From 8ce09ae7436053cc4f632d1a797ba503c3ee0fa3 Mon Sep 17 00:00:00 2001
From: KRATOS <84986124+gnanam1990@users.noreply.github.com>
Date: Fri, 3 Apr 2026 20:23:14 +0530
Subject: [PATCH] fix: disable cache_control injection for third-party
 providers (#276)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

getPromptCachingEnabled() returned true for all providers including
Azure Foundry, OpenAI, Gemini, and GitHub. This caused cache_control
blocks to be injected into every request sent to 3P endpoints.

Azure Foundry's strict Responsible AI content filter treats unexpected
Anthropic-specific fields (cache_control: { type: "ephemeral" }) as
a jailbreak signal and rejects the request with a 400 error — even
for a simple prompt like "hi".

Fix: return false early when provider is not firstParty, bedrock, or
vertex — the only providers that understand and support prompt caching.

Fixes #273
Related: #267 (Finding 1)

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 src/services/api/claude.ts | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/src/services/api/claude.ts b/src/services/api/claude.ts
index b5e55c37..32416683 100644
--- a/src/services/api/claude.ts
+++ b/src/services/api/claude.ts
@@ -331,6 +331,14 @@ export function getExtraBodyParams(betaHeaders?: string[]): JsonObject {
 }
 
 export function getPromptCachingEnabled(model: string): boolean {
+  // Prompt caching is an Anthropic-specific feature. Third-party providers
+  // do not understand cache_control blocks and strict backends (e.g. Azure
+  // Foundry) reject or flag requests that contain them.
+  const provider = getAPIProvider()
+  if (provider !== 'firstParty' && provider !== 'bedrock' && provider !== 'vertex') {
+    return false
+  }
+
   // Global disable takes precedence
   if (isEnvTruthy(process.env.DISABLE_PROMPT_CACHING)) return false