diff --git a/packages/coding-agent/CHANGELOG.md b/packages/coding-agent/CHANGELOG.md
index 92726ebc..a8b4ea02 100644
--- a/packages/coding-agent/CHANGELOG.md
+++ b/packages/coding-agent/CHANGELOG.md
@@ -9,6 +9,7 @@
 
 ### Fixed
 
+- Fixed HTTP timeout setting not being respected for non-Codex providers (e.g., llama.cpp via OpenAI-compatible API). The `httpIdleTimeoutMs` setting (set via `/settings` HTTP timeout) now applies as the default SDK request timeout for all providers that support it, not just OpenAI Codex Responses. Disabling the timeout (HTTP timeout = false) now correctly disables SDK timeouts for all supported providers ([#5294](https://github.com/earendil-works/pi/issues/5294)).
 - Fixed opening and listing very large JSONL session files by reading session entries line-by-line instead of materializing the full file as one string ([#5231](https://github.com/earendil-works/pi/issues/5231)).
 
 ## [0.78.0] - 2026-05-29
diff --git a/packages/coding-agent/src/core/sdk.ts b/packages/coding-agent/src/core/sdk.ts
index a4401177..417e8a11 100644
--- a/packages/coding-agent/src/core/sdk.ts
+++ b/packages/coding-agent/src/core/sdk.ts
@@ -343,9 +343,7 @@ export async function createAgentSession(options: CreateAgentSessionOptions = {}
 			}
 			const providerRetrySettings = settingsManager.getProviderRetrySettings();
 			const timeoutMs =
-				options?.timeoutMs ??
-				providerRetrySettings.timeoutMs ??
-				(model.api === "openai-codex-responses" ? settingsManager.getHttpIdleTimeoutMs() : undefined);
+				options?.timeoutMs ?? providerRetrySettings.timeoutMs ?? settingsManager.getHttpIdleTimeoutMs();
 			const websocketConnectTimeoutMs =
 				options?.websocketConnectTimeoutMs ?? settingsManager.getWebSocketConnectTimeoutMs();
 			const attributionHeaders = getAttributionHeaders(model, settingsManager, options?.sessionId);