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/scripts/system-check.test.ts
+++ b/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',
--- a/scripts/system-check.ts
+++ b/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) {