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/components/ProviderManager.test.tsx
+++ b/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>
-    listOllamaModels?: () => Promise<
-      Array<{
-        name: string
-        sizeBytes?: number | null
-        family?: string | null
-        families?: string[]
-        parameterSize?: string | null
-        quantizationLevel?: string | null
-      }>
-    >
+    probeOllamaGenerationReadiness?: () => Promise<{
+      state: 'ready' | 'unreachable' | 'no_models' | 'generation_failed'
+      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),
-    listOllamaModels: options?.listOllamaModels ?? (async () => []),
+    probeOllamaGenerationReadiness:
+      options?.probeOllamaGenerationReadiness ??
+      (async () => ({
+        state: 'unreachable' as const,
+        models: [],
+      })),
  }))

  mock.module('../utils/githubModelsCredentials.js', () => ({
@@ -455,19 +463,22 @@ test('ProviderManager first-run Ollama preset auto-detects installed models', as
    async () => undefined,
    {
      addProviderProfile,
-      hasLocalOllama: async () => true,
-      listOllamaModels: async () => [
-        {
-          name: 'gemma4:31b-cloud',
-          family: 'gemma',
-          parameterSize: '31b',
-        },
-        {
-          name: 'kimi-k2.5:cloud',
-          family: 'kimi',
-          parameterSize: '2.5b',
-        },
-      ],
+      probeOllamaGenerationReadiness: async () => ({
+        state: 'ready',
+        models: [
+          {
+            name: 'gemma4:31b-cloud',
+            family: 'gemma',
+            parameterSize: '31b',
+          },
+          {
+            name: 'kimi-k2.5:cloud',
+            family: 'kimi',
+            parameterSize: '2.5b',
+          },
+        ],
+        probeModel: 'gemma4:31b-cloud',
+      }),
    },
  )

--- a/src/components/ProviderManager.tsx
+++ b/src/components/ProviderManager.tsx
@@ -37,13 +37,14 @@ import {
  readGithubModelsTokenAsync,
 } from '../utils/githubModelsCredentials.js'
 import {
-  hasLocalOllama,
-  listOllamaModels,
+  probeOllamaGenerationReadiness,
+  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,
@@ -52,7 +53,6 @@ import {
 import { Pane } from './design-system/Pane.js'
 import TextInput from './TextInput.js'
 import { useCodexOAuthFlow } from './useCodexOAuthFlow.js'
-import { useSetAppState } from '../state/AppState.js'

 export type ProviderManagerResult = {
  action: 'saved' | 'cancelled'
@@ -222,6 +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,
@@ -450,32 +473,21 @@ export function ProviderManager({ mode, onDone }: Props): React.ReactNode {
    setOllamaSelection({ state: 'loading' })

    void (async () => {
-      const available = await hasLocalOllama(draft.baseUrl)
-      if (!available) {
+      const readiness = await probeOllamaGenerationReadiness({
+        baseUrl: draft.baseUrl,
+      })
+      if (readiness.state !== 'ready') {
        if (!cancelled) {
          setOllamaSelection({
            state: 'unavailable',
-            message:
-              'Could not reach Ollama. Start Ollama first, or enter the endpoint manually.',
+            message: describeOllamaSelectionIssue(readiness, draft.baseUrl),
          })
        }
        return
      }

-      const models = await listOllamaModels(draft.baseUrl)
-      if (models.length === 0) {
-        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')
+      const ranked = rankOllamaModels(readiness.models, 'balanced')
+      const recommended = recommendOllamaModel(readiness.models, 'balanced')
      if (!cancelled) {
        setOllamaSelection({
          state: 'ready',
--- a/src/components/memory/memoryFileSelectorPaths.test.ts
+++ b/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(
-      '/repo/packages/app/AGENTS.md',
+    const cwd = join('/repo', 'packages', 'app')
+    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')],
-        '/repo/packages/app',
+        [projectFile(outsideRepoPath)],
+        cwd,
      ),
-    ).toBe('/repo/packages/app/AGENTS.md')
+    ).toBe(join(cwd, 'AGENTS.md'))
  })
 })