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.ts
+++ b/src/utils/providerDiscovery.ts
@@ -4,6 +4,13 @@ import { DEFAULT_OPENAI_BASE_URL } from '../services/api/providerConfig.js'
 export const DEFAULT_OLLAMA_BASE_URL = 'http://localhost:11434'
 export const DEFAULT_ATOMIC_CHAT_BASE_URL = 'http://127.0.0.1:1337'

+export type OllamaGenerationReadiness = {
+  state: 'ready' | 'unreachable' | 'no_models' | 'generation_failed'
+  models: OllamaModelDescriptor[]
+  probeModel?: string
+  detail?: string
+}
+
 function withTimeoutSignal(timeoutMs: number): {
  signal: AbortSignal
  clear: () => void
@@ -20,6 +27,83 @@ function trimTrailingSlash(value: string): string {
  return value.replace(/\/+$/, '')
 }

+function compactDetail(value: string, maxLength = 180): string {
+  const compact = value.trim().replace(/\s+/g, ' ')
+  if (!compact) {
+    return ''
+  }
+
+  if (compact.length <= maxLength) {
+    return compact
+  }
+
+  return `${compact.slice(0, maxLength)}...`
+}
+
+type OllamaTagsPayload = {
+  models?: Array<{
+    name?: string
+    size?: number
+    details?: {
+      family?: string
+      families?: string[]
+      parameter_size?: string
+      quantization_level?: string
+    }
+  }>
+}
+
+function normalizeOllamaModels(
+  payload: OllamaTagsPayload,
+): OllamaModelDescriptor[] {
+  return (payload.models ?? [])
+    .filter(model => Boolean(model.name))
+    .map(model => ({
+      name: model.name!,
+      sizeBytes: typeof model.size === 'number' ? model.size : null,
+      family: model.details?.family ?? null,
+      families: model.details?.families ?? [],
+      parameterSize: model.details?.parameter_size ?? null,
+      quantizationLevel: model.details?.quantization_level ?? null,
+    }))
+}
+
+async function fetchOllamaModelsProbe(
+  baseUrl?: string,
+  timeoutMs = 5000,
+): Promise<{
+  reachable: boolean
+  models: OllamaModelDescriptor[]
+}> {
+  const { signal, clear } = withTimeoutSignal(timeoutMs)
+  try {
+    const response = await fetch(`${getOllamaApiBaseUrl(baseUrl)}/api/tags`, {
+      method: 'GET',
+      signal,
+    })
+
+    if (!response.ok) {
+      return {
+        reachable: false,
+        models: [],
+      }
+    }
+
+    const payload = (await response.json().catch(() => ({}))) as OllamaTagsPayload
+    return {
+      reachable: true,
+      models: normalizeOllamaModels(payload),
+    }
+  } catch {
+    return {
+      reachable: false,
+      models: [],
+    }
+  } finally {
+    clear()
+  }
+}
+
 export function getOllamaApiBaseUrl(baseUrl?: string): string {
  const parsed = new URL(
    baseUrl || process.env.OLLAMA_BASE_URL || DEFAULT_OLLAMA_BASE_URL,
@@ -121,61 +205,15 @@ export function getLocalOpenAICompatibleProviderLabel(baseUrl?: string): string
 }

 export async function hasLocalOllama(baseUrl?: string): Promise<boolean> {
-  const { signal, clear } = withTimeoutSignal(1200)
-  try {
-    const response = await fetch(`${getOllamaApiBaseUrl(baseUrl)}/api/tags`, {
-      method: 'GET',
-      signal,
-    })
-    return response.ok
-  } catch {
-    return false
-  } finally {
-    clear()
-  }
+  const { reachable } = await fetchOllamaModelsProbe(baseUrl, 1200)
+  return reachable
 }

 export async function listOllamaModels(
  baseUrl?: string,
 ): Promise<OllamaModelDescriptor[]> {
-  const { signal, clear } = withTimeoutSignal(5000)
-  try {
-    const response = await fetch(`${getOllamaApiBaseUrl(baseUrl)}/api/tags`, {
-      method: 'GET',
-      signal,
-    })
-    if (!response.ok) {
-      return []
-    }
-
-    const data = (await response.json()) as {
-      models?: Array<{
-        name?: string
-        size?: number
-        details?: {
-          family?: string
-          families?: string[]
-          parameter_size?: string
-          quantization_level?: string
-        }
-      }>
-    }
-
-    return (data.models ?? [])
-      .filter(model => Boolean(model.name))
-      .map(model => ({
-        name: model.name!,
-        sizeBytes: typeof model.size === 'number' ? model.size : null,
-        family: model.details?.family ?? null,
-        families: model.details?.families ?? [],
-        parameterSize: model.details?.parameter_size ?? null,
-        quantizationLevel: model.details?.quantization_level ?? null,
-      }))
-  } catch {
-    return []
-  } finally {
-    clear()
-  }
+  const { models } = await fetchOllamaModelsProbe(baseUrl, 5000)
+  return models
 }

 export async function listOpenAICompatibleModels(options?: {
@@ -294,3 +332,106 @@ export async function benchmarkOllamaModel(
    clear()
  }
 }
+
+export async function probeOllamaGenerationReadiness(options?: {
+  baseUrl?: string
+  model?: string
+  timeoutMs?: number
+}): Promise<OllamaGenerationReadiness> {
+  const timeoutMs = options?.timeoutMs ?? 8000
+  const { reachable, models } = await fetchOllamaModelsProbe(
+    options?.baseUrl,
+    timeoutMs,
+  )
+  if (!reachable) {
+    return {
+      state: 'unreachable',
+      models: [],
+    }
+  }
+
+  if (models.length === 0) {
+    return {
+      state: 'no_models',
+      models: [],
+    }
+  }
+
+  const requestedModel = options?.model?.trim() || undefined
+  if (requestedModel && !models.some(model => model.name === requestedModel)) {
+    return {
+      state: 'generation_failed',
+      models,
+      probeModel: requestedModel,
+      detail: `requested model not installed: ${requestedModel}`,
+    }
+  }
+
+  const probeModel = requestedModel ?? models[0]!.name
+  const { signal, clear } = withTimeoutSignal(timeoutMs)
+
+  try {
+    const response = await fetch(`${getOllamaApiBaseUrl(options?.baseUrl)}/api/chat`, {
+      method: 'POST',
+      headers: {
+        'Content-Type': 'application/json',
+      },
+      signal,
+      body: JSON.stringify({
+        model: probeModel,
+        stream: false,
+        messages: [{ role: 'user', content: 'Reply with OK.' }],
+        options: {
+          temperature: 0,
+          num_predict: 8,
+        },
+      }),
+    })
+
+    if (!response.ok) {
+      const responseBody = await response.text().catch(() => '')
+      const detailSuffix = compactDetail(responseBody)
+      return {
+        state: 'generation_failed',
+        models,
+        probeModel,
+        detail: detailSuffix
+          ? `status ${response.status}: ${detailSuffix}`
+          : `status ${response.status}`,
+      }
+    }
+
+    try {
+      await response.json()
+    } catch {
+      return {
+        state: 'generation_failed',
+        models,
+        probeModel,
+        detail: 'invalid JSON response',
+      }
+    }
+
+    return {
+      state: 'ready',
+      models,
+      probeModel,
+    }
+  } catch (error) {
+    const detail =
+      error instanceof Error
+        ? error.name === 'AbortError'
+          ? 'request timed out'
+          : error.message
+        : String(error)
+
+    return {
+      state: 'generation_failed',
+      models,
+      probeModel,
+      detail,
+    }
+  } finally {
+    clear()
+  }
+}