fix: shim reliability and protocol compliance overhaul

Addresses the most critical remaining issues in the provider shim layer,
building on top of #124 (recursive schema normalization + try/finally).

openaiShim.ts:
- Throw APIError via SDK factory instead of plain Error — enables retry
  on 429/503 (was completely broken: zero retries for all 3P providers)
- Guard stop_reason !== null before emitting usage-only message_delta
  (Azure/Groq send usage before finish_reason)
- Fix assistant content: join text parts instead of invalid as-string cast
  (Mistral rejects array content on assistant role)
- Expose real HTTP Response in withResponse() for header inspection
- Skip stream_options for local providers (Ollama < 0.5 compatibility)

codexShim.ts:
- Throw APIError at all 4 throw sites (HTTP + 3 streaming errors)
- Add tool_choice 'none' mapping (was silently ignored)
- Forward is_error flag with Error: prefix (matching openaiShim)

src/services/api/codexShim.ts

@@ -1,3 +1,4 @@
+import { APIError } from '@anthropic-ai/sdk'
 import type {
   ResolvedCodexCredentials,
   ResolvedProviderRequest,
@@ -234,7 +235,10 @@ export function convertAnthropicMessagesToResponsesInput(
           items.push({
             type: 'function_call_output',
             call_id: callId,
-            output: convertToolResultToText(toolResult.content),
+            output: (() => {
+              const out = convertToolResultToText(toolResult.content)
+              return toolResult.is_error ? `Error: ${out}` : out
+            })(),
           })
         }
 
@@ -453,6 +457,7 @@ function convertToolChoice(toolChoice: unknown): unknown {
   if (!choice?.type) return undefined
   if (choice.type === 'auto') return 'auto'
   if (choice.type === 'any') return 'required'
+  if (choice.type === 'none') return 'none'
   if (choice.type === 'tool' && choice.name) {
     return {
       type: 'function',
@@ -553,7 +558,13 @@ export async function performCodexRequest(options: {
 
   if (!response.ok) {
     const errorBody = await response.text().catch(() => 'unknown error')
-    throw new Error(`Codex API error ${response.status}: ${errorBody}`)
+    let errorResponse: object | undefined
+    try { errorResponse = JSON.parse(errorBody) } catch { /* raw text */ }
+    throw APIError.generate(
+      response.status, errorResponse,
+      `Codex API error ${response.status}: ${errorBody}`,
+      response.headers as unknown as Record<string, string>,
+    )
   }
 
   return response
@@ -633,11 +644,9 @@ export async function collectCodexCompletedResponse(
 
   for await (const event of readSseEvents(response)) {
     if (event.event === 'response.failed') {
-      throw new Error(
-        event.data?.response?.error?.message ??
-          event.data?.error?.message ??
-          'Codex response failed',
-      )
+      const msg = event.data?.response?.error?.message ??
+        event.data?.error?.message ?? 'Codex response failed'
+      throw APIError.generate(500, undefined, msg, {} as Record<string, string>)
     }
 
     if (
@@ -650,7 +659,10 @@ export async function collectCodexCompletedResponse(
   }
 
   if (!completedResponse) {
-    throw new Error('Codex response ended without a completed payload')
+    throw APIError.generate(
+      500, undefined, 'Codex response ended without a completed payload',
+      {} as Record<string, string>,
+    )
   }
 
   return completedResponse
@@ -806,11 +818,9 @@ export async function* codexStreamToAnthropic(
     }
 
     if (event.event === 'response.failed') {
-      throw new Error(
-        payload?.response?.error?.message ??
-          payload?.error?.message ??
-          'Codex response failed',
-      )
+      const msg = payload?.response?.error?.message ??
+        payload?.error?.message ?? 'Codex response failed'
+      throw APIError.generate(500, undefined, msg, {} as Record<string, string>)
     }
   }
 

src/services/api/openaiShim.ts

@@ -21,6 +21,7 @@
  *   OPENAI_MODEL                     — optional; use github:copilot or openai/gpt-4.1 style IDs
  */
 
+import { APIError } from '@anthropic-ai/sdk'
 import { isEnvTruthy } from '../../utils/envUtils.js'
 import { hydrateGithubModelsTokenFromSecureStorage } from '../../utils/githubModelsCredentials.js'
 import {
@@ -33,6 +34,7 @@ import {
   type ShimCreateParams,
 } from './codexShim.js'
 import {
+  isLocalProviderUrl,
   resolveCodexApiCredentials,
   resolveProviderRequest,
 } from './providerConfig.js'
@@ -213,7 +215,10 @@ function convertMessages(
 
         const assistantMsg: OpenAIMessage = {
           role: 'assistant',
-          content: convertContentBlocks(textContent) as string,
+          content: (() => {
+            const c = convertContentBlocks(textContent)
+            return typeof c === 'string' ? c : Array.isArray(c) ? c.map((p: { text?: string }) => p.text ?? '').join('') : ''
+          })(),
         }
 
         if (toolUses.length > 0) {
@@ -242,7 +247,10 @@ function convertMessages(
       } else {
         result.push({
           role: 'assistant',
-          content: convertContentBlocks(content) as string,
+          content: (() => {
+            const c = convertContentBlocks(content)
+            return typeof c === 'string' ? c : Array.isArray(c) ? c.map((p: { text?: string }) => p.text ?? '').join('') : ''
+          })(),
         })
       }
     }
@@ -617,7 +625,8 @@ async function* openaiStreamToAnthropic(
       if (
         !hasEmittedFinalUsage &&
         chunkUsage &&
-        (chunk.choices?.length ?? 0) === 0
+        (chunk.choices?.length ?? 0) === 0 &&
+        lastStopReason !== null
       ) {
         yield {
           type: 'message_delta',
@@ -666,9 +675,12 @@ class OpenAIShimMessages {
   ) {
     const self = this
 
+    let httpResponse: Response | undefined
+
     const promise = (async () => {
       const request = resolveProviderRequest({ model: params.model })
       const response = await self._doRequest(request, params, options)
+      httpResponse = response
 
       if (params.stream) {
         return new OpenAIShimStream(
@@ -695,8 +707,9 @@ class OpenAIShimMessages {
           const data = await promise
           return {
             data,
-            response: new Response(),
-            request_id: makeMessageId(),
+            response: httpResponse ?? new Response(),
+            request_id:
+              httpResponse?.headers.get('x-request-id') ?? makeMessageId(),
           }
         }
 
@@ -774,7 +787,7 @@ class OpenAIShimMessages {
       body.max_completion_tokens = maxCompletionTokensValue
     }
 
-    if (params.stream) {
+    if (params.stream && !isLocalProviderUrl(request.baseUrl)) {
       body.stream_options = { include_usage: true }
     }
 
@@ -890,12 +903,20 @@ class OpenAIShimMessages {
       const errorBody = await response.text().catch(() => 'unknown error')
       const rateHint =
         isGithub && response.status === 429 ? formatRetryAfterHint(response) : ''
-      throw new Error(
+      let errorResponse: object | undefined
+      try { errorResponse = JSON.parse(errorBody) } catch { /* raw text */ }
+      throw APIError.generate(
+        response.status,
+        errorResponse,
         `OpenAI API error ${response.status}: ${errorBody}${rateHint}`,
+        response.headers as unknown as Record<string, string>,
       )
     }
 
-    throw new Error('OpenAI shim: request loop exited unexpectedly')
+    throw APIError.generate(
+      500, undefined, 'OpenAI shim: request loop exited unexpectedly',
+      {} as Record<string, string>,
+    )
   }
 
   private _convertNonStreamingResponse(