diff --git a/CHANGELOG.md b/CHANGELOG.md
index b33e557a0b..b03cbad7a8 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -2,6 +2,8 @@
 
 - Agent Bridge: Consolidate bridged tools implementation into the existing sandbox model proxy service (eliminate Python requirement for using bridged tools).
 - Anthropic: Correctly replay reasoning when sourced from Inspect cache.
+- OpenAI Compatible: Don't ever send `background` parameter as this is OpenAI service-specific.
+- OpenAI Compatible: Added support for disabling reasoning history emulation.
 - Grok: Correctly replay tool calling errors in message history.
 - VLLM and SGLang: Don't require API key environment variable to be set when running in local mode.
 - Google: Support `minimal` and `medium` reasoning effort levels for Gemini 3 Flash.
@@ -13,7 +15,6 @@
 - Inspect View: Scale ANSI display in messages view to preserve row/column layout without wrapping.
 - Inspect View: Render custom tool view when viewing messages.
 - Bugfix: Prevent component not found error during Human Agent transition.
-- OpenAI Compatible: Added support for disabling reasoning history emulation.
 
 ## 0.3.159 (03 January 2026)
 
diff --git a/src/inspect_ai/model/_providers/openai_compatible.py b/src/inspect_ai/model/_providers/openai_compatible.py
index 821ad4c7f1..062beb71a5 100644
--- a/src/inspect_ai/model/_providers/openai_compatible.py
+++ b/src/inspect_ai/model/_providers/openai_compatible.py
@@ -161,7 +161,7 @@ async def generate(
                 tools=tools,
                 tool_choice=tool_choice,
                 config=config,
-                background=False,
+                background=None,
                 service_tier=None,
                 prompt_cache_key=NOT_GIVEN,
                 prompt_cache_retention=NOT_GIVEN,
diff --git a/src/inspect_ai/model/_providers/openai_responses.py b/src/inspect_ai/model/_providers/openai_responses.py
index f5fe3a8b37..6098011540 100644
--- a/src/inspect_ai/model/_providers/openai_responses.py
+++ b/src/inspect_ai/model/_providers/openai_responses.py
@@ -69,14 +69,14 @@ async def generate_responses(
     handle_bad_request: Callable[[APIStatusError], ModelOutput | Exception]
     | None = None,
 ) -> ModelOutput | tuple[ModelOutput | Exception, ModelCall]:
-    # batch mode and background are incompatible
-    if batcher:
-        background = False
-
     # background in extra_body should be applied
     if background is None and config.extra_body:
         background = config.extra_body.pop("background", None)
 
+    # batch mode and background are incompatible
+    if batcher:
+        background = None
+
     # allocate request_id (so we can see it from ModelCall)
     request_id = http_hooks.start_request()