Fix codex mcp default model

packages/server/src/server/agent/providers/codex-mcp-agent.test.ts

@@ -504,7 +504,7 @@ describe("CodexMcpAgentClient (MCP integration)", () => {
         provider: "codex-mcp",
         cwd,
         modeId: "full-access",
-        model: "gpt-4.1",
+        model: "gpt-5.1-codex",
       } as AgentSessionConfig;
 
       let session: AgentSession | null = null;

packages/server/src/server/agent/providers/codex-mcp-agent.ts

@@ -87,6 +87,7 @@ const CODEX_MODES: AgentMode[] = [
 ];
 
 const DEFAULT_CODEX_MODE_ID = "auto";
+const DEFAULT_CODEX_MODEL_ID = "gpt-5.1-codex";
 
 const MODE_PRESETS: Record<
   string,
@@ -221,7 +222,7 @@ function buildCodexMcpConfig(
   return {
     prompt,
     cwd: config.cwd,
-    model: config.model,
+    model: config.model ?? DEFAULT_CODEX_MODEL_ID,
     "approval-policy": approvalPolicy,
     sandbox,
     config: extra,
@@ -716,7 +717,7 @@ class CodexMcpAgentSession implements AgentSession {
 
     this.updateIdentifiersFromResponse(response);
     if (this.modelRejected && !this.runtimeModel) {
-      this.runtimeModel = "default";
+      this.runtimeModel = DEFAULT_CODEX_MODEL_ID;
     }
 
     if (!turnState.sawAssistant) {

plan.md

@@ -59,11 +59,19 @@ Build a new Codex MCP provider side‑by‑side with the existing Codex SDK prov
   - The reference supports permissions - copy the working approach.
   - **Done (2025-12-24 18:53)**: Matched happy-cli elicitation flow by avoiding duplicate permission requests when exec events pre-seed pending entries and aligned permission tool naming with CodexBash.
 
-- [ ] **Fix**: Use valid model instead of gpt-4.1.
+- [ ] **Fix**: Test `approval-policy=untrusted` instead of `on-request`.
+
+  - Happy CLI uses `"untrusted"` for default mode, voice-dev uses `"on-request"`.
+  - `"on-request"` may not trigger MCP elicitation.
+  - Change MODE_PRESETS["auto"] to use `"untrusted"` and test if real elicitation works.
+  - If it works, remove the synthetic permission gating workaround.
+
+- [x] **Fix**: Use valid model instead of gpt-4.1.
 
   - gpt-4.1 does not exist and is rejected by Codex CLI.
   - Check what models are actually available (run `codex --help` or check docs).
   - Update tests and provider to use a valid default model.
+  - **Done (2025-12-24 18:58)**: Updated Codex MCP default model to gpt-5.1-codex and switched runtime info test to use the valid model id.
 
 - [ ] **Fix**: Resolve typecheck errors in `codex-mcp-agent.ts`.