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>
This commit is contained in:
nehan
GitHub
@@ -320,10 +320,7 @@ export function classifyOpenAIHttpFailure(options: {
|
||||
}
|
||||
}
|
||||
|
||||
if (
|
||||
(options.status >= 200 && options.status < 300 && isMalformedProviderResponse(body)) ||
|
||||
(options.status >= 400 && isMalformedProviderResponse(body))
|
||||
) {
|
||||
if (options.status >= 400 && isMalformedProviderResponse(body)) {
|
||||
return {
|
||||
source: 'http',
|
||||
category: 'malformed_provider_response',
|
||||
|
||||
@@ -117,3 +117,170 @@ test('redacts credentials in transport diagnostic URL logs', async () => {
|
||||
expect(logLine).not.toContain('user:supersecret')
|
||||
expect(logLine).not.toContain('supersecret@')
|
||||
})
|
||||
test('logs self-heal localhost fallback with redacted from/to URLs', async () => {
|
||||
const debugSpy = mock(() => {})
|
||||
mock.module('../../utils/debug.js', () => ({
|
||||
logForDebugging: debugSpy,
|
||||
}))
|
||||
|
||||
const nonce = `${Date.now()}-${Math.random()}`
|
||||
const { createOpenAIShimClient } = await import(`./openaiShim.ts?ts=${nonce}`)
|
||||
|
||||
process.env.OPENAI_BASE_URL = 'http://user:supersecret@localhost:11434/v1'
|
||||
process.env.OPENAI_API_KEY = 'supersecret'
|
||||
|
||||
globalThis.fetch = mock(async (input: string | Request) => {
|
||||
const url = typeof input === 'string' ? input : input.url
|
||||
if (url.includes('localhost')) {
|
||||
throw Object.assign(new TypeError('fetch failed'), {
|
||||
code: 'ENOTFOUND',
|
||||
})
|
||||
}
|
||||
|
||||
return new Response(
|
||||
JSON.stringify({
|
||||
id: 'chatcmpl-1',
|
||||
model: 'qwen2.5-coder:7b',
|
||||
choices: [
|
||||
{
|
||||
message: {
|
||||
role: 'assistant',
|
||||
content: 'ok',
|
||||
},
|
||||
finish_reason: 'stop',
|
||||
},
|
||||
],
|
||||
usage: {
|
||||
prompt_tokens: 5,
|
||||
completion_tokens: 2,
|
||||
total_tokens: 7,
|
||||
},
|
||||
}),
|
||||
{
|
||||
status: 200,
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
},
|
||||
)
|
||||
}) as typeof globalThis.fetch
|
||||
|
||||
const client = createOpenAIShimClient({}) as {
|
||||
beta: {
|
||||
messages: {
|
||||
create: (params: Record<string, unknown>) => Promise<unknown>
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
await expect(
|
||||
client.beta.messages.create({
|
||||
model: 'qwen2.5-coder:7b',
|
||||
messages: [{ role: 'user', content: 'hello' }],
|
||||
max_tokens: 64,
|
||||
stream: false,
|
||||
}),
|
||||
).resolves.toBeDefined()
|
||||
|
||||
const fallbackLog = debugSpy.mock.calls.find(call =>
|
||||
typeof call?.[0] === 'string' &&
|
||||
call[0].includes('self-heal retry reason=localhost_resolution_failed'),
|
||||
)
|
||||
|
||||
expect(fallbackLog).toBeDefined()
|
||||
const logLine = String(fallbackLog?.[0])
|
||||
expect(logLine).toContain('from=http://redacted:redacted@localhost:11434/v1/chat/completions')
|
||||
expect(logLine).toContain('to=http://redacted:redacted@127.0.0.1:11434/v1/chat/completions')
|
||||
expect(logLine).not.toContain('supersecret')
|
||||
})
|
||||
|
||||
test('logs self-heal toolless retry for local tool-call incompatibility', async () => {
|
||||
const debugSpy = mock(() => {})
|
||||
mock.module('../../utils/debug.js', () => ({
|
||||
logForDebugging: debugSpy,
|
||||
}))
|
||||
|
||||
const nonce = `${Date.now()}-${Math.random()}`
|
||||
const { createOpenAIShimClient } = await import(`./openaiShim.ts?ts=${nonce}`)
|
||||
|
||||
process.env.OPENAI_BASE_URL = 'http://localhost:11434/v1'
|
||||
process.env.OPENAI_API_KEY = 'ollama'
|
||||
|
||||
let callCount = 0
|
||||
globalThis.fetch = mock(async () => {
|
||||
callCount += 1
|
||||
if (callCount === 1) {
|
||||
return new Response('tool_calls are not supported', {
|
||||
status: 400,
|
||||
headers: {
|
||||
'Content-Type': 'text/plain',
|
||||
},
|
||||
})
|
||||
}
|
||||
|
||||
return new Response(
|
||||
JSON.stringify({
|
||||
id: 'chatcmpl-1',
|
||||
model: 'qwen2.5-coder:7b',
|
||||
choices: [
|
||||
{
|
||||
message: {
|
||||
role: 'assistant',
|
||||
content: 'ok',
|
||||
},
|
||||
finish_reason: 'stop',
|
||||
},
|
||||
],
|
||||
usage: {
|
||||
prompt_tokens: 7,
|
||||
completion_tokens: 3,
|
||||
total_tokens: 10,
|
||||
},
|
||||
}),
|
||||
{
|
||||
status: 200,
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
},
|
||||
)
|
||||
}) as typeof globalThis.fetch
|
||||
|
||||
const client = createOpenAIShimClient({}) as {
|
||||
beta: {
|
||||
messages: {
|
||||
create: (params: Record<string, unknown>) => Promise<unknown>
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
await expect(
|
||||
client.beta.messages.create({
|
||||
model: 'qwen2.5-coder:7b',
|
||||
messages: [{ role: 'user', content: 'hello' }],
|
||||
tools: [
|
||||
{
|
||||
name: 'Read',
|
||||
description: 'Read file',
|
||||
input_schema: {
|
||||
type: 'object',
|
||||
properties: {
|
||||
filePath: { type: 'string' },
|
||||
},
|
||||
required: ['filePath'],
|
||||
},
|
||||
},
|
||||
],
|
||||
max_tokens: 64,
|
||||
stream: false,
|
||||
}),
|
||||
).resolves.toBeDefined()
|
||||
|
||||
const fallbackLog = debugSpy.mock.calls.find(call =>
|
||||
typeof call?.[0] === 'string' &&
|
||||
call[0].includes('self-heal retry reason=tool_call_incompatible mode=toolless'),
|
||||
)
|
||||
|
||||
expect(fallbackLog).toBeDefined()
|
||||
expect(fallbackLog?.[1]).toEqual({ level: 'warn' })
|
||||
})
|
||||
|
||||
@@ -2931,6 +2931,204 @@ test('classifies chat-completions endpoint 404 failures with endpoint_not_found
|
||||
}),
|
||||
).rejects.toThrow('openai_category=endpoint_not_found')
|
||||
})
|
||||
test('self-heals localhost resolution failures by retrying local loopback base URL', async () => {
|
||||
process.env.OPENAI_BASE_URL = 'http://localhost:11434/v1'
|
||||
|
||||
const requestUrls: string[] = []
|
||||
globalThis.fetch = (async (input, _init) => {
|
||||
const url = typeof input === 'string' ? input : input.url
|
||||
requestUrls.push(url)
|
||||
|
||||
if (url.includes('localhost')) {
|
||||
const error = Object.assign(new TypeError('fetch failed'), {
|
||||
code: 'ENOTFOUND',
|
||||
})
|
||||
throw error
|
||||
}
|
||||
|
||||
return new Response(
|
||||
JSON.stringify({
|
||||
id: 'chatcmpl-1',
|
||||
model: 'qwen2.5-coder:7b',
|
||||
choices: [
|
||||
{
|
||||
message: {
|
||||
role: 'assistant',
|
||||
content: 'hello from loopback',
|
||||
},
|
||||
finish_reason: 'stop',
|
||||
},
|
||||
],
|
||||
usage: {
|
||||
prompt_tokens: 4,
|
||||
completion_tokens: 3,
|
||||
total_tokens: 7,
|
||||
},
|
||||
}),
|
||||
{
|
||||
status: 200,
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
},
|
||||
)
|
||||
}) as FetchType
|
||||
|
||||
const client = createOpenAIShimClient({}) as OpenAIShimClient
|
||||
|
||||
await expect(
|
||||
client.beta.messages.create({
|
||||
model: 'qwen2.5-coder:7b',
|
||||
messages: [{ role: 'user', content: 'hello' }],
|
||||
max_tokens: 64,
|
||||
stream: false,
|
||||
}),
|
||||
).resolves.toBeDefined()
|
||||
|
||||
expect(requestUrls[0]).toBe('http://localhost:11434/v1/chat/completions')
|
||||
expect(requestUrls).toContain('http://127.0.0.1:11434/v1/chat/completions')
|
||||
})
|
||||
|
||||
test('self-heals local endpoint_not_found by retrying with /v1 base URL', async () => {
|
||||
process.env.OPENAI_BASE_URL = 'http://localhost:11434'
|
||||
|
||||
const requestUrls: string[] = []
|
||||
globalThis.fetch = (async (input, _init) => {
|
||||
const url = typeof input === 'string' ? input : input.url
|
||||
requestUrls.push(url)
|
||||
|
||||
if (url === 'http://localhost:11434/chat/completions') {
|
||||
return new Response('Not Found', {
|
||||
status: 404,
|
||||
headers: {
|
||||
'Content-Type': 'text/plain',
|
||||
},
|
||||
})
|
||||
}
|
||||
|
||||
return new Response(
|
||||
JSON.stringify({
|
||||
id: 'chatcmpl-1',
|
||||
model: 'qwen2.5-coder:7b',
|
||||
choices: [
|
||||
{
|
||||
message: {
|
||||
role: 'assistant',
|
||||
content: 'hello from /v1',
|
||||
},
|
||||
finish_reason: 'stop',
|
||||
},
|
||||
],
|
||||
usage: {
|
||||
prompt_tokens: 5,
|
||||
completion_tokens: 2,
|
||||
total_tokens: 7,
|
||||
},
|
||||
}),
|
||||
{
|
||||
status: 200,
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
},
|
||||
)
|
||||
}) as FetchType
|
||||
|
||||
const client = createOpenAIShimClient({}) as OpenAIShimClient
|
||||
|
||||
await expect(
|
||||
client.beta.messages.create({
|
||||
model: 'qwen2.5-coder:7b',
|
||||
messages: [{ role: 'user', content: 'hello' }],
|
||||
max_tokens: 64,
|
||||
stream: false,
|
||||
}),
|
||||
).resolves.toBeDefined()
|
||||
|
||||
expect(requestUrls).toEqual([
|
||||
'http://localhost:11434/chat/completions',
|
||||
'http://localhost:11434/v1/chat/completions',
|
||||
])
|
||||
})
|
||||
|
||||
test('self-heals tool-call incompatibility by retrying local Ollama requests without tools', async () => {
|
||||
process.env.OPENAI_BASE_URL = 'http://localhost:11434/v1'
|
||||
|
||||
const requestBodies: Array<Record<string, unknown>> = []
|
||||
globalThis.fetch = (async (_input, init) => {
|
||||
const requestBody = JSON.parse(String(init?.body)) as Record<string, unknown>
|
||||
requestBodies.push(requestBody)
|
||||
|
||||
if (requestBodies.length === 1) {
|
||||
return new Response('tool_calls are not supported', {
|
||||
status: 400,
|
||||
headers: {
|
||||
'Content-Type': 'text/plain',
|
||||
},
|
||||
})
|
||||
}
|
||||
|
||||
return new Response(
|
||||
JSON.stringify({
|
||||
id: 'chatcmpl-1',
|
||||
model: 'qwen2.5-coder:7b',
|
||||
choices: [
|
||||
{
|
||||
message: {
|
||||
role: 'assistant',
|
||||
content: 'fallback without tools',
|
||||
},
|
||||
finish_reason: 'stop',
|
||||
},
|
||||
],
|
||||
usage: {
|
||||
prompt_tokens: 8,
|
||||
completion_tokens: 4,
|
||||
total_tokens: 12,
|
||||
},
|
||||
}),
|
||||
{
|
||||
status: 200,
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
},
|
||||
)
|
||||
}) as FetchType
|
||||
|
||||
const client = createOpenAIShimClient({}) as OpenAIShimClient
|
||||
|
||||
await expect(
|
||||
client.beta.messages.create({
|
||||
model: 'qwen2.5-coder:7b',
|
||||
messages: [{ role: 'user', content: 'hello' }],
|
||||
tools: [
|
||||
{
|
||||
name: 'Read',
|
||||
description: 'Read a file',
|
||||
input_schema: {
|
||||
type: 'object',
|
||||
properties: {
|
||||
filePath: { type: 'string' },
|
||||
},
|
||||
required: ['filePath'],
|
||||
},
|
||||
},
|
||||
],
|
||||
max_tokens: 64,
|
||||
stream: false,
|
||||
}),
|
||||
).resolves.toBeDefined()
|
||||
|
||||
expect(requestBodies).toHaveLength(2)
|
||||
expect(Array.isArray(requestBodies[0]?.tools)).toBe(true)
|
||||
expect(requestBodies[0]?.tool_choice).toBeUndefined()
|
||||
expect(
|
||||
requestBodies[1]?.tools === undefined ||
|
||||
(Array.isArray(requestBodies[1]?.tools) && requestBodies[1]?.tools.length === 0),
|
||||
).toBe(true)
|
||||
expect(requestBodies[1]?.tool_choice).toBeUndefined()
|
||||
})
|
||||
|
||||
test('preserves valid tool_result and drops orphan tool_result', async () => {
|
||||
let requestBody: Record<string, unknown> | undefined
|
||||
@@ -2999,7 +3197,7 @@ test('preserves valid tool_result and drops orphan tool_result', async () => {
|
||||
{
|
||||
role: 'user',
|
||||
content: 'What happened?',
|
||||
}
|
||||
},
|
||||
],
|
||||
},
|
||||
],
|
||||
@@ -3008,14 +3206,14 @@ test('preserves valid tool_result and drops orphan tool_result', async () => {
|
||||
})
|
||||
|
||||
const messages = requestBody?.messages as Array<Record<string, unknown>>
|
||||
|
||||
|
||||
// Should have: system, user, assistant (tool_use), tool (valid_call_1), user
|
||||
// Should NOT have: tool (orphan_call_2)
|
||||
|
||||
|
||||
const toolMessages = messages.filter(m => m.role === 'tool')
|
||||
expect(toolMessages.length).toBe(1)
|
||||
expect(toolMessages[0].tool_call_id).toBe('valid_call_1')
|
||||
|
||||
|
||||
const orphanMessage = toolMessages.find(m => m.tool_call_id === 'orphan_call_2')
|
||||
expect(orphanMessage).toBeUndefined()
|
||||
})
|
||||
|
||||
@@ -48,10 +48,12 @@ import {
|
||||
} from './codexShim.js'
|
||||
import { fetchWithProxyRetry } from './fetchWithProxyRetry.js'
|
||||
import {
|
||||
getLocalProviderRetryBaseUrls,
|
||||
getGithubEndpointType,
|
||||
isLocalProviderUrl,
|
||||
resolveRuntimeCodexCredentials,
|
||||
resolveProviderRequest,
|
||||
getGithubEndpointType,
|
||||
shouldAttemptLocalToollessRetry,
|
||||
} from './providerConfig.js'
|
||||
import {
|
||||
buildOpenAICompatibilityErrorMessage,
|
||||
@@ -1427,48 +1429,95 @@ class OpenAIShimMessages {
|
||||
headers['X-GitHub-Api-Version'] = '2022-11-28'
|
||||
}
|
||||
|
||||
// Build the chat completions URL
|
||||
// Azure Cognitive Services / Azure OpenAI require a deployment-specific path
|
||||
// and an api-version query parameter.
|
||||
// Standard format: {base}/openai/deployments/{model}/chat/completions?api-version={version}
|
||||
// Non-Azure: {base}/chat/completions
|
||||
let chatCompletionsUrl: string
|
||||
if (isAzure) {
|
||||
const apiVersion = process.env.AZURE_OPENAI_API_VERSION ?? '2024-12-01-preview'
|
||||
const deployment = request.resolvedModel ?? process.env.OPENAI_MODEL ?? 'gpt-4o'
|
||||
// If base URL already contains /deployments/, use it as-is with api-version
|
||||
if (/\/deployments\//i.test(request.baseUrl)) {
|
||||
const base = request.baseUrl.replace(/\/+$/, '')
|
||||
chatCompletionsUrl = `${base}/chat/completions?api-version=${apiVersion}`
|
||||
} else {
|
||||
// Strip trailing /v1 or /openai/v1 if present, then build Azure path
|
||||
const base = request.baseUrl.replace(/\/(openai\/)?v1\/?$/, '').replace(/\/+$/, '')
|
||||
chatCompletionsUrl = `${base}/openai/deployments/${deployment}/chat/completions?api-version=${apiVersion}`
|
||||
const buildChatCompletionsUrl = (baseUrl: string): string => {
|
||||
// Azure Cognitive Services / Azure OpenAI require a deployment-specific
|
||||
// path and an api-version query parameter.
|
||||
if (isAzure) {
|
||||
const apiVersion = process.env.AZURE_OPENAI_API_VERSION ?? '2024-12-01-preview'
|
||||
const deployment = request.resolvedModel ?? process.env.OPENAI_MODEL ?? 'gpt-4o'
|
||||
|
||||
// If base URL already contains /deployments/, use it as-is with api-version.
|
||||
if (/\/deployments\//i.test(baseUrl)) {
|
||||
const normalizedBase = baseUrl.replace(/\/+$/, '')
|
||||
return `${normalizedBase}/chat/completions?api-version=${apiVersion}`
|
||||
}
|
||||
|
||||
// Strip trailing /v1 or /openai/v1 if present, then build Azure path.
|
||||
const normalizedBase = baseUrl
|
||||
.replace(/\/(openai\/)?v1\/?$/, '')
|
||||
.replace(/\/+$/, '')
|
||||
|
||||
return `${normalizedBase}/openai/deployments/${deployment}/chat/completions?api-version=${apiVersion}`
|
||||
}
|
||||
} else {
|
||||
chatCompletionsUrl = `${request.baseUrl}/chat/completions`
|
||||
|
||||
return `${baseUrl}/chat/completions`
|
||||
}
|
||||
|
||||
const fetchInit = {
|
||||
const localRetryBaseUrls = isLocal
|
||||
? getLocalProviderRetryBaseUrls(request.baseUrl)
|
||||
: []
|
||||
|
||||
let activeBaseUrl = request.baseUrl
|
||||
let chatCompletionsUrl = buildChatCompletionsUrl(activeBaseUrl)
|
||||
const attemptedLocalBaseUrls = new Set<string>([activeBaseUrl])
|
||||
let didRetryWithoutTools = false
|
||||
|
||||
const promoteNextLocalBaseUrl = (
|
||||
reason: 'endpoint_not_found' | 'localhost_resolution_failed',
|
||||
): boolean => {
|
||||
for (const candidateBaseUrl of localRetryBaseUrls) {
|
||||
if (attemptedLocalBaseUrls.has(candidateBaseUrl)) {
|
||||
continue
|
||||
}
|
||||
|
||||
const previousUrl = chatCompletionsUrl
|
||||
attemptedLocalBaseUrls.add(candidateBaseUrl)
|
||||
activeBaseUrl = candidateBaseUrl
|
||||
chatCompletionsUrl = buildChatCompletionsUrl(activeBaseUrl)
|
||||
|
||||
logForDebugging(
|
||||
`[OpenAIShim] self-heal retry reason=${reason} method=POST from=${redactUrlForDiagnostics(previousUrl)} to=${redactUrlForDiagnostics(chatCompletionsUrl)} model=${request.resolvedModel}`,
|
||||
{ level: 'warn' },
|
||||
)
|
||||
|
||||
return true
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
let serializedBody = JSON.stringify(body)
|
||||
|
||||
const refreshSerializedBody = (): void => {
|
||||
serializedBody = JSON.stringify(body)
|
||||
}
|
||||
|
||||
const buildFetchInit = () => ({
|
||||
method: 'POST' as const,
|
||||
headers,
|
||||
body: JSON.stringify(body),
|
||||
body: serializedBody,
|
||||
signal: options?.signal,
|
||||
}
|
||||
})
|
||||
|
||||
const maxAttempts = isGithub ? GITHUB_429_MAX_RETRIES : 1
|
||||
const maxSelfHealAttempts = isLocal
|
||||
? localRetryBaseUrls.length + 1
|
||||
: 0
|
||||
const maxAttempts = (isGithub ? GITHUB_429_MAX_RETRIES : 1) + maxSelfHealAttempts
|
||||
|
||||
const throwClassifiedTransportError = (
|
||||
error: unknown,
|
||||
requestUrl: string,
|
||||
preclassifiedFailure?: ReturnType<typeof classifyOpenAINetworkFailure>,
|
||||
): never => {
|
||||
if (options?.signal?.aborted) {
|
||||
throw error
|
||||
}
|
||||
|
||||
const failure = classifyOpenAINetworkFailure(error, {
|
||||
url: requestUrl,
|
||||
})
|
||||
const failure =
|
||||
preclassifiedFailure ??
|
||||
classifyOpenAINetworkFailure(error, {
|
||||
url: requestUrl,
|
||||
})
|
||||
const redactedUrl = redactUrlForDiagnostics(requestUrl)
|
||||
const safeMessage =
|
||||
redactSecretValueForDisplay(
|
||||
@@ -1499,11 +1548,14 @@ class OpenAIShimMessages {
|
||||
responseHeaders: Headers,
|
||||
requestUrl: string,
|
||||
rateHint = '',
|
||||
preclassifiedFailure?: ReturnType<typeof classifyOpenAIHttpFailure>,
|
||||
): never => {
|
||||
const failure = classifyOpenAIHttpFailure({
|
||||
status,
|
||||
body: errorBody,
|
||||
})
|
||||
const failure =
|
||||
preclassifiedFailure ??
|
||||
classifyOpenAIHttpFailure({
|
||||
status,
|
||||
body: errorBody,
|
||||
})
|
||||
const redactedUrl = redactUrlForDiagnostics(requestUrl)
|
||||
|
||||
logForDebugging(
|
||||
@@ -1525,10 +1577,13 @@ class OpenAIShimMessages {
|
||||
let response: Response | undefined
|
||||
for (let attempt = 0; attempt < maxAttempts; attempt++) {
|
||||
try {
|
||||
response = await fetchWithProxyRetry(chatCompletionsUrl, fetchInit)
|
||||
response = await fetchWithProxyRetry(
|
||||
chatCompletionsUrl,
|
||||
buildFetchInit(),
|
||||
)
|
||||
} catch (error) {
|
||||
const isAbortError =
|
||||
fetchInit.signal?.aborted === true ||
|
||||
options?.signal?.aborted === true ||
|
||||
(typeof DOMException !== 'undefined' &&
|
||||
error instanceof DOMException &&
|
||||
error.name === 'AbortError') ||
|
||||
@@ -1541,7 +1596,19 @@ class OpenAIShimMessages {
|
||||
throw error
|
||||
}
|
||||
|
||||
throwClassifiedTransportError(error, chatCompletionsUrl)
|
||||
const failure = classifyOpenAINetworkFailure(error, {
|
||||
url: chatCompletionsUrl,
|
||||
})
|
||||
|
||||
if (
|
||||
isLocal &&
|
||||
failure.category === 'localhost_resolution_failed' &&
|
||||
promoteNextLocalBaseUrl('localhost_resolution_failed')
|
||||
) {
|
||||
continue
|
||||
}
|
||||
|
||||
throwClassifiedTransportError(error, chatCompletionsUrl, failure)
|
||||
}
|
||||
|
||||
if (response.ok) {
|
||||
@@ -1633,6 +1700,10 @@ class OpenAIShimMessages {
|
||||
return responsesResponse
|
||||
}
|
||||
const responsesErrorBody = await responsesResponse.text().catch(() => 'unknown error')
|
||||
const responsesFailure = classifyOpenAIHttpFailure({
|
||||
status: responsesResponse.status,
|
||||
body: responsesErrorBody,
|
||||
})
|
||||
let responsesErrorResponse: object | undefined
|
||||
try { responsesErrorResponse = JSON.parse(responsesErrorBody) } catch { /* raw text */ }
|
||||
throwClassifiedHttpError(
|
||||
@@ -1641,10 +1712,49 @@ class OpenAIShimMessages {
|
||||
responsesErrorResponse,
|
||||
responsesResponse.headers,
|
||||
responsesUrl,
|
||||
'',
|
||||
responsesFailure,
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
const failure = classifyOpenAIHttpFailure({
|
||||
status: response.status,
|
||||
body: errorBody,
|
||||
})
|
||||
|
||||
if (
|
||||
isLocal &&
|
||||
failure.category === 'endpoint_not_found' &&
|
||||
promoteNextLocalBaseUrl('endpoint_not_found')
|
||||
) {
|
||||
continue
|
||||
}
|
||||
|
||||
const hasToolsPayload =
|
||||
Array.isArray(body.tools) &&
|
||||
body.tools.length > 0
|
||||
|
||||
if (
|
||||
!didRetryWithoutTools &&
|
||||
failure.category === 'tool_call_incompatible' &&
|
||||
shouldAttemptLocalToollessRetry({
|
||||
baseUrl: activeBaseUrl,
|
||||
hasTools: hasToolsPayload,
|
||||
})
|
||||
) {
|
||||
didRetryWithoutTools = true
|
||||
delete body.tools
|
||||
delete body.tool_choice
|
||||
refreshSerializedBody()
|
||||
|
||||
logForDebugging(
|
||||
`[OpenAIShim] self-heal retry reason=tool_call_incompatible mode=toolless method=POST url=${redactUrlForDiagnostics(chatCompletionsUrl)} model=${request.resolvedModel}`,
|
||||
{ level: 'warn' },
|
||||
)
|
||||
continue
|
||||
}
|
||||
|
||||
let errorResponse: object | undefined
|
||||
try { errorResponse = JSON.parse(errorBody) } catch { /* raw text */ }
|
||||
throwClassifiedHttpError(
|
||||
@@ -1654,6 +1764,7 @@ class OpenAIShimMessages {
|
||||
response.headers as unknown as Headers,
|
||||
chatCompletionsUrl,
|
||||
rateHint,
|
||||
failure,
|
||||
)
|
||||
}
|
||||
|
||||
|
||||
@@ -2,8 +2,10 @@ import { afterEach, expect, test } from 'bun:test'
|
||||
|
||||
import {
|
||||
getAdditionalModelOptionsCacheScope,
|
||||
getLocalProviderRetryBaseUrls,
|
||||
isLocalProviderUrl,
|
||||
resolveProviderRequest,
|
||||
shouldAttemptLocalToollessRetry,
|
||||
} from './providerConfig.js'
|
||||
|
||||
const originalEnv = {
|
||||
@@ -83,3 +85,42 @@ test('skips local model cache scope for remote openai-compatible providers', ()
|
||||
|
||||
expect(getAdditionalModelOptionsCacheScope()).toBeNull()
|
||||
})
|
||||
|
||||
test('derives local retry base URLs with /v1 and loopback fallback candidates', () => {
|
||||
expect(getLocalProviderRetryBaseUrls('http://localhost:11434')).toEqual([
|
||||
'http://localhost:11434/v1',
|
||||
'http://127.0.0.1:11434',
|
||||
'http://127.0.0.1:11434/v1',
|
||||
])
|
||||
})
|
||||
|
||||
test('does not derive local retry base URLs for remote providers', () => {
|
||||
expect(getLocalProviderRetryBaseUrls('https://api.openai.com/v1')).toEqual([])
|
||||
})
|
||||
|
||||
test('enables local toolless retry for likely Ollama endpoints with tools', () => {
|
||||
expect(
|
||||
shouldAttemptLocalToollessRetry({
|
||||
baseUrl: 'http://localhost:11434/v1',
|
||||
hasTools: true,
|
||||
}),
|
||||
).toBe(true)
|
||||
})
|
||||
|
||||
test('disables local toolless retry when no tools are present', () => {
|
||||
expect(
|
||||
shouldAttemptLocalToollessRetry({
|
||||
baseUrl: 'http://localhost:11434/v1',
|
||||
hasTools: false,
|
||||
}),
|
||||
).toBe(false)
|
||||
})
|
||||
|
||||
test('disables local toolless retry for non-Ollama local endpoints', () => {
|
||||
expect(
|
||||
shouldAttemptLocalToollessRetry({
|
||||
baseUrl: 'http://localhost:1234/v1',
|
||||
hasTools: true,
|
||||
}),
|
||||
).toBe(false)
|
||||
})
|
||||
|
||||
@@ -305,6 +305,101 @@ export function isLocalProviderUrl(baseUrl: string | undefined): boolean {
|
||||
}
|
||||
}
|
||||
|
||||
function trimTrailingSlash(value: string): string {
|
||||
return value.replace(/\/+$/, '')
|
||||
}
|
||||
|
||||
function normalizePathWithV1(pathname: string): string {
|
||||
const trimmed = trimTrailingSlash(pathname)
|
||||
if (!trimmed || trimmed === '/') {
|
||||
return '/v1'
|
||||
}
|
||||
|
||||
if (trimmed.toLowerCase().endsWith('/v1')) {
|
||||
return trimmed
|
||||
}
|
||||
|
||||
return `${trimmed}/v1`
|
||||
}
|
||||
|
||||
function isLikelyOllamaEndpoint(baseUrl: string): boolean {
|
||||
try {
|
||||
const parsed = new URL(baseUrl)
|
||||
const hostname = parsed.hostname.toLowerCase()
|
||||
const pathname = parsed.pathname.toLowerCase()
|
||||
|
||||
if (parsed.port === '11434') {
|
||||
return true
|
||||
}
|
||||
|
||||
return (
|
||||
hostname.includes('ollama') ||
|
||||
pathname.includes('ollama')
|
||||
)
|
||||
} catch {
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
export function getLocalProviderRetryBaseUrls(baseUrl: string): string[] {
|
||||
if (!isLocalProviderUrl(baseUrl)) {
|
||||
return []
|
||||
}
|
||||
|
||||
try {
|
||||
const parsed = new URL(baseUrl)
|
||||
const original = trimTrailingSlash(parsed.toString())
|
||||
const seen = new Set<string>([original])
|
||||
const candidates: string[] = []
|
||||
|
||||
const addCandidate = (hostname: string, pathname: string): void => {
|
||||
const next = new URL(parsed.toString())
|
||||
next.hostname = hostname
|
||||
next.pathname = pathname
|
||||
next.search = ''
|
||||
next.hash = ''
|
||||
|
||||
const normalized = trimTrailingSlash(next.toString())
|
||||
if (seen.has(normalized)) {
|
||||
return
|
||||
}
|
||||
|
||||
seen.add(normalized)
|
||||
candidates.push(normalized)
|
||||
}
|
||||
|
||||
const v1Pathname = normalizePathWithV1(parsed.pathname)
|
||||
if (v1Pathname !== trimTrailingSlash(parsed.pathname)) {
|
||||
addCandidate(parsed.hostname, v1Pathname)
|
||||
}
|
||||
|
||||
const hostname = parsed.hostname.toLowerCase().replace(/^\[|\]$/g, '')
|
||||
if (hostname === 'localhost' || hostname === '::1') {
|
||||
addCandidate('127.0.0.1', parsed.pathname || '/')
|
||||
addCandidate('127.0.0.1', v1Pathname)
|
||||
}
|
||||
|
||||
return candidates
|
||||
} catch {
|
||||
return []
|
||||
}
|
||||
}
|
||||
|
||||
export function shouldAttemptLocalToollessRetry(options: {
|
||||
baseUrl: string
|
||||
hasTools: boolean
|
||||
}): boolean {
|
||||
if (!options.hasTools) {
|
||||
return false
|
||||
}
|
||||
|
||||
if (!isLocalProviderUrl(options.baseUrl)) {
|
||||
return false
|
||||
}
|
||||
|
||||
return isLikelyOllamaEndpoint(options.baseUrl)
|
||||
}
|
||||
|
||||
export function isCodexBaseUrl(baseUrl: string | undefined): boolean {
|
||||
if (!baseUrl) return false
|
||||
try {
|
||||
@@ -412,6 +507,9 @@ export function resolveProviderRequest(options?: {
|
||||
? normalizedGeminiEnvBaseUrl
|
||||
: asNamedEnvUrl(process.env.OPENAI_BASE_URL, 'OPENAI_BASE_URL')
|
||||
|
||||
// In Mistral mode, a literal "undefined" MISTRAL_BASE_URL is treated as
|
||||
// misconfiguration and falls back to OPENAI_API_BASE, then
|
||||
// DEFAULT_MISTRAL_BASE_URL for a safe default endpoint.
|
||||
const fallbackEnvBaseUrl = isMistralMode
|
||||
? (primaryEnvBaseUrl === undefined
|
||||
? asNamedEnvUrl(process.env.OPENAI_API_BASE, 'OPENAI_API_BASE') ?? DEFAULT_MISTRAL_BASE_URL
|
||||
|
||||
@@ -70,7 +70,7 @@ describe('runAutoFixCheck', () => {
|
||||
|
||||
test('handles timeout gracefully', async () => {
|
||||
const result = await runAutoFixCheck({
|
||||
lint: 'sleep 10',
|
||||
lint: 'node -e "setTimeout(() => {}, 10000)"',
|
||||
timeout: 100,
|
||||
|
||||
cwd: '/tmp',
|
||||
|
||||
@@ -46,14 +46,31 @@ async function runCommand(
|
||||
|
||||
const killTree = () => {
|
||||
try {
|
||||
if (!isWindows && proc.pid) {
|
||||
if (isWindows && proc.pid) {
|
||||
// shell=true on Windows can leave child commands running unless we
|
||||
// terminate the full process tree.
|
||||
const killer = spawn('taskkill', ['/pid', String(proc.pid), '/T', '/F'], {
|
||||
windowsHide: true,
|
||||
stdio: 'ignore',
|
||||
})
|
||||
killer.unref()
|
||||
return
|
||||
}
|
||||
|
||||
if (proc.pid) {
|
||||
// Kill the entire process group
|
||||
process.kill(-proc.pid, 'SIGTERM')
|
||||
} else {
|
||||
proc.kill('SIGTERM')
|
||||
return
|
||||
}
|
||||
|
||||
proc.kill('SIGTERM')
|
||||
} catch {
|
||||
// Process may have already exited
|
||||
// Process may have already exited; fallback to direct child kill.
|
||||
try {
|
||||
proc.kill('SIGTERM')
|
||||
} catch {
|
||||
// Ignore final fallback errors.
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -26,10 +26,10 @@ test('initializeWiki creates the expected wiki scaffold', async () => {
|
||||
|
||||
expect(result.alreadyExisted).toBe(false)
|
||||
expect(result.createdFiles).toEqual([
|
||||
'.openclaude/wiki/schema.md',
|
||||
'.openclaude/wiki/index.md',
|
||||
'.openclaude/wiki/log.md',
|
||||
'.openclaude/wiki/pages/architecture.md',
|
||||
join('.openclaude', 'wiki', 'schema.md'),
|
||||
join('.openclaude', 'wiki', 'index.md'),
|
||||
join('.openclaude', 'wiki', 'log.md'),
|
||||
join('.openclaude', 'wiki', 'pages', 'architecture.md'),
|
||||
])
|
||||
expect(await readFile(paths.schemaFile, 'utf8')).toContain(
|
||||
'# OpenClaude Wiki Schema',
|
||||
|
||||
Reference in New Issue
Block a user