From e6184c1cc688b00efc7db1485d4427a19ec17ebe Mon Sep 17 00:00:00 2001
From: Jan Renz <janrenz@Mac.fritz.box>
Date: Sun, 31 May 2026 14:32:16 +0200
Subject: [PATCH] fix: allow disabling prompt caching

(cherry picked from commit c1c1a12fe61399acd696886efb441a3445f8b5e3)
---
 agent/agent_init.py               |  5 ++++-
 hermes_cli/config.py              |  5 ++++-
 tests/run_agent/test_run_agent.py | 24 ++++++++++++++++++++++++
 3 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/agent/agent_init.py b/agent/agent_init.py
index 5d65c4176e3..7546cb130ec 100644
--- a/agent/agent_init.py
+++ b/agent/agent_init.py
@@ -521,7 +521,10 @@ def init_agent(
         from hermes_cli.config import load_config as _load_pc_cfg
 
         _pc_cfg = _load_pc_cfg().get("prompt_caching", {}) or {}
-        _ttl = _pc_cfg.get("cache_ttl", "5m")
+        if isinstance(_pc_cfg, dict) and _pc_cfg.get("enabled") is False:
+            agent._use_prompt_caching = False
+            agent._use_native_cache_layout = False
+        _ttl = _pc_cfg.get("cache_ttl", "5m") if isinstance(_pc_cfg, dict) else "5m"
         if _ttl in {"5m", "1h"}:
             agent._cache_ttl = _ttl
     except Exception:
diff --git a/hermes_cli/config.py b/hermes_cli/config.py
index 050f1975db9..115096fda2c 100644
--- a/hermes_cli/config.py
+++ b/hermes_cli/config.py
@@ -1410,8 +1410,11 @@ DEFAULT_CONFIG = {
     },
 
     # Anthropic prompt caching (Claude via OpenRouter or native Anthropic API).
-    # cache_ttl must be "5m" or "1h" (Anthropic-supported tiers); other values are ignored.
+    # Set enabled: false as an escape hatch for strict providers that reject
+    # cache_control markers; cache_ttl must be "5m" or "1h" (Anthropic-supported
+    # tiers), other values are ignored.
     "prompt_caching": {
+        "enabled": True,
         "cache_ttl": "5m",
     },
 
diff --git a/tests/run_agent/test_run_agent.py b/tests/run_agent/test_run_agent.py
index da8a446bf8d..69b02c9cd61 100644
--- a/tests/run_agent/test_run_agent.py
+++ b/tests/run_agent/test_run_agent.py
@@ -1026,6 +1026,30 @@ class TestInit:
             )
             assert a._cache_ttl == "5m"
 
+    def test_prompt_caching_enabled_false_disables_cache_markers(self):
+        """prompt_caching.enabled=false is an escape hatch for strict providers."""
+        with (
+            patch("run_agent.get_tool_definitions", return_value=[]),
+            patch("run_agent.check_toolset_requirements", return_value={}),
+            patch("agent.anthropic_adapter._anthropic_sdk"),
+            patch(
+                "hermes_cli.config.load_config",
+                return_value={"prompt_caching": {"enabled": False}},
+            ),
+        ):
+            a = AIAgent(
+                api_key="test-key-1234567890",
+                provider="anthropic",
+                model="claude-sonnet-4-6",
+                base_url="https://api.anthropic.com/v1/",
+                quiet_mode=True,
+                skip_context_files=True,
+                skip_memory=True,
+            )
+            assert a.api_mode == "anthropic_messages"
+            assert a._use_prompt_caching is False
+            assert a._use_native_cache_layout is False
+
     def test_valid_tool_names_populated(self):
         """valid_tool_names should contain names from loaded tools."""
         tools = _make_tool_defs("web_search", "terminal")