feat(api): improve local provider reliability with readiness and self-healing (#738)

* feat(api): classify openai-compatible provider failures * Update src/services/api/providerConfig.ts Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update src/services/api/errors.ts Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * feat(api): harden openai-compatible diagnostics and env fallback * Update src/services/api/openaiShim.ts Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update src/services/api/openaiShim.ts Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update src/services/api/errors.ts Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update src/services/api/errors.ts Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * fix openaiShim duplicate requests and diagnostics * remove unused url from http failure classifier * dedupe env diagnostic warnings * Remove hardcoded URLs from OpenAI error tests Removed hardcoded URLs from network failure classification tests. * Update providerConfig.envDiagnostics.test.ts * fix(openai-shim): return successful responses and restore localhost classifier tests * Update src/services/api/openaiShim.ts Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update src/services/api/openaiShim.ts Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update src/services/api/openaiShim.ts Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * feat(provider): add truthful local generation readiness checks Implement Phase 2 provider readiness behavior by adding structured Ollama generation probes, wiring setup flows to readiness states, extending system-check with generation readiness output, and updating focused tests. * feat(api): add local self-healing fallback retries Implement Phase 3 self-healing behavior for local OpenAI-compatible providers: retry base URL fallbacks for localhost resolution and endpoint mismatches, plus capability-gated toolless retry for tool-incompatible local models; include diagnostics and focused tests. * fix(api): address review blockers for local provider reliability * Update src/utils/providerDiscovery.ts Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update src/services/api/openaiShim.ts Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * fix: harden readiness probes and cross-platform test stability * fix: refresh toolless retry payload and stabilize osc clipboard test * fix: harden Ollama readiness parsing and redact provider URLs --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2026-04-20 12:24:02 +04:00
parent b09972f223
commit 4cb963e660
22 changed files with 1452 additions and 208 deletions
--- a/src/utils/providerDiscovery.test.ts
+++ b/src/utils/providerDiscovery.test.ts
@@ -1,9 +1,9 @@
 import { afterEach, expect, mock, test } from 'bun:test'

-import {
-  getLocalOpenAICompatibleProviderLabel,
-  listOpenAICompatibleModels,
-} from './providerDiscovery.js'
+async function loadProviderDiscoveryModule() {
+  // @ts-expect-error cache-busting query string for Bun module mocks
+  return import(`./providerDiscovery.js?ts=${Date.now()}-${Math.random()}`)
+}

 const originalFetch = globalThis.fetch
 const originalEnv = {
@@ -16,6 +16,8 @@ afterEach(() => {
 })

 test('lists models from a local openai-compatible /models endpoint', async () => {
+  const { listOpenAICompatibleModels } = await loadProviderDiscoveryModule()
+
  globalThis.fetch = mock((input, init) => {
    const url = typeof input === 'string' ? input : input.url
    expect(url).toBe('http://localhost:1234/v1/models')
@@ -47,6 +49,8 @@ test('lists models from a local openai-compatible /models endpoint', async () =>
 })

 test('returns null when a local openai-compatible /models request fails', async () => {
+  const { listOpenAICompatibleModels } = await loadProviderDiscoveryModule()
+
  globalThis.fetch = mock(() =>
    Promise.resolve(new Response('not available', { status: 503 })),
  ) as typeof globalThis.fetch
@@ -56,13 +60,19 @@ test('returns null when a local openai-compatible /models request fails', async
  ).resolves.toBeNull()
 })

-test('detects LM Studio from the default localhost port', () => {
+test('detects LM Studio from the default localhost port', async () => {
+  const { getLocalOpenAICompatibleProviderLabel } =
+    await loadProviderDiscoveryModule()
+
  expect(getLocalOpenAICompatibleProviderLabel('http://localhost:1234/v1')).toBe(
    'LM Studio',
  )
 })

-test('detects common local openai-compatible providers by hostname', () => {
+test('detects common local openai-compatible providers by hostname', async () => {
+  const { getLocalOpenAICompatibleProviderLabel } =
+    await loadProviderDiscoveryModule()
+
  expect(
    getLocalOpenAICompatibleProviderLabel('http://localai.local:8080/v1'),
  ).toBe('LocalAI')
@@ -71,8 +81,212 @@ test('detects common local openai-compatible providers by hostname', () => {
  ).toBe('vLLM')
 })

-test('falls back to a generic local openai-compatible label', () => {
+test('falls back to a generic local openai-compatible label', async () => {
+  const { getLocalOpenAICompatibleProviderLabel } =
+    await loadProviderDiscoveryModule()
+
  expect(
    getLocalOpenAICompatibleProviderLabel('http://127.0.0.1:8080/v1'),
  ).toBe('Local OpenAI-compatible')
+})
+
+test('ollama generation readiness reports unreachable when tags endpoint is down', async () => {
+  const { probeOllamaGenerationReadiness } = await loadProviderDiscoveryModule()
+
+  const calledUrls: string[] = []
+  globalThis.fetch = mock(input => {
+    const url = typeof input === 'string' ? input : input.url
+    calledUrls.push(url)
+    return Promise.resolve(new Response('not available', { status: 503 }))
+  }) as typeof globalThis.fetch
+
+  await expect(
+    probeOllamaGenerationReadiness({
+      baseUrl: 'http://localhost:11434',
+    }),
+  ).resolves.toMatchObject({
+    state: 'unreachable',
+    models: [],
+  })
+
+  expect(calledUrls).toEqual([
+    'http://localhost:11434/api/tags',
+  ])
+})
+
+test('ollama generation readiness reports no models when server is reachable', async () => {
+  const { probeOllamaGenerationReadiness } = await loadProviderDiscoveryModule()
+
+  const calledUrls: string[] = []
+  globalThis.fetch = mock(input => {
+    const url = typeof input === 'string' ? input : input.url
+    calledUrls.push(url)
+    return Promise.resolve(
+      new Response(JSON.stringify({ models: [] }), {
+        status: 200,
+        headers: { 'Content-Type': 'application/json' },
+      }),
+    )
+  }) as typeof globalThis.fetch
+
+  await expect(
+    probeOllamaGenerationReadiness({
+      baseUrl: 'http://localhost:11434',
+    }),
+  ).resolves.toMatchObject({
+    state: 'no_models',
+    models: [],
+  })
+
+  expect(calledUrls).toEqual([
+    'http://localhost:11434/api/tags',
+  ])
+})
+
+test('ollama generation readiness reports generation_failed when requested model is missing', async () => {
+  const { probeOllamaGenerationReadiness } = await loadProviderDiscoveryModule()
+
+  const calledUrls: string[] = []
+  globalThis.fetch = mock(input => {
+    const url = typeof input === 'string' ? input : input.url
+    calledUrls.push(url)
+    return Promise.resolve(
+      new Response(
+        JSON.stringify({
+          models: [{ name: 'llama3.1:8b', size: 1024 }],
+        }),
+        {
+          status: 200,
+          headers: { 'Content-Type': 'application/json' },
+        },
+      ),
+    )
+  }) as typeof globalThis.fetch
+
+  await expect(
+    probeOllamaGenerationReadiness({
+      baseUrl: 'http://localhost:11434',
+      model: 'qwen2.5-coder:7b',
+    }),
+  ).resolves.toMatchObject({
+    state: 'generation_failed',
+    probeModel: 'qwen2.5-coder:7b',
+    detail: 'requested model not installed: qwen2.5-coder:7b',
+  })
+
+  expect(calledUrls).toEqual(['http://localhost:11434/api/tags'])
+})
+
+test('ollama generation readiness reports generation failures when chat probe fails', async () => {
+  const { probeOllamaGenerationReadiness } = await loadProviderDiscoveryModule()
+
+  globalThis.fetch = mock(input => {
+    const url = typeof input === 'string' ? input : input.url
+    if (url.endsWith('/api/tags')) {
+      return Promise.resolve(
+        new Response(
+          JSON.stringify({
+            models: [{ name: 'qwen2.5-coder:7b', size: 42 }],
+          }),
+          {
+            status: 200,
+            headers: { 'Content-Type': 'application/json' },
+          },
+        ),
+      )
+    }
+
+    return Promise.resolve(new Response('model not found', { status: 404 }))
+  }) as typeof globalThis.fetch
+
+  await expect(
+    probeOllamaGenerationReadiness({
+      baseUrl: 'http://localhost:11434',
+      model: 'qwen2.5-coder:7b',
+    }),
+  ).resolves.toMatchObject({
+    state: 'generation_failed',
+    probeModel: 'qwen2.5-coder:7b',
+  })
+})
+
+test('ollama generation readiness reports generation_failed when chat probe returns invalid JSON', async () => {
+  const { probeOllamaGenerationReadiness } = await loadProviderDiscoveryModule()
+
+  globalThis.fetch = mock(input => {
+    const url = typeof input === 'string' ? input : input.url
+    if (url.endsWith('/api/tags')) {
+      return Promise.resolve(
+        new Response(
+          JSON.stringify({
+            models: [{ name: 'llama3.1:8b', size: 1024 }],
+          }),
+          {
+            status: 200,
+            headers: { 'Content-Type': 'application/json' },
+          },
+        ),
+      )
+    }
+
+    return Promise.resolve(
+      new Response('<html>proxy error</html>', {
+        status: 200,
+        headers: { 'Content-Type': 'text/html' },
+      }),
+    )
+  }) as typeof globalThis.fetch
+
+  await expect(
+    probeOllamaGenerationReadiness({
+      baseUrl: 'http://localhost:11434',
+    }),
+  ).resolves.toMatchObject({
+    state: 'generation_failed',
+    probeModel: 'llama3.1:8b',
+    detail: 'invalid JSON response',
+  })
+})
+
+test('ollama generation readiness reports ready when chat probe succeeds', async () => {
+  const { probeOllamaGenerationReadiness } = await loadProviderDiscoveryModule()
+
+  globalThis.fetch = mock(input => {
+    const url = typeof input === 'string' ? input : input.url
+    if (url.endsWith('/api/tags')) {
+      return Promise.resolve(
+        new Response(
+          JSON.stringify({
+            models: [{ name: 'llama3.1:8b', size: 1024 }],
+          }),
+          {
+            status: 200,
+            headers: { 'Content-Type': 'application/json' },
+          },
+        ),
+      )
+    }
+
+    return Promise.resolve(
+      new Response(
+        JSON.stringify({
+          message: { role: 'assistant', content: 'OK' },
+          done: true,
+        }),
+        {
+          status: 200,
+          headers: { 'Content-Type': 'application/json' },
+        },
+      ),
+    )
+  }) as typeof globalThis.fetch
+
+  await expect(
+    probeOllamaGenerationReadiness({
+      baseUrl: 'http://localhost:11434',
+    }),
+  ).resolves.toMatchObject({
+    state: 'ready',
+    probeModel: 'llama3.1:8b',
+  })
 })