diff --git a/agent/agent_init.py b/agent/agent_init.py index e1e4c024edd..2f824c4bc6b 100644 --- a/agent/agent_init.py +++ b/agent/agent_init.py @@ -521,9 +521,8 @@ def init_agent( from hermes_cli.config import load_config as _load_pc_cfg _pc_cfg = _load_pc_cfg().get("prompt_caching", {}) or {} - if isinstance(_pc_cfg, dict) and _pc_cfg.get("enabled") is False: - agent._use_prompt_caching = False - agent._use_native_cache_layout = False + # prompt_caching.enabled=false is honored in _anthropic_prompt_cache_policy + # (applied above and on every re-derivation), so no override is needed here. _ttl = _pc_cfg.get("cache_ttl", "5m") if isinstance(_pc_cfg, dict) else "5m" if _ttl in {"5m", "1h"}: agent._cache_ttl = _ttl diff --git a/agent/agent_runtime_helpers.py b/agent/agent_runtime_helpers.py index 5560e4cd5c1..ced03c9f01f 100644 --- a/agent/agent_runtime_helpers.py +++ b/agent/agent_runtime_helpers.py @@ -1443,6 +1443,21 @@ def anthropic_prompt_cache_policy( eff_api_mode = api_mode if api_mode is not None else (agent.api_mode or "") eff_model = (model if model is not None else agent.model) or "" + # Global kill switch: prompt_caching.enabled=false disables cache_control + # markers on every path (init, /model switch, fallback re-derivation). + # Escape hatch for strict Anthropic-compatible proxies that inject their + # own markers server-side — stacking ours on top exceeds Anthropic's + # 4-breakpoint limit and 400s. Gating here (not just at init) keeps the + # switch honored after a model switch or fallback re-evaluates the policy. + try: + from hermes_cli.config import load_config as _load_pc_cfg + + _pc_cfg = _load_pc_cfg().get("prompt_caching", {}) or {} + if isinstance(_pc_cfg, dict) and _pc_cfg.get("enabled") is False: + return False, False + except Exception: + pass + model_lower = eff_model.lower() provider_lower = eff_provider.lower() is_claude = "claude" in model_lower diff --git a/scripts/release.py b/scripts/release.py index 625d329f277..7460271c0a7 100755 --- a/scripts/release.py +++ b/scripts/release.py @@ -45,6 +45,7 @@ ACP_REGISTRY_MANIFEST = REPO_ROOT / "acp_registry" / "agent.json" # Auto-extracted from noreply emails + manual overrides AUTHOR_MAP = { + "janrenz@Mac.fritz.box": "janrenz", # PR #35862 salvage (prompt_caching.enabled escape hatch for strict providers) "syahidfrd@gmail.com": "syahidfrd", # PR #17059 salvage (tag unverified senders in Slack thread context to mitigate indirect prompt injection) "5823452+sgabel@users.noreply.github.com": "sgabel", # PR #13139 salvage (redact secrets in user-facing approval prompts) "130270192+CRWuTJ@users.noreply.github.com": "CRWuTJ", # PR #17082 salvage (cancel delayed Telegram deliveries on disconnect so buffered flushes don't dispatch into a torn-down session) diff --git a/tests/run_agent/test_anthropic_prompt_cache_policy.py b/tests/run_agent/test_anthropic_prompt_cache_policy.py index ba6e54f0372..6a257e46aba 100644 --- a/tests/run_agent/test_anthropic_prompt_cache_policy.py +++ b/tests/run_agent/test_anthropic_prompt_cache_policy.py @@ -8,7 +8,7 @@ the native layout on OpenRouter) surfaces loudly. from __future__ import annotations -from unittest.mock import MagicMock +from unittest.mock import MagicMock, patch from run_agent import AIAgent @@ -326,7 +326,91 @@ class TestExplicitOverrides: assert (should, native) == (True, False) +# ───────────────────────────────────────────────────────────────────── +# prompt_caching.enabled=false global kill switch +# ───────────────────────────────────────────────────────────────────── + + +class TestPromptCachingDisabledKillSwitch: + """prompt_caching.enabled=false must disable cache_control markers on + every endpoint class and every re-derivation path (init, /model switch, + fallback). This is the correct escape hatch for a strict Anthropic- + compatible proxy that injects its own markers server-side — a single + per-setup toggle, not a blanket strip that would regress the many + well-behaved third-party gateways the policy deliberately caches on. + """ + + def _disabled_cfg(self): + return patch( + "hermes_cli.config.load_config", + return_value={"prompt_caching": {"enabled": False}}, + ) + + def test_disables_native_anthropic(self): + agent = _make_agent( + provider="anthropic", + base_url="https://api.anthropic.com", + api_mode="anthropic_messages", + model="claude-sonnet-4-6", + ) + with self._disabled_cfg(): + assert agent._anthropic_prompt_cache_policy() == (False, False) + + def test_disables_openrouter_claude(self): + agent = _make_agent( + provider="openrouter", + base_url="https://openrouter.ai/api/v1", + api_mode="chat_completions", + model="anthropic/claude-sonnet-4.6", + ) + with self._disabled_cfg(): + assert agent._anthropic_prompt_cache_policy() == (False, False) + + def test_disables_third_party_anthropic_gateway(self): + # llm.echo.tech-style LiteLLM proxy — the reported failure case. + agent = _make_agent( + provider="anthropic", + base_url="https://llm.echo.tech", + api_mode="anthropic_messages", + model="claude-sonnet-4-6", + ) + with self._disabled_cfg(): + assert agent._anthropic_prompt_cache_policy() == (False, False) + + def test_survives_model_switch_re_derivation(self): + # Start native Anthropic, /model switch to a proxy — disable must hold. + agent = _make_agent( + provider="anthropic", + base_url="https://api.anthropic.com", + api_mode="anthropic_messages", + model="claude-opus-4.6", + ) + with self._disabled_cfg(): + assert agent._anthropic_prompt_cache_policy( + provider="anthropic", + base_url="https://llm.echo.tech", + api_mode="anthropic_messages", + model="claude-sonnet-4-6", + ) == (False, False) + + def test_enabled_true_keeps_third_party_caching_on(self): + # The well-behaved third-party gateways a blanket strip would break + # must keep caching by default. + agent = _make_agent( + provider="anthropic", + base_url="https://llm.echo.tech", + api_mode="anthropic_messages", + model="claude-sonnet-4-6", + ) + with patch( + "hermes_cli.config.load_config", + return_value={"prompt_caching": {"enabled": True}}, + ): + assert agent._anthropic_prompt_cache_policy() == (True, True) + + # ───────────────────────────────────────────────────────────────────── # Long-lived prefix cache policy (cross-session 1h tier) # ───────────────────────────────────────────────────────────────────── + diff --git a/website/docs/developer-guide/context-compression-and-caching.md b/website/docs/developer-guide/context-compression-and-caching.md index 93240a486c0..e3cc855e5ac 100644 --- a/website/docs/developer-guide/context-compression-and-caching.md +++ b/website/docs/developer-guide/context-compression-and-caching.md @@ -362,6 +362,7 @@ Prompt caching is automatically enabled when: ```yaml # config.yaml — TTL is configurable (must be "5m" or "1h") prompt_caching: + enabled: true # set false to stop sending cache_control markers (strict-proxy escape hatch) cache_ttl: "5m" ``` diff --git a/website/docs/user-guide/configuration.md b/website/docs/user-guide/configuration.md index 0bcda2138a4..bcc77f25e73 100644 --- a/website/docs/user-guide/configuration.md +++ b/website/docs/user-guide/configuration.md @@ -915,17 +915,20 @@ For Claude on **native Anthropic**, **OpenRouter**, and **Nous Portal**, Hermes The Qwen Cloud (Alibaba DashScope) upstream caps cache TTL at 5 minutes, so Hermes uses the 5-minute breakpoint TTL there instead. Other Claude-via-third-party paths (AWS Bedrock, Azure Foundry) fall back to the provider's own caching defaults. xAI Grok uses a separate session-pinned conversation-id mechanism — see [xAI prompt caching](/integrations/providers#xai-grok--responses-api--prompt-caching). -No knob exists to disable this — caching is always-on and saves money even on single-turn conversations because the system prompt alone is a meaningful fraction of the input token count. +Caching is on by default and saves money even on single-turn conversations because the system prompt alone is a meaningful fraction of the input token count. It can be turned off entirely with the `enabled` knob below when a strict provider rejects `cache_control` markers. -The one explicit knob is the cache TTL tier Hermes requests on Anthropic-style breakpoints: +The explicit knobs are whether caching runs at all and the cache TTL tier Hermes requests on Anthropic-style breakpoints: ```yaml prompt_caching: + enabled: true # set false to stop sending cache_control markers entirely cache_ttl: "5m" # "5m" or "1h" (Anthropic-supported tiers); other values are ignored ``` `cache_ttl` selects the breakpoint TTL Hermes attaches for Claude via the native Anthropic API, OpenRouter, and Nous Portal. Only the two Anthropic-supported tiers (`"5m"`, `"1h"`) are honored — any other value is ignored. Providers with their own caps (e.g. Qwen Cloud, which maxes at 5 minutes) still clamp to what the upstream allows. +`enabled` defaults to `true`. Set it to `false` as an escape hatch for strict Anthropic-compatible proxies that inject their own `cache_control` markers server-side — stacking those on top of Hermes' breakpoints can exceed Anthropic's 4-breakpoint limit and return HTTP 400 `"A maximum of 4 blocks with cache_control may be provided"`. Disabling caching on that setup passes requests through without client-side markers so the proxy manages its own. + ## Auxiliary Models Hermes uses "auxiliary" models for side tasks like image analysis, web page summarization, browser screenshot analysis, session-title generation, and context compression. By default (`auxiliary.*.provider: "auto"`), Hermes routes every auxiliary task to your **main chat model** — the same provider/model you picked in `hermes model`. You don't need to configure anything to get started, but be aware that on expensive reasoning models (Opus, MiniMax M2.7, etc.) auxiliary tasks add meaningful cost. If you want cheap-and-fast side tasks regardless of your main model, set `auxiliary..provider` and `auxiliary..model` explicitly (for example, Gemini Flash on OpenRouter for vision and web extraction).