fix: align SkillTool schema error output

* fix: address code scanning alerts

Parse Gemini hostnames instead of matching raw URL substrings, redact gRPC error logs, and harden the Finder drag-drop test escape helper so the flagged paths are fixed without regressing working behavior.

* Potential fix for pull request finding 'CodeQL / Clear-text logging of sensitive information'

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>

* fix: restore safe grpc error summaries

A later autofix commit removed the exported gRPC error summarizer while the new regression test still imported it. Restore the safe name/code-only summary so CI stays green without reintroducing clear-text logging.

* fix: keep grpc logging generic

Remove the stale helper/test pair and keep the gRPC startup and stream logs free of error-derived data so the CodeQL clear-text logging alert stays closed while the rest of the security fixes remain intact.

---------

Co-authored-by: OpenClaude Worker 3 <worker-3@openclaude.local>
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>

src/commands/provider/provider.test.tsx

@@ -52,7 +52,11 @@ async function renderFinalFrame(node: React.ReactNode): Promise<string> {
     patchConsole: false,
   })
 
-  await instance.waitUntilExit()
+  // Timeout guard: if render throws before exit effect fires, don't hang
+  await Promise.race([
+    instance.waitUntilExit(),
+    new Promise<void>(resolve => setTimeout(resolve, 3000)),
+  ])
   return stripAnsi(extractLastFrame(getOutput()))
 }
 

src/components/ProviderManager.test.tsx

@@ -0,0 +1,305 @@
+import { PassThrough } from 'node:stream'
+
+import { afterEach, expect, mock, test } from 'bun:test'
+import React from 'react'
+import stripAnsi from 'strip-ansi'
+
+import { createRoot } from '../ink.js'
+import { AppStateProvider } from '../state/AppState.js'
+
+const SYNC_START = '\x1B[?2026h'
+const SYNC_END = '\x1B[?2026l'
+
+const ORIGINAL_ENV = {
+  CLAUDE_CODE_USE_GITHUB: process.env.CLAUDE_CODE_USE_GITHUB,
+  GITHUB_TOKEN: process.env.GITHUB_TOKEN,
+  GH_TOKEN: process.env.GH_TOKEN,
+}
+
+function extractLastFrame(output: string): string {
+  let lastFrame: string | null = null
+  let cursor = 0
+
+  while (cursor < output.length) {
+    const start = output.indexOf(SYNC_START, cursor)
+    if (start === -1) {
+      break
+    }
+
+    const contentStart = start + SYNC_START.length
+    const end = output.indexOf(SYNC_END, contentStart)
+    if (end === -1) {
+      break
+    }
+
+    const frame = output.slice(contentStart, end)
+    if (frame.trim().length > 0) {
+      lastFrame = frame
+    }
+    cursor = end + SYNC_END.length
+  }
+
+  return lastFrame ?? output
+}
+
+function createTestStreams(): {
+  stdout: PassThrough
+  stdin: PassThrough & {
+    isTTY: boolean
+    setRawMode: (mode: boolean) => void
+    ref: () => void
+    unref: () => void
+  }
+  getOutput: () => string
+} {
+  let output = ''
+  const stdout = new PassThrough()
+  const stdin = new PassThrough() as PassThrough & {
+    isTTY: boolean
+    setRawMode: (mode: boolean) => void
+    ref: () => void
+    unref: () => void
+  }
+
+  stdin.isTTY = true
+  stdin.setRawMode = () => {}
+  stdin.ref = () => {}
+  stdin.unref = () => {}
+  ;(stdout as unknown as { columns: number }).columns = 120
+  stdout.on('data', chunk => {
+    output += chunk.toString()
+  })
+
+  return {
+    stdout,
+    stdin,
+    getOutput: () => output,
+  }
+}
+
+async function waitForCondition(
+  predicate: () => boolean,
+  options?: { timeoutMs?: number; intervalMs?: number },
+): Promise<void> {
+  const timeoutMs = options?.timeoutMs ?? 2000
+  const intervalMs = options?.intervalMs ?? 10
+  const startedAt = Date.now()
+
+  while (Date.now() - startedAt < timeoutMs) {
+    if (predicate()) {
+      return
+    }
+    await Bun.sleep(intervalMs)
+  }
+
+  throw new Error('Timed out waiting for ProviderManager test condition')
+}
+
+function createDeferred<T>(): {
+  promise: Promise<T>
+  resolve: (value: T) => void
+} {
+  let resolve!: (value: T) => void
+  const promise = new Promise<T>(r => {
+    resolve = r
+  })
+  return { promise, resolve }
+}
+
+function mockProviderProfilesModule(): void {
+  mock.module('../utils/providerProfiles.js', () => ({
+    addProviderProfile: () => null,
+    applyActiveProviderProfileFromConfig: () => {},
+    deleteProviderProfile: () => ({ removed: false, activeProfileId: null }),
+    getActiveProviderProfile: () => null,
+    getProviderPresetDefaults: () => ({
+      provider: 'openai',
+      name: 'Mock provider',
+      baseUrl: 'http://localhost:11434/v1',
+      model: 'mock-model',
+      apiKey: '',
+    }),
+    getProviderProfiles: () => [],
+    setActiveProviderProfile: () => null,
+    updateProviderProfile: () => null,
+  }))
+}
+
+function mockProviderManagerDependencies(
+  syncRead: () => string | undefined,
+  asyncRead: () => Promise<string | undefined>,
+): void {
+  mockProviderProfilesModule()
+
+  mock.module('../utils/githubModelsCredentials.js', () => ({
+    clearGithubModelsToken: () => ({ success: true }),
+    GITHUB_MODELS_HYDRATED_ENV_MARKER: 'CLAUDE_CODE_GITHUB_TOKEN_HYDRATED',
+    hydrateGithubModelsTokenFromSecureStorage: () => {},
+    readGithubModelsToken: syncRead,
+    readGithubModelsTokenAsync: asyncRead,
+  }))
+
+  mock.module('../utils/settings/settings.js', () => ({
+    updateSettingsForSource: () => ({ error: null }),
+  }))
+}
+
+async function waitForFrameOutput(
+  getOutput: () => string,
+  predicate: (output: string) => boolean,
+  timeoutMs = 2500,
+): Promise<string> {
+  let output = ''
+
+  await waitForCondition(() => {
+    output = stripAnsi(extractLastFrame(getOutput()))
+    return predicate(output)
+  }, { timeoutMs })
+
+  return output
+}
+
+async function mountProviderManager(
+  ProviderManager: React.ComponentType<{
+    mode: 'first-run' | 'manage'
+    onDone: () => void
+  }>,
+): Promise<{
+  getOutput: () => string
+  dispose: () => Promise<void>
+}> {
+  const { stdout, stdin, getOutput } = createTestStreams()
+  const root = await createRoot({
+    stdout: stdout as unknown as NodeJS.WriteStream,
+    stdin: stdin as unknown as NodeJS.ReadStream,
+    patchConsole: false,
+  })
+
+  root.render(
+    <AppStateProvider>
+      <ProviderManager
+        mode="manage"
+        onDone={() => {}}
+      />
+    </AppStateProvider>,
+  )
+
+  return {
+    getOutput,
+    dispose: async () => {
+      root.unmount()
+      stdin.end()
+      stdout.end()
+      await Bun.sleep(0)
+    },
+  }
+}
+
+async function renderProviderManagerFrame(
+  ProviderManager: React.ComponentType<{
+    mode: 'first-run' | 'manage'
+    onDone: () => void
+  }>,
+  options?: {
+    waitForOutput?: (output: string) => boolean
+    timeoutMs?: number
+  },
+): Promise<string> {
+  const mounted = await mountProviderManager(ProviderManager)
+  const output = await waitForFrameOutput(
+    mounted.getOutput,
+    frame => {
+      if (!options?.waitForOutput) {
+        return frame.includes('Provider manager')
+      }
+      return options.waitForOutput(frame)
+    },
+    options?.timeoutMs ?? 2500,
+  )
+
+  await mounted.dispose()
+  return output
+}
+
+afterEach(() => {
+  mock.restore()
+
+  for (const [key, value] of Object.entries(ORIGINAL_ENV)) {
+    if (value === undefined) {
+      delete process.env[key as keyof typeof ORIGINAL_ENV]
+    } else {
+      process.env[key as keyof typeof ORIGINAL_ENV] = value
+    }
+  }
+})
+
+test('ProviderManager resolves GitHub virtual provider from async storage without sync reads in render flow', async () => {
+  delete process.env.CLAUDE_CODE_USE_GITHUB
+  delete process.env.GITHUB_TOKEN
+  delete process.env.GH_TOKEN
+
+  const syncRead = mock(() => {
+    throw new Error('sync credential read should not run in ProviderManager render flow')
+  })
+  const asyncRead = mock(async () => 'stored-token')
+
+  mockProviderManagerDependencies(syncRead, asyncRead)
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { ProviderManager } = await import(`./ProviderManager.js?ts=${nonce}`)
+  const output = await renderProviderManagerFrame(ProviderManager, {
+    waitForOutput: frame =>
+      frame.includes('Provider manager') &&
+      frame.includes('GitHub Models') &&
+      frame.includes('token stored'),
+  })
+
+  expect(output).toContain('Provider manager')
+  expect(output).toContain('GitHub Models')
+  expect(output).toContain('token stored')
+  expect(output).not.toContain('No provider profiles configured yet.')
+
+  expect(syncRead).not.toHaveBeenCalled()
+  expect(asyncRead).toHaveBeenCalled()
+})
+
+test('ProviderManager avoids first-frame false negative while stored-token lookup is pending', async () => {
+  delete process.env.CLAUDE_CODE_USE_GITHUB
+  delete process.env.GITHUB_TOKEN
+  delete process.env.GH_TOKEN
+
+  const syncRead = mock(() => {
+    throw new Error('sync credential read should not run in ProviderManager render flow')
+  })
+  const deferredStoredToken = createDeferred<string | undefined>()
+  const asyncRead = mock(async () => deferredStoredToken.promise)
+
+  mockProviderManagerDependencies(syncRead, asyncRead)
+
+  const nonce = `${Date.now()}-${Math.random()}`
+  const { ProviderManager } = await import(`./ProviderManager.js?ts=${nonce}`)
+  const mounted = await mountProviderManager(ProviderManager)
+
+  const firstFrame = await waitForFrameOutput(
+    mounted.getOutput,
+    frame => frame.includes('Provider manager'),
+  )
+
+  expect(firstFrame).toContain('Checking GitHub Models credentials...')
+  expect(firstFrame).not.toContain('No provider profiles configured yet.')
+
+  deferredStoredToken.resolve('stored-token')
+
+  const resolvedFrame = await waitForFrameOutput(
+    mounted.getOutput,
+    frame => frame.includes('GitHub Models') && frame.includes('token stored'),
+  )
+
+  expect(resolvedFrame).toContain('GitHub Models')
+  expect(resolvedFrame).toContain('token stored')
+
+  await mounted.dispose()
+
+  expect(syncRead).not.toHaveBeenCalled()
+  expect(asyncRead).toHaveBeenCalled()
+})

src/components/ProviderManager.tsx

@@ -20,6 +20,7 @@ import {
   GITHUB_MODELS_HYDRATED_ENV_MARKER,
   hydrateGithubModelsTokenFromSecureStorage,
   readGithubModelsToken,
+  readGithubModelsTokenAsync,
 } from '../utils/githubModelsCredentials.js'
 import { isEnvTruthy } from '../utils/envUtils.js'
 import { updateSettingsForSource } from '../utils/settings/settings.js'
@@ -118,25 +119,38 @@ function profileSummary(profile: ProviderProfile, isActive: boolean): string {
   return `${providerKind} · ${profile.baseUrl} · ${profile.model} · ${keyInfo}${activeSuffix}`
 }
 
-function getGithubCredentialSource(
+function getGithubCredentialSourceFromEnv(
   processEnv: NodeJS.ProcessEnv = process.env,
 ): GithubCredentialSource {
-  if (readGithubModelsToken()?.trim()) {
-    return 'stored'
-  }
   if (processEnv.GITHUB_TOKEN?.trim() || processEnv.GH_TOKEN?.trim()) {
     return 'env'
   }
   return 'none'
 }
 
+async function resolveGithubCredentialSource(
+  processEnv: NodeJS.ProcessEnv = process.env,
+): Promise<GithubCredentialSource> {
+  const envSource = getGithubCredentialSourceFromEnv(processEnv)
+  if (envSource !== 'none') {
+    return envSource
+  }
+
+  if (await readGithubModelsTokenAsync()) {
+    return 'stored'
+  }
+
+  return 'none'
+}
+
 function isGithubProviderAvailable(
+  credentialSource: GithubCredentialSource,
   processEnv: NodeJS.ProcessEnv = process.env,
 ): boolean {
   if (isEnvTruthy(processEnv.CLAUDE_CODE_USE_GITHUB)) {
     return true
   }
-  return getGithubCredentialSource(processEnv) !== 'none'
+  return credentialSource !== 'none'
 }
 
 function getGithubProviderModel(
@@ -164,19 +178,24 @@ function getGithubProviderSummary(
 }
 
 export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
+  const initialGithubCredentialSource = getGithubCredentialSourceFromEnv()
+  const initialIsGithubActive = isEnvTruthy(process.env.CLAUDE_CODE_USE_GITHUB)
+  const initialHasGithubCredential = initialGithubCredentialSource !== 'none'
+
   const [profiles, setProfiles] = React.useState(() => getProviderProfiles())
   const [activeProfileId, setActiveProfileId] = React.useState(
     () => getActiveProviderProfile()?.id,
   )
-  const [githubProviderAvailable, setGithubProviderAvailable] = React.useState(() =>
-    isGithubProviderAvailable(),
+  const [githubProviderAvailable, setGithubProviderAvailable] = React.useState(
+    () => isGithubProviderAvailable(initialGithubCredentialSource),
   )
   const [githubCredentialSource, setGithubCredentialSource] = React.useState<GithubCredentialSource>(
-    () => getGithubCredentialSource(),
-  )
-  const [isGithubActive, setIsGithubActive] = React.useState(() =>
-    isEnvTruthy(process.env.CLAUDE_CODE_USE_GITHUB),
+    () => initialGithubCredentialSource,
   )
+  const [isGithubActive, setIsGithubActive] = React.useState(() => initialIsGithubActive)
+  const [isGithubCredentialSourceResolved, setIsGithubCredentialSourceResolved] =
+    React.useState(() => initialHasGithubCredential || initialIsGithubActive)
+  const githubRefreshEpochRef = React.useRef(0)
   const [screen, setScreen] = React.useState<Screen>(
     mode === 'first-run' ? 'select-preset' : 'menu',
   )
@@ -196,13 +215,48 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
   const currentStepKey = currentStep.key
   const currentValue = draft[currentStepKey]
 
+  const refreshGithubProviderState = React.useCallback((): void => {
+    const envCredentialSource = getGithubCredentialSourceFromEnv()
+    const githubActive = isEnvTruthy(process.env.CLAUDE_CODE_USE_GITHUB)
+    const canResolveFromEnv = githubActive || envCredentialSource !== 'none'
+
+    if (canResolveFromEnv) {
+      githubRefreshEpochRef.current += 1
+      setGithubCredentialSource(envCredentialSource)
+      setGithubProviderAvailable(isGithubProviderAvailable(envCredentialSource))
+      setIsGithubActive(githubActive)
+      setIsGithubCredentialSourceResolved(true)
+      return
+    }
+
+    setIsGithubCredentialSourceResolved(false)
+    const refreshEpoch = ++githubRefreshEpochRef.current
+    void (async () => {
+      const credentialSource = await resolveGithubCredentialSource()
+      if (refreshEpoch !== githubRefreshEpochRef.current) {
+        return
+      }
+
+      setGithubCredentialSource(credentialSource)
+      setGithubProviderAvailable(isGithubProviderAvailable(credentialSource))
+      setIsGithubActive(isEnvTruthy(process.env.CLAUDE_CODE_USE_GITHUB))
+      setIsGithubCredentialSourceResolved(true)
+    })()
+  }, [])
+
+  React.useEffect(() => {
+    refreshGithubProviderState()
+
+    return () => {
+      githubRefreshEpochRef.current += 1
+    }
+  }, [refreshGithubProviderState])
+
   function refreshProfiles(): void {
     const nextProfiles = getProviderProfiles()
     setProfiles(nextProfiles)
     setActiveProfileId(getActiveProviderProfile()?.id)
-    setGithubProviderAvailable(isGithubProviderAvailable())
-    setGithubCredentialSource(getGithubCredentialSource())
-    setIsGithubActive(isEnvTruthy(process.env.CLAUDE_CODE_USE_GITHUB))
+    refreshGithubProviderState()
   }
 
   function clearStartupProviderOverrideFromUserSettings(): string | null {
@@ -640,7 +694,11 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
         {statusMessage && <Text>{statusMessage}</Text>}
         <Box flexDirection="column">
           {profiles.length === 0 && !githubProviderAvailable ? (
+            isGithubCredentialSourceResolved ? (
               <Text dimColor>No provider profiles configured yet.</Text>
+            ) : (
+              <Text dimColor>Checking GitHub Models credentials...</Text>
+            )
           ) : (
             <>
               {profiles.map(profile => (

src/grpc/server.ts

@@ -40,7 +40,7 @@ export class GrpcServer {
       grpc.ServerCredentials.createInsecure(),
       (error, boundPort) => {
         if (error) {
-          console.error('Failed to start gRPC server', error)
+          console.error('Failed to start gRPC server')
           return
         }
         console.log(`gRPC Server running at ${host}:${boundPort}`)
@@ -225,7 +225,7 @@ export class GrpcServer {
           call.end()
         }
       } catch (err: any) {
-        console.error("Error processing stream:", err)
+        console.error('Error processing stream')
         call.write({
           error: {
             message: err.message || "Internal server error",

src/ink/reconciler.ts

@@ -366,14 +366,12 @@ const reconciler = createReconciler<
   createTextInstance(
     text: string,
     _root: DOMElement,
-    hostContext: HostContext,
+    _hostContext: HostContext,
   ): TextNode {
-    if (!hostContext.isInsideText) {
-      throw new Error(
-        `Text string "${text}" must be rendered inside <Text> component`,
-      )
-    }
-
+    // react-compiler memoization can reuse cached <Text> elements without
+    // re-traversing getChildHostContext, so hostContext.isInsideText may be
+    // stale. Always create the text node — Ink will render it correctly
+    // regardless of the context tracking state.
     return createTextNode(text)
   },
   resetTextContent() {},

src/services/api/openaiShim.test.ts

@@ -261,6 +261,58 @@ test('preserves Gemini tool call extra_content in follow-up requests', async ()
   })
 })
 
+test('does not infer Gemini mode from OPENAI_BASE_URL path substrings', async () => {
+  let capturedAuthorization: string | null = null
+
+  process.env.OPENAI_BASE_URL =
+    'https://evil.example/generativelanguage.googleapis.com/v1beta/openai'
+  delete process.env.OPENAI_API_KEY
+  process.env.GEMINI_API_KEY = 'gemini-secret'
+
+  globalThis.fetch = (async (_input, init) => {
+    const headers = init?.headers as Record<string, string> | undefined
+    capturedAuthorization =
+      headers?.Authorization ?? headers?.authorization ?? null
+
+    return new Response(
+      JSON.stringify({
+        id: 'chatcmpl-1',
+        model: 'fake-model',
+        choices: [
+          {
+            message: {
+              role: 'assistant',
+              content: 'ok',
+            },
+            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: 'fake-model',
+    messages: [{ role: 'user', content: 'hello' }],
+    max_tokens: 64,
+    stream: false,
+  })
+
+  expect(capturedAuthorization).toBeNull()
+})
+
 test('preserves image tool results as placeholders in follow-up requests', async () => {
   let requestBody: Record<string, unknown> | undefined
 
@@ -1769,3 +1821,237 @@ test('coalesces consecutive assistant messages preserving tool_calls (issue #202
   expect(assistantMsgs?.length).toBe(1) // two assistant turns merged into one
   expect(assistantMsgs?.[0]?.tool_calls?.length).toBeGreaterThan(0)
 })
+
+test('non-streaming: reasoning_content emitted as thinking block, used as text when content is null', async () => {
+  globalThis.fetch = (async (_input, _init) => {
+    return new Response(
+      JSON.stringify({
+        id: 'chatcmpl-1',
+        model: 'glm-5',
+        choices: [
+          {
+            message: {
+              role: 'assistant',
+              content: null,
+              reasoning_content: 'Let me think about this step by step.',
+            },
+            finish_reason: 'stop',
+          },
+        ],
+        usage: {
+          prompt_tokens: 10,
+          completion_tokens: 20,
+          total_tokens: 30,
+        },
+      }),
+      {
+        headers: {
+          'Content-Type': 'application/json',
+        },
+      },
+    )
+  }) as FetchType
+
+  const client = createOpenAIShimClient({}) as OpenAIShimClient
+
+  const result = (await client.beta.messages.create({
+    model: 'glm-5',
+    system: 'test system',
+    messages: [{ role: 'user', content: 'hello' }],
+    max_tokens: 64,
+    stream: false,
+  })) as { content: Array<Record<string, unknown>> }
+
+  expect(result.content).toEqual([
+    { type: 'thinking', thinking: 'Let me think about this step by step.' },
+    { type: 'text', text: 'Let me think about this step by step.' },
+  ])
+})
+
+test('non-streaming: empty string content does not fall through to reasoning_content as text', async () => {
+  globalThis.fetch = (async (_input, _init) => {
+    return new Response(
+      JSON.stringify({
+        id: 'chatcmpl-1',
+        model: 'glm-5',
+        choices: [
+          {
+            message: {
+              role: 'assistant',
+              content: '',
+              reasoning_content: 'Chain of thought here.',
+            },
+            finish_reason: 'stop',
+          },
+        ],
+        usage: {
+          prompt_tokens: 10,
+          completion_tokens: 20,
+          total_tokens: 30,
+        },
+      }),
+      {
+        headers: {
+          'Content-Type': 'application/json',
+        },
+      },
+    )
+  }) as FetchType
+
+  const client = createOpenAIShimClient({}) as OpenAIShimClient
+
+  const result = (await client.beta.messages.create({
+    model: 'glm-5',
+    system: 'test system',
+    messages: [{ role: 'user', content: 'hello' }],
+    max_tokens: 64,
+    stream: false,
+  })) as { content: Array<Record<string, unknown>> }
+
+  // reasoning_content should be a thinking block, and also used as text
+  // since content is empty string (treated as absent)
+  expect(result.content).toEqual([
+    { type: 'thinking', thinking: 'Chain of thought here.' },
+    { type: 'text', text: 'Chain of thought here.' },
+  ])
+})
+
+test('non-streaming: real content takes precedence over reasoning_content', async () => {
+  globalThis.fetch = (async (_input, _init) => {
+    return new Response(
+      JSON.stringify({
+        id: 'chatcmpl-1',
+        model: 'glm-5',
+        choices: [
+          {
+            message: {
+              role: 'assistant',
+              content: 'The answer is 42.',
+              reasoning_content: 'I need to calculate this.',
+            },
+            finish_reason: 'stop',
+          },
+        ],
+        usage: {
+          prompt_tokens: 10,
+          completion_tokens: 20,
+          total_tokens: 30,
+        },
+      }),
+      {
+        headers: {
+          'Content-Type': 'application/json',
+        },
+      },
+    )
+  }) as FetchType
+
+  const client = createOpenAIShimClient({}) as OpenAIShimClient
+
+  const result = (await client.beta.messages.create({
+    model: 'glm-5',
+    system: 'test system',
+    messages: [{ role: 'user', content: 'hello' }],
+    max_tokens: 64,
+    stream: false,
+  })) as { content: Array<Record<string, unknown>> }
+
+  expect(result.content).toEqual([
+    { type: 'thinking', thinking: 'I need to calculate this.' },
+    { type: 'text', text: 'The answer is 42.' },
+  ])
+})
+
+test('streaming: thinking block closed before tool call', async () => {
+  globalThis.fetch = (async (_input, _init) => {
+    const chunks = makeStreamChunks([
+      {
+        id: 'chatcmpl-1',
+        object: 'chat.completion.chunk',
+        model: 'glm-5',
+        choices: [
+          {
+            index: 0,
+            delta: { role: 'assistant', reasoning_content: 'Thinking...' },
+            finish_reason: null,
+          },
+        ],
+      },
+      {
+        id: 'chatcmpl-1',
+        object: 'chat.completion.chunk',
+        model: 'glm-5',
+        choices: [
+          {
+            index: 0,
+            delta: {
+              tool_calls: [
+                {
+                  index: 0,
+                  id: 'call-1',
+                  type: 'function',
+                  function: {
+                    name: 'Bash',
+                    arguments: '{"command":"ls"}',
+                  },
+                },
+              ],
+            },
+            finish_reason: null,
+          },
+        ],
+      },
+      {
+        id: 'chatcmpl-1',
+        object: 'chat.completion.chunk',
+        model: 'glm-5',
+        choices: [
+          {
+            index: 0,
+            delta: {},
+            finish_reason: 'tool_calls',
+          },
+        ],
+      },
+    ])
+
+    return makeSseResponse(chunks)
+  }) as FetchType
+
+  const client = createOpenAIShimClient({}) as OpenAIShimClient
+
+  const result = await client.beta.messages
+    .create({
+      model: 'glm-5',
+      system: 'test system',
+      messages: [{ role: 'user', content: 'Run ls' }],
+      max_tokens: 64,
+      stream: true,
+    })
+    .withResponse()
+
+  const events: Array<Record<string, unknown>> = []
+  for await (const event of result.data) {
+    events.push(event)
+  }
+
+  const types = events.map(e => e.type)
+
+  // Verify thinking block is started, then closed, then tool call starts
+  const thinkingStartIdx = types.indexOf('content_block_start')
+  const firstStopIdx = types.indexOf('content_block_stop')
+  const toolStartIdx = types.indexOf(
+    'content_block_start',
+    thinkingStartIdx + 1,
+  )
+
+  expect(thinkingStartIdx).toBeGreaterThanOrEqual(0)
+  expect(firstStopIdx).toBeGreaterThan(thinkingStartIdx)
+  expect(toolStartIdx).toBeGreaterThan(firstStopIdx)
+
+  // Verify thinking block start content
+  const thinkingStart = events[thinkingStartIdx] as {
+    content_block?: Record<string, unknown>
+  }
+  expect(thinkingStart?.content_block?.type).toBe('thinking')
+})

src/services/api/openaiShim.ts

@@ -60,11 +60,22 @@ const GITHUB_API_VERSION = '2022-11-28'
 const GITHUB_429_MAX_RETRIES = 3
 const GITHUB_429_BASE_DELAY_SEC = 1
 const GITHUB_429_MAX_DELAY_SEC = 32
+const GEMINI_API_HOST = 'generativelanguage.googleapis.com'
 
 function isGithubModelsMode(): boolean {
   return isEnvTruthy(process.env.CLAUDE_CODE_USE_GITHUB)
 }
 
+function hasGeminiApiHost(baseUrl: string | undefined): boolean {
+  if (!baseUrl) return false
+
+  try {
+    return new URL(baseUrl).hostname.toLowerCase() === GEMINI_API_HOST
+  } catch {
+    return false
+  }
+}
+
 function formatRetryAfterHint(response: Response): string {
   const ra = response.headers.get('retry-after')
   return ra ? ` (Retry-After: ${ra})` : ''
@@ -201,6 +212,13 @@ function convertContentBlocks(
   return parts
 }
 
+function isGeminiMode(): boolean {
+  return (
+    isEnvTruthy(process.env.CLAUDE_CODE_USE_GEMINI) ||
+    hasGeminiApiHost(process.env.OPENAI_BASE_URL)
+  )
+}
+
 function convertMessages(
   messages: Array<{ role: string; message?: { role?: string; content?: unknown }; content?: unknown }>,
   system: unknown,
@@ -252,6 +270,7 @@ function convertMessages(
       // Check for tool_use blocks
       if (Array.isArray(content)) {
         const toolUses = content.filter((b: { type?: string }) => b.type === 'tool_use')
+        const thinkingBlock = content.find((b: { type?: string }) => b.type === 'thinking')
         const textContent = content.filter(
           (b: { type?: string }) => b.type !== 'tool_use' && b.type !== 'thinking',
         )
@@ -271,7 +290,9 @@ function convertMessages(
               name?: string
               input?: unknown
               extra_content?: Record<string, unknown>
-            }) => ({
+              signature?: string
+            }, index) => {
+              const toolCall: NonNullable<OpenAIMessage['tool_calls']>[number] = {
                 id: tu.id ?? `call_${crypto.randomUUID().replace(/-/g, '')}`,
                 type: 'function' as const,
                 function: {
@@ -281,8 +302,34 @@ function convertMessages(
                       ? tu.input
                       : JSON.stringify(tu.input ?? {}),
                 },
-              ...(tu.extra_content ? { extra_content: tu.extra_content } : {}),
-            }),
+              }
+
+              // Preserve existing extra_content if present
+              if (tu.extra_content) {
+                toolCall.extra_content = { ...tu.extra_content }
+              }
+
+              // Handle Gemini thought_signature
+              if (isGeminiMode()) {
+                // If the model provided a signature in the tool_use block itself (e.g. from a previous Turn/Step)
+                // Use thinkingBlock.signature for ALL tool calls in the same assistant turn if available.
+                // The API requires the same signature on every replayed function call part in a parallel set.
+                const signature = tu.signature ?? (thinkingBlock as any)?.signature
+
+                // 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: {
+                    ...existingGoogle,
+                    thought_signature: signature ?? "skip_thought_signature_validator"
+                  }
+                }
+              }
+
+              return toolCall
+            },
           )
         }
 
@@ -401,7 +448,7 @@ function normalizeSchemaForOpenAI(
 function convertTools(
   tools: Array<{ name: string; description?: string; input_schema?: Record<string, unknown> }>,
 ): OpenAITool[] {
-  const isGemini = isEnvTruthy(process.env.CLAUDE_CODE_USE_GEMINI)
+  const isGemini = isGeminiMode()
 
   return tools
     .filter(t => t.name !== 'ToolSearchTool') // Not relevant for OpenAI
@@ -443,6 +490,7 @@ interface OpenAIStreamChunk {
     delta: {
       role?: string
       content?: string | null
+      reasoning_content?: string | null
       tool_calls?: Array<{
         index: number
         id?: string
@@ -525,6 +573,8 @@ async function* openaiStreamToAnthropic(
     }
   >()
   let hasEmittedContentStart = false
+  let hasEmittedThinkingStart = false
+  let hasClosedThinking = false
   let lastStopReason: 'tool_use' | 'max_tokens' | 'end_turn' | null = null
   let hasEmittedFinalUsage = false
   let hasProcessedFinishReason = false
@@ -581,9 +631,34 @@ async function* openaiStreamToAnthropic(
       for (const choice of chunk.choices ?? []) {
         const delta = choice.delta
 
+        // Reasoning models (e.g. GLM-5, DeepSeek) may stream chain-of-thought
+        // in `reasoning_content` before the actual reply appears in `content`.
+        // Emit reasoning as a thinking block and content as a text block.
+        if (delta.reasoning_content != null && delta.reasoning_content !== '') {
+          if (!hasEmittedThinkingStart) {
+            yield {
+              type: 'content_block_start',
+              index: contentBlockIndex,
+              content_block: { type: 'thinking', thinking: '' },
+            }
+            hasEmittedThinkingStart = true
+          }
+          yield {
+            type: 'content_block_delta',
+            index: contentBlockIndex,
+            delta: { type: 'thinking_delta', thinking: delta.reasoning_content },
+          }
+        }
+
         // Text content — use != null to distinguish absent field from empty string,
         // some providers send "" as first delta to signal streaming start
-        if (delta.content != null) {
+        if (delta.content != null && delta.content !== '') {
+          // Close thinking block if transitioning from reasoning to content
+          if (hasEmittedThinkingStart && !hasClosedThinking) {
+            yield { type: 'content_block_stop', index: contentBlockIndex }
+            contentBlockIndex++
+            hasClosedThinking = true
+          }
           if (!hasEmittedContentStart) {
             yield {
               type: 'content_block_start',
@@ -603,7 +678,12 @@ async function* openaiStreamToAnthropic(
         if (delta.tool_calls) {
           for (const tc of delta.tool_calls) {
             if (tc.id && tc.function?.name) {
-              // New tool call starting
+              // New tool call starting — close any open thinking block first
+              if (hasEmittedThinkingStart && !hasClosedThinking) {
+                yield { type: 'content_block_stop', index: contentBlockIndex }
+                contentBlockIndex++
+                hasClosedThinking = true
+              }
               if (hasEmittedContentStart) {
                 yield {
                   type: 'content_block_stop',
@@ -633,6 +713,13 @@ async function* openaiStreamToAnthropic(
                   name: tc.function.name,
                   input: {},
                   ...(tc.extra_content ? { extra_content: tc.extra_content } : {}),
+                  // Extract Gemini signature from extra_content
+                  ...((tc.extra_content?.google as any)?.thought_signature
+                    ? {
+                        signature: (tc.extra_content.google as any)
+                          .thought_signature,
+                      }
+                    : {}),
                 },
               }
               contentBlockIndex++
@@ -678,6 +765,12 @@ async function* openaiStreamToAnthropic(
         if (choice.finish_reason && !hasProcessedFinishReason) {
           hasProcessedFinishReason = true
 
+          // Close any open thinking block that wasn't closed by content transition
+          if (hasEmittedThinkingStart && !hasClosedThinking) {
+            yield { type: 'content_block_stop', index: contentBlockIndex }
+            contentBlockIndex++
+            hasClosedThinking = true
+          }
           // Close any open content blocks
           if (hasEmittedContentStart) {
             yield {
@@ -1003,7 +1096,7 @@ class OpenAIShimMessages {
       ...(options?.headers ?? {}),
     }
 
-    const isGemini = isEnvTruthy(process.env.CLAUDE_CODE_USE_GEMINI)
+    const isGemini = isGeminiMode()
     const apiKey =
       this.providerOverride?.apiKey ?? process.env.OPENAI_API_KEY ?? ''
     // Detect Azure endpoints by hostname (not raw URL) to prevent bypass via
@@ -1116,6 +1209,7 @@ class OpenAIShimMessages {
             | string
             | null
             | Array<{ type?: string; text?: string }>
+          reasoning_content?: string | null
           tool_calls?: Array<{
             id: string
             function: { name: string; arguments: string }
@@ -1137,7 +1231,17 @@ class OpenAIShimMessages {
     const choice = data.choices?.[0]
     const content: Array<Record<string, unknown>> = []
 
-    const rawContent = choice?.message?.content
+    // Some reasoning models (e.g. GLM-5) put their reply in reasoning_content
+    // while content stays null — emit reasoning as a thinking block, then
+    // fall back to it for visible text if content is empty.
+    const reasoningText = choice?.message?.reasoning_content
+    if (typeof reasoningText === 'string' && reasoningText) {
+      content.push({ type: 'thinking', thinking: reasoningText })
+    }
+    const rawContent =
+      choice?.message?.content !== '' && choice?.message?.content != null
+        ? choice?.message?.content
+        : choice?.message?.reasoning_content
     if (typeof rawContent === 'string' && rawContent) {
       content.push({ type: 'text', text: rawContent })
     } else if (Array.isArray(rawContent) && rawContent.length > 0) {
@@ -1170,6 +1274,10 @@ class OpenAIShimMessages {
           name: tc.function.name,
           input,
           ...(tc.extra_content ? { extra_content: tc.extra_content } : {}),
+          // Extract Gemini signature from extra_content
+          ...((tc.extra_content?.google as any)?.thought_signature
+            ? { signature: (tc.extra_content.google as any).thought_signature }
+            : {}),
         })
       }
     }

src/services/compact/microCompact.test.ts

@@ -0,0 +1,127 @@
+import { describe, expect, test } from 'bun:test'
+
+import type { Message } from '../../types/message.js'
+import { createAssistantMessage, createUserMessage } from '../../utils/messages.js'
+
+// We test the exported collectCompactableToolIds behavior indirectly via
+// the public microcompactMessages + time-based path. But first we need to
+// verify the core predicate: MCP tools (prefixed 'mcp__') should be
+// compactable alongside the built-in tool set.
+
+// Import internals we can test
+import { evaluateTimeBasedTrigger } from './microCompact.js'
+
+/**
+ * Helper: build a minimal assistant message with a tool_use block.
+ */
+function assistantWithToolUse(toolName: string, toolId: string): Message {
+  return createAssistantMessage({
+    content: [
+      {
+        type: 'tool_use' as const,
+        id: toolId,
+        name: toolName,
+        input: {},
+      },
+    ],
+  })
+}
+
+/**
+ * Helper: build a user message with a tool_result block.
+ */
+function userWithToolResult(toolId: string, output: string): Message {
+  return createUserMessage({
+    content: [
+      {
+        type: 'tool_result' as const,
+        tool_use_id: toolId,
+        content: output,
+      },
+    ],
+  })
+}
+
+describe('microCompact MCP tool compaction', () => {
+  // We can't easily unit-test the private isCompactableTool directly,
+  // but we can test the full time-based microcompact path which exercises
+  // collectCompactableToolIds → isCompactableTool under the hood.
+  // The time-based path is the simplest to trigger: it content-clears
+  // old tool results when the gap since last assistant message exceeds
+  // the threshold.
+
+  // However, evaluateTimeBasedTrigger depends on config (GrowthBook).
+  // So instead, let's test the observable behavior by importing the
+  // microcompactMessages function and checking that MCP tool_use blocks
+  // are collected.
+
+  // Since collectCompactableToolIds is not exported, we test the predicate
+  // behavior by verifying that the module loads without error and that
+  // built-in and MCP tools are treated consistently.
+
+  test('module exports load correctly', async () => {
+    const mod = await import('./microCompact.js')
+    expect(mod.microcompactMessages).toBeFunction()
+    expect(mod.estimateMessageTokens).toBeFunction()
+    expect(mod.evaluateTimeBasedTrigger).toBeFunction()
+  })
+
+  test('estimateMessageTokens counts MCP tool_use blocks', async () => {
+    const { estimateMessageTokens } = await import('./microCompact.js')
+
+    const builtinMessages: Message[] = [
+      assistantWithToolUse('Read', 'tool-builtin-1'),
+      userWithToolResult('tool-builtin-1', 'file contents here'),
+    ]
+
+    const mcpMessages: Message[] = [
+      assistantWithToolUse('mcp__github__get_file_contents', 'tool-mcp-1'),
+      userWithToolResult('tool-mcp-1', 'file contents here'),
+    ]
+
+    const builtinTokens = estimateMessageTokens(builtinMessages)
+    const mcpTokens = estimateMessageTokens(mcpMessages)
+
+    // Both should produce non-zero estimates
+    expect(builtinTokens).toBeGreaterThan(0)
+    expect(mcpTokens).toBeGreaterThan(0)
+
+    // The tool_result content is identical, so token estimates should be
+    // similar (tool_use name differs slightly, so not exactly equal)
+    expect(Math.abs(builtinTokens - mcpTokens)).toBeLessThan(50)
+  })
+
+  test('microcompactMessages processes MCP tools without error', async () => {
+    const { microcompactMessages } = await import('./microCompact.js')
+
+    const messages: Message[] = [
+      assistantWithToolUse('mcp__slack__send_message', 'tool-mcp-2'),
+      userWithToolResult('tool-mcp-2', 'Message sent successfully'),
+      assistantWithToolUse('mcp__github__create_pull_request', 'tool-mcp-3'),
+      userWithToolResult('tool-mcp-3', JSON.stringify({ number: 42, url: 'https://github.com/org/repo/pull/42' })),
+    ]
+
+    // Should not throw — MCP tools should be handled gracefully
+    const result = await microcompactMessages(messages)
+    expect(result).toBeDefined()
+    expect(result.messages).toBeDefined()
+    expect(result.messages.length).toBe(messages.length)
+  })
+
+  test('microcompactMessages processes mixed built-in and MCP tools', async () => {
+    const { microcompactMessages } = await import('./microCompact.js')
+
+    const messages: Message[] = [
+      assistantWithToolUse('Read', 'tool-read-1'),
+      userWithToolResult('tool-read-1', 'some file content'),
+      assistantWithToolUse('mcp__playwright__screenshot', 'tool-mcp-4'),
+      userWithToolResult('tool-mcp-4', 'base64-encoded-screenshot-data'.repeat(100)),
+      assistantWithToolUse('Bash', 'tool-bash-1'),
+      userWithToolResult('tool-bash-1', 'command output'),
+    ]
+
+    const result = await microcompactMessages(messages)
+    expect(result).toBeDefined()
+    expect(result.messages.length).toBe(messages.length)
+  })
+})

src/services/compact/microCompact.ts

@@ -37,7 +37,7 @@ export const TIME_BASED_MC_CLEARED_MESSAGE = '[Old tool result content cleared]'
 
 const IMAGE_MAX_TOKEN_SIZE = 2000
 
-// Only compact these tools
+// Only compact these built-in tools (MCP tools are also compactable via prefix match)
 const COMPACTABLE_TOOLS = new Set<string>([
   FILE_READ_TOOL_NAME,
   ...SHELL_TOOL_NAMES,
@@ -49,7 +49,13 @@ const COMPACTABLE_TOOLS = new Set<string>([
   FILE_WRITE_TOOL_NAME,
 ])
 
-// --- Cached microcompact state (internal-only, gated by feature('CACHED_MICROCOMPACT')) ---
+const MCP_TOOL_PREFIX = 'mcp__'
+
+function isCompactableTool(name: string): boolean {
+  return COMPACTABLE_TOOLS.has(name) || name.startsWith(MCP_TOOL_PREFIX)
+}
+
+// --- Cached microcompact state (gated by feature('CACHED_MICROCOMPACT')) ---
 
 // Lazy-initialized cached MC module and state to avoid importing in external builds.
 // The imports and state live inside feature() checks for dead code elimination.
@@ -231,7 +237,7 @@ function collectCompactableToolIds(messages: Message[]): string[] {
       Array.isArray(message.message.content)
     ) {
       for (const block of message.message.content) {
-        if (block.type === 'tool_use' && COMPACTABLE_TOOLS.has(block.name)) {
+        if (block.type === 'tool_use' && isCompactableTool(block.name)) {
           ids.push(block.id)
         }
       }

src/services/tools/toolExecution.test.ts

@@ -0,0 +1,33 @@
+import { describe, expect, test } from 'bun:test'
+
+import { SkillTool } from '../../tools/SkillTool/SkillTool.js'
+import {
+  getSchemaValidationErrorOverride,
+  getSchemaValidationToolUseResult,
+} from './toolExecution.js'
+
+describe('getSchemaValidationErrorOverride', () => {
+  test('returns actionable missing-skill error for SkillTool', () => {
+    expect(getSchemaValidationErrorOverride(SkillTool, {})).toBe(
+      'Missing skill name. Pass the slash command name as the skill parameter (e.g., skill: "commit" for /commit, skill: "review-pr" for /review-pr).',
+    )
+  })
+
+  test('does not override unrelated tool schema failures', () => {
+    expect(getSchemaValidationErrorOverride({ name: 'Read' } as never, {})).toBe(
+      null,
+    )
+  })
+
+  test('does not override SkillTool when skill is present', () => {
+    expect(
+      getSchemaValidationErrorOverride(SkillTool, { skill: 'commit' }),
+    ).toBe(null)
+  })
+
+  test('uses the actionable override for structured toolUseResult too', () => {
+    expect(getSchemaValidationToolUseResult(SkillTool, {} as never)).toBe(
+      'InputValidationError: Missing skill name. Pass the slash command name as the skill parameter (e.g., skill: "commit" for /commit, skill: "review-pr" for /review-pr).',
+    )
+  })
+})

src/services/tools/toolExecution.ts

@@ -43,6 +43,7 @@ import { FILE_READ_TOOL_NAME } from '../../tools/FileReadTool/prompt.js'
 import { FILE_WRITE_TOOL_NAME } from '../../tools/FileWriteTool/prompt.js'
 import { NOTEBOOK_EDIT_TOOL_NAME } from '../../tools/NotebookEditTool/constants.js'
 import { POWERSHELL_TOOL_NAME } from '../../tools/PowerShellTool/toolName.js'
+import { SKILL_TOOL_NAME } from '../../tools/SkillTool/constants.js'
 import { parseGitCommitId } from '../../tools/shared/gitOperationTracking.js'
 import {
   isDeferredTool,
@@ -596,6 +597,31 @@ export function buildSchemaNotSentHint(
   )
 }
 
+export function getSchemaValidationErrorOverride(
+  tool: Tool,
+  input: unknown,
+): string | null {
+  if (tool.name !== SKILL_TOOL_NAME || !input || typeof input !== 'object') {
+    return null
+  }
+
+  const skill = (input as { skill?: unknown }).skill
+  if (skill === undefined || skill === null) {
+    return 'Missing skill name. Pass the slash command name as the skill parameter (e.g., skill: "commit" for /commit, skill: "review-pr" for /review-pr).'
+  }
+
+  return null
+}
+
+export function getSchemaValidationToolUseResult(
+  tool: Tool,
+  input: unknown,
+  fallbackMessage?: string,
+): string {
+  const override = getSchemaValidationErrorOverride(tool, input)
+  return `InputValidationError: ${override ?? fallbackMessage ?? ''}`
+}
+
 async function checkPermissionsAndCallTool(
   tool: Tool,
   toolUseID: string,
@@ -614,7 +640,9 @@ async function checkPermissionsAndCallTool(
   // Validate input types with zod (surprisingly, the model is not great at generating valid input)
   const parsedInput = tool.inputSchema.safeParse(input)
   if (!parsedInput.success) {
-    let errorContent = formatZodValidationError(tool.name, parsedInput.error)
+    const fallbackErrorContent = formatZodValidationError(tool.name, parsedInput.error)
+    let errorContent =
+      getSchemaValidationErrorOverride(tool, input) ?? fallbackErrorContent
 
     const schemaHint = buildSchemaNotSentHint(
       tool,
@@ -672,7 +700,11 @@ async function checkPermissionsAndCallTool(
               tool_use_id: toolUseID,
             },
           ],
-          toolUseResult: `InputValidationError: ${parsedInput.error.message}`,
+          toolUseResult: getSchemaValidationToolUseResult(
+            tool,
+            input,
+            parsedInput.error.message,
+          ),
           sourceToolAssistantUUID: assistantMessage.uuid,
         }),
       },

src/tools/SkillTool/SkillTool.test.ts

@@ -0,0 +1,31 @@
+import { describe, expect, test } from 'bun:test'
+
+import { SkillTool } from './SkillTool.js'
+
+describe('SkillTool missing parameter handling', () => {
+  test('missing skill stays required at the schema level', async () => {
+    const parsed = SkillTool.inputSchema.safeParse({})
+
+    expect(parsed.success).toBe(false)
+  })
+
+  test('validateInput still returns an actionable error when called with missing skill', async () => {
+    const result = await SkillTool.validateInput?.({} as never, {
+      options: { tools: [] },
+      messages: [],
+    } as never)
+
+    expect(result).toEqual({
+      result: false,
+      message:
+        'Missing skill name. Pass the slash command name as the skill parameter (e.g., skill: "commit" for /commit, skill: "review-pr" for /review-pr).',
+      errorCode: 1,
+    })
+  })
+
+  test('valid skill input still parses and validates', async () => {
+    const parsed = SkillTool.inputSchema.safeParse({ skill: 'commit' })
+
+    expect(parsed.success).toBe(true)
+  })
+})

src/tools/SkillTool/SkillTool.ts

@@ -352,6 +352,16 @@ export const SkillTool: Tool<InputSchema, Output, Progress> = buildTool({
   toAutoClassifierInput: ({ skill }) => skill ?? '',
 
   async validateInput({ skill }, context): Promise<ValidationResult> {
+    if (!skill || typeof skill !== 'string') {
+      return {
+        result: false,
+        message:
+          'Missing skill name. Pass the slash command name as the skill parameter ' +
+          '(e.g., skill: "commit" for /commit, skill: "review-pr" for /review-pr).',
+        errorCode: 1,
+      }
+    }
+
     // Skills are just skill names, no arguments
     const trimmed = skill.trim()
     if (!trimmed) {
@@ -434,7 +444,7 @@ export const SkillTool: Tool<InputSchema, Output, Progress> = buildTool({
     context,
   ): Promise<PermissionDecision> {
     // Skills are just skill names, no arguments
-    const trimmed = skill.trim()
+    const trimmed = skill ?? ''
 
     // Remove leading slash if present (for compatibility)
     const commandName = trimmed.startsWith('/') ? trimmed.substring(1) : trimmed
@@ -592,7 +602,7 @@ export const SkillTool: Tool<InputSchema, Output, Progress> = buildTool({
     // - Skill is a prompt-based skill
 
     // Skills are just names, with optional arguments
-    const trimmed = skill.trim()
+    const trimmed = skill ?? ''
 
     // Remove leading slash if present (for compatibility)
     const commandName = trimmed.startsWith('/') ? trimmed.substring(1) : trimmed

src/utils/api.test.ts

@@ -1,6 +1,7 @@
 import { expect, test } from 'bun:test'
 import { z } from 'zod/v4'
 import { getEmptyToolPermissionContext, type Tool, type Tools } from '../Tool.js'
+import { SkillTool } from '../tools/SkillTool/SkillTool.js'
 import { toolToAPISchema } from './api.js'
 
 test('toolToAPISchema preserves provider-specific schema keywords in input_schema', async () => {
@@ -64,3 +65,16 @@ test('toolToAPISchema preserves provider-specific schema keywords in input_schem
     },
   })
 })
+
+test('toolToAPISchema keeps skill required for SkillTool', async () => {
+  const schema = await toolToAPISchema(SkillTool, {
+    getToolPermissionContext: async () => getEmptyToolPermissionContext(),
+    tools: [] as unknown as Tools,
+    agents: [],
+  })
+
+  expect((schema as { input_schema: unknown }).input_schema).toMatchObject({
+    type: 'object',
+    required: ['skill'],
+  })
+})

src/utils/dragDropPaths.test.ts

@@ -4,6 +4,10 @@ import { tmpdir } from 'os'
 import { join } from 'path'
 import { extractDraggedFilePaths } from './dragDropPaths.js'
 
+function escapeFinderDraggedPath(filePath: string): string {
+  return filePath.replace(/([\\ ])/g, '\\$1')
+}
+
 describe('extractDraggedFilePaths', () => {
   // Paths that exist on any system.
   const thisFile = import.meta.path
@@ -80,6 +84,12 @@ describe('extractDraggedFilePaths', () => {
     })
   })
 
+  test('escapeFinderDraggedPath escapes spaces and backslashes', () => {
+    expect(escapeFinderDraggedPath('/tmp/my\\notes file.txt')).toBe(
+      '/tmp/my\\\\notes\\ file.txt',
+    )
+  })
+
   // Backslash-escaped paths are a Finder/macOS + Linux convention — on
   // Windows the shell-escape step is skipped, so these cases do not apply.
   if (process.platform !== 'win32') {
@@ -92,7 +102,7 @@ describe('extractDraggedFilePaths', () => {
 
       test('resolves an escaped real file with a space in its name', () => {
         // Raw form matches what a terminal delivers on Finder drag.
-        const escaped = spacedFile.replace(/ /g, '\\ ')
+        const escaped = escapeFinderDraggedPath(spacedFile)
         expect(extractDraggedFilePaths(escaped)).toEqual([spacedFile])
       })
     })

src/utils/githubModelsCredentials.hydrate.test.ts

@@ -41,7 +41,7 @@ describe('hydrateGithubModelsTokenFromSecureStorage', () => {
     }))
 
     const { hydrateGithubModelsTokenFromSecureStorage } = await import(
-      './githubModelsCredentials.js'
+      './githubModelsCredentials.js?hydrate=sets-token'
     )
     hydrateGithubModelsTokenFromSecureStorage()
     expect(process.env.GITHUB_TOKEN).toBe('stored-secret')
@@ -62,7 +62,7 @@ describe('hydrateGithubModelsTokenFromSecureStorage', () => {
     }))
 
     const { hydrateGithubModelsTokenFromSecureStorage } = await import(
-      './githubModelsCredentials.js'
+      './githubModelsCredentials.js?hydrate=preserve-existing'
     )
     hydrateGithubModelsTokenFromSecureStorage()
     expect(process.env.GITHUB_TOKEN).toBe('already')

src/utils/githubModelsCredentials.test.ts

@@ -1,13 +1,11 @@
 import { describe, expect, test } from 'bun:test'
 
-import {
-  clearGithubModelsToken,
-  readGithubModelsToken,
-  saveGithubModelsToken,
-} from './githubModelsCredentials.js'
-
 describe('readGithubModelsToken', () => {
-  test('returns undefined in bare mode', () => {
+  test('returns undefined in bare mode', async () => {
+    const { readGithubModelsToken } = await import(
+      './githubModelsCredentials.js?read-bare-mode'
+    )
+
     const prev = process.env.CLAUDE_CODE_SIMPLE
     process.env.CLAUDE_CODE_SIMPLE = '1'
     expect(readGithubModelsToken()).toBeUndefined()
@@ -20,7 +18,11 @@ describe('readGithubModelsToken', () => {
 })
 
 describe('saveGithubModelsToken / clearGithubModelsToken', () => {
-  test('save returns failure in bare mode', () => {
+  test('save returns failure in bare mode', async () => {
+    const { saveGithubModelsToken } = await import(
+      './githubModelsCredentials.js?save-bare-mode'
+    )
+
     const prev = process.env.CLAUDE_CODE_SIMPLE
     process.env.CLAUDE_CODE_SIMPLE = '1'
     const r = saveGithubModelsToken('abc')
@@ -33,7 +35,11 @@ describe('saveGithubModelsToken / clearGithubModelsToken', () => {
     }
   })
 
-  test('clear succeeds in bare mode', () => {
+  test('clear succeeds in bare mode', async () => {
+    const { clearGithubModelsToken } = await import(
+      './githubModelsCredentials.js?clear-bare-mode'
+    )
+
     const prev = process.env.CLAUDE_CODE_SIMPLE
     process.env.CLAUDE_CODE_SIMPLE = '1'
     expect(clearGithubModelsToken().success).toBe(true)

src/utils/githubModelsCredentials.ts

@@ -23,6 +23,19 @@ export function readGithubModelsToken(): string | undefined {
   }
 }
 
+export async function readGithubModelsTokenAsync(): Promise<string | undefined> {
+  if (isBareMode()) return undefined
+  try {
+    const data = (await getSecureStorage().readAsync()) as
+      | ({ githubModels?: GithubModelsCredentialBlob } & Record<string, unknown>)
+      | null
+    const t = data?.githubModels?.accessToken?.trim()
+    return t || undefined
+  } catch {
+    return undefined
+  }
+}
+
 /**
  * If GitHub Models mode is on and no token is in the environment, copy the
  * stored token into process.env so the OpenAI shim and validation see it.

src/utils/staticRender.tsx

@@ -97,8 +97,12 @@ export function renderToAnsiString(node: React.ReactNode, columns?: number): Pro
       patchConsole: false
     });
 
-    // Wait for the component to exit naturally
-    await instance.waitUntilExit();
+    // Wait for the component to exit naturally, with a timeout guard so
+    // tests never hang indefinitely if a render error prevents exit().
+    await Promise.race([
+      instance.waitUntilExit(),
+      new Promise<void>(resolve => setTimeout(resolve, 3000)),
+    ]);
 
     // Extract only the first frame's content to avoid duplication
     // (Ink outputs multiple frames in non-TTY mode)