mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-18 04:41:56 +00:00
7b76366552
Cuts input cost for first-turn Claude requests by ~85-90% on subsequent
sessions within an hour. Tools array (~13k tokens for default toolset) +
stable system prefix (~5-8k tokens) get a 1h cache_control marker; the
volatile suffix (memory, USER profile, timestamp, session id) sits in a
separate non-cached block at the end so it doesn't poison the cross-session
prefix when it changes.
Provider gate: Claude on native Anthropic (incl. OAuth subscription),
OpenRouter, and Nous Portal (which proxies to OpenRouter). All other
providers keep today's system_and_3 layout unchanged.
Layout (4 cache_control breakpoints, Anthropic max):
1. tools[-1] -> 1h (cross-session)
2. system content[0] -> 1h (cross-session, stable prefix)
3. messages[-2] -> 5m (within-session rolling)
4. messages[-1] -> 5m (within-session rolling)
Within-session rolling shrinks from 3 messages to 2 to free the breakpoint
budget. On Claude with realistic tool loadouts the long-lived tier carries
the bulk of cross-session value anyway.
System prompt is now always assembled cache-friendly: stable identity /
guidance / skills / platform hints first, then session-stable context
files (AGENTS.md, .cursorrules), then per-call volatile content. Old
single-string callers see the same logical content (same join order),
just reordered so volatile lives at the end.
Config knobs (defaults shown):
prompt_caching:
cache_ttl: "5m" # rolling-window TTL (unchanged)
long_lived_prefix: true # opt-out switch
long_lived_ttl: "1h" # cross-session prefix TTL
Live E2E (tests/agent/test_prompt_caching_live.py, gated on
OPENROUTER_API_KEY) on anthropic/claude-haiku-4.5 with default toolset:
Call 1 (cold): cache_write=13,415 cache_read=0
Call 2 (NEW agent + msg): cache_write=391 cache_read=13,025
Cross-session reuse: 97.09%
Implementation:
* agent/prompt_caching.py: new apply_anthropic_cache_control_long_lived()
+ mark_tools_for_long_lived_cache(); existing apply_anthropic_cache_control()
preserved verbatim for the fallback path.
* agent/anthropic_adapter.py: convert_tools_to_anthropic() now forwards
cache_control onto each Anthropic-format tool dict.
* run_agent.py: _build_system_prompt_parts() returns the 3-tier dict;
_build_system_prompt() joins them (backward compatible).
_supports_long_lived_anthropic_cache() policy added next to the existing
_anthropic_prompt_cache_policy() (which now also recognises Nous Portal
Claude — pre-existing gap fixed in passing).
_build_api_kwargs() resolves tools_for_api once and propagates the
marker through all four build paths (anthropic_messages, bedrock,
codex_responses, profile/legacy chat completions).
Long-lived flag plumbed into the runtime snapshot/restore + model-switch
+ fallback-promotion paths.
Tests:
* tests/agent/test_prompt_caching.py: +8 tests (TestMarkToolsForLongLivedCache,
TestApplyAnthropicCacheControlLongLived).
* tests/run_agent/test_anthropic_prompt_cache_policy.py: +9 tests
(TestSupportsLongLivedAnthropicCache matrix across 8 endpoint classes
+ a fallback-target case).
* tests/agent/test_prompt_caching_live.py: new live E2E (skipif when
OPENROUTER_API_KEY is unset; runs outside the hermetic suite).
* Targeted suites: 327/327 pass (caching/adapter/policy/builder).
* tests/agent/ + tests/run_agent/: 3992 pass, 17 skip, 1 pre-existing
flake (test_async_httpx_del_neuter::test_same_key_replaces_stale_loop_entry,
verified failing on pristine origin/main).
|
||
|---|---|---|
| .. | ||
| transports | ||
| __init__.py | ||
| account_usage.py | ||
| anthropic_adapter.py | ||
| auxiliary_client.py | ||
| bedrock_adapter.py | ||
| codex_responses_adapter.py | ||
| context_compressor.py | ||
| context_engine.py | ||
| context_references.py | ||
| copilot_acp_client.py | ||
| credential_pool.py | ||
| credential_sources.py | ||
| curator.py | ||
| curator_backup.py | ||
| display.py | ||
| error_classifier.py | ||
| file_safety.py | ||
| gemini_cloudcode_adapter.py | ||
| gemini_native_adapter.py | ||
| gemini_schema.py | ||
| google_code_assist.py | ||
| google_oauth.py | ||
| i18n.py | ||
| image_gen_provider.py | ||
| image_gen_registry.py | ||
| image_routing.py | ||
| insights.py | ||
| lmstudio_reasoning.py | ||
| manual_compression_feedback.py | ||
| markdown_tables.py | ||
| memory_manager.py | ||
| memory_provider.py | ||
| model_metadata.py | ||
| models_dev.py | ||
| moonshot_schema.py | ||
| nous_rate_guard.py | ||
| onboarding.py | ||
| plugin_llm.py | ||
| prompt_builder.py | ||
| prompt_caching.py | ||
| rate_limit_tracker.py | ||
| redact.py | ||
| retry_utils.py | ||
| shell_hooks.py | ||
| skill_commands.py | ||
| skill_preprocessing.py | ||
| skill_utils.py | ||
| subdirectory_hints.py | ||
| think_scrubber.py | ||
| title_generator.py | ||
| tool_guardrails.py | ||
| trajectory.py | ||
| usage_pricing.py | ||