fix(provider): honor NANOBOT_STREAM_IDLE_TIMEOUT_S in Codex provider

Every other streaming provider (anthropic, bedrock, openai_compat,
litellm) reads NANOBOT_STREAM_IDLE_TIMEOUT_S with a 90s default. The
Codex provider hardcoded 60s in _request_codex, so it could not be
tuned the same way and aborted streams sooner than its peers.

Read the same env var with the same default and pass it as the httpx
client timeout. The variable name and int parsing match anthropic /
openai_compat / bedrock verbatim.

#4009 normalized the error response when the timeout fires; this PR
fixes the timeout knob itself.

nanobot/providers/openai_codex_provider.py

@@ -5,6 +5,7 @@ from __future__ import annotations
 import asyncio
 import hashlib
 import json
+import os
 from collections.abc import Awaitable, Callable
 from typing import Any
 
@@ -177,7 +178,8 @@ async def _request_codex(
     on_content_delta: Callable[[str], Awaitable[None]] | None = None,
     on_tool_call_delta: Callable[[dict[str, Any]], Awaitable[None]] | None = None,
 ) -> tuple[str, list[ToolCallRequest], str]:
-    async with httpx.AsyncClient(timeout=60.0, verify=verify) as client:
+    idle_timeout_s = int(os.environ.get("NANOBOT_STREAM_IDLE_TIMEOUT_S", "90"))
+    async with httpx.AsyncClient(timeout=idle_timeout_s, verify=verify) as client:
         async with client.stream("POST", url, headers=headers, json=body) as response:
             if response.status_code != 200:
                 text = await response.aread()

tests/providers/test_openai_codex_provider.py

@@ -76,8 +76,8 @@ async def test_codex_request_non_200_populates_http_metadata(monkeypatch) -> Non
             request=request,
         )
 
-    def fake_client(*, timeout: float, verify: bool) -> httpx.AsyncClient:
+    def fake_client(*, timeout: int, verify: bool) -> httpx.AsyncClient:
-        assert timeout == 60.0
+        assert timeout == 90
         assert verify is True
         return original_client(transport=httpx.MockTransport(handler), timeout=timeout)
 
@@ -95,6 +95,27 @@ async def test_codex_request_non_200_populates_http_metadata(monkeypatch) -> Non
     assert error.should_retry is True
 
 
+@pytest.mark.asyncio
+async def test_codex_request_honors_stream_idle_timeout_env(monkeypatch) -> None:
+    """NANOBOT_STREAM_IDLE_TIMEOUT_S overrides the default Codex stream timeout."""
+    monkeypatch.setenv("NANOBOT_STREAM_IDLE_TIMEOUT_S", "5")
+    original_client = httpx.AsyncClient
+    seen: dict[str, int] = {}
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        return httpx.Response(200, request=request)
+
+    def fake_client(*, timeout: int, verify: bool) -> httpx.AsyncClient:
+        seen["timeout"] = timeout
+        return original_client(transport=httpx.MockTransport(handler), timeout=timeout)
+
+    monkeypatch.setattr("nanobot.providers.openai_codex_provider.httpx.AsyncClient", fake_client)
+
+    await _request_codex("https://codex.example/responses", {}, {"input": []}, verify=True)
+
+    assert seen["timeout"] == 5
+
+
 @pytest.mark.asyncio
 async def test_codex_prompt_cache_key_uses_stable_conversation_prefix(monkeypatch) -> None:
     bodies: list[dict] = []