: 'Gemma 2 9B', description: 'Google Gemma' },
+    { value: 'google/gemma-2-2b-it', label: 'Gemma 2 2B', description: 'Google Gemma' },
+    // MISTRAL MODELS
+    { value: 'mistralai/mistral-large-3-675b-instruct-2512', label: 'Mistral Large 3 675B', description: 'Mistral' },
+    { value: 'mistralai/mistral-large-2-instruct', label: 'Mistral Large 2', description: 'Mistral' },
+    { value: 'mistralai/mistral-large', label: 'Mistral Large', description: 'Mistral' },
+    { value: 'mistralai/mistral-medium-3-instruct', label: 'Mistral Medium 3', description: 'Mistral' },
+    { value: 'mistralai/mistral-small-4-119b-2603', label: 'Mistral Small 4 119B', description: 'Mistral' },
+    { value: 'mistralai/mistral-small-3.1-24b-instruct-2503', label: 'Mistral Small 3.1 24B', description: 'Mistral' },
+    { value: 'mistralai/mistral-small-24b-instruct', label: 'Mistral Small 24B', description: 'Mistral' },
+    { value: 'mistralai/mistral-7b-instruct-v0.3', label: 'Mistral 7B v0.3', description: 'Mistral' },
+    { value: 'mistralai/mistral-7b-instruct-v0.2', label: 'Mistral 7B v0.2', description: 'Mistral' },
+    { value: 'mistralai/mixtral-8x22b-instruct-v0.1', label: 'Mixtral 8x22B', description: 'Mistral' },
+    { value: 'mistralai/mixtral-8x22b-instruct-v0.1', label: 'Mixtral 8x22B Instruct', description: 'Mistral' },
+    { value: 'mistralai/mixtral-8x7b-instruct-v0.1', label: 'Mixtral 8x7B', description: 'Mistral' },
+    { value: 'mistralai/mistral-nemotron', label: 'Mistral Nemotron', description: 'Mistral' },
+    { value: 'mistralai/mathstral-7b-v0.1', label: 'Mathstral 7B', description: 'Math' },
+    { value: 'mistralai/ministral-14b-instruct-2512', label: 'Ministral 14B', description: 'Mistral' },
+    { value: 'mistralai/devstral-2-123b-instruct-2512', label: 'Devstral 2 123B', description: 'Code' },
+    { value: 'mistralai/magistral-small-2506', label: 'Magistral Small', description: 'Mistral' },
+    // MICROSOFT PHI MODELS (text only - no vision)
+    { value: 'microsoft/phi-4-multimodal-instruct', label: 'Phi 4 Multimodal', description: 'Multimodal' },
+    { value: 'microsoft/phi-4-mini-instruct', label: 'Phi 4 Mini', description: 'Phi' },
+    { value: 'microsoft/phi-3.5-mini-instruct', label: 'Phi 3.5 Mini', description: 'Phi' },
+    { value: 'microsoft/phi-3-small-128k-instruct', label: 'Phi 3 Small 128K', description: 'Phi' },
+    { value: 'microsoft/phi-3-small-8k-instruct', label: 'Phi 3 Small 8K', description: 'Phi' },
+    { value: 'microsoft/phi-3-medium-128k-instruct', label: 'Phi 3 Medium 128K', description: 'Phi' },
+    { value: 'microsoft/phi-3-medium-4k-instruct', label: 'Phi 3 Medium 4K', description: 'Phi' },
+    { value: 'microsoft/phi-3-mini-128k-instruct', label: 'Phi 3 Mini 128K', description: 'Phi' },
+    { value: 'microsoft/phi-3-mini-4k-instruct', label: 'Phi 3 Mini 4K', description: 'Phi' },
+    // QWEN MODELS
+    { value: 'qwen/qwen3.5-397b-a17b', label: 'Qwen 3.5 397B', description: 'Qwen' },
+    { value: 'qwen/qwen3.5-122b-a10b', label: 'Qwen 3.5 122B', description: 'Qwen' },
+    { value: 'qwen/qwen3-next-80b-a3b-instruct', label: 'Qwen 3 Next 80B', description: 'Qwen' },
+    { value: 'qwen/qwen2.5-7b-instruct', label: 'Qwen 2.5 7B', description: 'Qwen' },
+    { value: 'qwen/qwen2-7b-instruct', label: 'Qwen 2 7B', description: 'Qwen' },
+    { value: 'qwen/qwen3-32b', label: 'Qwen 3 32B', description: 'Qwen' },
+    { value: 'qwen/qwen3-8b', label: 'Qwen 3 8B', description: 'Qwen' },
+    // DEEPSEEK MODELS
+    { value: 'deepseek-ai/deepseek-r1', label: 'DeepSeek R1', description: 'DeepSeek' },
+    { value: 'deepseek-ai/deepseek-v3', label: 'DeepSeek V3', description: 'DeepSeek' },
+    { value: 'deepseek-ai/deepseek-v3.2', label: 'DeepSeek V3.2', description: 'DeepSeek' },
+    { value: 'deepseek-ai/deepseek-v3.1-terminus', label: 'DeepSeek V3.1 Terminus', description: 'DeepSeek' },
+    { value: 'deepseek-ai/deepseek-v3.1', label: 'DeepSeek V3.1', description: 'DeepSeek' },
+    // IBM GRANITE MODELS
+    { value: 'ibm/granite-3.3-8b-instruct', label: 'Granite 3.3 8B', description: 'IBM Granite' },
+    { value: 'ibm/granite-3.0-8b-instruct', label: 'Granite 3.0 8B', description: 'IBM Granite' },
+    { value: 'ibm/granite-3.0-3b-a800m-instruct', label: 'Granite 3.0 3B', description: 'IBM Granite' },
+    // OTHER MODELS
+    { value: 'databricks/dbrx-instruct', label: 'DBRX Instruct', description: 'Other' },
+    { value: '01-ai/yi-large', label: 'Yi Large', description: 'Other' },
+    { value: 'ai21labs/jamba-1.5-large-instruct', label: 'Jamba 1.5 Large', description: 'Other' },
+    { value: 'ai21labs/jamba-1.5-mini-instruct', label: 'Jamba 1.5 Mini', description: 'Other' },
+    { value: 'writer/palmyra-creative-122b', label: 'Palmyra Creative 122B', description: 'Other' },
+    { value: 'writer/palmyra-fin-70b-32k', label: 'Palmyra Fin 70B 32K', description: 'Other' },
+    { value: 'writer/palmyra-med-70b', label: 'Palmyra Med 70B', description: 'Other' },
+    { value: 'writer/palmyra-med-70b-32k', label: 'Palmyra Med 70B 32K', description: 'Other' },
+    // Z-AI GLM MODELS
+    { value: 'z-ai/glm5', label: 'GLM-5', description: 'Z-AI' },
+    { value: 'z-ai/glm4.7', label: 'GLM-4.7', description: 'Z-AI' },
+    // MINIMAX MODELS
+    { value: 'minimaxai/minimax-m2.5', label: 'MiniMax M2.5', description: 'MiniMax' },
+    // MOONSHOT KIMI MODELS
+    { value: 'moonshotai/kimi-k2.5', label: 'Kimi K2.5', description: 'Moonshot' },
+    { value: 'moonshotai/kimi-k2-instruct', label: 'Kimi K2 Instruct', description: 'Moonshot' },
+    { value: 'moonshotai/kimi-k2-thinking', label: 'Kimi K2 Thinking', description: 'Moonshot' },
+    { value: 'moonshotai/kimi-k2.5-thinking', label: 'Kimi K2.5 Thinking', description: 'Moonshot' },
+    { value: 'moonshotai/kimi-k2-instruct-0905', label: 'Kimi K2 Instruct 0905', description: 'Moonshot' },
+  ]
+}
+
+let cachedNvidiaNimOptions: ModelOption[] | null = null
+
+export function getCachedNvidiaNimModelOptions(): ModelOption[] {
+  if (!cachedNvidiaNimOptions) {
+    cachedNvidiaNimOptions = getNvidiaNimModels()
+  }
+  return cachedNvidiaNimOptions
+}

src/utils/model/openaiContextWindows.ts

@@ -104,6 +104,57 @@ const OPENAI_CONTEXT_WINDOWS: Record<string, number> = {
   'devstral-latest':          256_000,
   'ministral-3b-latest':      256_000,
 
+  // NVIDIA NIM - popular models
+  'nvidia/llama-3.1-nemotron-70b-instruct': 128_000,
+  'nvidia/llama-3.1-nemotron-ultra-253b-v1': 128_000,
+  'nvidia/nemotron-mini-4b-instruct': 32_768,
+  'meta/llama-3.1-405b-instruct': 128_000,
+  'meta/llama-3.1-70b-instruct': 128_000,
+  'meta/llama-3.1-8b-instruct': 128_000,
+  'meta/llama-3.2-90b-instruct': 128_000,
+  'meta/llama-3.2-1b-instruct': 128_000,
+  'meta/llama-3.2-3b-instruct': 128_000,
+  'meta/llama-3.3-70b-instruct': 128_000,
+  // Google Gemma via NVIDIA NIM
+  'google/gemma-2-27b-it': 8_192,
+  'google/gemma-2-9b-it': 8_192,
+  'google/gemma-3-27b-it': 131_072,
+  'google/gemma-3-12b-it': 131_072,
+  'google/gemma-3-4b-it': 131_072,
+  // DeepSeek via NVIDIA NIM
+  'deepseek-ai/deepseek-r1': 128_000,
+  'deepseek-ai/deepseek-v3': 128_000,
+  'deepseek-ai/deepseek-v3.2': 128_000,
+  // Qwen via NVIDIA NIM
+  'qwen/qwen3-32b': 128_000,
+  'qwen/qwen3-8b': 128_000,
+  'qwen/qwen2.5-7b-instruct': 32_768,
+  // Mistral via NVIDIA NIM
+  'mistralai/mistral-large-3-675b-instruct-2512': 256_000,
+  'mistralai/mistral-large-2-instruct': 256_000,
+  'mistralai/mistral-small-3.1-24b-instruct-2503': 32_768,
+  'mistralai/mixtral-8x7b-instruct-v0.1': 32_768,
+  // Microsoft Phi via NVIDIA NIM
+  'microsoft/phi-4-mini-instruct': 16_384,
+  'microsoft/phi-3.5-mini-instruct': 16_384,
+  'microsoft/phi-3-mini-128k-instruct': 128_000,
+  // IBM Granite via NVIDIA NIM
+  'ibm/granite-3.3-8b-instruct': 8_192,
+  'ibm/granite-8b-code-instruct': 8_192,
+  // GLM models via NVIDIA NIM
+  'z-ai/glm5': 200_000,
+  'z-ai/glm4.7': 128_000,
+  // Kimi models via NVIDIA NIM
+  'moonshotai/kimi-k2.5': 200_000,
+  'moonshotai/kimi-k2-instruct': 128_000,
+  // DBRX via NVIDIA NIM
+  'databricks/dbrx-instruct': 131_072,
+  // Jamba via NVIDIA NIM
+  'ai21labs/jamba-1.5-large-instruct': 256_000,
+  'ai21labs/jamba-1.5-mini-instruct': 256_000,
+  // Yi via NVIDIA NIM
+  '01-ai/yi-large': 32_768,
+
   // MiniMax (all M2.x variants share 204,800 context, 131,072 max output)
   'MiniMax-M2.7':             204_800,
   'MiniMax-M2.7-highspeed':   204_800,
@@ -118,6 +169,13 @@ const OPENAI_CONTEXT_WINDOWS: Record<string, number> = {
   'minimax-m2.1':             204_800,
   'minimax-m2.1-highspeed':   204_800,
 
+  // MiniMax new models
+  'MiniMax-Text-01':          524_288,
+  'MiniMax-Text-01-Preview':  262_144,
+  'MiniMax-Vision-01':        32_768,
+  'MiniMax-Vision-01-Fast':   16_384,
+  'MiniMax-M2':               204_800,
+
   // Google (via OpenRouter)
   'google/gemini-2.0-flash':1_048_576,
   'google/gemini-2.5-pro':  1_048_576,
@@ -126,6 +184,8 @@ const OPENAI_CONTEXT_WINDOWS: Record<string, number> = {
   'gemini-2.0-flash':              1_048_576,
   'gemini-2.5-pro':                1_048_576,
   'gemini-2.5-flash':              1_048_576,
+  'gemini-3.1-pro':                1_048_576,
+  'gemini-3.1-flash-lite-preview': 1_048_576,
 
   // Ollama local models
   // Llama 3.1+ models support 128k context natively (Meta official specs).
@@ -144,6 +204,21 @@ const OPENAI_CONTEXT_WINDOWS: Record<string, number> = {
   'llama3.2:1b':              128_000,
   'qwen3:8b':                 128_000,
   'codestral':                 32_768,
+
+  // Alibaba DashScope (Coding Plan)
+  // Model context windows from DashScope API /models endpoint (April 2026).
+  // Values sourced from: qwen3.5-plus/qwen3-coder-plus (1M), qwen3-coder-next/max (256K),
+  // kimi-k2.5 (256K), glm-5/glm-4.7 (198K).
+  // Max output tokens: Qwen variants (64K/32K), GLM (16K).
+  'qwen3.6-plus':           1_000_000,
+  'qwen3.5-plus':           1_000_000,
+  'qwen3-coder-plus':       1_000_000,
+  'qwen3-coder-next':         262_144,
+  'qwen3-max':                262_144,
+  'qwen3-max-2026-01-23':     262_144,
+  'kimi-k2.5':                262_144,
+  'glm-5':                    202_752,
+  'glm-4.7':                  202_752,
 }
 
 /**
@@ -246,6 +321,12 @@ const OPENAI_MAX_OUTPUT_TOKENS: Record<string, number> = {
   'minimax-m2.5-highspeed':  131_072,
   'minimax-m2.1':            131_072,
   'minimax-m2.1-highspeed':  131_072,
+  // New MiniMax models
+  'MiniMax-M2':              131_072,
+  'MiniMax-Text-01':          65_536,
+  'MiniMax-Text-01-Preview':  65_536,
+  'MiniMax-Vision-01':        16_384,
+  'MiniMax-Vision-01-Fast':    16_384,
 
   // Google (via OpenRouter)
   'google/gemini-2.0-flash':   8_192,
@@ -255,6 +336,8 @@ const OPENAI_MAX_OUTPUT_TOKENS: Record<string, number> = {
   'gemini-2.0-flash':              8_192,
   'gemini-2.5-pro':                65_536,
   'gemini-2.5-flash':              65_536,
+  'gemini-3.1-pro':                65_536,
+  'gemini-3.1-flash-lite-preview': 65_536,
 
   // Ollama local models (conservative safe defaults)
   'llama3.3:70b':               4_096,
@@ -271,6 +354,43 @@ const OPENAI_MAX_OUTPUT_TOKENS: Record<string, number> = {
   'llama3.2:1b':                4_096,
   'qwen3:8b':                   8_192,
   'codestral':                   8_192,
+
+  // NVIDIA NIM models
+  'nvidia/llama-3.1-nemotron-70b-instruct': 32_768,
+  'nvidia/nemotron-mini-4b-instruct': 8_192,
+  'meta/llama-3.1-405b-instruct': 32_768,
+  'meta/llama-3.1-70b-instruct': 32_768,
+  'meta/llama-3.2-90b-instruct': 32_768,
+  'meta/llama-3.3-70b-instruct': 32_768,
+  'google/gemma-2-27b-it': 4_096,
+  'google/gemma-3-27b-it': 16_384,
+  'google/gemma-3-12b-it': 16_384,
+  'deepseek-ai/deepseek-r1': 32_768,
+  'deepseek-ai/deepseek-v3': 32_768,
+  'deepseek-ai/deepseek-v3.2': 32_768,
+  'qwen/qwen3-32b': 32_768,
+  'qwen/qwen2.5-7b-instruct': 8_192,
+  'mistralai/mistral-large-3-675b-instruct-2512': 32_768,
+  'mistralai/mixtral-8x7b-instruct-v0.1': 8_192,
+  'microsoft/phi-4-mini-instruct': 4_096,
+  'microsoft/phi-3.5-mini-instruct': 4_096,
+  'ibm/granite-3.3-8b-instruct': 4_096,
+  'z-ai/glm5': 32_768,
+  'moonshotai/kimi-k2.5': 32_768,
+  'databricks/dbrx-instruct': 32_768,
+  'ai21labs/jamba-1.5-large-instruct': 32_768,
+  '01-ai/yi-large': 8_192,
+
+  // Alibaba DashScope (Coding Plan)
+  'qwen3.6-plus':              65_536,
+  'qwen3.5-plus':              65_536,
+  'qwen3-coder-plus':          65_536,
+  'qwen3-coder-next':          65_536,
+  'qwen3-max':                 32_768,
+  'qwen3-max-2026-01-23':      32_768,
+  'kimi-k2.5':                 32_768,
+  'glm-5':                     16_384,
+  'glm-4.7':                   16_384,
 }
 
 function lookupByModel<T>(table: Record<string, T>, model: string): T | undefined {